Design Optimization of Bionic Liquid Cooling Plate Based on PSO-BP Neural Network Surrogate Model and Multi-Objective Genetic Algorithm

To improve the simulation accuracy of disease prediction model, a modified hybrid algorithm combining BP neural network (BPNN) with particle swarm optimization (PSO) algorithm based on chaos theory optimization is proposed considering BPNN is easy to fall into the local extremum. The chaos theory is used to optimize PSO algorithm to overcome the premature convergence of the traditional PSO algorithm. Then, the improved CAPSO algorithm is used to train the BPNN, to make full use of the global search characteristic of PSO algorithm and the local search ability of BPNN. The fitness function of the PSO algorithm is used as the energy function, and the optimization method of the improved hybrid algorithm is selected according to the specified number of evolution. An optimized network model was used to predict the prevalence of coronary heart disease. Compared with other algorithms such as BP neural network, the results show that the proposed algorithm has high accuracy and can significantly improve the quality of prediction.

Particle swarm optimization (PSO) can be interpreted physically as a particular discretization of a stochastic damped mass-spring system. Knowledge of this analogy has been crucial to derive the PSO continuous model and to introduce different PSO family members including the generalized PSO (GPSO) algorithm, which is the generalization of PSO for any time discretization step. In this paper, we present the stochastic analysis of the linear continuous and generalized PSO models for the case of a stochastic center of attraction. Analysis of the GPSO second order trajectories is performed and clarifies the roles of the PSO parameters and that of the cost function through the algorithm execution: while the PSO parameters mainly control the eigenvalues of the dynamical systems involved, the mean trajectory of the center of attraction and its covariance functions with the trajectories and their derivatives (or the trajectories in the near past) act as forcing terms to update first and second order trajectories. The similarity between the oscillation center dynamics observed for different kinds of benchmark functions might explain the PSO success for a broad range of optimization problems. Finally, a comparison between real simulations and the linear continuous PSO and GPSO models is shown. As expected, the GPSO tends to the continuous PSO when time step approaches zero. Both models account fairly well for the dynamics (first and second order moments) observed in real runs. This analysis constitutes so far the most realistic attempt to better understand and approach the real PSO dynamics from a stochastic point of view.

To propose a CT scanner tube fault diagnosis method based on a BP neural network optimized by particle swarm optimization (PSO) algorithm for identifying typical faults such as filament open circuit, filament half open circuit, scanning noise and arc discharge. Key parameters such as anode voltage, current, tube temperature, scanning time, and current fluctuation amplitude are selected, and the data set is constructed based on 357 sets of fault samples, which are divided into training set and test set. PSO is used to optimize the initial weights and thresholds of BP neural network, and PSO-BP model is constructed for fault classification. The classification accuracies of the model on the training and test sets are 96.25% and 92.31%, respectively, and the Pearson correlation coefficients of each fault type range from 0.894 to 0.971, indicating a strong linear relationship between the fault features and categories. Compared with the traditional methods, the PSO-BP model has obvious advantages in terms of accuracy and robustness. PSO-based BP neural network can effectively improve the diagnostic performance of typical faults of CT bulb tube, which has a good application prospect and provides a new method for the intelligent diagnosis of CT equipment.

Considering that the global navigation satellite system (GNSS) has the influence of positioning and atmospheric signals from time to time in meteorology, errors caused by moisture, and so on in the effect of the propagation path, these factors have led to the influence of various indexes of meteorological factors. In this study, a meteorological prediction algorithm based on the CNSS and particle swarm optimization is proposed. Aiming at the phenomenon that the particle swarm optimization (PSO) algorithm is prone to slow convergence speed and low optimization accuracy and there is a local optimal but cannot achieve the global optimal, an adaptive Kent chaotic map PSO algorithm is proposed. Through the comprehensive analysis of the meteorological input indicators in the GNSS, a noncurrent weight evaluation system is proposed. Under different evaluation systems, the PSO algorithm is applied, and PCA weight can obtain the best prediction effect. Then, the GA model, PSO model, and ADPSO model are used to predict PM2.5 index in meteorology. The results show that the proposed ADPSO algorithm has a good performance in RMSE, MAE, and R2 model evaluation.

In this article, an optimization procedure of composite structures is proposed and applied to a vehicle subframe redesign. The process is divided into two stages and surrogate models are built by Gaussian Process Regression. The modified Fast Flexible Filling designs is used to deal with the non-rectangular design region problem. And combined with the adaptive sampling method, uniform training and test points which increase the accuracy of surrogate models are obtained. The two established surrogate models are solved by non-dominated sorting genetic algorithm-II and particle swarm optimization algorithm, respectively. The redesigned subframe exhibits significantly weight reduction and performance improvement.

Three-dimensional numerical investigation on flow and heat transfer characteristics and multi-objective optimization of interconnected microchannels

A hierarchical multiscale off-road mobility model is enhanced through the development of an artificial neural network (ANN) surrogate model that captures the complex material behavior of deformable terrain. By exploiting the learning capability of neural networks, the incremental stress and strain relationship of granular terrain is predicted by the ANN representative volume elements (RVE) at various states of the stress and strain. A systematic training procedure for ANN RVEs is developed with a virtual tire test rig model for producing training data from the discrete-element (DE) RVEs without relying on computationally intensive full vehicle simulations on deformable terrain. The ANN surrogate RVEs are then integrated into the hierarchical multiscale computational framework as a lower-scale model with the scalable parallel computing capability, while the macroscale terrain deformation is described by the finite element (FE) approach. It is demonstrated with several numerical examples that off-road vehicle mobility performances predicted by the proposed FE-ANN multiscale terrain model are in good agreement with those of the FE-DE multiscale model while achieving a substantial computational time reduction. The accuracy and robustness of the ANN RVE for fine-grain sand terrain are discussed for scenarios not considered in training datasets. Furthermore, a drawbar pull test simulation is presented with the ANN RVE developed with data in the cornering scenario and validated against the full-scale vehicle test data. The numerical results confirm the predictive ability of the FE-ANN multiscale terrain model for off-road mobility simulations.

Complex system design problems tend to be high dimensional and nonlinear, and also often involve multiple objectives and mixed-integer variables. Heuristic optimization algorithms have the potential to address the typical (if not most) characteristics of such complex problems. Among them, the Particle Swarm Optimization (PSO) algorithm has gained significant popularity due to its maturity and fast convergence abilities. This paper seeks to translate the unique benefits of PSO from solving typical continuous single-objective optimization problems to solving multi-objective mixed-discrete problems, which is a relatively new ground for PSO application. The previously developed Mixed-Discrete Particle Swarm Optimization (MDPSO) algorithm, which includes an exclusive diversity preservation technique to prevent premature particle clustering, has been shown to be a powerful single-objective solver for highly constrained MINLP problems. In this paper, we make fundamental advancements to the MDPSO algorithm, enabling it to solve challenging multi-objective problems with mixed-discrete design variables. In the velocity update equation, the explorative term is modified to point towards the non-dominated solution that is the closest to the corresponding particle (at any iteration). The fractional domain in the diversity preservation technique, which was previously defined in terms of a single global leader, is now applied to multiple global leaders in the intermediate Pareto front. The multi-objective MDPSO (MO-MDPSO) algorithm is tested using a suite of diverse benchmark problems and a disc-brake design problem. To illustrate the advantages of the new MO-MDPSO algorithm, the results are compared with those given by the popular Elitist Non-dominated Sorting Genetic Algorithm-II (NSGA-II).

To resolve the problem of short-term power load forecasting, we propose a self-adapting particle swarm optimization (PSO) algorithm to optimize the error back propagation (BP) neural network model. The proposed model is called PSO-BP model which employs PSO to adjust control parameters of BP neural network. In order to verify the performance of PSO-BP, the practical datum of a city in China are selected in the experiments. Simulation results show that our approach outperforms simple BP neural network.

