CN111783880A - Complicated transmission chain predictive maintenance system and method based on industrial Internet of things - Google Patents
Complicated transmission chain predictive maintenance system and method based on industrial Internet of things Download PDFInfo
- Publication number
- CN111783880A CN111783880A CN202010618860.7A CN202010618860A CN111783880A CN 111783880 A CN111783880 A CN 111783880A CN 202010618860 A CN202010618860 A CN 202010618860A CN 111783880 A CN111783880 A CN 111783880A
- Authority
- CN
- China
- Prior art keywords
- data
- frequency
- cloud
- algorithm
- intelligent
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/023—Power-transmitting endless elements, e.g. belts or chains
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/20—Administration of product repair or maintenance
Abstract
A complicated transmission chain predictive maintenance system based on an industrial Internet of things comprises hardware equipment and a system control module, wherein the hardware equipment comprises a high-frequency sensor network, a high-frequency signal processing device and intelligent hardware, the high-frequency sensor network is used for collecting working signals in real time or periodically, the high-frequency signal processing device is used for preprocessing the working signals, and the intelligent hardware utilizes a wavelet characteristic extraction algorithm to process data at a local end and uploads the data to a cloud end; the cloud is used for verifying and storing data, analyzing the data by using an intelligent algorithm with feature extraction, and finally outputting a corresponding fault feature state. The invention adopts a special data processing device aiming at the related high-frequency signals, disperses the processing capacity required by the core processing unit and improves the stability of the system; according to the characteristics of complex vibration signals, high-frequency data dimensionality reduction is completed on the edge side through feature extraction, an equipment state degradation analysis edge cloud data framework is constructed by combining with a cloud algorithm, and predictive maintenance of a complex transmission chain mechanism is achieved.
Description
Technical Field
The invention relates to the field of online state monitoring and fault diagnosis, in particular to a system and a method for equipment predictive maintenance aiming at a complex transmission chain mechanism by adopting an industrial Internet of things architecture.
Background
For a complex transmission chain mechanism, the fault mechanism is complex due to the fact that influence factors of rear-section loads are various. For the drive chain mechanism of the core, it is often the key of the whole system. If the operation state of the mechanism can be accurately monitored and the future operation state of the mechanism can be predicted, the occurrence of faults can be effectively avoided, particularly the deterioration of progressive faults is delayed, and the predictive maintenance of the mechanism can be efficiently realized.
The predictive maintenance systems of the existing mechanisms of this type have considerable limitations:
on one hand, the analysis and diagnosis functions of the product are weak and single, the product is only limited to local analysis, the monitoring of fault risks is lacked, the alarm is sent only when obvious faults occur, and early warning is difficult to realize; on the other hand, most of the fault diagnosis methods of the existing products are based on the analysis of static parameters by using the traditional signal analysis method, such as analyzing vibration signals and temperature parameters at certain moments by using a spectrogram and diagnosing faults by comparing fault characteristic frequency and characteristic amplitude, and the methods need strong field knowledge and rich experience of workers. More importantly, the methods cannot reflect the characteristic change process of the system, cannot meet the fault diagnosis requirement of the dynamic system, and are still in passive protection.
At the same time, the limitations of the technology also stem from the following reasons:
1. complexity of the kind of fault signal. The mechanism model of the system is complex, the related information is various, and meanwhile, the signals have the problem of multiple time scales, such as low-frequency temperature signals related to environmental information, high-frequency vibration signals related to mechanical mechanisms and high-frequency current and voltage signals related to electric dragging;
2. the fault signal features are difficult to extract. The system is complex in transmission structure and specific in fault state, so that fault types are difficult to extract, and signals in a degradation process are complex;
3. limitations of the fault analysis method. The analysis method for the system mainly comprises the following steps: based on the analysis of signals, through time domain and frequency domain signals, and combined with related experience analysis, the method needs to introduce artificial experience; based on the judgment of the analytical model, the failure of the state is judged through parameter and state signal evaluation, and the method strongly depends on the precision of the mathematical model; based on the judgment of knowledge, an artificial intelligence related algorithm and an expert system are adopted to construct a model failure knowledge model, and the method needs a large amount of data to train the model.
Disclosure of Invention
Aiming at the fault failure characteristic of a complex transmission chain mechanism, the invention aims to provide a fault predictive maintenance system based on an industrial Internet of things, which is realized mainly by two parts, namely hardware deployment of the complex transmission chain mechanism and a system data link.
