Compasation Method Research Of Automatic Weather Station Temperature And Humidity Sensor

The HMP45D temperature and humidity sensors used in the meteorological observation are vulnerable to surroundings in practical observation, which leads that the data error is big and great influence to the application of meteorological data. So we need to take the measures to compensate the temperature and humidity sensors.In this paper, in order to compensate the effects of that the HMP45D temperature and humidity sensors are vulnerable to environmental parameters in practical observation, we compensate the temperature effects of humidity sensor using the Particle Swarm optimization algorithm(PSO) combined with Back Propagation(BP)network based on Particle Swarm Optimization(PSO)algorithm. And on the same time, we compensate the humidity effects of the temperature sensor using the improved mind evolutionary algorithm of BP neural network model.The main research contents include:The temperature and humidity sensors analysis of the effects influenced by the environmental parameters. Firstly, the influence of environmental parameters on temperature and humidity sensor is analyzed in theory. Then we obtain the corresponding observation data from the specific experiment. Through the analysis of the data, it is concluded that the temperature has a great influence on the humidity sensor and the humidity has a great influence on the temperature sensor.The compensation algorithm model of the temperature influence on humidity sensor, which is based on the actual observed data, establish the PSO-BP neural network model to compensate the temperature effects of humidity. The global optimization of the initial weights and thresholds of BP neural network is carried out by using the particle swarm optimization algorithm. The results show that PSO-BP neural network not only can overcome the limitations that the traditional BP neural network is easy to fall into local minimum, but also have the higher precision, and it can more effectively compensate the influence of temperature on humidity sensor.The compensation algorithm model of humidity influence on temperature sensor, takes some improving researches into advolution operation, alienation operation and convergence conditions in mind evolutionary algorithm.,and makes some adaptive adjustment of the distributing weights in the convergence operation.Differential operation is introduced into alienation operation and the convergence condition is improved at the same time.The humidity compensation model which using improved mind evolutionary algorithm of BP neural network model is proposed. And the analysis is studied by comparing with the results of general BP neural network model which without optimization.At the same time, the curve fitting method and the compensation model of RBF neural network are also studied.The compensation results of the two methods are compared and analyzed,and we determined that the RBF neural network model has higher accuracy than the curve fitting method.