CN109359767B - Intelligent expression method and device for fault recognition result in intelligent manufacturing process - Google Patents
Intelligent expression method and device for fault recognition result in intelligent manufacturing process Download PDFInfo
- Publication number
- CN109359767B CN109359767B CN201811113319.XA CN201811113319A CN109359767B CN 109359767 B CN109359767 B CN 109359767B CN 201811113319 A CN201811113319 A CN 201811113319A CN 109359767 B CN109359767 B CN 109359767B
- Authority
- CN
- China
- Prior art keywords
- layer
- network
- manufacturing process
- fault
- deep
- 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.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 12
- 239000010410 layer Substances 0.000 claims description 60
- 239000002356 single layer Substances 0.000 claims description 36
- 210000002569 neuron Anatomy 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 12
- 230000000007 visual effect Effects 0.000 claims description 12
- 230000003213 activating effect Effects 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims 2
- 230000036541 health Effects 0.000 description 11
- 238000000605 extraction Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000034994 death Effects 0.000 description 1
- 231100000517 death Toxicity 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of intelligent manufacturing fault prediction, in particular to an intelligent expression method and device for a fault identification result in an intelligent manufacturing process.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing fault prediction, in particular to an intelligent expression method and device for a fault identification result in an intelligent manufacturing process.
Background
The complex industrial system has the increasingly prominent trend of equipment complexity, system integration and large-scale enlargement, so that a fault signal has the characteristic of concealment, faults can be timely and effectively detected and measures can be taken, the production efficiency can be improved, the product quality can be improved, and the economic loss and unnecessary personal injuries and deaths can be reduced. Therefore, attention is being paid to a fault diagnosis technique for improving the safety and reliability of a complex industrial system.
Faults in modern industrial systems are characterized by being hidden, random, low in amplitude, unobvious in fault characteristics, easily covered by noise and easily submerged by large normal changes. Through research, the fault state results form a health situation map of the manufacturing process, and timely prediction and diagnosis are one of the key factors for guaranteeing the system safety and inhibiting fault deterioration. How to intuitively and clearly express the health state of the manufacturing process and how to show the health state of the manufacturing process becomes a problem worthy of solution.
Disclosure of Invention
The invention provides an intelligent expression method and device for a fault identification result in an intelligent manufacturing process, which can intuitively and clearly express the health state of the manufacturing process and show the health state of the manufacturing process in multiple aspects.
The invention provides an intelligent expression method for a fault identification result in an intelligent manufacturing process, which comprises the following steps:
step A, collecting historical fault signals generated in the manufacturing process, eliminating noise signals and generating sample fault data;
b, generating single-layer network data from the sample fault data;
step C, splitting the weight of single-layer network training into a plurality of combinations of basis functions;
d, generating visual deep-layer network parameters;
e, determining the characteristic and the variation trend of the feature space similarity between the current layer and the previous layer;
and F, expressing a fault identification result based on the deep network.
Further, the historical fault data in the step a includes: the amplitude, phase and frequency of the signal generated during the manufacturing process; the signal generated during the manufacturing process consists of a fault signal and a noise signal.
Further, the step C specifically includes: through single-layer network's parameter visualization, the weight split of single-layer network training is the combination of a plurality of basis functions, thereby carries out single-layer network's feature extraction through the dot product transform of original signal and a plurality of basis functions.
Further, the step D specifically includes:
d1, visualizing the parameters of the single-layer network;
step D2, acquiring an activation relation between a current layer neuron and a previous layer neuron in the deep network;
step D3, determining the maximum input mode for activating the neuron nodes of the current layer, and taking the nodes as the linear weighted combination of the filter of the previous layer;
d4, generating deep network parameters;
and D5, visualizing the deep network parameters.
Further, the step E specifically includes:
and determining the characteristic and the variation trend of the characteristic space similarity between the current layer and the previous layer through the characteristics extracted by the layer-by-layer visual network.
The invention provides an intelligent expression device for a fault identification result in an intelligent manufacturing process, which comprises a control module and a storage module for storing a control instruction, wherein the control module reads the instruction and executes the following steps:
step A, collecting historical fault signals generated in the manufacturing process, eliminating noise signals and generating sample fault data;
b, generating single-layer network data from the sample fault data;
step C, splitting the weight of single-layer network training into a plurality of combinations of basis functions;
d, generating visual deep-layer network parameters;
e, determining the characteristic and the variation trend of the feature space similarity between the current layer and the previous layer;
and F, expressing a fault identification result based on the deep network.
Further, the historical fault data in the step a includes: the amplitude, phase and frequency of the signal generated during the manufacturing process; the signal generated during the manufacturing process consists of a fault signal and a noise signal.
Further, the step C of the control module reading the instruction specifically executes the steps of:
through single-layer network's parameter visualization, the weight split of single-layer network training is the combination of a plurality of basis functions, thereby carries out single-layer network's feature extraction through the dot product transform of original signal and a plurality of basis functions.
Further, the step D of reading the instruction by the control module specifically executes the steps of:
d1, visualizing the parameters of the single-layer network;
step D2, acquiring an activation relation between a current layer neuron and a previous layer neuron in the deep network;
step D3, determining the maximum input mode for activating the neuron nodes of the current layer, and taking the nodes as the linear weighted combination of the filter of the previous layer;
d4, generating deep network parameters;
and D5, visualizing the deep network parameters.
Further, the step E of reading the instruction by the control module specifically executes the steps of:
and determining the characteristic and the variation trend of the characteristic space similarity between the current layer and the previous layer through the characteristics extracted by the layer-by-layer visual network.
The invention has the beneficial effects that: the invention discloses an intelligent expression method and device for fault identification results in an intelligent manufacturing process.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a flow chart of an intelligent expression method for a fault identification result of an intelligent manufacturing process according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of step D of an intelligent expression method for a fault identification result of an intelligent manufacturing process according to an embodiment of the present invention.
Detailed Description
Referring to fig. 1, an embodiment of the present invention provides an intelligent expression method for a fault identification result in an intelligent manufacturing process, including the following steps:
step A, collecting historical fault signals generated in the manufacturing process, eliminating noise signals and generating sample fault data;
b, generating single-layer network data from the sample fault data;
step C, splitting the weight of single-layer network training into a plurality of combinations of basis functions;
d, generating visual deep-layer network parameters;
step E, determining the characteristic space similarity and the change trend between the current layer and the previous layer, so as to analyze the expression mode of the fault information from shallow to deep, visually reflect the internal structure of the monitored big data and enhance the understanding of the essence of the monitored big data;
and F, expressing fault recognition results based on the deep network, further forming a health situation map of the manufacturing process by using the recognition results, clearly expressing the health state of the manufacturing process, and showing the health state of the manufacturing process from multiple aspects of result recognition, trend development, confidence evaluation and the like by combining a radar map, an Asahi chart and the like.
Further, the historical fault data in the step a includes: the amplitude, phase and frequency of the signal generated during the manufacturing process; the signal generated during the manufacturing process consists of a fault signal and a noise signal.
Further, the step C specifically includes: through single-layer network's parameter visualization, the weight split of single-layer network training is the combination of a plurality of basis functions, thereby carries out single-layer network's feature extraction through the dot product transform of original signal and a plurality of basis functions.
Referring to fig. 2, further, the step D specifically includes:
d1, visualizing the parameters of the single-layer network;
step D2, acquiring an activation relation between a current layer neuron and a previous layer neuron in the deep network;
step D3, determining the maximum input mode for activating the neuron nodes of the current layer, and taking the nodes as the linear weighted combination of the filter of the previous layer;
d4, generating deep network parameters;
and D5, visualizing the deep network parameters.
Further, the step E specifically includes:
and determining the characteristic and the variation trend of the characteristic space similarity between the current layer and the previous layer through the characteristics extracted by the layer-by-layer visual network.
The embodiment of the invention provides an intelligent expression device for a fault identification result in an intelligent manufacturing process, which comprises a control module and a storage module for storing a control instruction, wherein the control module reads the instruction and executes the following steps:
step A, collecting historical fault signals generated in the manufacturing process, eliminating noise signals and generating sample fault data;
b, generating single-layer network data from the sample fault data;
step C, splitting the weight of single-layer network training into a plurality of combinations of basis functions;
d, generating visual deep-layer network parameters;
step E, determining the characteristic space similarity and the change trend between the current layer and the previous layer, so as to analyze the expression mode of the fault information from shallow to deep, visually reflect the internal structure of the monitored big data and enhance the understanding of the essence of the monitored big data;
and F, expressing fault recognition results based on the deep network, further forming a health situation map of the manufacturing process by using the recognition results, clearly expressing the health state of the manufacturing process, and showing the health state of the manufacturing process from multiple aspects of result recognition, trend development, confidence evaluation and the like by combining a radar map, an Asahi chart and the like.
