CN117102950B - Fault analysis method, device, electronic equipment and computer readable storage medium - Google Patents
Fault analysis method, device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN117102950B CN117102950B CN202311340560.7A CN202311340560A CN117102950B CN 117102950 B CN117102950 B CN 117102950B CN 202311340560 A CN202311340560 A CN 202311340560A CN 117102950 B CN117102950 B CN 117102950B
- Authority
- CN
- China
- Prior art keywords
- fault
- feature
- prediction
- probability
- decision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 23
- 238000009826 distribution Methods 0.000 claims abstract description 60
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 abstract description 8
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 14
- 238000004590 computer program Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 238000005520 cutting process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q11/00—Accessories fitted to machine tools for keeping tools or parts of the machine in good working condition or for cooling work; Safety devices specially combined with or arranged in, or specially adapted for use in connection with, machine tools
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
The application relates to the technical field of data analysis, and discloses a fault analysis method, a device, electronic equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring fault prediction data of the numerical control machine tool, wherein each fault feature related to the prediction fault prediction data is the reason probability of the fault cause, and taking each fault feature and the reason probability corresponding to each fault feature together as a fault factor distribution set; according to a preset contribution prediction algorithm, respectively determining a prediction weight value of each fault feature in a fault factor distribution set, wherein the prediction weight value is characterized by the influence degree of the fault feature on a fault decision result; and fusing the cause probability and the predicted weight value of the target fault feature to any target fault feature in the fault factor distribution set to obtain the fault importance value of the target fault feature. By adopting the technical scheme, the technical problem of low maintenance efficiency of the numerical control machine tool caused by difficult interpretation of faults of the numerical control machine tool can be solved.
Description
Technical Field
The present application relates to the field of data analysis technologies, and relates to a fault analysis method, a fault analysis device, an electronic device, and a computer readable storage medium.
Background
With the high-speed development of manufacturing industry, the wider the application of the numerical control machine tool, the indispensable in the production and manufacturing of enterprises becomes. If some equipment of the numerical control machine tool fails, the equipment cannot be found and processed in time, the normal operation of the whole system is affected, and even the system stops operating, so that serious economic loss and casualties are brought to enterprises. Therefore, whether the numerical control machine tool has a fault is usually predicted through the model, when the model predicts that the numerical control machine tool has the fault, the output prediction result is generally fault codes or abnormal sensor data so as to inform a user that the numerical control machine tool has the fault, but the reason for generating the fault codes or the reason for causing the abnormality of the sensor data cannot be known based on the fault codes or the abnormal sensor data, and the reason for causing the fault of the numerical control machine tool cannot be predicted by the model because the model is a black box model, and the user cannot acquire the reason for causing the fault of the numerical control machine tool from the prediction process of the model, so that the user cannot easily understand the prediction result output by the model, and further the user cannot easily maintain the numerical control machine tool based on the prediction result output by the model.
The foregoing is provided merely for the purpose of facilitating an understanding of the technical solutions of the present application and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The main purpose of the present application is to provide a fault analysis method, a device, an electronic apparatus and a computer readable storage medium, which aim to solve the technical problem of low maintenance efficiency of a numerical control machine caused by difficulty in explaining faults of the numerical control machine.
To achieve the above object, the present application provides a fault analysis method, including:
acquiring fault prediction data of a numerical control machine tool, respectively predicting the reason probability that each fault feature related to the fault prediction data is a fault reason, and taking each fault feature and the reason probability corresponding to each fault feature together as a fault factor distribution set;
according to a preset contribution prediction algorithm, respectively determining a prediction weight value of each fault feature in the fault factor distribution set, wherein the prediction weight value is characterized by the influence degree of the fault feature on a fault decision result, and the fault decision result is obtained based on the fault prediction of the numerical control machine tool;
fusing the cause probability and the predicted weight value of any target fault feature in the fault factor distribution set to obtain a fault importance value of the target fault feature;
The step of obtaining the failure prediction data of the numerical control machine tool, and predicting the reason probability that each failure feature related to the failure prediction data is a failure reason respectively comprises the following steps:
acquiring the fault prediction data of the numerical control machine, wherein the fault prediction data is any input data of a fault prediction model corresponding to the numerical control machine;
inputting the fault prediction data into a local interpretation model, and disturbing the fault prediction data based on a preset disturbance strategy through the local interpretation model to generate a neighborhood similarity sample of the fault prediction data;
and predicting the reason probability that each fault characteristic in the neighborhood similar samples is the fault reason.
To achieve the above object, the present application provides a failure analysis apparatus including:
the cause probability determining module is used for acquiring fault prediction data of the numerical control machine tool, respectively predicting the cause probability that each fault feature related to the fault prediction data is a fault cause, and taking each fault feature and the cause probability corresponding to each fault feature together as a fault factor distribution set;
the weight value determining module is used for respectively determining the predicted weight value of each fault feature in the fault factor distribution set according to a preset contribution prediction algorithm, wherein the predicted weight value is characterized by the influence degree of the fault feature on a fault decision result, and the fault decision result is obtained based on the fault prediction of the numerical control machine tool;
The fault importance value determining module is used for fusing the cause probability and the prediction weight value of any target fault feature in the fault factor distribution set to obtain the fault importance value of the target fault feature;
the cause probability determining module is further used for obtaining the fault prediction data of the numerical control machine tool, wherein the fault prediction data is any input data of a fault prediction model corresponding to the numerical control machine tool; inputting the fault prediction data into a local interpretation model, and disturbing the fault prediction data based on a preset disturbance strategy through the local interpretation model to generate a neighborhood similarity sample of the fault prediction data; and predicting the reason probability that each fault characteristic in the neighborhood similar samples is the fault reason.