The purpose of the invention is realized by adopting the following technical scheme. The complex transmission chain predictive maintenance system based on the industrial Internet of things comprises hardware equipment and a cloud end;
the hardware equipment comprises a high-frequency sensor network, a high-frequency signal processing device and intelligent hardware, wherein the high-frequency sensor network is used for collecting working signals of the complex transmission chain mechanism in real time or periodically and transmitting the collected working signals to the high-frequency signal processing device; the high-frequency signal processing device is used for preprocessing the working signal and transmitting the preprocessed working signal to the intelligent hardware; the intelligent hardware is used for eliminating abnormal data in the working signals, performing feature extraction on the eliminated working signals by using a wavelet characteristic extraction algorithm, and performing time sequence data queuing on the extracted feature data; the intelligent hardware is also provided with a transmission interface from a data edge side to a cloud end;
the cloud comprises a verification and storage module, an analysis module and a model training module, wherein the verification and storage module is used for verifying the accuracy of data and storing the data in the cloud; the analysis module analyzes the verified and stored data by using an intelligent algorithm with feature extraction and outputs a corresponding fault feature state; the model training module is used for training a wavelet characteristic extraction algorithm used by the intelligent hardware and an intelligent algorithm with characteristic extraction used by the analysis module, and issuing the trained characteristic value to the intelligent hardware and the analysis module.
Furthermore, the high-frequency sensor network comprises a Hall sensor, a vibration displacement sensor and a temperature sensor.
Furthermore, the high-frequency signal processing device comprises a voltage and current signal acquisition and processing device and a vibration displacement signal acquisition and processing device.
Further, the intelligent hardware is but not limited to one of a Linux-based PLC and an intelligent gateway device.
Further, the intelligent algorithm with feature extraction adopts a machine learning algorithm, such as a BP neural network algorithm.
The purpose of the invention is realized by adopting the following technical scheme. The complex transmission chain predictive maintenance method based on the industrial Internet of things comprises a local end data processing part and a cloud end data processing part;
the local end data processing part comprises the following implementation steps:
(1) the method comprises the steps that a Hall sensor, a vibration displacement sensor and a temperature sensor are arranged aiming at a complex transmission chain mechanism to form a sensor network, and the Hall sensor, the vibration displacement sensor and the temperature sensor are used for respectively collecting a high-frequency voltage current signal, a high-frequency vibration signal and a temperature signal of a complex transmission chain system in real time or periodically;
(2) training a wavelet characteristic extraction algorithm used by intelligent hardware at a local end and an intelligent algorithm with characteristic extraction used by an analysis module at a cloud end by utilizing big data in a cloud platform, and issuing a characteristic value obtained by training to the intelligent hardware and the analysis module;
(3) preprocessing a high-frequency voltage current signal by using a voltage current signal acquisition processing device to complete complex frequency domain transformation of a voltage current periodic signal; preprocessing the high-frequency vibration signal by using a vibration displacement signal acquisition and processing device to finish the preparation of a wavelet algorithm of the vibration signal;
(4) transmitting the preprocessed high-frequency voltage current signals, the preprocessed high-frequency vibration signals and the preprocessed temperature signals to intelligent hardware for processing, eliminating abnormal data in various signals, performing feature extraction on the eliminated data by using a wavelet characteristic extraction algorithm, and performing time sequence data queuing on the extracted feature data;
(5) transmitting the processed high-frequency voltage current data, high-frequency vibration data and temperature data to a cloud terminal by using a transmission interface from a data edge side to the cloud terminal;
the cloud data processing part comprises the following implementation steps:
(1) respectively verifying the accuracy of various data arriving at a cloud server, and simultaneously storing the data in the cloud;
(2) and carrying out data analysis by using an intelligent algorithm with feature extraction to obtain a corresponding fault feature state.
Compared with the prior art, the invention has the following advantages and technical effects:
(1) the edge side data acquisition and processing hardware facilities adopt a dedicated data processing device (namely a high-frequency signal processing device) aiming at the related high-frequency characteristic signals, so that the processing capacity required by a core processing unit is dispersed, the stability of the system is improved, and the problem of multi-time scale data fusion is solved;
(2) according to the data transmission link and the separated intelligent algorithm, high-frequency data dimensionality reduction is completed on the edge side through feature extraction aiming at the characteristics of a complex vibration signal, an equipment state degradation analysis edge cloud data architecture is constructed by combining with a cloud algorithm, and predictive maintenance of a complex transmission link mechanism based on an industrial Internet of things architecture is achieved.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
FIG. 1 is a hardware deployment diagram of a complex drive train mechanism.
Fig. 2 is a schematic diagram of a predictive maintenance system data link based on the industrial internet of things.
[ reference numerals ]
101-motor, 102-coupler, 103-gear box, 104-belt transmission mechanism, 105-belt wheel, 106-three-phase cable, 107-Hall sensor, 108-vibration displacement signal acquisition and processing device, 109-vibration displacement sensor, 110-current and voltage signal acquisition and processing device, 111-temperature sensor, and 112-intelligent hardware;
201-sensor data, 202-data preprocessing, 203-wavelet characteristic extraction algorithm, 204-data edge side to cloud end transmission interface, 205-local end data processing part, 206-edge layer to cloud end data transmission channel, 207-cloud end data verification and storage, 208-intelligent algorithm with characteristic extraction, 209-fault characteristic state output, 210-cloud end data processing part, 211-wavelet combined intelligent algorithm model training, 212-characteristic values of model training are used in the local end wavelet characteristic extraction algorithm, and 213-characteristic values of model training are used in the cloud end intelligent algorithm.
Detailed Description
The following further describes the implementation of the present invention with reference to the drawings, but the embodiments and the protection scope of the present invention are not limited thereto.
The invention relates to a complex transmission chain predictive maintenance system based on an industrial Internet of things. The hardware equipment comprises a high-frequency sensor network, a high-frequency signal processing device and intelligent hardware, wherein the high-frequency sensor network comprises a temperature sensor, a vibration sensor, a displacement sensor and a current-voltage sensor; the high-frequency signal processing device comprises a vibration signal acquisition processing device and a current and voltage signal acquisition processing device, and is mainly used for preprocessing data; the intelligent hardware mainly implements local processing and transmission of data, and can be, but is not limited to, a Linux-based PLC, an intelligent gateway device, and the like. The data link comprises a data local processing part and a cloud processing part, wherein the local processing part mainly comprises data acquisition, high-frequency signal preprocessing, data transmission preprocessing and edge cloud transmission; the cloud processing mainly comprises cloud data verification and storage and intelligent algorithm analysis, wherein the intelligent algorithm is mainly a machine learning algorithm and can be but is not limited to a BP neural network algorithm; the high-frequency signal preprocessing is like: complex frequency domain transformation of voltage and current periodic signals and preparation of a wavelet algorithm of vibration signals; the main functions of the data transmission preprocessing are abnormal data elimination, data dimension reduction and data queuing; the data edge cloud transmission and cloud data verification and storage scheme is a mainstream industrial Internet of things platform scheme; the intelligent algorithm of the cloud end is combined with the algorithm of the local end, an input layer and an output layer of a related algorithm are respectively deployed according to the local end and the cloud end, the intelligent algorithm is combined with the local end to mainly extract related characteristic parameters as data preprocessing, and the intelligent algorithm is combined with a machine learning algorithm to extract a related degradation state.
Please refer to fig. 1 and fig. 2, which illustrate an embodiment of the present invention. The complex drive chain system of this embodiment is applied to a belt drive system, and includes a motor 101 as a power source, a gear box 103, a coupling 102 connecting an output shaft of the motor and an input shaft of the gear box, a belt drive 104 connecting a pulley at an input end and an output shaft of the gear box, a pulley 105 as an output end of the belt drive, and a three-phase cable 106 connecting the motor and a power source.
