Machine equipment state monitoring system based on deep learning and voice recognition

Abstract

The invention discloses a machine equipment state monitoring system based on deep learning and voice recognition. The system comprises a training data collection module used for collecting voice signals; a manual marking module used for marking the voice signals to form a sound sample library, wherein sound samples are sent to a preset neural network model for training after being subjected to pretreatment and feature extraction; a real-time data collection module used for collecting the voice signals and sending the signals to the trained neural network model; and a state recognition module used for being combined with artificial experience to comprehensively recognize and determine a running state of a machine via the voice signal and feeding back and outputting a result. According to the system, the running state of machine equipment can be monitored in real time, and meanwhile when the machine equipment is faulted or in a dangerous state, an alarm signal is emitted to notice an equipment keeper to maintain in time, so that work efficiency is improved; and meanwhile, a deep learning algorithm is used and combined with the artificial experience to train the neural network model,so that the system has the advantages of high recognition accuracy, good safety, high efficiency and intellectualization.

Description

technical field [0001] The invention relates to the technical field of sound signal recognition, in particular to a machine equipment status monitoring system based on deep learning and sound recognition. Background technique [0002] At present, during the use of machinery and equipment in the factory environment, due to the influence of natural factors such as temperature, humidity, geographical location and human factors, the machinery and equipment are prone to wear and aging and many other problems. Machine equipment condition monitoring is a very complicated process. Although there are many researches on machine equipment condition monitoring and fault diagnosis, due to the many types of faults, the occurrence of faults is accidental or random. At the same time, due to the complexity of machine equipment itself Therefore, the status monitoring and fault diagnosis of machinery and equipment is still a problem worth exploring. [0003] According to the characteristic de...

AI Technical Summary

Problems solved by technology

[0004] (1) Major machinery and equipment or expensive large units used in production are inconvenient to access for inspection or cannot be disassembled for inspection when failure occurs

[0005] (2) Machinery and equipment with high safety requirements are not only difficult to maintain, but also costly

[0006] (3) Insufficient consideration of the importance of production, personal safety, environmental protection, social impact, etc.

[0007] (4) When analyzing and processing data, most diagnostic methods use various independent models to solve problems. This method needs to combine various models well, and needs to consider multiple situations in different problems, so it has certain advantages. limitations

[0008] (5) It is still difficult to have a good remote diagnosis method to completely solve the fault diagnosis of machinery and equipment in complex systems

Images