CN117670086A - Compressor fault prediction method and system based on big data and machine learning - Google Patents
Compressor fault prediction method and system based on big data and machine learning Download PDFInfo
- Publication number
- CN117670086A CN117670086A CN202311659532.1A CN202311659532A CN117670086A CN 117670086 A CN117670086 A CN 117670086A CN 202311659532 A CN202311659532 A CN 202311659532A CN 117670086 A CN117670086 A CN 117670086A
- Authority
- CN
- China
- Prior art keywords
- compressor
- fault
- data
- operation data
- normal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000010801 machine learning Methods 0.000 title claims abstract description 22
- 230000001537 neural effect Effects 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 11
- 230000008859 change Effects 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 22
- 238000004519 manufacturing process Methods 0.000 description 11
- 238000007405 data analysis Methods 0.000 description 6
- 238000001595 flow curve Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to a compressor fault prediction method and system based on big data and machine learning, wherein the method comprises the following steps of S1, collecting historical operation data of a compressor to be detected; s2, based on the normal operation data, determining normal state data of the compressor to be tested under each working condition state according to preset big data and a machine learning method; s3, constructing an initial neural learning network based on the normal state data, inputting the fault operation data into the initial neural learning network for training, and obtaining a comprehensive early warning model; s4, continuously inputting the collected real-time working condition operation data of the compressor to be tested into the comprehensive early warning model, and predicting whether the compressor to be tested is about to fail, and the type, the reason and the time point of the failure. The method can accurately predict the compressor before the compressor fails, so that the compressor can be maintained in time, and the maintenance cost is reduced.
Description
Technical Field
The invention relates to the technical field of compressors, in particular to a compressor fault prediction method and system based on big data and machine learning.
Background
The compressor is a machine for compressing gas to increase gas pressure or delivering gas, and in recent years, the compressor has been widely used with the development of mechanization. Compressors are one of the essential key devices in the mining industry, metallurgical industry, mechanical manufacturing industry, civil engineering, petrochemical industry, refrigeration and gas separation engineering, and defense industry. However, in the case of long-term continuous operation, various faults may occur in the production process of the compressor, and the maintenance difficulty is high, and the cause of the faults needs to be analyzed temporarily, so that the production line is delayed or even stopped, and huge losses are caused. In order to avoid sudden faults, after the compressor is operated for a period of time, people perform regular maintenance, and for maintenance based on the operation time, maintenance work is usually concentrated, the workload is large, and the generated faults are difficult to prevent in time. The defects of uncontrollable faults of the compressor, random faults, maintenance lag and large loss exist.
With the improvement of the self-control level, the prior art also has the technical means of actively maintaining the equipment before the fault occurs by detecting the performance of the equipment, so that the identification rate of abnormal parameters can be improved within a limited range, but due to the lack of a unified frame, difficult data collection and processing, insufficient and accurate data quantity, uncertainty of a prediction process and a prediction result or judgment only according to observation experience, limited applicability of a data algorithm, incapability of realizing advanced equipment fault prediction and accurate fault cause analysis, inaccurate equipment state evaluation (relatively abstract good, general, poor and the like) and incapability of achieving early warning maintenance which is still active, preventive and more accurate.
In addition, there are also means such as signal classification and acquisition to predict the failure of the compressor, but the prediction accuracy is limited and the practicability is not high.
Disclosure of Invention
First, the technical problem to be solved
In view of the defects and shortcomings of the prior art, the invention provides a compressor fault prediction method and a system based on big data and machine learning, which solve the technical problems of uncontrollable prevention of compressor faults, maintenance lag and large loss in the prior art.
(II) technical scheme
In order to achieve the above object, the present invention provides a compressor fault prediction method based on big data and machine learning, comprising:
s1, collecting historical operation data of a compressor to be tested;
the historical operation data comprise normal operation data and fault operation data of the compressor under each working condition state;
s2, based on the normal operation data, determining normal state data of the compressor to be tested under each working condition state according to preset big data and a machine learning method;
s3, constructing an initial neural learning network based on the normal state data, inputting the fault operation data into the initial neural learning network for training, and obtaining a comprehensive early warning model;
s4, continuously inputting the collected real-time working condition operation data of the compressor to be tested into the comprehensive early warning model, and predicting whether the compressor to be tested is about to fail, and the type, the reason and the time point of the failure.
