CN111783856A - Equipment fault auxiliary diagnosis method and system for manufacturing industry - Google Patents
Equipment fault auxiliary diagnosis method and system for manufacturing industry Download PDFInfo
- Publication number
- CN111783856A CN111783856A CN202010559907.7A CN202010559907A CN111783856A CN 111783856 A CN111783856 A CN 111783856A CN 202010559907 A CN202010559907 A CN 202010559907A CN 111783856 A CN111783856 A CN 111783856A
- Authority
- CN
- China
- Prior art keywords
- equipment
- value
- diagnosed
- feature
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 34
- 238000003745 diagnosis Methods 0.000 title claims abstract description 30
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000007477 logistic regression Methods 0.000 claims description 37
- 238000012549 training Methods 0.000 claims description 29
- 238000009826 distribution Methods 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 12
- 238000013024 troubleshooting Methods 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000011835 investigation Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 15
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000002159 abnormal effect Effects 0.000 description 7
- 230000005856 abnormality Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Mathematical Optimization (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a manufacturing industry-oriented equipment fault auxiliary diagnosis method and a system, wherein the method comprises the following processes: generating a predicted value of the running state of the equipment to be diagnosed; monitoring the real value of the running state of the equipment to be diagnosed in real time; and judging whether the equipment to be diagnosed has faults or not based on the difference value between the predicted value and the true value. The system comprises but is not limited to a state prediction module, a state monitoring module and a fault judgment module; the state prediction module is used for generating a predicted value of the running state of the equipment to be diagnosed, the state monitoring module is used for monitoring a true value of the running state of the equipment to be diagnosed in real time, and the fault judgment module is used for judging whether the equipment to be diagnosed is in fault or not based on a difference value of the predicted value and the true value. The invention can effectively assist maintenance personnel to judge whether the monitored equipment has faults, has the advantages of short fault diagnosis time, low labor cost, small dependence on personnel experience and technical level and the like, and can further improve the operation and maintenance efficiency and the production benefit of the equipment in the manufacturing industry.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a manufacturing industry-oriented equipment fault auxiliary diagnosis method and system.
Background
At present, more and more manufacturing enterprises have started to implement digital, automatic and intelligent transformation, so as to improve the manufacturing efficiency and quality, and reduce the operation cost and labor cost. Therefore, the manufacturing system with high stability and high reliability can be an important guarantee for enterprises to improve the production efficiency.
The equipment fault diagnosis of the manufacturing enterprises usually depends on manual inspection maintenance, inspection personnel need to regularly inspect machines every day, find faults and report the faults to maintenance personnel, and the maintenance personnel take different measures according to the size of the faults, feed the faults back to a main task of a workshop, report the faults to a plant manager and the like. Obviously, the whole process of the manual inspection mode consumes a large amount of human resources, the labor cost is high, the requirements on the experience and the technical level of inspection personnel are high, the dependency exists, the equipment diagnosis time is long, the overhaul period is short, the maintenance efficiency is low, and the running condition of the equipment cannot be tracked in real time, so that the stability and the reliability of a manufacturing system cannot be ensured by the conventional manual inspection maintenance scheme, and the digital, automatic and intelligent reconstruction of a manufacturing enterprise cannot be realized.
Although some intelligent diagnosis schemes for equipment faults are proposed, the problems of high labor cost, high dependence on experience and technical level of personnel, long equipment fault diagnosis time and the like still exist due to the technical limitation of the intelligent diagnosis schemes.
Disclosure of Invention
The invention provides a manufacturing industry-oriented equipment fault auxiliary diagnosis method and system in order to solve the problems of high labor cost, long fault diagnosis time, excessive dependence on personnel and the like in the existing fault diagnosis scheme of manufacturing industry equipment.
In order to achieve the technical purpose, the invention specifically discloses a manufacturing industry-oriented equipment fault auxiliary diagnosis method, which comprises the following processes: generating a predicted value of the running state of the equipment to be diagnosed; monitoring the real value of the running state of the equipment to be diagnosed in real time; and judging whether the equipment to be diagnosed is in fault or not based on the difference value between the predicted value and the true value.
