Temperature decoupling control of double-level air flow field dynamic vacuum system based on neural network and prediction principle
Highlights
► DAFDV system is a strong coupling, large time-delay, and nonlinear system. ► Present an adaptive, predictive PID decoupling control method for a real-time system. ► Elman neural network and IPSO are used to tune parameters of system on-line. ► Propose a new kind of multi-step ahead prediction method for slow time-varying system. ► The experiments are performed on a real plant to validate the efficiency.
Introduction
Double-level air flow field dynamic vacuum system (DAFDV) is that the air flow temperatures in two concatenate chambers maintain in steady equilibrium states while maintaining a certain flow rate into and out of the chambers. DAFDV systems have great application value for the simulation of dynamic atmospheric environments, calibration of meteorological instruments and research of humidity generation technology based on two-temperature or two-temperature two-pressure principle (Wang, 2003, Kitano et al., 2008, Helmut, 2008). Air temperature control of single chamber has been widely studied by many scholars (Lawton and Patterson, 2000, Ghoumari et al., 2005, Thompson and Dexter, 2005, Qi and Deng, 2009, Li et al., 2011), and some findings have been extensively applied in industrial practices. However, researches on DAFDV systems have scarcely been represented in the open literature. This may be attributed to two major sources of difficulty. First, the simple and adequate dynamic relationships among the process variables are difficult to establish due to the nonlinearity, uncertainties and structure complexities. Second, the two air temperatures in the two concatenate chambers suffer impact from each other’s fluctuations. If the two air temperatures cannot be decoupled effectively, they would not only delay reach steady states, but also not accomplish independent control at all. Therefore, in order to achieve rapid, accurate and independent control, it is necessary to decouple these two variables. However, how the appropriate decoupling method is selected according to the characteristics of control object is a key problem.
The traditional decoupling ways to a multi-input multi-output (MIMO) system is mainly represented by modern frequency domain methods such as diagonal dominance matrix, relative gain analysis method, characteristic curve method, state variable method, inverse Nyquist array and so on (Wang, 2000). These methods, which are based on strict transfer functions or state spaces, play an important role in decoupling the linear time-invariant MIMO systems. However, these methods are difficult to achieve dynamic decoupling for nonlinear or uncertain or time-variant MIMO systems because accurate system models are difficult to develop for these systems. Thereby, these traditional decoupling methods are confined to a certain application scope.
With the development of decoupling control theory, a multitude of other decoupling methods such as adaptive decoupling, energy decoupling, disturbance decoupling, robust decoupling, fuzzy decoupling, neural networks decoupling, prediction decoupling, intelligent decoupling methods represented mainly by the fuzzy decoupling and the neural networks decoupling, have been proposed and applied in many control practices. The detailed introduction to these decoupling methods are summarized (Dong et al., 2011), this paper no longer repeats them.
Adaptive decoupling has merits in decoupling a system with many uncertain factors and can solve the system’s uncertainty to a certain extent. Multilayer neural networks have adaptive, self-learning, strong fault tolerance abilities and are universal approximators capable of approximating any nonlinear function to any desired degree of accuracy, making it a powerful tool for the decoupling control of nonlinear systems. The modified output–input feedback (OIF) Elman neural network, as a kind of recurrent neural network, is superior to the static neural network such as back-propagation (BP) and radial basis function (RBF) neural network on the dynamic characteristic (Wu et al., 2011a), and it is now extensively applied in the fields of system identification, nonlinear control and prediction control (Serhat et al., 2003, Qi et al., 2005, Gao and Wang, 2007). However, neural networks commonly require to be combined with other algorithms to realize decoupling control (Wu and Chai, 1997, Li, 2006).
Prediction is an effective means to control a time-delay system. Furthermore, the proportional-integral-derivative (PID) controller is widely used in many fields due to its simplicity and robustness (Kumar et al., 2007, Shi et al., 2008, Xu et al., 2008).
Based on the above discussions, an adaptive PID decoupling control method based on the modified OIF Elman neural network and prediction principle is proposed in this paper. Because the DAFDV system is a strong coupling, complex MIMO nonlinear system with large time-delay and uncertainty, which can hardly acquire satisfactory control performance and even cannot reach the steady state at all by the conventional PID controller with fixed parameters. By the identification function of the OIF Elman neural network, the PID parameters are tuned on-line. Thus, the couplings between the manipulated variables can be treated as corresponding exterior disturbances, so the proposed controller is used to eliminate disturbance and obtain desired control performance in different operating regions. The time-delay effects can be reduced or eliminated by the prediction. The main contribution of this study is to propose an effective decoupling control strategy, which can be applied to a real-time plant conveniently, for the strong coupling, large-time delay and nonlinear system make it is difficult to elaborate a mathematic model precise enough for the control.
The paper is structured in the following way. In Section 2, the composition of DAFDV system is presented. In order to analyze the system properties conveniently, the models of the DAFDV system are qualitatively developed in Section 3. Section 4 is proposed the adaptive PID decoupling control method based on the modified OIF Elman neural network and prediction principle. In Section 5, the experimental results on a real-time DAFDV system are presented. Conclusions are drawn in Section 6.
Section snippets
Composition of DAFDV system
The DAFDV system, as shown in Fig. 1, mainly consists of the pressure control system and the temperature control system. In Fig. 1, the air flows in the dash dotted arrows direction while the liquid (water or ethanol) in the solid arrows direction. The middle part of the air flowing through is the pressure control loop. The temperature control system is constituted of water bath temperature control (WBTC) subsystem and ethanol bath temperature control (EBTC) subsystem. These two subsystems,
Modeling of the DAFDV system
In this section, the models of the DAFDV system are qualitatively developed for analyzing the system properties conveniently. The temperature control process of the DAFDV system is that: (1) the water temperature of T1 is manipulated by the heater or chiller. (2) The air temperature in C2 is controlled by changing the inlet water temperature of E1, i.e., the water temperature of T1.
Temperature decoupling control strategy of the DAFDV system
The structure for the temperature decoupling control of the DAFDV system is shown in Fig. 3, which combines the modified OIF Elman neural network and the PID controller with prediction algorithm.
In Fig. 3, i=1, 2, ri(k) is the reference input, yi(k) the real temperature output, ymi(k) is the modified OIF Elman neural network identification model output, ei(k) is the error between the set-point value ri(k) and output yi(k) in every sampling point, ui(k) is the manipulated variable, NN1(NN2) the
Experimental results
A set of 240 experimental data which is collected from the real DAFDV system is applied to simulation experiment. Before the simulation experiment, the determination to the number of hidden node and IPSO parameters is a key problem, which is directly associated with the performance of the identification model by the modified OIF Elman neural network. In this research, the number of hidden node is given as 2r+1 according to Kolmogorov theorem, where r is the number of input variables. There are
Conclusions
Based on the modified OIF Elman neural networks and the prediction principle, an adaptive PID decoupling controller is designed to achieve the rapid, precise and especially independent control for the upstream and downstream temperatures of the DAFDV coupling system. As for the two kinds of typical application cases of the DAFDV system, corresponding field experiments based on a real plant (the DAFDV system) are carried out. The experimental results show that the settling times of the upstream
Acknowledgements
This work is supported by a special key project of National Public Sector of China (Grant No, GYHY200706003) and the National Natural Science Foundation Innovation Group of China (61121003).
References (23)
- et al.
Simulation of dynamic response of a countercurrent heat exchanger to inlet temperature or mass flow rate change
Appl. Therm. Eng.
(2006) - et al.
Decoupling control of double-level dynamic vacuum system based on neural networks and prediction principle
Vacuum
(2011) - et al.
A high-stability air temperature control system
Precis. Eng.
(2000) - et al.
Multivariable control of indoor air temperature and humidity in a direct expansion (DX) air conditioning (A/C) system
Build. Environ.
(2009) - et al.
A fuzzy decision-making approach to temperature control in air-conditioning systems
Control Eng. Pract.
(2005) - et al.
Power decoupling control of a solid oxide fuel cell and gas turbine hybrid power system
J. Power Sources
(2011) - et al.
Thermal modeling of a solid oxide fuel cell and micro gas turbine hybrid power system based on modified LS-SVM
Int. J. Hydrogen Energy
(2011) - et al.
Identification of nonlinear dynamic system based on Elman neural network
Comput. Eng. Appl.
(2007) - et al.
Non-linear constrained MPC: real-time implementation of greenhouse air temperature control
Comput. Electron. Agric.
(2005) Miniaturized two-pressure generator for relative humidity
Int. J. Thermophys.
(2008)
Dynamic parameter tuning of particle swarm optimization
IEEJ Trans. Electr. Electron.
Cited by (24)
Dynamic thermal model and control performance analysis over frequency domain of temperature control unit
2023, Case Studies in Thermal EngineeringCooling/heating dual-stage actuators decoupling structure design and energy management strategy for thermostatic airflow control
2023, Thermal Science and Engineering ProgressAn improved OIF Elman neural network based on CSO algorithm and its applications
2021, Computer CommunicationsCitation Excerpt :In this case, the artificial neural network has developed rapidly due to its good nonlinear fitting ability and generalization ability [8–11]. OIF Elman neural network has better robustness and adaptability than ordinary neural network, and has unique advantages in solving nonlinear problems [12–14]. The OIF Elman neural network is based on the traditional Elman network model, the feedback of the output layer is added to the hidden layer to realize the delay and storage of historical information.