Referring to fig. 1, the hardware device includes a hall sensor 107, a voltage and current signal collecting and processing device 110 electrically connected to the hall sensor, a vibration displacement sensor 109, a vibration displacement signal collecting and processing device 108 electrically connected to the vibration displacement sensor, a temperature sensor 111, and an intelligent hardware 112 electrically connected to the voltage and current signal collecting and processing device, the vibration displacement signal collecting and processing device, and the temperature sensor. The hall sensor 107 is disposed on the three-phase cable 106, and is configured to collect a high-frequency current voltage signal related to a cable side in real time or periodically, and transmit the signal to the voltage-current signal collecting and processing device 110 for processing, and transmit the processed high-frequency current voltage signal to the intelligent hardware 112 through the device. The number of the vibration displacement sensors 109 is 3, the vibration displacement sensors are respectively arranged on the motor 101, the gear box 103 and the belt wheel 105, and the vibration displacement sensors are used for respectively acquiring high-frequency vibration signals of corresponding equipment in real time or periodically, transmitting the signals to the vibration displacement signal acquisition device 108 for processing, and transmitting the processed high-frequency vibration signals to the intelligent hardware 112 through the device. The temperature sensor 111 is used for acquiring temperature signals of a core area in a complex drive chain system in real time or periodically, for example, in the motor in the embodiment, the matching area of the rotor and the stator is an area with high heat dissipation capacity, and the temperature sensor is mounted on a housing of the motor and is used for acquiring the temperature signals of the area and transmitting the temperature signals to the intelligent hardware 112.
Referring to fig. 2, based on the hardware shown in fig. 1, the present embodiment provides a complex driving chain predictive maintenance method based on the industrial internet of things, wherein a data link of the complex driving chain predictive maintenance method mainly includes a data processing portion 205 at a local side and a cloud data processing portion 210. A data processing part at a local side deploys three types of sensors aiming at a complex transmission chain mechanism to form a high-frequency sensor network, and respectively collects a high-frequency voltage current signal, a high-frequency vibration signal and a temperature signal in real time or periodically through a Hall sensor 107, a vibration displacement sensor 109 and a temperature sensor 111; the high-frequency voltage and current signals are preprocessed through a voltage and current signal acquisition and processing device 110 to finish complex frequency domain transformation of voltage and current periodic signals, and the high-frequency vibration signals are preprocessed through a vibration displacement signal acquisition and processing device 108 to finish preparation of a wavelet algorithm of the vibration signals; the preprocessed high-frequency voltage current signals, high-frequency vibration signals and temperature signals are transmitted to the intelligent hardware 112 to be processed, abnormal data in various signals are removed, the removed data are subjected to feature extraction through a wavelet characteristic extraction algorithm 203 loaded by the intelligent hardware, and the extracted feature data are subjected to time sequence data queuing, so that the influence of unreliability on signal transmission is reduced; the processed high-frequency voltage current signal, high-frequency vibration signal and temperature signal are transmitted to the cloud end through a transmission interface 204 from the data edge side to the cloud end, which is set by intelligent hardware, and the data transmission channel 206 from the data edge layer to the cloud end is accessed into an industrial internet of things protocol. The cloud data processing part is used for respectively verifying the accuracy of the related data by the verification and storage module after the data reaches the cloud server, and storing the data in the cloud to finish the verification and storage 207 of the cloud data; the verified and stored data is subjected to data analysis by an intelligent algorithm 208 with feature extraction to obtain a corresponding fault feature state, and the final fault feature state output 209 is completed.
The predictive maintenance system further comprises a model training module of wavelet combined with an intelligent algorithm, wherein the model training module is used for training a wavelet characteristic extraction algorithm 203 of the local end and an intelligent algorithm 208 with characteristic extraction of the cloud end, and issuing a characteristic value obtained by training to the wavelet characteristic extraction algorithm of the local end and the intelligent algorithm of the cloud end for use.
The invention has not been described in detail in part of the common general knowledge of those skilled in the art.
Finally, the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting, and other modifications or equivalent substitutions made by the technical solutions of the present invention by those of ordinary skill in the art should be covered within the scope of the claims of the present invention as long as they do not depart from the design and scope of the technical solutions of the present invention.
Claims (6)
1. A complex transmission chain predictive maintenance system based on an industrial Internet of things is characterized by comprising hardware equipment and a cloud end;
the hardware equipment comprises a high-frequency sensor network, a high-frequency signal processing device and intelligent hardware, wherein the high-frequency sensor network is used for collecting working signals of the complex transmission chain mechanism in real time or periodically and transmitting the collected working signals to the high-frequency signal processing device; the high-frequency signal processing device is used for preprocessing the working signal and transmitting the preprocessed working signal to the intelligent hardware; the intelligent hardware is used for eliminating abnormal data in the working signals, performing feature extraction on the eliminated working signals by using a wavelet characteristic extraction algorithm, and performing time sequence data queuing on the extracted feature data; the intelligent hardware is also provided with a transmission interface from a data edge side to a cloud end;
the cloud comprises a verification and storage module, an analysis module and a model training module, wherein the verification and storage module is used for verifying the accuracy of data and storing the data in the cloud; the analysis module analyzes the verified and stored data by using an intelligent algorithm with feature extraction and outputs a corresponding fault feature state; the model training module is used for training a wavelet characteristic extraction algorithm used by the intelligent hardware and an intelligent algorithm with characteristic extraction used by the analysis module, and issuing the trained characteristic value to the intelligent hardware and the analysis module.
2. The industrial internet of things-based complex drive chain predictive maintenance system according to claim 1, wherein the high-frequency sensor network comprises a hall-type sensor, a vibration displacement-type sensor and a temperature sensor.
3. The system of claim 2, wherein the high-frequency signal processing device comprises a voltage-current signal acquisition and processing device and a vibration-displacement signal acquisition and processing device.
4. The system of claim 1, wherein the intelligent hardware is but not limited to one of a Linux-based PLC and an intelligent gateway device.
5. The system of claim 1, wherein the intelligent algorithm with feature extraction is a machine learning algorithm, such as a BP neural network algorithm.
6. A complex transmission chain predictive maintenance method based on an industrial Internet of things is characterized by comprising a local end data processing part and a cloud end data processing part;
the local end data processing part comprises the following implementation steps:
(1) the method comprises the steps that a Hall sensor, a vibration displacement sensor and a temperature sensor are arranged aiming at a complex transmission chain mechanism to form a sensor network, and the Hall sensor, the vibration displacement sensor and the temperature sensor are used for respectively collecting a high-frequency voltage current signal, a high-frequency vibration signal and a temperature signal of the complex transmission chain mechanism in real time or periodically;
(2) training a wavelet characteristic extraction algorithm used by intelligent hardware at a local end and an intelligent algorithm with characteristic extraction used by an analysis module at a cloud end by utilizing big data in a cloud platform, and issuing a characteristic value obtained by training to the intelligent hardware and the analysis module;
(3) preprocessing a high-frequency voltage current signal by using a voltage current signal acquisition processing device to complete complex frequency domain transformation of a voltage current periodic signal; preprocessing the high-frequency vibration signal by using a vibration displacement signal acquisition and processing device to finish the preparation of a wavelet algorithm of the vibration signal;
(4) transmitting the preprocessed high-frequency voltage current signals, the preprocessed high-frequency vibration signals and the preprocessed temperature signals to intelligent hardware for processing, eliminating abnormal data in various signals, performing feature extraction on the eliminated data by using a wavelet characteristic extraction algorithm, and performing time sequence data queuing on the extracted feature data;
(5) transmitting the processed high-frequency voltage current data, high-frequency vibration data and temperature data to a cloud terminal by using a transmission interface from a data edge side to the cloud terminal;
the cloud data processing part comprises the following implementation steps:
(1) respectively verifying the accuracy of various data arriving at a cloud server, and simultaneously storing the data in the cloud;
(2) and carrying out data analysis by using an intelligent algorithm with feature extraction to obtain a corresponding fault feature state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010618860.7A CN111783880A (en) | 2020-06-30 | 2020-06-30 | Complicated transmission chain predictive maintenance system and method based on industrial Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010618860.7A CN111783880A (en) | 2020-06-30 | 2020-06-30 | Complicated transmission chain predictive maintenance system and method based on industrial Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111783880A true CN111783880A (en) | 2020-10-16 |
Family
ID=72760059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010618860.7A Pending CN111783880A (en) | 2020-06-30 | 2020-06-30 | Complicated transmission chain predictive maintenance system and method based on industrial Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783880A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1976401A (en) * | 2005-12-02 | 2007-06-06 | 富士胶片株式会社 | Remote shooting system and camera system |
| CN102520697A (en) * | 2011-12-16 | 2012-06-27 | 西安建筑科技大学 | Onsite information preprocessing method of remote cooperative diagnosis |
| CN108873830A (en) * | 2018-05-31 | 2018-11-23 | 华中科技大学 | A kind of production scene online data collection analysis and failure prediction system |
| CN109724791A (en) * | 2019-02-22 | 2019-05-07 | 朱清 | A kind of intelligence vibration analysis and trouble-shooter and its working method |
| US20190191287A1 (en) * | 2015-01-17 | 2019-06-20 | Machinesense, Llc | System and method for turbomachinery preventive maintenance and root cause failure determination |
| CN110059775A (en) * | 2019-05-22 | 2019-07-26 | 湃方科技(北京)有限责任公司 | Rotary-type mechanical equipment method for detecting abnormality and device |
| US20200051419A1 (en) * | 2017-10-11 | 2020-02-13 | Analog Devices Global Unlimited Company | Cloud-based machine health monitoring |
| CN111273196A (en) * | 2020-03-11 | 2020-06-12 | 杭州安脉盛智能技术有限公司 | Health management system and method applied to nuclear power large-scale power transformer |
-
2020
- 2020-06-30 CN CN202010618860.7A patent/CN111783880A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1976401A (en) * | 2005-12-02 | 2007-06-06 | 富士胶片株式会社 | Remote shooting system and camera system |
| CN102520697A (en) * | 2011-12-16 | 2012-06-27 | 西安建筑科技大学 | Onsite information preprocessing method of remote cooperative diagnosis |
| US20190191287A1 (en) * | 2015-01-17 | 2019-06-20 | Machinesense, Llc | System and method for turbomachinery preventive maintenance and root cause failure determination |
| US20200051419A1 (en) * | 2017-10-11 | 2020-02-13 | Analog Devices Global Unlimited Company | Cloud-based machine health monitoring |
| CN108873830A (en) * | 2018-05-31 | 2018-11-23 | 华中科技大学 | A kind of production scene online data collection analysis and failure prediction system |
| CN109724791A (en) * | 2019-02-22 | 2019-05-07 | 朱清 | A kind of intelligence vibration analysis and trouble-shooter and its working method |
| CN110059775A (en) * | 2019-05-22 | 2019-07-26 | 湃方科技(北京)有限责任公司 | Rotary-type mechanical equipment method for detecting abnormality and device |
| CN111273196A (en) * | 2020-03-11 | 2020-06-12 | 杭州安脉盛智能技术有限公司 | Health management system and method applied to nuclear power large-scale power transformer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112989712B (en) | Aeroengine fault diagnosis method based on 5G edge calculation and deep learning | |
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN110376522B (en) | Motor fault diagnosis method of data fusion deep learning network | |
| US11113905B2 (en) | Fault detection system and method for vehicle system prognosis | |
| CN106066184B (en) | System and method for detecting vehicle system faults | |
| Zhang et al. | Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network | |
| CN103115789B (en) | Second generation small-wave support vector machine assessment method for damage and remaining life of metal structure | |
| CN111504676A (en) | Equipment fault diagnosis method, device and system based on multi-source monitoring data fusion | |
| CN104386449B (en) | On-line checking intelligent protection device is taken turns end to end for mining belt conveyer | |
| CN107247230A (en) | A kind of electric rotating machine state monitoring method based on SVMs and data-driven | |
| CN107909118A (en) | A kind of power distribution network operating mode recording sorting technique based on deep neural network | |
| CN107061183A (en) | A kind of automation method for diagnosing faults of offshore wind farm unit | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN113776794A (en) | Fault diagnosis method, device and system for embedded edge computing | |
| CN111795819B (en) | Gear box fault diagnosis method integrating vibration and current signal collaborative learning | |
| CN106656669A (en) | Equipment parameter abnormity detection system and method based on self-adaptive setting of threshold | |
| CN115238785A (en) | Rotary machine fault diagnosis method and system based on image fusion and integrated network | |
| CN112305388A (en) | On-line monitoring and diagnosing method for partial discharge fault of generator stator winding insulation | |
| CN105099804B (en) | Detection method, server and the terminal of unit failure | |
| CN113697424B (en) | Belt conveyor monitoring and fault diagnosis system and method based on cloud technology | |
| CN111783880A (en) | Complicated transmission chain predictive maintenance system and method based on industrial Internet of things | |
| CN112819029A (en) | Novel machine learning method for diagnosing gearbox fault based on multi-scale permutation entropy | |
| CN107766882A (en) | Epicyclic gearbox method for diagnosing faults based on the more granularities of data-driven quantization characteristic | |
| CN105424387A (en) | Steering gear real-time remote intelligent monitoring system | |
| CN214330806U (en) | Wind driven generator system and fault analysis equipment of wind driven generator |
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 |