Further, the process of generating the predicted value of the operating state of the device to be diagnosed includes, but is not limited to, the following processes: collecting historical real-time operation data of equipment to be diagnosed at a set frequency; counting the distribution characteristics of the historical real-time operation data within a first preset time length, and generating the time sequence characteristics of the historical real-time operation data within a second preset time length; training a feature classifier by using the distribution features to predict a first feature value of a future operating condition through the feature classifier; training a feature regressor by using the time sequence features to predict a second feature value of a future operating condition through the feature regressor; and performing feature fusion on the first feature value and the second feature value to generate the predicted value.
Further, the process of determining whether the device to be diagnosed is faulty includes, but is not limited to, the following processes: taking the difference value between the predicted value and the true value as the input of a logistic regression classifier, and judging whether the equipment to be diagnosed is in fault or not according to the output of the logistic regression classifier; the training set of the logistic regression classifier includes labeled sample training data.
Further, the method further comprises: and when the equipment to be diagnosed is judged to be in fault, calculating the characteristic weight of each real value corresponding to the current fault, and then providing visual investigation reference data for a user according to the characteristic weight and each real value.
Further, the time sequence characteristic is generated by adopting a time sequence sliding window mode, and the duration of the sliding window is less than or equal to the second preset duration.
Further, the distribution characteristic is a low-frequency characteristic, and the timing characteristic is a high-frequency characteristic; and the first preset duration is longer than the second preset duration.
Further, the logistic regression classifier is trained by:
s1, classifying the samples of the current active learning sample set by using a logistic regression classifier to obtain the classification result of the samples in each active learning sample set;
s2, manually marking the samples with the classification result probability in a preset interval, and adding the marked samples into a training set;
s3, using all the marked training samples to adjust the parameters of the current logistic regression classifier so as to update the current logistic regression classifier;
s4, verifying whether the classification accuracy of the current logistic regression classifier reaches a set value or whether no unmarked sample exists in the active learning sample set, ending iteration, otherwise, executing the steps S1-S4 in a circulating mode.
In order to achieve the technical purpose, the invention also discloses a manufacturing industry-oriented equipment fault auxiliary diagnosis system, which comprises but is not limited to a state prediction module, a state monitoring module and a fault judgment module. The state prediction module is used for generating a predicted value of the running state of the equipment to be diagnosed; the state monitoring module is used for monitoring the real value of the running state of the equipment to be diagnosed in real time; and the fault judgment module is used for judging whether the equipment to be diagnosed has faults or not based on the difference value between the predicted value and the true value.
Further, the state prediction module includes, but is not limited to, a data acquisition unit, a feature extraction unit, a preliminary prediction unit, and a feature fusion unit. The data acquisition unit is used for acquiring historical real-time operation data of the equipment to be diagnosed at a set frequency; the characteristic extraction unit is used for counting the distribution characteristics of the historical real-time operation data in a first preset time length and generating the time sequence characteristics of the historical real-time operation data in a second preset time length; a preliminary prediction unit, configured to train a feature classifier using the distribution features to predict a first feature value of a future operating condition by the feature classifier; and a second feature value for training a feature regressor using the timing features to predict future operating conditions by the feature regressor; and the feature fusion unit is used for performing feature fusion on the first feature value and the second feature value to generate the predicted value.
Further, the fault judgment module is configured to use a difference value between the predicted value and the true value as an input of a logistic regression classifier, and judge whether the device to be diagnosed is faulty according to an output of the logistic regression classifier; the training set of the logistic regression classifier includes labeled sample training data.
Further, the system also comprises a troubleshooting reference module. The troubleshooting reference module is used for calculating the feature weight of each real value corresponding to the current fault when the equipment to be diagnosed fails, and providing visual troubleshooting reference data for a user according to the feature weight and each real value.
