This work proposes the application of an iterative learning model predictive control(ILMPC)approach based on an adaptive fault observer(FOBILMPC)for fault-tolerant control and trajectory tracking in air-breathing hype...This work proposes the application of an iterative learning model predictive control(ILMPC)approach based on an adaptive fault observer(FOBILMPC)for fault-tolerant control and trajectory tracking in air-breathing hypersonic vehicles.In order to increase the control amount,this online control legislation makes use of model predictive control(MPC)that is based on the concept of iterative learning control(ILC).By using offline data to decrease the linearized model’s faults,the strategy may effectively increase the robustness of the control system and guarantee that disturbances can be suppressed.An adaptive fault observer is created based on the suggested ILMPC approach in order to enhance overall fault tolerance by estimating and compensating for actuator disturbance and fault degree.During the derivation process,a linearized model of longitudinal dynamics is established.The suggested ILMPC approach is likely to be used in the design of hypersonic vehicle control systems since numerical simulations have demonstrated that it can decrease tracking error and speed up convergence when compared to the offline controller.展开更多
This paper presents a Nonlinear Model Predictive Controller(NMPC)for the path following of autonomous vehicles and an algorithm to adaptively adjust the preview distance.The prediction model includes vehicle dynamics,...This paper presents a Nonlinear Model Predictive Controller(NMPC)for the path following of autonomous vehicles and an algorithm to adaptively adjust the preview distance.The prediction model includes vehicle dynamics,path following dynamics,and system input dynamics.The single-track vehicle model considers the vehicle’s coupled lateral and longitudinal dynamics,as well as nonlinear tire forces.The tracking error dynamics are derived based on the curvilinear coordinates.The cost function is designed to minimize path tracking errors and control effort while considering constraints such as actuator bounds and tire grip limits.An algorithm that utilizes the optimal preview distance vector to query the corresponding reference curvature and reference speed.The length of the preview path is adaptively adjusted based on the vehicle speed,heading error,and path curvature.We validate the controller performance in a simulation environment with the autonomous racing scenario.The simulation results show that the vehicle accurately follows the highly dynamic path with small tracking errors.The maximum preview distance can be prior estimated and guidance the selection of the prediction horizon for NMPC.展开更多
Compared with traditional feedback control,predictive control can eliminate the lag of pose control and avoid the snakelike motion of shield machines.Therefore,a shield pose prediction model was proposed based on dyna...Compared with traditional feedback control,predictive control can eliminate the lag of pose control and avoid the snakelike motion of shield machines.Therefore,a shield pose prediction model was proposed based on dynamic modeling.Firstly,the dynamic equations of shield thrust system were established to clarify the relationship between force and movement of shield machine.Secondly,an analytical model was proposed to predict future multistep pose of the shield machine.Finally,a virtual prototype model was developed to simulate the dynamic behavior of the shield machine and validate the accuracy of the proposed pose prediction method.Results reveal that the model proposed can predict the shield pose with high accuracy,which can provide a decision basis whether for manual or automatic control of shield pose.展开更多
This study presents a machine learning-based method for predicting fragment velocity distribution in warhead fragmentation under explosive loading condition.The fragment resultant velocities are correlated with key de...This study presents a machine learning-based method for predicting fragment velocity distribution in warhead fragmentation under explosive loading condition.The fragment resultant velocities are correlated with key design parameters including casing dimensions and detonation positions.The paper details the finite element analysis for fragmentation,the characterizations of the dynamic hardening and fracture models,the generation of comprehensive datasets,and the training of the ANN model.The results show the influence of casing dimensions on fragment velocity distributions,with the tendencies indicating increased resultant velocity with reduced thickness,increased length and diameter.The model's predictive capability is demonstrated through the accurate predictions for both training and testing datasets,showing its potential for the real-time prediction of fragmentation performance.展开更多
As a significant inducement during the development of oil and gas,the role of remaining recoverable reserves is more observable especially in the later phase of development of oilfield.Depended on the production decli...As a significant inducement during the development of oil and gas,the role of remaining recoverable reserves is more observable especially in the later phase of development of oilfield.Depended on the production decline method in petroleum reservoir engineering,a new model of predicting recoverable and remaining recoverable reserves has been展开更多