Optionally, in S2, the normal state data includes:
the value range of each normal operation parameter;
traversing the association curve of each normal operating parameter;
and a change curve of each normal operation parameter according to working conditions.
Optionally, the operation parameters of the normal operation data include:
gas inflow temperature, gas outflow temperature, compressor operating voltage, current, compressor operating efficiency, compressor vibration frequency, compressor flow, compressor pressure.
Optionally, the traversing correlation curve of each normal operating parameter includes:
under each working condition, the correlation curves of each normal operation parameter and other i normal operation parameters;
i=1, 2, 3..n-1, n is the number of normal operating parameter entries.
Optionally, S3 specifically includes:
s31, constructing an initial neural learning network based on the normal state data;
s32, dividing the fault operation data into different fault types and fault levels according to a pre-constructed fault rule; each fault level corresponds to at least one fault type;
s33, respectively inputting fault operation data of each fault type into an initial neural learning network for training, and obtaining a comprehensive early warning model.
Optionally, S1 further includes:
and aiming at the accidental fault type, adopting empirical analysis to set fault operation data when the accidental fault type occurs.
Optionally, S3 further includes:
and inputting real-time fault operation data of the compressor into the comprehensive early warning model for training to obtain an optimized comprehensive early warning model.
Optionally, S1 further includes:
and carrying out data cleaning pretreatment on the historical operation data, and filtering abnormal values and noise interference.
Optionally, the method further comprises:
and carrying out interpolation processing on missing values in the historical operation data, wherein the interpolated values are empirically set values.
In a second aspect, the present invention also provides a compressor fault prediction system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods of the first aspect described above when the computer program is executed.
(III) beneficial effects
The invention provides a compressor fault prediction method and a system based on big data and machine learning. And inputting the actual working condition data into a prediction model, and predicting the fault of the compressor according to the development of the real-time data. Early fault early warning is carried out through factors such as running state deviation and parameter change of the compressor, abnormality of the compressor is predicted, so that an operator has enough time to develop running maintenance on the compressor which is about to break down but is not yet, the influence of the fault is analyzed and evaluated, production adjustment can be carried out in time according to the state of the compressor, and the stop risk is greatly reduced. The method has high prediction accuracy, can furthest reduce the running risk of equipment, reasonably distributes running maintenance resources, and has good prospect.
Drawings
FIG. 1 is a flow chart of a compressor fault prediction method based on big data and machine learning according to an embodiment of the present invention;
FIG. 2 is a schematic diagram showing steps of a method for predicting a failure of a compressor based on big data and machine learning according to an embodiment of the present invention;
fig. 3 is an optimization iteration schematic of the comprehensive early warning model according to an embodiment of the present invention.
Detailed Description
The invention will be better explained by the following detailed description of the embodiments with reference to the drawings.
The compressor is used as key equipment widely applied in industry, maintains normal operation and importance thereof, and has large maintenance difficulty, long time and high loss after the compressor fails. At present, in the common period time, the compressors are overhauled in batches to reduce the fault occurrence rate, the workload is large, the overhauling time is long, the production is slow due to the fact that the production is stopped for cooperation and the like, and the loss is high during overhauling.
With the improvement of the self-control level, the data acquisition means are rich, the accumulation of data is more and more, the operation and maintenance work of the compressor is greatly facilitated, the state of the equipment is judged by the state detection and diagnosis means, the reliability evaluation means and the life prediction means based on the current actual working condition of the equipment, the early signs of faults are identified, the fault positions, the severity degree and the fault development trend are judged, and the equipment is actively maintained before the performance of the equipment is reduced to a certain degree or the faults are about to occur according to the analysis and diagnosis result. The method aims at predicting the abnormality of the compressor in advance, has enough advance time for operators to carry out operation maintenance on the compressor, analyzes and evaluates the influence of faults, is beneficial to ensuring the normal operation of the compressor system, greatly reduces the stop risk and reasonably distributes operation maintenance resources.
For this reason, as shown in fig. 1 and 2, the present invention proposes a compressor fault prediction method based on big data and machine learning, and combines the analysis prediction capability of big data and the fast application capability of a model to improve the precision and sensitivity of equipment fault prediction, and the method includes:
s1, collecting historical operation data of a compressor to be tested and storing the historical operation data in a database;
the historical operation data can be various operation data of the compressor obtained through the scada system and/or the dynamic equipment operation data acquisition system, and comprise normal operation data and fault operation data of the compressor in each working condition state, and particularly comprise a plurality of parameters such as gas inflow temperature, gas outflow temperature, compressor operation voltage, current, compressor operation efficiency, compressor vibration frequency, compressor flow, compressor pressure, mechanical structure, compressor rotation speed and the like.
In some embodiments, because there are some abnormal values or null values, interference values, etc. during the original data acquisition, in order to ensure the accuracy and reliability of the data, in some embodiments, the historical operation data is further subjected to data cleaning preprocessing to filter out abnormal values and noise interference. And performing interpolation processing on missing values existing in the historical fault operation data, wherein the interpolated values can be empirically set values.
S2, determining normal state data of the compressor to be tested under each working condition state based on normal operation data according to preset big data and a machine learning method.
Through the big data and the machine learning method, the range value of the operating parameters of the compressor equipment in normal operation under each working condition, the relevance among the parameters (such as the relevance between the operating parameters and the compressor state), the influence mode of the working condition change on the parameters (the influence of the parameters such as pressure, flow, temperature and the like on the compressor), the characteristics and the like can be judged, and finally the normal state data of the compressor to be detected can be obtained.
S3, constructing an initial neural learning network based on the normal state data, inputting the fault operation data into the initial neural learning network for training, and obtaining a comprehensive early warning model;
by means of a neural network data analysis algorithm, influence factors (related operation parameters) causing faults can be qualitatively and quantitatively analyzed, and the probability of faults caused by the influence factors is determined.
S4, continuously inputting the collected real-time working condition operation data of the compressor to be tested into the comprehensive early warning model, and predicting whether the compressor to be tested is about to fail, and the type, the reason and the time point of the failure.
The method uses historical operation data of the compressor to analyze big data, utilizes machine learning to determine normal operation state data of equipment, utilizes a neural network data analysis algorithm to qualitatively and quantitatively analyze parameters of fault operation, determines weights of all parameters when the fault is generated, and further determines a prediction model. The actual working condition data are input into a prediction model, the faults of the compressor are predicted according to the development of the real-time data, early fault early warning is carried out through the factors such as the running state deviation and parameter change of the compressor, and the abnormality of the compressor is predicted.
Because the compressor has long normal operation time and a relatively rich normal operation data, in some embodiments, the historical operation data collected in step S1 may include all time period operation data records of the same kind of compressor to be tested after the automatic input production.
In one embodiment, the first 24 hours of data at the time of the compressor failure is considered to be failure operation data, and the remainder are considered to be normal operation. In practice, there are other fault operation data divided according to the actual operation time of the compressor, such as 30 minutes before fault, 1 hour before fault, etc., which are not limiting.
In addition, since the compressor is continuously operated, there are some occasional faults, and since the number of occurrences is small, the occasional faults are high, and only a small amount of data exists, at this time, fault characteristic parameters and fault characteristic parameter weights of the occasional faults can be set by an empirical analysis method. If fault operation data when the fault type happens is set through methods such as expert judgment, data analysis of brain storm and accidental faults, possible reasons and influence factors generated by the fault are researched, and a preliminary reason and influence factor relation is established.
Further, step S2 is implemented, and the normal operation data collected in step S1 is analyzed by using a big data method and a machine learning method, so as to determine the normal state data of the compressor to be tested in each working condition state.
Specifically, the normal state data may include: the value range of each normal operation parameter; traversing the association curve of each normal operating parameter; and a change curve of each normal operation parameter according to working conditions.
In one embodiment, the normal operation parameters (normal operation data) include: gas inflow temperature, gas outflow temperature, compressor operating voltage, current, compressor operating efficiency, compressor vibration frequency, compressor flow, compressor pressure.
The traversing association curve of each normal operation parameter is the association curve of each normal operation parameter and other i normal operation parameters under each working condition; i=1, 2, 3..n-1, n is the number of normal operating parameter entries.
For example:
correlation of gas inflow temperature with other 1 normal operating parameter:
a gas inflow temperature-gas outflow temperature curve; a gas inflow temperature-compressor operating voltage curve;
a gas inflow temperature-current curve; a gas inflow temperature-compressor operating efficiency curve;
a gas inflow temperature-compressor vibration frequency curve; a gas inflow temperature-compressor flow curve; the gas flows into the temperature-compressor pressure curve.
Correlation of gas inflow temperature with other 2 normal operating parameters:
a gas inflow temperature-gas outflow temperature-compressor operating voltage curve;
a gas inflow temperature-gas outflow temperature-current curve; a gas inflow temperature-gas outflow temperature-compressor operating efficiency curve; a gas inflow temperature-gas outflow temperature-compressor vibration frequency curve; a gas inflow temperature-gas outflow temperature-compressor flow curve; a gas inflow temperature-gas outflow temperature-compressor pressure curve.
A gas inflow temperature-compressor operating voltage-current curve; a gas inflow temperature-compressor operating voltage-compressor operating efficiency curve;
a gas inflow temperature-compressor operating voltage-compressor vibration frequency curve; a gas inflow temperature-compressor operating voltage-compressor flow curve; a gas inflow temperature-compressor operating voltage-compressor pressure curve;
a gas inflow temperature-current-compressor operating efficiency curve; a gas inflow temperature-current-compressor vibration frequency curve; a gas inflow temperature-current-compressor flow curve; a gas inflow temperature-current-compressor pressure curve;
a gas inflow temperature-compressor operating efficiency-compressor vibration frequency curve; a gas inflow temperature-compressor operating efficiency-compressor flow curve; a gas inflow temperature-compressor operating efficiency-compressor pressure curve; a gas inflow temperature-compressor vibration frequency-compressor flow curve; a gas inflow temperature-compressor vibration frequency-compressor pressure curve; gas inflow temperature-compressor flow-compressor pressure curve, etc.
And so on, respectively acquiring the association curves of each normal operation parameter and other i normal operation parameters, which are not listed here.
Further, step S3 is implemented, and in an embodiment, it is specifically implemented as follows:
s31, constructing an initial neural learning network based on the normal state data;
s32, dividing the fault operation data into different fault types and fault levels according to a pre-constructed fault rule; each fault level corresponds to at least one fault type;
s33, respectively inputting fault operation data of each fault type into an initial neural learning network for training, and obtaining a comprehensive early warning model.
And further, the prediction of possible faults of the compressor is carried out through the comprehensive early warning model.
The fault rules include: fault type, possible fault cause and fault level for each fault type, etc.
The fault types may include: vibration and abnormal noise, thrust bearing failure, radial bearing damage, oil seal ring failure, etc.
The failure causes may include component loosening, rotor imbalance, etc.
Each failure type corresponds to at least one failure cause.
The above-mentioned fault types and fault causes may include all fault types and fault causes accumulated according to experience of the skilled person in actual production life.
Wherein the fault level can be a level evaluated by human experience (comprehensively considering maintenance duration, maintenance cost, production stopping loss and the like): no influence, mild influence, moderate influence, severe influence, etc. The maintenance time, maintenance cost, production stopping loss and other weights can be judged empirically to score, and finally the score grade is obtained.
In some embodiments, S32 is specifically implemented by dividing the data of each fault type according to the possible fault reasons, and in step S33, the operation data corresponding to each fault reason is respectively input into the initial neural learning network for training, so as to obtain the comprehensive early warning model.
For example, in an embodiment, such as abnormal vibration of the compressor, may be related to a change in operating condition data of the compressor, or may be related to a structural change of the compressor itself, where related parameters include a medium flow, a pressure, a rotation speed, an operating voltage, a current, a mechanical structural change of the compressor, etc., by using a neural network data analysis algorithm, weights of each possible influencing parameter, such as the most possible influence of the flow, the weight is 0.8, the pressure is 0.2, the flow is 0.05, and the structural change is 0.05, can be defined according to feature values of vibration actually occurring and a change trend of each parameter during the fault by combining the neural network data analysis algorithm. And further, the prediction of the occurrence reason of the fault is realized.
