It is difficult to accurately predict the response of some stochastic and complicated manufacturing processes. Data‐driven learning methods which can mine unseen relationship between influence parameters and outputs are regarded as an effective solution. In this study, support vector machine (SVM) is applied to develop prediction models for machining processes. Kernel function and loss function are Gaussian radial basis function and ε‐insensitive loss function, respectively. To improve the prediction accuracy and reduce parameter adjustment time of SVM model, artificial bee colony algorithm (ABC) is employed to optimize internal parameters of SVM model. Further, to evaluate the optimization performance of ABC in parameters determination of SVM, this study compares the prediction performance of SVM models optimized by well‐known evolutionary and swarm‐based algorithms (differential evolution (DE), genetic algorithm (GA), particle swarm optimization (PSO), and ABC) and analyzes ability of these optimization algorithms from their optimization mechanism and convergence speed based on experimental datasets of turning and milling. Experimental results indicate that the selected four evaluation indicators values that reflect prediction accuracy and adjustment time for ABC‐SVM are better than DE‐SVM, GA‐SVM, and PSO‐SVM except three indicator values of DE‐SVM for AISI 1045 steel under the case that training set is enough to develop the prediction model. ABC algorithm has less control parameters, faster convergence speed, and stronger searching ability than DE, GA, and PSO algorithms for optimizing the internal parameters of SVM model. These results shed light on choosing a satisfactory optimization algorithm of SVM for manufacturing processes.
Stock market performance is one key indicator of the economic condition of a country, and stock price forecasting is important for investments and financial risk management. However, the inherent nonlinearity and complexity in stock price movements imply that simple conventional modeling techniques are not adequate for stock price forecasting. In this paper, we present a hybrid model (ARIMA + GPRC) which combines the autoregressive integrated moving average (ARIMA) model and Gaussian process regression (GPR) with a combined covariance function (GPRC). The proposed hybrid model can account for both the linearity and nonlinearity in stock price movements. Based on daily data on three stocks listed on the Shanghai Stock Exchange (SSE), it is found that GPRC outperforms GPR with a single covariance function. Further, the proposed hybrid model is compared with the ARIMA model, artificial neural network (ANN), and GPRC model. Based on the forecasting trend and the statistical performance of the four models, the ARIMA + GPRC model is found to be the dominant model for stock price forecasting and can significantly improve forecasting performance.
Under the impetus of green manufacturing and a low-carbon economy, the critical challenge lies in reducing energy consumption while maintaining machining quality. Against this background, this paper presents the method of modeling and effect analysis for surface roughness and specific energy consumption during TC18 machining using Deep Reinforcement Learning and Neural Networks. In this method, to reduce the experiment cost, multilayer-layer design (MLD) for computer simulation is applied to design a physical experiment, and to improve modeling accuracy, backpropagation neural network (BPNN) optimized by Double deep Q network algorithm (DDQN) is utilized to develop the prediction models of surface roughness (Ra) and specific energy consumption of cutting (Esec). Finaly, the synergistic influence of cutting parameters on Ra and Esec is analyzed based on the prediction models of Ra and Esec built by MLD and DDQN-BPNN. The effectiveness and low cost of MLD and the excellent prediction performance of DDQN-BPNN are verified by comparisons of optimized BPNNs using common heuristic optimization algorithms through the milling experiment of TC18. These technologies provide effective solutions for modeling and factor impact of target features in machining field, and research results provides an effective guidance for the selection of milling parameters of TC18 to reduce the specific energy consumption of cutting under ensuring or improving machining quality.
To address the issues of workpiece distortion and excessive material melting caused by heat accumulation during laser cutting of thin-walled sheet metal components, this paper proposes a segmented optimization method for process parameters in sheet metal laser cutting considering thermal effects. The method focuses on predetermined perforation points and machining paths. Firstly, an innovative temperature prediction model is established for the nth perforation point during the cutting process, with a prediction error of less than 10%. Secondly, using the PSO-BP-constructed prediction model for laser cutting quality features and an empirical model for processing efficiency features, a multi-objective model for quality and efficiency is generated. The NSGA II algorithm is employed to solve the objective optimization model and obtain the Pareto front. Next, based on the predicted temperature at the perforation point using the model , the TOPSIS decision-making method is applied. Different weights for quality and efficiency are set during the cutting stages where the temperature is below the lower threshold and above the upper threshold. Various combinations of machining parameters are selected, and by switching the parameters during the cutting process, the thermal accumulation (i.e., temperature) during processing is controlled within a given range. Finally, the effectiveness of the proposed approach is verified through actual machining experiments.
21 November 2022 in The International Journal of Advanced Manufacturing Technology