Unlock instant, AI-driven research and patent intelligence for your innovation.

Intelligent manufacturing product identification and detection method based on machine hearing

A technology of intelligent manufacturing and detection methods, applied in the field of mechanical waves, can solve problems such as failure to meet application requirements, acoustic research limitations, and technical encryption

Pending Publication Date: 2021-10-22
璀璨智声苏州智能系统有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the product noise detection market mostly relies on manual detection or imported equipment from abroad. However, due to reasons such as expensive equipment and technical encryption, my country's acoustic research has been restricted to varying degrees, so it has not met the application requirements.
In the industrial production line, the operators are currently responsible for the full-time noise evaluation in the professional quiet room. Due to manual identification, missed judgments and misjudgments will occur, and if the undetected quality problems are circulated to the market, it will cause bad business. At the same time, the annual labor cost is also high, which greatly affects the growth of the enterprise

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent manufacturing product identification and detection method based on machine hearing
  • Intelligent manufacturing product identification and detection method based on machine hearing
  • Intelligent manufacturing product identification and detection method based on machine hearing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0009] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Embodiment 1: A method for identifying and detecting intelligent manufacturing products based on machine hearing. The entire mechanism of noise detection technology is divided into five parts, namely, sound recognition Acquisition, signal processing, acoustic computing, AI computing and interactive systems.

[0010] A. Acoustic collection: use the microphone or microphone array of the sound collection equipment, adopt the sound source positioning technology, and collect the sound signal through the high-precision pickup.

[0011] B. Signal processing: collect the sound signal, identify the sound source and eliminate other sound signals in the sound sample. The sound signal of the fault is retained for feature extraction, the sound detection is performed to diagnose the fault type, and the fault location is found. And upload for signal processing.

[0012...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an intelligent manufacturing product identification and detection method based on machine hearing. The method comprises the following steps: A, collecting a sound signal through a microphone; B, combining an acoustic algorithm and data analysis; C, on the basis of machine learning / deep learning, detecting products in the production line, and finding defective products, and positioning faults; D, performing intelligent judgment; C, accurately predicting a fault by using a deep learning model; and F, monitoring and detecting the existing equipment in real time, finding a suspected fault and performing intelligent early warning, and further predicting the service life of the equipment.

Description

technical field [0001] The invention belongs to the technical field of machine acoustics and relates to acoustic environment, vibration noise and mechanical waves in media. Background technique [0002] At present, the product noise detection market mostly relies on manual detection or imported equipment from abroad. However, due to reasons such as expensive equipment and technical encryption, my country's acoustic research has been restricted to varying degrees, so it has not met the application requirements. In the industrial production line, the operators are currently responsible for the full-time noise evaluation in the professional quiet room. Due to manual identification, there will be missed judgments and misjudgments, and if the undetected quality problems are circulated to the market, it will cause bad business. At the same time, the annual labor cost is also high, which greatly affects the growth of the enterprise. [0003] At present, there are many signals that...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01H17/00G01M99/00G10L25/51
CPCG01H17/00G01M99/005G10L25/51
Inventor 魏军博
Owner 璀璨智声苏州智能系统有限公司