And the accuracy and the sensitivity of equipment fault prediction are improved by combining the analysis prediction capability of big data and the quick application capability of the model.
The compressor continuously runs, continuous data can be generated, and in order to keep the practicability of the comprehensive early warning model, the built model is continuously corrected and checked through continuous iteration of future running data, so that the accuracy degree and reliability of prediction are further improved.
In practical application, as shown in fig. 3, the method further comprises accessing real-time production data, verifying the modeled type, continuously and completely learning the running state data of normal and abnormal working conditions, realizing optimization iteration of the model through a machine learning algorithm, and continuously improving the accuracy of the model. Specifically, the method can include updating the normal state data after the new normal operation data is subjected to machine learning, updating the initial neural network, and inputting the real-time fault operation data of the compressor into the comprehensive early warning model for training so as to obtain an optimized comprehensive early warning model.
The method can include the fault occurrence state of the compressor as far as possible, effectively solve the fault problem of the compressor, and realize comprehensive early warning.
The invention provides a compressor fault prediction method based on big data and machine learning, which combines the positive working condition and the abnormal working condition through big data analysis and machine learning algorithm, considers the change condition and the mutual association relation of each parameter of normal working condition operation, establishes the association relation between each operation parameter and the working condition, establishes a fault prediction model of compressor equipment, reduces the error judgment probability of faults, improves the accuracy of identifying the root cause of the faults and the contribution degree of each parameter to the faults, realizes the advanced prediction of the faults possibly generated by the compressor equipment, gives out each influencing factor, gives a more definite consideration direction to maintenance staff, and reduces the maintenance time.
The method can make predictions according to real-time data, starts tracking when equipment is separated from a normal operation model, and performs trend analysis and judgment on influence factors, so that early warning is performed in a long enough time before a fault occurs, abnormal conditions are found in the early stage of the fault occurrence, abnormal changes of various parameters are analyzed, and then the possible reasons and types of the fault are judged by combining a fault tree.
According to the method, the fault tree is adopted to conduct grading classification on faults possibly generated, parameter analysis of different faults is achieved, and therefore root causes of the faults are truly given out. And equipment problems are identified at the early stage of failure, the equipment problems are diagnosed, the equipment reliability is improved, the equipment maintenance cost generated by unreasonable preventive maintenance is saved, and the safety, reliability and intellectualization of equipment operation are improved.
The present application also provides a compressor fault prediction system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods described above when executing the computer program.
In some embodiments, a fault pre-alarm is also included for alerting personnel to quickly respond based on the type, cause and time of occurrence of the fault as predicted by the fault prediction module.
In the description of the present invention, it is to be understood that in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present specification, the terms "one embodiment," "some embodiments," "examples," "particular examples," or "some examples," etc., refer to particular features, structures, materials, or characteristics described in connection with the embodiment or example as being included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that alterations, modifications, substitutions and variations may be made in the above embodiments by those skilled in the art within the scope of the invention.
Claims (10)
1. The compressor fault prediction method based on big data and machine learning is characterized by comprising the following steps:
s1, collecting historical operation data of a compressor to be tested;
the historical operation data comprise normal operation data and fault operation data of the compressor under each working condition state;
s2, based on the normal operation data, determining normal state data of the compressor to be tested under each working condition state according to preset big data and a machine learning method;
s3, constructing an initial neural learning network based on the normal state data, inputting the fault operation data into the initial neural learning network for training, and obtaining a comprehensive early warning model;
s4, continuously inputting the collected real-time working condition operation data of the compressor to be tested into the comprehensive early warning model, and predicting whether the compressor to be tested is about to fail, and the type, the reason and the time point of the failure.
2. The method of claim 1, wherein in S2, the normal state data comprises:
the value range of each normal operation parameter;
traversing the association curve of each normal operating parameter;
and a change curve of each normal operation parameter according to working conditions.
3. The method of claim 1 or 2, wherein the operating parameters of the normal operating data include:
gas inflow temperature, gas outflow temperature, compressor operating voltage, current, compressor operating efficiency, compressor vibration frequency, compressor flow, compressor pressure.
4. A method according to claim 3, wherein traversing the correlation for each normal operating parameter comprises:
under each working condition, the correlation curves of each normal operation parameter and other i normal operation parameters;
i=1, 2, 3..n-1, n is the number of normal operating parameter entries.
5. The method of claim 1, wherein S3 specifically comprises:
s31, constructing an initial neural learning network based on the normal state data;
s32, dividing the fault operation data into different fault types and fault levels according to a pre-constructed fault rule; each fault level corresponds to at least one fault type;
s33, respectively inputting fault operation data of each fault type into an initial neural learning network for training, and obtaining a comprehensive early warning model.
6. The method of claim 1, wherein S1 further comprises:
and aiming at the accidental fault type, adopting empirical analysis to set fault operation data when the accidental fault type occurs.
7. The method of claim 1, wherein S3 further comprises:
and inputting real-time fault operation data of the compressor into the comprehensive early warning model for training to obtain an optimized comprehensive early warning model.
8. The method of claim 1, wherein S1 further comprises:
and carrying out data cleaning pretreatment on the historical operation data, and filtering abnormal values and noise interference.
9. The method of claim 1, wherein in S1, further comprising:
and carrying out interpolation processing on missing values in the historical operation data, wherein the interpolated values are empirically set values.
10. A compressor fault prediction system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of the preceding claims 1-9 when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311659532.1A CN117670086A (en) | 2023-12-06 | 2023-12-06 | Compressor fault prediction method and system based on big data and machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311659532.1A CN117670086A (en) | 2023-12-06 | 2023-12-06 | Compressor fault prediction method and system based on big data and machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117670086A true CN117670086A (en) | 2024-03-08 |
Family
ID=90074645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311659532.1A Pending CN117670086A (en) | 2023-12-06 | 2023-12-06 | Compressor fault prediction method and system based on big data and machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117670086A (en) |
-
2023
- 2023-12-06 CN CN202311659532.1A patent/CN117670086A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
| CN110414155B (en) | Fan component temperature abnormity detection and alarm method with single measuring point | |
| CN110208019B (en) | Dynamic threshold early warning method for monitoring state of mobile equipment | |
| CN108896299A (en) | A kind of gearbox fault detection method | |
| CN110836696A (en) | Remote fault prediction method and system suitable for phase modulator system | |
| CN110469496B (en) | Intelligent early warning method and system for water pump | |
| CN114215705B (en) | Wind turbine generator system fault early warning method and system | |
| CN113705924A (en) | Intelligent diagnosis method and system for thermal control equipment | |
| CN112633611A (en) | Submarine cable state maintenance strategy optimization method and system based on big data analysis | |
| CN114139297B (en) | Expert diagnosis system based on machine pump equipment state monitoring and big data analysis | |
| CN115186924A (en) | Equipment health state evaluation method and device based on artificial intelligence | |
| CN111879522B (en) | Steam turbine operation monitoring and fault distinguishing method and system based on time sequence probability | |
| Zhang et al. | Anomaly detection: A robust approach to detection of unanticipated faults | |
| CN113313365A (en) | Degradation early warning method and device for primary air fan | |
| CN111766514B (en) | Data analysis method for equipment detection point | |
| CN113418731A (en) | Online fault diagnosis method for cigarette making machine set | |
| CN117670086A (en) | Compressor fault prediction method and system based on big data and machine learning | |
| CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
| CN113955149B (en) | Health diagnosis method and device for motor system | |
| CN116595657A (en) | Engine quality prediction system | |
| EP3303835B1 (en) | Method for windmill farm monitoring | |
| Zhang | Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data | |
| CN117851877A (en) | Wind power blade fracture early warning method and device based on SCADA data association analysis and readable storage medium | |
| CN117662491A (en) | Main pump fault diagnosis method and system based on principal component and deep learning algorithm | |
| CN115857578A (en) | Self-early warning adjustment system and method for temperature abnormity of condensate pump thrust pad |
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 |