Model Predictive Method Research Articles

Model predictive control parameter optimization method for autonomous vehicles

Aiming at the problem of insufficient tracking accuracy and long computational time of model predictive control algorithm in trajectory tracking of autonomous vehicles, a model predictive control parameter optimization method based on a nondominated sorting whale optimization algorithm was proposed. In this method, the parameter optimization problem of the model predictive control algorithm was transformed into a multiobjective optimization problem, with the predictive horizon, control horizon, and sample time as optimized objectives and the sum of squared lateral trajectory errors and computational time as optimized variables. The multiobjective optimization problem was solved using the nondominated sort whale optimization algorithm, and then the Pareto optimal solution set was obtained. The best solution was determined using the expert scoring method, continuous order weighted average operator method, game theory combination weighting method, and technique for order preference by similarity to the ideal solution method. Finally, the phase plane method is used to analyze the vehicle handling stability. The experimental results show that compared with the initial method, the lateral trajectory errors of the proposed method are reduced by 66.09% on average, and the computational time is reduced by 54.68% on average. Therefore, the proposed method is considered to be an effective method for parameter optimization of model predictive control.

Online monitoring and fault early warning prediction method for the operational status of steam turbine sliding pin systems

Abstract In modern power systems, ensuring the safe and reliable operation of the sliding pin system in large steam turbine generator sets is crucial. However, the measurable parameters in the current distributed control system are insufficient for fault early detection of the sliding pin system’s operational state. Additionally, there is a lack of relevant research in this area at present. This paper utilizes a typical 300 MW-class unit as a case study. By analyzing the operational mechanism and fault modes of the sliding pin system, a method for online monitoring of its operational status based on cylinder expansion measurement parameters is proposed. Based on this foundation, taking the advantage of long short-term memory (LSTM) network to effectively extract features from univariate time series, and integrating improved particle swarm optimization (IPSO) for automatic hyperparameter optimization, a multi-step prediction model and fault prediction method for the operational status of sliding pin systems based on IPSO-LSTM is designed. Test results based on various performance evaluation metrics indicate that the IPSO-LSTM algorithm significantly enhances the prediction model’s accuracy. Specifically, the TVIWAC-PSO model, which varies the inertia weight (TVIW) and acceleration coefficients simultaneously in the PSO algorithm, optimizes by enhancing global search in the early stages and emphasizing local search in the later stages of iteration. Furthermore, TVIWAC-PSO demonstrates superior performance in optimizing the hyperparameters of the LSTM algorithm. Finally, based on the gap standard between sliding pins and keyway in the actual operating procedures of the unit, combined with the low-pressure cylinder and rotor expansion difference operation standard, thresholds for anomaly detection and early fault prediction of the sliding pin system’s operational status are provided. This study holds significant engineering application value.

Short-term hybrid prognostics of fuel cells: A comparative and improvement study

Accurately predicting the performance degradation trend of fuel cells helps take measures in advance and prolong the stack's service life, leading to a novel hybrid forecasting approach. The first grey model prediction method based on residual exponential smoothing optimization (ES-R-GM) can capture the voltage deterioration trend. We explore the integration of two different ES techniques, specifically the double ES (ES2) and cubic ES (ES3), to investigate their effect on enhancing the predictive accuracy of the GM model. The second method of the adaptive network fuzzy inference system (ANFIS) can characterize local nonlinear behavior. We utilize the simulated annealing (SA) algorithm to optimize ANFIS results under different fuzzy rule selection strategies. The outcomes of the two prediction methods mentioned above are combined to create a hybrid prediction using the data fusion method and the moving window technique. Various hybrid methods are evaluated under general conditions and further detailed optimization. The data collected from the experimental platform confirms the suggested hybrid framework. The results show that the hybrid ES3-R-GM + ANFIS-SC method outperformed the single models in final prediction accuracy and can effectively track both global trends and local changes. Simultaneously, it takes less time to calculate than the literature. Moreover, when applied to consistent public datasets, the hybrid approach maintains its robustness and accuracy compared with other hybrid prognostic methods.

Numerical simulation and intelligent prediction of a 500 t/d municipal solid waste incinerator

After classifying municipal solid waste (MSW), understanding how changes in its characteristics affect the incineration process becomes essential. Optimizing and adjusting operating parameters is crucial to ensure the smooth operation of MSW incinerators. In this study, we developed a three-dimensional numerical simulation model for a 500 t/d MSW incinerator, based on a two-fluid model that accounts for grate motion. We examined the effects of load and moisture on the combustion process. Using the results from the numerical simulation and on-site operational data, we established a machine learning model to predict incinerator conditions based on load, waste particle size, and moisture content. The average relative errors for the training and test sets were approximately 0.33 % and 0.44 %, respectively. Finally, we compared the influence of different operating parameters on flue gas temperature. Our numerical simulation model and intelligent prediction method offer valuable guidance for optimizing existing MSW incinerators and designing new ones.

Sound speed prediction of seafloor sediments in the South Yellow Sea based on BP-AdaBoost model

Based on the sound speed and physical property measurements of seafloor sediments obtained in the central part of the South Yellow Sea, a multi-parameter prediction model for the sound speed of seafloor sediments based on seven parameters, including density, porosity, water content, liquid limit, plasticity index, compression coefficient, and median grain size, was developed by using the BP-AdaBoost fusion algorithm. The results show that the model, configured with 7 input layer neurons, 10 hidden layer neurons, 1 output node, a learning rate of 0.1, and 300 training iterations, achieved a correlation coefficient of 0.962. The mean absolute error (MAE) of the predicted sound speed was 10.19 m/s, and the mean relative error (MAPE) was 0.66%. These results are better than those of single-parameter and dual-parameter prediction equations and other machine learning models. The BP-AdaBoost model prediction method of sound speed of seafloor sediments established in this paper is better than the single-parameter and dual-parameter prediction equations and other prediction models, and it can provide a new way for the prediction of sound speed of seafloor sediments in the study area.

Automated model order reduction for building thermal load prediction using smart thermostats data

This paper presents a methodology to automatically determine the structure of sufficiently accurate grey-box models for model predictive control, energy efficiency and flexibility applications in buildings. The methodology is based on model reduction and system identification techniques, with a path that enhances data pre-processing, a multistage order reduction, and parameter estimation. The model structure is determined with a cascade approach that either neglects, keeps, or aggregates thermal zones by using discrete and continuous frequency domain techniques. Once the optimal structure is identified, the parameters are calibrated with the measured data from smart thermostats, using the model predictive control relevant identification method. The methodology is applied to a monitored house located in Québec, Canada. The developed algorithm identifies adjacent zones, even when the building layout is unknown, by studying indoor temperature fluctuations. The results concerning the model creation suggest that, for this specific building, the aggregation by floor is the most efficient way for creating reduced order thermal models, limiting uncertainty due to thermal zone interaction. This methodology provides control-oriented models that accurately predict response up to 24-h ahead with Root Mean Square Error less than 0.5 °C and acceptable Fitness Function values for the minimum number of selected parameters. Finally, several scenarios demonstrate the insights gained from using grey-box building thermal models for design, control, and retrofitting applications.

Expanded virtual vector-based model forecastable control strategy for three-phase two-level inverters

Abstract A three-phase, two-level inverter based on model forecastable control has good transient performance but poor steady-state performance. Considering the limitation of a limited number of discrete voltage vectors in a two-level inverter topology, this paper proposes a virtual vector model prediction method based on the analysis of a time-stepped forecasting model for a three-phase grid-connected inverter. First, three fixed virtual voltage vectors are constructed in each sector, and the action time of the required fundamental vector is found. Then, the cost function is constructed, and the optimum is selected among the virtual and fundamental voltage vectors in each sector. Finally, a hardware-in-the-loop experiment was carried out based on the PE-Expert4 experimental platform developed by Myway Co., LTD. The results show that the proposed virtual vector model forecastable control strategy can effectively improve the transient and steady-state performance of three-phase two-level inverters.

Accelerated MPC: A real-time model predictive control acceleration method based on TSMixer and 2D block stochastic configuration network imitative controller

Modern industrial processes demand real-time model predictive control (MPC) method within the constraints of limited computing resources. This paper introduces an accelerated MPC method to address the issue. Specifically, we employ the time series mixing model (TSMixer) to construct a predictive model capable of accurately forecasting the behavior of the system under control. Furthermore, we extend the capabilities of TSMixer by integrating a feature classification model (TSMixer with FCM). This enhanced version takes into account both future information and static variables, resulting in superior accuracy compared to the transformer model while maintaining a significantly smaller parameter count. Finally, to further enhance MPC’s responsiveness, we develop a two-dimensional block stochastic configuration network (2D-BSCN) imitative controller. This innovative network clones the behavior of rolling optimization, effectively replacing online optimization to reduce computational time. The experimental results show that the accelerated MPC has an excellent performance in numerical simulation and actual industrial processes. Notably, the algorithm achieves a smaller FLOPs and tracking time than other state-of-the-art models, well within the requirement for industrial process control.

Short-Term Power Load Forecasting Method Based on GRU-Transformer Combined Neural Network Model

Load Forecast (LF) is an important task in the planning, control and application of public power systems. Accurate Short Term Load Forecast (STLF) is the premise of safe and economical operation of a power system. In the research of short-term power load forecasting, machine learning and deep learning are the most popular methods at present, but there still exists a problem that the single and simple structure of power load forecasting model leads to low accuracy of load forecasting. In order to improve the accuracy of STLF, a Gated Cycle Unit (GRU)-Transformer combined neural network model is proposed. Transformer encoder structure is used as feature extractor to mine the complex mapping relationships between the input features and load. The advantage of self-attention mechanism is used to solve the problem of information loss of long sequences in short-term power load forecasting. At the same time, the multivariate time series model of GRU is used for model training. The experimental results on the power load data set of a certain region in southwest China and Panama City show that the proposed combined model prediction method has higher accuracy than those proposed in other literatures, which further proves its feasibility and superiority.

A goal-conditioned policy search method with multi-timescale value function tuning

PurposeCurrent reinforcement learning (RL) algorithms are facing issues such as low learning efficiency and poor generalization performance, which significantly limit their practical application in real robots. This paper aims to adopt a hybrid model-based and model-free policy search method with multi-timescale value function tuning, aiming to allow robots to learn complex motion planning skills in multi-goal and multi-constraint environments with a few interactions.Design/methodology/approachA goal-conditioned model-based and model-free search method with multi-timescale value function tuning is proposed in this paper. First, the authors construct a multi-goal, multi-constrained policy optimization approach that fuses model-based policy optimization with goal-conditioned, model-free learning. Soft constraints on states and controls are applied to ensure fast and stable policy iteration. Second, an uncertainty-aware multi-timescale value function learning method is proposed, which constructs a multi-timescale value function network and adaptively chooses the value function planning timescales according to the value prediction uncertainty. It implicitly reduces the value representation complexity and improves the generalization performance of the policy.FindingsThe algorithm enables physical robots to learn generalized skills in real-world environments through a handful of trials. The simulation and experimental results show that the algorithm outperforms other relevant model-based and model-free RL algorithms.Originality/valueThis paper combines goal-conditioned RL and the model predictive path integral method into a unified model-based policy search framework, which improves the learning efficiency and policy optimality of motor skill learning in multi-goal and multi-constrained environments. An uncertainty-aware multi-timescale value function learning and selection method is proposed to overcome long horizon problems, improve optimal policy resolution and therefore enhance the generalization ability of goal-conditioned RL.

GL-STGCNN: Enhancing Multi-Ship Trajectory Prediction with MPC Correction

In addressing the challenges of trajectory prediction in multi-ship interaction scenarios and aiming to improve the accuracy of multi-ship trajectory prediction, this paper proposes a multi-ship trajectory prediction model, GL-STGCNN. The GL-STGCNN model employs a ship interaction adjacency matrix extraction module to obtain a more reasonable ship interaction adjacency matrix. Additionally, after obtaining the distribution of predicted trajectories using the model, a model predictive control trajectory correction method is introduced to enhance the accuracy and reasonability of the predicted trajectories. Through quantitative analysis of different datasets, it was observed that GL-STGCNN outperforms previous prediction models with a 31.8% improvement in the average displacement error metric and a 16.8% improvement in the final displacement error metric. Furthermore, trajectory correction through model predictive control shows a performance boost of 44.5% based on the initial predicted trajectory distribution. While GL-STGCNN excels in multi-ship interaction trajectory prediction by reasonably modeling ship interaction adjacency matrices and employing trajectory correction, its performance may vary in different datasets and ship motion patterns. Future work could focus on adapting the model’s ship interaction adjacency matrix modeling to diverse environmental scenarios for enhanced performance.

Performance degradation model and life prediction method of spool pair caused by erosion wear

The erosion of solid particles in the fluid causes the wear of the metering edge of the spool pair, resulting in a decrease in system performance. This paper aims to develop a general method to evaluate performance degradation and life prediction of spool pairs induced by erosion. Considering the diversity of influencing factors and the complexity of operating conditions, traditional numerical calculation methods will consume huge computational costs. It is difficult to qualitatively and quantitatively analyze the evolution of metering edge by numerical calculation. The erosion prediction model (EPM) constructed by machine learning methods can be used to predict the wear profile discretized in time and space. Combined with the mathematical model of the valve-controlled cylinder, a performance degradation model (PDM) that can simulate real-time working conditions is established. Through the data exchange and iterative update between EPM and PDM, a complete digital platform for the calculation of slide valve durability is constructed. After comparing with the experimental results, it can be concluded that the proposed method can realize the performance degradation evaluation and life prediction of the spool pair caused by erosion wear under continuous working conditions.

Study on Predicting Liquid Production Profile in Horizontal Wells Considering the Mechanism of Annular Flow Resistance and Water Control

The coated particle ICD water control technology has been widely used in horizontal well completion in offshore oil fields in recent years, but there is a lack of research on the simulation and prediction methods for liquid production profiles. By analyzing the dynamic inflow process of fluid, starting from the laws of momentum conservation and mass conservation, a coupled mathematical model of horizontal well reservoir wellbore pressure drop considering the mechanism of annular flow resistance was established, and solved through programming. Based on the actual well data of a certain block in an offshore oilfield, a horizontal well reservoir production model was established. The calculation results of the example show that the annular flow resistance and water control technology can effectively control the balanced liquid production of horizontal wells, thereby increasing the anhydrous oil recovery period and improving the oil recovery rate of the oilfield; The coupling model simulation and prediction method can fully reflect the mutual influence between the oil reservoir, wellbore annulus, ICD, and horizontal wellbore; The effective diameter of the ICD valve affects the changes in oil production and water content. The placement of the ICD well section has a significant effect on water control, and the compactness of the filled particles has a certain impact on pressure and water content changes.

Generalized control for distributed energy inverter in community microgrid system: Off-grid and grid-connected operation

With the increasing penetration of distributed energy resources (DER) in microgrids, DER power inverters have become a critical asset for providing power support to these microgrids. Meanwhile, the grid-forming (GFM) inverters, among these DER inverters, have gained significant attention in microgrid applications for their capability to enable the DERs to operate in different microgrid conditions and various operation modes. Moreover, with the implementation of these GFM inverters, smooth operation mode transition, GFM functions as well as black start functions can be obtained to improve the operation of the microgrid systems. In this article, a generalized control method for a single-phase GFM inverter is developed for community microgrid applications, facilitating smooth operation behavior in both operation modes with grid support functions and stable transition for different microgrid conditions. The control design procedure and function analysis of the proposed control method are explained in detail based on the community microgrid system. The effectiveness of the method in this paper is demonstrated on a 10 kW single-phase GFM inverter prototype with comparison to a model predictive method in recent literature.

A study on ice resistance prediction based on deep learning data generation method

Accurate prediction of ice resistance plays an important role in ensuring the safety of ship navigation when sailing in ice regions. This paper focuses on the design of a data generation deep learning model and an interpretable ice resistance prediction deep learning model. By selecting the appropriate ship, ice parameters and model experimental data to build the dataset, the influence of different data preprocessing methods on the model results are discussed. The processed data is expanded by Deep Convolutional Generative Adversarial Network (DCGAN). On this basis, a Graph Neural Network (GNN) is built to explain the distribution of network weights and the generalization effect of the model. The established model (GNN-DCGAN) and several ice resistance prediction methods are compared and analyzed. In addition, the design of polar ships needs to comprehensively consider the dynamic changes of ship design parameters and the mechanical properties of ice. In this paper, taking MT UIKKU as an example, the parameter sensitivity analysis is carried out to study the scope of application of the model and the contribution of different parameters. The results show that the DCGAN method can improve the prediction accuracy and application scope of GNN model. The predictions exhibit a high level of agreement with the experimental data, which can provide valuable references for the design of ship in ice regions.

Short term power load forecasting system based on improved neural network deep learning model

AbstractThe electricity load prediction is closely related to production and daily life. The electricity load prediction is also a very important task. With the widespread application of smart grids, load data shows an exponential growth trend. The huge amount of data in the load makes power prediction even more difficult. On the basis of traditional prediction algorithms, a power load prediction model based on machine learning and neural networks is designed. Because the single model prediction has the unstable results, a combined model is obtained based on the ensemble learning idea and two single model prediction method. The prediction results are detected by the load data. From the experimental results, the mean absolute percentage error (MAPE) of the AdaBoost‐GRU data fusion model is 0.066%. Compared to the AdaBoost‐GRU data fusion model, the MAPE decreases by 1.59% and 1.12%, respectively. The relative mass scores of the two groups decrease by 132.57% and 89.14%, respectively. The prediction accuracy is improved, which has advantages compared to traditional combination models. It can effectively enhance the accuracy of short‐term power grid load forecasting. It is an important scientific and practical reference for power grid decision‐making.

Comparative Analysis of Bursting Pressure Prediction Methods for Steam Generator Tube With Volume Defect

Abstract This paper compares the difference and accuracy of bursting pressure prediction based on the flow stress σf prediction method, plastic collapse prediction method, and ductile damage model prediction method in Inconel 690 steam generator tube (SGT) with volume defect. The tensile and smooth tube bursting tests determine the parameters required for the three prediction methods. The three methods predict the bursting pressures for four deep volume defects in SGT. The results are compared and analyzed with the experimental data. The results show that the ductile damage model prediction method is the best to predict the SGT bursting pressure error with volume defects simulating the structure's deformation and damage failure process.

A hybrid model with combined feature selection based on optimized VMD and improved multi-objective coati optimization algorithm for short-term wind power prediction

With the continuous global increase in installed wind power capacity and subsequent surge in power generation, the contradiction between the safe operation of the grid and the efficient consumption of new energy after large-scale grid connection has become increasingly prominent. This paper presents a hybrid model prediction method to further improve the stability and accuracy of wind power prediction. Firstly, variational modal decomposition (VMD) optimized by the coati optimization algorithm (COA) is employed to decompose original wind power, mitigating the non-stationary characteristics of the power sequence. Subsequently, permutation entropy (PE) is used to recombine the decomposed components, and the combined feature selection method is achieved by integrating the Spearman correlation coefficient (SCC) and the autocorrelation function (ACF). Then, the multivariate combined model is constructed, and the improved multi-objective coati optimization algorithm (IMOCOA) determines the weight coefficients of each model to enhance the performance of the hybrid model. Finally, research and analysis are conducted from multiple scenarios and time scales using historical operating data from a wind farm in Xinjiang. The experimental results show that the proposed prediction model effectively improves the accuracy and stability of the wind power prediction compared with other popular prediction models.

A Mobile Hybrid Robot and Its Accuracy Issue in Machining of Large-Scale Structures

Accurate and efficient manufacturing of large-scale structures is an important and challenging issue. To this end, a mobile hybrid robot named CraftsRobot is designed and developed for in-situ machining the local features of large-scale structures. The mobile hybrid robot comprises a mobile vehicle, a guide rail, a two degree-of-freedom (DoF) mechanical arm, and a five-DoF light-weight parallel module. The interaction mechanism between the parallel module and the mechanical arm is disclosed to build the error prediction model. On this basis, a model predictive compensation method is proposed. In each servo cycle, the command pose of the parallel module is modified and under the effect of the interaction-induced error superimposed on the modified command pose, the parallel module will reach the target pose. The results of simulation and experiment both verify the effectiveness of the compensation model. After compensation, the mobile hybrid robot is applied to machine the features on a typical large-scale structure and the machining errors are within 0.04 mm. The experimental results show that the designed robot can machine local features of large-scale structures in situ and meet the precision requirements. Together, this study provides a novel approach to achieve accurate and efficient manufacturing of large-scale structures.

Classified functional mixed effects model prediction.

In nowadays biomedical research, there has been a growing demand for making accurate prediction at subject levels. In many of these situations, data are collected as longitudinal curves and display distinct individual characteristics. Thus, prediction mechanisms accommodated with functional mixed effects models (FMEM) are useful. In this paper, we developed a classified functional mixed model prediction (CFMMP) method, which adapts classified mixed model prediction (CMMP) to the framework of FMEM. Performance of CFMMP against functional regression prediction based on simulation studies and the consistency property of CFMMP estimators are explored. Real-world applications of CFMMP are illustrated using real world examples including data from the hormone research menstrual cycles and the diffusion tensor imaging.