CN110134571B - Method and device for monitoring health state of rotary mechanical equipment - Google Patents
Method and device for monitoring health state of rotary mechanical equipment Download PDFInfo
- Publication number
- CN110134571B CN110134571B CN201910431259.4A CN201910431259A CN110134571B CN 110134571 B CN110134571 B CN 110134571B CN 201910431259 A CN201910431259 A CN 201910431259A CN 110134571 B CN110134571 B CN 110134571B
- Authority
- CN
- China
- Prior art keywords
- state
- data
- type
- status
- analysis result
- 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
Images
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
Abstract
The embodiment of the invention provides a health state monitoring method and device for rotary mechanical equipment, wherein the method comprises the following steps: acquiring state data in the running process of the rotary mechanical equipment; selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis to obtain a state analysis result corresponding to each state type; wherein the status type includes: the system comprises a start-stop state, an abnormal state and a working condition state, wherein the state data are related parameter data in the running process. And selecting corresponding state data according to different state types, and carrying out feature extraction and machine learning algorithm analysis to obtain a state analysis result corresponding to each state type, so that the accuracy and timeliness of the state analysis result can be ensured.
Description
Technical Field
The invention relates to the technical field of mechanical state monitoring, in particular to a method and a device for monitoring the health state of rotary mechanical equipment.
Background
Rotary machines are machines that rely primarily on rotary motion to perform specific functions, and typical rotary machines include steam turbines, gas turbines, centrifugal and axial compressors, fans, pumps, water turbines, generators, aeroengines, and the like.
At present, online monitoring of the health of rotary mechanical equipment generally comprises equipment abnormality detection, fault diagnosis and the like, and the online abnormality detection and working condition identification of the mechanical equipment are mainly realized through a threshold value and an expert system. The method comprises the steps of deploying a sensor on the mechanical equipment, collecting state parameters such as triaxial vibration and temperature of the mechanical equipment on line, setting a triaxial vibration and temperature threshold, alarming when the triaxial vibration and temperature threshold is exceeded, and sending state data to the cloud platform through a network. After receiving the alarm, the analyst manually analyzes the vibration spectrum, judges the reason of the alarm and determines that the pump fails.
The existing online health monitoring method of the rotary mechanical equipment is mainly based on manual abnormality detection and fault analysis, is doped with excessive subjective factors, and cannot guarantee the accuracy and timeliness of discrimination.
Disclosure of Invention
In order to solve the above problems, an embodiment of the present invention provides a method and an apparatus for monitoring health status of a rotary mechanical device.
In a first aspect, an embodiment of the present invention provides a method for monitoring health status of a rotary mechanical device, including: acquiring state data in the running process of the rotary mechanical equipment; selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis to obtain a state analysis result corresponding to each state type; wherein the status type includes: the system comprises a start-stop state, an abnormal state and a working condition state, wherein the state data are related parameter data in the running process.
In a second aspect, an embodiment of the present invention provides a method for monitoring health status of a rotary mechanical device, including: if the state type, the state analysis result and the feature data corresponding to the state type are received, performing secondary analysis on the received feature data to verify the state analysis result; transmitting the verification result to the terminal or transmitting the verification result to the user side; after the terminal obtains state data in the running process of the rotary mechanical equipment, the state analysis result is obtained by selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis, wherein the state types comprise: the system comprises a start-stop state, an abnormal state and a working condition state, wherein the state data are related parameter data in the running process.
In a third aspect, an embodiment of the present invention provides a health status monitoring device for a rotary mechanical device, including: the acquisition module is used for acquiring state data in the running process of the rotary mechanical equipment; the processing module is used for selecting corresponding state data according to different state types, carrying out feature extraction and machine learning algorithm analysis, and obtaining a state analysis result corresponding to each state type; wherein the status type includes: the system comprises a start-stop state, an abnormal state and a working condition state, wherein the state data are related parameter data in the running process.
In a fourth aspect, an embodiment of the present invention provides a server, including: the processing module is used for carrying out secondary analysis on the received characteristic data if the state type, the state analysis result and the characteristic data corresponding to the state type are received, so as to realize verification of the state analysis result; the sending module is used for sending the verification result to the terminal or sending the verification result to the user side; after the terminal obtains state data in the running process of the rotary mechanical equipment, the state analysis result is obtained by selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis, wherein the state types comprise: the system comprises a start-stop state, an abnormal state and a working condition state, wherein the state data are related parameter data in the running process.
