CN115081518B - Intelligent search-based fault diagnosis method and system for low-temperature refrigeration system - Google Patents
Intelligent search-based fault diagnosis method and system for low-temperature refrigeration system Download PDFInfo
- Publication number
- CN115081518B CN115081518B CN202210634641.7A CN202210634641A CN115081518B CN 115081518 B CN115081518 B CN 115081518B CN 202210634641 A CN202210634641 A CN 202210634641A CN 115081518 B CN115081518 B CN 115081518B
- Authority
- CN
- China
- Prior art keywords
- information
- trained
- temperature
- fault diagnosis
- data
- 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
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Devices That Are Associated With Refrigeration Equipment (AREA)
Abstract
The invention discloses a fault diagnosis method and a fault diagnosis system for a low-temperature refrigeration system based on intelligent search, wherein the method comprises the following steps: uniformly storing the working state information of the cold equipment into a data set to be trained; training the data set to be trained to obtain the weight of the network model to be trained; inputting the re-detected working state information of the refrigeration equipment into a network model based on the weight information to establish a low-temperature refrigeration system fault database and a low-temperature refrigeration system fault diagnosis rule data table; adjusting training parameters of the network model, outputting training diagnosis results based on the established low-temperature refrigerating system fault database and the low-temperature refrigerating system fault diagnosis rule data table, and obtaining the network model which is completed to be trained; the network model receives the newly acquired working state information of the refrigeration equipment, adopts a low-temperature fault diagnosis database judgment rule to carry out fault diagnosis on the working state of the refrigeration equipment and outputs a diagnosis result.
Description
Technical Field
The invention relates to the technical field of fault detection of a low-temperature refrigerating system, in particular to a fault diagnosis method and system of the low-temperature refrigerating system based on intelligent search.
Background
In the field of low-temperature refrigeration, the refrigeration equipment and the refrigeration environment need to be precisely controlled, so that the normal operation of the cold chain equipment can be ensured. In the prior art, faults of the low-temperature refrigerating system are generally carried out through modes such as a performance detection line and manual detection, however, the performance detection line can only reflect abnormal curves and parameters, maintenance personnel cannot be guided to solve the problems, and many problems can only be acquired through the detection line, a universal meter and a manual listening mode, so that the phenomena of inaccurate fault diagnosis data, fault leakage diagnosis and operation of fault equipment in hidden danger are caused, and the defects are brought to normal operation of the refrigerating system.
Disclosure of Invention
According to the problems existing in the prior art, the invention discloses a low-temperature refrigerating system fault diagnosis method based on intelligent search, which specifically comprises the following steps:
the method for automatically searching and intelligently diagnosing the faults of the low-temperature refrigerating system by establishing a database comprises the following steps:
collecting working state information of refrigeration equipment, and uniformly storing the data information into a data set to be trained;
building a convolutional neural network, and training a data set to be trained to obtain the weight of the data set to be trained of the network model;
inputting the re-detected working state information of the refrigeration equipment into a network model based on the weight information to establish a low-temperature refrigeration system fault database and a low-temperature refrigeration system fault diagnosis rule data table;
adjusting training parameters of the network model, inputting working state information of the refrigeration equipment into the network model for training, outputting training diagnosis results based on the established low-temperature refrigeration system fault database and the low-temperature refrigeration system fault diagnosis rule data table, and obtaining the trained network model;
the network model receives the newly acquired working state information of the refrigeration equipment, adopts a low-temperature fault diagnosis database judgment rule to carry out fault diagnosis on the working state of the refrigeration equipment and outputs a diagnosis result.
When training the data set to be trained, the data set to be trained is: dividing data to be trained into a plurality of parts according to characteristic information, carrying out global average pooling operation on each part of data to obtain global context information of each part of data after each channel is coded in a neural network, carrying out independent keyword labeling on each part of input global context information to obtain attention weight of each channel, and multiplying the attention weight and input information to obtain fault codes.
And performing loss calculation by using a cross entropy loss method so as to optimize the convolutional neural network, storing weight information after each generation of training is finished in the optimization process, and selecting the weight information with the minimum loss value as the weight of the data set to be trained by the network model.
When the fault database of the low-temperature refrigerating system is established:
firstly, establishing a data table with a model as an index, wherein the data table comprises temperature, wind speed, noise and refrigerant leakage factor information;
the temperature, wind speed, noise and gas leakage conditions of a pipeline, a compressor, a fan and an interface are detected by adopting a temperature sensor, a wind speed sensor, a noise sensor and a gas leakage detector extension type;
and inputting the data detected by the extension type sample into a data table according to the model index.
When the fault diagnosis rule data table of the low-temperature refrigerating system is established:
establishing a data table with a model as an index, wherein the data table comprises temperature, wind speed, noise and upper and lower limit element information of refrigerant leakage;
the upper and lower standard values of temperature, wind speed, noise and gas leakage of a pipeline, a compressor, a fan and an interface of a computer type are recorded into a data table;
recording the fault code judged after the upper limit and the lower limit are exceeded into a data table;
the upper and lower limit criteria are logically associated with the fault code.
The low-temperature fault diagnosis database judging rule is as follows:
receiving temperature, noise, wind speed and gas leakage information of the refrigeration equipment in the working state, and outputting the information to a trained network model for fault diagnosis;
and searching the input information according to the model, judging whether the input information is temperature data, entering a fault database of the low-temperature refrigeration system if the input information is temperature data, comparing the input information with the upper limit and the lower limit of a fault diagnosis rule data table of the low-temperature refrigeration system, judging that the fault occurs and outputting a fault code if the fault diagnosis rule data table exceeds the upper limit and the lower limit.
When the network model performs fault diagnosis: and (3) indexing according to the machine type, sequentially searching temperature, wind speed, noise and refrigerant leakage conditions one by one, and outputting a plurality of corresponding fault codes if a plurality of parameters exceeding upper and lower limits occur in the searching process.
A cryogenic refrigeration system fault diagnosis system based on intelligent searching and mining technology automatically searches and intelligently diagnoses faults of a cryogenic refrigeration system by establishing a database, and comprises the following components:
the information acquisition unit acquires working state information of the refrigeration equipment and uniformly stores the data information into a data set to be trained;
the model construction unit is used for establishing a convolutional neural network, and training a data set to be trained by adopting the convolutional neural network to obtain the weight of the data set to be trained by the network model;
the model training unit firstly establishes a low-temperature refrigerating system fault database and a low-temperature refrigerating system fault diagnosis rule data table, inputs the re-detected working state information of the refrigerating equipment into the network model based on weight information for training, adjusts training parameters of the network model, outputs a training diagnosis result and obtains a trained network model;
and the result output unit is used for receiving the newly acquired working state information of the refrigeration equipment, carrying out fault diagnosis on the working condition of the refrigeration equipment by adopting a low-temperature fault diagnosis database judgment rule and outputting a diagnosis result.
By adopting the technical scheme, the method and the system for diagnosing the fault of the low-temperature refrigerating system based on intelligent search, provided by the invention, ensure that the network model has certain identification and judgment precision by establishing and training the neural network model, and achieve the effect of quickly and accurately finding out the fault point through the fault code by inputting the working state parameter information of the refrigerating system into the network model for fault diagnosis, thereby realizing the accurate and efficient working effect of the low-temperature refrigerating system and greatly improving the working efficiency of maintenance personnel.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and 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 the method of the present invention;
FIG. 2 is a schematic diagram of a low-temperature fault diagnosis database judgment rule in the method of the invention;
fig. 3 is a block diagram of the system of the present invention.
Detailed Description
In order to make the technical scheme and advantages of the present invention more clear, the technical scheme in the embodiment of the present invention is clearly and completely described below with reference to the accompanying drawings in the embodiment of the present invention:
the fault diagnosis method of the low-temperature refrigeration system based on intelligent search as shown in fig. 1 specifically comprises the following steps:
s1, collecting working state information such as temperature, noise, wind speed, refrigerant leakage condition and the like of a low-temperature refrigerating system, carrying out data processing and early classification on the collected information, and finally uniformly storing the processed data to define a data set to be trained.
And S2, building a convolutional neural network, wherein the neural network comprises a trunk feature extraction network and a reinforcement feature extraction network, when a data set to be trained is trained, firstly loading initial weight information, inputting the data set to be trained, firstly training the data set for 60 times, modifying learning rate for different data sets to achieve the best effect, storing the weight information after each training, and selecting the weight information with the minimum loss as a final result.
And S3, inputting the re-detected working state information of the refrigeration equipment into a network model based on the weight information, and establishing a low-temperature refrigeration system fault database and a low-temperature refrigeration system fault diagnosis rule data table.
The fault database of the low-temperature refrigeration system is specifically established by the following modes:
firstly, establishing a data table with a model as an index, wherein the data table comprises temperature, wind speed, noise and refrigerant leakage elements;
detecting the temperature, wind speed, noise and gas leakage of a pipeline, a compressor, a fan and an interface by using a temperature sensor, a wind speed sensor, a noise sensor and a gas leakage detector, and taking 20 samples as average values of sample sizes;
and inputting the data detected by the extension type sample into a data table according to the model index.
The fault diagnosis rule data table of the low-temperature refrigeration system is established by adopting the following modes:
firstly, establishing a data table with a model as an index, wherein the data table comprises upper and lower limit elements of temperature, wind speed, noise and refrigerant leakage;
the temperature, wind speed, noise and upper and lower limit standard values of gas leakage of a pipeline, a compressor, a fan and an interface of a computer type are recorded into a data table.
And recording the fault codes exceeding the upper limit value and the lower limit value in the data table.
The upper and lower limit standards are in one-to-one correspondence with the fault code logic.
And S4, adjusting training parameters of the network model, inputting working state information of the refrigeration equipment into the network model for training, outputting a training diagnosis result based on the established low-temperature refrigeration system fault database and the low-temperature refrigeration system fault diagnosis rule data table, and obtaining the trained network model.
In the specific implementation process, as shown in fig. 2, the temperature, noise, wind speed and gas leakage information of the low-temperature refrigerating system are input into a network model, information retrieval is carried out on the input information according to a model, whether the temperature data are temperature data is judged, if the temperature data are temperature data, the temperature data are input into a fault database of the low-temperature refrigerating system, meanwhile, the temperature data are compared with the upper limit value and the lower limit value of a fault diagnosis rule data table of the low-temperature refrigerating system, if the temperature data are above the upper limit value or below the lower limit value, the judging result is fault, and a fault code is output, so that the process of training a neural network model is finally realized, and the network model is ensured to have certain judging and identifying precision.
And S5, finally, the network model receives the newly acquired working state information of the refrigeration equipment, performs fault diagnosis on the working condition of the refrigeration equipment by adopting a low-temperature fault diagnosis database judgment rule, and outputs a diagnosis result.
Further, when training the data set to be trained: dividing data to be trained into a plurality of parts according to characteristic information, carrying out global average pooling operation on each part of data to obtain global context information of each part of data after each channel is coded in a neural network, carrying out independent keyword labeling on each part of input global context information to obtain attention weight of each channel, and multiplying the attention weight and input information to obtain fault codes.
Wherein the fault code consists of letters and numbers, the letters are 1 bit, the numbers are 4 bits (2 bits are reserved), such as refrigerant leakage fault Y00; wherein the letter rules may be: s represents: the electric appliance system, Y represents the compressor system, D represents the evaporator, W represents the box, Z represents the capillary, L represents the condenser, F represents the low-temperature pipeline. Wherein the numerical rule may be: 00. refrigerant leakage, 1, power failure, 2, voltage failure, 3, current failure, 4, resistance failure, 5, too high temperature, 6, too low temperature, 7, too high noise, 8 and too low wind speed.
Further, a cross entropy loss method is used for carrying out loss calculation so as to optimize the convolutional neural network, weight information is stored after each generation of training is finished in the optimization process, and the weight information with the minimum loss value is selected as the weight of the data set to be trained by the network model.
Loss calculation is performed in training by using a cross entropy loss method to optimize the network:
where M represents the number of categories of refrigeration system operating state parameters, yic represents a sign function (0 or 1), pic represents the predicted probability that the observation sample i belongs to category c.
Further, the low-temperature fault diagnosis database judging rule is as follows:
receiving temperature, noise, wind speed and gas leakage information of the refrigeration equipment in the working state, and outputting the information to a trained network model for fault diagnosis;
and searching the input information according to the model, judging whether the input information is temperature data, entering a fault database of the low-temperature refrigeration system if the input information is temperature data, comparing the input information with the upper limit and the lower limit of a fault diagnosis rule data table of the low-temperature refrigeration system, judging that the fault occurs and outputting a fault code if the fault diagnosis rule data table exceeds the upper limit and the lower limit.
Further, when the network model performs fault diagnosis: and (3) indexing according to the machine type, sequentially searching temperature, wind speed, noise and refrigerant leakage conditions one by one, and outputting a plurality of corresponding fault codes if a plurality of parameters exceeding upper and lower limits occur in the searching process.
In practical application, the sensor for low-temperature diagnosis is connected with a diagnosed product, the machine type is input through a display end, diagnosis is started, sensor information data including temperature, wind speed, noise and refrigerant leakage data are transmitted to a network model through the sensor, the temperature, the wind speed, the noise and the refrigerant leakage in a low-temperature refrigerating system fault database and a low-temperature refrigerating system fault diagnosis rule data table are sequentially searched and compared, if the temperature data is in the temperature range of the machine type, the machine type is compared, logic judgment is carried out by adopting a low-temperature fault diagnosis database judgment rule, and a fault code is given. If the air-speed comparison is free of problems, entering into noise comparison, if the air-speed comparison is free of problems, entering into refrigerant leakage comparison, if the air-speed comparison is free of problems, judging to be in accordance with judgment logic through judgment, and displaying fault codes to an output end.
As shown in fig. 3, a fault diagnosis system for a cryogenic refrigeration system based on an intelligent search and mining technology, which automatically searches and intelligently diagnoses faults of the cryogenic refrigeration system by establishing a database, comprises:
the information acquisition unit acquires working state information of the refrigeration equipment and uniformly stores the data information into a data set to be trained;
the model construction unit is used for establishing a convolutional neural network, and training a data set to be trained by adopting the convolutional neural network to obtain the weight of the data set to be trained by the network model;
the model training unit firstly establishes a low-temperature refrigerating system fault database and a low-temperature refrigerating system fault diagnosis rule data table, inputs the re-detected working state information of the refrigerating equipment into the network model based on weight information for training, adjusts training parameters of the network model, outputs a training diagnosis result and obtains a trained network model;
and the result output unit is used for receiving the newly acquired working state information of the refrigeration equipment, carrying out fault diagnosis on the working condition of the refrigeration equipment by adopting a low-temperature fault diagnosis database judgment rule and outputting a diagnosis result.
The system performs fault diagnosis and implementation based on the method disclosed by the application, inputs the detected temperature, noise, wind speed and gas leakage information of the low-temperature refrigerating system into a neural network model for fault judgment, performs fault judgment according to logical relation terms, outputs fault codes and displays the fault codes.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (7)
1. A refrigerating system fault diagnosis method based on intelligent search is characterized in that: the method for automatically searching and intelligently diagnosing the faults of the refrigerating system by establishing a database comprises the following steps:
collecting working state information of refrigeration equipment, and uniformly storing the data information into a data set to be trained;
building a convolutional neural network, and training a data set to be trained to obtain the weight of the data set to be trained of the network model;
inputting the re-detected working state information of the refrigeration equipment into a network model based on the weight information to establish a refrigeration system fault database and a refrigeration system fault diagnosis rule data table;
adjusting training parameters of the network model, inputting working state information of the refrigeration equipment into the network model for training, outputting training diagnosis results based on the established refrigeration system fault database and the refrigeration system fault diagnosis rule data table, and obtaining the trained network model;
the network model receives the newly acquired working state information of the refrigeration equipment, adopts a fault diagnosis database judgment rule to carry out fault diagnosis on the working condition of the refrigeration equipment and outputs a diagnosis result;
when training the data set to be trained, the data set to be trained is: dividing data to be trained into a plurality of parts according to characteristic information, carrying out global average pooling operation on each part of data to obtain global context information of each part of data after each channel is coded in a neural network, carrying out independent keyword labeling on each part of input global context information to obtain attention weight of each channel, and multiplying the attention weight and input information to obtain fault codes.
2. The method according to claim 1, characterized in that: and performing loss calculation by using a cross entropy loss method so as to optimize the convolutional neural network, storing weight information after each generation of training is finished in the optimization process, and selecting the weight information with the minimum loss value as the weight of the data set to be trained by the network model.
3. The method according to claim 2, characterized in that: when the refrigerating system fault database is established:
firstly, establishing a data table with a model as an index, wherein the data table comprises temperature, wind speed, noise and refrigerant leakage factor information;
the temperature, wind speed, noise and gas leakage conditions of a pipeline, a compressor, a fan and an interface are detected by adopting a temperature sensor, a wind speed sensor, a noise sensor and a gas leakage detector extension type;
and inputting the data detected by the extension type sample into a data table according to the model index.
4. The method according to claim 2, characterized in that: when the refrigerating system fault diagnosis rule data table is established, the following steps are carried out:
establishing a data table with a model as an index, wherein the data table comprises temperature, wind speed, noise and upper and lower limit element information of refrigerant leakage;
the upper and lower standard values of temperature, wind speed, noise and gas leakage of a pipeline, a compressor, a fan and an interface of a computer type are recorded into a data table;
recording the fault code judged after the upper limit and the lower limit are exceeded into a data table;
the upper and lower limit criteria are logically associated with the fault code.
5. The method according to claim 4, wherein: the fault diagnosis database judging rule is as follows:
receiving temperature, noise, wind speed and gas leakage information of the refrigeration equipment in the working state, and outputting the information to a trained network model for fault diagnosis;
and searching the input information according to the model, judging whether the input information is temperature data, entering a refrigerating system fault database if the input information is temperature data, comparing the input information with the upper limit and the lower limit of a refrigerating system fault diagnosis rule data table, judging that faults occur and outputting fault codes if the input information exceeds the upper limit and the lower limit.
6. The method according to claim 5, wherein: when the network model performs fault diagnosis: and (3) indexing according to the machine type, sequentially searching temperature, wind speed, noise and refrigerant leakage conditions one by one, and outputting a plurality of corresponding fault codes if a plurality of parameters exceeding upper and lower limits occur in the searching process.
7. A refrigerating system fault diagnosis system based on intelligent searching and excavating technology is characterized in that: automatic searching and intelligent diagnosis of faults of the refrigerating system by establishing a database comprises the following steps:
the information acquisition unit acquires working state information of the refrigeration equipment and uniformly stores the data information into a data set to be trained;
the model construction unit is used for establishing a convolutional neural network, and training a data set to be trained by adopting the convolutional neural network to obtain the weight of the data set to be trained by the network model;
the model training unit firstly establishes a refrigerating system fault database and a refrigerating system fault diagnosis rule data table, inputs the re-detected working state information of the refrigerating equipment into the network model based on weight information for training, adjusts training parameters of the network model, outputs a training diagnosis result and obtains a trained network model; when the data set to be trained is trained: dividing data to be trained into a plurality of parts according to characteristic information, carrying out global average pooling operation on each part of data to obtain global context information of each part of data after each channel is coded in a neural network, carrying out independent keyword labeling on each part of input global context information to obtain attention weight of each channel, and multiplying the attention weight and input information to obtain fault codes
And the result output unit is used for receiving the newly acquired working state information of the refrigeration equipment, carrying out fault diagnosis on the working condition of the refrigeration equipment by adopting a fault diagnosis database judgment rule and outputting a diagnosis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210634641.7A CN115081518B (en) | 2022-06-06 | 2022-06-06 | Intelligent search-based fault diagnosis method and system for low-temperature refrigeration system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210634641.7A CN115081518B (en) | 2022-06-06 | 2022-06-06 | Intelligent search-based fault diagnosis method and system for low-temperature refrigeration system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115081518A CN115081518A (en) | 2022-09-20 |
| CN115081518B true CN115081518B (en) | 2023-05-16 |
Family
ID=83252009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210634641.7A Active CN115081518B (en) | 2022-06-06 | 2022-06-06 | Intelligent search-based fault diagnosis method and system for low-temperature refrigeration system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115081518B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010025474A (en) * | 2008-07-22 | 2010-02-04 | Samsung Electronics Co Ltd | Failure diagnostic device used in refrigerating cycle equipment |
| CN113792762A (en) * | 2021-08-24 | 2021-12-14 | 华南理工大学 | Water chilling unit fault diagnosis method, system and medium based on Bayesian optimization LightGBM |
-
2022
- 2022-06-06 CN CN202210634641.7A patent/CN115081518B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010025474A (en) * | 2008-07-22 | 2010-02-04 | Samsung Electronics Co Ltd | Failure diagnostic device used in refrigerating cycle equipment |
| CN113792762A (en) * | 2021-08-24 | 2021-12-14 | 华南理工大学 | Water chilling unit fault diagnosis method, system and medium based on Bayesian optimization LightGBM |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115081518A (en) | 2022-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111444940A (en) | Fault diagnosis method for critical parts of fan | |
| CN112179691B (en) | Mechanical equipment running state abnormity detection system and method based on counterstudy strategy | |
| CN113792762A (en) | Water chilling unit fault diagnosis method, system and medium based on Bayesian optimization LightGBM | |
| CN115187832A (en) | Energy system fault diagnosis method based on deep learning and gram angular field image | |
| CN112097365A (en) | Air conditioner fault detection and identification method and device based on prediction and classification model | |
| CN114484731A (en) | Method and device for diagnosing faults of central air conditioner based on stacking fusion algorithm | |
| CN111380686A (en) | XGboost algorithm model-based fan main bearing fault monitoring and diagnosis method | |
| CN115614292B (en) | Vibration monitoring device and method for vertical water pump unit | |
| CN111723925A (en) | Method, device, equipment and medium for fault diagnosis of on-road intelligent train air conditioning unit | |
| CN115544140A (en) | Photovoltaic power station performance detection system and method based on artificial intelligence | |
| CN112001511A (en) | Equipment reliability and dynamic risk evaluation method, system and equipment based on data mining | |
| CN109344518A (en) | A kind of method for diagnosing faults of base station heat management system | |
| CN115392782A (en) | Method and system for monitoring and diagnosing health state of process system of nuclear power plant | |
| CN115902476A (en) | Multi-dimensional transformer fault diagnosis and state evaluation system and method | |
| CN115081518B (en) | Intelligent search-based fault diagnosis method and system for low-temperature refrigeration system | |
| CN118300860A (en) | Power network anomaly detection system based on machine learning and advanced semantic mapping | |
| CN118501692A (en) | Servo motor fault diagnosis method and system | |
| CN113505531B (en) | Diagnostic model construction method based on combination of traditional diagnosis and machine learning method and aiming at abnormal valve clearance faults of reciprocating machinery | |
| CN110968703A (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN116664098A (en) | Abnormality detection method and system for photovoltaic power station | |
| CN115186581A (en) | Engine water temperature fault prediction method and device and storage medium | |
| CN111639711B (en) | Oil pipeline leakage monitoring method based on pressure monitoring time sequence data | |
| Deng et al. | A cost-sensitive dense network for fault diagnosis under data imbalance | |
| CN106056223A (en) | Platform for vehicle remote diagnosis and spare part retrieval | |
| CN118501720B (en) | Lithium battery abnormality detection system based on big data 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |