Segmented neural network pressure sensor pressure detection method and system

Abstract

The invention discloses a segmented neural network pressure sensor pressure detection method and system. The method comprises the steps of setting a BP neural network in a segmented mode, determining a training function, determining an optimal hidden layer and optimizing a genetic algorithm; sequentially dividing the detection range of the piezoresistive pressure sensor into a low section and a high section, arranging BP neural networks respectively, determining an appropriate neural network training function and the optimal number of hidden layers, improving the recognition accuracy, and optimizing the initial weights and threshold values of the BP neural networks with the optimal number of hidden layers through a genetic algorithm; and determining a segmented neural network model based on genetic algorithm optimization. The method has the advantages that the local search capability of the BP neural network is fully exerted, the algorithm stability is improved, the algorithm is prevented from falling into a local optimal value, and the output readability, the pressure recognition precision, the pressure recognition speed and the pressure recognition stability of the piezoresistive pressure sensor are effectively improved.

Description

technical field [0001] The invention relates to a pressure detection method and system of a segmented neural network pressure sensor, belonging to the technical field of sensors. Background technique [0002] With the advent of the Internet of Everything era, humans have begun to use various sensors on a large scale to sense changes in the outside world to achieve informatization and intelligence. As the core of the Internet of Everything, pressure recognition plays an extremely important role in the Internet of Things. In intelligent robots, pressure recognition is the key to achieve accurate completion of various interactive tasks. In intelligent cars, pressure recognition is the core of key functions such as tire pressure detection. Pressure recognition is also widely used in intelligent medical care, biometrics and other fields. [0003] Pressure identification means that for any pressure applied to the pressure sensor, the specific applied pressure value can be ident...

AI Technical Summary

Problems solved by technology

[0005] In the piezoresistive pressure sensor, the effective identification of pressure is a complex and challenging detection problem. There are three main difficulties. On the one hand, the piezoresistive effect of the strained material in the pressure sensor is nonlinear with the change of external force. resulting in poorly readable output that, despite its excellent performance, cannot be used

On the one hand, due to the lack of an effective and fast piezoresistive pressure sensor output reading method, the recognition speed in actual use is slow, which will increase the delay of using the pressure sensor system

On the other hand, during the actual use of the pressure sensor, the pressure applied to the sensor will have a certain range of jitter, such interference increases the difficulty of pressure recognition

Images