Further, the historical fault data in the step a includes: the amplitude, phase and frequency of the signal generated during the manufacturing process; the signal generated during the manufacturing process consists of a fault signal and a noise signal.
Further, the step C of the control module reading the instruction specifically executes the steps of:
through single-layer network's parameter visualization, the weight split of single-layer network training is the combination of a plurality of basis functions, thereby carries out single-layer network's feature extraction through the dot product transform of original signal and a plurality of basis functions.
Further, the step D of reading the instruction by the control module specifically executes the steps of:
d1, visualizing the parameters of the single-layer network;
step D2, acquiring an activation relation between a current layer neuron and a previous layer neuron in the deep network;
step D3, determining the maximum input mode for activating the neuron nodes of the current layer, and taking the nodes as the linear weighted combination of the filter of the previous layer;
d4, generating deep network parameters;
and D5, visualizing the deep network parameters.
Further, the step E of reading the instruction by the control module specifically executes the steps of:
and determining the characteristic and the variation trend of the characteristic space similarity between the current layer and the previous layer through the characteristics extracted by the layer-by-layer visual network.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and the present invention shall fall within the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means.
Claims (2)
1. An intelligent expression method for a fault identification result in an intelligent manufacturing process is characterized by comprising the following steps:
step A, collecting historical fault signals generated in the manufacturing process, eliminating noise signals and generating sample fault data;
b, generating single-layer network data from the sample fault data;
step C, splitting the weight of single-layer network training into a plurality of combinations of basis functions;
d, generating visual deep-layer network parameters;
e, determining the characteristic and the variation trend of the feature space similarity between the current layer and the previous layer;
f, expressing a fault identification result based on the deep network;
wherein, the historical fault data in the step a includes: the amplitude, phase and frequency of the signal generated during the manufacturing process; the signal generated in the manufacturing process consists of a fault signal and a noise signal;
the step C specifically comprises the following steps: splitting the weight of single-layer network training into a combination of a plurality of basis functions through parameter visualization of the single-layer network, and extracting the characteristics of the single-layer network through dot product transformation of an original signal and the plurality of basis functions;
the step D specifically comprises the following steps:
d1, visualizing the parameters of the single-layer network;
step D2, acquiring an activation relation between a current layer neuron and a previous layer neuron in the deep network;
step D3, determining the maximum input mode for activating the neuron nodes of the current layer, and taking the nodes as the linear weighted combination of the filter of the previous layer;
d4, generating deep network parameters;
step D5, visualizing the deep network parameters;
the step E specifically comprises the following steps:
and determining the characteristic and the variation trend of the characteristic space similarity between the current layer and the previous layer through the characteristics extracted by the layer-by-layer visual network.
2. The intelligent expression device for the fault identification result in the intelligent manufacturing process is characterized by comprising a control module and a storage module for storing control instructions, wherein the control module reads the instructions to execute the following steps:
step A, collecting historical fault signals generated in the manufacturing process, eliminating noise signals and generating sample fault data;
b, generating single-layer network data from the sample fault data;
step C, splitting the weight of single-layer network training into a plurality of combinations of basis functions;
d, generating visual deep-layer network parameters;
e, determining the characteristic and the variation trend of the feature space similarity between the current layer and the previous layer;
f, expressing a fault identification result based on the deep network;
wherein, the historical fault data in the step a includes: the amplitude, phase and frequency of the signal generated during the manufacturing process; the signal generated in the manufacturing process consists of a fault signal and a noise signal;
the step C of reading the instruction by the control module specifically comprises the following steps:
splitting the weight of single-layer network training into a combination of a plurality of basis functions through parameter visualization of the single-layer network, and extracting the characteristics of the single-layer network through dot product transformation of an original signal and the plurality of basis functions;
the step D of reading the instruction by the control module specifically comprises the following steps:
d1, visualizing the parameters of the single-layer network;
step D2, acquiring an activation relation between a current layer neuron and a previous layer neuron in the deep network;