The invention has the beneficial effects that: the invention can effectively assist maintenance personnel to judge whether the monitored equipment has faults, has the advantages of short fault diagnosis time, low labor cost, small dependence on personnel experience and technical level and the like, and can further improve the operation and maintenance efficiency and the production benefit of the equipment in the manufacturing industry.
Aiming at the monitoring of relevant equipment in the manufacturing industry, the method can monitor the running condition of the equipment in real time and efficiently diagnose the fault reason of the equipment, and can display the running deviation of the equipment in real time so as to ensure the normal running of a manufacturing system. Moreover, the equipment state information acquired by the method has continuity and higher data mining value.
In addition, aiming at the problem that manufacturing enterprises are difficult to manually arrange and label abnormal data of equipment by acquiring a large amount of real abnormal data, the invention provides an abnormal detection scheme based on active learning, and the labor cost of traditional manual labeling is obviously reduced.
Drawings
Fig. 1 shows a schematic flow diagram of a method for auxiliary diagnosis of a device fault for the manufacturing industry.
FIG. 2 is a schematic diagram illustrating the operation of a manufacturing-oriented equipment failure auxiliary diagnostic system according to some embodiments of the present invention.
Detailed Description
The invention provides a method and a system for auxiliary diagnosis of equipment failure in manufacturing industry, which are explained and explained in detail in the following with reference to the attached drawings.
The first embodiment is as follows:
as shown in fig. 1 and 2, to solve at least one problem in the prior art, the present embodiment may provide a method for auxiliary diagnosis of equipment failure for manufacturing industry, which can implement real-time monitoring of the operation condition of equipment and efficient auxiliary diagnosis of equipment failure. The method includes, but is not limited to, the following processes.
First, historical real-time operating data of the equipment to be diagnosed is collected at a set frequency. The set frequency can be set according to actual needs, such as 0.1Hz, and the present embodiment can acquire real-time data of different sensors of the device every 10s according to device differences. For example, various sensors may be used to collect corresponding real-time operating data of the machine, including but not limited to pressure, temperature, rotational speed, etc., and pressure sensors may be used to collect pressure data, temperature sensors may be used to collect temperature, etc.
Secondly, the invention obtains corresponding time sequence characteristics and distribution characteristics according to the collected real-time operation data of the equipment so as to analyze and process the frequency division rate of the operation data of the equipment. The processing of the multi-frequency timing characteristics may be performed simultaneously, as described in more detail below.
And counting the distribution characteristics of the historical real-time operation data within a first preset time length, for example, counting and analyzing the distribution ranges of different sensor data values of different equipment according to daily frequency, and then distributing the equipment values into different characteristic buckets according to the ranges to prepare data for low-frequency characteristic prediction. That is, the distribution characteristic of the present embodiment is a low frequency characteristic, and the first preset time period may be one day, for example. Examples are as follows: to the equipment on a certain small-size part production line, its rotational speed is the part production number divided by the production time, and its rotational speed value interval is roughly at [ 0/minute, 60/minute ], and this embodiment can divide it into three characteristic buckets: less than 10/min, between 10/min and 30/min, more than 30/min.
And generating the time sequence characteristic of the historical real-time operation data within a second preset time length, wherein the first preset time length is often longer than the second preset time length. And generating the time sequence characteristic by adopting a time sequence sliding window mode, wherein the duration of the sliding window can be less than or equal to a second preset duration. In the embodiment, the sliding window takes 10 minutes as the duration of the sliding window to cut the data into sequences of time windows, preferably, the characteristic mean value per minute is taken as the characteristic value of the minute, and finally, the characteristic values [ w ] of 10 sequences in 10 minutes are obtained1,w2,…,w10]Preparing data for high-frequency characteristic prediction; that is, the timing characteristic of the embodiment may be a high frequency characteristic, and the second preset time period may be, for example, 10 minutes.
And thirdly, predicting real-time operation data of the equipment by training a machine learning model, and simultaneously monitoring the operation condition of the equipment in real time. The process of predicting the operation data of the equipment can comprise a base learner learning stage and a meta learner learning stage, and the first characteristic value is obtained through the learning of the base learner
And a second characteristic value
A learning stage of a base learner: training a feature classifier by using the distributed features to predict a first feature value of a future operating condition through the feature classifier
The feature classifier of the present embodiment is preferably a low frequency bayesian feature classifier. The Bayesian feature classifier is used for counting the most possible feature values of the device, such as rotating speed values, at different hours of a day from the daily frequency. Model input is hoursThe input value is 10 at a value, such as 10 am, and finally, the most probable feature value of the device at 10 am can be predicted by the classifier:
wherein,
for representing a predicted feature outcome; x is the number ofiRepresenting features that are related to the predicted feature (i.e., all other features except the current feature); n represents the number of other features; p (y) represents the probability of occurrence of event y, P (x)iY) represents x under the condition of occurrence of event yiThe probability of (c).
Then, a time sequence characteristic is used for training a characteristic regressor, and a second characteristic value of the future operation condition is predicted through the characteristic regressor
The feature regressor of the present embodiment is preferably a high-frequency Light Gradient boosting machine (distributed Gradient boosting framework based on decision tree algorithm) feature regressor. The LightGBM feature regressor of the present embodiment may predict a feature value, such as a rotational speed value, of the device for 10s in the future from the feature values of the past 10 minutes. The model input is the mean value of features per minute over the past ten minutes [ w1,w2,…,w10]And predicting the characteristic value of 10s in the future. LightGBM is an open source machine learning project developed by Microsoft 2017, efficiently realizes a Gradient Boosting Decision Tree (GBDT) algorithm, performs engineering optimization on the traditional GBDT and Xgboost (eXtrememe Gradientboosting), and can increase the algorithm operation speed without losing the precision, for example, the operation is performed in the following mode.
Wherein,
for representing characteristic prediction results, Fi(xj) Represents the predicted result of the ith decision tree, LiIndicating that the ith decision tree trains the target based on the (i-1) th decision tree.
Then, a meta-learner learning phase is performed: i.e., the prediction result of the fusion-based learner, may include, but is not limited to, a feature value after 10s of prediction, for example. And performing feature fusion on the first feature value and the second feature value to generate a predicted value.
The input of the meta-learner is the prediction result of the base learner
The predicted result is the characteristic value of the device after 10s, and the embodiment adopts the Elasticent regression algorithm to convert L into L1Regularization term and L2Regular terms are perfectly combined together, model overfitting is inhibited, and model generalization capability is improved:
wherein L is a loss function of the regression algorithm, W is a regression equation coefficient,
is L1Regular term coefficient balance L1And L2The regularization term, α, is the coefficient of the regularization term as a whole.
Therefore, the invention can generate the predicted value of the running state of the equipment to be diagnosed through the learning stage of the base learner and the learning stage of the meta learner, and the invention can monitor the actual value of the running state of the equipment to be diagnosed in real time.
And finally, judging whether the equipment to be diagnosed has faults or not based on the difference value between the obtained predicted value and the true value. The predicted value and the true value related to the present embodiment can be both the characteristic values of the corresponding parameters. The classification algorithm can be used to analyze whether an abnormality occurs in the device and can provide a diagnosis-assisting cause of the abnormality. More specifically, the process of determining whether the device to be diagnosed has a fault includes: and taking the difference value between the predicted value and the true value as the input of a logistic regression classifier (equipment abnormity classifier), and judging whether the equipment to be diagnosed has faults or not according to the output of the logistic regression classifier. As shown in fig. 2, the present embodiment may provide abnormality detection based on active learning, including an active learning portion and an auxiliary diagnosis portion.
An active learning part: a sufficiently good classification model is learned with as few labeled samples as possible for the target. The input of the equipment abnormity classifier is the difference value between the characteristic predicted value and the real characteristic value of the multistage characteristic prediction module, and the output is a classification result which indicates whether the current machine is in an abnormal condition.
