CN111207067A - Air compressor fault diagnosis method based on fuzzy support vector machine - Google Patents
Air compressor fault diagnosis method based on fuzzy support vector machine Download PDFInfo
- Publication number
- CN111207067A CN111207067A CN201910486348.9A CN201910486348A CN111207067A CN 111207067 A CN111207067 A CN 111207067A CN 201910486348 A CN201910486348 A CN 201910486348A CN 111207067 A CN111207067 A CN 111207067A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- air compressor
- vector machine
- support vector
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B51/00—Testing machines, pumps, or pumping installations
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention relates to an air compressor fault diagnosis method based on a fuzzy support vector machine, which comprises the following steps: acquiring specific parameter data of the air compressor during operation; classifying the operation faults of the air compressor, and collecting and recording specific parameter data when the air compressor fails; corresponding to the faults of different types, establishing corresponding support vector machine models, and performing secondary classification through the vector machine so as to judge whether the faults occur or not; building a fuzzy expert system; the support vector machine model and the fuzzy expert system are connected in series to obtain the running parameters of the air compressor, the large-loop fault diagnosis is carried out through the support vector machine model to obtain the running fault type, and then the diagnosis result is input to the fuzzy expert system in combination with the running parameters to realize the fault diagnosis of the air compressor. The invention has the advantages that: the support vector machine is combined with the fuzzy expert system, so that a rule base of the fuzzy expert system is simplified, and the method has the advantages of simplicity, high efficiency, stability and accuracy.
Description
Technical Field
The invention belongs to the technical field of information and control, relates to an automation technology, and particularly relates to an air compressor fault diagnosis method based on a fuzzy support vector machine.
Background
Modern equipment puts higher and higher requirements on safety and reliability, and fault diagnosis technology is very important when faults of large-scale industrial equipment cause great accidents and harm once the faults occur. The fault diagnosis can bring great economic effect and social effect while ensuring the safety, reliability and operation of equipment, can accurately and efficiently guide industrial field production in time, and helps to discover and solve faults as early as possible. The air compressor is used as an important device of a complete air separation device, the working performance of the air compressor directly influences and restricts the yield and quality of air separation products, and currently, for the air compressor, the DCS system is mainly used for monitoring and recording parameters of the operation process of the air compressor and processing and monitoring vibration signals of the air compressor, so that the integral operation fault diagnosis of the air compressor system is lacked.
Disclosure of Invention
The invention mainly solves the problem that the prior art cannot detect the integral operation fault of the air compressor system, and provides the air compressor fault diagnosis method based on the fuzzy support vector machine, which has the advantages of simplicity, high efficiency, stability and accuracy.
The technical scheme adopted by the invention for solving the technical problem is that the air compressor fault diagnosis method based on the fuzzy support vector machine comprises the following steps:
s1: acquiring specific parameter data of the air compressor during operation;
s2: classifying the operation faults of the air compressor, and collecting and recording specific parameter data when the air compressor fails;
s3: corresponding to the faults of different types, establishing corresponding support vector machine models, and performing secondary classification through the vector machine so as to judge whether the faults occur or not;
s4: building a fuzzy expert system;
s5: the support vector machine model and the fuzzy expert system are connected in series to obtain the running parameters of the air compressor, the large-loop fault diagnosis is carried out through the support vector machine model to obtain the running fault type, and then the diagnosis result is input to the fuzzy expert system in combination with the running parameters to realize the fault diagnosis of the air compressor.
The method carries out summary classification on common faults in the operation process of the air compressor, establishes a corresponding support vector machine model for training each fault type according to the fault data, and establishes a fuzzy expert system for diagnosing the fault reason. The method combines the support vector machine and the fuzzy expert system, simplifies a rule base of the fuzzy expert system, and has the advantages of simplicity, high efficiency, stability and accuracy.
As a preferable scheme of the above scheme, the specific parameter data includes primary shaft vibration, secondary shaft vibration, tertiary shaft vibration, lubrication oil temperature, lubrication oil pressure, main motor bearing temperature, main motor current, exhaust pressure, exhaust flow, ambient temperature, and air inlet precooler temperature of the air compressor.
As a preferable mode of the above, in step S2, the operation failure of the air compressor is divided into a mechanical failure, an oil path failure, and an air path failure.
As a preferable scheme of the above scheme, the kernel function of the support vector machine module adopts an RBF gaussian function
Where i is 1,2,. n, j is 1,2,. n, xi＝[x1,x2,…,xn]E X represents a number of feature spaces in which each sample of input data contains, Xj＝[x1,x2,…,xn]E X denotes a number of feature spaces that each sample of input data contains, σ being the width parameter of the function, the radial extent of action of the control function.
As a preferable scheme of the above scheme, the penalty parameter c of the support vector machine and the parameter g of the kernel function are obtained by grid cross validation.
As a preferable scheme of the above scheme, the constructing of the fuzzy expert system comprises the following steps:
s61: setting corresponding fuzzy sets and membership functions for specific parameter data of the air compressor during operation and fault categories obtained by the operation of the support vector machine to obtain fuzzy vectors of fault symptoms
X＝(μx1,μx2,…,μxm)
μxi(i ═ 1,2, …, m) is the degree of membership of the object with the symptom xi, xi denoting the possible occurrence of the symptom;
s62: setting corresponding fuzzy sets and membership functions for the operation faults of the air compressor to obtain fuzzy vectors of fault causes
Y＝(μy1,μy2,…,μyn)
μyi(i ═ 1,2, …, n) is the degree of membership of the object with the fault yi, which represents the cause of the fault that may occur;
s63: according to the relation between the fuzzy vector of the fault sign and the fuzzy vector of the fault reason
Y＝X°R′
A fuzzy relation matrix R' is obtained and "°" represents the fuzzy operator.
As a preferable scheme of the scheme, the fuzzy operator adopts a Min-Max fuzzy operator.
As a preferable mode of the above, the fuzzy relation matrix R' is obtained by:
s81: establishing a fuzzy rule base;
s82: using Mamdani type fuzzy inference
In the formula RcFor the operation rule, A is the input fuzzy subset, B is the output fuzzy subset, x and y correspond to the variables A and B, respectively, muA(x) And muB(y) is the corresponding membership function;
s83: relation of combination
Y＝X°R′
To obtain
S84: separately solving the matrix RiThen obtaining a fuzzy relation matrix R'
R′＝R1∪R2∪…∪Ri
Where i is 1,2, …, k, k is the number of rules in the fuzzy rule base.
As a preferable scheme of the above scheme, the fuzzy result set Y is obtained by the fuzzy expert system in the step S51Fuzzy result set Y1Is subjected to clarification to obtain Y1′,Y1' with a set threshold value y1By comparison, when Y1' greater than threshold y1And judging that the fault occurs in time, otherwise, not occurring.
As a preferable solution of the above solution, the fuzzy result set Y1The method is clarified by an area gravity center method.
Support vector machine
Drawings
FIG. 1 is a schematic flow chart of the present invention.
FIG. 2 is a schematic flow chart of constructing a fuzzy expert system according to the present invention.
FIG. 3 is a table of data selected in example 2.
Fig. 4 is a graph showing the results of mechanical failure diagnosis on the first set of data in embodiment 2.
Fig. 5 is a diagram showing the results of oil passage failure diagnosis on the first group of data in embodiment 2.
Fig. 6 is a diagram illustrating a result of gas path fault diagnosis on the first set of data in embodiment 2.
FIG. 7 is a graph of fuzzy expert system diagnostic results for the first set of data in example 2.
FIG. 8 is a graph of the fuzzy expert system diagnostic results for the second set of data in example 2.
Detailed Description
The technical solution of the present invention is further described below by way of examples with reference to the accompanying drawings.
Example 1:
a method for diagnosing the fault of an air compressor based on a fuzzy support vector machine is shown in figure 1 and comprises the following steps:
s1: acquiring specific parameter data of the air compressor during operation, wherein the specific parameter data comprises primary shaft vibration, secondary shaft vibration, tertiary shaft vibration, lubricating oil temperature, lubricating oil pressure, main motor bearing temperature, main motor current, exhaust pressure, exhaust flow, ambient temperature and air inlet precooler temperature of the air compressor, and the parameters can be acquired from an air compressor supplier and acquired in the actual production process;
s2: classifying the operation faults of the air compressor, dividing the operation faults into mechanical faults, oil circuit faults and air circuit faults, and collecting and recording specific parameter data when the air compressor fails;
s3: corresponding to different types of faults, establishing corresponding support vector machine models, and when establishing the support vector machine models, adopting RBF Gaussian function as kernel function of the support vector machine module
Where i is 1,2,. n, j is 1,2,. n, xi＝[x1,x2,…,xn]E X represents a number of feature spaces in which each sample of input data contains, Xj＝[x1,x2,…,xn]E X represents a plurality of characteristic quantity spaces contained in each sample of input data, sigma is a width parameter of the function, the radial action range of the function is controlled, binary classification is carried out through a vector machine, wherein the binary classification result of mechanical faults is 0 or 1, the binary classification result of oil circuit faults is 0 or 2, the result of gas circuit faults is 0 or 3, the binary classification result is 0 and indicates that no faults occur, the binary classification result is not 0 and indicates that faults occur, and the penalty parameter c of the support vector machine and the parameter g of the kernel function pass through grid cross checkObtaining the certificate;
s4: constructing a fuzzy expert system, as shown in fig. 2, specifically comprising the following steps:
s41: setting corresponding fuzzy sets and membership functions for specific parameter data of the air compressor during operation and fault categories obtained by the operation of the support vector machine to obtain fuzzy vectors of fault symptoms
X＝(μx1,μx2,…,μxm)
μxi(i ═ 1,2, …, m) is the membership degree of the object with the symptom xi, xi represents the possible symptom, and the value of m in the embodiment is 12;
s42: setting corresponding fuzzy sets and membership functions for the operation faults of the air compressor to obtain fuzzy vectors of fault causes
Y＝(μy1,μy2,…,μyn)
μyi(i ═ 1,2, …, n) is subject to have membership degree of fault yi, yi represents the fault reason that may appear, the value of n in this embodiment is 10, 10 kinds of fault reasons representing the air compressor include shaft vibration too big of first, second and third level, shaft vibration too big caused by too high oil temperature, bearing temperature too high caused by too low oil pressure, exhaust flow reduction caused by grid fluctuation, exhaust flow too low caused by too high suction temperature, exhaust flow too low caused by intercooler fault and surge;
s43: according to the relation between the fuzzy vector of the fault sign and the fuzzy vector of the fault reason
Y＝X°R′
Obtaining a fuzzy relation matrix R ', ' degree ' represents a fuzzy operator, and the fuzzy operator adopts a ' Min-Max ' fuzzy operator in the embodiment
Where "V" is the sign of a sum, which means taking the maximum or maximum value for all y values,
is the sign of the product of two terms, "μ" denotes the corresponding degree of membership;
the fuzzy relation matrix R' is obtained by the following steps:
s431: establishing a fuzzy rule base;
s432: using Mamdani type fuzzy inference
In the formula RcFor the operation rule, A is the input fuzzy subset, B is the output fuzzy subset, x and y correspond to the variables A and B, respectively, muA(x) And muB(y) is the corresponding membership function;
s433: relation of combination
Y＝X°R′
To obtain
S84: separately solving the matrix RiThen obtaining a fuzzy relation matrix R'
R′＝R1∪R2∪…∪Ri
Where i is 1,2, …, k, k is the number of rules in the fuzzy rule base.
S5: the support vector machine model and the fuzzy expert system are connected in series to obtain the operating parameters of the air compressor, the large-loop fault diagnosis is carried out through the support vector machine model to obtain the operating fault type, the diagnosis result is input to the fuzzy expert system in combination with the operating parameters to obtain a fuzzy result set Y1Using area gravity center method to gather fuzzy result set Y1Is subjected to clarification to obtain Y1′，Y1' with a set threshold value y1By comparison, when Y1' greater than threshold y1And judging that the fault occurs in time, otherwise, not occurring. The area barycenter method formula is as follows
Wherein z is0For the clearness, a and b are the lower and upper limits, μ, of the discourse of the clearnessC′(z) is a membership function for z.
Example 2:
in this embodiment, the method in embodiment 1 is verified by using the air compressor fault data in the actual production process, and the data of two groups of air compressors during fault operation are respectively taken: the first group is the bearing temperature caused by the oil temperature being too high, and the second group is the exhaust flow caused by the air suction temperature being too high, and the data is shown in figure 3.
And performing fault diagnosis by using the first group of data, and firstly, assuming that the first group of data has no fault, namely setting the labels of mechanical fault, oil circuit fault and gas circuit fault to be 0, wherein the label 0 indicates normal, and the label non-0 indicates fault. Respectively bringing parameter data and labels into corresponding constructed and tested support vector machine models to be used as test samples to detect large loop faults, wherein the mechanical fault diagnosis result is shown in figure 4 and indicates that no mechanical fault occurs, the oil path fault diagnosis result is shown in figure 5, the two classification results are 2 and indicate that oil path faults occur, the gas path fault diagnosis result is shown in figure 6 and indicates that no gas path faults occur, the large loop fault detection result 2 and 11 operation parameters of the air compressor are input into a fuzzy expert system to obtain a diagnosis result, which is shown in figure 7, the output of y5 is 0.85, the rest outputs are 0.5, and y1 to y10 represent fault reasons and sequentially correspond to the conditions that the vibration of a primary shaft is too large, the vibration of a secondary shaft is too large, the vibration of a tertiary shaft is too large, the vibration of an oil temperature is too high, and the temperature of a bearing is too high due to the oil temperature, The bearing temperature is too high due to too low oil pressure, the exhaust flow is reduced due to power grid fluctuation, the exhaust flow is too low due to too high air suction temperature, the exhaust flow is too low and surging are caused by intercooler faults, y5 represents that the bearing temperature is too high due to too high oil temperature, and the output is larger than a threshold value of 0.5, so that the fault reason of the air compressor of the group of data is judged to be too high due to too high oil temperature, and is the same as the fault reason of the actual air compressor.
Similarly, the second set of data is verified, and as a result, as shown in fig. 8, the output of y8 is 0.85 which is greater than the threshold value of 0.5, and y8 represents that the exhaust flow is too low due to too high intake temperature, and the detection result is the same as the actual situation.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (10)
1. An air compressor fault diagnosis method based on a fuzzy support vector machine is characterized by comprising the following steps: the method comprises the following steps:
s1: acquiring specific parameter data of the air compressor during operation;
s2: classifying the operation faults of the air compressor, and collecting and recording specific parameter data when the air compressor fails;
s3: corresponding to the faults of different types, establishing corresponding support vector machine models, and performing secondary classification through the vector machine so as to judge whether the faults occur or not;
s4: building a fuzzy expert system;
s5: the support vector machine model and the fuzzy expert system are connected in series to obtain the running parameters of the air compressor, the large-loop fault diagnosis is carried out through the support vector machine model to obtain the running fault type, and then the diagnosis result is input to the fuzzy expert system in combination with the running parameters to realize the fault diagnosis of the air compressor.
2. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 1, wherein: the specific parameter data comprises primary shaft vibration, secondary shaft vibration, tertiary shaft vibration, lubricating oil temperature, lubricating oil pressure, main motor bearing temperature, main motor current, exhaust pressure, exhaust flow, ambient temperature and air inlet precooler temperature of the air compressor.
3. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 1, wherein: in the step S2, the operation failure of the air compressor is classified into a mechanical failure, an oil path failure, and an air path failure.
4. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 1, wherein: the kernel function of the support vector machine module adopts RBF Gaussian function
Where i is 1,2,. n, j is 1,2,. n, xi＝[x1,x2,…,xn]E X represents a number of feature spaces in which each sample of input data contains, Xj＝[x1,x2,…,xn]E X denotes a number of feature spaces that each sample of input data contains, σ being the width parameter of the function, the radial extent of action of the control function.
5. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 1 or 4, wherein: and the penalty parameter c of the support vector machine and the parameter g of the kernel function are obtained through grid cross validation.
6. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 1, wherein: the construction of the fuzzy expert system comprises the following steps:
s61: setting corresponding fuzzy sets and membership functions for specific parameter data of the air compressor during operation and fault categories obtained by the operation of the support vector machine to obtain fuzzy vectors of fault symptoms
X＝(μx1,μx2,…,μxm)
μxi(i ═ 1,2, …, m) is the degree of membership of the object with the symptom xi, xi denoting the possible occurrence of the symptom;
s62: setting corresponding fuzzy sets and membership functions for the operation faults of the air compressor to obtain fuzzy vectors of fault causes
Y＝(μy1,μy2,…,μyn)
μyi(i ═ 1,2, …, n) is the degree of membership of the object with the fault yi, which represents the cause of the fault that may occur;
s63: according to the relation between the fuzzy vector of the fault sign and the fuzzy vector of the fault reason
A fuzzy relation matrix R' is obtained,
representing a blurring operator.
7. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 6, wherein: the fuzzy operator adopts a Min-Max fuzzy operator.
8. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 6, wherein: the fuzzy relation matrix R' is obtained by the following steps:
s81: establishing a fuzzy rule base;
s82: using Mamdani type fuzzy inference
In the formula RcFor the operation rule, A is the input fuzzy subset, B is the output fuzzy subset, x and y correspond to the variables A and B, respectively, muA(x) And muB(y) is the corresponding membership function;
s83: relation of combination
To obtain
S84: separately solving the matrix RiThen obtaining a fuzzy relation matrix R'
R′＝R1∪R2∪…∪Ri
Where i is 1,2, …, k, k is the number of rules in the fuzzy rule base.
9. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 1, wherein: obtaining a fuzzy result set Y through a fuzzy expert system in the step S51Fuzzy result set Y1Is subjected to clarification to obtain Y1′,Y1' with a set threshold value y1By comparison, when Y1' greater than threshold y1And judging that the fault occurs in time, otherwise, not occurring.
10. The air compressor fault diagnosis method based on the fuzzy support vector machine as claimed in claim 9, wherein: the fuzzy result set Y1The method is clarified by an area gravity center method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910486348.9A CN111207067A (en) | 2019-06-05 | 2019-06-05 | Air compressor fault diagnosis method based on fuzzy support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910486348.9A CN111207067A (en) | 2019-06-05 | 2019-06-05 | Air compressor fault diagnosis method based on fuzzy support vector machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111207067A true CN111207067A (en) | 2020-05-29 |
Family
ID=70783258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910486348.9A Pending CN111207067A (en) | 2019-06-05 | 2019-06-05 | Air compressor fault diagnosis method based on fuzzy support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111207067A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112317109A (en) * | 2020-09-27 | 2021-02-05 | 鞍钢集团矿业有限公司 | Cone crusher fault pre-judging method |
| CN113279994A (en) * | 2021-04-14 | 2021-08-20 | 杭州电子科技大学 | Support vector machine and two-type fuzzy based fault diagnosis method for centrifugal nitrogen compressor |
| CN114165474A (en) * | 2022-02-11 | 2022-03-11 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus and computer storage medium for detecting a fault condition of an air compressor |
| CN114323691A (en) * | 2021-12-28 | 2022-04-12 | 中国科学院工程热物理研究所 | Gas circuit fault diagnosis device and method for compressed air energy storage system |
| CN114326561A (en) * | 2021-11-23 | 2022-04-12 | 国网浙江省电力有限公司嘉兴供电公司 | Control method of air compressor |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1015765B1 (en) * | 1997-09-16 | 2003-08-20 | Flow International Corporation | Apparatus and method for diagnosing the status of specific components in high-pressure fluid pumps |
| CN105065277A (en) * | 2009-05-18 | 2015-11-18 | 艾默生环境优化技术有限公司 | Compressor and diagnostic system thereof |
-
2019
- 2019-06-05 CN CN201910486348.9A patent/CN111207067A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1015765B1 (en) * | 1997-09-16 | 2003-08-20 | Flow International Corporation | Apparatus and method for diagnosing the status of specific components in high-pressure fluid pumps |
| CN105065277A (en) * | 2009-05-18 | 2015-11-18 | 艾默生环境优化技术有限公司 | Compressor and diagnostic system thereof |
Non-Patent Citations (4)
| Title |
|---|
| 张万君 等: ""基于模糊数学的炮射导弹制导装置故障诊断"", 《装甲兵工程学院学报》 * |
| 杜文礼 等: ""基于模糊诊断专家系统的空压机故障诊断方法"", 《科技风》 * |
| 王禾军: ""基于支持向量机与模糊推理的智能信息融合方法研究"", 《中国博士学位论文全文数据库信息科技辑》 * |
| 董海鹰: "《智能控制理论及应用》", 30 September 2016, 中国铁道出版社 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112317109A (en) * | 2020-09-27 | 2021-02-05 | 鞍钢集团矿业有限公司 | Cone crusher fault pre-judging method |
| CN112317109B (en) * | 2020-09-27 | 2022-02-18 | 鞍钢集团矿业有限公司 | Cone crusher fault pre-judging method |
| CN113279994A (en) * | 2021-04-14 | 2021-08-20 | 杭州电子科技大学 | Support vector machine and two-type fuzzy based fault diagnosis method for centrifugal nitrogen compressor |
| CN114326561A (en) * | 2021-11-23 | 2022-04-12 | 国网浙江省电力有限公司嘉兴供电公司 | Control method of air compressor |
| CN114323691A (en) * | 2021-12-28 | 2022-04-12 | 中国科学院工程热物理研究所 | Gas circuit fault diagnosis device and method for compressed air energy storage system |
| CN114323691B (en) * | 2021-12-28 | 2023-06-23 | 中国科学院工程热物理研究所 | Air path fault diagnosis device and method for compressed air energy storage system |
| CN114165474A (en) * | 2022-02-11 | 2022-03-11 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus and computer storage medium for detecting a fault condition of an air compressor |
| CN114165474B (en) * | 2022-02-11 | 2022-05-06 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus and computer storage medium for detecting a fault condition of an air compressor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111207067A (en) | Air compressor fault diagnosis method based on fuzzy support vector machine | |
| CN108664010A (en) | Generating set fault data prediction technique, device and computer equipment | |
| CN109753998A (en) | The fault detection method and system, computer program of network are generated based on confrontation type | |
| CN109186973A (en) | A kind of mechanical failure diagnostic method of unsupervised deep learning network | |
| CN110110768A (en) | Fault Diagnosis of Roller Bearings based on Concurrent Feature study and multi-categorizer | |
| CN110376522A (en) | A kind of Method of Motor Fault Diagnosis of the deep learning network of data fusion | |
| CN104267668A (en) | Bayes-method-based spaceflight valve part fault diagnosis method in machining process | |
| CN109626161A (en) | A kind of Elevator Fault Diagnosis method | |
| CN112747924A (en) | Bearing life prediction method based on attention mechanism and residual error neural network | |
| CN112860183A (en) | Multisource distillation-migration mechanical fault intelligent diagnosis method based on high-order moment matching | |
| CN116720048A (en) | Power station auxiliary machine fault diagnosis method and system based on machine learning model | |
| CN116257747A (en) | Early abnormality detection method for rotor system of fusion kurtosis and convolution self-encoder | |
| CN112949874B (en) | Power distribution terminal defect characteristic self-diagnosis method and system | |
| CN114416423A (en) | Root cause positioning method and system based on machine learning | |
| CN114418146A (en) | Electromechanical equipment fault diagnosis method, system and terminal based on rule engine | |
| CN112748331A (en) | Circuit breaker mechanical fault identification method and device based on DS evidence fusion | |
| CN113469252A (en) | Extra-high voltage converter valve operation state evaluation method considering unbalanced samples | |
| Huang et al. | Fuel cell engine fault diagnosis expert system based on decision tree | |
| CN115791174B (en) | Rolling bearing abnormality diagnosis method, system, electronic equipment and storage medium | |
| CN113093695A (en) | Data-driven SDN controller fault diagnosis system | |
| CN111783941A (en) | Mechanical equipment diagnosis and classification method based on probability confidence degree convolutional neural network | |
| CN116955071A (en) | Fault classification method, device, equipment and storage medium | |
| CN116629409A (en) | SOFC system fault probability prediction method based on naive Bayes algorithm | |
| CN110490218A (en) | A kind of rolling bearing fault self-learning method based on two-stage DBN | |
| CN113279994B (en) | Support vector machine and two-type fuzzy based fault diagnosis method for centrifugal nitrogen compressor |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200529 |
|
| RJ01 | Rejection of invention patent application after publication |