In a fifth aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor executes the program to implement the steps of the method for monitoring the health status of the rotary mechanical device according to the first aspect or the second aspect of the present invention.
In a sixth aspect, embodiments of the present invention provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for monitoring the health status of a rotary-type mechanical device of the first or second aspects of the present invention.
According to the health state monitoring method and device for the rotary mechanical equipment, the corresponding state data are selected according to different state types, feature extraction and machine learning algorithm analysis are carried out, the state analysis result corresponding to each state type is obtained, and the accuracy and timeliness of the state analysis result can be guaranteed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for monitoring health status of a rotary mechanical device according to an embodiment of the present invention;
fig. 2 is a diagram of a health status monitoring device of a rotary mechanical device according to an embodiment of the present invention;
FIG. 3 is a diagram of a server according to an embodiment of the present invention;
fig. 4 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention provides a health state monitoring method of rotary mechanical equipment. The execution body corresponding to the method may be a terminal disposed at one side of the rotary mechanical device, or may be a server in communication with the terminal, or may be implemented by interaction between the terminal and the server, which is not particularly limited in the embodiment of the present invention. For convenience of explanation, the embodiment of the invention takes the execution main body as the terminal and the server as examples, and the health state monitoring method of the rotary mechanical equipment provided by the embodiment of the invention is explained.
Fig. 1 is a flowchart of a method for monitoring health status of a rotary mechanical device according to an embodiment of the present invention, as shown in fig. 1, where the method for monitoring health status of a rotary mechanical device includes:
101, acquiring state data in the running process of the rotary mechanical equipment.
In 101, a data acquisition processing edge terminal, referred to as a terminal, is provided at a preset position of a rotary mechanical device (referred to as a mechanical device hereinafter). The terminal integrates acceleration, temperature and other sensors and is installed and fixed on mechanical equipment through stud, magnetic attraction, gluing and other modes. The state data are related parameter data in the operation process of the mechanical equipment, and the terminal can collect related state data of the mechanical equipment, such as vibration signal data, temperature data and the like.
102, selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis to obtain a state analysis result corresponding to each state type.
At 102, health status monitoring of a mechanical device is accomplished by detecting changes in different status types, including, but not limited to: a start-stop condition, an abnormal condition, and a condition. The change in the status data reflects the change in the status type, such as by comparing the value of the status data with a preset threshold value, thereby obtaining the change in the status type. In the embodiment of the invention, corresponding state data are selected for analysis according to different state types. For example, the magnitude of the acceleration of the vibration signal reflects the start-stop operating condition, and the temperature in the temperature signal reflects the start-stop oil temperature condition. So that the analysis data of the start-up and shut-down state includes vibration signal data and temperature signal data.
And extracting the characteristics of the state data, wherein the extracted characteristic data comprises, but is not limited to, the average value, the maximum value, the peak-to-peak value and other time domain characteristics of specific parameters in the state data, and the frequency domain characteristics such as frequency spectrum characteristics, envelope spectrum characteristics, wavelet energy and the like. The extracted features are analyzed through a machine algorithm, a state analysis result corresponding to each state type can be obtained, and the specific algorithm type can be determined according to the type of the state data to be analyzed.
After the corresponding state analysis result of the state type is determined, the health state monitoring of the mechanical equipment can be realized through methods such as alarming, displaying state information in real time and the like.
According to the health state monitoring method for the rotary mechanical equipment, corresponding state data are selected according to different state types, feature extraction and machine learning algorithm analysis are carried out, state analysis results corresponding to each state type are obtained, and accuracy and timeliness of the state analysis results can be guaranteed.
Based on the content of the foregoing embodiment, as an optional embodiment, after obtaining a state analysis result corresponding to each state type, the method further includes: if the analysis results of the state types are changed, the state data or the characteristic data corresponding to the state types are sent to the server in combination with the state types and the state analysis results, so that the server can check the state analysis results after performing secondary analysis according to the corresponding characteristic data.
Considering that the terminal arranged at the mechanical equipment end has limited computing capability, when the terminal judges that the state type is changed, if the terminal starts or stops the operation, corresponding data and information are sent to a server for further computation, so that a more accurate computing result is obtained. Specifically, if the analysis result of the state type obtained after the analysis changes (is inconsistent with the state monitored before), the state type, the state analysis result and the characteristic data corresponding to the state type are sent to the server for secondary analysis. The secondary analysis in the embodiment of the invention is relative to the (primary) analysis of the feature extraction and machine learning algorithms that have been performed by the terminal. The server has larger computing power, so that an algorithm model with higher accuracy can be realized, and compared with a terminal, the accuracy is higher. And secondary analysis and verification are carried out at the server end, so that the characteristic utilization rate is higher, and a more accurate calculation result can be obtained. The server in the embodiment of the invention can be a local server or a cloud server.
According to the health state monitoring method for the rotary mechanical equipment, the characteristic data corresponding to the state type is sent to the server, and compared with the transmission of the complete state data, the bandwidth resource overhead for transmitting the complete state data can be reduced to a great extent. After the server performs high-accuracy secondary analysis according to the corresponding characteristic data, the state analysis result is checked, and a more accurate state analysis result can be obtained.
Based on the foregoing embodiments, as an optional embodiment, the state type is a start-stop state, the state data includes vibration signal data of the mechanical device, and accordingly, corresponding state data is selected according to different state types, feature extraction and machine learning algorithm analysis are performed, and a state analysis result corresponding to each state type is obtained, including: extracting features of vibration signal data of mechanical equipment, and analyzing corresponding machine learning algorithm to obtain a state analysis result of a start-stop state; the machine learning algorithm includes: linear models, nonlinear models, tree models, and probabilistic models.
The start-stop state can be analyzed through vibration signal data of mechanical equipment, and the algorithm analysis of machine learning can be correspondingly realized by adopting algorithms such as a linear model, a nonlinear model, a tree model, a probability model and the like in machine learning, so that a state analysis result of the start-stop state is obtained. For example, the method is realized by logistic regression in a linear model, a support vector machine, a multi-layer perceptron in a nonlinear model, a decision tree in a tree model, bayes and other algorithms.
According to the health state monitoring method for the rotary mechanical equipment, provided by the embodiment of the invention, the vibration signal data of the mechanical equipment is subjected to feature extraction, and corresponding machine learning algorithm analysis is performed, so that the analysis result of the start-stop state can be accurately obtained.
Based on the foregoing embodiments, as an optional embodiment, the state types are abnormal states, the state data includes mechanical equipment vibration signal data and temperature signal data, and accordingly, corresponding state data is selected according to different state types, feature extraction and machine learning algorithm analysis are performed, and a state analysis result corresponding to each state type is obtained, including: extracting characteristics of vibration signal data and temperature signal data of mechanical equipment, and analyzing corresponding machine learning algorithms to obtain a state analysis result of an abnormal state; wherein the machine learning algorithm comprises: a density-based detection algorithm, a proximity-based detection algorithm, a model-based detection algorithm, etc.
The abnormal state can be analyzed through vibration signal data and temperature signal data of the mechanical equipment, and correspondingly, algorithms such as a density-based detection algorithm, a proximity-based detection algorithm, a model-based detection algorithm and the like in machine learning can be adopted to realize the algorithm analysis of the machine learning, so that a state analysis result of the abnormal state is obtained. According to the health state monitoring method for the rotary mechanical equipment, provided by the embodiment of the invention, the vibration signal data and the temperature signal data of the mechanical equipment are subjected to feature extraction, and corresponding machine learning algorithm analysis is performed, so that an analysis result of an abnormal state can be accurately obtained.
Based on the foregoing embodiments, as an optional embodiment, the state types include working condition states, the state data includes vibration signal data and temperature signal data of the mechanical device, and accordingly, corresponding state data is selected according to different state types, feature extraction and machine learning algorithm analysis are performed, and a state analysis result corresponding to each state type is obtained, including: extracting characteristics of vibration signal data and temperature signal data of mechanical equipment, and performing machine learning algorithm analysis to obtain a state analysis result corresponding to a working condition state; wherein the machine learning algorithm comprises: tree-based classification algorithms, ensemble learning, deep learning.
