CN113532631A - Intelligent manufactured product identification and detection method based on machine hearing - Google Patents
Intelligent manufactured product identification and detection method based on machine hearing Download PDFInfo
- Publication number
- CN113532631A CN113532631A CN202110764629.3A CN202110764629A CN113532631A CN 113532631 A CN113532631 A CN 113532631A CN 202110764629 A CN202110764629 A CN 202110764629A CN 113532631 A CN113532631 A CN 113532631A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- sound
- machine
- method based
- detection method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 9
- 230000005236 sound signal Effects 0.000 claims abstract description 12
- 238000004519 manufacturing process Methods 0.000 claims abstract description 9
- 238000007405 data analysis Methods 0.000 claims abstract description 4
- 238000013135 deep learning Methods 0.000 claims abstract description 3
- 230000002950 deficient Effects 0.000 claims abstract description 3
- 238000013136 deep learning model Methods 0.000 claims abstract 2
- 238000010801 machine learning Methods 0.000 claims abstract 2
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 238000003889 chemical engineering Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses an intelligent manufactured product identification and detection method based on machine hearing, which comprises the following steps that A, firstly, sound signals are collected through a microphone: b, combining an acoustic algorithm and data analysis; c, detecting products in the production line on the basis of machine learning/deep learning, finding out defective products and positioning faults; d, carrying out intelligent judgment; e, accurately predicting the fault by using a deep learning model; and F, simultaneously, the existing equipment can be monitored and detected in real time, suspected faults are found, intelligent early warning is given, and the service life of the equipment can be further predicted.
Description
Technical Field
The invention belongs to the technical field of machine acoustics, and relates to a sound environment, vibration noise and mechanical waves in media.
Background
At present, the market of product noise detection mostly depends on manual detection or foreign imported equipment, but because of the reasons of expensive equipment price, technical encryption and the like, acoustic research in China is always limited to different degrees, and therefore the application requirements are not met. In the industry production line, at present, an operator is responsible for noise judgment in a professional mute room, and due to the fact that missed judgment and misjudgment are caused by manual identification, and undetected quality problems are circulated to the market, bad enterprise reputation can be caused, meanwhile, the labor cost is high every year, and the growth of enterprises is greatly influenced.
At present, there are many signals available for monitoring the operation state of mechanical equipment and diagnosing faults, such as force signals, temperature signals, vibration signals, sound signals, and the like, wherein the latter two signals are most applied. Generally, a sound signal is composed of pure tones and noise, and the noise is generally considered harmful and should be eliminated. Most mechanical device operating conditions or fault signals are contained in the noise. Therefore, the device is subjected to state monitoring and fault diagnosis, and noise analysis is an important entry point. The sound emitted during the operation of the high-speed mechanical equipment contains the sound signals of the inherent structure, namely 'basic noise', such as vibration caused by the rotation of a main shaft, the meshing of gears, the friction of contact surfaces of parts, the rotation of a bearing, the rotation of a lead screw and the like, and noise caused by manufacturing and assembling errors. The signals are mixed together to reflect the running state of the mechanical equipment, so that the sound signals of the running state of the mechanical equipment are used for feature extraction and analysis, and high-efficiency technical guarantee can be provided for fault diagnosis and maintenance in the whole running process of the mechanical equipment, so that the efficiency of mechanical numerical control machining can be greatly improved, and the safety of equipment and personnel can be guaranteed. Therefore, a set of high-precision sound testing system for the running state of mechanical equipment is imperative to be developed.
With the comprehensive promotion of intelligent manufacturing with an industrial internet as a carrier and the continuous promotion of new products of intelligent manufacturing equipment with sensing, analyzing, reasoning, decision-making and control functions, the application market of machine hearing in the aspects of equipment monitoring and fault diagnosis is wide, and the application scenes of machine hearing are very wide in various industries from automobiles, household appliances, industrial production, electric power energy sources to chemical engineering, aviation, ships and the like.
Disclosure of Invention
The invention collects sound signals through a microphone, performs acoustic detection on products through an acoustic algorithm and data analysis, finds out defective products and intelligently judges the reason. And monitoring and detecting the equipment in real time, finding suspected faults and giving intelligent early warning. The surface quality of the product is not affected by non-contact, and no additional machine or manual operation is needed; and the noise abnormal sound of the product can be detected more directly and more accurately by corresponding vibration sensing. The quality defects are accurately and intelligently identified and judged, meanwhile, high-quality sound data information provides an effective basis for quality management, and the competitiveness of the manufacturing industry is improved in the digital era.
Drawings
FIG. 1: schematic diagram of intelligent product identification and detection method based on machine hearing for patent invention
FIG. 2: the mechanism diagram of the whole noise detection technology of the invention patent
FIG. 3: machine hearing based intelligent manufactured product identification signal processing flow chart for invention patent
Detailed Description
The technical solution in the embodiment of the present invention will be clearly and completely described below, in embodiment 1: the intelligent product identifying and detecting method based on machine hearing includes 5 parts of identifying sound acquisition, signal processing, acoustic calculation, AI calculation and interaction system.
A. Recognizing and collecting sound: the microphone or the microphone array of the sound collecting equipment is utilized, the sound source positioning technology is adopted, the sound signals are collected through the high-precision sound pick-up,
B. signal processing: and collecting the sound signals, and identifying and eliminating other sound signals in the sound sample by the sound source. And (4) keeping the sound signals of the fault, extracting the characteristics, detecting and diagnosing the fault type by sound, and finding out the fault position. And uploaded for signal processing.
C. Acoustic calculation: the analog signal is converted to a digital signal. And then, applying the obtained signal to a MUSIC algorithm to calculate the angle of the position of the fault sound source. Experiments prove that the improved MUSIC algorithm has higher resolution capability on the strong correlated information source with smaller interval under the condition of low signal-to-noise ratio
AI calculation: and secondly, carrying out acoustic analysis calculation, and storing the voiceprint characteristics and all data of each offline product into a database. Through big data analysis, the trend of production quality can be known, and the problem of system quality can be judged.
E. An interactive system: and analyzing and comparing the sounds in the database by combining an acoustic database and a deep learning algorithm, and outputting a result to the sound signal. And (3) rapidly finding potential faults of the product and providing intelligent early warning.
As a further technical solution of the present invention, the step a specifically is: and (3) positioning and identifying the collected sound which is noise generated by machine abnormity in industrial production, judging that the collection angle and the position of the sound have no problem if the comparison result is consistent, belonging to effective sound, and judging that the sound is invalid if the comparison result is inconsistent.
As a further technical solution of the present invention, the step B specifically is: and (4) the sound data of the product to be detected and the feature point data in the standard sound data are used as the reference to complete the registration of the sound to be detected and the standard sound, and the data comparison is carried out.
As a further technical solution of the present invention, the data comparison standard in step C is: and judging the consistent sound when the comparison consistency rate of the feature points is more than or equal to 99.5%, and judging the inconsistent sound when the comparison consistency rate of the feature points is less than or equal to 99.5%.
As a further technical solution of the present invention, the state of step A, B, C, D, E is: and data acquisition and analysis are carried out in real time, defects are identified and quality judgment is carried out on line, and the method is applied to batch production and realizes real-time monitoring and judgment of the whole production process.
Claims (1)
1. The invention aims to provide an intelligent manufactured product identification and detection method based on machine hearing to solve the problems in the background technology.
To achieve the object, it is characterized in that by a, the sound signal is collected first by a microphone: b, combining an acoustic algorithm and data analysis; c, detecting products in the production line on the basis of machine learning/deep learning, finding out defective products and positioning faults; d, carrying out intelligent judgment; e, accurately predicting the fault by using a deep learning model; f, the existing equipment can be monitored and detected in real time.
The described embodiments are only some embodiments of the invention, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110764629.3A CN113532631A (en) | 2021-07-07 | 2021-07-07 | Intelligent manufactured product identification and detection method based on machine hearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110764629.3A CN113532631A (en) | 2021-07-07 | 2021-07-07 | Intelligent manufactured product identification and detection method based on machine hearing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113532631A true CN113532631A (en) | 2021-10-22 |
Family
ID=78097883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110764629.3A Pending CN113532631A (en) | 2021-07-07 | 2021-07-07 | Intelligent manufactured product identification and detection method based on machine hearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113532631A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876951A (en) * | 2018-06-13 | 2018-11-23 | 贾成举 | A kind of teaching Work attendance method based on voice recognition |
| CN109065030A (en) * | 2018-08-01 | 2018-12-21 | 上海大学 | Ambient sound recognition methods and system based on convolutional neural networks |
| WO2019097412A1 (en) * | 2017-11-14 | 2019-05-23 | Asquared Iot Pvt. Ltd. | System and method for multimedia-based performance monitoring of an equipment |
| CN110718231A (en) * | 2019-09-12 | 2020-01-21 | 深圳市铭华航电工艺技术有限公司 | Monitoring method, device, terminal and storage medium based on acoustic network |
| CN110940539A (en) * | 2019-12-03 | 2020-03-31 | 桂林理工大学 | Machine equipment fault diagnosis method based on artificial experience and voice recognition |
| KR20210056465A (en) * | 2019-11-08 | 2021-05-20 | 가톨릭관동대학교산학협력단 | Deep learning-based autonomous vehicle auditory system for the visually impaired and method thereof |
-
2021
- 2021-07-07 CN CN202110764629.3A patent/CN113532631A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019097412A1 (en) * | 2017-11-14 | 2019-05-23 | Asquared Iot Pvt. Ltd. | System and method for multimedia-based performance monitoring of an equipment |
| CN108876951A (en) * | 2018-06-13 | 2018-11-23 | 贾成举 | A kind of teaching Work attendance method based on voice recognition |
| CN109065030A (en) * | 2018-08-01 | 2018-12-21 | 上海大学 | Ambient sound recognition methods and system based on convolutional neural networks |
| CN110718231A (en) * | 2019-09-12 | 2020-01-21 | 深圳市铭华航电工艺技术有限公司 | Monitoring method, device, terminal and storage medium based on acoustic network |
| KR20210056465A (en) * | 2019-11-08 | 2021-05-20 | 가톨릭관동대학교산학협력단 | Deep learning-based autonomous vehicle auditory system for the visually impaired and method thereof |
| CN110940539A (en) * | 2019-12-03 | 2020-03-31 | 桂林理工大学 | Machine equipment fault diagnosis method based on artificial experience and voice recognition |
Non-Patent Citations (1)
| Title |
|---|
| 翟永杰 等: "基于计算机听觉技术的电力设备状态监测研究综述", 《广东电力》, vol. 32, no. 9, 8 October 2019 (2019-10-08), pages 24 - 32 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109506921B (en) | Fault diagnosis and early warning method for rotary machine | |
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN112173636B (en) | Method for detecting faults of belt conveyor carrier roller by inspection robot | |
| JP2006292734A (en) | Determination model producing support device for test device and test device, and endurance test device and endurance test method | |
| WO2023279382A1 (en) | Motor bearing running state fault detection method and system | |
| Hayashi et al. | Study of machine fault diagnosis system using neural networks | |
| KR20060100248A (en) | Inspection apparatus, aid device for creating judgment model therefor, abnormality detection device for endurance test apparatus and endurance test method | |
| CN116701984B (en) | Automatic fault diagnosis system of numerical control machine tool based on machine learning | |
| CN110398362B (en) | Robot RV reducer fault diagnosis and positioning method | |
| CN115437358A (en) | Intelligent state monitoring and fault diagnosis system and fault diagnosis method for industrial robot | |
| CN117113104A (en) | Intelligent management system and method applying data analysis technology | |
| CN114510979A (en) | Underwater equipment inspection system and method based on edge calculation | |
| CN116625683A (en) | Wind turbine generator system bearing fault identification method, system and device and electronic equipment | |
| CN113532631A (en) | Intelligent manufactured product identification and detection method based on machine hearing | |
| CN113418731A (en) | Online fault diagnosis method for cigarette making machine set | |
| CN114862283B (en) | Quality inspection method and quality inspection device for machine tool machining | |
| CN111456915A (en) | Fault diagnosis device and method for internal components of fan engine room | |
| CN115034094A (en) | Prediction method and system for operation state of metal processing machine tool | |
| JP2006300524A (en) | Abnormal sound inspection method | |
| Waters et al. | Vibration Anomaly Detection using Deep Autoencoders for Smart Factory | |
| Burda et al. | Entropy approach in the analysis of vibration and partial discharge signals | |
| CN201583341U (en) | Spot-check detection device for vibration state of water flooding unit | |
| CN111157812A (en) | Power equipment fault monitoring method based on electromagnetic induction | |
| CN117672255B (en) | Abnormal equipment identification method and system based on artificial intelligence and equipment operation sound | |
| CN112485018B (en) | Mechanical equipment energy consumption abnormity detection method based on mechanism data fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |