Surrogate models have shown to be effective in assisting metaheuristic algorithms for solving computationally expensive complex optimization problems. The effectiveness of existing surrogate-assisted algorithms, however, has only been verified on low-dimensional In this paper, a cooperative swarm algorithm is proposed, which particle (PSO) and social learning-based PSO (SL-PSO) cooperatively search the global optimum. cooperation between SL-PSO consists two aspects. First, they share...

Conventional evolutionary algorithms (EAs) are not well suited for solving expensive optimization problems due to the fact that they often require a large number of fitness evaluations obtain acceptable solutions. To alleviate difficulty, this paper presents multitasking framework computationally problems. In framework, knowledge is transferred from cheap help solution problem on basis recently proposed multifactorial EA (MFEA), leading faster convergence problem. However, existing MFEAs do...

Gaussian processes (GPs) are the most popular model used in surrogate-assisted evolutionary optimization of computationally expensive problems, mainly because GPs able to measure uncertainty estimated fitness values, based on which certain infill sampling criteria can be guide search and update surrogate model. However, computation time for constructing may become excessively long when number training samples increases, makes it inappropriate use them as surrogates optimization. To address...

Gaussian processes (GPs) are widely used in surrogate-assisted evolutionary optimization of expensive problems mainly due to the ability provide a confidence level their outputs, making it possible adopt principled surrogate management methods, such as acquisition function Bayesian optimization. Unfortunately, GPs become less practical for high-dimensional multiobjective and many-objective computational complexity is cubic number training samples. In this article, we propose computationally...

This paper is concerned with the trajectory tracking control problem for wheeled mobile robots (WMRs) subject to actuator faults. The challenge lies in partial loss of effectiveness actuated wheels which results strong controllability WMR, rendering classical fault-tolerant methods infeasible. To overcome this obstacle, a novel mixed-gain adaption technique put forward and skillfully combined robust prescribed performance method. resulting achieves WMR predefined settling time accuracy,...

The recent financial crisis and other major crises have suggested that there are some strong interactions interdependence between several supply chains their external environments in various ways. A set of interdependent is called a holistic chain network (H-SCN) this paper. There need to focus on building the resilience (in short, ability system recover from damage or disruption) an entire H-SCN as it believed such strongly relevant economic recession triggered by crises. objectives paper...

To promote research on dynamic constrained multiobjective optimization, we first propose a group of generic test problems with challenging characteristics, including different modes the true Pareto front (e.g., convexity-concavity and connectedness-disconnectedness) changing feasible region. Subsequently, motivated by challenges presented dynamism constraints, design optimization algorithm nondominated solution selection operator, mating strategy, population change detection method, response...

This paper presents a robust event-triggered model predictive control (MPC) strategy for multiple high-speed trains (MHSTs) with random switching topologies. Due to the complicated operation environment of railways, communication topology MHSTs system is time-varying and changes among set directed graphs, which can be characterized as Markov chain. By adopting concept MPC, this studies distributed cooperative leader-following consensus MHSTs, in novel introduced determine when information...

Operational indices optimization is crucial for the global in beneficiation processes. This paper presents a multitasking multiobjective evolutionary method to solve operational optimization, which involves formulated multifactorial (MO-MFO) problem and proposed MFO algorithm solving established MO-MFO problem. The includes multiple level of accurate models are generated on basis data set collected from production. Among models, most one considered be original functions solved problem, while...

Obtaining accurate point prediction of industrial processes' key variables is challenging due to the outliers and noise that are common in data. Hence intervals (PIs) have been widely adopted quantify uncertainty related prediction. In order improve accuracy level associated with prediction, this article estimates PIs by using ensemble stochastic configuration networks (SCNs) bootstrap method. The estimated can guarantee both modeling stability computational efficiency. To encourage...

Information systems are a kind of service and they throughout every element modern industrial business system, much like blood in our body. Types information heterogeneous because extreme uncertainty changes systems. To effectively manage systems, modelling the work domain (or domain) is necessary. In this paper, framework for system proposed its application to enterprise outlined. The defined based on general tool called function-context-behaviour-principle-state-structure (FCBPSS). FCBPSS...

In offline data-driven optimization, only historical data is available for making it impossible to validate the obtained solutions during optimization. To address these difficulties, this paper proposes an evolutionary algorithm assisted by two surrogates, one coarse model and fine model. The surrogate (CS) aims guide quickly find a promising subregion in search space, whereas focuses on leveraging good according knowledge transferred from CS. Since Pareto optimal have not been validated...

It is challenging to develop point prediction models with high accuracy due that outliers and noise are commonly present in the real-world data. In this context, article proposes a novel robust stochastic configuration network (SCN) uses bootstrap ensemble strategy construct intervals (PIs). Since output weights of original SCN computed by least-squares method, which sensitive an unknown distribution or outliers, based on mixture Gaussian Laplace distributions (MoGL-SCN) Bayesian framework...

Rougher flotation, composed of unit processes operating at a fast time scale and economic performance measurements known as operational indices measured slower scale, is very basic the first concentration stage for flotation plants. Optimizing process rougher circuits extremely important due to high profit arising from optimality indices. This paper presents novel off-policy Q-learning method learn optimal solution without knowledge dynamics To this end, first, control dual-rate formulated....

This paper provides a method for automatically selecting optimal operational indices unit processes in an industrial plant using measured data and without knowing dynamical models of the process. A dynamic multiobjective optimization problem is defined to find that lead plant-wide production close their target values. case-based reasoning (CBR) technique also employed, which uses stored experience human expert determine appropriate given indices. The solutions CBR are combined form baseline...

This article presents a novel technique to achieve plant-wide performance optimization for large-scale unknown industrial processes by integrating the reinforcement learning method with multiagent game theory. A main advantage of this is that optimal achieved distributed approach where multiple agents solve simplified local nonzero-sum problems so global Nash equilibrium reached. To end, first, problem reformulated decomposition into subproblems each production index in framework. Then,...

As an essential component in multi- and many-objective optimization, decision-making process either selects a subset of solutions from the whole Pareto front or guides search toward small part during evolutionary process. In recent years, for optimization problems (MaOPs), number algorithms have been developed to optimal solutions. However, there is lack research works focusing on designing approaches. order overcome this deficiency, we propose novel knee-based method several interest (SOIs)...

For dynamic multiobjective optimization problems (DMOPs), it is challenging to track the varying Pareto-optimal front. Most traditional approaches estimate sets in decision space. However, obtained solutions do not necessarily satisfy desired properties of makers objective Inverse model-based algorithms have a great potential solve such problems. Nonetheless, existing ones low precision for handling DMOPs with nonlinear correlations between and vectors, which greatly limits application...

This article is concerned with the distributed optimal resource allocation problem local feasibility constraints for high-order multiagent systems (MASs) over weight-balanced digraphs. Generally, are addressed based on feasible direction, determined by some time-dependent discontinuous functions. impedes MASs, as resulting control signal yields challenges in explicit controller design. To overcome this problem, a novel integrated event-triggered strategy proposed article. It achieves outputs...