scholarly journals Online Tuning of PID controller using Black Box Multi-Objective Optimization and Reinforcement Learning

2018 ◽  
Vol 51 (32) ◽  
pp. 844-849
Author(s):  
Ashwad Pandit ◽  
Bipin Hingu
Keyword(s):  
Reinforcement Learning ◽  
Pid Controller ◽  
Black Box ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Online Tuning

Multiobjective Optimization for High Dimensional Expensively Constrained Black-Box Problems

2021 ◽  
pp. 1-59
Author(s):  
George Cheng ◽  
G. Gary Wang ◽  
Yeong-Maw Hwang
Keyword(s):  
Multiobjective Optimization ◽  
Trust Region ◽  
Adaptive Strategy ◽  
Black Box ◽  
Superior Performance ◽  
High Dimensional ◽  
Multi Objective Optimization ◽  
Semiconductor Substrate ◽  
Multi Objective ◽  
Computationally Expensive

Abstract Multi-objective optimization (MOO) problems with computationally expensive constraints are commonly seen in real-world engineering design. However, metamodel based design optimization (MBDO) approaches for MOO are often not suitable for high-dimensional problems and often do not support expensive constraints. In this work, the Situational Adaptive Kreisselmeier and Steinhauser (SAKS) method was combined with a new multi-objective trust region optimizer (MTRO) strategy to form the SAKS-MTRO method for MOO problems with expensive black-box constraint functions. The SAKS method is an approach that hybridizes the modeling and aggregation of expensive constraints and adds an adaptive strategy to control the level of hybridization. The MTRO strategy uses a combination of objective decomposition and K-means clustering to handle MOO problems. SAKS-MTRO was benchmarked against four popular multi-objective optimizers and demonstrated superior performance on average. SAKS-MTRO was also applied to optimize the design of a semiconductor substrate and the design of an industrial recessed impeller.

scholarly journals Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination Unit

Electronics ◽  
2019 ◽  
Vol 8 (2) ◽  
pp. 231 ◽  
Author(s):  
Panagiotis Kofinas ◽  
Anastasios I. Dounis
Keyword(s):  
Reinforcement Learning ◽  
Flow Rate ◽  
Pid Controller ◽  
Hybrid Control ◽  
Q Learning ◽  
State Action ◽  
Continuous State ◽  
Multi Agent ◽  
Flow Rate Control ◽  
Online Tuning

This paper proposes a hybrid Zeigler-Nichols (Z-N) fuzzy reinforcement learning MAS (Multi-Agent System) approach for online tuning of a Proportional Integral Derivative (PID) controller in order to control the flow rate of a desalination unit. The PID gains are set by the Z-N method and then are adapted online through the fuzzy Q-learning MAS. The fuzzy Q-learning is introduced in each agent in order to confront with the continuous state-action space. The global state of the MAS is defined by the value of the error and the derivative of error. The MAS consists of three agents and the output signal of each agent defines the percentage change of each gain. The increment or the reduction of each gain can be in the range of 0% to 100% of its initial value. The simulation results highlight the performance of the suggested hybrid control strategy through comparison with the conventional PID controller tuned by Z-N.

Multi-Objective Optimization and Parameter Tuning for Turbine PID Controller

2013 ◽  
Vol 779-780 ◽  
pp. 971-976
Author(s):  
Yuan Sheng Lin ◽  
Yong Li ◽  
Fei Fei Song ◽  
Da Wei Teng
Keyword(s):  
Decision Making ◽  
Pid Controller ◽  
Optimization Technique ◽  
Disturbance Attenuation ◽  
Subsequent Stage ◽  
Multi Objective Optimization ◽  
Pareto Solution ◽  
Acceptable Solution ◽  
Multi Objective ◽  
Multi Attribute Decision Making

The tuning of PID controller parameters is the most important task in PID design process. A new tuning method is presented for PID parameters, based on multi-objective optimization technique and multi-attribute decision making method. Three performances of a PID controller, i.e. the accurate set point tracking, disturbance attenuation and robust stability are studied simultaneously. These specifications are usually competitive and any acceptable solution requires a tradeoff among them. A hybrid approaches is proposed. In the first stage, a Non-dominated Sorting Genetic Algorithm II (NSGA II) is employed to approximate the set of Pareto solution through an evolutionary optimization process. In the subsequent stage, a multi-attribute decision making (MADM) approach is adopted to rank these solutions from best to worst and to determine the best solution in a deterministic environment with a single decision maker. The ranking of Pareto solution is based on entropy weight and TOPSIS method. A turbine PID design example is conducted to illustrate the analysis process in present study. The effectiveness of this universal framework is supported by the simulation results.

Multi-Objective Optimization Based Multi-Objective Controller Tuning Method with Robust Stabilization of Fractional Calculus CSTR

2021 ◽  
Vol 16 ◽  
pp. 375-382
Author(s):  
T. Sudha
Keyword(s):  
Decision Making ◽  
Fractional Order ◽  
Pid Controller ◽  
Genetic Evaluation ◽  
Performance Estimation ◽  
Multi Criteria Decision Making ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Flower Pollination ◽  
Fractional Order Pid

In Continuous Stirred Tank Reactor (CSTR) have Fractional order PID with the nominal order PID controller has been used to Multi-Criteria Decision Making (MCDM) and EMO (Evolutionary Multi-objective Optimization) by adjustment of control parameters like Hybrid methods in Multi objective optimization. But, this Fractional order PID with the nominal PID controller has maximum performance estimation. Proposed research work focused the Flower Pollination Algorithm based on Multi objective optimization with Genetic evaluation and Fractional order PID with the nominal PID controller is provides CSTR results. When a flower is displayed to maximum variations in this practical state, the Genetic evaluation has been used to identify the variations. The FPID (Flower Pollination Integral Derivative) is used for tuning the parameters of a Fractional order PID with the nominal PID controller for each region to improve the multi-criteria decision making. FPID also denoted as Flower Optimization Integral Derivative (FOID). The Genetic evaluation scheduler has been combined with multiple local linear Fractional order PID with the nominal PID controller to check the stability of loop for entire regions with various levels of temperatures. MATLAB results demonstrate that the feasibility of using the proposed Fractional order PID with the nominal PID controller compared than the existing PID controller, and it shows the FOID attained better results.

Sign in / Sign up

Export Citation Format

Share Document