CN114137915A - Fault diagnosis method for industrial equipment - Google Patents
Fault diagnosis method for industrial equipment Download PDFInfo
- Publication number
- CN114137915A CN114137915A CN202111371213.1A CN202111371213A CN114137915A CN 114137915 A CN114137915 A CN 114137915A CN 202111371213 A CN202111371213 A CN 202111371213A CN 114137915 A CN114137915 A CN 114137915A
- Authority
- CN
- China
- Prior art keywords
- fault
- equipment
- value
- diagnosed
- monitoring parameter
- 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 75
- 238000003745 diagnosis Methods 0.000 title claims abstract description 71
- 238000012544 monitoring process Methods 0.000 claims abstract description 125
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 238000013210 evaluation model Methods 0.000 claims abstract description 23
- 238000011176 pooling Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000007257 malfunction Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 16
- 230000008569 process Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 238000003066 decision tree Methods 0.000 description 9
- 238000010801 machine learning Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 230000015654 memory Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a fault diagnosis method of industrial equipment, which comprises the following steps: collecting samples, wherein the samples comprise normal samples and fault samples; constructing a parameter evaluation model, and training the parameter evaluation model by adopting a normal sample; evaluating the monitoring parameters of the equipment to be diagnosed by adopting the trained parameter evaluation model to obtain a monitoring parameter evaluation value; updating the fault sample according to the monitoring parameter evaluation value and the corresponding monitoring parameter; constructing a fault recognition model, and training the fault recognition model by adopting a fault sample; and acquiring real-time monitoring parameters of the equipment to be diagnosed, and identifying the real-time monitoring parameters through the trained fault identification model to obtain a fault diagnosis result. The invention improves the fault diagnosis efficiency and the fault diagnosis accuracy of the industrial equipment.
Description
Technical Field
The invention belongs to the field of fault diagnosis, and particularly relates to a fault diagnosis method for industrial equipment.
Background
The fault diagnosis mainly refers to detecting, separating and identifying faults occurring in the operation process of a system or equipment, namely judging whether the faults occur or not, positioning the positions and types of the faults and the like. Currently, the main fault diagnosis methods include the following:
1. fault diagnosis method based on expert system
The fault diagnosis method based on the expert system is characterized in that a knowledge base is established by utilizing the accumulated experiences of field experts in long-term practice, and a set of computer program is designed to simulate the reasoning and decision process of human experts for fault diagnosis. The expert system is mainly composed of a knowledge base, an inference engine, a comprehensive database, a man-machine interface, an interpretation module and the like.
The fault diagnosis method based on the expert system can utilize rich experience knowledge of experts, does not need to carry out mathematical modeling on the system, and is easy to understand the diagnosis result, thereby being widely applied. However, the expert knowledge required by the method is difficult to obtain, which becomes a major bottleneck in the development of expert systems; secondly, the accuracy degree of diagnosis depends on the richness degree of expert experience and the knowledge level in the knowledge base; finally, when the rules are more, the problems of matching conflict, combined explosion and the like exist in the reasoning process, so that the reasoning speed is low and the efficiency is low.
2. Fault diagnosis method based on graph theory
The Fault diagnosis method based on graph theory mainly includes a Signed Directed Graph (SDG) method and a Fault tree (Fault tree) method. SDG is a widely used graphical model describing system causality. A fault tree is a special logic diagram. The diagnosis method based on fault tree is an analysis process from fruit to cause, and performs inference analysis step by step from the fault state of the system to finally determine the basic cause, the influence degree and the occurrence probability of the fault.
The fault diagnosis method based on the graph theory has the characteristics of simple modeling, easy understanding of results, wide application range and the like. However, when the system or the device is complicated, the searching process of this method becomes very complicated, the diagnosis accuracy is not high, and an invalid fault diagnosis result may be given, so in practical application, it is mostly used in combination with other methods.
3. Fault diagnosis method based on analytical model
The fault diagnosis method based on the analytical model utilizes the accurate mathematical model of the system and the observable input and output quantities to construct a residual signal to reflect the inconsistency between the expected behavior of the system and the actual operation mode, and then carries out fault diagnosis based on the analysis of the residual signal.
The fault diagnosis based on the analytical model utilizes deep knowledge of the interior of the system, and has good diagnosis effect. However, the methods rely on the accurate mathematical model of the diagnosed object, and the accurate mathematical model of the object is often difficult to establish in practice, and at this time, the fault diagnosis method based on the analytic model is not suitable any more.
4. Fault diagnosis method based on multivariate statistical analysis
The fault diagnosis method based on multivariate statistical analysis is to utilize the correlation among multiple variables of the process to carry out fault diagnosis on the process, and the method utilizes a multivariate projection method to decompose a multivariate sample space into a lower-dimensional projection subspace spanned by principal component variables and a corresponding residual error subspace according to the historical data of the process variables, constructs statistics capable of reflecting the space change in the two subspaces respectively, then projects observation vectors to the two subspaces respectively, and calculates corresponding statistic indexes for process monitoring.
The fault diagnosis method based on the multivariate statistical analysis does not need to deeply understand the structure and the principle of the system, is completely based on the measurement data of the sensor in the operation process of the system, and has simple algorithm and easy realization. However, the physics of faults diagnosed by such methods is ambiguous, difficult to interpret, and due to the complexity of the actual system, there are many problems to be further investigated in such methods, such as non-linearity between process variables, and the dynamics and time-variability of the process.
