Local Optimization Problem Research Articles

Coordinated Control of the Onboard and Wayside Energy Storage System of an Urban Rail Train Based on Rule Mining

There are three major challenges to the broad implementation of energy storage systems (ESSs) in urban rail transit: maximizing the absorption of regenerative braking power, enabling online global optimal control, and ensuring algorithm portability. To address these problems, a coordinated control framework between onboard and wayside ESSs is proposed in this study, and the related control strategy is obtained by transforming the global optimization problem into a combination of rule-based and local optimization problems. The design process of the strategy is divided into three parts: offline optimization, rule extraction, and local optimization. First, a genetic algorithm is used to optimize the charge/discharge threshold curves under typical operational conditions. Then, the rules of offline optimization results are obtained from an expert system, and the nonlinear rules are mined with local optimization methods. Finally, a coordinated strategy is presented based on the outcomes of the three parts. A power hardware-in-the-loop (PHIL) experimental platform based on RTLAB is built, and the above coordination strategy is verified based on data for the Beijing Metro Batong Line. The experimental results show that the strategy can effectively improve the energy-saving rate and reduce the regeneration failure rate substantially, with the effect being close to the offline global optimal solution. The algorithm proposed in this paper achieves near global optimal energy-saving optimization results with lower computational costs, and has strong portability, providing a good solution for the large-scale application of onboard and wayside energy storage coordination control.

Routing and facility location optimization in a dairy products supply chain

Routing and facility location optimization is an important aspect of supply chain management. This is because the problem of determining which facilities within a supply chain echelon should cost-effectively supply products to facilities in the next echelon is usually encountered by supply chain managers and analysts. In this paper, a linear programming model for supply chain routing and facility location optimization has been proposed. The model can be solved using the PuLP optimization library implemented in Python programming language. The model has been applied to a small dairy products supply chain to determine the most cost-effective routes for products in the supply chain. The optimization results proffered the optimal contribution of each factory warehouse to each distribution warehouse in order to satisfy distribution warehouse demand while minimizing costs. The results of the study indicated that the model is efficient in solving the routing and facility location optimization problem usually encountered in supply chain management. Therefore, this study will aid supply chain analysts and managers in determining the most cost-effective route for distributing products between echelons or stages of supply chains under study.

Research on Gas Multi-indicator Warning Method of Coal Mine Working Face Based on MOA-Transformer.

The gas emission from the coal mine working face is influenced by multiple factors, resulting in the real-time value, fluctuation, and trend changes of gas concentration being relatively independent and interrelated. This paper establishes a gas multi-indicator warning method that can comprehensively warn the status of real-time value, fluctuation, and trend changes of gas concentration from the working face. This paper proposes six basic indicators and includes two main research contents: intelligent threshold partition and gas multi-indicator warning. First, this paper proposes an intelligent threshold partition algorithm based on GF-KMeans (genetic fixed-centered K-means), which combines a genetic algorithm (GA) and an FC-KMeans (fixed-centered K-means) algorithm to dynamically partition the threshold range corresponding to the gas warning level. The GA solves the local optimal problem in the traditional K-Means algorithm, enhancing its stability and predictability. The FC-KMeans algorithm achieves a more precise control in the initial clustering center selection. Second, this paper researches a gas multi-indicator warning method based on a multihead optimal attention (MOA)-Transformer. By using the multihead optimization attention mechanism to represent classification features and utilizing Transformer's encoder structure to classify gas warning. The experimental result shows that the accuracy of the MOA-Transformer method is 86.17%, which is 3.45% higher than that of the Transformer method. The precision of the MOA-Transformer method is 88.78%, which is 3.75% higher than that of the Transformer method. The recall of the MOA-Transformer method is 85.23%, which is 4.70% higher than that of the Transformer method. The macro-F1 of the MOA-Transformer method is 86.96%, which is 4.39% higher than that of the Transformer method. The results fully demonstrate the superiority of the MOA-Transformer method in gas warning tasks.

Integration of optimal power flow with combined heat and power dispatch of renewable wind energy based power system using chaotic driving training based optimization

Combined heat and power economic dispatch (CHPED) based optimal power flow (OPF) problem has been studied in this article using a new, practical approach based on chaotic driving training optimization (DTBO) (CDTBO). In the proposed technique (CDTBO), the chaotic based learning is integrated with DTBO to overcome the local optimal problem and inferior convergence speed of the existing algorithms. OPF is an important concern to retain the power system running effectively. In order to meet the demand for reasonably priced power generation with optimal power flow in transmission lines, the authors combined CHPED and OPF. Since fuel is changing daily in the current environment, using renewable energy sources to generate electricity economically is crucial. The renewable energy source like wind energy is integrated with thermal units for economic power generation with reducing the thermal fuel consumption of CHPED-based OPF system. The proposed technique implemented on CHPED based IEEE-30 bus system for renewable and without renewable energy sources with considering different cases. The suggested problem considering with valve point loading of thermal units, transmission losses and uncertainties of wind speed to address the non-linearity of the renewable-based CHPED-OPF system. Cost minimization, voltage deviation control, transmission losses minimization and stability index are the single objectives of the prospective system. Furthermore tested on multi-objective functions for simultaneously minimization of cost with emission and simultaneously minimization of active power loss with voltage profile. It is observed that the proposed CDTBO technique helps to reduce the cost by 2% and 12.8% for renewable based system as compared to non-renewable system for multi-objective function. The robustness of the proposed solution has been verified by implementing the statistical analysis on two systems with least variation of mean and optimal values of cost with the tolerance of less than 0.0035%. A comparison has been made with recent well known optimization techniques to address the superiority of the suggested CDTBO algorithm.

Task offloading scheme of vehicular cloud edge computing based on Digital Twin and improved A3C

In traditional vehicle edge computing research, the limited computing resources of edge servers are not fully considered. At the same time, when using deep reinforcement learning (DRL) to solve vehicle edge computing problems, it is not fully considered that DRL requires a large amount of real-time data and is prone to gradient explosion or disappearance, over-fitting and local optimal solution problems. Therefore, this article proposes a digital twin (DT)-assisted vehicular cloud edge computing offloading solution. To solve the problem of limited edge server computing resources, this article proposes a vehicle, cloud, and edge server collaboration solution. In response to the problem that DRL requires a large amount of real-time data, this paper proposes a real-time data acquisition method based on DT technology. Aiming at the gradient explosion or disappearance, overfitting, and local optimal solution problems of the asynchronous dominant actor–critic (A3C) algorithm, this paper proposes an improved algorithm of A3C, which introduces the ɛ-greedy strategy and dynamic baseline to increase the possibility of exploration and increase the generalization ability of the model through Dropout technology. During the training process, this article also uses the stochastic gradient descent (SGD) algorithm to accelerate the training process and reduce the computational complexity. The simulation results show that compared with other solutions, the improved algorithm proposed in this paper can effectively reduce the delay and energy consumption of offloading tasks at the vehicular edge cloud.

Path Planning Analysis of Mobile Robot with Improved Ant Colony Algorithm

Aiming at the problems of poor convergence and local optimization in path planning using the basic ant colony algorithm, this paper studies an improved ant colony algorithm to enhance the effect of mobile robot path planning. Firstly, the state transition probability of the ant colony algorithm is modified, and the influence of the angle on node selection is increased by adding a new angle index heuristic function. Then, the sorting and elite ant colony algorithm strategies are fused to research a path length difference pheromone update method, improving the efficiency of the ant colony algorithm in planning the optimal path. Finally, through a comparison with the basic ant colony algorithm simulation on MATLAB, the feasibility and effectiveness of the improved ant colony algorithm are verified.

Evolution inspired binary flower pollination for the uncapacitated facility location problem

The present paper introduces a modified flower pollination algorithm (FPA) enhanced by evolutionary operators to solve the uncapacitated facility location problem (UFLP), which is one of the well-known location science problems. The aim in UFLP is to select some locations to open facilities among a certain number of candidate locations so as to minimize the total cost, which is the sum of facility opening costs and transportation costs. Since UFLP is a binary optimization problem, FPA, which is introduced to solve real-valued optimization problems, is redesigned to be able to conduct search in binary domains. This constitutes one of the contributions of the present study. In this context, some evolutionary operators such as crossover and mutation are adopted by the proposed FPA. Next, the mutation operator is further enhanced by making use of an adaptive procedure that introduces greater level of diversity at earlier iterations and encourages intensification toward the end of search. Thus, while premature convergence and local optima problems at earlier iterations are avoided, a more intensified search around the found promising regions is performed. Secondarily, as demonstrated in this study, by making use of the reported evolutionary procedures, FPA is able to run in binary spaces without employing any additional auxiliary procedures such as transfer functions. All available benchmarking instances are solved by the proposed approach. As demonstrated by the comprehensive experimental study that includes statistically verified results, the developed approach is found as a promising algorithm that can be extended to numerous binary optimization problems.

Hybrid Strategy Improved Beetle Antennae Search Algorithm and Application

The multi-dimensional optimization of mechanisms is a typical optimization problem encountered in mechanical design. Herein, the Hybrid strategy improved Beetle Antennae Search (HSBAS) algorithm is proposed to solve the multi-dimensional optimization problems encountered in structural design. To solve the problems of local optimization and low accuracy of the high-dimensional solution of the Beetle Antennae Search (BAS) algorithm, the algorithm adopts the adaptive step strategy, multi-directional exploration strategy, and Lens Opposition-Based Learning strategy, significantly reducing the probability of the algorithm falling into the local optimum and improving its global search capability. Comparative experiments of the improved algorithm are carried out by selecting eleven benchmark test functions. HSBAS can reach 1 × 10−22 accuracy from the optimal value when dealing with low-dimensional functions. It can also obtain 1 × 10−2 accuracy when dealing with high-dimensional functions, significantly improving the algorithm’s capability. According to Friedman’s ranking test result, HSBAS ranks first, which proves that HSBAS is superior to the other three algorithms. The HSBAS algorithm is further used to optimize the design of the altitude compensation module of the gravity compensation device for solar wings, controlling the fluctuation of bearing capacity within 0.25%, which shows that the algorithm can be used as an effective tool for engineering structural optimization problems.

HVAC energy cost minimization in smart grids: A cloud-based demand side management approach with game theory optimization and deep learning

In this paper, we present a novel cloud-based demand side management (DSM) optimization approach for the cost reduction of energy usage in heating, ventilation and air conditioning (HVAC) systems in residential homes at the district level. The proposed approach achieves optimization through scheduling of HVAC energy usage within permissible bounds set by house users. House smart home energy management (SHEM) devices are connected to the utility/aggregator via a dedicated communication network that is used to enable DSM. Each house SHEM can predict its own HVAC energy usage for the next 24 h using minimalistic deep learning (DL) prediction models. These predictions are communicated to the aggregator, which will then do day ahead optimizations using the proposed game theory (GT) algorithm. The GT model captures the interaction between aggregator and customers and identifies a solution to the GT problem that translates into HVAC energy peak shifting and peak reduction achieved by rescheduling HVAC energy usage. The found solution is communicated by the aggregator to houses SHEM devices in the form of offers via DSM signals. If customers’ SHEM devices accept the offer, then energy cost reduction will be achieved. To validate the proposed algorithm, we conduct extensive simulations with a custom simulation tool based on GridLab-D tool, which is integrated with DL prediction models and optimization libraries. Results show that HVAC energy cost can be reduced by up to 36% while indirectly also reducing the peak-to-average (PAR) and the aggregated net load by up to 9.97%.

Advancing fluid identification via well-logging data: Leveraging persistent initialization and transformer modeling

In the domain of energy exploration, the forecasting of fluid via well logging is pivotal in directing exploration endeavors. Understanding the composition of fluid underground is key for exploration teams to accurately determine the size, potential reserves, and quality of oil and gas resources. This knowledge is critical in refining exploration tactics and employing resources wisely. We present a novel machine learning architecture termed “PIFormer” for predicting fluid. This design merges Persistence Initialization with a Transformer module. The combination of persistent initialization and Transformer modules is achieved by using the persistent initialization feature representation as input to the Transformer model. Persistent initialization provides a stable starting point, enabling the Transformer model to converge to effective feature representations more rapidly during the learning process. This combination helps address issues in existing methods such as training instability, slow convergence, and local optima problems caused by random initialization. By integrating persistent initialization and the Transformer model, prior knowledge and global information can be more effectively utilized, enhancing the accuracy and robustness of fluid identification. Compared to existing models, the combination of persistent initialization and the Transformer model demonstrates higher accuracy and robustness in fluid identification tasks. Specifically, our approach achieves significant improvements in fluid identification accuracy and outperforms existing models across various types of fluid identification problems. Additionally, our method significantly reduces model training time and improves convergence speed. These results clearly indicate that the combination of persistent initialization and the Transformer model effectively addresses limitations in existing models for fluid identification tasks, providing new avenues and methods for further research and application in this field.

A novel structure learning method of Bayesian networks based on the neighboring complete node ordering search

Learning the optimal structure of a Bayesian network (BN) from observational data has received considerable research attention. In most structure learning methods based on scoring and searching, the discrete space of BNs is used, and the scale of the network grows exponentially with the number of nodes n, that is, O(n!2Cn2). Any existing scoring function in the BN space has multiple peaks. Thus, when using heuristic algorithms, local optimum problems may occur while searching in this space. As the search process involves only a small part of the space, the final learning result is not always ideal. In this study, the scoring and searching task is implemented in the complete node ordering space, and a novel neighbor operation is proposed for improving learning accuracy. This technique reduces the search space to O(n!) and facilitates optimized learning of a structure. Furthermore, techniques for efficiency optimization are proposed, which address the problems of high computational complexity and repetitive calculation of family scores.

Enhancing Lung Nodule Classification: A Novel CViEBi-CBGWO Approach with Integrated Image Preprocessing.

Cancer detection and accurate classification pose significant challenges for medical professionals, as it is described as a lethal illness. Diagnosing the malignant lung nodules in its initial stage significantly enhances the recovery and survival rates. Therefore, a novel model named convolutional vision Elman bidirectional-based crossover boosted grey wolf optimization (CViEBi-CBGWO) has been proposed to enhance classification accuracy. CT images selected for further preprocessing are obtained from the LUNA16 dataset and LIDC-IDRI dataset. The data undergoes preprocessing phases involving normalization, data augmentation, and filtering to improve the generalization ability as well as image quality. The local features within the preprocessed images are extracted by implementing the convolutional neural network (CNN). For extracting the global features within the preprocessed images, the vision transformer (ViT) model consists of five encoder blocks. The attained local and global features are combined to generate the feature map. The Elman bidirectional long short-term memory (EBiLSTM) model is applied to categorize the generated feature map as benign and malignant. The crossover operation is integrated with the grey wolf optimization (GWO) algorithm, and the combined form of CBGWO fine-tunes the parameters of the CViEBi model, eliminating the problem of local optima. Experimental validation is conducted using various evaluation measures to assess effectiveness. Comparative analysis demonstrates a superior classification accuracy of 98.72% in the proposed method compared to existing methods.

A path planning method for unmanned aerial vehicle based on improved wolf pack algorithm

SummaryIn the rapidly developing field of unmanned aerial vehicle (UVA) technology, solving local optimal problems and achieving efficient smooth planning are crucial for improving the operational efficiency and safety of UVA systems. To address these needs, our study introduces a novel optimization algorithm, called IWPA‐APF, which aims to improve path planning efficiency. This algorithm is a fusion of the artificial potential field (APF) method and the improved wolf‐pack algorithm (IWPA) to solve common problems such as local optima and inefficient planning in the path planning process. The IWPA‐APF algorithm improves search efficiency and accuracy by incorporating an adaptive step size that significantly refines the key behaviors of the traditional IWPA, which is based on the wolf pack algorithm (WPA). In addition, the algorithm incorporates specific planning constraints, such as turn angles and tolerance limits, to minimize getting stuck in local optima. The process involves generating initial plans through multiple iterations of the IWPA, followed by further refinement using the method of integrating APF's repulsive force field. Simulation results show that the IWPA‐APF algorithm outperforms traditional methods, offering shorter flight distances and improved safety, thereby establishing itself as a robust solution for UAV path planning in obstacle‐rich environments.

Weakly Supervised Few-Shot Object Detection with DETR

In recent years, Few-shot Object Detection (FSOD) has become an increasingly important research topic in computer vision. However, existing FSOD methods require strong annotations including category labels and bounding boxes, and their performance is heavily dependent on the quality of box annotations. However, acquiring strong annotations is both expensive and time-consuming. This inspires the study on weakly supervised FSOD (WS-FSOD in short), which realizes FSOD with only image-level annotations, i.e., category labels. In this paper, we propose a new and effective weakly supervised FSOD method named WFS-DETR. By a well-designed pretraining process, WFS-DETR first acquires general object localization and integrity judgment capabilities on large-scale pretraining data. Then, it introduces object integrity into multiple-instance learning to solve the common local optimum problem by comprehensively exploiting both semantic and visual information. Finally, with simple fine-tuning, it transfers the knowledge learned from the base classes to the novel classes, which enables accurate detection of novel objects. Benefiting from this ``pretraining-refinement'' mechanism, WSF-DETR can achieve good generalization on different datasets. Extensive experiments also show that the proposed method clearly outperforms the existing counterparts in the WS-FSOD task.

The study on mechanical model considering optimal self-adaption in the bottleneck area

It aims to solve the problem that the evacuation state of pedestrians depicted by the traditional social force model in a crowded multiexit scenario has a relatively large difference with the actual state, especially the 'optimal path' considered by the self-driving force is the problem of shortest path, and the multiexit evacuation mode depicted by the 'herd behavior' is the local optimum problem. Through in-depth analysis of actual evacuation data of pedestrians and causes of problem, a new crowd evacuation optimization model is established in order to effectively improve the simulation accuracy of crowd evacuation in a multi-exit environment. The model obtains the direction of motion of pedestrians using a field model, fully considers the factors such as exit distance, distribution of pedestrians and regional crowding degree, makes a global optimization for the self-driving force in the social force model using a centralized and distributed network model, and makes a local optimization for it using an elephant herding algorithm, so as to establish a new evacuation optimization method for optimal self-adaption in the bottleneck area. The performance status is compared between the improved social force model and the new model by experiments, and the key factors that affect the new model are analyzed in an in-depth manner. The results show that the new model can optimize the optimal path choice at the early stage of evacuation and improve the evacuation efficiency of pedestrians at the late stage, so as to ensure relatively even distribution of pedestrians at each exit, and also make the simulated evacuation process be more real; and the improvement in overall evacuation efficiency is greater when the number of pedestrians to be evacuated is larger. Therefore, the new model provides a method to solve the phenomenon of disorder in overall pedestrian evacuation due to excessive crowd density during the process of multi-exit evacuation.

Multi-UAV DMPC Cooperative Guidance with Constraints of Terminal Angle and Obstacle Avoidance

This paper studies the salvo attack problem for multiple unmanned aerial vehicles (UAVs) against a maneuvering target, and a guidance scheme based on distributed model predictive control (DMPC) is presented to achieve cooperative interception with constraints of terminal impact angle and no-fly zone (or obstacle) avoidance. Firstly, for guaranteeing the synchronization of UAVs in calculating their acceleration commands, the assumed predictive trajectories are introduced, whose deviation from the actual state trajectories is limited by the designed compatibility constraints. Secondly, based on the velocity-obstacle model, the obstacle avoidance constraints are presented, and for guaranteeing the convergence of impact time and impact angles, the auxiliary controller and terminal ingredients are developed, which complete the design of DMPC cooperative guidance scheme. Subsequently, the rigorous proof for the convergence of the proposed guidance scheme is provided. Based on the above design, a complete implementation process of the guidance scheme is presented, in which each UAV uses the particle swarm optimization algorithm to solve the preprocessed local optimization problem, and only the shared information among neighbors is utilized for calculation. Finally, the numerical simulations are conducted under diverse cases, which demonstrate the effectiveness of the proposed guidance scheme when solving cooperative interception problems with terminal angle and obstacle avoidance constraints.

A multi-objective optimization model for medical waste recycling network design under uncertainties

Transporting medical waste (MW) generated by medical institutions (MIs) is a process that poses potential threats to the environment and public safety. Therefore, it is vital to find a safe and efficient way to transport this type of waste to disposal centers (DCs). However, there are challenges in the transportation of MW due to random factors such as the generation of waste in an unpredictable manner and unforeseen travel times. In this paper, we propose a bi-level optimization model to minimize site selection costs, transportation costs, time-window penalties costs, and transportation risks under uncertainties. The concepts of “loading reliability”, “travel time reliability” and “transportation risk” are adopted in the proposed optimization model. The simulated annealing algorithm (SA) is employed to address the optimal location problem (Upper level), which involves minimizing the construction cost, transportation cost (DC-CP-DC), and transportation risk (estimated using Bayesian method). To tackle the capacity-constrained vehicle routing problem considering transportation risk and time window penalties (Lower level), we propose an improved genetic algorithm named harmony search algorithm (IHSGA). Subsequently, the results from the lower level are looped back to the upper level, fostering mutual influence between the two stages. We demonstrate the effectiveness and correctness of the proposed model and algorithm using S city in China as an illustrative example. Furthermore, a series of sensitivity analyses were conducted to examine the impact of various factors. The findings highlight the pivotal roles of both travel time reliability and loading reliability in designing the medical waste recycling network. In comparison to the general Genetic Algorithm (GA) and CPLEX solver, the modified IHSGA presented in this paper exhibits superior performance.

Hydrogen refueling station location optimization under uncertainty

Hydrogen refueling stations (HRS) are essential for the growth of the hydrogen energy and fuel cell vehicle industry, making the strategic decision of their location and scale critical. This study advances the HRS location optimization problem by integrating network planning and hydrogen scheduling optimization, a novel approach that addresses both where and how big HRSs should be, alongside managing supply relations and hydrogen transportation scheduling. Uniquely, it incorporates uncertainty factors in hydrogen demand, using a two-stage multi-period stochastic programming model designed to minimize both construction and operational costs under variable demand scenarios, while also ensuring customer satisfaction. Our main contributions include the development of this comprehensive model and the introduction of an efficient metaheuristic algorithm to solve it, significantly enhancing computational efficiency. The effectiveness of our approach is demonstrated through numerical experiments, and a sensitivity analysis provides crucial insights, underlining the practical implications for HRS infrastructure development. The findings not only offer a methodological advancement in HRS location selection but also deliver tangible results that can guide industry stakeholders in strategic decision-making, marking a significant step forward in the sustainable development of hydrogen energy infrastructure.

Collision-free path planning for cable-driven continuum robot based on improved artificial potential field

AbstractContinuum robot has become a research hotspot due to its excellent dexterity, flexibility and applicability to constrained environments. However, the effective, secure and accurate path planning for the continuum robot remains a challenging issue, for that it is difficult to choose a suitable inverse kinematics solution due to its redundancy in the confined environment. This paper presents a collision-free path planning method based on the improved artificial potential field (APF) for the cable-driven continuum robot, in which the beetle antennae search algorithm is adopted to deal with the optimal problem of APF without the necessary for velocity kinematics. In addition, the local optimum problem of traditional APF is solved by the randomness of the antennae’s direction vector which can make the algorithm easily jump out of local minima. The simulation and experimental results verify the efficiency of the proposed path planning method.

Autonomous High-Speed Overtaking of Intelligent Chassis Using Fast Iterative Model Predictive Control

High-speed overtaking is one of the structured driving scenarios of autonomous vehicles (AVs), and safety and real-time control requirements must be fulfilled during this scenario. In this work, we develop an overtaking path-planning and tracking framework for AVs based on the improved artificial potential field (APF) and fast iterative model predictive control (MPC). The improved APF is used to plan a feasible, high-speed overtaking path by considering the constraints of vehicle dynamics and introducing the adjustment factor into the potential function to avoid local optimization and target unreachability problems. In addition, to reduce the computational burden and fulfill the real-time control requirements of trajectory tracking, a fast iterative MPC algorithm is proposed herein. This algorithm adds disturbances that possess the nonlinear characteristics of the real model by using a linearized model. In terms of vehicle configuration, we consider that the target vehicle has the four-wheel steer (4WS)-four-wheel drive (4WD) chassis configuration and the fast iterative MPC is also used to coordinate the conflict between 4WS and direct yaw moment control (DYC) to improve tracking accuracy and vehicle stability during overtaking. Simulink/Carsim co-simulation and hardware-in-the-loop (HIL) tests are conducted to verify the effectiveness of the proposed controller.