step D3, determining the maximum input mode for activating the neuron nodes of the current layer, and taking the nodes as the linear weighted combination of the filter of the previous layer;
d4, generating deep network parameters;
step D5, visualizing the deep network parameters;
the step E of reading the instruction by the control module specifically comprises the following steps:
and determining the characteristic and the variation trend of the characteristic space similarity between the current layer and the previous layer through the characteristics extracted by the layer-by-layer visual network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811113319.XA CN109359767B (en) | 2018-09-25 | 2018-09-25 | Intelligent expression method and device for fault recognition result in intelligent manufacturing process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811113319.XA CN109359767B (en) | 2018-09-25 | 2018-09-25 | Intelligent expression method and device for fault recognition result in intelligent manufacturing process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109359767A CN109359767A (en) | 2019-02-19 |
| CN109359767B true CN109359767B (en) | 2022-03-25 |
Family
ID=65351356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811113319.XA Active CN109359767B (en) | 2018-09-25 | 2018-09-25 | Intelligent expression method and device for fault recognition result in intelligent manufacturing process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109359767B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN214492536U (en) | 2021-01-27 | 2021-10-26 | 杭州海康机器人技术有限公司 | Differential drive device and automatic guided vehicle |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6904330B2 (en) * | 2002-08-07 | 2005-06-07 | Kimberly-Clark Worldwide, Inc. | Manufacturing information and troubleshooting system and method |
| CN104914851B (en) * | 2015-05-21 | 2017-05-24 | 北京航空航天大学 | Adaptive fault detection method for airplane rotation actuator driving device based on deep learning |
| US10712738B2 (en) * | 2016-05-09 | 2020-07-14 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for industrial internet of things data collection for vibration sensitive equipment |
| CN106953802B (en) * | 2017-03-01 | 2020-03-03 | 浙江工商大学 | Network optimal path selection method based on deep learning |
| EP3607506B1 (en) * | 2017-04-17 | 2021-07-14 | Cerebras Systems Inc. | Fabric vectors for deep learning acceleration |
-
2018
- 2018-09-25 CN CN201811113319.XA patent/CN109359767B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109359767A (en) | 2019-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112783940B (en) | Multi-source time sequence data fault diagnosis method and medium based on graph neural network | |
| Li et al. | Mechanical fault diagnosis based on redundant second generation wavelet packet transform, neighborhood rough set and support vector machine | |
| CN102824172B (en) | EEG (electroencephalogram) feature extraction method | |
| CN112486097A (en) | Cutting platform wear state monitoring method and system based on model algorithm and readable storage medium | |
| CN113177537B (en) | Fault diagnosis method and system for rotary mechanical equipment | |
| CN109262369B (en) | Cutter state detection system and method | |
| CN112454008A (en) | Cutting platform service life prediction method and system based on network model and readable storage medium | |
| CN110261080B (en) | Heterogeneous rotary mechanical anomaly detection method and system based on multi-mode data | |
| EP2370837A1 (en) | Method and system for real time production management and reservoir characterization | |
| CN105626502A (en) | Plunger pump health assessment method based on wavelet packet and Laplacian Eigenmap | |
| CN115359386A (en) | Safe fishing method, system and medium for oceanic fishery based on Internet of things | |
| CN109359767B (en) | Intelligent expression method and device for fault recognition result in intelligent manufacturing process | |
| CN110263944A (en) | A kind of multivariable failure prediction method and device | |
| Soualhi et al. | PHM survey: Implementation of signal processing methods for monitoring bearings and gearboxes | |
| CN116625683A (en) | Wind turbine generator system bearing fault identification method, system and device and electronic equipment | |
| CN117437933A (en) | Feature cluster combination generation type learning-based unsupervised detection method for fault of voiceprint signal of transformer | |
| CN110929677A (en) | Vibration data on-line monitoring analysis system | |
| CN114844796B (en) | Method, device and medium for abnormality detection of time sequence KPI | |
| Ning et al. | An intelligent device fault diagnosis method in industrial internet of things | |
| CN115221769A (en) | Fault prediction method, system, electronic equipment and storage medium | |
| CN114217147A (en) | Acoustic fingerprint early warning device for large power transformer | |
| CN112417966A (en) | Multi-dimensional machine fault detection method based on audio signal characteristics and AI algorithm | |
| Su et al. | Fault diagnosis method based on a new manifold learning framework | |
| Oliveira et al. | Multiway analysis in data SONAR classification | |
| Liu | Fault Detection Method of CNC Machine Tool Based on Wavelet Transform |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 528000 Foshan Institute of science and technology, Xianxi reservoir West Road, Shishan town, Nanhai District, Foshan City, Guangdong Province Patentee after: Foshan University Country or region after: China Address before: 528000 Foshan Institute of science and technology, Xianxi reservoir West Road, Shishan town, Nanhai District, Foshan City, Guangdong Province Patentee before: FOSHAN University Country or region before: China |