CN117216521A - Intelligent diagnosis method for fault of aircraft based on neural network - Google Patents
Intelligent diagnosis method for fault of aircraft based on neural network Download PDFInfo
- Publication number
- CN117216521A CN117216521A CN202311191819.6A CN202311191819A CN117216521A CN 117216521 A CN117216521 A CN 117216521A CN 202311191819 A CN202311191819 A CN 202311191819A CN 117216521 A CN117216521 A CN 117216521A
- Authority
- CN
- China
- Prior art keywords
- convolution layer
- input end
- layer
- axis acceleration
- classification
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 22
- 238000003745 diagnosis Methods 0.000 title claims abstract description 17
- 230000001133 acceleration Effects 0.000 claims abstract description 97
- 239000011159 matrix material Substances 0.000 claims abstract description 34
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 12
- 230000014509 gene expression Effects 0.000 claims description 9
- 238000011176 pooling Methods 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 6
- 238000002405 diagnostic procedure Methods 0.000 claims description 2
- 230000017105 transposition Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides an intelligent diagnosis method for an aircraft fault based on a neural network, which is characterized in that after x-axis acceleration, y-axis acceleration and z-axis acceleration of an aircraft are acquired, an autocorrelation matrix of the x-axis, the y-axis and the z-axis is respectively constructed, data characteristics are enhanced, the convolutional neural network is convenient to extract, slight anomalies of the data are easier to identify, each convolutional neural network processes an autocorrelation matrix to obtain acceleration characteristics of each axis, and then a classifier is adopted to process the acceleration characteristics of 3 axes to obtain the type of the aircraft fault.
Description
Technical Field
The invention relates to the technical field of aircraft fault diagnosis, in particular to an intelligent aircraft fault diagnosis method based on a neural network.
Background
With the rapid development of aviation industry, various faults may occur in the running process of the aircraft, and the faults may cause the performance of the aircraft to be reduced, or even the safety accidents to occur. In the running process of the aircraft, the x-axis acceleration, the y-axis acceleration and the z-axis acceleration of the aircraft determine the attitude of the aircraft, and the flying attitude determines the direction of the aircraft, so that the flying height is influenced and the flying direction is also influenced. However, in the existing fault diagnosis method of the aircraft, each real-time sensing data is monitored by a sensor, each real-time sensing data is compared with a threshold value, when the threshold value is exceeded, the fault of the corresponding sensor monitoring point is determined, but in the mode, the fault of the aircraft cannot be pre-determined in advance, and after the threshold value is exceeded, the aircraft is abnormal.
Disclosure of Invention
The invention aims to provide an intelligent diagnosis method for an aircraft fault based on a neural network, which solves the problem that the existing diagnosis method for the aircraft fault cannot predict the aircraft fault in advance.
The embodiment of the invention is realized by the following technical scheme: an intelligent diagnosis method for fault of an aircraft based on a neural network comprises the following steps:
s1, acquiring x-axis acceleration, y-axis acceleration and z-axis acceleration of an aircraft through a gyroscope;
s2, constructing an autocorrelation matrix of the x-axis acceleration, constructing an autocorrelation matrix of the y-axis acceleration, and constructing an autocorrelation matrix of the z-axis acceleration;
s3, processing each autocorrelation matrix through each convolutional neural network to obtain acceleration characteristics;
s4, classifying the acceleration characteristics by using a classifier to obtain the fault type of the aircraft.
Further, the step S2 is a step of constructing an autocorrelation matrix of the x-axis accelerationThe formula is: x is X 1 ＝(A x ) T A x The formula for constructing the autocorrelation matrix of the y-axis acceleration is as follows: x is X 2 ＝(A y ) T A y The formula for constructing the autocorrelation matrix of the z-axis acceleration is as follows: x is X 3 ＝(A z ) T A z Wherein X is 1 Is an autocorrelation matrix of X-axis acceleration, X 2 For the autocorrelation matrix of the y-axis acceleration, X 3 An autocorrelation matrix for the z-axis acceleration, A x Is a one-dimensional x-axis acceleration vector A y Is a one-dimensional y-axis acceleration vector A z The one-dimensional z-axis acceleration vector is represented by T, which is a transpose operation.
Further, the convolutional neural network in S3 includes: a first convolution layer, a second convolution layer, a third convolution layer, a fourth convolution layer, a fifth convolution layer, a sixth convolution layer, a attention block, and an adder A1;
the input end of the first convolution layer is used as the input end of the convolution neural network, and the output end of the first convolution layer is connected with the input end of the second convolution layer; the output end of the second convolution layer is respectively connected with the input end of the third convolution layer and the input end of the fifth convolution layer; the input end of the attention block is connected with the output end of the third convolution layer, and the output end of the attention block is connected with the input end of the fourth convolution layer; the first input end of the adder A1 is connected with the output end of the fourth convolution layer, the second input end of the adder A1 is connected with the output end of the fifth convolution layer, and the output end of the adder A1 is connected with the input end of the sixth convolution layer; the output end of the sixth convolution layer is used as the output end of the convolution neural network.
Further, the attention block includes: a seventh convolution layer, an eighth convolution layer, a ninth convolution layer, a global pooling layer, a full connection layer, a Sigmoid layer, a multiplier and an adder A2;
the input end of the seventh convolution layer is used as the input end of the attention block, and the output end of the seventh convolution layer is respectively connected with the input end of the eighth convolution layer, the first input end of the multiplier and the input end of the global pooling layer; the input end of the full-connection layer is connected with the output end of the global pooling layer, and the output end of the full-connection layer is connected with the input end of the Sigmoid layer; the second input end of the multiplier is connected with the output end of the Sigmoid layer, and the output end of the multiplier is connected with the first input end of the adder A2; the second input of the adder A2 is connected to the output of the ninth convolution layer, and its output is the output of the attention block.
Further, the expression of the Sigmoid layer is:wherein x is i For the ith input of the Sigmoid layer, sigmoid is an S-type activation function,/>Is the ith output of the Sigmoid layer.
Further, the classifier in S4 includes: the device comprises a first classifying unit, a second classifying unit, a third classifying unit and a classified output unit;
the first classification unit is used for processing acceleration characteristics corresponding to the x-axis acceleration to obtain a first classification value; the second classification unit is used for processing acceleration characteristics corresponding to the y-axis acceleration to obtain a second classification value; the third classification unit is used for processing acceleration characteristics corresponding to the z-axis acceleration to obtain a third classification value; the classification output unit is used for obtaining the fault type of the aircraft according to the first classification value, the second classification value and the third classification value.
Further, the expressions of the first classification unit, the second classification unit and the third classification unit are:
wherein y is a classification value output by the first classification unit, the second classification unit or the third classification unit, exp is an exponential function based on a natural constant, h j The j-th acceleration characteristic, w, of the first classification unit, the second classification unit or the third classification unit j Weight of the j-th acceleration feature, b i For the bias of the jth acceleration feature, N is the number of acceleration features and ln is a logarithmic function.
Further, the expression of the classification output unit is:
Y＝sigmoid(W 1 y 1 +W 2 y 2 +W 3 y 3 )
wherein Y is the output of the classified output unit, sigmoid is the S-type activation function, Y 1 For the first classification value, y 2 For a second classification value, y 3 For the third classification value, W 1 For the first classification value y 1 Weight of the second classification value y 2 Weight, W of (2) 3 For the third classification value y 3 Is a weight of (2).
The technical scheme of the embodiment of the invention has at least the following advantages and beneficial effects: according to the method, after the x-axis acceleration, the y-axis acceleration and the z-axis acceleration of the aircraft are acquired, the autocorrelation matrixes of the x-axis, the y-axis and the z-axis are respectively constructed, the data characteristics are enhanced, the convolutional neural network is convenient to extract, slight anomalies of the data are easier to identify, each convolutional neural network processes one autocorrelation matrix to obtain the acceleration characteristics of each axis, and then a classifier is adopted to process the acceleration characteristics of 3 axes to obtain the fault type of the aircraft.
Drawings
FIG. 1 is a flow chart of an intelligent diagnostic method for aircraft failure based on a neural network;
FIG. 2 is a schematic diagram of a convolutional neural network;
fig. 3 is a schematic structural view of the attention block.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
As shown in fig. 1, an intelligent diagnosis method for an aircraft fault based on a neural network comprises the following steps:
s1, acquiring x-axis acceleration, y-axis acceleration and z-axis acceleration of an aircraft through a gyroscope;
s2, constructing an autocorrelation matrix of the x-axis acceleration, constructing an autocorrelation matrix of the y-axis acceleration, and constructing an autocorrelation matrix of the z-axis acceleration;
s3, processing each autocorrelation matrix through each convolutional neural network to obtain acceleration characteristics;
s4, classifying the acceleration characteristics by using a classifier to obtain the fault type of the aircraft.
The formula for constructing the autocorrelation matrix of the x-axis acceleration in the step S2 is as follows: x is X 1 ＝(A x ) T A x The formula for constructing the autocorrelation matrix of the y-axis acceleration is as follows: x is X 2 ＝(A y ) T A y The formula for constructing the autocorrelation matrix of the z-axis acceleration is as follows: x is X 3 ＝(A z ) T A z Wherein X is 1 Is an autocorrelation matrix of X-axis acceleration, X 2 For the autocorrelation matrix of the y-axis acceleration, X 3 An autocorrelation matrix for the z-axis acceleration, A x Is a one-dimensional x-axis acceleration vector A y Is a one-dimensional y-axis acceleration vector A z The one-dimensional z-axis acceleration vector is represented by T, which is a transpose operation.
As shown in fig. 2, the convolutional neural network in S3 includes: a first convolution layer, a second convolution layer, a third convolution layer, a fourth convolution layer, a fifth convolution layer, a sixth convolution layer, a attention block, and an adder A1;
the input end of the first convolution layer is used as the input end of the convolution neural network, and the output end of the first convolution layer is connected with the input end of the second convolution layer; the output end of the second convolution layer is respectively connected with the input end of the third convolution layer and the input end of the fifth convolution layer; the input end of the attention block is connected with the output end of the third convolution layer, and the output end of the attention block is connected with the input end of the fourth convolution layer; the first input end of the adder A1 is connected with the output end of the fourth convolution layer, the second input end of the adder A1 is connected with the output end of the fifth convolution layer, and the output end of the adder A1 is connected with the input end of the sixth convolution layer; the output end of the sixth convolution layer is used as the output end of the convolution neural network.
As shown in fig. 3, the attention block includes: a seventh convolution layer, an eighth convolution layer, a ninth convolution layer, a global pooling layer, a full connection layer, a Sigmoid layer, a multiplier and an adder A2;
the input end of the seventh convolution layer is used as the input end of the attention block, and the output end of the seventh convolution layer is respectively connected with the input end of the eighth convolution layer, the first input end of the multiplier and the input end of the global pooling layer; the input end of the full-connection layer is connected with the output end of the global pooling layer, and the output end of the full-connection layer is connected with the input end of the Sigmoid layer; the second input end of the multiplier is connected with the output end of the Sigmoid layer, and the output end of the multiplier is connected with the first input end of the adder A2; the second input of the adder A2 is connected to the output of the ninth convolution layer, and its output is the output of the attention block.
The expression of the Sigmoid layer is:wherein x is i For the ith input of the Sigmoid layer, sigmoid is an S-type activation function,/>Is the ith output of the Sigmoid layer.
The classifier in S4 includes: the device comprises a first classifying unit, a second classifying unit, a third classifying unit and a classified output unit;
the first classification unit is used for processing acceleration characteristics corresponding to the x-axis acceleration to obtain a first classification value; the second classification unit is used for processing acceleration characteristics corresponding to the y-axis acceleration to obtain a second classification value; the third classification unit is used for processing acceleration characteristics corresponding to the z-axis acceleration to obtain a third classification value; the classification output unit is used for obtaining the fault type of the aircraft according to the first classification value, the second classification value and the third classification value.
The expressions of the first classifying unit, the second classifying unit and the third classifying unit are as follows:
wherein y is a classification value output by the first classification unit, the second classification unit or the third classification unit, exp is an exponential function based on a natural constant, h j The j-th acceleration characteristic, w, of the first classification unit, the second classification unit or the third classification unit j Weight of the j-th acceleration feature, b j For the bias of the jth acceleration feature, N is the number of acceleration features and ln is a logarithmic function.
The expression of the classification output unit is as follows:
Y＝sigmoid(W 1 y 1 +W 2 y 2 +W 3 y 3 )
wherein Y is the output of the classified output unit, sigmoid is the S-type activation function, Y 1 For the first classification value, y 2 For a second classification value, y 3 For the third classification value, W 1 For the first classification value y 1 Weight of the second classification value y 2 Weight, W of (2) 3 For the third classification value y 3 Is a weight of (2).
In the present invention, the types of faults of the aircraft are classified according to the magnitude of the output Y of the classification output unit.
The technical scheme of the embodiment of the invention has at least the following advantages and beneficial effects: according to the method, after the x-axis acceleration, the y-axis acceleration and the z-axis acceleration of the aircraft are acquired, the autocorrelation matrixes of the x-axis, the y-axis and the z-axis are respectively constructed, the data characteristics are enhanced, the convolutional neural network is convenient to extract, slight anomalies of the data are easier to identify, each convolutional neural network processes one autocorrelation matrix to obtain the acceleration characteristics of each axis, and then a classifier is adopted to process the acceleration characteristics of 3 axes to obtain the fault type of the aircraft.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The intelligent diagnosis method for the fault of the aircraft based on the neural network is characterized by comprising the following steps of:
s1, acquiring x-axis acceleration, y-axis acceleration and z-axis acceleration of an aircraft through a gyroscope;
s2, constructing an autocorrelation matrix of the x-axis acceleration, constructing an autocorrelation matrix of the y-axis acceleration, and constructing an autocorrelation matrix of the z-axis acceleration;
s3, processing each autocorrelation matrix through each convolutional neural network to obtain acceleration characteristics;
s4, classifying the acceleration characteristics by using a classifier to obtain the fault type of the aircraft.
2. The intelligent diagnosis method for the fault of the aircraft based on the neural network according to claim 1, wherein the formula for constructing the autocorrelation matrix of the x-axis acceleration in S2 is as follows: x is X 1 ＝(A x ) T A x The formula for constructing the autocorrelation matrix of the y-axis acceleration is as follows: x is X 2 ＝(A y ) T A y The formula for constructing the autocorrelation matrix of the z-axis acceleration is as follows: x is X 3 ＝(A z ) T A z Wherein X is 1 Is an autocorrelation matrix of X-axis acceleration, X 2 For the autocorrelation matrix of the y-axis acceleration, X 3 An autocorrelation matrix for the z-axis acceleration, A x Is a one-dimensional x-axis acceleration vector A y Az is a one-dimensional y-axis acceleration vector, and T is a transposition operation.
3. The intelligent diagnosis method for fault of aircraft based on neural network according to claim 1, wherein the convolutional neural network in S3 comprises: a first convolution layer, a second convolution layer, a third convolution layer, a fourth convolution layer, a fifth convolution layer, a sixth convolution layer, a attention block, and an adder A1;
the input end of the first convolution layer is used as the input end of the convolution neural network, and the output end of the first convolution layer is connected with the input end of the second convolution layer; the output end of the second convolution layer is respectively connected with the input end of the third convolution layer and the input end of the fifth convolution layer; the input end of the attention block is connected with the output end of the third convolution layer, and the output end of the attention block is connected with the input end of the fourth convolution layer; the first input end of the adder A1 is connected with the output end of the fourth convolution layer, the second input end of the adder A1 is connected with the output end of the fifth convolution layer, and the output end of the adder A1 is connected with the input end of the sixth convolution layer; the output end of the sixth convolution layer is used as the output end of the convolution neural network.
4. The neural network-based aircraft fault intelligent diagnostic method of claim 3, wherein the attention block comprises: a seventh convolution layer, an eighth convolution layer, a ninth convolution layer, a global pooling layer, a full connection layer, a Sigmoid layer, a multiplier and an adder A2;
the input end of the seventh convolution layer is used as the input end of the attention block, and the output end of the seventh convolution layer is respectively connected with the input end of the eighth convolution layer, the first input end of the multiplier and the input end of the global pooling layer; the input end of the full-connection layer is connected with the output end of the global pooling layer, and the output end of the full-connection layer is connected with the input end of the Sigmoid layer; the second input end of the multiplier is connected with the output end of the Sigmoid layer, and the output end of the multiplier is connected with the first input end of the adder A2; the second input of the adder A2 is connected to the output of the ninth convolution layer, and its output is the output of the attention block.
5. The intelligent diagnosis method for the fault of the aircraft based on the neural network according to claim 4, wherein the expression of the Sigmoid layer is:wherein x is i For the ith input of the Sigmoid layer, sigmoid is an S-type activation function,/>Is the ith output of the Sigmoid layer.
6. The intelligent diagnosis method for the fault of the aircraft based on the neural network according to claim 1, wherein the classifier in S4 comprises: the device comprises a first classifying unit, a second classifying unit, a third classifying unit and a classified output unit;
the first classification unit is used for processing acceleration characteristics corresponding to the x-axis acceleration to obtain a first classification value; the second classification unit is used for processing acceleration characteristics corresponding to the y-axis acceleration to obtain a second classification value; the third classification unit is used for processing acceleration characteristics corresponding to the z-axis acceleration to obtain a third classification value; the classification output unit is used for obtaining the fault type of the aircraft according to the first classification value, the second classification value and the third classification value.
7. The intelligent diagnosis method for the fault of the aircraft based on the neural network according to claim 6, wherein expressions of the first classification unit, the second classification unit and the third classification unit are:
wherein y is a classification value output by the first classification unit, the second classification unit or the third classification unit, exp is an exponential function based on a natural constant, h j The j-th acceleration characteristic, w, of the first classification unit, the second classification unit or the third classification unit j Weight of the j-th acceleration feature, b j For the bias of the jth acceleration feature, N is the number of acceleration features and ln is a logarithmic function.
8. The neural network-based intelligent diagnosis method for an aircraft fault according to claim 6, wherein the expression of the classification output unit is:
Y＝sigmoid(W 1 y 1 +W 2 y 2 +W 3 y 3 )
wherein Y is the output of the classified output unit, sigmoid is the S-type activation function, Y 1 For the first classification value, y 2 For a second classification value, y 3 For the third classification value, W 1 For the first classification value y 1 Weight of the second classification value y 2 Weight, W of (2) 3 For the third classification value y 3 Is a weight of (2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311191819.6A CN117216521B (en) | 2023-09-14 | 2023-09-14 | Intelligent diagnosis method for fault of aircraft based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311191819.6A CN117216521B (en) | 2023-09-14 | 2023-09-14 | Intelligent diagnosis method for fault of aircraft based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117216521A true CN117216521A (en) | 2023-12-12 |
| CN117216521B CN117216521B (en) | 2024-07-12 |
Family
ID=89042112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311191819.6A Active CN117216521B (en) | 2023-09-14 | 2023-09-14 | Intelligent diagnosis method for fault of aircraft based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117216521B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200120110A1 (en) * | 2018-10-15 | 2020-04-16 | Microsoft Technology Licensing, Llc | Neural network architectures employing interrelatedness |
| CN111259927A (en) * | 2020-01-08 | 2020-06-09 | 西北工业大学 | Rocket engine fault diagnosis method based on neural network and evidence theory |
| WO2020244134A1 (en) * | 2019-06-05 | 2020-12-10 | 华南理工大学 | Multi-task feature sharing neural network-based intelligent fault diagnosis method |
| CN114112398A (en) * | 2021-11-25 | 2022-03-01 | 中原工学院 | Fault diagnosis method for rolling bearing under variable speed working condition |
| CN115712821A (en) * | 2022-12-02 | 2023-02-24 | 中国计量大学 | Elevator fault diagnosis method based on graph neural network |
| WO2023123593A1 (en) * | 2021-12-30 | 2023-07-06 | 浙大城市学院 | Variational mode decomposition and residual network-based aviation bearing fault diagnosis method |
-
2023
- 2023-09-14 CN CN202311191819.6A patent/CN117216521B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200120110A1 (en) * | 2018-10-15 | 2020-04-16 | Microsoft Technology Licensing, Llc | Neural network architectures employing interrelatedness |
| WO2020244134A1 (en) * | 2019-06-05 | 2020-12-10 | 华南理工大学 | Multi-task feature sharing neural network-based intelligent fault diagnosis method |
| CN111259927A (en) * | 2020-01-08 | 2020-06-09 | 西北工业大学 | Rocket engine fault diagnosis method based on neural network and evidence theory |
| CN114112398A (en) * | 2021-11-25 | 2022-03-01 | 中原工学院 | Fault diagnosis method for rolling bearing under variable speed working condition |
| WO2023123593A1 (en) * | 2021-12-30 | 2023-07-06 | 浙大城市学院 | Variational mode decomposition and residual network-based aviation bearing fault diagnosis method |
| CN115712821A (en) * | 2022-12-02 | 2023-02-24 | 中国计量大学 | Elevator fault diagnosis method based on graph neural network |
Non-Patent Citations (2)
| Title |
|---|
| 杨柏;关焕新;王森;杨亮;王鹤蓉;: "基于深层卷积神经网络电动飞机主驱动电机故障诊断方法", 微电机, no. 03, 31 March 2020 (2020-03-31) * |
| 颉潭成;陈孟会;徐彦伟;李先锋;: "卷积神经网络在轴承故障识别的应用", 制造业自动化, no. 01, 31 January 2020 (2020-01-31) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117216521B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
| CN114282579A (en) | Aviation bearing fault diagnosis method based on variational modal decomposition and residual error network | |
| CN111639678A (en) | INS/GPS integrated navigation fault detection and diagnosis method based on integrated neural network | |
| CN110428191B (en) | Method for identifying fragile nodes of power distribution network | |
| CN113091872A (en) | Method and device for diagnosing fault sensor | |
| CN112465045A (en) | Supply chain exception event detection method based on twin neural network | |
| CN115452376A (en) | Bearing fault diagnosis method based on improved lightweight deep convolution neural network | |
| CN116428124A (en) | Fault diagnosis method based on large number of equipment of same type | |
| CN116956215A (en) | Fault diagnosis method and system for transmission system | |
| CN110266527B (en) | Sensor node fault classification alarm method and device based on spatial correlation | |
| CN108827671A (en) | A kind of Trouble Diagnostic Method of Machinery Equipment | |
| CN117216521B (en) | Intelligent diagnosis method for fault of aircraft based on neural network | |
| CN112069738B (en) | Electric steering engine residual life prediction method and system based on DBN and multilayer fuzzy LSTM | |
| CN117231590A (en) | Fault prediction system and method for hydraulic system | |
| Guo et al. | Operation stage division and RUL prediction of bearings based on 1DCNN-ON-LSTM | |
| CN117251793A (en) | Mechanical arm fault diagnosis method based on deep learning under nuclear radiation environment | |
| CN115205582A (en) | Intelligent drawing-simulating aviation sensor fault detection and classification method | |
| CN109726492B (en) | Reliability analysis method for airborne redundancy electrical circuit interconnection system without failure data | |
| CN117571321B (en) | Bearing fault detection method, device, equipment and storage medium | |
| CN110826690A (en) | Equipment state identification method and system and computer readable storage medium | |
| CN118133189B (en) | Bridge structure health state real-time monitoring method and system | |
| CN117666368B (en) | Unmanned aerial vehicle multi-machine cooperation operation method and system based on Internet of things | |
| CN112429252B (en) | Flight emergency prediction method based on PCA algorithm | |
| CN114593919B (en) | Novel rolling bearing fault diagnosis method and system | |
| CN112421767B (en) | Power grid disaster prevention emergency panoramic monitoring method and device |
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 |