Because of their complex behavior, wastewater treatment processes (WWTPs) are very difficult to control. In this paper, the design and implementation of a nonlinear model-predictive control (NMPC) ...system are discussed. The proposed NMPC comprises a self-organizing radial basis function neural network (SORBFNN) identifier and a multiobjective optimization method. The SORBFNN with concurrent structure and parameter learning is developed as a model identifier for approximating the online states of dynamic systems. Then, the solution of the multiobjective optimization is obtained by a gradient method which can shorten the solution time of optimal control problems. Moreover, the conditions for the stability analysis of NMPC are presented. Experiments reveal that the proposed control technique gives satisfactory tracking and disturbance rejection performance for WWTPs. Experimental results on a real WWTP show the efficacy of the proposed NMPC for industrial processes in many applications.
An echo-state network (ESN) is an effective alternative to gradient methods for training recurrent neural network. However, it is difficult to determine the structure (mainly the reservoir) of the ...ESN to match with the given application. In this paper, a growing ESN (GESN) is proposed to design the size and topology of the reservoir automatically. First, the GESN makes use of the block matrix theory to add hidden units to the existing reservoir group by group, which leads to a GESN with multiple subreservoirs. Second, every subreservoir weight matrix in the GESN is created with a predefined singular value spectrum, which ensures the echo-sate property of the ESN without posterior scaling of the weights. Third, during the growth of the network, the output weights of the GESN are updated in an incremental way. Moreover, the convergence of the GESN is proved. Finally, the GESN is tested on some artificial and real-world time-series benchmarks. Simulation results show that the proposed GESN has better prediction performance and faster leaning speed than some ESNs with fixed sizes and topologies.
Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition ...accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time.
Air quality is currently arousing drastically increasing attention from the governments and populace all over the world. In this paper, we propose a heuristic recurrent air quality predictor (RAQP) ...to infer air quality. The RAQP exploits some key meteorology- and pollution-related variables to infer air pollutant concentrations (APCs), e.g. the fine particulate matter (PM2.5). It is natural that the meteorological factors and APCs at the current time have strong influences on air quality the next adjacent moment, that is to say, there exist high correlations between them. With this consideration, applying simple machine learners to the current meteorology- and pollution-related factors can reliably predict the air quality indices at a time later. However, owing to the nonlinear and chaotic reasons, the above correlations decline with the time interval enlarged. In such cases, it fails to forecast the air quality after several hours by only using simple machine learners and the current measurements of meteorology- and pollution-related variables. To solve the problem, our RAQP method recurrently applies the 1-h prediction model, which learns the current records of meteorology- and pollution-related factors to predict the air quality 1 h later, to then estimate the air quality after several hours. Via extensive experiments, results confirm that the RAQP predictor is superior to the relevant state-of-the-art techniques and nonrecurrent methods when applied to air quality prediction.
The real-time availability of key water quality parameters is of great importance for an advanced and optimized process control in wastewater treatment plants (WWTPs). However, due to the complex ...environment conditions and costly measuring instruments, it is generally difficult and time-consuming to measure certain key water quality parameters online, such as the effluent biochemical oxygen demand (BOD) and the effluent total nitrogen (TN). Recently, artificial neural networks have powered the online prediction tasks in several WWTPs. Hence, in this paper, an adaptive task-oriented radial basis function (ATO-RBF) network is developed to design prediction models for accurate timely acquirements of the effluent BOD and the effluent TN. The advantage of ATO-RBF network is that the architecture is not designed by human engineers; it is adaptively generated from the data to be processed. First, to enhance the learning ability and generalization performance of prediction models, an error correction-based growing strategy and a second-order learning algorithm are combined to design the ATO-RBF network. Then, RFB nodes with low significance would be pruned without sacrificing the learning accuracy, making the prediction model more compact. Additionally, the convergence of the ATO-RBF network is analyzed based on the Lyapunov criterion, which can guarantee its feasibility in practical applications. Finally, the proposed methodology is verified by benchmark simulations and real industrial data, showing superior prediction accuracy in compared with conventional methods.
A novel growing-and-pruning (GP) approach is proposed, which optimizes the structure of a fuzzy neural network (FNN). This GP-FNN is based on radial basis function neurons, which have center and ...width vectors. The structure-learning phase and the parameter-training phase are performed concurrently. The structure-learning approach relies on the sensitivity analysis of the output. A set of fuzzy rules can be inserted or reduced during the learning process. The parameter-training algorithm is implemented using a supervised gradient decent method. The convergence of the GP-FNN-learning process is also discussed in this paper. The proposed method effectively generates a fuzzy neural model with a highly accurate and compact structure. Simulation results demonstrate that the proposed GP-FNN has a self-organizing ability, which can determine the structure and parameters of the FNN automatically. The algorithm performs better than some other existing self-organizing FNN algorithms.
Aiming at the complexity, nonlinearity and difficulty in modeling of nonlinear system. In this paper, an improved back-propagation(BP) neural network based on restricted boltzmann machine(RBM-IBPNN) ...is proposed for nonlinear systems modeling. First, the structure of BP neural network(BPNN) is optimized by using sensitivity analysis(SA) and mutual information(MI) of the hidden neurons. Namely when the SA value and the MI value of the hidden neurons satisfy the set standard, the corresponding neurons will be pruned, split or merged. second, the restricted boltzmann machine(RBM) is employed to perform parameters initialization of training on the IBPNN. Finally, the proposed RBM-IBPNN is evaluated on nonlinear system identification, lorenz chaotic time series prediction and the total phosphorus prediction problems. The experimental results demonstrate that the proposed RBM-IBPNN not only has faster convergence speed and higher prediction accuracy, but also realizes a more compact network structure.
This article devises a photograph-based monitoring model to estimate the real-time PM 2.5 concentrations, overcoming currently popular electrochemical sensor-based PM 2.5 monitoring methods' ...shortcomings such as low-density spatial distribution and time delay. Combining the proposed monitoring model, the photographs taken by various camera devices (e.g., surveillance camera, automobile data recorder, and mobile phone) can widely monitor PM 2.5 concentration in megacities. This is beneficial to offering helpful decision-making information for atmospheric forecast and control, thus reducing the epidemic of COVID-19. To specify, the proposed model fuses Information Abundance measurement and Wide and Deep learning, dubbed as IAWD, for PM 2.5 monitoring. First, our model extracts two categories of features in a newly proposed DS transform space to measure the information abundance (IA) of a given photograph since the growth of PM 2.5 concentration decreases its IA. Second, to simultaneously possess the advantages of memorization and generalization, a new wide and deep neural network is devised to learn a nonlinear mapping between the above-mentioned extracted features and the groundtruth PM 2.5 concentration. Experiments on two recently established datasets totally including more than 100 000 photographs demonstrate the effectiveness of our extracted features and the superiority of our proposed IAWD model as compared to state-of-the-art relevant computing techniques.
Multiobjective particle swarm optimization (MOPSO) algorithms have attracted much attention for their promising performance in solving multiobjective optimization problems (MOPs). In this paper, an ...adaptive MOPSO (AMOPSO) algorithm, based on a hybrid framework of the solution distribution entropy and population spacing (SP) information, is developed to improve the search performance in terms of convergent speed and precision. First, an adaptive global best (gBest) selection mechanism, based on the solution distribution entropy, is introduced to analyze the evolutionary tendency and balance the diversity and convergence of nondominated solutions in the archive. Second, an adaptive flight parameter adjustment mechanism, using the population SP information, is proposed to obtain the distribution of particles with suitable diversity and convergence, which can balance the global exploration and local exploitation abilities of the particles. Third, based on the gBest selection mechanism and the adaptive flight parameter mechanism, this proposed AMOPSO algorithm not only has high accuracy, but also attain a set of optimal solutions with better diversity. Finally, the performance of the proposed AMOPSO algorithm is validated and compared with other five state-of-the-art algorithms on a number of benchmark problems and water distribution system. The experimental results validate the effectiveness of the proposed AMOPSO algorithm, as well as demonstrate that AMOPSO outperforms other MOPSO algorithms in solving MOPs.
Long short-term memory (LSTM) neural network has been widely studied and applied in the real world. To obtain the LSTM neural network with better accuracy and more appropriate structure, the hybrid ...coding particle swarm optimization (HCPSO) algorithm is proposed. Firstly, the hybrid coding scheme is developed to represent the weights and structure of LSTM neural network, simultaneously. Then, the novel update mechanism is proposed to adjust the position of particles. Meanwhile, the discrete update strategy (DUS) and adaptive nonlinear moderate random search strategy (ANMRS) are proposed to enhance the convergence and global search capability of HCPSO, respectively. Finally, the effectiveness of HCPSO is demonstrated by multiple numerical examples. The experiment results show that the proposed HCPSO algorithm is more competitive in optimizing LSTM neural networks than other algorithms.