The working condition state can be analyzed through vibration signal data and temperature signal data of the mechanical equipment, and correspondingly, algorithm analysis of machine learning can be realized by adopting tree-based classification algorithms, integrated learning, deep learning and other algorithms in machine learning, so that a state analysis result of the working condition state is obtained. According to the health state monitoring method for the rotary mechanical equipment, provided by the embodiment of the invention, the vibration signal data and the temperature signal data of the mechanical equipment are subjected to feature extraction, and corresponding machine learning algorithm analysis is performed, so that the analysis result of the working condition state can be accurately obtained
The embodiment of the invention provides a health state monitoring method of rotary mechanical equipment, which is realized by taking a server as an execution main body, and comprises the following steps: if the state type, the state analysis result and the feature data corresponding to the state type are received, performing high-accuracy secondary analysis on the received feature data to verify the state analysis result; transmitting the checked state analysis result; the state analysis result is obtained by selecting corresponding state data according to different state types after the terminal acquires the state data in the running process of the rotary mechanical equipment, and performing feature extraction and machine learning algorithm analysis; wherein the status types include: the starting and stopping state, the abnormal state and the working condition state, and the state data are related parameter data in the running process.
In the embodiment of the invention, the server is used as an execution main body. After the terminal realizes the preliminary analysis, if the analysis result of the state type obtained after the analysis changes (is inconsistent with the state monitored before), the state type, the state analysis result and the characteristic data corresponding to the state type are sent to a server for analysis. If the server receives the state type, the state analysis result and the characteristic data corresponding to the state type, performing high-accuracy secondary analysis, and comparing the analysis result with the analysis result of the terminal according to the analysis result, thereby realizing verification of the terminal analysis result. The secondary analysis in the embodiment of the invention is relative to the feature extraction and machine learning algorithm (primary) analysis already performed by the terminal.
In the specific implementation process, a machine learning analysis algorithm corresponding to the terminal can be adopted in the server for analysis, but a more accurate calculation result can be obtained due to the strong calculation capability of the server.
And after verification, sending a verified state analysis result. For example, two schemes may be adopted, one is to feed back the verification result to the terminal, and the terminal is used to view and alarm the state analysis result. And secondly, the verification result is sent to a user terminal, such as a mobile terminal of the user, and the user can receive the verified state analysis result, alarm information and the like through the user terminal. Specifically, the method can push alarm notification, start-stop state, running time, working condition state, fault cause analysis and the like for the mechanical equipment user side through a mobile phone application client side, a webpage front end and the like. Meanwhile, the mobile phone application client and the webpage front end can support the functions of health evaluation, automatic generation of diagnostic reports and the like according to the state of the mechanical equipment.
As an alternative embodiment, the terminal and the server are connected in a network, and the connection mode can adopt wireless data transmission modes such as 2G, 4G, NB-IoT, loRa, bluetooth, wiFi and the like, and can also adopt wired transmission modes such as RS-485 and the like.
As an alternative embodiment, the terminal may perform data transmission with the server in a networking manner through a relay device such as a gateway.
According to the health state monitoring method for the rotary mechanical equipment, if the server receives the state type, the state analysis result and the characteristic data corresponding to the state type, the server performs secondary analysis on the received characteristic data, so that the state analysis result is checked, and a more accurate state analysis result can be obtained.
Compared with the current health state detection method based on the threshold value and the expert system, the terminal and the server obtained based on the method of the embodiments can improve the accuracy of abnormality detection alarm, reduce the data transmission quantity of the terminal and the energy consumption of transmission, and solve the timeliness problem that fault diagnosis depends on manual experts. Taking centrifugal pump equipment as an example, the abnormality detection accuracy is averagely improved by 10 percent compared with the traditional threshold method, the transmission quantity of terminal data is reduced by more than 10 times, the transmission energy consumption is reduced by about 25 percent, the fault diagnosis time is reduced from about 8 hours required by manual diagnosis of an expert to about 15-30 minutes, and the fault response time is improved by more than 15 times
Fig. 2 is a structural diagram of a health status monitoring device for a rotary mechanical device according to an embodiment of the present invention, as shown in fig. 2, the health status monitoring device for a rotary mechanical device includes: an acquisition module 201 and a processing module 202. The acquisition module 201 is used for acquiring state data in the running process of the rotary mechanical equipment; the processing module 202 is configured to select corresponding state data according to different state types, perform feature extraction and machine learning algorithm analysis, and obtain a state analysis result corresponding to each state type; wherein the status types include: the starting and stopping state, the abnormal state and the working condition state, and the state data are related parameter data in the running process.
The acquisition module 201 integrates acceleration, temperature and other sensor functions, and can collect state data related to the mechanical equipment, such as vibration signal data, temperature data and the like.
The processing module 202 selects corresponding state data for analysis according to different state types. The processing module 202 performs feature extraction on the state data, where the extracted feature data includes, but is not limited to, a mean value, a maximum value, a peak-to-peak value, and other frequency domain features of specific parameters in the state data, as well as frequency domain features, envelope spectrum features, wavelet energy, and other frequency domain features. The extracted features are analyzed through a machine algorithm, a state analysis result corresponding to each state type can be obtained, and the specific algorithm type can be determined according to the type of the state data to be analyzed.
The embodiment of the device provided by the embodiment of the present invention is for implementing the above embodiments of the method, and specific flow and details refer to the above embodiments of the method, which are not repeated herein.
According to the health state monitoring device for the rotary mechanical equipment, provided by the embodiment of the invention, the processing module selects the corresponding state data according to different state types, performs feature extraction and machine learning algorithm analysis, obtains the state analysis result corresponding to each state type, and can ensure the accuracy and timeliness of the state analysis result.
Fig. 3 is a structural diagram of a server according to an embodiment of the present invention, as shown in fig. 3, where the server includes: a processing module 301 and a transmitting module 302. The processing module 301 is configured to, if a status type, a status analysis result, and feature data corresponding to the status type are received, perform a secondary analysis on the received feature data, so as to verify the status analysis result; the sending module 302 is configured to send the checked state analysis result; after the terminal obtains state data in the running process of the rotary mechanical equipment, the state analysis result is obtained by selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis, wherein the state types comprise: the system comprises a start-stop state, an abnormal state and a working condition state, wherein the state data are related parameter data in the running process.
After the terminal performs the preliminary analysis, if the analysis result of the state type obtained after the analysis changes (is inconsistent with the state monitored before), the state type, the state analysis result and the feature data corresponding to the state type are sent to the processing module 301 for secondary analysis (relative to the analysis of the feature extraction and the machine learning algorithm performed by the terminal). If the processing module 301 receives the state type, the state analysis result, and the feature data corresponding to the state type, it performs high-accuracy secondary analysis, and compares the analysis result with the analysis result of the terminal, thereby implementing verification of the terminal analysis result.
After verification, the sending module 302 sends the verified state analysis result. For example, two schemes may be adopted, one is to feed back the verification result to the terminal, and the other is to send the verification result to the user terminal, such as the mobile terminal of the user.
According to the server provided by the embodiment of the invention, if the server receives the state type, the state analysis result and the characteristic data corresponding to the state type, the server performs secondary analysis on the received characteristic data, so that the verification of the state analysis result is realized, and a more accurate state analysis result can be obtained.
Fig. 4 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 4, where the electronic device may include: a processor (processor) 401, a communication interface (Communications Interface) 402, a memory (memory) 403, and a bus 404, wherein the processor 401, the communication interface 402, and the memory 403 complete communication with each other through the bus 404. The communication interface 402 may be used for information transfer of an electronic device. The processor 401 may call logic instructions in the memory 403 to perform a method comprising: acquiring state data in the running process of the rotary mechanical equipment; selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis to obtain a state analysis result corresponding to each state type; wherein the status types include: the starting and stopping state, the abnormal state and the working condition state, and the state data are related parameter data in the running process.
Further, the logic instructions in the memory 403 may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above-described method embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present invention also provide a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the method provided in the above embodiments, for example, including: acquiring state data in the running process of the rotary mechanical equipment; selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis to obtain a state analysis result corresponding to each state type; wherein the status types include: the starting and stopping state, the abnormal state and the working condition state, and the state data are related parameter data in the running process.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for monitoring the health status of a rotary mechanical device, comprising:
acquiring state data in the running process of the rotary mechanical equipment;
selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis to obtain a state analysis result corresponding to each state type;
wherein the status type includes: starting and stopping state, abnormal state and working condition state, wherein the state data are related parameter data in the running process;
after the state analysis result corresponding to each state type is obtained, the method further comprises the following steps:
if the analysis is informed that the state type result is changed, the state type, the state analysis result and the characteristic data corresponding to the state type are sent to a server, so that the server can check the state analysis result after performing secondary analysis according to the corresponding characteristic data;
wherein, under the condition that the state type is a start-stop state, the state data comprises vibration signal data of mechanical equipment;
under the condition that the state type is abnormal, the state data comprise vibration signal data and temperature signal data of mechanical equipment;
in the case where the status type includes a condition status, the status data includes machine vibration signal data and temperature signal data.
2. The method for monitoring the health status of a rotary mechanical device according to claim 1, wherein the selecting the corresponding status data according to different status types, performing feature extraction and machine learning algorithm analysis to obtain a status analysis result corresponding to each status type, includes:
extracting features of vibration signal data of mechanical equipment, and analyzing corresponding machine learning algorithm to obtain a state analysis result of a start-stop state;
the machine learning algorithm includes: linear models, nonlinear models, tree models, and probabilistic models.
3. The method for monitoring the health status of a rotary mechanical device according to claim 1, wherein the selecting the corresponding status data according to different status types, performing feature extraction and machine learning algorithm analysis to obtain a status analysis result corresponding to each status type, includes:
extracting characteristics of vibration signal data and temperature signal data of mechanical equipment, and analyzing corresponding machine learning algorithms to obtain a state analysis result of an abnormal state;
wherein the machine learning algorithm comprises: density-based detection algorithms, proximity-based detection algorithms, and model-based detection algorithms.
4. The method for monitoring the health status of a rotary mechanical device according to claim 1, wherein the selecting the corresponding status data according to different status types, performing feature extraction and machine learning algorithm analysis to obtain a status analysis result corresponding to each status type, includes:
extracting characteristics of vibration signal data and temperature signal data of mechanical equipment, and performing machine learning algorithm analysis to obtain a state analysis result corresponding to a working condition state;
wherein the machine learning algorithm comprises: tree-based classification algorithms, ensemble learning, deep learning.
5. A method for monitoring the health status of a rotary mechanical device, comprising:
if the state type, the state analysis result and the feature data corresponding to the state type are received, performing secondary analysis on the received feature data to verify the state analysis result;
transmitting the checked state analysis result;
after the terminal obtains state data in the running process of the rotary mechanical equipment, the state analysis result is obtained by selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis, wherein the state types comprise: starting and stopping state, abnormal state and working condition state, wherein the state data are related parameter data in the running process;
wherein, under the condition that the state type is a start-stop state, the state data comprises vibration signal data of mechanical equipment;
under the condition that the state type is abnormal, the state data comprise vibration signal data and temperature signal data of mechanical equipment;
in the case where the status type includes a condition status, the status data includes machine vibration signal data and temperature signal data.
6. A health status monitoring device for a rotary-type mechanical device, comprising:
the acquisition module is used for acquiring state data in the running process of the rotary mechanical equipment;
the processing module is used for selecting corresponding state data according to different state types, carrying out feature extraction and machine learning algorithm analysis, and obtaining a state analysis result corresponding to each state type;
the device is further configured to, after obtaining a state analysis result corresponding to each state type:
if the analysis is informed that the state type result is changed, the state type, the state analysis result and the characteristic data corresponding to the state type are sent to a server, so that the server can check the state analysis result after performing secondary analysis according to the corresponding characteristic data;
wherein the status type includes: starting and stopping state, abnormal state and working condition state, wherein the state data are related parameter data in the running process;
wherein, under the condition that the state type is a start-stop state, the state data comprises vibration signal data of mechanical equipment;
under the condition that the state type is abnormal, the state data comprise vibration signal data and temperature signal data of mechanical equipment;
in the case where the status type includes a condition status, the status data includes machine vibration signal data and temperature signal data.
7. A server, comprising:
the processing module is used for carrying out secondary analysis on the received characteristic data if the state type, the state analysis result and the characteristic data corresponding to the state type are received, so as to realize verification of the state analysis result;
the sending module is used for sending the verification result to the terminal or sending the verification result to the user side;
after the terminal obtains state data in the running process of the rotary mechanical equipment, the state analysis result is obtained by selecting corresponding state data according to different state types, and performing feature extraction and machine learning algorithm analysis, wherein the state types comprise: starting and stopping state, abnormal state and working condition state, wherein the state data are related parameter data in the running process;
wherein, under the condition that the state type is a start-stop state, the state data comprises vibration signal data of mechanical equipment;
under the condition that the state type is abnormal, the state data comprise vibration signal data and temperature signal data of mechanical equipment;
in the case where the status type includes a condition status, the status data includes machine vibration signal data and temperature signal data.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the method for monitoring the health of a rotary-type mechanical device according to any one of claims 1 to 5 when the program is executed by the processor.
9. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of monitoring the health status of a rotary-type mechanical device according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431259.4A CN110134571B (en) | 2019-05-22 | 2019-05-22 | Method and device for monitoring health state of rotary mechanical equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431259.4A CN110134571B (en) | 2019-05-22 | 2019-05-22 | Method and device for monitoring health state of rotary mechanical equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110134571A CN110134571A (en) | 2019-08-16 |
| CN110134571B true CN110134571B (en) | 2023-05-02 |
Family
ID=67572453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910431259.4A Active CN110134571B (en) | 2019-05-22 | 2019-05-22 | Method and device for monitoring health state of rotary mechanical equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110134571B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110714869B (en) * | 2019-09-30 | 2020-09-22 | 华能四川水电有限公司 | Method and device for detecting central offset of rotor, storage medium and equipment |
| CN110907207B (en) * | 2019-11-25 | 2022-08-09 | 湃方科技(天津)有限责任公司 | Running state detection method and device for non-marking mechanical equipment |
| CN110996289A (en) * | 2019-12-11 | 2020-04-10 | 湃方科技(天津)有限责任公司 | Intelligent gateway, method and system for machine state monitoring diagnostic instrument |
| CN112146749A (en) * | 2020-09-08 | 2020-12-29 | 成都安尔法智控科技有限公司 | Method and system for analyzing starting and stopping states of equipment based on vibration signals |
| CN112067310A (en) * | 2020-09-11 | 2020-12-11 | 阴悦 | Health state monitoring system applying non-invasive high-frequency ultrasonic stress wave gas turbine |
| CN111931389B (en) * | 2020-10-12 | 2021-01-01 | 湃方科技(天津)有限责任公司 | Method and device for analyzing normal and abnormal running state of rotary equipment |
| CN112329825B (en) * | 2020-10-23 | 2022-12-06 | 贵州电网有限责任公司 | Transformer mechanical fault diagnosis method based on information dimension division and decision tree lifting |
| CN113110981B (en) * | 2021-03-26 | 2024-04-09 | 北京中大科慧科技发展有限公司 | Air conditioner room health energy efficiency detection method for data center |
| US11796993B2 (en) * | 2021-05-12 | 2023-10-24 | Yokogawa Electric Corporation | Systems, methods, and devices for equipment monitoring and fault prediction |
| CN115307896A (en) * | 2022-09-20 | 2022-11-08 | 重庆忽米网络科技有限公司 | Equipment health state detection method based on machine learning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104833926A (en) * | 2015-05-07 | 2015-08-12 | 昆山弗尔赛能源有限公司 | Monitoring method for standby power system of fuel cell and system thereof |
| CN105700509A (en) * | 2014-11-28 | 2016-06-22 | 奇点新源国际技术开发(北京)有限公司 | Vehicle-borne terminal detection method and device based on CAN bus |
| CN105719112A (en) * | 2015-05-22 | 2016-06-29 | 北京小度信息科技有限公司 | Determination method and device for distribution abnormal state, and server |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI430212B (en) * | 2010-06-08 | 2014-03-11 | Gorilla Technology Inc | Abnormal behavior detection system and method using automatic classification of multiple features |
| CN103823458A (en) * | 2014-03-17 | 2014-05-28 | 广东华南计算技术研究所 | Remote diagnosis device, method and system for equipment |
| CN108168682A (en) * | 2017-12-22 | 2018-06-15 | 中国南方电网有限责任公司超高压输电公司曲靖局 | A kind of GIL On-line Faults monitoring system based on vibration signal support vector machines |
| CN108510153B (en) * | 2018-02-08 | 2022-09-16 | 同济大学 | Multi-working-condition rotary machine fault diagnosis method |
| CN108919044B (en) * | 2018-03-30 | 2020-09-29 | 国电南瑞科技股份有限公司 | Active identification method for unit distribution power grid faults based on mutual verification mechanism |
| CN208210013U (en) * | 2018-05-07 | 2018-12-07 | 苏州德姆斯信息技术有限公司 | Vibration analysis system based on things-internet gateway edge calculations |
| CN109784284A (en) * | 2019-01-22 | 2019-05-21 | 上海瀚挚电子科技有限公司 | The self study recognition methods of working condition based on rotating machinery |
-
2019
- 2019-05-22 CN CN201910431259.4A patent/CN110134571B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105700509A (en) * | 2014-11-28 | 2016-06-22 | 奇点新源国际技术开发(北京)有限公司 | Vehicle-borne terminal detection method and device based on CAN bus |
| CN104833926A (en) * | 2015-05-07 | 2015-08-12 | 昆山弗尔赛能源有限公司 | Monitoring method for standby power system of fuel cell and system thereof |
| CN105719112A (en) * | 2015-05-22 | 2016-06-29 | 北京小度信息科技有限公司 | Determination method and device for distribution abnormal state, and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110134571A (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110134571B (en) | Method and device for monitoring health state of rotary mechanical equipment | |
| CN109474494B (en) | Equipment detection method, device, server and storage medium | |
| US20200051419A1 (en) | Cloud-based machine health monitoring | |
| US10458416B2 (en) | Apparatus and method for monitoring a pump | |
| CN109397703B (en) | Fault detection method and device | |
| US8964995B2 (en) | Acoustic diagnosis and correction system | |
| WO2017008451A1 (en) | Abnormal load detecting method for cloud computing oriented online service | |
| CN104866632A (en) | Failure data acquisition method, device and terminal of electric household appliance | |
| CN111353911A (en) | Power equipment operation and maintenance method, system, equipment and storage medium | |
| KR102444442B1 (en) | System and method for diagnosing facility fault | |
| JP6564799B2 (en) | Threshold determination device, threshold determination method and program | |
| CN104639368A (en) | Method and device for processing faults of communications network equipment | |
| CN103746829A (en) | Cluster-based fault perception system and method thereof | |
| CN113516244B (en) | Intelligent operation and maintenance method and device, electronic equipment and storage medium | |
| CN114647234B (en) | Medical equipment monitoring method and device based on Internet of things and storage medium | |
| WO2020144600A1 (en) | A methods for determining an alternate current motor fault in a non-variable frequency device based on current analysis | |
| CN111781498A (en) | Data analysis system of equipment detection point | |
| CN110469461A (en) | A kind of fracture predictor method of blower tooth band, its device and readable storage medium storing program for executing | |
| CN116016274B (en) | Abnormal communication detection method and system | |
| CN110598797B (en) | Fault detection method and device, storage medium and electronic device | |
| CN116680641A (en) | User electricity consumption abnormality detection method based on machine learning algorithm | |
| EP3423789B1 (en) | Systems and methods thereof for determination of a device state based on current consumption monitoring and machine-learning thereof | |
| CN116910635A (en) | Pressure regulator fault diagnosis method and device based on federal learning and expansion convolution | |
| CN115249126A (en) | Nuclear power station equipment comprehensive state evaluation method and device based on feature vector space | |
| CN114666210A (en) | Alarm method and device based on big data log analysis |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Jinyang Inventor after: Ma Jun Inventor after: Wu Tongda Inventor before: Li Jinyang Inventor before: Ma Jun Inventor before: Wu Tongda Inventor before: Liu Yongpan |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |