Abstract
Devices used to set and control the environmental temperature are critical to the performance of gas-sensitive material analyzers, which use silicon microcantilevers to characterize the gas-sensitive materials. This paper describes a novel microtemperature-control device that uses a double Peltier structure to replace the traditional refrigerant temperature control system. A proportional-integral-derivative (PID) algorithm is used to achieve accurate and fast temperature control, with a long short-term memory (LSTM) network trained to identify the nonlinear dynamics of the Peltier system. A neighbor hybrid mean center opposition-based learning particle swarm optimization (NHCOPSO) algorithm is proposed to optimize the PID controller. The LSTM network identification is obviously better than that of previous Peltier system identification methods, and the NHCOPSO algorithm is found to be superior to other improved PSO and evolutionary algorithms on benchmark functions and in PID parameter optimization. Experimental results show that the proposed temperature control device greatly improves the accuracy and efficiency of gas-sensitive material analysis with a temperature control range of −40 to 180°C, a temperature control tolerance within ±0.05°C, a maximum heating rate of 20°C/min, and a maximum cooling rate of −10°C/min.
Highlights
As microelectromechanical system (MEMS) technology continues to be improved, the applications of silicon microcantilevers in gas-sensing material performance analysis are expanding [1], [2]
This paper proposes a method of model identification for the Peltier temperature control system based on an long short-term memory (LSTM) network
The results show that network LSTM25 achieves the best performance in terms of identifying the Peltier temperature control system designed in this paper, as the output curve on the basic test sets is the most similar to that of the practical system
Summary
As microelectromechanical system (MEMS) technology continues to be improved, the applications of silicon microcantilevers in gas-sensing material performance analysis are expanding [1], [2]. By analyzing some PSO improvement strategies, neighbor hybrid mean center opposition-based learning particle swarm optimization (NHCOPSO) is developed This technique improves the temperature control precision and speed of a silicon microcantilever-based gassensitive material analyzer by identifying the optimum PID control parameters quickly and accurately over a large range. Reference [4] describes the conversion of the adsorption and desorption of gas molecules onto a gas-sensing material into changes in the resonant frequency of the cantilever, which enables the calculation of key dynamic/thermodynamic parameters of gas-sensitive materials, such as the enthalpy change ΔH, entropy change ΔS, Gibbs free energy G, and Langmuir equilibrium constant K Based on this derivation [4], the present paper mainly analyzes the relationship between the enthalpy change of the gas-sensing material performance parameters and the experimental temperature deviation. Let ΔT1 and ΔT2 in (3) be independent variables, let E be the dependent variable, and set the other parameters as constants
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
