CN107167497B - Equipment fault detection method and system - Google Patents
Equipment fault detection method and system Download PDFInfo
- Publication number
- CN107167497B CN107167497B CN201710502240.5A CN201710502240A CN107167497B CN 107167497 B CN107167497 B CN 107167497B CN 201710502240 A CN201710502240 A CN 201710502240A CN 107167497 B CN107167497 B CN 107167497B
- Authority
- CN
- China
- Prior art keywords
- fault
- equipment
- model
- parameters
- temperature
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Radiation Pyrometers (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a method and a system for detecting equipment faults. The method comprises the following steps: obtaining model parameters and a rule base; the model parameters include: the equipment type, the equipment structure, the number, the distribution and the attribute of the measuring points; the rule base includes: fault type, corresponding fault characteristic parameters and set threshold; constructing a fault model of the equipment according to the model parameter combination rule base, wherein each equipment type corresponds to a plurality of fault models, and each fault model comprises a fault characteristic parameter, a set threshold value of the fault characteristic parameter and a corresponding fault type; acquiring an infrared thermal image of each measuring point of the equipment; extracting equipment characteristic parameters in the infrared thermal image according to the model parameters; obtaining a fault detection result of the equipment according to the fault model and the equipment characteristic parameters; the fault detection result comprises a fault part and a fault severity level. By adopting the method and the system provided by the invention, the running state of the equipment can be analyzed in real time, the on-line detection is realized, and the detection precision of the equipment fault is improved.
Description
Technical Field
The invention relates to the field of intelligent detection, in particular to a method and a system for detecting equipment faults.
Background
In the field of equipment state detection, an infrared detection technology is one of equipment fault detection technologies, and particularly for the type of electrical equipment, the fault detection technology is generally adopted for fault detection. When the parts of the running equipment are worn, fatigued, broken, deformed, corroded, loosened, melted, material deteriorated, abnormal vibration and other faults occur, temperature change can occur directly or indirectly, the whole or partial heat balance of the equipment is also destroyed or influenced, heat in the equipment is necessarily transferred to the outer surface of the equipment step by step through heat transfer, the change of an outer surface temperature field is caused, and the change can be detected by using a thermal infrared imager.
The thermal infrared imager works on the principle of using a photoelectric device to detect and measure radiation and to correlate the radiation with the surface temperature. All objects above absolute zero (-273 ℃) emit infrared radiation. The infrared thermal imager receives infrared radiation energy of a detected target by utilizing the infrared detector and the optical imaging objective lens, and reflects the infrared radiation energy onto a photosensitive element of the infrared detector in a pattern form, so that an infrared thermal image is obtained, and the thermal image corresponds to a thermal distribution field of the surface of an object. In popular terms, a thermal infrared imager converts invisible infrared energy emitted by an object into a visible thermal image. Different colors on the thermal image represent different temperatures of the measured object. By looking up the thermal image, the overall temperature distribution condition of the measured object can be observed, and the heating condition of the object is researched, so that the judgment of the next work is carried out. Therefore, the existing equipment fault detection method generally comprises the steps of analyzing a thermal image in a later period, judging the fault condition of equipment, and has a certain time delay property and a certain experience requirement for an analyst, so that the equipment fault detection precision is not high.
Disclosure of Invention
The invention aims to provide a method and a system for detecting equipment faults, which are used for realizing real-time online detection and improving the detection precision of the equipment faults.
In order to achieve the above object, the present invention provides the following solutions:
a method of device failure detection, the method comprising:
obtaining model parameters and a rule base; the model parameters include: the equipment type, the equipment structure, the number, the distribution and the attribute of the measuring points; different equipment types correspond to different equipment structures, measuring point numbers, distribution and measuring point attributes; the rule base includes: fault type, fault characteristic parameters corresponding to the fault type, a set threshold value of the fault characteristic parameters and logic rules of fault diagnosis;
constructing a fault model of the equipment according to the model parameter combination rule base, wherein each equipment type corresponds to a plurality of fault models, and each fault model comprises a fault characteristic parameter, a set threshold value of the fault characteristic parameter and a corresponding fault type;
acquiring an infrared thermal image of each measuring point of the equipment;
extracting equipment characteristic parameters in the infrared thermal image according to the model parameters;
obtaining a fault detection result of the equipment according to the fault model and the equipment characteristic parameters and the logic rule of fault diagnosis; the fault detection result comprises a fault part and a fault severity level.
Optionally, the rule base further includes: and processing suggestions and fault reasons corresponding to the fault types.
Optionally, the rule base is in an open structure, and is used for adding a new logic rule for fault diagnosis and/or a new fault type, and the new fault type corresponds to a new fault characteristic parameter and a new set threshold value.
Optionally, the model parameters further include: and the temperature/temperature rise standard parameters and the alarm parameters are used for judging whether the temperature/temperature rise actual values of the measuring points are larger than the standard parameters, and outputting the alarm parameters when the temperature/temperature rise actual values of the measuring points are larger than the standard parameters.
Optionally, the obtaining the fault detection result of the device according to the fault model and the device feature parameter specifically includes:
extracting a fault model corresponding to the equipment according to the equipment characteristic parameters, wherein the fault model corresponding to the equipment is a fault model corresponding to the equipment type to which the equipment belongs;
comparing the equipment characteristic parameters with the fault models corresponding to the equipment one by one, and acquiring fault types corresponding to the equipment according to the logic rules of fault diagnosis;
for each fault type corresponding to the equipment, determining a fault part corresponding to the fault type according to the fault type and the model parameters;
comparing the equipment characteristic parameters with fault characteristic parameters corresponding to the fault types to obtain a difference value of the equipment characteristic parameters and the fault characteristic parameters;
according to logic rules in the rule base, carrying out logic weighting calculation on the difference value to determine the fault severity level of the fault type; and sequentially obtaining fault positions and fault severity levels corresponding to all fault types corresponding to the equipment.
Optionally, after obtaining the fault detection result of the device, the method further includes:
and acquiring corresponding processing suggestions and fault reasons according to the fault model.
Optionally, after obtaining the fault detection result of the device according to the fault model and the device feature parameter, the method further includes:
comparison analysis of longitudinal historical data: generating a temperature and/or temperature rising trend curve according to the historical data of the same measuring point, and analyzing the historical trend and predicting future data;
and (3) comparing and analyzing data of the transverse similar equipment: and comparing and displaying infrared images of different measuring points of the same measuring position of the same equipment to obtain temperature/temperature rise parameters and temperature distribution of the same equipment.
A device fault detection system, the system comprising: the device comprises an image acquisition device, an image recognition device, an infrared analysis device and an image display device;
the input end of the image recognition device is connected with the output end of the image acquisition device and is used for receiving the infrared thermal image of each measuring point of the equipment acquired by the image acquisition device and extracting the equipment characteristic parameters corresponding to the model parameters in the infrared thermal image; the model parameters include: the equipment type, the equipment structure, the number, the distribution and the attribute of the measuring points;
the input end of the infrared analysis device is connected with the output end of the image recognition device and is used for outputting a fault detection result of the equipment according to the equipment characteristic parameters extracted by the image recognition device; the fault detection result comprises a fault part and a fault severity level;
the input end of the image display device is connected with the output end of the infrared analysis device and is used for displaying the fault detection result.
Optionally, the system further comprises:
the input end of the first alarm device is connected with the output end of the image recognition device, and when the temperature of the measuring point exceeds a set temperature threshold value, the first alarm device starts an alarm and outputs information of fault detection abnormality to the image display device;
and the input end of the second alarm device is connected with the output end of the image acquisition device, and the acquisition prompt alarm is started according to the acquisition period of the image acquisition device.
Optionally, the system controls the image acquisition device to automatically position the measuring point for image acquisition through the two-dimensional code or the bar code of the measuring point of the equipment.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the method can automatically give corresponding evaluation to the equipment state after data acquisition, quickly give the running state of the equipment, quickly screen the equipment with serious defects or major hidden danger in a large amount of measured data, has great significance for reducing the working intensity of users, improving the working efficiency and improving the effectiveness of diagnosis results, and accords with the development trend of intelligent instruments. The management of test data is facilitated, trend tracking, history comparison and transverse comparison are facilitated, data and image analysis are facilitated, and equipment fault diagnosis and equipment state assessment are facilitated; meanwhile, according to the temperature trend curve, the temperature rise speed can be rapidly calculated, the temperature development is predicted, maintenance and overhaul preparation work is arranged in advance, emergency is avoided, and the influence of shutdown can be reduced to the minimum. Through remote control and communication function, the test of the equipment in the occasion with special requirements is conveniently realized in a remote control mode.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an embodiment 1 of the method for detecting equipment faults according to the present invention;
FIG. 2 is a block diagram of an apparatus fault detection system of the present invention;
FIG. 3 is a schematic flow chart of an embodiment 2 of the method for detecting a device failure according to the present invention;
fig. 4 is a modeling flowchart corresponding to embodiment 2 of the equipment failure detection method according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Fig. 1 is a flowchart of an embodiment 1 of the method for detecting a device failure according to the present invention. As shown in fig. 1, the method includes:
step 101: obtaining model parameters and a rule base; different types of devices correspond to different fault detection models (the same fault detection model is used by the same type of device), the fault detection models are established according to model parameters and a rule base, and the model parameters comprise: the equipment type, the equipment structure, the number and the distribution of the measuring points, the measuring point attribute, the temperature/temperature rise standard parameter, the alarm parameter and the like; different equipment types correspond to different equipment structures, number of measuring points, distribution and measuring point attributes. The purpose of setting the temperature/temperature rise standard parameter and the alarm parameter in the model parameter is as follows: the alarm parameters serve as simple alarm functions, and simple and automatic evaluation is carried out on whether the temperature of the measuring point exceeds the absolute standard of the set alarm temperature, so that on one hand, workers are reminded to carry out important investigation on the measuring point, and on the other hand, the evaluation result can be counted into a diagnosis conclusion of the equipment, and the final diagnosis conclusion is influenced through a corresponding calculation algorithm. The alarm of the temperature of the measuring point does not mean that the equipment is normal, and the alarm of the temperature of the measuring point is accompanied with the abnormality of the equipment.
Abundant fault diagnosis rules are built in the rule base aiming at different types of equipment, so that effective diagnosis analysis of 90% of equipment faults can be realized, and the rule base comprises: fault type, fault characteristic parameters corresponding to the fault type, set threshold values of the fault characteristic parameters and logic rules of fault diagnosis; the method can also comprise fault reasons and processing methods corresponding to the fault types. The rule base adopts an open structure, can be supplemented and perfected according to new rules found in research and practical application, and is a continuously improved and continuously updated database.
Step 102: and constructing a fault model. And constructing a fault model of the equipment according to the model parameter combination rule base, wherein each equipment type corresponds to a plurality of fault models, and each fault model comprises a fault characteristic parameter, a set threshold value of the fault characteristic parameter and a corresponding fault type. That is, different fault models are built according to different equipment parameter combination rule bases in the model parameters, each equipment can correspond to a plurality of fault models, and each fault model comprises a fault type, a fault characteristic parameter and a set threshold value corresponding to the fault characteristic parameter.
For example, the rule base includes: the fault type, the characteristic parameters, the set threshold value of the diagnosis parameters, the severity level calculation logic, the reasons and the processing methods corresponding to various fault characteristics respectively form corresponding fault models according to the equipment type and the structure. Such as: for 220kV Current Transformer (CT) equipment, corresponding fault types include: the temperature of the lead joint is high, the local overheating of the porcelain insulator is supported, the temperature abnormality of the transformer is measured, and the like, and the characteristic parameters respectively corresponding to the lead joint are as follows: the temperature of the lead joint supports the temperature rise distribution of the porcelain insulator, the external temperature of the transformer position and the like. When the fault model is built, the infrared analysis software can build a four-level equipment structure tree of 'factory-area-equipment-measuring points', and the attributes of the nodes of different levels are set through the corresponding tested equipment and measuring positions of the tree nodes of different levels. A fault model can be built in the device node attributes and alarm parameters can be set in the measurement location node attributes.
The model established in the PC-end infrared analysis software is loaded into the thermal infrared imager through uploading operation, and automatic diagnosis can be realized through field test.
Step 103: and acquiring an infrared thermal image of each measuring point of the equipment. When the equipment is detected, different measuring points are correspondingly arranged on different parts of the equipment, so that different infrared thermal image graphs of the different measuring points can be obtained, and the aim of fixed-point detection is fulfilled.
Step 104: and extracting the equipment characteristic parameters in the infrared thermal image. And extracting corresponding equipment characteristic parameters in the infrared thermal image of each measuring point according to the model parameters, such as temperature and temperature rise parameters of the electrical equipment.
Step 105: and obtaining a device detection result. Obtaining a fault detection result of the device according to the fault model and the device characteristic parameter, wherein the fault detection result comprises a fault part, a fault severity level and the like, and for example, the fault detection result can further comprise: the processing proposal and the fault reason corresponding to the fault type, etc.
The specific process for obtaining the equipment detection result is as follows:
extracting a fault model corresponding to the equipment according to the equipment characteristic parameters, wherein the fault model corresponding to the equipment is a fault model corresponding to the equipment type to which the equipment belongs;
comparing the equipment characteristic parameters with the fault models one by one, and acquiring fault types according to logic rules;
for each fault type, determining a fault part corresponding to the fault type according to the fault type and the model parameters; comparing the equipment characteristic parameters with fault characteristic parameters corresponding to the fault types to obtain a difference value of the equipment characteristic parameters and the fault characteristic parameters; according to logic rules in the rule base, carrying out logic weighting calculation on the difference value to determine the fault severity level of the fault type;
and sequentially obtaining fault positions and fault severity grades corresponding to all fault types.
Because the fault model is a fault type determined according to a parameter corresponding rule base in model parameters, the model parameters comprise the number and distribution of measuring points, therefore, the fault type comprises information of each measuring point, a fault part can be obtained according to the fault type in the fault model, and then corresponding processing suggestions and fault reasons can be obtained according to the fault model.
For the fault severity level of the device, for example, the fault model constructed by the rule base illustrated in step 102, the corresponding determination rules for the high temperature fault model of the lead joint include: the temperature of the corresponding position of the single-phase CT exceeds the set threshold value of the diagnostic parameter 1 or the difference value of the corresponding position of the three-phase CT exceeds the set threshold value of the diagnostic parameter 2 or the relative temperature difference between the corresponding position of the single-phase CT and other two phases exceeds the set threshold value of the diagnostic parameter 3. Weighting according to the difference value between the actual value of the corresponding parameter and the threshold value to obtain a severity score, comparing the severity score with a severity coefficient corresponding to the rule base to obtain a fault grade corresponding to the high temperature of the CT lead joint, and arranging the severity grades of the obtained faults in a sequence from high to low; and marking colors on the infrared thermal image according to the corresponding fault severity levels from high to low, wherein each fault severity level corresponds to different colors respectively, and evaluating the state of the machine according to the severity level according to the different colors.
Besides the fixed-point fault detection, the functions of longitudinal historical data comparison analysis and transverse similar equipment comparison analysis can be realized:
comparison analysis of longitudinal historical data: generating a temperature and/or temperature rising trend curve according to the historical data of the same measuring point, and analyzing the historical trend and predicting future data;
and (3) comparing and analyzing data of the transverse similar equipment: and comparing and displaying infrared images of different measuring points of the same measuring position of the same equipment to obtain temperature/temperature rise parameters and temperature distribution of the same equipment, and assisting in further fault diagnosis.
In addition, the method of the invention has the following characteristics:
(1) The infrared analysis software can establish a device structure tree, and set the attributes of the nodes of different levels through the tree nodes of different levels corresponding to the tested devices and the measured positions. A diagnostic model can be built in the device node properties and alarm parameters can be set in the measurement location node properties.
The model established in the PC-end infrared analysis software is loaded into the thermal infrared imager through uploading operation, and automatic diagnosis can be realized through field test. The images in the thermal imager can be automatically and batched imported into the PC-end infrared analysis software through the downloading operation.
(2) And (5) data management. The infrared analysis software can realize data transplantation, and can be mutually transplanted among different PC ends through backup and restoration operations of equipment structure trees and/or infrared thermal image graphs. The infrared images can be exported in batches into a required picture format and automatically named through the device measuring points and date ranges in the selected range.
(3) And (5) testing and reminding. And setting the attribute of the equipment node 'acquisition period', so as to realize test reminding and expiration alarming. And according to the acquisition period defined by the node attribute of the structural tree equipment, alarming after exceeding the set acquisition period compared with the latest test time.
(4) Automatically acquiring the ambient temperature and calculating the temperature rise. The temperature rise is calculated according to the difference between the measured point temperature and the ambient temperature. An environment temperature sensing device is arranged in the thermal infrared imager, the environment temperature of equipment in the testing process is automatically acquired and recorded in infrared image information data, and corresponding temperature rise data can be automatically generated.
(5) And (5) cloud storage. The device structure tree is established at a local area network cloud or an Internet cloud through infrared analysis software, and the infrared thermal imager is connected with the cloud device structure tree through Wi-Fi, 3G/4G network and the like, so that cloud storage is realized. And establishing a device structure tree on a local area network or an Internet cloud server, setting a network storage mode by the thermal infrared imager, establishing connection between the thermal infrared imager and the cloud server after correctly configuring a cloud address, a user and a password, and forming a network mapping address corresponding to the device structure tree of the cloud server on the thermal infrared imager, wherein an infrared picture shot on site can be directly stored in a corresponding position of the cloud server. The thermal infrared imager is also provided with a buffer area, and for the environment with poor temporary network signals, the temporary network signals can be temporarily stored in the buffer area, and the network signals automatically searched by the thermal infrared imager are automatically sent to the cloud after meeting the requirement.
The PC end infrared analysis software can also be directly connected with a cloud end equipment structure tree through network setting, and the infrared image is checked and analyzed to complete infrared intelligent diagnosis. The cloud server can support a plurality of terminals to simultaneously use the same equipment structure tree, so that infrared analysis software installed at different PC ends can be connected to the same equipment structure tree through a network, and data sharing is achieved. The cloud server can also be connected through the mobile terminal, and when the mobile phone APP infrared analysis software is used, the mobile interconnection can be realized through checking and analysis of the cloud server.
(6) Remote control and communication. The mobile phone APP is used for carrying out wake-up, focusing, shooting and storage by using the Wi-Fi, 3G/4G, bluetooth and other wireless control and temporary fixed installation of the thermal infrared imager, so that the monitoring needs of special occasions which are inconvenient to approach, not allowed to enter or have high environmental risks in the machine operation are realized. All functions of the thermal infrared imager can be realized through mobile phone APP remote control.
Fig. 2 is a block diagram of the fault detection system of the device of the present invention. As shown in fig. 2, the system includes: an image acquisition device 201, an image recognition device 202, an infrared analysis device 203 and an image display device 204; the input end of the image recognition device 202 is connected with the output end of the image acquisition device 201, and is used for receiving the infrared thermal image of each measuring point of the equipment acquired by the image acquisition device 201 and extracting the equipment characteristic parameters corresponding to the model parameters in the infrared thermal image; the model parameters include: the equipment type, the equipment structure, the number, the distribution and the attribute of the measuring points; the input end of the infrared analysis device 203 is connected with the output end of the image recognition device 202, and is used for outputting a fault detection result of the equipment according to the equipment characteristic parameters extracted by the image recognition device 202; the fault detection result comprises a fault part and a severity level; the input end of the image display device 204 is connected to the output end of the infrared analysis device 203, so as to display the fault detection result.
The image acquisition device 201 is composed of a conventional optical imaging system, a detector and a signal processor, and is used for acquiring an infrared thermal image of a detection target. The infrared radiation of the detected target is focused on a detector through an optical imaging system, the detector generates an electric signal, and the electric signal is amplified and digitized to a signal processor of a thermal imager to form an infrared thermal image. The image acquisition device 201 can be a portable thermal infrared imager or an online infrared monitoring device. The image recognition device 202 and the infrared analysis device 203 may be a computer or an integrated chip, and when the integrated chip is used, the integrated chip may be integrated on the image acquisition device 201. The image display device 204 may be a display of a thermal infrared imager, or may be a display screen of a computer, a mobile terminal, or an infrared monitoring system.
The apparatus may further include: (1) And the input end of the first alarm device is connected with the output end of the image recognition device 202, and when the temperature of the measuring point exceeds a set temperature threshold value, the first alarm device starts alarm and outputs abnormal fault detection information to the image display device 204. (2) And the input end of the storage device is connected with the output end of the image acquisition device 201, and the output end of the storage device is connected with the input end of the infrared analysis device 203. (3) And the input end of the second alarm device is connected with the output end of the image acquisition device 201, and the acquisition prompt alarm is started according to the acquisition period of the image acquisition device 201.
The device can realize the functions of image acquisition, fault analysis and detection, data management, test reminding and the like.
(1) And (3) image acquisition: through the two-dimensional code or the bar code of the equipment measuring point, the thermal infrared imager can be automatically positioned on the measuring point path. For example, the number of the measuring point 5 is input at the computer end or the two-dimensional code of the measuring point 5 is scanned, the thermal infrared imager can automatically position the measuring point 5 for image acquisition, so that automatic acquisition and quick storage are realized, and images in the thermal infrared imager can be automatically and batched led into the PC end.
(2) Fault analysis and detection: the image recognition device 202 performs fault analysis on the collected infrared thermal image by combining with the infrared analysis device 203, judges the fault type, obtains the fault position and the fault level, can trigger a corresponding alarm device to alarm, and can trigger an alarm at any time when the fault level is higher than a certain set level or the fault level in the fault type is higher than a certain level. And the longitudinal historical data comparison analysis and the transverse similar equipment comparison analysis can be completed.
The implementation method of the longitudinal historical data comparison analysis comprises the following steps: and generating a temperature and/or temperature rise trend curve for the historical data under the measuring points to realize trend comparison and tracking. The diagnosis model analyzes and predicts the historical trend, and realizes trend diagnosis.
The method for realizing the comparison analysis of the transverse similar equipment comprises the following steps: and comparing and displaying infrared images of the same measuring position of the same equipment, and comparing the temperature/temperature rise parameters and temperature distribution of the same equipment by using a diagnosis model to realize comparison diagnosis.
(3) And (3) data management: the data can be transplanted, and the data can be mutually transplanted among different PC ends through the backup and restore operation of the equipment fault analysis result and/or the infrared thermal image. The infrared images can be exported in batches into a required picture format and automatically named through the device measuring points and date ranges in the selected ranges.
(4) And (3) test reminding: and setting the attribute of the equipment node 'acquisition period', so as to realize test reminding and expiration alarming. And according to the acquisition period defined by the node attribute of the structural tree equipment, alarming after exceeding the set acquisition period compared with the latest test time.
Fig. 3 is a schematic flow chart of an embodiment 2 of the method for detecting a device failure according to the present invention. As shown in fig. 3, the method includes three parts: an image recognition section 301, a failure analysis model section 302, an image analysis section 303;
when the complete machine test is finished, the infrared thermal image corresponding to the machine part 1, the machine part 2 and the machine part 3 is respectively subjected to image recognition, and the corresponding equipment characteristic parameters are extracted by combining the relevant model parameters in the fault analysis model, wherein the characteristic parameters are the characteristic parameters required by the fault analysis model for carrying out fault analysis on the equipment.
The model parameters of the fault analysis model correspond to corresponding rules in the rule base to form a fault model for the device. A device may correspond to a number of different faults, the fault characteristics and fault threshold values (set thresholds) of which are represented by fault models. The fault signature indicates the fault type and the threshold value determines the severity of the fault for each of the model parameters.
The fault analysis model compares the extracted equipment characteristic parameters with the fault model through a certain diagnosis logic rule operation, and if the characteristic parameters meet the fault characteristics and threshold requirements of a certain fault model, the fault type and severity level are correspondingly generated. The rule base also stores simple processing suggestions aiming at different fault types and severity and reasons (namely fault sources) possibly causing the fault, and then the diagnosis conclusion outputs fault positions, fault types, fault sources, severity, processing suggestions and the like.
As described above, one apparatus may have different faults at the same time, and the output of all the faults is completed by comparing the fault models 1-n one by one, and when a plurality of faults exist at the same time, the faults are arranged in order of severity level from high to low. Different fault levels correspond to different color alarms and are displayed at corresponding positions of the equipment structure tree. Finally, the severity level of the equipment failure is obtained.
The measuring point alarm parameters are used as simple alarm functions, simple automatic evaluation is carried out on whether the measuring point temperature exceeds the absolute standard of the set alarm temperature, the evaluation result can be counted into the diagnosis conclusion of the equipment, and the final diagnosis conclusion is influenced by a corresponding calculation algorithm. The alarm of the temperature of the measuring point does not mean that the equipment diagnosis conclusion is normal, and the alarm of the temperature of the measuring point is accompanied with the abnormality of the equipment diagnosis conclusion.
The process and method for completing diagnosis on the PC-side infrared analysis software are similar to those on a thermal infrared imager. Firstly, a fault analysis model is built on software, the fault analysis model is uploaded to a thermal imager, and data is downloaded after the test is completed. And operating the diagnosis system through software menu operation, and completing diagnosis one by one for each complete machine test in the equipment tree structure.
The invention sets an open rule base, which can be supplemented and perfected by rule editing tools according to new problems encountered in practical application, besides optimizing by adjusting fault analysis model. This part is integrated in the components of the fault analysis model part.
The invention can be applied to the field of equipment state monitoring. Such as: the method comprises the steps of power plant booster station electrical equipment periodic detection, inspection temperature detection of inspection points of various factory rotating machines, equipment fault analysis, life prediction and the like.
Fig. 4 is a modeling flowchart corresponding to embodiment 2 of the equipment failure detection method according to the present invention. As shown in fig. 4, the modeling flow includes:
step 401: inspecting the machine;
step 402: constructing a device structure tree and modeling;
step 403: uploading;
step 404: collecting an infrared thermal image of equipment on site;
step 405: performing field diagnosis, namely performing fault diagnosis by using the established model;
step 406: judging whether the equipment problem needs to be confirmed by a worker, if so, returning to the step 404, and re-acquiring an infrared thermal image of the equipment for analysis by the worker; if not, go to step 407;
step 407: downloading;
step 408: further analysis and diagnosis;
step 409: judging whether the diagnosis result has deviation or not, if so, returning to the step 402, and reestablishing a model; if not, go to step 4010;
step 4010: confirming a conclusion;
step 4011: judging whether the equipment model has change or not; if yes, returning to step 402, re-establishing the model; if not, the infrared thermal image of the equipment is acquired again.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (9)
1. A method of equipment failure detection, the method comprising:
obtaining model parameters and a rule base; the model parameters include: the equipment type, the equipment structure, the number, the distribution and the attribute of the measuring points; different equipment types correspond to different equipment structures, measuring point numbers, distribution and measuring point attributes; the rule base includes: fault type, fault characteristic parameters corresponding to the fault type, a set threshold value of the fault characteristic parameters and logic rules of fault diagnosis;
constructing a fault model of the equipment according to the model parameter combination rule base, wherein each equipment type corresponds to a plurality of fault models, and each fault model comprises a fault characteristic parameter, a set threshold value of the fault characteristic parameter and a corresponding fault type;
acquiring an infrared thermal image of each measuring point of the equipment;
extracting equipment characteristic parameters in the infrared thermal image according to the model parameters;
obtaining a fault detection result of the equipment according to the fault model and the equipment characteristic parameters and the logic rule of fault diagnosis; the fault detection result comprises a fault part and a fault severity level;
the step of obtaining the fault detection result of the equipment according to the fault model and the equipment characteristic parameters specifically comprises the following steps:
extracting a fault model corresponding to the equipment according to the equipment characteristic parameters, wherein the fault model corresponding to the equipment is a fault model corresponding to the equipment type to which the equipment belongs;
comparing the equipment characteristic parameters with the fault models corresponding to the equipment one by one, and acquiring fault types corresponding to the equipment according to the logic rules of fault diagnosis;
for each fault type corresponding to the equipment, determining a fault part corresponding to the fault type according to the fault type and the model parameters;
comparing the equipment characteristic parameters with fault characteristic parameters corresponding to the fault types to obtain a difference value of the equipment characteristic parameters and the fault characteristic parameters;
according to logic rules in the rule base, carrying out logic weighting calculation on the difference value to determine the fault severity level of the fault type; and sequentially obtaining fault positions and fault severity levels corresponding to all fault types corresponding to the equipment.
2. The method of claim 1, wherein the rule base further comprises: and processing suggestions and fault reasons corresponding to the fault types.
3. Method according to claim 1, characterized in that the rule base is an open structure for adding new fault diagnosis logic rules and/or new fault types corresponding to new fault characteristic parameters and new set thresholds.
4. The method of claim 1, wherein the model parameters further comprise: and the temperature/temperature rise standard parameters and the alarm parameters are used for judging whether the temperature/temperature rise actual values of the measuring points are larger than the standard parameters, and outputting the alarm parameters when the temperature/temperature rise actual values of the measuring points are larger than the standard parameters.
5. The method according to claim 2, wherein after obtaining the fault detection result of the device, further comprising:
and acquiring corresponding processing suggestions and fault reasons according to the fault model.
6. The method according to claim 1, wherein after obtaining the fault detection result of the device according to the fault model and the device characteristic parameter, the method further comprises:
comparison analysis of longitudinal historical data: generating a temperature and/or temperature rising trend curve according to the historical data of the same measuring point, and analyzing the historical trend and predicting future data;
and (3) comparing and analyzing data of the transverse similar equipment: and comparing and displaying infrared images of different measuring points of the same measuring position of the same equipment to obtain temperature/temperature rise parameters and temperature distribution of the same equipment.
7. An equipment failure detection system for performing the equipment failure detection method of any of claims 1-6, the system comprising: the device comprises an image acquisition device, an image recognition device, an infrared analysis device and an image display device;
the input end of the image recognition device is connected with the output end of the image acquisition device and is used for receiving the infrared thermal image of each measuring point of the equipment acquired by the image acquisition device and extracting the equipment characteristic parameters corresponding to the model parameters in the infrared thermal image; the model parameters include: the equipment type, the equipment structure, the number, the distribution and the attribute of the measuring points;
the input end of the infrared analysis device is connected with the output end of the image recognition device and is used for outputting a fault detection result of the equipment according to the equipment characteristic parameters extracted by the image recognition device; the fault detection result comprises a fault part and a fault severity level;
the input end of the image display device is connected with the output end of the infrared analysis device and is used for displaying the fault detection result.
8. The system of claim 7, wherein the system further comprises:
the input end of the first alarm device is connected with the output end of the image recognition device, and when the temperature of the measuring point exceeds a set temperature threshold value, the first alarm device starts an alarm and outputs information of fault detection abnormality to the image display device;
and the input end of the second alarm device is connected with the output end of the image acquisition device, and the acquisition prompt alarm is started according to the acquisition period of the image acquisition device.
9. The system of claim 7, wherein the system controls the image acquisition device to automatically position the measuring point for image acquisition by a two-dimensional code or a bar code of the measuring point of the device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710502240.5A CN107167497B (en) | 2017-06-27 | 2017-06-27 | Equipment fault detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710502240.5A CN107167497B (en) | 2017-06-27 | 2017-06-27 | Equipment fault detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107167497A CN107167497A (en) | 2017-09-15 |
| CN107167497B true CN107167497B (en) | 2023-08-08 |
Family
ID=59826914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710502240.5A Active CN107167497B (en) | 2017-06-27 | 2017-06-27 | Equipment fault detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107167497B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909096A (en) * | 2017-11-08 | 2018-04-13 | 南京因泰莱电器股份有限公司 | A kind of fault of converter early warning criterion implementation method based on two points of K mean clusters |
| CN107992581B (en) * | 2017-12-07 | 2020-12-08 | 北京能源集团有限责任公司 | Service processing method, device and system |
| CN108896186A (en) * | 2018-05-15 | 2018-11-27 | 云南电网有限责任公司迪庆供电局 | The method and device of equipment intelligent diagnosis |
| CN109325603B (en) * | 2018-09-11 | 2020-12-01 | 国网河北省电力有限公司沧州供电分公司 | Fault request processing method and device and terminal equipment |
| CN109271407A (en) * | 2018-09-27 | 2019-01-25 | 西安银石科技发展有限责任公司 | A kind of equipment routing inspection method based on machine learning |
| CN109738752B (en) * | 2018-11-13 | 2021-01-29 | 杭州意能电力技术有限公司 | Rapid imaging method for ground grid maintenance |
| CN109711570A (en) * | 2018-12-26 | 2019-05-03 | 中国移动通信集团江苏有限公司 | Method, apparatus, equipment and the medium of machine monitoring |
| CN109900501A (en) * | 2019-01-31 | 2019-06-18 | 石家庄铁道大学 | High-speed EMUs vehicle artificial intelligence lossless detection method |
| CN110274695A (en) * | 2019-03-21 | 2019-09-24 | 国网浙江省电力有限公司丽水供电公司 | A kind of substation equipment failure method for inspecting |
| CN110618888A (en) * | 2019-08-01 | 2019-12-27 | 平安科技（深圳）有限公司 | Method and related device for repeatedly identifying system errors |
| CN111177485B (en) * | 2019-12-16 | 2023-06-27 | 中建材智慧工业科技有限公司 | Parameter rule matching based equipment fault prediction method, equipment and medium |
| CN111337237B (en) * | 2020-03-17 | 2021-10-15 | 北京必可测科技股份有限公司 | Equipment fault diagnosis method and system |
| CN112834884A (en) * | 2021-01-07 | 2021-05-25 | 华翔翔能科技股份有限公司 | Partial discharge analysis method and system for oil-immersed transformer |
| CN112881842A (en) * | 2021-01-25 | 2021-06-01 | 众智学府信息技术有限公司 | Intelligent diagnosis module for equipment |
| CN113358229B (en) * | 2021-06-17 | 2022-12-13 | 北京源仿科技有限公司 | Intelligent detection and simulation method for power transformation equipment |
| CN113848761A (en) * | 2021-09-23 | 2021-12-28 | 上海基申智能科技有限公司 | Electric appliance safety early warning system and control method |
| CN114065790A (en) * | 2021-09-27 | 2022-02-18 | 华能汕头海门发电有限责任公司 | Two-dimensional code management system based on image recognition temperature |
| CN114236314A (en) * | 2021-12-17 | 2022-03-25 | 瀚云科技有限公司 | Fault detection method, device, equipment and storage medium |
| CN115090514A (en) * | 2022-06-24 | 2022-09-23 | 北京建工资源循环利用投资有限公司 | Control method and device of garbage screening system, electronic equipment and medium |
| CN117931575A (en) * | 2024-01-26 | 2024-04-26 | 广东云达智能物联科技有限公司 | Terminal information digital management system based on Internet of things |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819239A (en) * | 2010-04-06 | 2010-09-01 | 嘉兴学院 | Rapidly constructed transformer fault diagnosis system based on three-dimensional temperature field |
| CN103617469A (en) * | 2013-12-18 | 2014-03-05 | 重庆大学 | Equipment failure prediction method and system of electrical power system |
| CN105548747A (en) * | 2015-12-04 | 2016-05-04 | 国网技术学院 | Equipment fault identification system and method based on infrared temperature measurement technology |
| CN106197672A (en) * | 2016-06-21 | 2016-12-07 | 国家电网公司 | A kind of transformator method of real-time based on infrared thermal imaging |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9606520B2 (en) * | 2009-06-22 | 2017-03-28 | Johnson Controls Technology Company | Automated fault detection and diagnostics in a building management system |
| US9509923B2 (en) * | 2012-01-10 | 2016-11-29 | General Electric Company | Continuous infrared thermography monitoring and life management system for heat recovery steam generators |
-
2017
- 2017-06-27 CN CN201710502240.5A patent/CN107167497B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819239A (en) * | 2010-04-06 | 2010-09-01 | 嘉兴学院 | Rapidly constructed transformer fault diagnosis system based on three-dimensional temperature field |
| CN103617469A (en) * | 2013-12-18 | 2014-03-05 | 重庆大学 | Equipment failure prediction method and system of electrical power system |
| CN105548747A (en) * | 2015-12-04 | 2016-05-04 | 国网技术学院 | Equipment fault identification system and method based on infrared temperature measurement technology |
| CN106197672A (en) * | 2016-06-21 | 2016-12-07 | 国家电网公司 | A kind of transformator method of real-time based on infrared thermal imaging |
Non-Patent Citations (1)
| Title |
|---|
| 黄立 ; .第四讲 红外诊断工作程序及要求.电世界.1999,(11),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107167497A (en) | 2017-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107167497B (en) | Equipment fault detection method and system | |
| CN112039073B (en) | Collaborative optimization method and system suitable for fault judgment of power distribution room equipment | |
| CN105548747A (en) | Equipment fault identification system and method based on infrared temperature measurement technology | |
| WO2019214231A1 (en) | Faulty arc detection method, device and system | |
| CN111431284B (en) | BIM technology-based intelligent transformer substation management and control system | |
| CN113763667B (en) | Fire disaster early warning and state monitoring device and method based on 5G edge calculation | |
| CN113779769A (en) | Cable test digital twinning system and working method thereof | |
| CN113820017A (en) | Generator carbon brush temperature monitoring system based on infrared image and temperature prediction method | |
| CN115238915A (en) | Industrial equipment fault prediction and health monitoring system | |
| CN116418117A (en) | Equipment detection system for intelligent power grid | |
| CN111384776B (en) | VR-based transformer substation three-dimensional panoramic state monitoring method and system | |
| CN105867267A (en) | Method for automatically reporting instrument readings of distribution station room through image identification technology | |
| CN114419753A (en) | Intelligent patrol system and method | |
| CN117319451B (en) | Urban fire-fighting Internet of things supervision system based on multi-mode big data and method thereof | |
| CN206862938U (en) | A kind of equipment fault detection means | |
| CN112153344B (en) | Power distribution room equipment state online intelligent monitoring system and method based on embedded GPU platform and deep learning | |
| CN116523498A (en) | AI-based power facility inspection method, system, device and storage medium | |
| CN116258333A (en) | Intelligent inspection method and intelligent inspection system for nuclear power plant | |
| JP2023018016A (en) | Management system and cause analysis system | |
| CN114942075A (en) | Power equipment fault detection and analysis method | |
| CN113866536A (en) | Temperature rise detection method and device and temperature rise detection system | |
| CN112782236B (en) | Material state monitoring method, system and device of converter cabinet and storage medium | |
| CN114113900A (en) | GIL detection system and using method thereof | |
| US20210108618A1 (en) | System and method for determining an operating condition of a wind turbine | |
| CN105784192A (en) | Method for monitoring power equipment in cable pit online through optical fiber sensing technology |
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 |