Search results

Sensorless interior permanent magnet in-wheel motor (IPMIWM), as an exemplar of modular automation system, has attracted considerable interests in recent years. This paper aims to investigate a novel hybrid control approach for the sensorless IPMIWM from a cyber-physical systems (CPS) perspective.

The control approach is presented based on the hybrid dynamical theory. In the standstill-low (S-L) speed, the rotor position/speed signal is estimated by the method of the high frequency (HF) voltage signal injection. The least square support vector machine (LS-SVM) is used to acquire the rotor position/speed signal in medium-high (M-H) speed operation. Hybrid automata model of the IPMIWM is established due to its hybrid dynamic characteristics in wide speed range. A hybrid state observer (HSO), including a discrete state observer (DSO) and a continuous state observer (CSO), is designed for rotor position/speed estimation of the IPMIWM.

The hardware-in-the-loop testing based on dSPACE is carried out on the test bench. Experimental investigations demonstrate the hybrid control approach can not only identify the rotor position/speed signal with a certain load but also be able to reject the load disturbance. The reliability and the effectiveness of the proposed hybrid control approach were verified.

The proposed hybrid control approach for the sensorless IPMIWM promotes the deep combination and coordination of sensorless IPMIWM drive system. It also theoretically supports and extends the development of the hybrid control of the highly integrated modular automation system.

When recommending products to consumers, it is important to be able to accurately predict how consumers will rate them. However, existing collaborative filtering models are difficult to achieve a balance between rating prediction accuracy and complexity. Therefore, the purpose of this paper is to propose an accurate and effective model to predict users’ ratings of products for the accurate recommendation of products to users.

First, we introduce an attention mechanism that dynamically assigns weights to user preferences, highlighting key interaction information and enhancing the model’s understanding of user behavior. Second, a fold embedding strategy is employed to segment user interaction data, increasing the information density of each subset while reducing the complexity of the attention mechanism. Finally, a masking strategy is integrated to mitigate overfitting by concealing portions of user-item interactions, thereby improving the model’s generalization ability.

The experimental results demonstrate that the proposed model significantly minimizes prediction error across five real-world datasets. On average, the evaluation metrics root mean square error (RMSE) and mean absolute error (MAE) are reduced by 9.11 and 13.3%, respectively. Additionally, the Friedman test results confirm that these improvements are statistically significant. Consequently, the proposed model more accurately captures the intrinsic correlation between users and products, leading to a substantial reduction in prediction error.

We propose a novel collaborative filtering model to learn the user-item interaction matrix effectively. Additionally, we introduce a fold embedding strategy to reduce the computational resource consumption of the attention mechanism. Finally, we implement a masking strategy to encourage the model to focus on key features and patterns, thereby mitigating overfitting.

The purpose of this study is to improve the control performance of grid-connected photovoltaic (PV) inverters with inductive-capacitive-inductive (LCL) filters by proposing a new robust current control based on uncertainty and disturbance estimator (UDE).

The control strategy combines the capacitor current feedback with a UDE-based control to solve robust stability issues in the presence of parametric uncertainties and disturbances.

This paper provides guidelines for tuning the controller parameters where it is shown to be easy to implement by simply selecting the appropriate feedback coefficient, the reference model and an approximate lumped disturbance bandwidth. Simulation and experimental results demonstrate the effectiveness of the proposed controller in terms of resonance damping, tracking performance and robust stability under grid uncertainties and disturbances.

This paper offers a new approach for designing implementable robust controllers for LCL-filtered grid-connected PV inverters.

A new UDE-based current control is proposed to improve the stability performance of grid-connected PV inverters. The advantages of UDE-based control are its simple structure, easy tuning and robustness under parameter uncertainties and disturbances. Simulation and experimental results support the theoretical findings.

This paper proposes a spoke-type fractional-slot concentrated windings (FSCW) permanent magnet (PM) machine for special vehicle driving systems to obtain higher torque and power density, high efficiency and wide field-weakening range. To enhance the efficiencies of multi-objective optimization processes, the respond surface (RS) method and black-hole (BH) algorithm are used.

The spoke-type FSCW PM machine is optimized to meet the requirements of the special vehicle driving system. The combination of the RS and BH algorithm is used to obtain high torque, low torque ripple and high efficiency.

The optimal spoke-type PM machine is obtained, and it has higher torque density, lower torque ripple, cogging torque and wider magnetic field weakening range. Finally, a 15-kW prototype machine is fabricated and tested to verify the results of the optimization method and finite-element analysis.

This paper designs a high torque density and efficiency spoke-type FSCW PM machine, which is superior for special vehicle driving systems. Meanwhile, the RS model combined with BH algorithm is applied to the field of electrical machine multi-objective optimal design.

The purpose of this paper is to cut down energy consumption and eliminate production waste on mixed-model assembly lines. Therefore, a supermarket integrated dynamic cyclic kitting system with the application of electric vehicles (EVs) is introduced. The system resorts to just-in-time (JIT) and segmented sub-line assignment strategies, with the objectives of minimizing line-side inventory and energy consumption.

Hybrid opposition-based learning and variable neighborhood search (HOVMQPSO), a multi-objective meta-heuristics algorithm based on quantum particle swarm optimization is proposed, which hybridizes opposition-based learning methodology as well as a variable neighborhood search mechanism. Such algorithm extends the search space and is capable of obtaining more high-quality solutions.