In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel...In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel cells(PEMFC).Firstly,the Shapley additive explanations(SHAP)value method is used to select external characteristic parameters with high contributions as inputs for the data-driven approach.Next,a novel swarm optimization algorithm,the enhanced search ant colony optimization,is proposed.This algorithm improves the ant colony optimization(ACO)algorithm based on a reinforcement factor to avoid premature convergence and accelerate the convergence speed.Comparative experiments are set up to compare the performance differences between particle swarm optimization(PSO),ACO,and ENSACO.Finally,a data-driven method based on ENSACO-LSTM is proposed to predict the power degradation trend of PEMFCs.And actual aging data is used to validate the method.The results show that,within a limited number of iterations,the optimization capability of ENSACO is significantly stronger than that of PSO and ACO.Additionally,the prediction accuracy of the ENSACO-LSTM method is greatly improved,with an average increase of approximately 50.58%compared to LSTM,PSO-LSTM,and ACO-LSTM.展开更多
This paper proposes a modification of the Forrestal-Warren perforation model aimed at extending its applicability range to intermediately-thick high-hardness armor steel plates.When impacted by armorpiercing projectil...This paper proposes a modification of the Forrestal-Warren perforation model aimed at extending its applicability range to intermediately-thick high-hardness armor steel plates.When impacted by armorpiercing projectiles,these plates tend to fail through adiabatic shear plugging which significantly reduces their ballistic resistance.To address this effect,an approach for determining effective thickness was defined and incorporated into the predictive model.Ballistic impact tests were performed to assess the modification's validity,in which ARMOX 500T steel plates were subjected to perpendicular impacts from 7.62×39 mm steel-cored rounds under various velocities.Frequent target failure by soft plugging was observed,as well as the brittle shatter of the hard steel core.Key properties of the recovered plugs including their mass,length and diameter were measured and reported along with the projectiles'residual velocities.Additionally,independent data from the open literature were included in the analysis for further validation.The original Forrestal-Warren model and the novel effective thickness modification were then used to establish the relationship between impact and residual velocities,as well as to determine the ballistic limit velocity.The comparison revealed that the proposed approach significantly improves the model's accuracy,showing a strong correlation with experimental data and reducing deviations to within a few percent.This enhancement highlights the potential of the effective thickness term,which could also be applied to other predictive models to extend their applicability range.Further exploration into other armor steels and impact conditions is recommended to assess the method's versatility.展开更多
[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
In grey system theory,the studies in the field of grey prediction model are focused on real number sequences,rather than grey number ones.Hereby,a prediction model based on interval grey number sequences is proposed.B...In grey system theory,the studies in the field of grey prediction model are focused on real number sequences,rather than grey number ones.Hereby,a prediction model based on interval grey number sequences is proposed.By mining the geometric features of interval grey number sequences on a two-dimensional surface,all the interval grey numbers are converted into real numbers by means of certain algorithm,and then the prediction model is established based on those real number sequences.The entire process avoids the algebraic operations of grey number,and the prediction problem of interval grey number is usefully solved.Ultimately,through an example＇s program simulation,the validity and practicability of this novel model are verified.展开更多
A constrained generalized predictive control （GPC） algorithm based on the T-S fuzzy model is presented for the nonlinear system. First, a Takagi-Sugeno （T-S） fuzzy model based on the fuzzy cluster algorithm and th...A constrained generalized predictive control （GPC） algorithm based on the T-S fuzzy model is presented for the nonlinear system. First, a Takagi-Sugeno （T-S） fuzzy model based on the fuzzy cluster algorithm and the orthogonalleast square method is constructed to approach the nonlinear system. Since its consequence is linear, it can divide the nonlinear system into a number of linear or nearly linear subsystems. For this T-S fuzzy model, a GPC algorithm with input constraints is presented. This strategy takes into account all the constraints of the control signal and its increment, and does not require the calculation of the Diophantine equations. So it needs only a small computer memory and the computational speed is high. The simulation results show a good performance for the nonlinear systems.展开更多
In order to deeply research the structure discrepancy and modeling mechanism among different grey prediction models, the equivalence and unbiasedness of grey prediction models are analyzed and verified. The results sh...In order to deeply research the structure discrepancy and modeling mechanism among different grey prediction models, the equivalence and unbiasedness of grey prediction models are analyzed and verified. The results show that all the grey prediction models that are strictly derived from x^（0）（k） ＋az^（1）（k） = b have the identical model structure and simulation precision. Moreover, the unbiased simulation for the homogeneous exponential sequence can be accomplished. However, the models derived from dx^（1）/dt ＋ ax^（1）= b are only close to those derived from x^（0）（k） ＋ az^（1）（k） = b provided that ｜a｜ has to satisfy｜a｜ 0.1; neither could the unbiased simulation for the homogeneous exponential sequence be achieved. The above conclusions are proved and verified through some theorems and examples.展开更多
The accuracy of present flatness predictive method is limited and it just belongs to software simulation. In order to improve it, a novel flatness predictive model via T-S cloud reasoning network implemented by digita...The accuracy of present flatness predictive method is limited and it just belongs to software simulation. In order to improve it, a novel flatness predictive model via T-S cloud reasoning network implemented by digital signal processor(DSP) is proposed. First, the combination of genetic algorithm(GA) and simulated annealing algorithm(SAA) is put forward, called GA-SA algorithm, which can make full use of the global search ability of GA and local search ability of SA. Later, based on T-S cloud reasoning neural network, flatness predictive model is designed in DSP. And it is applied to 900 HC reversible cold rolling mill. Experimental results demonstrate that the flatness predictive model via T-S cloud reasoning network can run on the hardware DSP TMS320 F2812 with high accuracy and robustness by using GA-SA algorithm to optimize the model parameter.展开更多
This work is concerned with identification and nonlinear predictive control method for MIMO Hammerstein systems with constraints. Firstly, an identification method based on steady-state responses and sub-model method ...This work is concerned with identification and nonlinear predictive control method for MIMO Hammerstein systems with constraints. Firstly, an identification method based on steady-state responses and sub-model method is introduced to MIMO Hammerstein system. A modified version of artificial bee colony algorithm is proposed to improve the prediction ability of Hammerstein model. Next, a computationally efficient nonlinear model predictive control algorithm(MGPC) is developed to deal with constrained problem of MIMO system. The identification process and performance of MGPC are shown. Numerical results about a polymerization reactor validate the effectiveness of the proposed method and the comparisons show that MGPC has a better performance than QDMC and basic GPC.展开更多
Pre-knowledge of machined surface roughness is the key to improve whole machining efficiency and meanwhile reduce the expenditure in machining optical glass components.In order to predict the surface roughness in ultr...Pre-knowledge of machined surface roughness is the key to improve whole machining efficiency and meanwhile reduce the expenditure in machining optical glass components.In order to predict the surface roughness in ultrasonic vibration assisted grinding of brittle materials,the surface morphologies of grinding wheel were obtained firstly in the present work,the grinding wheel model was developed and the abrasive trajectories in ultrasonic vibration assisted grinding were also investigated,the theoretical model for surface roughness was developed based on the above analysis.The prediction model was developed by using Gaussian processing regression(GPR)due to the influence of brittle fracture on machined surface roughness.In order to validate both the proposed theoretical and GPR models,32sets of experiments of ultrasonic vibration assisted grinding of BK7optical glass were carried out.Experimental results show that the average relative errors of the theoretical model and GPR prediction model are13.11%and8.12%,respectively.The GPR prediction results can match well with the experimental results.展开更多
Based on the idea of fusing modeling, an integrated prediction model for sintering process was proposed. A framework for sulfur content prediction was established, which integrated multi modeling ways together, includ...Based on the idea of fusing modeling, an integrated prediction model for sintering process was proposed. A framework for sulfur content prediction was established, which integrated multi modeling ways together, including mathematical model combined with neural network(NN), rule model based on empirical knowledge and model-choosing coordinator. Via metallurgic mechanism analysis and material balance computation, a mathematical model calculated the sulfur content in agglomerate by the material balance equation with some parameters predicted by NN method. In the other model, the relationship between sulfur content and key factors was described in the form of expert rules. The model-choosing coordinator based on fuzzy logic was introduced to decide the weight of result of each model according to process conditions. The model was tested by industrial application data and produced a relatively satisfactory prediction error. The model also preferably reflected the varying tendency of sulfur content in agglomerate as the evidence of its prediction performance.展开更多
Electronic warfare is a modern combat mode,in which predicting digital material consumption is a key for material requirements planning(MRP).In this paper,we introduce an insensitive loss function(ε) and propose a ε...Electronic warfare is a modern combat mode,in which predicting digital material consumption is a key for material requirements planning(MRP).In this paper,we introduce an insensitive loss function(ε) and propose a ε-SVR-based prediction approach.First,we quantify values of influencing factors of digital equipments in electronic warfare and a small-sample data on real consumption to form a real combat data set,and preprocess it to construct the sample space.Subsequently,we establish the ε-SVR-based prediction model based on "wartime influencing factors-material consumption" and perform model training.In case study,we give 8 historical battle events with battle damage data and predict 3 representative kinds of digital materials by using the proposed approach.The results illustrate its higher accuracy and more convenience compared with other current approaches.Taking data acquisition controller prediction as an example,our model has better prediction performance(RMSE=0.575 7,MAPE(%)=12.037 6 and R^2=0.996 0) compared with BP neural network model(RMSE=1.272 9,MAPE(%)=23.577 5 and R^2=0.980 3) and GM(1,1) model(RMSE=2.095 0,MAPE(%)=24.188 0 and R^2=0.946 6).The fact shows that the approach can be used to support decision-making for MRP in electronic warfare.展开更多
The rapid increase of the scale and the complexity of the controlled plants bring new challenges such as computing power and storage for conventional control systems.Cloud computing is concerned as a powerful solution...The rapid increase of the scale and the complexity of the controlled plants bring new challenges such as computing power and storage for conventional control systems.Cloud computing is concerned as a powerful solution to handle complex large-scale control missions by using sufficient computing resources.However,the computing ability enables more complex devices and more data to be involved and most of the data have not been fully utilized.Meanwhile,it is even impossible to obtain an accurate model of each device in the complex control systems for the model-based control algorithms.Therefore,motivated by the above reasons,we propose a data-driven predictive cloud control system.To achieve the proposed system,a practical data-driven predictive cloud control testbed is established and together a cloud-edge communication scheme is developed.Finally,the simulations and experiments demonstrate the effectiveness of the proposed system.展开更多
The mechanical system with backlash is distinguished between a＂backlash mode＂and a＂contact mode＂.The inherent switching between the two operating modes makes the system a prime example of hybrid system.For elimina...The mechanical system with backlash is distinguished between a＂backlash mode＂and a＂contact mode＂.The inherent switching between the two operating modes makes the system a prime example of hybrid system.For eliminating the bad effect of backlash, a piecewise affine（PWA） model of the mechanical servo system with backlash is built.The optimal control of constrained PWA system is obtained by taking advantage of model predictive control（MPC） method, and the explicit solution of MPC in a look-up table form is figured out by combining the dynamic programming and multi-parametric quadratic programming, thereby establishing an explicit hybrid model predictive controller.Furthermore, a piecewise quadratic（PWQ） function for guaranteeing the stability of closed-loop control is found by formulating the search of PWQ function as a semi-definite programming problem.In the tracking experiments, it is demonstrated that the explicit hybrid model predictive controller has a good traction control effect on the mechanical system with backlash.The error meets the demands of real system.Further, compared to the direct on-line computation, the computation burden is reduced by the explicit solution, thereby being suitable for real-time control of system with short sampling time.展开更多
For a class of linear discrete-time systems that is subject to randomly occurred networked packet loss in industrial cyber physical systems, a novel robust model predictive control method with active compensation mech...For a class of linear discrete-time systems that is subject to randomly occurred networked packet loss in industrial cyber physical systems, a novel robust model predictive control method with active compensation mechanism was proposed. The probability distribution of packet loss is described as the Bernoulli distributed white sequences. By using the Lyapunov stability theory, the existing sufficient conditions of the controller are derived from solving a group of linear matrix inequalities. Moreover, dropout-rate with uncertainty and unknown dropout-rate are also considered, which can greatly reduce the conservativeness of the controller. The designed robust model predictive control method not only efficiently eliminates the negative effects of the networked data loss in industrial cyber physical systems but also ensures the stability of closed-loop system. Two examples were provided to illustrate the superiority and effectiveness of the proposed method.展开更多
基金supported by the National Natural Science Foundation of China(12072090).
文摘This work proposes the application of an iterative learning model predictive control(ILMPC)approach based on an adaptive fault observer(FOBILMPC)for fault-tolerant control and trajectory tracking in air-breathing hypersonic vehicles.In order to increase the control amount,this online control legislation makes use of model predictive control(MPC)that is based on the concept of iterative learning control(ILC).By using offline data to decrease the linearized model’s faults,the strategy may effectively increase the robustness of the control system and guarantee that disturbances can be suppressed.An adaptive fault observer is created based on the suggested ILMPC approach in order to enhance overall fault tolerance by estimating and compensating for actuator disturbance and fault degree.During the derivation process,a linearized model of longitudinal dynamics is established.The suggested ILMPC approach is likely to be used in the design of hypersonic vehicle control systems since numerical simulations have demonstrated that it can decrease tracking error and speed up convergence when compared to the offline controller.
基金“National Science and Technology Council”(NSTC 111-2221-E-027-088)。
文摘This paper presents a Nonlinear Model Predictive Controller(NMPC)for the path following of autonomous vehicles and an algorithm to adaptively adjust the preview distance.The prediction model includes vehicle dynamics,path following dynamics,and system input dynamics.The single-track vehicle model considers the vehicle’s coupled lateral and longitudinal dynamics,as well as nonlinear tire forces.The tracking error dynamics are derived based on the curvilinear coordinates.The cost function is designed to minimize path tracking errors and control effort while considering constraints such as actuator bounds and tire grip limits.An algorithm that utilizes the optimal preview distance vector to query the corresponding reference curvature and reference speed.The length of the preview path is adaptively adjusted based on the vehicle speed,heading error,and path curvature.We validate the controller performance in a simulation environment with the autonomous racing scenario.The simulation results show that the vehicle accurately follows the highly dynamic path with small tracking errors.The maximum preview distance can be prior estimated and guidance the selection of the prediction horizon for NMPC.
基金Project(2023JBZY030)supported by the Fundamental Research Funds for the Central Universities,ChinaProject(U1834208)supported by the National Natural Science Foundation of China。
文摘Compared with traditional feedback control,predictive control can eliminate the lag of pose control and avoid the snakelike motion of shield machines.Therefore,a shield pose prediction model was proposed based on dynamic modeling.Firstly,the dynamic equations of shield thrust system were established to clarify the relationship between force and movement of shield machine.Secondly,an analytical model was proposed to predict future multistep pose of the shield machine.Finally,a virtual prototype model was developed to simulate the dynamic behavior of the shield machine and validate the accuracy of the proposed pose prediction method.Results reveal that the model proposed can predict the shield pose with high accuracy,which can provide a decision basis whether for manual or automatic control of shield pose.
基金supported by Poongsan-KAIST Future Research Center Projectthe fund support provided by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(Grant No.2023R1A2C2005661)。
文摘This study presents a machine learning-based method for predicting fragment velocity distribution in warhead fragmentation under explosive loading condition.The fragment resultant velocities are correlated with key design parameters including casing dimensions and detonation positions.The paper details the finite element analysis for fragmentation,the characterizations of the dynamic hardening and fracture models,the generation of comprehensive datasets,and the training of the ANN model.The results show the influence of casing dimensions on fragment velocity distributions,with the tendencies indicating increased resultant velocity with reduced thickness,increased length and diameter.The model's predictive capability is demonstrated through the accurate predictions for both training and testing datasets,showing its potential for the real-time prediction of fragmentation performance.
文摘As a significant inducement during the development of oil and gas,the role of remaining recoverable reserves is more observable especially in the later phase of development of oilfield.Depended on the production decline method in petroleum reservoir engineering,a new model of predicting recoverable and remaining recoverable reserves has been
基金Supported by the Major Science and Technology Project of Jilin Province(20220301010GX)the International Scientific and Technological Cooperation(20240402071GH).
文摘In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel cells(PEMFC).Firstly,the Shapley additive explanations(SHAP)value method is used to select external characteristic parameters with high contributions as inputs for the data-driven approach.Next,a novel swarm optimization algorithm,the enhanced search ant colony optimization,is proposed.This algorithm improves the ant colony optimization(ACO)algorithm based on a reinforcement factor to avoid premature convergence and accelerate the convergence speed.Comparative experiments are set up to compare the performance differences between particle swarm optimization(PSO),ACO,and ENSACO.Finally,a data-driven method based on ENSACO-LSTM is proposed to predict the power degradation trend of PEMFCs.And actual aging data is used to validate the method.The results show that,within a limited number of iterations,the optimization capability of ENSACO is significantly stronger than that of PSO and ACO.Additionally,the prediction accuracy of the ENSACO-LSTM method is greatly improved,with an average increase of approximately 50.58%compared to LSTM,PSO-LSTM,and ACO-LSTM.
基金supported by the Ministry of Science,Technological Development and Innovation of the Republic of Serbia,through the Contract no.451-03-65/2024-03/200105
文摘This paper proposes a modification of the Forrestal-Warren perforation model aimed at extending its applicability range to intermediately-thick high-hardness armor steel plates.When impacted by armorpiercing projectiles,these plates tend to fail through adiabatic shear plugging which significantly reduces their ballistic resistance.To address this effect,an approach for determining effective thickness was defined and incorporated into the predictive model.Ballistic impact tests were performed to assess the modification's validity,in which ARMOX 500T steel plates were subjected to perpendicular impacts from 7.62×39 mm steel-cored rounds under various velocities.Frequent target failure by soft plugging was observed,as well as the brittle shatter of the hard steel core.Key properties of the recovered plugs including their mass,length and diameter were measured and reported along with the projectiles'residual velocities.Additionally,independent data from the open literature were included in the analysis for further validation.The original Forrestal-Warren model and the novel effective thickness modification were then used to establish the relationship between impact and residual velocities,as well as to determine the ballistic limit velocity.The comparison revealed that the proposed approach significantly improves the model's accuracy,showing a strong correlation with experimental data and reducing deviations to within a few percent.This enhancement highlights the potential of the effective thickness term,which could also be applied to other predictive models to extend their applicability range.Further exploration into other armor steels and impact conditions is recommended to assess the method's versatility.
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
基金supported by the National Natural Science Foundation of China(7084001290924022)the Ph.D.Thesis Innovation and Excellent Foundation of Nanjing University of Aeronautics and Astronautics(2010)
文摘In grey system theory,the studies in the field of grey prediction model are focused on real number sequences,rather than grey number ones.Hereby,a prediction model based on interval grey number sequences is proposed.By mining the geometric features of interval grey number sequences on a two-dimensional surface,all the interval grey numbers are converted into real numbers by means of certain algorithm,and then the prediction model is established based on those real number sequences.The entire process avoids the algebraic operations of grey number,and the prediction problem of interval grey number is usefully solved.Ultimately,through an example＇s program simulation,the validity and practicability of this novel model are verified.
基金This Project was supported by the National Natural Science Foundation of China (60374037 and 60574036)the Opening Project Foundation of National Lab of Industrial Control Technology (0708008).
文摘A constrained generalized predictive control （GPC） algorithm based on the T-S fuzzy model is presented for the nonlinear system. First, a Takagi-Sugeno （T-S） fuzzy model based on the fuzzy cluster algorithm and the orthogonalleast square method is constructed to approach the nonlinear system. Since its consequence is linear, it can divide the nonlinear system into a number of linear or nearly linear subsystems. For this T-S fuzzy model, a GPC algorithm with input constraints is presented. This strategy takes into account all the constraints of the control signal and its increment, and does not require the calculation of the Diophantine equations. So it needs only a small computer memory and the computational speed is high. The simulation results show a good performance for the nonlinear systems.
基金supported by the National Natural Science Foundation of China(1147105951375517+5 种基金71271226)the China Postdoctoral Science Foundation Funded Project(2014M560712)Chongqing Frontier and Applied Basic Research Project(cstc2014jcyj A00024)the Ministry of Education of Humanities and Social Sciences Youth Foundation(14YJAZH033)the Chongqing Municipal Education Scientific Planning Project(2012-GX-142)the Higher School Teaching Reform Research Project in Chongqing(1202010)
文摘In order to deeply research the structure discrepancy and modeling mechanism among different grey prediction models, the equivalence and unbiasedness of grey prediction models are analyzed and verified. The results show that all the grey prediction models that are strictly derived from x^（0）（k） ＋az^（1）（k） = b have the identical model structure and simulation precision. Moreover, the unbiased simulation for the homogeneous exponential sequence can be accomplished. However, the models derived from dx^（1）/dt ＋ ax^（1）= b are only close to those derived from x^（0）（k） ＋ az^（1）（k） = b provided that ｜a｜ has to satisfy｜a｜ 0.1; neither could the unbiased simulation for the homogeneous exponential sequence be achieved. The above conclusions are proved and verified through some theorems and examples.
基金Project(E2015203354)supported by Natural Science Foundation of Steel United Research Fund of Hebei Province,ChinaProject(ZD2016100)supported by the Science and the Technology Research Key Project of High School of Hebei Province,China+1 种基金Project(LJRC013)supported by the University Innovation Team of Hebei Province Leading Talent Cultivation,ChinaProject(16LGY015)supported by the Basic Research Special Breeding of Yanshan University,China
文摘The accuracy of present flatness predictive method is limited and it just belongs to software simulation. In order to improve it, a novel flatness predictive model via T-S cloud reasoning network implemented by digital signal processor(DSP) is proposed. First, the combination of genetic algorithm(GA) and simulated annealing algorithm(SAA) is put forward, called GA-SA algorithm, which can make full use of the global search ability of GA and local search ability of SA. Later, based on T-S cloud reasoning neural network, flatness predictive model is designed in DSP. And it is applied to 900 HC reversible cold rolling mill. Experimental results demonstrate that the flatness predictive model via T-S cloud reasoning network can run on the hardware DSP TMS320 F2812 with high accuracy and robustness by using GA-SA algorithm to optimize the model parameter.
基金Projects(61573052,61273132)supported by the National Natural Science Foundation of China
文摘This work is concerned with identification and nonlinear predictive control method for MIMO Hammerstein systems with constraints. Firstly, an identification method based on steady-state responses and sub-model method is introduced to MIMO Hammerstein system. A modified version of artificial bee colony algorithm is proposed to improve the prediction ability of Hammerstein model. Next, a computationally efficient nonlinear model predictive control algorithm(MGPC) is developed to deal with constrained problem of MIMO system. The identification process and performance of MGPC are shown. Numerical results about a polymerization reactor validate the effectiveness of the proposed method and the comparisons show that MGPC has a better performance than QDMC and basic GPC.
基金Project(51375119) supported by the National Natural Science Foundation of China
文摘Pre-knowledge of machined surface roughness is the key to improve whole machining efficiency and meanwhile reduce the expenditure in machining optical glass components.In order to predict the surface roughness in ultrasonic vibration assisted grinding of brittle materials,the surface morphologies of grinding wheel were obtained firstly in the present work,the grinding wheel model was developed and the abrasive trajectories in ultrasonic vibration assisted grinding were also investigated,the theoretical model for surface roughness was developed based on the above analysis.The prediction model was developed by using Gaussian processing regression(GPR)due to the influence of brittle fracture on machined surface roughness.In order to validate both the proposed theoretical and GPR models,32sets of experiments of ultrasonic vibration assisted grinding of BK7optical glass were carried out.Experimental results show that the average relative errors of the theoretical model and GPR prediction model are13.11%and8.12%,respectively.The GPR prediction results can match well with the experimental results.
文摘Based on the idea of fusing modeling, an integrated prediction model for sintering process was proposed. A framework for sulfur content prediction was established, which integrated multi modeling ways together, including mathematical model combined with neural network(NN), rule model based on empirical knowledge and model-choosing coordinator. Via metallurgic mechanism analysis and material balance computation, a mathematical model calculated the sulfur content in agglomerate by the material balance equation with some parameters predicted by NN method. In the other model, the relationship between sulfur content and key factors was described in the form of expert rules. The model-choosing coordinator based on fuzzy logic was introduced to decide the weight of result of each model according to process conditions. The model was tested by industrial application data and produced a relatively satisfactory prediction error. The model also preferably reflected the varying tendency of sulfur content in agglomerate as the evidence of its prediction performance.
基金funded by National Natural Science Foundation of China(grant number 61473311,70901075)Natural Science Foundation of Beijing Municipality(grant number 9142017)military projects funded by the Chinese Army。
文摘Electronic warfare is a modern combat mode,in which predicting digital material consumption is a key for material requirements planning(MRP).In this paper,we introduce an insensitive loss function(ε) and propose a ε-SVR-based prediction approach.First,we quantify values of influencing factors of digital equipments in electronic warfare and a small-sample data on real consumption to form a real combat data set,and preprocess it to construct the sample space.Subsequently,we establish the ε-SVR-based prediction model based on "wartime influencing factors-material consumption" and perform model training.In case study,we give 8 historical battle events with battle damage data and predict 3 representative kinds of digital materials by using the proposed approach.The results illustrate its higher accuracy and more convenience compared with other current approaches.Taking data acquisition controller prediction as an example,our model has better prediction performance(RMSE=0.575 7,MAPE(%)=12.037 6 and R^2=0.996 0) compared with BP neural network model(RMSE=1.272 9,MAPE(%)=23.577 5 and R^2=0.980 3) and GM(1,1) model(RMSE=2.095 0,MAPE(%)=24.188 0 and R^2=0.946 6).The fact shows that the approach can be used to support decision-making for MRP in electronic warfare.
基金supported by the National Natural Science Foundation of China(61836001,62122014,62173036,62102022)。
文摘The rapid increase of the scale and the complexity of the controlled plants bring new challenges such as computing power and storage for conventional control systems.Cloud computing is concerned as a powerful solution to handle complex large-scale control missions by using sufficient computing resources.However,the computing ability enables more complex devices and more data to be involved and most of the data have not been fully utilized.Meanwhile,it is even impossible to obtain an accurate model of each device in the complex control systems for the model-based control algorithms.Therefore,motivated by the above reasons,we propose a data-driven predictive cloud control system.To achieve the proposed system,a practical data-driven predictive cloud control testbed is established and together a cloud-edge communication scheme is developed.Finally,the simulations and experiments demonstrate the effectiveness of the proposed system.
基金supported by the Beijing Education Committee Cooperation Building Foundation Project (XK100070532)
文摘The mechanical system with backlash is distinguished between a＂backlash mode＂and a＂contact mode＂.The inherent switching between the two operating modes makes the system a prime example of hybrid system.For eliminating the bad effect of backlash, a piecewise affine（PWA） model of the mechanical servo system with backlash is built.The optimal control of constrained PWA system is obtained by taking advantage of model predictive control（MPC） method, and the explicit solution of MPC in a look-up table form is figured out by combining the dynamic programming and multi-parametric quadratic programming, thereby establishing an explicit hybrid model predictive controller.Furthermore, a piecewise quadratic（PWQ） function for guaranteeing the stability of closed-loop control is found by formulating the search of PWQ function as a semi-definite programming problem.In the tracking experiments, it is demonstrated that the explicit hybrid model predictive controller has a good traction control effect on the mechanical system with backlash.The error meets the demands of real system.Further, compared to the direct on-line computation, the computation burden is reduced by the explicit solution, thereby being suitable for real-time control of system with short sampling time.
基金Project(61673199)supported by the National Natural Science Foundation of ChinaProject(ICT1800400)supported by the Open Research Project of the State Key Laboratory of Industrial Control Technology,Zhejiang University,China
文摘For a class of linear discrete-time systems that is subject to randomly occurred networked packet loss in industrial cyber physical systems, a novel robust model predictive control method with active compensation mechanism was proposed. The probability distribution of packet loss is described as the Bernoulli distributed white sequences. By using the Lyapunov stability theory, the existing sufficient conditions of the controller are derived from solving a group of linear matrix inequalities. Moreover, dropout-rate with uncertainty and unknown dropout-rate are also considered, which can greatly reduce the conservativeness of the controller. The designed robust model predictive control method not only efficiently eliminates the negative effects of the networked data loss in industrial cyber physical systems but also ensures the stability of closed-loop system. Two examples were provided to illustrate the superiority and effectiveness of the proposed method.