The algorithm flow of the equipment abnormality classifier is as follows: (1) selecting a logistic regression classifier and a corresponding training set (initially zero) and a verification set (with labeled samples), and actively learning a sample set (without labeled samples); (2) initializing logistic regression classifier (equipment anomaly classifier in fig. 2) parameters; (3) classifying the samples of the current active learning sample set one by using a logistic regression classifier to obtain the classification result of the samples in each active learning sample set, and selecting the samples with the classification result probability in a preset interval, wherein the preset interval in the embodiment is [0.4, 0.6 ]; the closer the classification result is to 0.5, the higher uncertainty of the current model to the sample is shown, and corresponding manual labeling can be carried out; (4) the maintenance personnel can manually label the selected sample in the preset interval, and then add the labeled sample into a training set, so that the training set of the logistic regression classifier comprises training data with the labeled sample; compared with the method for judging the fault by only marking the sample, the method reduces a lot of manual marking workload, so that the data cost of marking abnormal equipment by manufacturing enterprises can be effectively reduced; (5) performing parameter adjustment (fine-tuning) on the current logistic regression classifier by using all currently labeled training samples to update the current logistic regression classifier; (6) and (4) verifying whether the classification accuracy of the current logistic regression classifier reaches a set value, for example, performing mirror image verification on a verification set by using the current logistic regression classifier, if the performance of the current logistic regression classifier reaches the classification accuracy of 80% or no unlabelled sample exists in the active learning sample set, ending iteration, and otherwise, circularly executing (3) - (6). The purpose of the active learning process is to learn a classification module on the logistic regression classifier on the premise of marking a small number of samples as much as possible so as to reduce the labor cost of manual marking (marking abnormal equipment data).
And a diagnosis assisting part: the object is to monitor the operating conditions of the equipment and to provide equipment abnormality information to the equipment in which the abnormal condition occurs. For the real-time state data of the equipment, the deviation between the predicted value and the current real-time data is obtained by utilizing a multi-stage characteristic prediction model, and the operation condition of the equipment, which is provided for maintenance personnel, is monitored by visualizing each characteristic deviation value; and then, whether the current equipment has faults can be analyzed by using the model of the current iterative learning of the active learning module, if the equipment has faults, the deviation of different characteristics is provided for maintenance personnel to help the maintenance personnel to diagnose which characteristics of the equipment have problems, then coefficients of different characteristics of the logistic regression model are provided, and the maintenance personnel is further helped to diagnose which characteristics are most relevant to the faults and assist the maintenance personnel to investigate reasons. In some embodiments of the present invention, when a failure of the device to be diagnosed is determined, the feature weight of each real value corresponding to the current failure is calculated, and then visual troubleshooting reference data can be provided for a user according to the feature weight and each real value.
Example two:
as shown in fig. 2, the present embodiment provides a manufacturing-oriented auxiliary diagnosis system for equipment failure based on the same inventive concept as the first embodiment. The entire equipment failure assisted diagnostic system framework may include three parts: the system comprises a data acquisition part, a multi-stage feature prediction model part and an abnormality detection part based on active learning, wherein the multi-stage feature prediction model part can comprise two-stage prediction, and the thought is derived from an ensemble learning stacking frame and is divided into a base learning part and a meta learning part. Specifically, the fault auxiliary diagnosis system can include, but is not limited to, a state prediction module, a state monitoring module, a fault judgment module and a troubleshooting reference module.
And the state prediction module is used for generating a predicted value of the running state of the equipment to be diagnosed. The state prediction module comprises but is not limited to a data acquisition unit, a feature extraction unit, a preliminary prediction unit and a feature fusion unit.
And the data acquisition unit is used for acquiring historical real-time operation data of the equipment to be diagnosed at a set frequency.
The characteristic extraction unit is used for counting the distribution characteristics of the historical real-time operation data in a first preset time length and generating the time sequence characteristics of the historical real-time operation data in a second preset time length; in this embodiment, the time sequence characteristic may be generated by using a time sequence sliding window manner, and a duration of the sliding window is less than or equal to a second preset duration. The distribution characteristic is a low-frequency characteristic, the time sequence characteristic is a high-frequency characteristic, and the first preset time length is longer than the second preset time length.
The preliminary prediction unit is used for training a feature classifier by utilizing the distribution features so as to predict a first feature value of a future operating condition through the feature classifier; and a second feature value for training the feature regressor with the timing features to predict future operating conditions with the feature regressor.
And the characteristic fusion unit is used for carrying out characteristic fusion on the first characteristic value and the second characteristic value so as to generate a predicted value.
And the state monitoring module is used for monitoring the real value of the running state of the equipment to be diagnosed in real time.
And the fault judgment module is used for judging whether the equipment to be diagnosed has faults or not based on the difference value between the predicted value and the true value. The fault judgment module is also used for taking the difference value between the predicted value and the true value as the input of the logistic regression classifier and judging whether the equipment to be diagnosed is in fault or not according to the output of the logistic regression classifier; the training set of the logistic regression classifier includes labeled sample training data.
And the troubleshooting reference module is used for calculating the characteristic weight of each real value corresponding to the current fault when the equipment to be diagnosed fails, and providing visual troubleshooting reference data for a user according to the characteristic weight and each real value.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable storage medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM-Only Memory, or flash Memory), an optical fiber device, and a portable Compact Disc Read-Only Memory (CDROM). Additionally, the computer-readable storage medium may even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic Gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic Gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "the present embodiment," "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and simplifications made in the spirit of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. A manufacturing-oriented equipment fault auxiliary diagnosis method is characterized by comprising the following steps:
generating a predicted value of the running state of the equipment to be diagnosed;
monitoring the real value of the running state of the equipment to be diagnosed in real time;
and judging whether the equipment to be diagnosed is in fault or not based on the difference value between the predicted value and the true value.
2. The method for assisting in diagnosing the equipment failure in the manufacturing industry according to claim 1, wherein the step of generating the predicted value of the operation state of the equipment to be diagnosed includes:
collecting historical real-time operation data of equipment to be diagnosed at a set frequency;
counting the distribution characteristics of the historical real-time operation data within a first preset time length, and generating the time sequence characteristics of the historical real-time operation data within a second preset time length;
training a feature classifier by using the distribution features to predict a first feature value of a future operating condition through the feature classifier; training a feature regressor by using the time sequence features to predict a second feature value of a future operating condition through the feature regressor;
and performing feature fusion on the first feature value and the second feature value to generate the predicted value.
3. The auxiliary diagnosis method for equipment failure in manufacturing industry according to claim 1 or 2, wherein the process of determining whether the equipment to be diagnosed is failed comprises:
and taking the difference value between the predicted value and the true value as the input of a logistic regression classifier, and judging whether the equipment to be diagnosed is in fault or not according to the output of the logistic regression classifier.
4. The auxiliary diagnosis method for equipment failure in manufacturing industry according to claim 1 or 2, further comprising:
and when the equipment to be diagnosed is judged to be in fault, calculating the characteristic weight of each real value corresponding to the current fault, and then providing visual investigation reference data for a user according to the characteristic weight and each real value.
5. The auxiliary diagnosis method for equipment fault facing manufacturing industry of claim 2, wherein the time sequence feature is generated by adopting a time sequence sliding window mode, and the duration of the sliding window is less than or equal to the second preset duration.
6. The auxiliary diagnosis method for equipment failure in manufacturing industry according to claim 3,
training the logistic regression classifier by:
s1, classifying the samples of the current active learning sample set by using a logistic regression classifier to obtain the classification result of the samples in each active learning sample set;
s2, manually marking the samples with the classification result probability in a preset interval, and adding the marked samples into a training set;
s3, using all the marked training samples to adjust the parameters of the current logistic regression classifier so as to update the current logistic regression classifier;
and S4, verifying whether the classification accuracy of the current logistic regression classifier reaches a set value or whether no unlabeled sample exists in the active learning sample set, ending iteration, and otherwise, executing S1-S4 in a circulating mode.
7. A manufacturing-oriented equipment failure auxiliary diagnostic system, comprising:
the state prediction module is used for generating a predicted value of the running state of the equipment to be diagnosed;
the state monitoring module is used for monitoring the real value of the running state of the equipment to be diagnosed in real time;
and the fault judgment module is used for judging whether the equipment to be diagnosed has faults or not based on the difference value between the predicted value and the true value.
8. The manufacturing-oriented equipment fault assisted diagnosis system of claim 7, wherein the state prediction module comprises:
the data acquisition unit is used for acquiring historical real-time operation data of the equipment to be diagnosed at a set frequency;
the characteristic extraction unit is used for counting the distribution characteristics of the historical real-time operation data in a first preset time length and generating the time sequence characteristics of the historical real-time operation data in a second preset time length;
a preliminary prediction unit, configured to train a feature classifier using the distribution features to predict a first feature value of a future operating condition by the feature classifier; and a second feature value for training a feature regressor using the timing features to predict future operating conditions by the feature regressor;
and the feature fusion unit is used for performing feature fusion on the first feature value and the second feature value to generate the predicted value.
9. The manufacturing-oriented equipment failure auxiliary diagnostic system of claim 7 or 8,
the fault judgment module is used for taking the difference value between the predicted value and the true value as the input of a logistic regression classifier and judging whether the equipment to be diagnosed is in fault or not according to the output of the logistic regression classifier; the training set of the logistic regression classifier includes labeled sample training data.
10. The manufacturing-oriented equipment fault assisted diagnostic system of claim 7, further comprising:
and the troubleshooting reference module is used for calculating the characteristic weight of each real value corresponding to the current fault when the equipment to be diagnosed fails, and providing visual troubleshooting reference data for a user according to the characteristic weight and each real value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010559907.7A CN111783856B (en) | 2020-06-18 | 2020-06-18 | Equipment fault auxiliary diagnosis method and system for manufacturing industry |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010559907.7A CN111783856B (en) | 2020-06-18 | 2020-06-18 | Equipment fault auxiliary diagnosis method and system for manufacturing industry |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111783856A true CN111783856A (en) | 2020-10-16 |
| CN111783856B CN111783856B (en) | 2022-10-04 |
Family
ID=72757390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010559907.7A Active CN111783856B (en) | 2020-06-18 | 2020-06-18 | Equipment fault auxiliary diagnosis method and system for manufacturing industry |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783856B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114352A (en) * | 2023-09-15 | 2023-11-24 | 北京阿帕科蓝科技有限公司 | Vehicle maintenance method, device, computer equipment and storage medium |
| CN118313363A (en) * | 2024-06-05 | 2024-07-09 | 浙江省北大信息技术高等研究院 | Mechanical fault diagnosis method, system, equipment and storage medium |
| CN118313363B (en) * | 2024-06-05 | 2024-10-22 | 浙江省北大信息技术高等研究院 | Mechanical fault diagnosis method, system, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011054088A (en) * | 2009-09-04 | 2011-03-17 | National Institute Of Information & Communication Technology | Information processor, information processing method, program, and interactive system |
| US20150095003A1 (en) * | 2013-09-30 | 2015-04-02 | Ypf Tecnología S.A. | Device and method for detection and/or diagnosis of faults in a processes, equipment and sensors |
| CN107524572A (en) * | 2016-06-22 | 2017-12-29 | 南京理工大学 | A kind of wind-driven generator set on line state monitoring and method for diagnosing faults |