The application also provides an electronic device comprising: the fault analysis method comprises a memory, a processor and a program of the fault analysis method stored on the memory and capable of running on the processor, wherein the program of the fault analysis method can realize the steps of the fault analysis method when being executed by the processor.
The present application also provides a computer-readable storage medium having stored thereon a program for implementing a failure analysis method, which when executed by a processor implements the steps of the failure analysis method as described above.
The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the fault analysis method as described above.
The application provides a fault analysis method, a device, an electronic device and a computer readable storage medium, the application predicts the reason probability that each fault feature related to the fault prediction data is a fault reason by acquiring the fault prediction data of the numerical control machine, and obtains a fault factor distribution set of the fault prediction data, so that the probability that each fault feature is likely to cause the fault of the numerical control machine can be determined, and then the prediction weight value of each fault feature in the fault factor distribution set is calculated by a preset contribution prediction algorithm, and further the influence degree of the fault feature on the fault decision result can be determined based on the prediction weight value, further, for any fault feature, the fault importance value of the fault feature is determined based on the prediction weight value and the reason probability, and the fault importance value of the fault feature can be characterized as the relevant degree that the fault feature causes the fault of the numerical control machine, namely the numerical control is likely to cause the fault of the numerical control machine based on the fault importance value of each fault feature, namely, the numerical control is assisted by the numerical control, and further, compared with the numerical control machine can be realized by the fact that the numerical control machine is only the reason that the fault sensor is not predicted by the fault reason of the numerical control machine is not being able to cause the fault cause by the fault control machine, and the maintenance efficiency of the numerical control machine tool is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic flow chart of a first embodiment of a fault analysis method according to the present application;
FIG. 2 is a schematic flow chart of a second embodiment of the fault analysis method of the present application;
FIG. 3 is a schematic flow chart of a third embodiment of a fault analysis method according to the present application;
FIG. 4 is a schematic diagram of an apparatus according to an embodiment of the fault analysis method of the present application;
fig. 5 is a schematic device structure diagram of a hardware operating environment related to a fault analysis method in an embodiment of the present application.
The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments.
Detailed Description
In order to make the above objects, features and advantages of the present application more comprehensible, the following description will make the technical solutions of the embodiments of the present application clear and complete with reference to the accompanying drawings of the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, based on the embodiments herein, which are within the scope of the protection of the present application, will be within the purview of one of ordinary skill in the art without the exercise of inventive faculty.
Some numerical control machine tools in general may employ a traditional machine learning or deep learning model to determine a fault prediction model of the numerical control machine tool, but the fault prediction model is generally regarded as a black box, and is difficult to interpret in the decision process of the fault prediction model, by constructing a LIME-SHAP (Local Interpretable Model-agnostic Explanations-SHapley Additive exPlanations, a local interpretable model-saprolip is added and interpreted), combining the Local Interpretable Model (LIME) with the SHAP, a more comprehensive, consistent and accurate interpretation result can be provided in the numerical control machine tool, specifically, the local interpretation model is determined by LIME to determine the cause probability of each fault feature related to the fault prediction data as a fault cause, the prediction contribution value of each fault feature is calculated by the SHAP to determine a prediction weight value, and the fault importance value is determined jointly based on the cause probability and the prediction weight value, so as to interpret the prediction result of the fault prediction model. By explaining the fault prediction model, a user can know the internal decision process of the model, whether the decision of the model is reasonable and correct can be verified, the decision of the fault prediction model is not based on improper bias, wrong data or improper training, and the reliability and verifiability of a fault decision result are improved. In addition, the method and the device realize transparency and interpretability of the prediction process of the fault prediction model, and help a user to quickly identify the wrong or inaccurate decision of the fault prediction model. If the decision process of the numerical control machine tool is not transparent, when the numerical control machine tool fails, the root cause of the failure is difficult to find out. The decision process of the fault prediction model can help the user to locate the problem and improve the problem after being transparent. And users are generally more receptive and use models that can interpret their decisions. If the user can understand the working principle and the decision process of the fault prediction model, the user is more likely to work together with the numerical control machine tool, and can better cope with different production conditions of the numerical control machine tool.
Example 1
Referring to fig. 1, an embodiment of the present application provides a fault analysis method, in a first embodiment of the fault analysis method of the present application, the fault analysis method includes:
step S10, obtaining fault prediction data of a numerical control machine tool, respectively predicting the reason probability that each fault feature related to the fault prediction data is a fault reason, and taking each fault feature and the reason probability corresponding to each fault feature together as a fault factor distribution set;
it should be noted that, the method of the embodiment of the present application may explain a fault prediction model of a numerically-controlled machine tool, where the fault prediction model is used to receive sensor data of the numerically-controlled machine tool to predict whether the numerically-controlled machine tool generates a fault, and the fault prediction data may be input data of the fault prediction model of the numerically-controlled machine tool, where the input data may be the sensor data of the numerically-controlled machine tool. The fault characteristics are determined based on fault prediction data, and the fault characteristics can be the fault prediction data or data related to the fault prediction data, wherein the fault prediction data is sensor data of the numerical control machine tool. The fault factor distribution set comprises all fault characteristics related to the fault prediction data and the reason probability corresponding to each fault characteristic.
Step S20, respectively determining the prediction weight value of each fault feature in the fault factor distribution set according to a preset contribution prediction algorithm, wherein the prediction weight value is characterized by the influence degree of the fault feature on a fault decision result, and the fault decision result is obtained based on the fault prediction of the numerical control machine tool;
the prediction contribution prediction algorithm is used for measuring the prediction contribution value of each fault feature to the model fault prediction of the numerical control machine, and further can determine a prediction weight value based on the prediction contribution value, wherein the prediction contribution prediction algorithm can be SHAP, the prediction weight value is characterized by the contribution duty ratio of the fault feature to the output of the fault prediction model, the prediction weight value is characterized by the influence degree of the fault feature to a fault decision result, and the fault decision result is obtained by carrying out fault prediction on the numerical control machine.
Further, step S20 includes:
s21, predicting the predicted contribution value of each fault feature in the fault factor distribution set according to the preset contribution prediction algorithm;
and step S22, respectively distributing a prediction weight value to each fault characteristic based on each prediction contribution value.
It should be noted that, each fault feature in the fault factor distribution set has a corresponding prediction contribution value, the prediction contribution value is obtained by calculating the fault feature based on a preset contribution prediction algorithm SHAP, the shape of the fault feature is obtained by calculating the shape of the fault feature, by way of example, any fault feature in the fault factor distribution set is generated to generate a feature combination including the fault feature and a feature combination not including the feature to determine a power set related to the fault feature, the power set includes all feature combinations related to the fault feature, the marginal contribution of each feature combination in the power set is calculated, the marginal contribution refers to the change of the output of the fault prediction model after the fault feature is added in the feature combination, the shape of the fault feature is obtained based on the marginal contribution of the fault feature in all possible feature combinations, and the shape is a computationally intensive task, especially when the feature quantity is large, in practical application, an approximation method or sampling technique is generally used to estimate the shape to reduce the computational complexity. Finally, the resulting Shapley values can be used to explain the relative importance of the fault signature to the model output, help understand the model's predictive process, and provide a quantified measure of the contribution of the fault signature. The method can be used for a decision process of an analysis model, and is particularly beneficial to identifying important fault characteristics in the field of complex numerical control machine tools.
For any fault feature, a preset weight value of the fault feature is determined based on the ratio of the predicted contribution value of the fault feature in the total contribution value.
And step S30, fusing the cause probability and the predicted weight value of the target fault feature for any target fault feature in the fault factor distribution set to obtain the fault importance value of the target fault feature.
It should be noted that, the fault importance value is characterized as the correlation degree of the fault feature causing the fault of the numerical control machine tool, the fault importance value is proportional to the correlation degree, and the fault importance value of the target fault feature is obtained by multiplying the cause probability of the target fault feature by the predicted weight value. In addition, in the numerically-controlled machine tool, the target fault characteristic can be any fault characteristic in the fault factor distribution set, and the technical content characterized by the embodiment of the application does not replace any part or system of the numerically-controlled machine tool, but provides a transparent and understandable decision support for the numerically-controlled machine tool.
According to the method, the fault prediction data of the numerical control machine tool are obtained, the reason probability that each fault feature related to the fault prediction data is a fault cause is predicted, and the fault factor distribution set of the fault prediction data is obtained, so that the probability that each fault feature possibly causes the numerical control machine tool to generate faults can be determined, further, the prediction weight value of each fault feature in the fault factor distribution set is calculated through a preset contribution prediction algorithm, the influence degree of the fault feature on a fault decision result can be determined based on the prediction weight value, further, for any fault feature, the fault importance value of the fault feature is jointly determined based on the prediction weight value and the reason probability, and the fault importance value of the fault feature is determined based on the prediction weight value and the reason probability.
Example two
Further, referring to fig. 2, in another embodiment of the present application, the same or similar content as the above embodiment may be referred to the above description, and will not be repeated herein. On the basis, the step of obtaining the failure prediction data of the numerical control machine tool and respectively predicting the reason probability that each failure feature related to the failure prediction data is the failure reason comprises the following steps:
step A10, obtaining the fault prediction data of the numerical control machine tool, wherein the fault prediction data is any input data of a fault prediction model corresponding to the numerical control machine tool;
step A20, inputting the fault prediction data into a local interpretation model, so as to disturb the fault prediction data based on a preset disturbance strategy by the local interpretation model to generate a neighborhood similar sample of the fault prediction data;
and step A30, predicting the reason probability that each fault characteristic in the neighborhood similar sample is the fault reason.
It should be noted that, any input data refers to sensor data input into a fault prediction model, a preset disturbance strategy refers to adding tiny disturbance around the fault prediction data, generating a neighborhood similar sample similar to but slightly different from a local interpretation model, the local interpretation model is determined based on LIME, and the embodiment of the application approximates a fault decision result of a black box model (fault prediction model) by using a local approximation model based on LIME. The local approximation model interprets the behavior of the model in the vicinity of the interpretation object by fitting a neighborhood similarity sample and corresponding fault decision results. SHAP uses Shapley values to assign a predictive weight to each fault signature. The local interpretation model may be trained based on a plurality of fault prediction data and a plurality of fault factor distribution sets. The fault prediction data may include, but is not limited to, tool temperature, vibration sensor data, cutting force, etc. of the numerically controlled machine tool, after adding a small disturbance around the fault prediction data, a neighborhood similar sample is generated, and data points similar to the fault prediction data are added in the neighborhood similar sample, so the fault feature related to the fault prediction data may be a fault feature in the neighborhood similar sample, and thus the fault feature may include, in addition to the feature in the fault prediction data, a feature different from but similar to the fault prediction data in the neighborhood similar sample, for example, the fault feature includes, but is not limited to: tool temperature, cutting depth associated with cutting force, and cutting speed and feed rate vibration force associated with vibration sensor data.
Illustratively, steps a10 through a30 include: inputting the fault prediction data into a local interpretation model, carrying out disturbance on the periphery of the fault prediction data based on a preset disturbance strategy through the local interpretation model, generating a neighborhood similar sample with the fault prediction data, and predicting the reason probability that each fault feature in the neighborhood similar sample is a fault reason to obtain a fault factor distribution set. These neighborhood similarity samples are used to interpret the behavior of the fault prediction model in the local approximation model. These neighborhood similarity samples are typically very similar to the original samples but slightly different data points to aid in understanding the prediction of the fault prediction model based on the fault prediction data. Both the fault importance and the local interpretation model are tools for interpreting the behavior of the fault prediction model, but their layers of interest are different. The feature importance value may tell the user which fault features are of higher importance to the fault prediction model, while the local interpretation model provides detailed information on how the fault prediction model makes decisions in case of a fault prediction based on the fault prediction data. By the two interpretation methods, a user (engineers and operators) can more comprehensively, consistently and accurately understand the working state and fault decision result of the numerical control machine tool system, thereby being beneficial to optimizing maintenance plans, equipment performance and production efficiency.
Further, the step of predicting the cause probability that each fault feature in the neighborhood similarity sample is the cause of the fault includes:
step B10, for any target fault feature in the neighborhood similarity sample, predicting the probability that the target fault feature is the fault cause independently, and obtaining the independent probability that the target fault feature is the fault cause;
step B20, predicting the probability that other fault characteristics in the neighborhood similarity sample affect the target fault characteristics to be the fault reasons, and obtaining the association probability of the target fault characteristics;
and step B30, the independent probability and the associated probability are used as the reason probability of the target fault characteristic.
It should be noted that, the probability of cause of each fault feature in the neighborhood similarity sample needs to be predicted, and each fault feature may be a cause of a fault of the numerically controlled machine tool, and a certain fault feature may be affected by other fault features to be a cause of a fault of the numerically controlled machine tool. The accuracy of the probability of predicting the cause can be improved by predicting the independent probability that the fault feature is the cause of the fault separately and by predicting the associated probability that the fault feature is affected by other fault features to be the fault feature. And predicting the cause probability of the target fault feature according to the local interpretation model for any target fault feature in the neighborhood similarity face-to-face model. The local interpretation model is trained in advance, and can be a linear regression model or a decision tree model, and the training process of the local interpretation model is as follows: determining a model to be trained, and determining a training sample, wherein the training sample comprises: the method comprises the steps of inputting a fault prediction sample and a fault factor distribution label into a model to be trained, predicting the cause probability of each fault feature related to the fault prediction sample, obtaining a fault factor training set, further calculating training model loss based on the fault factor distribution label and the fault factor training set, wherein the training model loss can be set to be the distance between the fault factor distribution label and the fault factor training set, and the like, further judging whether the training model loss is converged or not, taking the model to be trained as a local interpretation model if the training model loss is converged, and re-obtaining a new training sample to perform training optimization on the model to be trained again if the training model loss is not converged until the training model loss is converged.
Further, since the output of the fault prediction model is usually a complex combination result model which may have nonlinear relation, interaction and other complex properties, the prediction contribution value of a single fault feature cannot directly reflect the importance of the fault feature to the fault prediction model, so in order to comprehensively consider the importance of the fault feature to the fault prediction model, the reason probability of the local interpretation model output needs to be combined with the prediction contribution value to comprehensively consider how the influence of the fault feature changes along with the change of the input condition, so as to more comprehensively understand the importance of the feature to the overall model, and help the user understand the influence of the feature to the overall model and how they interact under different input conditions. This helps to better understand and interpret the behavior of the fault prediction model.
Wherein after the step of fusing the cause probability of the fault feature and the predicted weight value for any fault feature in the fault factor distribution set to obtain a fault importance value of the fault feature, the fault analysis method further includes:
and step C10, respectively carrying out visual display on the cause probability in the fault factor distribution set, the predicted weight value and the fault importance value of each fault feature in the fault factor distribution set according to preset display conditions.
It should be noted that, the preset display condition is characterized by the reason probability of each fault feature, the fault importance value and the display form corresponding to the prediction weight value, the preset display condition may be in the form of a chart or a graphic, etc., the icon form may be a histogram, etc., and by way of example, the reason probability corresponding to each fault feature is displayed according to the form of the histogram, each fault feature corresponds to a columnar bar of the reason probability, the prediction weight value corresponding to each fault feature is displayed according to the form of the histogram in a more visual way, each fault feature corresponds to a columnar bar of the prediction weight value, the fault importance value corresponding to each fault feature is displayed according to the form of the histogram, each fault feature corresponds to a columnar bar of the fault importance value, the reason probability, the prediction weight value and the color of the columnar bar corresponding to the fault importance value are different, and the reason probability in the fault factor distribution set, the prediction weight value and the fault importance value of each fault feature in the machine tool distribution set may be displayed on the man-machine interaction interface of the numerical control based on the probability and the human-machine interaction of the fault factor set. According to the embodiment of the invention, the reason probability, the fault importance value and the prediction weight value of each fault feature are visually presented, so that a user can more easily understand the fault decision result output by the fault prediction model.
Example III
Further, referring to fig. 3, in another embodiment of the present application, the same or similar content as the above embodiment may be referred to the above description, and will not be repeated. On the basis, after the step of fusing the cause probability and the predicted weight value of any target fault feature in the fault factor distribution set to obtain the fault importance value of the target fault feature, the fault analysis method further comprises the following steps:
step D10, obtaining a fault decision result output by a fault prediction model corresponding to the numerical control machine tool;
step D20, taking the fault prediction data as a decision starting point and the fault decision result as a decision end point of a fault decision path;
step D30, selecting a fault feature with the cause probability larger than a first decision threshold as a first decision point, selecting a fault feature with the predictive weight value larger than a second decision threshold as a second decision point, and selecting a fault feature with the fault importance value larger than a third decision threshold as a third decision point from all fault features in the fault factor distribution set;
and D40, sequentially connecting the decision starting point, the first decision point, the second decision point, the third decision point and the decision end point to obtain a fault decision path of the fault prediction model.
The fault decision result may be a prediction result output by the fault prediction model, the fault decision result may be a fault type of a fault generated by the numerical control machine tool, the decision starting point may be initial data of the fault prediction model for performing fault prediction, the decision end point may be a result obtained after the fault prediction model performs fault prediction, the first decision threshold, the second decision threshold and the third decision threshold may be determined based on actual conditions, for example, the first decision threshold may be an average value of cause probabilities of each fault feature, may be a value with highest cause probability of each fault feature, may also be a value with the cause probabilities of the third or fourth and the like selected as the first decision threshold after the cause probabilities are ordered from large to small, the second decision threshold may be an average value of predicted weight values of each fault feature, may also be a value with highest predicted weight value in each fault feature, and the third decision threshold may be an average value of important value of fault feature of each fault feature, or a value with highest fault importance value in each fault feature, and the like. The first decision point, the second decision point and the third decision point may all include one or more fault features, the first decision point displaying a fault feature and a cause probability of the fault feature that are greater than the first decision threshold, the second decision point displaying a fault feature and a predicted weight value of the fault feature that are greater than the second decision threshold, the third decision point displaying a fault feature and a fault importance value of the fault feature that are greater than the third decision threshold. The fault decision path may be presented to the user in the form of a graphic. The first decision point, the second decision point, the third decision point and the decision end point are connected end to end in sequence to obtain a fault decision path of the fault prediction model. The fault decision path in the embodiment of the application can describe the process how the fault prediction model goes from input data to a fault decision result, which is helpful for a user to identify the decision logic of the fault prediction model and understand that the fault prediction model outputs the fault decision result.
The fault analysis method further includes, after the step of obtaining the fault importance value of the target fault feature by fusing the cause probability and the prediction weight value of the target fault feature for any target fault feature in the fault factor distribution set:
step X10, selecting the fault feature with the highest fault importance value from the fault features as a query object;
and step X20, searching historical data matched with the query object in a preset operation database of the numerical control machine tool, so as to analyze the historical data and determine historical fault signs of the query object.
It should be noted that, the user may check the cause probability corresponding to the fault feature, the prediction weight value and the fault importance value of each fault feature in the fault factor distribution set on the man-machine interaction interface of the numerically-controlled machine tool, so that the user may know the influence degree of each fault feature on the prediction result of the fault prediction model based on each fault importance value, and the fault importance value may also be characterized as the importance degree of the fault feature on the decision of the fault prediction model, so after determining the fault importance value corresponding to each fault feature, the fault feature with the highest fault importance value may be selected from each fault feature as the query object, and then the historical data corresponding to the query object may be searched, so that the historical fault sign is the data that may affect the numerically-controlled machine tool to generate the fault based on the historical fault evidence may be searched more specifically through the fault importance value. For example, if the fault importance value of the vibration data is high, the history data of the vibration data of the numerical control machine tool may be queried for signs of abnormality or fault. The fault importance value based on the fault characteristics may also assist the user in making a presumption regarding the cause of the failure of the numerical control machine. By knowing which fault signatures are most critical to the decision of the fault prediction model, assumptions can be made from these fault signatures and further explore possible causes. For example, if the failure importance value of vibration data is relatively high, it can be presumed that the vibration problem may be related to the failure of the numerical control machine.
Example IV
Referring to fig. 4, an embodiment of the present application further provides a fault analysis apparatus, including:
the cause probability determining module 10 is configured to obtain failure prediction data of a numerically-controlled machine tool, respectively predict cause probabilities that failure features related to the failure prediction data are failure causes, and jointly use the failure features and the cause probabilities corresponding to the failure features as a failure factor distribution set;
the weight value determining module 20 is configured to determine, according to a preset contribution prediction algorithm, a predicted weight value of each fault feature in the fault factor distribution set, where the predicted weight value is characterized by an influence degree of the fault feature on a fault decision result, and the fault decision result is obtained based on performing fault prediction on the numerical control machine tool;
and the fault importance value determining module 30 is configured to fuse, for any target fault feature in the fault factor distribution set, a cause probability and a prediction weight value of the target fault feature, and obtain a fault importance value of the target fault feature.
Optionally, the cause probability determining module 10 is further configured to:
acquiring the fault prediction data of the numerical control machine, wherein the fault prediction data is any input data of a fault prediction model corresponding to the numerical control machine;
Inputting the fault prediction data into a local interpretation model, and disturbing the fault prediction data based on a preset disturbance strategy through the local interpretation model to generate a neighborhood similarity sample of the fault prediction data;
and predicting the reason probability that each fault characteristic in the neighborhood similar samples is the fault reason.
Optionally, the cause probability determining module 10 is further configured to:
for any target fault feature in the neighborhood similarity sample, individually predicting the probability that the target fault feature is the fault cause to obtain the independent probability that the target fault feature is the fault cause;
predicting the probability that other fault characteristics in the neighborhood similarity sample affect the target fault characteristics to be the fault reasons, and obtaining the association probability of the target fault characteristics;
and the independent probability and the associated probability are used as the reason probability of the target fault characteristic. Optionally, the weight value determining module 20 is further configured to:
predicting the predicted contribution value of each fault feature in the fault factor distribution set according to the preset contribution prediction algorithm;
and respectively distributing a prediction weight value to each fault characteristic based on each prediction contribution value.
Optionally, the fault importance determination module 30 is further configured to:
and respectively carrying out visual display on the cause probability in the fault factor distribution set, the predicted weight value and the fault importance value of each fault feature in the fault factor distribution set according to preset display conditions.
Optionally, the fault importance determination module 30 is further configured to:
obtaining a fault decision result output by a fault prediction model corresponding to the numerical control machine tool;
taking the fault prediction data as a decision starting point and taking the fault decision result as a decision end point of a fault decision path;
selecting a fault feature with the cause probability larger than a first decision threshold from the fault features in the fault factor distribution set as a first decision point, selecting a fault feature with the prediction weight value larger than a second decision threshold as a second decision point, and selecting a fault feature with the fault importance value larger than a third decision threshold as a third decision point;
and sequentially connecting the decision starting point, the first decision point, the second decision point, the third decision point and the decision end point to obtain a fault decision path of the fault prediction model.
Optionally, the fault importance determination module 30 is further configured to:
selecting the fault feature with the highest fault importance value from the fault features as a query object;
searching historical data matched with the query object in a preset operation database of the numerical control machine tool, and analyzing the historical data to determine historical fault signs of the query object.
The fault analysis device provided by the application adopts the fault analysis method in the embodiment, and aims to solve the technical problem of low maintenance efficiency of the numerical control machine caused by difficulty in explaining the fault of the numerical control machine. Compared with the prior art, the fault analysis method provided by the embodiment of the present application has the same beneficial effects as the fault analysis method provided by the above embodiment, and other technical features in the fault analysis device are the same as the features disclosed by the method of the above embodiment, which are not described in detail herein.
Example five
The embodiment of the application provides an electronic device, which may be a playing device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the fault analysis method of the above embodiments.
Referring now to fig. 5, a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistant, personal digital assistants), PADs (portable Android device, tablet computers), PMPs (Portable Media Player, portable multimedia players), vehicle terminals (e.g., car navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 5 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 5, the electronic apparatus may include a processing device 1001 (e.g., a central processor, a graphics processor, or the like) that can perform various appropriate actions and processes according to a program stored in a ROM (Read-Only Memory) 1002 or a program loaded from a storage device 1003 into a RAM (Random Access Memory ) 1004. In the RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, the ROM1002, and the RAM1004 are connected to each other by a bus 1005. An input/output (I/O) interface 1006 is also connected to the bus.
In general, the following systems may be connected to the I/O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, tachometer, gyroscope, and the like; an output device 1008 including, for example, an LCD (Liquid Crystal Display ), a speaker, a vibrator, and the like; storage device 1003 including, for example, a magnetic tape, a hard disk, and the like; and communication means 1009. The communication means may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. While electronic devices having various systems are shown in the figures, it should be understood that not all of the illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through a communication system, or installed from a storage system, or installed from ROM. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by a processing system.
The electronic equipment provided by the application adopts the fault analysis method in the first embodiment to solve the technical problem that the maintenance efficiency of the numerical control machine tool is low because the fault of the numerical control machine tool is difficult to explain. Compared with the prior art, the beneficial effects of the product flow data distribution provided by the embodiment of the present application are the same as those of the fault analysis method provided by the above embodiment, and other technical features of the fault analysis device are the same as those disclosed by the method of the above embodiment, which are not described in detail herein.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the description of the above embodiments, particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Example six
The present embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon for performing the fault analysis method in the first embodiment described above.
The computer readable storage medium provided in the embodiments of the present application may be, for example, a usb disk, but is not limited to, an apparatus, or a device of electronic, magnetic, optical, electromagnetic, infrared, or semiconductor, or a combination of any of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable EPROM (Electrical Programmable Read Only Memory, read-only memory) or flash memory, an optical fiber, a portable compact disc CD-ROM (compact disc read-only memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this embodiment, the computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution apparatus, device, or apparatus. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The above-described computer-readable storage medium may be contained in an electronic device; or may exist alone without being assembled into an electronic device.
The computer-readable storage medium carries one or more programs that, when executed by an electronic device, cause the electronic device to: acquiring fault prediction data of a numerical control machine tool, respectively predicting the reason probability that each fault feature related to the fault prediction data is a fault reason, and taking each fault feature and the reason probability corresponding to each fault feature together as a fault factor distribution set; according to a preset contribution prediction algorithm, respectively determining a prediction weight value of each fault feature in the fault factor distribution set, wherein the prediction weight value is characterized by the influence degree of the fault feature on a fault decision result, and the fault decision result is obtained based on the fault prediction of the numerical control machine tool; and fusing the cause probability of the target fault feature and the prediction weight value for any target fault feature in the fault factor distribution set to obtain a fault importance value of the target fault feature, wherein the step of obtaining the fault prediction data of the numerical control machine tool and respectively predicting the cause probability of each fault feature related to the fault prediction data as a fault cause comprises the following steps: acquiring the fault prediction data of the numerical control machine, wherein the fault prediction data is any input data of a fault prediction model corresponding to the numerical control machine; inputting the fault prediction data into a local interpretation model, and disturbing the fault prediction data based on a preset disturbance strategy through the local interpretation model to generate a neighborhood similarity sample of the fault prediction data; and predicting the reason probability that each fault characteristic in the neighborhood similar samples is the fault reason.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a LAN (local area network ) or WAN (Wide Area Network, wide area network), or it may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of devices, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based devices which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented in software or hardware. Wherein the name of the module does not constitute a limitation of the unit itself in some cases.
The computer readable storage medium provided by the application stores computer readable program instructions for executing the fault analysis method, and aims to solve the technical problem of low maintenance efficiency of the numerical control machine caused by difficulty in explaining faults of the numerical control machine. Compared with the prior art, the beneficial effects of the computer readable storage medium provided by the embodiment of the present application are the same as those of the fault analysis method provided by the above embodiment, and are not described herein.
Example seven
The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the fault analysis method as described above.
The computer program product aims at solving the technical problem that the maintenance efficiency of the numerical control machine tool is low because the failure of the numerical control machine tool is difficult to explain. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the fault analysis method provided by the above embodiment, and are not described herein.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims.
Claims (9)
1. A fault analysis method, the fault analysis method comprising:
acquiring fault prediction data of a numerical control machine tool, respectively predicting the reason probability that each fault feature related to the fault prediction data is a fault reason, and taking each fault feature and the reason probability corresponding to each fault feature together as a fault factor distribution set;
according to a preset contribution prediction algorithm, respectively determining a prediction weight value of each fault feature in the fault factor distribution set, wherein the prediction weight value is characterized by the influence degree of the fault feature on a fault decision result, and the fault decision result is obtained based on the fault prediction of the numerical control machine tool;
fusing the cause probability and the predicted weight value of any target fault feature in the fault factor distribution set to obtain a fault importance value of the target fault feature;
The step of obtaining the failure prediction data of the numerical control machine tool, and predicting the reason probability that each failure feature related to the failure prediction data is a failure reason respectively comprises the following steps:
acquiring the fault prediction data of the numerical control machine, wherein the fault prediction data is any input data of a fault prediction model corresponding to the numerical control machine;
inputting the fault prediction data into a local interpretation model, and disturbing the fault prediction data based on a preset disturbance strategy through the local interpretation model to generate a neighborhood similarity sample of the fault prediction data;
and predicting the reason probability that each fault characteristic in the neighborhood similar samples is the fault reason.
2. The method of claim 1, wherein predicting the cause probability that each of the fault features in the neighborhood similarity samples is the cause of the fault comprises:
for any target fault feature in the neighborhood similarity sample, individually predicting the probability that the target fault feature is the fault cause to obtain the independent probability that the target fault feature is the fault cause;
predicting the probability that other fault characteristics in the neighborhood similarity sample affect the target fault characteristics to be the fault reasons, and obtaining the association probability of the target fault characteristics;
And the independent probability and the associated probability are used as the reason probability of the target fault characteristic.
3. The fault analysis method of claim 1, wherein the step of determining the predicted weight value of each fault feature in the fault factor distribution set according to a preset contribution prediction algorithm includes:
predicting the predicted contribution value of each fault feature in the fault factor distribution set according to the preset contribution prediction algorithm;
and respectively distributing a prediction weight value to each fault characteristic based on each prediction contribution value.
4. The fault analysis method of claim 1, wherein after the step of fusing the probability of cause and the predicted weight value of the target fault feature for any target fault feature in the fault factor distribution set to obtain a fault importance value of the target fault feature, the fault analysis method further comprises:
and respectively carrying out visual display on the cause probability in the fault factor distribution set, the predicted weight value and the fault importance value of each fault feature in the fault factor distribution set according to preset display conditions.
5. The fault analysis method according to claim 1, wherein after the step of fusing the cause probability and the predicted weight value of the target fault feature for any target fault feature in the fault factor distribution set to obtain the fault importance value of the target fault feature, the fault analysis method further comprises:
selecting the fault feature with the highest fault importance value from the fault features as a query object;
searching historical data matched with the query object in a preset operation database of the numerical control machine tool, and analyzing the historical data to determine historical fault signs of the query object.
6. The fault analysis method according to any one of claims 1 to 5, wherein after the step of fusing the cause probability and the predictive weight value of the target fault feature to obtain the fault importance value of the target fault feature for any one target fault feature in the fault factor distribution set, the fault analysis method further comprises:
obtaining a fault decision result output by a fault prediction model corresponding to the numerical control machine tool;
taking the fault prediction data as a decision starting point and taking the fault decision result as a decision end point of a fault decision path;
Selecting a fault feature with the cause probability larger than a first decision threshold from the fault features in the fault factor distribution set as a first decision point, selecting a fault feature with the prediction weight value larger than a second decision threshold as a second decision point, and selecting a fault feature with the fault importance value larger than a third decision threshold as a third decision point;
and sequentially connecting the decision starting point, the first decision point, the second decision point, the third decision point and the decision end point to obtain a fault decision path of the fault prediction model.
7. A fault analysis device, characterized in that the fault analysis device comprises:
the cause probability determining module is used for acquiring fault prediction data of the numerical control machine tool, respectively predicting the cause probability that each fault feature related to the fault prediction data is a fault cause, and taking each fault feature and the cause probability corresponding to each fault feature together as a fault factor distribution set;
the weight value determining module is used for respectively determining the predicted weight value of each fault feature in the fault factor distribution set according to a preset contribution prediction algorithm, wherein the predicted weight value is characterized by the influence degree of the fault feature on a fault decision result, and the fault decision result is obtained based on the fault prediction of the numerical control machine tool;
The fault importance value determining module is used for fusing the cause probability and the prediction weight value of any target fault feature in the fault factor distribution set to obtain the fault importance value of the target fault feature;
the cause probability determining module is further used for obtaining the fault prediction data of the numerical control machine tool, wherein the fault prediction data is any input data of a fault prediction model corresponding to the numerical control machine tool; inputting the fault prediction data into a local interpretation model, and disturbing the fault prediction data based on a preset disturbance strategy through the local interpretation model to generate a neighborhood similarity sample of the fault prediction data; and predicting the reason probability that each fault characteristic in the neighborhood similar samples is the fault reason.
8. An electronic device, the electronic device comprising:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the fault analysis method of any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program for realizing the failure analysis method, the program for realizing the failure analysis method being executed by a processor to realize the steps of the failure analysis method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311340560.7A CN117102950B (en) | 2023-10-17 | 2023-10-17 | Fault analysis method, device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311340560.7A CN117102950B (en) | 2023-10-17 | 2023-10-17 | Fault analysis method, device, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117102950A CN117102950A (en) | 2023-11-24 |
| CN117102950B true CN117102950B (en) | 2023-12-22 |
Family
ID=88809336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311340560.7A Active CN117102950B (en) | 2023-10-17 | 2023-10-17 | Fault analysis method, device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117102950B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07156044A (en) * | 1993-11-30 | 1995-06-20 | Nippei Toyama Corp | Trouble prediction system of machine tool |
| CN103064340A (en) * | 2011-10-21 | 2013-04-24 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
| CN106503813A (en) * | 2016-10-27 | 2017-03-15 | 清华大学 | Prospective maintenance decision-making technique and system based on hoisting equipment working condition |
| CN111147306A (en) * | 2019-12-30 | 2020-05-12 | 深圳猛犸电动科技有限公司 | Fault analysis method and device of Internet of things equipment and Internet of things platform |
| CN115935243A (en) * | 2023-03-01 | 2023-04-07 | 武汉同创万智数字科技有限公司 | Fault analysis method based on data processing |
| CN116184988A (en) * | 2023-05-04 | 2023-05-30 | 中科航迈数控软件(深圳)有限公司 | Multi-mode data-based fault prediction method, device, equipment and storage medium |
| CN116226676A (en) * | 2023-05-08 | 2023-06-06 | 中科航迈数控软件(深圳)有限公司 | Machine tool fault prediction model generation method suitable for extreme environment and related equipment |
| CN116628611A (en) * | 2023-05-23 | 2023-08-22 | 西南科技大学 | Visual analysis method and system for association of abnormal modes of machine tool operation data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110106734A1 (en) * | 2009-04-24 | 2011-05-05 | Terrance Boult | System and appartus for failure prediction and fusion in classification and recognition |
-
2023
- 2023-10-17 CN CN202311340560.7A patent/CN117102950B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07156044A (en) * | 1993-11-30 | 1995-06-20 | Nippei Toyama Corp | Trouble prediction system of machine tool |
| CN103064340A (en) * | 2011-10-21 | 2013-04-24 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
| CN106503813A (en) * | 2016-10-27 | 2017-03-15 | 清华大学 | Prospective maintenance decision-making technique and system based on hoisting equipment working condition |
| CN111147306A (en) * | 2019-12-30 | 2020-05-12 | 深圳猛犸电动科技有限公司 | Fault analysis method and device of Internet of things equipment and Internet of things platform |
| CN115935243A (en) * | 2023-03-01 | 2023-04-07 | 武汉同创万智数字科技有限公司 | Fault analysis method based on data processing |
| CN116184988A (en) * | 2023-05-04 | 2023-05-30 | 中科航迈数控软件(深圳)有限公司 | Multi-mode data-based fault prediction method, device, equipment and storage medium |
| CN116226676A (en) * | 2023-05-08 | 2023-06-06 | 中科航迈数控软件(深圳)有限公司 | Machine tool fault prediction model generation method suitable for extreme environment and related equipment |
| CN116628611A (en) * | 2023-05-23 | 2023-08-22 | 西南科技大学 | Visual analysis method and system for association of abnormal modes of machine tool operation data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117102950A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4109347A2 (en) | Method for processing multimodal data using neural network, device, and medium | |
| US20210192376A1 (en) | Automated, progressive explanations of machine learning results | |
| CN116776289B (en) | Numerical control machine tool processing method, device, electronic equipment and readable storage medium | |
| CN116277040B (en) | Mechanical arm vibration suppression method, device, equipment and medium based on deep learning | |
| EP3879754A1 (en) | Network traffic prediction method, device, and electronic device | |
| JP7545461B2 (en) | DATA PROCESSING METHOD, DATA PROCESSING APPARATUS, ELECTRONIC DEVICE, STORAGE MEDIUM, AND COMPUTER PROGRAM | |
| CN108595343A (en) | The test method and device of application program | |
| EP3502872A1 (en) | Pipeline task verification for a data processing platform | |
| CN113076358A (en) | Report generation method, device, equipment and storage medium | |
| CN117093477A (en) | Software quality assessment method and device, computer equipment and storage medium | |
| CN111680116A (en) | Map-based position information display method, system, medium, and electronic device | |
| CN114186090A (en) | Intelligent quality inspection method and system for image annotation data | |
| Wang et al. | Traffic Performance GPT (TP-GPT): Real-Time Data Informed Intelligent ChatBot for Transportation Surveillance and Management | |
| CN117102950B (en) | Fault analysis method, device, electronic equipment and computer readable storage medium | |
| CN117709715A (en) | Tunnel engineering construction risk assessment method, system, terminal and medium | |
| US20140089234A1 (en) | Interactive visualization of multi-objective optimization | |
| CN116126655A (en) | Coal mining machine fault prompting method, system, storage medium and equipment | |
| CN115563810A (en) | Lead screw service life prediction method and device, electronic equipment and readable storage medium | |
| CN114461499A (en) | Abnormal information detection model construction method and gray scale environment abnormal detection method | |
| CN104081399A (en) | Wire harness analysis device, wire harness analysis method, and wire harness analysis program | |
| WO2021178402A1 (en) | Automated design tool | |
| KR101997012B1 (en) | Appratus and method for estimating resource of program based on automata state complexity | |
| CN118465533B (en) | Motor power test system | |
| CN116451792B (en) | Method, system, device and storage medium for solving large-scale fault prediction problem | |
| US20230237249A1 (en) | Method and system for generating an automation engineering project in a technical installation using multidisciplinary approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |