To comply with the effluent standards and growing demands for safety reliability, operation of wastewater treatment processes (WWTPs) has been considered as a multiobjective control problem. In this article, data-driven predictive (MOPC) method is developed to deal conflicting objectives improve performance WWTPs. The main contributions MOPC are three folds: first, strategy in design MOPC. And an adaptive fuzzy neural network identifier, using relevant process data, designed catch nonlinear...

The broad learning system (BLS) has been identified as an important research topic in machine learning. However, the typical BLS suffers from poor robustness for uncertainties because of its characteristic deterministic representation. To overcome this problem, a type-2 fuzzy (FBLS) is designed and analyzed article. First, group interval neurons was used to replace feature BLS. Then, representation can be improved obtain good robustness. Second, pseudoinverse algorithm adjust parameter FBLS....

Model predictive control (MPC) has been considered as a promising alternative for the of nonlinear systems. However, this controller suffers from challenge that it is difficult to deal with complex systems incomplete datasets. To solve problem, novel MPC, by utilizing knowledge-data-driven model (KDDM), designed and analyzed in article. In comparison existing literatures, MPC (KDD-MPC) contains these following contributions. First, systematic strategy developed reduce online computational...

Self-healing control plays a crucial role in taking remedial action to minimize the adverse impacts of sludge bulking wastewater treatment process (WWTP). However, since is strong nonlinear and complex with multiple fault conditions, conventional self-healing difficult obtain reliable performance. Thus, purpose this article design broad learning-based predictive controller (BL-SHPC) for WWTP. The main innovations proposed are threefold. First, dynamic fuzzy learning system an adaptive...

Decision making is essential to utilize the operation information of wastewater treatment process (WWTP) provide inhibition strategy for sludge bulking. However, since majority decision-making models focus solely on knowledge or data resources, avoiding interrelations and dependencies between information, these are difficult obtain comprehensive precise solutions. Thus, solve this problem, a knowledge-aided data-driven fuzzy (KD-FDM) model designed First, recursive reconstruction...

For high-resolution range profile (HRRP)-based radar automatic target recognition (RATR), adequate training data are required to characterize a signature effectively and get good performance. However, collecting enough involving HRRP samples from each orientation is hard. To tackle the HRRP-based RATR task with limited data, novel dynamic learning strategy proposed based on single-hidden layer feedforward network (SLFN) an assistant classifier. In offline phase, used for pretraining SLFN...

Extreme learning machine (ELM) is a fast algorithm for the single-hidden layer feedforward neural networks. However, usually we cannot guarantee stability of ELM because parameters are generated randomly, such as its biases hidden and connecting weights between input layer. Besides, it hard single model to achieve high predicted accuracy on dataset with low-quality data. In this paper, first propose modified residual (R-ELM) improve ELM's performance. R-ELM, trained by original m-th (m > 1)...

In practical applications, sampled-data systems are often affected by unforeseen physical constraints that may cause deviations in the sampling interval from expected value and result fluctuations a probabilistic way, where probability distribution of stochastic intervals is time-varying unknown. How to design stable tracking controller for control unknown challenging task. A model predictive (SSDMPC) strategy T-S fuzzy (TSFSs) proposed overcome this challenge. First, based on input delay...

For anti-active-interference-oriented cognitive radar systems, the mismatch between acquired and actual interference information may result in serious degradation of anti-active-interference performance. To yield more effective knowledge electromagnetic environment eliminate effect, activity prediction technique, which deduces future behaviors based on current observations, has received increasing attention. However, high computational complexities limit application conventional methods...

Fuzzy broad learning system is regarded as an effective algorithm to utilize the measured data for modeling nonlinear systems. However, due possible existence of inadequate or loss, it a challenge design suitable fuzzy with shortage issue modeling. Therefore, knowledge transfer-based developed in this paper. First, extracted from process used construct initial condition. Then, model can obtain precise parameter and structure. Second, evaluation mechanism employed rebuild by judging...