The particle swarm optimization (PSO) algorithm presents a new way for finding optimal solutions of complex optimization problems. In this paper a modified particle swarm optimization algorithm is presented. We modify the PSO algorithm in some aspects. Firstly, a contractive factor is introduced to the position update equation, and the particles are limited in search region. A new strategy for updating velocity is then adopted, in which the velocity is weakened linearly. Thirdly, using an idea of intersecting two modified PSO algorithms. Finally, adding an item of integral control in the modified algorithm can improve its global search ability. Based on these strategies, we proposed a new PSO algorithm named crossed PSO algorithm. Simulation results show that the crossed PSO is superior to the original PSO algorithm and can get overall promising performance over a wide range of problems.

To solve the strong randomicity and slow convergence of the Particle Swarm Optimization(PSO) algorithms, two new particle’s position renewal formulas were analyzed on the basis of extrapolation in mathematics. A new modified PSO algorithms (called Leading PSO algorithms) was put forward. The Direct Torque Control(DTC) System was built in the environment of Matlab(Simulink). The weight and threshold values of BP Neural Network were trained using the modified PSO algorithms. Some disadvantages such as slow convergence speed and easily plunging into the local solution were avoided effectively. The simulation result shows that the system works well, and the rotor speed identifier has great static and dynamic performance.

In axial compressor blade design optimization research, the surrogate model serves as a critical tool for performance prediction, but its construction often incurs high computational costs. To reduce surrogate model construction costs while ensuring prediction accuracy, this study proposes a primary-auxiliary composite neural network surrogate model based on flow field extraction. During model construction, extensive internal flow field data are extracted and employed to support model training, which enables efficient global optimization. To validate the proposed surrogate model, this study selects the Darmstadt transonic compressor (DTC) as the test case, sets the rotor blade sweep as the optimization variable, and targets increases in both the compressor stable operating range and the efficiency at the peak-efficiency point as the optimization objectives. The study employed the primary-auxiliary composite surrogate model with the non-dominated sorting genetic algorithm II (NSGA-II) to explore the Pareto frontier and execute aerodynamic performance optimization design. Results demonstrate that, under few-shot conditions, the prediction accuracy achieved using the primary-auxiliary composite surrogate model is 61.2% higher compared to directly constructed surrogate models. Optimization of the rotor blade sweep led to a reduction in tip leakage flow intensity, a downstream shift, and weakening of boundary layer separation at the lower blade span. While the design point efficiency experienced a minor increase, the stable operating range of the compressor expanded by 17.7%. This study verifies the applicability of the primary-auxiliary composite surrogate model to compressor blade profile optimization and provides a novel means to boost prediction accuracy under low-cost surrogate model constraints.

Control of thermal uniformity in microwave heating process by BPNN and adaptive particle swarm optimization

Collaborative beamforming in wireless sensor networks using a novel particle swarm optimization algorithm variant

Neural Network system for SoC is one topic in the world. Recently, SoC began to combine AI technique by Python. When developers consider Intelligent system on SoC, the co-design software and hardware are significant. In this case, small devices and embedded system are target system. For IoT, those techniques will grow up in the world. Those cases, avoiding premature convergence while keeping performance is a challenge in training the neural network, especially in a case of large NNs or a large number of training data. In this case, one problem is a huge memory and processing power. For tiny memory and processing system as SoC, we propose an improved particle swarm optimization (PSO) algorithm called the PSOseed2 algorithm for training NN. The PSOseed2 algorithm solves the premature convergence of the standard PSO (SPSO) algorithm by slightly modifying the velocity update function without adding many computational tasks to the SPSO algorithm. We evaluated this algorithm on field programmable gate array (FPGA)-based NN and software-based NN and trained these NNs with different PSO algorithms that are SPSO, PSOseed, PSOseed2, and dissipative PSO. Experimental results with different datasets confirmed that the NNs trained by the proposed PSOseed2 algorithm had better recognition rates and lower global learning errors than the NN trained by other PSO algorithms. In this talk, I would like to talk those relational research in the world and our results and discussion.