To solve the problem of high-energy consumption in activated sludge wastewater treatment, a reinforcement learning-based particle swarm optimization (RLPSO) was proposed to optimize the control setting in the sewage process. This algorithm tries to take advantage of the valid history information to guide the behavior of particles through a reinforcement learning strategy. First, an elite network is constructed by selecting elite particles and recording their successful search behavior. Then the network is trained and evaluated to effectively predict the particle velocity. In the periodic wastewater treatment process, the RLPSO runs repeatedly according to the optimized cycle. Finally, RLPSO was tested based on Benchmark Simulation Model 1 (BSM1) of sewage treatment, and the simulation results showed that it could effectively reduce the energy consumption on the premise of ensuring qualified water quality. Furthermore, the performance of RLPSO was analyzed using the benchmarks with higher dimension, which verifies the effectiveness of the algorithm and provides the possibility for RLPSO to be applied to a wider range of problems.
Surface electromyography (sEMG) is a kind of valuable bioelectric signal and very potential in the field of human–machine interaction. Ideal interactions require sEMG based patterns recognition not only with high accuracy but also with good rapidity. However, too much real-time feature-related computation will greatly slow down the interaction, especially for multichannel sEMG. To decrease the feature-related time consumption, the paper formulates the feature reduction as an optimization problem, and develops a double-phases particle swarm optimization (PSO) with hybrid coding to solve the problem. In the research, the initial feature data set with 31 kinds of feature is built firstly based on eight subjects’ 16 channels forearm sEMG signals, then PSO is introduced to conduct the feature reduction of 31 × 16 dimensions through the feature and channel optimization in double phases. During the optimization, two improved k-nearest neighbor (KNN) methods such as weighted representation based KNN (WRKNN) and weighted local mean representation based KNN (WLMRKNN) are introduced to classify the gestures, and the classification accuracy is used to evaluate the particles of PSO. Experimental results and comparison analysis show that PSO based feature reduction methods outperform genetic algorithm (GA), ant colony optimization (ACO) and principal component analysis (PCA) based feature reduction methods. With the optimized feature data subset by PSO, WRKNN and WLMRKNN are superior to KNN, quadratic discriminant analysis (QDA), and naive bayes (NB) greatly. The proposed method can be applied in the pattern recognition of high dimensional sEMG with multichannel or high-density channels for the purpose of rapidity and without a decline of accuracy in real-time control. Further, it can be used to reduce the economic cost of the personalized customization equipment through the optimal channels for any subjects in the future.
Accurate measurement of key quality variables is of great significance for evaluating product quality and ensuring production safety. How to extract useful dynamic latent features from complex process data for effective quality prediction is still a difficult and hot topic in soft sensing modeling. The existing soft sensing models based on LSTM do not consider the correlation between hidden states of different time steps when extracting dynamic nonlinear features. To solve these problems, a novel bidirectional long short-term memory network with weighted attention mechanism (WA-BiLSTM) is proposed in this paper to improve the prediction performance for dynamic nonlinear industrial processes. In the WA-BiLSTM model, the bidirectional structure of BiLSTM is used to learn the dynamic information of the input sequence. A weighted attention mechanism layer is designed to dynamically extract the correlation information between the hidden states of different batches. In addition, the ratio between the historical hidden states and the current hidden state is adjusted reasonably by assigning adaptive parameters. Finally, the experimental results on a debutanizer column process and an IndPensim process demonstrate the effectiveness and superiority of the proposed method.
Data‐driven soft sensors are widely used to predict quality indices in propylene polymerization processes to improve the availability of measurements and efficiency. To deal with the nonlinearity and dynamics in propylene polymerization processes, a novel soft sensor based on quality‐relevant slow feature analysis and Bayesian regression is proposed in this paper. The proposed method can handle the dynamics of the process better by extracting quality‐relevant slow features, which present both the slowly varying characteristic and the correlations with quality indices. Meanwhile, a Bayesian inference model is developed to predict the quality indices, which takes advantages of a probability framework with iterative maximum likelihood techniques for parameter estimation and a sparse constraint for avoiding overfitting. Finally, a case study is conducted with data sampled from a practical industrial propylene polymerization process to demonstrate the effectiveness and superiority of the proposed method.
As a nondestructive testing (NDT) technology, pulsed thermography (PT) has been widely used in the defect detection of the composite products due to its efficiency and large detection range. To enhance the distinction between defective and defect-free region and eliminate the influence of the measurement noise and nonuniform background of the thermal image generated by PT, a number of thermographic data analysis approaches have been proposed. However, these traditional methods only consider the correlations among the pixel while leave the time series correlations unmodeled. In this paper, a sparse moving window principal component thermography (SMWPCT) method is proposed to incorporate several thermal images using the moving window strategy. Also, the sparse trick is used to provide clearer and more interpretable results because of the structure sparsity. The effectiveness of the method is verified by the defect detection experiment of carbon fiber-reinforced plastic specimens.
20 November 2023 in IEEE Robotics and Automation Letters
To enable mobile robots to safely and effectively accomplish path planning tasks on uneven terrains, this letter proposes a Gaussian adaptive strategy-based multi-objective evolutionary optimization. Firstly, path solutions are generated by employing spline interpolation on the digital elevation model of the terrain map. Subsequently, a multi-objective optimization function is constructed, considering parameters such as path length, uniformity, slope, and relief. These parameters are computed using the elevation values of the terrain. Secondly, an evolutionary optimization algorithm based on a Gaussian adaptive strategy is introduced. This strategy ensures the uniform distribution, adaptability, and size stability of the reference points set. Additionally, it controls the selection rate of non-dominant contribution points during the optimization process. Finally, experimental results conducted in five different real environments demonstrate the suitability of the proposed algorithm for solving path planning problems on uneven terrain.