PID Controller Autotuning Design by a Deterministic Q-SLP Algorithm

Pongfai, Jirapun; Su, Xiaojie; Zhang, Huiyan; Assawinchaichote, Wudhichai

doi:10.1109/access.2020.2979810

Cited by 13 publications

(11 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By considering data distribution in the variable boundary, generative model is used. Several studies [27][28][29][30][31][32] first proposed Long-Short Term Network (LSTM) for obtaining entire long-term and short-term data dependence on the variable. LSTM is generally used to obtain long-term dependence information about the network.…”

Section: Review Of Related Workmentioning

confidence: 99%

Real‐time data‐driven PID controller for multivariable process employing deep neural network

Jeyaraj¹,

Nadar²

2022

Asian Journal of Control

View full text Add to dashboard Cite

The complex industrial processes exhibiting nonstationary and multivariable with time‐varying dynamics result in low accuracy. Also, stability compensation is difficult to be obtained by a conventional PID controller. Hence, a deep learning‐based data‐driven PID controller is designed for unmodeled dynamics compensation for complex industrial processes. In this research work, a nonlinear PID controller is designed with a deep neural network (DNN) model from unmodeled dynamics of the complex industrial processes. To validate the performance, results from stability compensation and convergence of the model parameters for closed‐loop systems were obtained. When tested on a real‐time twin tank system, it achieved an accurate output flowrate with 97.65% accuracy and 1.89% peak overshoot compared with conventional PID controller. Both simulated and experimental results validate that proposed controller has improved stability and uniform convergence of system variables. The proposed deep learning‐based PID controller was employed on a twin tank control system. This confirms the feasibility and practical application of a real‐time complex process.

show abstract

Section: Review Of Related Workmentioning

confidence: 99%

Real‐time data‐driven PID controller for multivariable process employing deep neural network

Jeyaraj¹,

Nadar²

2022

Asian Journal of Control

View full text Add to dashboard Cite

show abstract

“…During the process of autotuning, the fitness function is used to determine the quality. Normally, the fitness function is utilized by applying a performance index [19], such as the integral of the absolute error (IAE), the integral of the time multiplied squared error (ITSE), the integral of the time multiplied absolute error (ITAE), and the integral of the squared error (ISE). They are defined as follows [19]:…”

Section: The Pid Controller and The Fitness Functionmentioning

confidence: 99%

“…different operations [15]- [18].However, many methods, such as Cohen-Coon and phase and gain margin methods have been proposed to overcome the limitations of the conventional methods, but they require experienced designers and more time for tuning [19].…”

Section: Introductionmentioning

confidence: 99%

“…Earlier, the artificial intelligence (AI) evaluation and swarm algorithm was commonly applied to optimally tune PID parameters by continuously minimizing the performance index until it approached the best system response [19], such as the ant lion optimizer (ALO) algorithm [20], the gas brownian motion optimization (GBMO) [21], the bacterial foraging optimization (BFO) algorithm [22], the improved sine cosine algorithm [23], the cuckoo search optimization (CSO) [7], the bat algorithm [24], the ant colony optimized (ACO) [25], the genetic algorithm (GA) [26], [27], the world cup optimization (WCO) [28], the gray wolf optimization algorithm [12], [29], the kidney-inspired algorithm [30], the green leaf-hopper flame optimization algorithm (GLFOA) [31], the improved QUATRE algorithm [32], the fractional-order fish migration optimization algorithm (FOFMO) [33] and the particle swarm optimization (PSO) algorithm [34].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Proportional-Integral-Derivative Parametric Autotuning by Novel Stable Particle Swarm Optimization (NSPSO)

2022

Self Cite

View full text Add to dashboard Cite

To improve the performance, robustness and stability of autotuning the proportional integral and derivative (PID) parameter, the novel stable particle swarm optimization (NSPSO) is proposed in this paper. The NSPSO is the combination of the particle swarm and optimization algorithm with the new stable rule to reconsider the survival of the remaining particle in the search space for handling the instability of the system. The new rule is proposed based on proving the stability according to the Lypunov stability theorem. Additionally, to show the method's superiority in performance and robustness, the proposed method is compared with the results of simulations with the particle swarm optimization (PSO), the hybrid particle swarm optimization-grey wolf optimization (PSO-GWO), the whale optimization algorithm (WOA) and the social spider optimization algorithm (SSO) based on a direct current (DC) motor control system. In the comparative performance, the various fitness functions are applied, while the comparative robustness and the changed operation point of the DC motor are applied. After comparing the methods, the proposed method obtains better results than the PSO, PSO-GWO, WOA and SSO in both performance and robustness.INDEX TERMS DC motor, Lypunov stability, optimization, particle swarm and optimization (PSO), Proportional integral and derivative (PID).

show abstract

“…However, these swarm intelligence algorithms may fall into a local optimal solution. Therefore, new swarm intelligence learning algorithms that combine the reinforcement learning algorithm [37]- [50] and swarm intelligence algorithm have been proposed by researchers, such as the Q-SLP algorithm and MM-MADRL algorithm [51] and [52]. These algorithms interact with the environment by using reinforcement learning algorithms and reward their users.…”

Section: Introductionmentioning

confidence: 99%

Improved MM-MADRL Algorithm for Automatic Tuning of Multiparameter Control Systems

2022

Self Cite

View full text Add to dashboard Cite

Control systems are widely used in our lives, and good control can be achieved by obtaining the optimal tuning parameters of the control system. The number of parameters that need to be adjusted for different control systems varies. With an increase in tuning parameters, the difficulty of tuning grows. Therefore, this paper proposes an improved monkey multiagent DRL (IMM-MADRL) algorithm and selects 3 test functions to test the setting environment of 2-7 parameters. Thus, these parameters are adjusted. The IMM-MADRL algorithm is based on the modified monkey-multiagent DRL (MM-MADRL) algorithm, and its initialization method, position update method and somersault operation are further improved so that it can perform good parameter tuning for a control system with many parameters. The simulation part of this paper proves the advantage of the IMM-MADRL algorithm in a multiparameter control system.INDEX TERMS Incomplete differential PID controller, modified monkey-multiagent DRL (MM-MADRL) algorithm, Improved modified monkey-multiagent DRL (IMM-MADRL) algorithm, Optimization.

show abstract

PID Controller Autotuning Design by a Deterministic Q-SLP Algorithm

Cited by 13 publications

References 48 publications

Real‐time data‐driven PID controller for multivariable process employing deep neural network

Real‐time data‐driven PID controller for multivariable process employing deep neural network

Proportional-Integral-Derivative Parametric Autotuning by Novel Stable Particle Swarm Optimization (NSPSO)

Improved MM-MADRL Algorithm for Automatic Tuning of Multiparameter Control Systems

Contact Info

Product

Resources

About