基于深度学习的传感器故障数据分析系统设计

Design of sensor fault data analysis system based on deep learning

摘要:

传统传感器故障数据分析系统硬件及程序设计不够兼容，存在实时性差，分析结果不够精准的问题。据此，提出基于深度学习设计了一种新的传感器故障数据分析系统，由传感器、ARM数据处理器、主电路板、FODI数据处理器、集成采集接口板、故障数据传感器、多转质感器、场效应传感器、GKCL储存器组成系统的硬件结构，ASVH248的最大特点就是分辨率高，能够有效提高系统显示的清晰度。分别设计了故障数据采集程序、数据处理程序和数据存储程序。为了检测系统的有效性，由采集程序采集传感器内部数据，处理程序对数据结果进行分析，存储程序负责记录分析后的结果。设定对比实验，结果表明，基于深度学习设计的传感器故障数据分析系统分析结果精准度提高了15.28%，实时性更强，使用价值更高。

Abstract:

The traditional sensor fault data analysis system hardware and program design are not compatible enough, and there is a problem that the real-time performance is poor and the analysis result is not accurate enough. Based on this, a new sensor fault data analysis system based on deep learning is proposed, which consists of sensor, ARM data processor, main circuit board, FODI data processor, integrated acquisition interface board, fault data sensor, multi-turn sensor, The field effect sensor and GKCL memory form the hardware structure of the system. The biggest feature of ASVH248 is the high resolution, which can effectively improve the clarity of the system display. Fault data acquisition programs, data processing programs, and data storage programs are designed separately. In order to check the effectiveness of the system, the internal data of the sensor is collected by the acquisition program, the processing program analyzes the data result, and the storage program is responsible for recording the result of the analysis. The contrast experiment was set up. The results show that the accuracy of the analysis results of the sensor fault data analysis system based on deep learning design is 15.28%, and the real-time performance is stronger and the use value is higher.