5. Fault diagnosis method based on signal processing
The fault diagnosis method based on signal processing analyzes and processes the measured signal by various signal processing methods, extracts the time domain or frequency domain characteristics of the signal related to the fault for fault diagnosis, and mainly comprises a spectrum analysis method and a wavelet transformation method.
The fault diagnosis method based on signal processing needs to manually design the signal processing process and details for fault diagnosis, however, for different problems, the selection and processing modes of signals are different, so that the application range of the method is small; meanwhile, the manually designed signal processing method is highly dependent on domain knowledge, which makes it difficult to accurately diagnose a fault from the extracted signal features.
6. Fault diagnosis method based on machine learning
The basic idea of the fault diagnosis method based on machine learning is to train a neural network or a support vector machine and other machine learning algorithms for fault diagnosis by utilizing historical data of the system under normal and various fault conditions. In fault diagnosis, a neural network is mainly used for classifying extracted fault features.
The fault diagnosis method based on machine learning takes the fault diagnosis accuracy as a learning target and has wide application range. However, the machine learning algorithm needs sample data in case of process failure, and the precision has a great relationship with the completeness and the representativeness of the sample, so that the machine learning algorithm is difficult to be used in industrial processes which cannot obtain a large amount of failure data.
Disclosure of Invention
Aiming at the defects in the prior art, the fault diagnosis method for the industrial equipment provided by the invention solves the problems of inaccurate fault diagnosis and low fault diagnosis efficiency in the prior art.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that: a method of fault diagnosis of an industrial device, comprising:
collecting samples, wherein the samples comprise normal samples and fault samples;
constructing a parameter evaluation model, and training the parameter evaluation model by adopting a normal sample;
evaluating the monitoring parameters of the equipment to be diagnosed by adopting the trained parameter evaluation model to obtain a monitoring parameter evaluation value;
updating the fault sample according to the monitoring parameter evaluation value and the corresponding monitoring parameter;
constructing a fault recognition model, and training the fault recognition model by adopting a fault sample;
and acquiring real-time monitoring parameters of the equipment to be diagnosed, and identifying the real-time monitoring parameters through the trained fault identification model to obtain a fault diagnosis result.
Further, the normal sample is:
DP＝{(Xt-k,Yt)|t∈{k,k+1,...,m},k>0}
wherein D isPRepresenting a set of normal samples, input X of normal samplest-kRepresenting the value of a monitoring parameter of the industrial equipment from the monitoring starting moment to the t-k moment, k representing the prediction time interval, m being a positive integer, m>k, output of Normal sample YtA monitoring parameter value representing the industrial equipment at the time t; when k is 1, input X of normal samplet-kAnd output YtRespectively representing a monitoring parameter value matrix of the industrial equipment from the monitoring starting moment to the previous moment and a monitoring parameter value of the industrial equipment at the current moment.
3. The method for fault diagnosis of an industrial device according to claim 2, wherein the fault samples are:
DE＝{(Xt,Yt),t∈{0,1,...,m}}
wherein D isERepresenting a set of fault samples, XtValue of a monitoring parameter representing the industrial plant at time t, YtAnd a fault label one-hot vector of the industrial equipment at the moment t.
Further, the parameter identification model comprises an input layer, a plurality of convolutional neural network layers, a flat layer, an LSTM layer, a full connection layer and an output layer which are connected in sequence; the convolutional neural network layer comprises a first convolutional layer, a first pooling layer, a second convolutional layer and a second pooling layer which are sequentially connected; the full connection layer adopts Relu function as an activation function.
Further, the updating the fault sample according to the monitoring parameter evaluation value and the corresponding monitoring parameter includes:
acquiring a difference value sigma between a monitoring parameter value and a monitoring parameter evaluation value of the equipment to be diagnosed according to the monitoring parameter evaluation value, wherein the difference value sigma is as follows:
σ＝f(Y,Y')
wherein f (Y, Y ') represents a difference value calculation function, Y represents a monitoring parameter value of the equipment to be diagnosed, Y' represents a monitoring parameter evaluation value, the monitoring parameter value and the monitoring parameter evaluation value are both sequences on continuous time points, and | represents an absolute value;
according to the difference value sigma, obtaining the stability H of the equipment to be diagnosed as follows:
wherein e represents a natural constant, W represents a weight coefficient of the monitoring parameter, the monitoring parameter includes n sub-monitoring parameters, and W ═ W1 w2…wn]，w1 w2…wnRespectively representing the weight coefficients of the n sub-monitoring parameters;
and acquiring corresponding monitoring parameters when the industrial equipment fails according to the stability H, and adding the corresponding monitoring parameters to the failure sample set to complete the updating of the failure sample.
Further, the obtaining, according to the stability H, a corresponding monitoring parameter when the device to be diagnosed fails includes:
obtaining a sample mean value and a standard deviation of a normal sample;
summing the sample mean value and triple standard deviation to obtain a sum value, and taking the sum value as a control upper limit;
calculating the difference between the sample mean value and the triple standard deviation to obtain a difference value, and taking the difference value as a lower control limit;
acquiring an average value of the upper control limit and the lower control limit, and taking the average value as a central line;
constructing a fault judgment condition according to the upper control limit, the lower control limit and the center line;
and acquiring the stability of the equipment to be diagnosed at the continuous time point, and acquiring corresponding monitoring parameters when the equipment to be diagnosed fails according to the stability and the fault judgment condition at the continuous time point.
Further, according to the upper control limit, the lower control limit and the center line, fault judgment conditions are constructed, and the fault judgment conditions comprise:
equally dividing the area between the upper control limit and the central line into three parts, and equally dividing the area between the lower control limit and the central line into three parts;
taking a region close to the upper control limit and a region close to the lower control limit as a region A, taking a region close to the central line as a region C, and taking a region between the region A and the region C as a region B;
and constructing a fault judgment condition according to the area A, the area B and the area C.
Further, the fault determination condition includes:
if the stability is lower than the lower control limit or higher than the upper control limit, the equipment to be diagnosed fails;
if the stability of the nine continuous time points is located in the area C and on one side of the central line, the equipment to be diagnosed fails;
if the stability at six continuous time points is increased or decreased progressively, the equipment to be diagnosed fails;
if the stability of fourteen continuous time points is alternately up and down, the equipment to be diagnosed fails;
if two of the three stability degrees at the continuous time points are located in the area A, the equipment to be diagnosed fails;
if four of the stability degrees on the five continuous time points are located outside the C area and on one side of the center line, the equipment to be diagnosed breaks down;
if fifteen stabilities at continuous time points are located in the C area and distributed on two sides of the center line, the equipment to be diagnosed fails;
and if the stabilities of eight continuous time points are positioned in the area A or the area B and distributed on two sides of the central line, the equipment to be diagnosed fails.
Further, the constructing a fault recognition model and training the fault recognition model by using the fault sample includes:
an XGboost model is adopted as a fault identification model;
and training the fault recognition model by adopting the fault sample.
The invention has the beneficial effects that:
(1) the invention provides a fault diagnosis method of industrial equipment, which improves the fault diagnosis efficiency and the fault diagnosis accuracy of the industrial equipment.
(2) The method comprises the steps of constructing a parameter evaluation model, selecting normal operation data of the industrial equipment as training sample data, realizing the pre-estimation of current detection parameters of the industrial equipment on the premise of not needing fault sample data, obtaining the current stability of the industrial equipment by combining the current actual monitoring parameters of the industrial equipment, further obtaining a stability sequence on a continuous time point, then constructing a fault judgment condition, monitoring the obtained stability sequence in real time through the fault judgment condition, and judging whether the operation of the industrial equipment is abnormal or not.
(3) The parameter evaluation model only takes normal data as a training sample, and the fault identification model only takes fault data as a training sample, so that the normal data and the fault data are not interfered with each other. In addition, only when the parameter evaluation model judges that the industrial equipment is abnormal in operation, the fault identification model is used for identifying fault data, so that the fault identification operation of normal operation data is avoided, and the fault diagnosis efficiency is improved.
(4) According to the fault identification method and the fault identification device, after the corresponding fault type is acquired by adopting the fault identification model, the detailed information such as the specific fault position, the specific fault reason and the like can be acquired by combining the fault type and the fault detailed information association table, so that operation and maintenance personnel are supported to quickly and accurately solve the fault problem.
Drawings
Fig. 1 is a flowchart of a fault diagnosis method for an industrial device according to an embodiment of the present disclosure.
Fig. 2 is a structural diagram of a parameter evaluation model provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of a condition one provided in an embodiment of the present application.
Fig. 4 is a schematic diagram of a condition two provided in the embodiment of the present application.
Fig. 5 is a schematic diagram of condition three provided in the embodiment of the present application.
Fig. 6 is a schematic diagram of condition four provided in the embodiment of the present application.
Fig. 7 is a schematic diagram of condition five provided in the embodiment of the present application.
Fig. 8 is a schematic diagram of condition six provided in an embodiment of the present application.
Fig. 9 is a schematic diagram of condition seven provided in an embodiment of the present application.
Fig. 10 is a schematic diagram of condition eight provided in the embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Example 1
As shown in fig. 1, a fault diagnosis method of an industrial device includes:
collecting samples, wherein the samples comprise normal samples and fault samples;
constructing a parameter evaluation model, and training the parameter evaluation model by adopting a normal sample;
evaluating the monitoring parameters of the equipment to be diagnosed by adopting the trained parameter evaluation model to obtain a monitoring parameter evaluation value;
updating the fault sample according to the monitoring parameter evaluation value and the corresponding monitoring parameter;
constructing a fault recognition model, and training the fault recognition model by adopting a fault sample;
and acquiring real-time monitoring parameters of the equipment to be diagnosed, and identifying the real-time monitoring parameters through the trained fault identification model to obtain a fault diagnosis result.
Optionally, the industrial equipment may include equipment such as a machine tool and a stamping device, but the technical scheme provided by the present invention is not limited to this, and the technical scheme provided by the present invention may also be applied to an industrial system.
Optionally, the monitoring parameter values may include a temperature value, a rotation speed value, a current value, a voltage value, and the like, and after data cleaning and parameter standardization operations are performed on the monitoring parameter values, the monitoring parameter values may be divided into normal samples and fault samples.
Data cleansing may include data consistency checking, null value processing, missing data processing, invalid value processing, duplicate value processing, and the like. Normalization is to eliminate the variability between features and facilitate weight learning during model training, and may include min-max normalization, Z-score normalization (zero-mean normalization), or fractional scaling normalization, etc.
In one possible embodiment, the normal sample is:
DP＝{(Xt-k,Yt),t∈{k,k+1,...,m},k>0}
wherein D isPRepresenting a set of normal samples, input X of normal samplest-kRepresenting the value of a monitoring parameter of the industrial equipment from the monitoring starting moment to the t-k moment, k representing the prediction time interval, m being a positive integer, m>k, output of Normal sample YtA monitoring parameter value representing the industrial equipment at the time t; when k is 1, input X of normal samplet-kAnd output YtRespectively representing a monitoring parameter value matrix of the industrial equipment from the monitoring starting moment to the previous moment and a monitoring parameter value of the industrial equipment at the current moment.
Optionally, if the monitored parameter value is multiple parameter values, inputting X of the normal samplet-kA monitoring parameter value matrix representing industrial equipment from the monitoring starting time to the t-k time and the output Y of a normal sampletA vector of monitored parameter values representing the industrial plant at time t.
In this embodiment, the monitoring parameter values in the normal sample are time series multidimensional data of the industrial equipment in the normal operation period.
In one possible embodiment, the fault sample is:
DE＝{(Xt,Yt),t∈{0,1,...,m}}
wherein D isERepresenting a set of fault samples, XtValue of a monitoring parameter representing the industrial plant at time t, YtA fault label one-hot vector representing the industrial equipment at time t.
And taking the monitoring parameter value and the fault label one-hot vector when the industrial equipment is in fault as a fault sample.
Optionally, an association table of the fault label and the fault details may be constructed, and after the fault type (fault label) is identified by the fault identification model, the fault details may be located by the association table.
As shown in fig. 2, the parameter identification model includes an input layer, a plurality of convolutional neural network layers, a flat layer, an LSTM (Long Short-Term Memory) layer, a full connection layer, and an output layer, which are connected in sequence; the convolutional neural network layer comprises a first convolutional layer, a first pooling layer, a second convolutional layer and a second pooling layer which are sequentially connected; the fully connected layer uses Relu function (linear rectification function) as the activation function.
Optionally, the training of the parameter evaluation model is supervised training.
The convolution layer is a two-dimensional convolution layer and is used for performing convolution operation on input data to extract features, a parameter matrix of m monitoring parameters at the h moments before t moment is used as input, namely X belongs to Rh×m×1Let the number of convolution kernels K, the specification of each convolution kernel F, the step S of the convolution, and the number of zero-padding P. For each convolution operation, zero-filling is first performed on the data X to convert the data volume into X' epsilon R(h+p)×(m+p)×1Then, convolution operation is performed, and the convolution operation is shown as the following formula.
Kernel∈RF×F×1
T＝Kernel×X'
Repeating the calculation for the input X according to the sequence from left to right and from top to bottom and the convolution step S, and reintegrating the Y values obtained each time into a matrix, namely obtaining the output Y belonging to Rh'×m'×dWherein h ═ (h-F +2 × P)/S +1, m ═ m-F +2 × P)/S +1, and d ═ 1.
The pooling layer can select two modes of maximum pooling (Max pooling) and Average pooling (Average pooling), and the calculation formula is as follows:
Maxpolling:y＝max(Xc)
Aceragepooling:y＝mean(Xc)
input XcThe output of the convolution layer is subjected to pooling operation from left to right and from top to bottom in order to obtain the output Y' belonging to Rh”×m”Wherein h ═ h-F/S +1, m ═ m-F/S + 1.
Meanwhile, considering that system or equipment monitoring parameters are usually positive values, Relu is selected as an activation function in the full connection layer, and Relu function definition domain function images are shown as follows.
f(x)＝max(0,x)。
In a possible implementation manner, the updating the fault sample according to the monitored parameter evaluated value and the corresponding monitored parameter includes:
acquiring a difference value sigma between a monitoring parameter value and a monitoring parameter evaluation value of the equipment to be diagnosed according to the monitoring parameter evaluation value, wherein the difference value sigma is as follows:
σ＝f(Y,Y')
wherein f (x, Y) represents a difference value calculation function, Y represents a monitoring parameter value of the device to be diagnosed, Y' represents a monitoring parameter evaluation value, and the monitoring parameter value and the monitoring parameter evaluation value are both a sequence on continuous time points.
Optionally, if the monitored parameter value is a plurality of parameter values, the parameter evaluation value is a vector, and the parameter evaluation value includes evaluation values corresponding to the plurality of parameter values.
The monitoring parameter evaluation value is in corresponding relation with the monitoring parameter value, the monitoring parameter evaluation value represents a monitoring parameter prediction value of the equipment to be diagnosed at a continuous time point, and the monitoring parameter value represents a monitoring parameter real value of the equipment to be diagnosed at the continuous time point. And obtaining a difference value sequence of the equipment to be diagnosed at continuous time points according to the monitoring parameters and the monitoring parameter evaluation value.
According to the difference value sigma, obtaining the stability H of the equipment to be diagnosed as follows:
wherein e represents a natural constant, W represents a weight coefficient of the monitoring parameter, the monitoring parameter includes n sub-monitoring parameters, and W ═ W1 w2…wn]，w1 w2…wnRespectively representing the weight coefficients of the n sub-monitoring parameters;
and acquiring corresponding monitoring parameters when the industrial equipment fails according to the stability H, and adding the corresponding monitoring parameters to the failure sample set to complete the updating of the failure sample.
In a possible implementation manner, the obtaining, according to the stability H, a corresponding monitoring parameter when the device to be diagnosed fails includes:
obtaining a sample mean value and a standard deviation of a normal sample;
summing the sample mean value and triple standard deviation to obtain a sum value, and taking the sum value as a control upper limit;
calculating the difference between the sample mean value and the triple standard deviation to obtain a difference value, and taking the difference value as a lower control limit;
acquiring an average value of the upper control limit and the lower control limit, and taking the average value as a central line;
constructing a fault judgment condition according to the upper control limit, the lower control limit and the center line;
and acquiring the stability of the equipment to be diagnosed at the continuous time point, and acquiring corresponding monitoring parameters when the equipment to be diagnosed fails according to the stability and the fault judgment condition at the continuous time point.
In this embodiment, the monitoring parameter value is time sequence multidimensional data of the industrial equipment in a normal operation period, and the stability of the equipment to be diagnosed at a continuous time point can be obtained by identifying the time sequence multidimensional data, so that a stability sequence is obtained.
In one possible implementation, constructing the fault determination condition according to the upper control limit, the lower control limit and the center line includes:
equally dividing the area between the upper control limit and the central line into three parts, and equally dividing the distance between the lower control limit and the central line into three parts;
taking a region close to the upper control limit and a region close to the lower control limit as a region A, taking a region close to the central line as a region C, and taking a region between the region A and the region C as a region B;
and constructing a fault judgment condition according to the area A, the area B and the area C.
In one possible embodiment, the failure determination condition includes conditions one to eight.
As shown in fig. 3, condition one is: if the stability is lower than the lower control limit or higher than the upper control limit, the equipment to be diagnosed fails;
as shown in fig. 4, the second condition is: if the stability of the nine continuous time points is positioned in the C area and is positioned on one side of the central line, the equipment to be diagnosed fails;
as shown in fig. 5, the third condition is: if the stability at six continuous time points is increased or decreased gradually, the equipment to be diagnosed is in failure;
as shown in fig. 6, condition four is: if the stability on fourteen continuous time points is alternately up and down, the equipment to be diagnosed is in failure;
as shown in fig. 7, condition five is: if two of the stabilities at the three continuous time points are located in the area A, the equipment to be diagnosed fails;
as shown in fig. 8, the sixth condition is: if four of the stability degrees on the five continuous time points are positioned outside the C area and on one side of the central line, the equipment to be diagnosed breaks down;
as shown in fig. 9, the condition seven is: if the stability of fifteen continuous time points is located in the C area and distributed on two sides of the central line, the equipment to be diagnosed fails;
as shown in fig. 10, condition eight is: if the stabilities at eight continuous time points are located in the area A or the area B and distributed on two sides of the central line, the equipment to be diagnosed fails.
In this embodiment, when the device to be diagnosed has a fault, the stability at the last time point in the continuous time points is used as a stability violation point (X in fig. 3 to 10), and the monitoring parameter corresponding to the stability violation point and the fault label one-hot vector corresponding to the monitoring parameter are used as fault samples.
In a possible implementation, the building a fault recognition model and training the fault recognition model by using fault samples includes:
an XGboost model is adopted as a fault identification model;
and training the fault recognition model by adopting the fault sample.
When the industrial equipment is detected to have a fault, specific fault types need to be identified, so that the fault is positioned, and operation and maintenance personnel can conveniently overhaul and investigate the fault. When the fault sample data is accumulated to a certain degree, an XGboost (Extreme Gradient Boosting) model is adopted to construct a fault identification model, the fault sample data is selected, the sample data is divided correspondingly (one part is used as training data and the other part is used as test data), supervised training is carried out, and a training result model is stored. The XGBoost is a product of a Decision Tree model and AdaBoost (Adaptive Boost, Adaptive enhancement), and is an improvement of a GDBT (Gradient Boosting Decision Tree) model, and a specific implementation form thereof is as follows.
If the block of round t-1 is knownA strategy tree is built based on the strategy tree, and the objective function Obj of the t-th round is constructed(t)The method comprises the following steps:
wherein, yiIs an actual value, ft-1(xi) Is the output result of the first t-1 decision trees, f (x)i) Output results of the decision tree for the t-th round, L (y)i,ft-1(xi)+f(xi) Is a loss function, i.e., Ω (f (x)) is regular.
And (3) performing second-order Taylor expansion on the loss function at the t-1 tree:
L(yi,ft-1(xi)+ft(xi))＝L(yi,ft-1(xi))+gif(xi)+hif(xi)2/2
wherein, L (y)i,ft-1(xi) Is the corresponding loss function value of the first t-1 trees, i.e. is the prediction error of the learning model composed of the first t-1 trees, is a constant, gi、hiFirst and second derivatives of the prediction error versus the current model, respectively.
For a decision tree, the following equation is given:
fk(x)＝wq(x)
where q (x) represents the leaf node index number of the output, is an index map whichThe effect is to map the input to the leaf above the index, wq(x)The value of the sequence number of the corresponding leaf node is shown, r shows the difficulty of node segmentation, T is the number of the leaf nodes, lambda shows the regularization coefficient of L2, and wjIs the predicted value of the jth leaf node,
modulo the leaf node vector.
The objective function can therefore be written in the form:
substituting the decision tree formula to obtain:
converting the first part of the above formula from the accumulation mode of all pairs of training sample sets into accumulation of all leaf nodes, and obtaining:
wherein, ItRepresenting a set of samples, Gj、HjRepresenting the sum of the first and second derivatives, respectively, of all input samples mapped as leaf nodes j.
To WjThe derivation is taken and is given in the formula:
based on the formula, the XGboost can construct a predicted value of each leaf node of the decision tree, a greedy algorithm is adopted to calculate the corresponding target function descending amount Gain of the decision tree after splitting until the maximum decision tree depth is reached, or the Gain value is less than 0, and the Gain calculation formula is shown as the following formula.
Wherein the content of the first and second substances,
GL、GRg value, H value corresponding to left and right nodes respectivelyL、HRAnd H values corresponding to the left node and the right node respectively, wherein I refers to the current node instance set.
And acquiring fault parameters of the equipment to be diagnosed, and carrying out standardized processing on the fault parameters. And according to the fault parameters, identifying the fault type through a fault identification model, and obtaining fault details through a fault type and fault detail association table so as to facilitate operation and maintenance personnel to carry out troubleshooting and maintenance on the equipment to be diagnosed based on the obtained fault details. The fault details may include the location of the fault and the cause of the fault.
Example 2
In this embodiment, a fault diagnosis apparatus for an industrial device is provided, which includes an acquisition module, a first training module, an evaluation module, an update module, a second training module, and an identification module.
The acquisition module is used for acquiring samples, wherein the samples comprise normal samples and fault samples;
the first training module is used for constructing a parameter evaluation model and training the parameter evaluation model by adopting a normal sample;
the evaluation module is used for evaluating the monitoring parameters of the equipment to be diagnosed by adopting the trained parameter evaluation model to obtain a monitoring parameter evaluation value;
the updating module is used for updating the fault sample according to the monitoring parameter evaluation value and the corresponding monitoring parameter;
the second training module is used for constructing a fault recognition model and training the fault recognition model by adopting a fault sample;
the identification module is used for acquiring real-time monitoring parameters of the equipment to be diagnosed, and identifying the real-time monitoring parameters through the trained fault identification model to obtain a fault diagnosis result.
Example 3
In the present embodiment, there is provided a fault diagnosis apparatus of an industrial apparatus, including a processor and a memory;
the memory stores computer-executable instructions;
the processor executes the computer-executable instructions stored in the memory, so that the processor performs the fault diagnosis method of the industrial equipment according to embodiment 1.
Example 4
In the present embodiment, a computer-readable storage medium is provided, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is used for implementing the fault diagnosis method of the industrial equipment according to embodiment 1.
Example 5
In the present embodiment, there is provided a computer program product including a computer program that, when executed by a processor, implements the fault diagnosis method of the industrial equipment described in embodiment 1.
The invention provides a fault diagnosis method of industrial equipment, which improves the fault diagnosis efficiency and the fault diagnosis accuracy of the industrial equipment.
The method comprises the steps of constructing a parameter evaluation model, selecting normal operation data of the industrial equipment as training sample data, realizing the pre-estimation of current detection parameters of the industrial equipment on the premise of not needing fault sample data, obtaining the current stability of the industrial equipment by combining the current actual monitoring parameters of the industrial equipment, further obtaining a stability sequence on a continuous time point, then constructing a fault judgment condition, monitoring the obtained stability sequence in real time through the fault judgment condition, and judging whether the operation of the industrial equipment is abnormal or not.
The parameter evaluation model only takes normal data as a training sample, and the fault identification model only takes fault data as a training sample, so that the normal data and the fault data are not interfered with each other. In addition, only when the parameter evaluation model judges that the industrial equipment is abnormal in operation, the fault identification model is used for identifying fault data, so that the fault identification operation of normal operation data is avoided, and the fault diagnosis efficiency is improved.
According to the fault identification method and the fault identification device, after the corresponding fault type is acquired by adopting the fault identification model, the detailed information such as the specific fault position, the specific fault reason and the like can be acquired by combining the fault type and the fault detailed information association table, so that operation and maintenance personnel are supported to quickly and accurately solve the fault problem.
Claims (9)
1. A method of diagnosing a fault in an industrial device, comprising:
collecting samples, wherein the samples comprise normal samples and fault samples;
constructing a parameter evaluation model, and training the parameter evaluation model by adopting a normal sample;
evaluating the monitoring parameters of the equipment to be diagnosed by adopting the trained parameter evaluation model to obtain a monitoring parameter evaluation value;
updating the fault sample according to the monitoring parameter evaluation value and the corresponding monitoring parameter;
constructing a fault recognition model, and training the fault recognition model by adopting a fault sample;
and acquiring real-time monitoring parameters of the equipment to be diagnosed, and identifying the real-time monitoring parameters through the trained fault identification model to obtain a fault diagnosis result.
2. The method for diagnosing a malfunction of an industrial device according to claim 1, wherein the normal sample is:
DP＝{(Xt-k,Yt)|t∈{k,k+1,...,m},k>0}
wherein D isPRepresenting a set of normal samples, input X of normal samplest-kRepresenting the value of a monitoring parameter of the industrial equipment from the monitoring starting moment to the t-k moment, k representing the prediction time interval, m being a positive integer, m>k, output of Normal sample YtMonitoring parameter for indicating industrial equipment at time tA numerical value; when k is 1, input X of normal samplet-kAnd output YtRespectively representing a monitoring parameter value matrix of the industrial equipment from the monitoring starting moment to the previous moment and a monitoring parameter value of the industrial equipment at the current moment.
3. The method for fault diagnosis of an industrial device according to claim 2, wherein the fault samples are:
DE＝{(Xt,Yt),t∈{0,1,...,m}}
wherein D isERepresenting a set of fault samples, XtValue of a monitoring parameter representing the industrial plant at time t, YtAnd a fault label one-hot vector of the industrial equipment at the moment t.
4. The fault diagnosis method of industrial equipment according to claim 1, wherein the parameter identification model comprises an input layer, a plurality of convolutional neural network layers, a flat layer, an LSTM layer, a full connection layer and an output layer which are connected in sequence; the convolutional neural network layer comprises a first convolutional layer, a first pooling layer, a second convolutional layer and a second pooling layer which are sequentially connected; the full connection layer adopts Relu function as an activation function.
5. The method for diagnosing the fault of the industrial equipment according to claim 1, wherein the updating the fault sample according to the evaluated value of the monitoring parameter and the corresponding monitoring parameter comprises:
acquiring a difference value sigma between a monitoring parameter value and a monitoring parameter evaluation value of the equipment to be diagnosed according to the monitoring parameter evaluation value, wherein the difference value sigma is as follows:
σ＝f(Y,Y')
wherein f (Y, Y ') represents a difference value calculation function, Y represents a monitoring parameter value of the equipment to be diagnosed, Y' represents a monitoring parameter evaluation value, the monitoring parameter value and the monitoring parameter evaluation value are both sequences on continuous time points, and | represents an absolute value;
according to the difference value sigma, obtaining the stability H of the equipment to be diagnosed as follows:
wherein e represents a natural constant, W represents a weight coefficient of the monitoring parameter, the monitoring parameter includes n sub-monitoring parameters, and W ═ W1 w2…wn]，w1 w2…wnRespectively representing the weight coefficients of the n sub-monitoring parameters;
and acquiring corresponding monitoring parameters when the industrial equipment fails according to the stability H, and adding the corresponding monitoring parameters to the failure sample set to complete the updating of the failure sample.
6. The method for diagnosing the fault of the industrial equipment according to claim 5, wherein the step of obtaining the corresponding monitoring parameter when the equipment to be diagnosed has the fault according to the stability H comprises the steps of:
obtaining a sample mean value and a standard deviation of a normal sample;
summing the sample mean value and triple standard deviation to obtain a sum value, and taking the sum value as a control upper limit;
calculating the difference between the sample mean value and the triple standard deviation to obtain a difference value, and taking the difference value as a lower control limit;
acquiring an average value of the upper control limit and the lower control limit, and taking the average value as a central line;
constructing a fault judgment condition according to the upper control limit, the lower control limit and the center line;
and acquiring the stability of the equipment to be diagnosed at the continuous time point, and acquiring corresponding monitoring parameters when the equipment to be diagnosed fails according to the stability and the fault judgment condition at the continuous time point.
7. The method of diagnosing a fault in an industrial apparatus according to claim 6, wherein constructing the fault determination condition based on the upper control limit, the lower control limit, and the center line includes:
equally dividing the area between the upper control limit and the central line into three parts, and equally dividing the area between the lower control limit and the central line into three parts;
taking a region close to the upper control limit and a region close to the lower control limit as a region A, taking a region close to the central line as a region C, and taking a region between the region A and the region C as a region B;
and constructing a fault judgment condition according to the area A, the area B and the area C.
8. The fault diagnosis method of an industrial apparatus according to claim 7, wherein the fault determination condition includes:
if the stability is lower than the lower control limit or higher than the upper control limit, the equipment to be diagnosed fails;
if the stability of the nine continuous time points is located in the area C and on one side of the central line, the equipment to be diagnosed fails;
if the stability at six continuous time points is increased or decreased progressively, the equipment to be diagnosed fails;
if the stability of fourteen continuous time points is alternately up and down, the equipment to be diagnosed fails;
if two of the three stability degrees at the continuous time points are located in the area A, the equipment to be diagnosed fails;
if four of the stability degrees on the five continuous time points are located outside the C area and on one side of the center line, the equipment to be diagnosed breaks down;
if fifteen stabilities at continuous time points are located in the C area and distributed on two sides of the center line, the equipment to be diagnosed fails;
and if the stabilities of eight continuous time points are positioned in the area A or the area B and distributed on two sides of the central line, the equipment to be diagnosed fails.
9. The method for fault diagnosis of industrial equipment according to claim 1, wherein the constructing a fault recognition model and training the fault recognition model with fault samples comprises:
an XGboost model is adopted as a fault identification model;
and training the fault recognition model by adopting the fault sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111371213.1A CN114137915A (en) | 2021-11-18 | 2021-11-18 | Fault diagnosis method for industrial equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111371213.1A CN114137915A (en) | 2021-11-18 | 2021-11-18 | Fault diagnosis method for industrial equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114137915A true CN114137915A (en) | 2022-03-04 |
Family
ID=80390453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111371213.1A Pending CN114137915A (en) | 2021-11-18 | 2021-11-18 | Fault diagnosis method for industrial equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114137915A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117149498A (en) * | 2023-10-27 | 2023-12-01 | 华能信息技术有限公司 | Power plant fault diagnosis method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170053463A1 (en) * | 2014-02-21 | 2017-02-23 | Ge Aviation Systems, Llc | System and method of fault detection |
| US20170061322A1 (en) * | 2015-08-31 | 2017-03-02 | International Business Machines Corporation | Automatic generation of training data for anomaly detection using other user's data samples |
| CN109102189A (en) * | 2018-08-10 | 2018-12-28 | 杨璇 | A kind of electrical equipment is health management system arranged and method |
| CN109635958A (en) * | 2018-12-12 | 2019-04-16 | 成都航天科工大数据研究院有限公司 | A kind of predictive industrial equipment maintaining method and maintenance system based on edge calculations |
| CN110703214A (en) * | 2019-10-15 | 2020-01-17 | 和尘自仪(嘉兴)科技有限公司 | Weather radar state evaluation and fault monitoring method |
| CN111190349A (en) * | 2019-12-30 | 2020-05-22 | 中国船舶重工集团公司第七一一研究所 | Method, system and medium for monitoring state and diagnosing fault of ship engine room equipment |
| CN111444940A (en) * | 2020-02-28 | 2020-07-24 | 山东大学 | Fault diagnosis method for critical parts of fan |
| CN111914320A (en) * | 2020-06-06 | 2020-11-10 | 同济大学 | No-sample turnout fault diagnosis method based on deep learning |
| CN112417766A (en) * | 2020-12-03 | 2021-02-26 | 深制科技(苏州)有限公司 | Fault diagnosis method mainly based on fault-free data |
| CN113052218A (en) * | 2021-03-15 | 2021-06-29 | 杭州电子科技大学 | Multi-scale residual convolution and LSTM fusion performance evaluation method for industrial process |
-
2021
- 2021-11-18 CN CN202111371213.1A patent/CN114137915A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170053463A1 (en) * | 2014-02-21 | 2017-02-23 | Ge Aviation Systems, Llc | System and method of fault detection |
| US20170061322A1 (en) * | 2015-08-31 | 2017-03-02 | International Business Machines Corporation | Automatic generation of training data for anomaly detection using other user's data samples |
| CN109102189A (en) * | 2018-08-10 | 2018-12-28 | 杨璇 | A kind of electrical equipment is health management system arranged and method |
| CN109635958A (en) * | 2018-12-12 | 2019-04-16 | 成都航天科工大数据研究院有限公司 | A kind of predictive industrial equipment maintaining method and maintenance system based on edge calculations |
| CN110703214A (en) * | 2019-10-15 | 2020-01-17 | 和尘自仪(嘉兴)科技有限公司 | Weather radar state evaluation and fault monitoring method |
| CN111190349A (en) * | 2019-12-30 | 2020-05-22 | 中国船舶重工集团公司第七一一研究所 | Method, system and medium for monitoring state and diagnosing fault of ship engine room equipment |
| CN111444940A (en) * | 2020-02-28 | 2020-07-24 | 山东大学 | Fault diagnosis method for critical parts of fan |
| CN111914320A (en) * | 2020-06-06 | 2020-11-10 | 同济大学 | No-sample turnout fault diagnosis method based on deep learning |
| CN112417766A (en) * | 2020-12-03 | 2021-02-26 | 深制科技(苏州)有限公司 | Fault diagnosis method mainly based on fault-free data |
| CN113052218A (en) * | 2021-03-15 | 2021-06-29 | 杭州电子科技大学 | Multi-scale residual convolution and LSTM fusion performance evaluation method for industrial process |
Non-Patent Citations (3)
| Title |
|---|
| XUN DONG: ""Deep Cost Adaptive Convolutional Network: A Classification Method for Imbalanced Mechanical Data"", 《IEEE ACCESS》, 31 December 2020 (2020-12-31) * |
| 张敏龙: ""带故障样本的弹性双阈值SVDD在线故障诊断算法及其应用"", 《振动工程学报》, 31 December 2016 (2016-12-31) * |
| 曾州: ""基于深度学习的风电机组传动系统故障诊断方法研究"", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, 15 September 2021 (2021-09-15) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117149498A (en) * | 2023-10-27 | 2023-12-01 | 华能信息技术有限公司 | Power plant fault diagnosis method and system |
| CN117149498B (en) * | 2023-10-27 | 2024-03-01 | 华能信息技术有限公司 | Power plant fault diagnosis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146246B (en) | Fault detection method based on automatic encoder and Bayesian network | |
| CN110929847A (en) | Converter transformer fault diagnosis method based on deep convolutional neural network | |
| CN111680875B (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| CN116380445B (en) | Equipment state diagnosis method and related device based on vibration waveform | |
| CN114297918A (en) | Aero-engine residual life prediction method based on full-attention depth network and dynamic ensemble learning | |
| CN114091504A (en) | Rotary machine small sample fault diagnosis method based on generation countermeasure network | |
| CN116593157A (en) | Complex working condition gear fault diagnosis method based on matching element learning under small sample | |
| CN110991471A (en) | Fault diagnosis method for high-speed train traction system | |
| CN114819315A (en) | Bearing degradation trend prediction method based on multi-parameter fusion health factor and time convolution neural network | |
| Ye et al. | A deep learning-based method for automatic abnormal data detection: Case study for bridge structural health monitoring | |
| CN114137915A (en) | Fault diagnosis method for industrial equipment | |
| CN113033611B (en) | Motor bearing data acquisition and fault diagnosis system | |
| CN117272196A (en) | Industrial time sequence data anomaly detection method based on time-space diagram attention network | |
| CN111783941A (en) | Mechanical equipment diagnosis and classification method based on probability confidence degree convolutional neural network | |
| Bond et al. | A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data | |
| CN116108371A (en) | Cloud service abnormity diagnosis method and system based on cascade abnormity generation network | |
| CN116224950A (en) | Intelligent fault diagnosis method and system for self-organizing reconstruction of unmanned production line | |
| CN112069621B (en) | Method for predicting residual service life of rolling bearing based on linear reliability index | |
| CN116204825A (en) | Production line equipment fault detection method based on data driving | |
| CN115034307A (en) | Vibration data self-confirmation method, system and terminal for multi-parameter self-adaptive fusion | |
| CN113935413A (en) | Distribution network wave recording file waveform identification method based on convolutional neural network | |
| CN113849479A (en) | Comprehensive energy supply station oil tank leakage detection method based on instant learning and self-adaptive threshold | |
| CN114046816A (en) | Sensor signal fault diagnosis method based on lightweight gradient lifting decision tree | |
| CN114487643A (en) | On-spot handing-over of extra-high voltage GIL equipment is accepted and is synthesized test platform | |
| CN115556099B (en) | Sustainable learning industrial robot fault diagnosis system and method |
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 |