Computational experiments demonstrated the outstanding performance of HOVQMPSO in solving the proposed part-feeding problem over the two benchmark algorithms non-dominated sorting genetic algorithm-II and quantum-behaved multi-objective particle swarm optimization. Additionally, using modified real-life assembly data, case studies are carried out, which imply HOVQMPSO of having good stability and great competitiveness in scheduling problems.

The feeding problem is based on static settings in a stable manufacturing system with determined material requirements, without considering the occurrence of uncertain incidents. Current study contributes to assembly line feeding with EV assignment and could be modified to allow cooperation between EVs.

The dynamic cyclic kitting problem with sub-line assignment applying EVs and supermarkets is solved by an innovative HOVMQPSO, providing both novel part-feeding strategy and effective intelligent algorithm for industrial engineering.

In this contribution, the solution of Mass-Spring-Damper Systems in the fractional context by using Caputo derivative and Orthogonal Collocation Method is investigated. For this purpose, different case studies considering constant and periodic sources are evaluated. The dimensional consistency of the model is guaranteed by introducing an auxiliary parameter. The obtained results are compared with those found by using both the analytical solution and the predictor-corrector method of Adams–Bashforth–Moulton type. The influence of the fractional order on the mechanical system is evaluated.

In the present contribution, an extension of the Orthogonal Collocation Method to solve fractional differential equations is proposed.

In general, the proposed methodology was able to solve a classical mechanical engineering problem with different characteristics.

The development of a new numerical method to solve fractional differential equations is the major contribution.

For a wide range of market actors, including policymakers, forecasting changes in commodity prices is crucial. As one of essential edible oil, peanut oil’s price swings are certainly important to predict. In this paper, the weekly wholesale price index for the period of January 1, 2010 to January 10, 2020 is used to address this specific forecasting challenge for the Chinese market.

The nonlinear auto-regressive neural network (NAR-NN) model is the forecasting method used. Forecasting performance based on various settings, such as training techniques, delay counts, hidden neuron counts and data segmentation ratios, are assessed to build the final specification.

With training, validation and testing root mean square errors of 5.89, 4.96 and 5.57, respectively, the final model produces reliable and accurate forecasts. Here, this paper demonstrates the applicability of the NAR-NN approach for commodity price predictions.

On the one hand, the findings may be used as independent technical price movement predictions. Conversely, they may be included in forecast combinations with forecasts derived from other models to form viewpoints of commodity price patterns for policy research.

China's agricultural production trusteeship is characterized by the organic link between household operation of small-scale peasant economy and agricultural socialized services, which releases agricultural development vitality and promotes agricultural modernization. As one of the agricultural production trusteeship modes, the whole process trusteeship is suitable for the actual situation of China's aging population and labor force transfer. This paper aims to construct an evolutionary game model containing multistakeholder to explore the behavior decisions through numerical simulation and to provide useful suggestions for the formation of a positive and stable trusteeship relationship and the sound development of the whole process trusteeship of agricultural production.

The paper incorporates village committees, service organizations and farmers into the same research framework, selects “guarantee + dividends” as the income distribution method and applies the evolutionary game method to analyze behavioral choices and evolutionary paths of stakeholders. By constructing the expectation function, establishing the replicator dynamic equations and analyzing the tripartite evolutionary stability strategy, the authors explore the factors that affect the stakeholders’ strategy choice and determine asymptotically stable points and stability conditions.

(1) There is a game relationship among village committees, farmers and service organizations in the whole process trusteeship of agricultural production, asymptotically stable points (0,0,1) and (1,1,1) are obtained through calculation. (2) The proportion of stakeholders' strategy choice, the weight of the whole process trusteeship of agricultural production in the performance appraisal of the village committee, the village committee's supervision cost, the village committee's reputation effect and the penalty for false dividends of the service organization will affect the speed at which the curve representing the tripartite relationship approaches two asymptotically stable points.

The countermeasures proposed in the paper have excellent reference value. (1) For areas that have realized the project: Village committees can solve the trusteeship problems exposed in the initial areas and improve farmers' satisfaction with the project. (2) For areas that have not realized the project: Those regions will receive more experience references and enhance their confidence in this project. The limitation of the paper is that it takes the main grain-producing areas in only the three northeastern provinces of China as the research object. The next research object will be extended to the whole country.

This paper propose strategies for realizing the orderly operation of the whole process trusteeship of agricultural production: first, increase the proportion of stakeholders' strategy choices; second, reduce the village committee's supervision cost; third, increase the weight of the whole process trusteeship of agricultural production in the performance appraisal of the village committee; fourth, improve the village committee's reputation effect; fifth, increase the penalty for false dividends of the service organization.

Agricultural production trusteeship is in its initial stage in China. The interest relationships between stakeholders are not yet clear. The paper innovatively applies the evolutionary game method to the research field of the whole process trusteeship of agricultural production. According to conditions in China, based on ensuring the guaranteed income, the paper introduces the dividend income variable and establishes a tripartite game model of village committees, service organization and farmers. The paper provides suggestions for the orderly and healthy development of China's agricultural production trusteeship and provides experience for the operation of other modes of agricultural production trusteeship.