| CN109215165A (en) * | 2018-08-08 | 2019-01-15 | 南京航空航天大学 | A kind of civil aircraft APU Performance Evaluation and fault early warning method |
| CN109506676A (en) * | 2018-11-16 | 2019-03-22 | 中国西安卫星测控中心 | Earth sensor method for diagnosing faults based on regression modeling |
-
2020
- 2020-06-18 CN CN202010559907.7A patent/CN111783856B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011054088A (en) * | 2009-09-04 | 2011-03-17 | National Institute Of Information & Communication Technology | Information processor, information processing method, program, and interactive system |
| US20150095003A1 (en) * | 2013-09-30 | 2015-04-02 | Ypf Tecnología S.A. | Device and method for detection and/or diagnosis of faults in a processes, equipment and sensors |
| CN107524572A (en) * | 2016-06-22 | 2017-12-29 | 南京理工大学 | A kind of wind-driven generator set on line state monitoring and method for diagnosing faults |
| CN109215165A (en) * | 2018-08-08 | 2019-01-15 | 南京航空航天大学 | A kind of civil aircraft APU Performance Evaluation and fault early warning method |
| CN109506676A (en) * | 2018-11-16 | 2019-03-22 | 中国西安卫星测控中心 | Earth sensor method for diagnosing faults based on regression modeling |
Non-Patent Citations (1)
| Title |
|---|
| 管毅等: "一种基于支持向量机的无线传感器故障检测的研究", 《科技通报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114352A (en) * | 2023-09-15 | 2023-11-24 | 北京阿帕科蓝科技有限公司 | Vehicle maintenance method, device, computer equipment and storage medium |
| CN117114352B (en) * | 2023-09-15 | 2024-04-09 | 北京阿帕科蓝科技有限公司 | Vehicle maintenance method, device, computer equipment and storage medium |
| CN118313363A (en) * | 2024-06-05 | 2024-07-09 | 浙江省北大信息技术高等研究院 | Mechanical fault diagnosis method, system, equipment and storage medium |
| CN118313363B (en) * | 2024-06-05 | 2024-10-22 | 浙江省北大信息技术高等研究院 | Mechanical fault diagnosis method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111783856B (en) | 2022-10-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7308385B2 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| US20170161963A1 (en) | Method of identifying anomalies | |
| CN112416643A (en) | Unsupervised anomaly detection method and unsupervised anomaly detection device | |
| CN112581719B (en) | Semiconductor packaging process early warning method and device based on time sequence generation countermeasure network | |
| JP2002532799A (en) | Case-based reasoning system and method and apparatus for sensor prediction, especially in technological processes of cement kilns | |
| US12079070B2 (en) | Alert similarity and label transfer | |
| CN112416662A (en) | Multi-time series data anomaly detection method and device | |
| EP3712728A1 (en) | Apparatus for predicting equipment damage | |
| CN111783856B (en) | Equipment fault auxiliary diagnosis method and system for manufacturing industry | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN113850773A (en) | Detection method, device, equipment and computer readable storage medium | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN116840658A (en) | Fault prediction and diagnosis method for chip firmware | |
| KR20230075150A (en) | Method for managing system health | |
| KR102667861B1 (en) | heavy electrical equipment treatment apparatus using deep learning-based prediction model and method therefor | |
| US11495114B2 (en) | Alert similarity and label transfer | |
| JP7202248B2 (en) | PLANT CONDITION MONITORING SYSTEM AND PLANT CONDITION MONITORING METHOD | |
| US20220308974A1 (en) | Dynamic thresholds to identify successive alerts | |
| Weber et al. | Supervised Transfer Learning Framework for Fault Diagnosis in Wind Turbines | |
| CN117272042A (en) | Photovoltaic power station monitoring method and device, electronic equipment and storage medium | |
| CN117790936A (en) | Energy storage battery management system | |
| CN118410449A (en) | Method, device and equipment for diagnosing abnormal information and readable storage medium | |
| CN118387262A (en) | Ship power system operation data analysis platform and analysis method | |
| CN118468078A (en) | Digital twin distribution network fault scene generation system based on reinforcement learning | |
| CN117436019A (en) | Fault identification method and device of sensing equipment |
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 |