CN112329341B - Fault diagnosis system and method based on AR and random forest model - Google Patents
Fault diagnosis system and method based on AR and random forest model Download PDFInfo
- Publication number
- CN112329341B CN112329341B CN202011202229.5A CN202011202229A CN112329341B CN 112329341 B CN112329341 B CN 112329341B CN 202011202229 A CN202011202229 A CN 202011202229A CN 112329341 B CN112329341 B CN 112329341B
- Authority
- CN
- China
- Prior art keywords
- data
- model
- industrial robot
- random forest
- module
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- 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
- G06F18/21—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
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- Y02P90/80—Management or planning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a fault diagnosis system and method based on AR and random forest models, wherein the method comprises the following steps: the data acquisition module acquires real-time acceleration value data of the industrial robot and stores the acquired data to the data storage module; on one hand, the data analysis module extracts the characteristic value of the AR model by using the acceleration group value of the industrial robot stored in the data storage module, and establishes and trains a random forest model; on the other hand, extracting a characteristic value of the AR model according to the real-time acceleration value of the industrial robot acquired by the data acquisition module; the fault diagnosis module predicts the operation fault of the industrial robot according to the trained random forest model of the data analysis module, sends the diagnosis result to a worker, and constructs a model by extracting the characteristics of historical data, so that the classification model has universality and the fault diagnosis accuracy is improved; and the characteristic value is predicted by using the constructed random forest model every time, so that the efficiency of real-time fault prediction is improved.
Description
Technical Field
The invention relates to the technical field of fault judgment and processing, in particular to a fault diagnosis system and method based on AR and a random forest model.
Background
With the development of modern science and technology, industrial robots are developing towards the direction of complication, integration and intellectualization, and playing more and more important roles in manufacturing enterprises. The operating condition of the industrial robot directly or indirectly influences the production efficiency of an enterprise, so that the operating fault of the industrial robot is diagnosed in time, the enterprise can know the actual operating state of the industrial robot in time, maintenance is arranged in time according to a diagnosis result, the maintenance cost can be reduced to the maximum extent, the damage of the industrial robot is reduced, and the operating state of the industrial robot is ensured to be good and the service life of the industrial robot is prolonged.
The existing robot operation fault diagnosis method is that an industrial robot is scored after field observation through experienced technicians, the subjective factor of the diagnosis mode is strong, a vibration signal of the industrial robot during operation cannot be accurately obtained, and the operation state of the industrial robot cannot be accurately evaluated; or through the method for evaluating the vibration signals of the industrial robot, a large amount of calculation is carried out on the industrial robot in each grading process according to the value of the relevant parameters of the vibration signals of the industrial robot as the value of the grade, and a model is not built, so that the single grading result has no universality, the probability of misjudgment is high, and the subsequent work of the industrial robot is adversely affected.
Disclosure of Invention
The invention provides a fault diagnosis system and method based on AR and random forest models, aiming at solving the problems that the operation state of an industrial robot cannot be accurately obtained due to strong subjective factors when an experienced technician observes the operation state of the industrial robot on site and the method for obtaining the relevant parameters of the vibration signals of the industrial robot needs to carry out a large amount of calculation and has high misjudgment probability.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the invention discloses a fault diagnosis system based on AR and a random forest model, which comprises a data acquisition module, a data storage module, a data analysis module and a fault diagnosis module, wherein the data acquisition module is used for acquiring a real-time acceleration value of an industrial robot; the data storage module is used for storing the acceleration value of the industrial robot acquired by the data acquisition module; the data analysis module extracts a characteristic value of the AR model by using the acceleration value data of the industrial robot stored in the data storage module, and establishes and trains a random forest model; and the fault diagnosis module is used for predicting the operation fault of the industrial robot according to the random forest model trained by the data analysis module.
Further, the fault diagnosis system based on the AR and the random forest model further comprises a human-computer interaction platform used for sending the diagnosis result of the fault diagnosis module to a worker.
Further, the data analysis module comprises an offline data modeling unit and a real-time data evaluation unit, wherein the offline data modeling unit extracts the characteristic value of the AR model by using the acceleration value data of the industrial robot stored in the data storage module, and establishes and trains a random forest model; and the real-time data evaluation unit extracts the characteristic value of the AR model according to the real-time acceleration value data of the industrial robot acquired by the data acquisition module.
Further, the data acquisition module comprises a vibration sensor for acquiring real-time acceleration value data of the industrial robot.
On the other hand, the invention discloses a fault diagnosis method based on AR and random forest models, which comprises the following steps:
the data acquisition module acquires real-time acceleration value data of the industrial robot and stores the acquired data value to the data storage module;
on one hand, the data analysis module extracts the characteristic value of the AR model by using the acceleration group value data of the industrial robot stored in the data storage module, and establishes and trains a random forest model; on the other hand, extracting a characteristic value of the AR model according to the real-time acceleration value data of the industrial robot acquired by the data acquisition module;
and the fault diagnosis module is used for predicting the operation fault of the industrial robot according to the random forest model trained by the data analysis module and sending a diagnosis result to a worker.
Further, the extracting the feature value of the AR model includes the steps of:
determining the order of the AR model parameter;
obtaining AR model parameters;
and optimizing the parameters.
Further, the establishing and training of the random forest model comprises the following steps:
determining an optional parameter value;
determining a training mode of a random forest model;
obtaining an optimal result and a model parameter set;
and storing the trained random forest model.
Furthermore, the acquisition frequency of the data acquisition module is 1 point/ms, and the acquisition cycle is a motion cycle.
The beneficial technical effects are as follows:
1. the invention provides a fault diagnosis system based on AR and a random forest model, which comprises a data acquisition module, a data storage module, a data analysis module and a fault diagnosis module, wherein the data acquisition module is used for acquiring a real-time acceleration value of an industrial robot; the data storage module is used for storing the acceleration value of the industrial robot acquired by the data acquisition module; the data analysis module extracts a characteristic value of the AR model by using the acceleration value data of the industrial robot stored in the data storage module, and establishes and trains a random forest model; the fault diagnosis module predicts the operation fault of the industrial robot according to the random forest model trained by the data analysis module, and the fault diagnosis system improves the accuracy and efficiency of fault prediction;
2. the invention provides a fault diagnosis method based on AR and a random forest model, which comprises the following steps:
the data acquisition module acquires real-time acceleration value data of the industrial robot and stores the acquired data value to the data storage module;
on one hand, the data analysis module extracts the characteristic value of the AR model by using the acceleration group value data of the industrial robot stored in the data storage module, and establishes and trains a random forest model; on the other hand, extracting a characteristic value of the AR model according to the real-time acceleration value data of the industrial robot acquired by the data acquisition module;
the fault diagnosis module predicts the operation fault of the industrial robot according to the random forest model trained by the data analysis module, sends a diagnosis result to a worker, and constructs a model by performing feature extraction on historical data, so that the classification model has universality and the fault diagnosis accuracy is improved; and the characteristic value is predicted by using the constructed random forest model every time, so that the efficiency of real-time fault prediction is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a fault diagnosis system based on AR and a random forest model according to the present invention;
FIG. 2 is a schematic diagram of a fault diagnosis method based on AR and a random forest model according to the present invention;
FIG. 3 is a time series diagram of a first set of fault data;
FIG. 4 is a second set of fault data time series diagrams;
FIG. 5 is a time series diagram of a third set of fault data;
FIG. 6 is a fourth set of time series diagrams of fault data;
FIG. 7 is a time series diagram of a fifth set of fault data;
FIG. 8 is a time series diagram of the presence or absence of fault data for the sixth group;
FIG. 9 is a time series diagram of a seventh group of data with or without failure;
FIG. 10 is a three-dimensional characteristic diagram with or without fault data, i.e. the characteristic values of the parameters of the original AR model;
FIG. 11 is another three-dimensional characteristic diagram with or without fault data, i.e. the characteristic values of the original AR model parameters;
FIG. 12 is a scatter plot after feature normalization and PCA with the selection of the 6 th and 7 th feature values.
Wherein, 1-no fault data, 2-fault data.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
First, the AR model used in the present invention is an Autoregressive model (Autoregressive model), which is a statistical method for processing time series.
The invention discloses a fault diagnosis system based on AR and a random forest model, which comprises a data acquisition module, a data storage module, a data analysis module and a fault diagnosis module, wherein the data acquisition module is used for acquiring the real-time acceleration value of an industrial robot, and specifically, the data acquisition module comprises a vibration sensor and an industrial personal computer, the vibration sensor is arranged on a stack of a manipulator of the industrial robot and is used for acquiring the real-time acceleration value of the industrial robot, and the vibration sensor is connected with the industrial personal computer through a 485 line; the data storage module is used for storing the acceleration value of the industrial robot acquired by the data acquisition module, and preferably, the data storage module is an inflixdb database; the data analysis module extracts a characteristic value of the AR model by using the acceleration value data of the industrial robot stored in the data storage module, and establishes and trains a random forest model; and the fault diagnosis module is used for predicting the operation fault of the industrial robot according to the random forest model trained by the data analysis module.
On the other hand, the invention discloses a fault diagnosis method based on AR and a random forest model, which specifically comprises the following steps with reference to FIG. 2:
the data acquisition module acquires real-time acceleration value data of the industrial robot and stores the acquired data value to the data storage module;
determining the total quantity value which is acquired each time and contains one robot operation cycle, specifically, acquiring an acceleration value acquired by a vibration sensor in a normal state, acquiring one point with the frequency of 1ms (data between 1ms and 2ms are automatically filtered), wherein the calculated quantity at each time is 1000 points, the calculated quantity at each time contains one motion cycle of a manipulator, namely, acquiring 80 groups of data in total, and storing the data into a mysql database through rabbitmq in real time; and acquiring acceleration values acquired by the vibration sensor under the fault condition, wherein the acquisition mode is the same as that under the normal state, and the acquisition modes are 80 groups in total, and storing the data into a database in real time through rabbitmq.
On one hand, the data analysis module extracts a characteristic value of the AR model by using the acceleration group value data of the industrial robot stored in the data storage module, and establishes and trains a random forest model; on the other hand, extracting a characteristic value of the AR model according to the real-time acceleration value data of the industrial robot acquired by the data acquisition module;
specifically, the method comprises the following steps:
extracting the characteristic value of the AR model specifically comprises the following steps:
determining order of AR model parameters
And fitting each acquired number by using the first N numbers to obtain N parameters, and performing the operation on each acquired data each time, so that the values of the N parameters can be obtained by using a least square method according to the equations, namely solving the over-determined equation set. Specifically, the total number of 80 normal data groups is 1000, that is, 80 groups of parameter values are obtained, each group has N numbers, if the variation range of the corresponding parameter values between each group does not exceed 5%, N is considered as the order of the AR model parameter, the test is started from data 5, 1 is sequentially added, and when the order is 7 in the experiment, the parameter variation range meets the condition, and the order is determined to be 7; similarly, for fault data, the order is also determined to be 7, also using the method described above.
Obtaining AR model parameters
Using an autoregressive AR model, with an order of 7, 160 sets of data were obtained, with 7 values for each set, with the first 80 sets being positive data and the second 80 sets being negative data, a broken line comparison of the time series, see fig. 3-9.
Taking 3 of these parameters and plotting a 3-dimensional feature map, as shown in fig. 10 and 11, the AR model parameters were found to be separable.
Parameter optimization
Because 7 parameters are more and some parameters with unobvious classification characteristics exist, the variance of each group of data is obtained, 160 groups of differences are obtained, the variance difference values of positive and negative data are taken for sorting, the characteristics of the two previous difference ranks are obtained, in the experiment, the characteristics are taken as the characteristics 6 and 7, after the characteristics are well obtained, the characteristics are standardized, the data is subjected to dimensionality reduction (PCA), and finally the obtained characteristic values have obvious divisible rows, as shown in FIG. 12.
Establishing and training a random forest model, specifically comprising the following steps:
determining optional parameter values
The random forest model has 6 large parameters, n _ estimators, max _ depth, min _ samples _ leaf, min _ samples _ split, max _ features and criterion, wherein the n _ estimators represent the maximum number of weak learners, and are selected from four numbers of 50, 100, 150 and 200 in the experiment; bootstrap indicates whether a replaced sample exists, and false or true is taken; criterion is a characteristic selection standard, and parameters gini and entcopy can be selected; max _ features represents the maximum number of features, taken 2 in the experiment; min _ samples _ leaf represents the minimum number of samples of the leaf node, and the selectable parameters are set to be 1 and 2.
Determining a mode of training a forest model
The Pipeline mechanism is used for realizing the streaming encapsulation and management of the program, and the repeated use of the model parameter set on the data set can be realized, so that the parameter adjustment is convenient; using GridSearchCV mechanism, inputting parameters with classifier type, selecting random forest model, 2-dimensional characteristic value of 160 groups, parameter list of the random forest, accuracy evaluation standard 'accuracy', 10-fold cross validation mode in experiment, namely, averagely dividing data into 10 parts, taking one part of data as test data and the rest of data as training data, calculating the accuracy of the model trained by the training data to predict the test data, taking 10 different test data each time to obtain the combination of 10 accuracies, then averaging, according to the parameters, obtaining the optimal result and model parameter set through GridSearchCV module: the best effect is 0.98 and the best parameter sets are clf __ criteria, 'gini', clf __ max _ features:2, clf __ min _ samples _ leaf:2, clf __ n _ estimators: 200.
And storing the trained random forest model.
And similarly, extracting the characteristic value of the AR model from the real-time acceleration data of the industrial robot acquired by the data acquisition module.
And the fault diagnosis module is used for predicting the operation fault of the industrial robot according to the random forest model trained by the data analysis module and sending a diagnosis result to a worker.
Specifically, the random forest classification model established and trained in the steps is used, the operating state of the industrial robot, namely whether the industrial robot operates normally or has faults at present, is judged by judging the characteristic value of the AR model of the acceleration value data of the industrial robot acquired by the data acquisition module in real time, is displayed through an interface, namely the acceleration value of the industrial robot is acquired by the vibration sensor in real time on line, is transmitted to the server through rabbitmq to be stored and analyzed, every 1000 sensors are acquired, 7-order AR model parameters are acquired, the first two optimal parameters are acquired in a filtering mode, then the stored random forest model is used for testing, and if 75% of results of continuous 1000 times of prediction are faulty, the industrial robot is considered to have problems.
As a preferred embodiment of the present invention, the fault diagnosis system based on the AR and the random forest model further includes a human-computer interaction platform for sending the diagnosis result of the fault diagnosis module to the worker, specifically, the fault diagnosis system may be connected to the database through an interface, and check the collected data information and the predicted result information in real time, and the fault diagnosis system may perform statistics and monitoring on the predicted result, and if a fault problem is predicted, notify the worker of the fault diagnosis result in time in a short message or mail manner.
In the description herein, references to the description of the term "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 invention. In this specification, the schematic representations of the terms used above do not necessarily 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.
The foregoing merely illustrates embodiments of the present invention and is not to be construed as limiting the scope thereof. It should be noted that modifications made by those skilled in the art without departing from the spirit of the present invention are within the scope of the present invention.
The above examples are only for describing the preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, and various modifications and improvements made to the technical solution of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.
Claims (3)
1. A fault diagnosis system based on AR and random forest models is characterized by comprising:
the data acquisition module is used for acquiring a real-time acceleration value of the industrial robot;
the data storage module is used for storing the acceleration value of the industrial robot acquired by the data acquisition module;
the data analysis module comprises an offline data modeling unit and a real-time data evaluation unit, wherein the offline data modeling unit extracts a characteristic value of the AR model by using historical acceleration value data of the industrial robot stored in the data storage module, and a random forest model is built and trained; the real-time data evaluation unit extracts a characteristic value of the AR model according to the real-time acceleration value data of the industrial robot collected by the data collection module;
the fault diagnosis module is used for judging the characteristic value of the AR model extracted from the real-time acceleration value data collected by the data collection module according to the random forest model trained by the data analysis module, predicting the operation fault of the industrial robot and diagnosing whether the current operation state of the industrial robot is normal or faulty;
the system also comprises a human-computer interaction platform used for sending the diagnosis result of the fault diagnosis module to a worker;
the data acquisition module comprises a vibration sensor, and the vibration sensor is arranged on a stack of a manipulator of the industrial robot and is used for acquiring real-time acceleration value data of the industrial robot;
the data acquisition module acquires a total quantity value containing one operation cycle each time, wherein the acquisition frequency is 1 point/ms, the calculation amount is 1000 points each time, the calculation amount each time contains one motion cycle of the manipulator, and the acquisition of the acceleration values acquired by 80 groups of vibration sensors in a normal state and the acquisition of the acceleration values acquired by 80 groups of vibration sensors under a fault condition are included;
wherein the extracting the feature value of the AR model comprises:
determining the order of the AR model parameters: respectively fitting 1000 collected normal acceleration value data 80 groups and 1000 collected fault acceleration value data 80 groups, obtaining N parameter values by using a least square method, and determining the order of the AR model parameter to be 7 when the variation range of the corresponding parameter value N between each group does not exceed 5% when the corresponding parameter value N reaches 7;
obtaining AR model parameters: using a 7-order AR model to obtain 80 groups of normal acceleration value data and 80 groups of fault acceleration value data, wherein each group of data has 7 parameters;
optimizing parameters: and aiming at the 7 parameters, obtaining 160 groups of variances by solving the variances of each group of data, sequencing 160 groups of difference values to obtain the characteristics of the two previous differences, carrying out characteristic standardization on the characteristics, reducing the dimension of the data, and finally obtaining two characteristic values which can be divided.
2. The fault diagnosis method of the fault diagnosis system according to claim 1, based on AR and random forest models, comprising the steps of:
the data acquisition module acquires real-time acceleration value data of the industrial robot and stores the acquired data value to the data storage module;
on one hand, the data analysis module extracts a characteristic value of the AR model by using historical acceleration group value data of the industrial robot stored in the data storage module, and establishes and trains a random forest model; on the other hand, extracting a characteristic value of the AR model according to the real-time acceleration value data of the industrial robot acquired by the data acquisition module;
and the fault diagnosis module judges the characteristic value of the AR model extracted from the real-time acceleration value data collected by the data collection module according to the random forest model trained by the data analysis module, predicts the operation fault of the industrial robot, diagnoses whether the current operation state of the industrial robot is normal or faulty, and sends the diagnosis result to a worker.
3. The method for fault diagnosis based on AR and random forest models according to claim 2, wherein the step of building and training the random forest models comprises the steps of:
determining an optional parameter value;
determining a training mode of a random forest model;
obtaining an optimal result and a model parameter set;
and storing the trained random forest model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011202229.5A CN112329341B (en) | 2020-11-02 | 2020-11-02 | Fault diagnosis system and method based on AR and random forest model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011202229.5A CN112329341B (en) | 2020-11-02 | 2020-11-02 | Fault diagnosis system and method based on AR and random forest model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112329341A CN112329341A (en) | 2021-02-05 |
| CN112329341B true CN112329341B (en) | 2022-07-08 |
Family
ID=74324025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011202229.5A Active CN112329341B (en) | 2020-11-02 | 2020-11-02 | Fault diagnosis system and method based on AR and random forest model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112329341B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114019282A (en) * | 2021-11-04 | 2022-02-08 | 云南电网有限责任公司电力科学研究院 | Transformer fault diagnosis method based on principal component analysis and random forest phase fusion |
| CN116214528B (en) * | 2023-05-10 | 2023-10-03 | 深圳市安信达存储技术有限公司 | Storage control method and control system for humanoid robot |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106599794A (en) * | 2016-11-21 | 2017-04-26 | 南京熊猫电子股份有限公司 | Six-axis industrial robot fault diagnosis method and system based on AR model |
| CN108388860B (en) * | 2018-02-12 | 2020-04-28 | 大连理工大学 | Aero-engine rolling bearing fault diagnosis method based on power entropy spectrum-random forest |
| CN109670553B (en) * | 2018-12-25 | 2022-08-12 | 福州大学 | Photovoltaic array fault diagnosis method based on adaptive neural fuzzy inference system |
| CN110231156B (en) * | 2019-06-26 | 2020-06-09 | 山东大学 | Service robot motion system fault diagnosis method and device based on time sequence characteristics |
| CN111046931A (en) * | 2019-12-02 | 2020-04-21 | 北京交通大学 | Turnout fault diagnosis method based on random forest |
| CN111178553A (en) * | 2019-12-16 | 2020-05-19 | 北京航天智造科技发展有限公司 | Industrial equipment health trend analysis method and system based on ARIMA and LSTM algorithms |
-
2020
- 2020-11-02 CN CN202011202229.5A patent/CN112329341B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112329341A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112329341B (en) | Fault diagnosis system and method based on AR and random forest model | |
| CN111241154A (en) | Storage battery fault early warning method and system based on big data | |
| KR102427205B1 (en) | Apparatus and method for generating training data of artificial intelligence model | |
| JP2010089760A (en) | Creation of reference value for troubleshooting of vehicle | |
| CN114239734B (en) | Distributed vehicle-mounted health management system | |
| CN115827411B (en) | On-line monitoring and operation and maintenance assessment system and method for automation equipment | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN111627199A (en) | Hydropower station dam safety monitoring system and monitoring method | |
| US8271233B2 (en) | Method of multi-level fault isolation design | |
| CN115037603A (en) | Diagnosis evaluation method, device and system of electricity consumption information acquisition equipment | |
| CN116880454A (en) | Intelligent diagnosis system and method for vehicle faults | |
| CN114912678A (en) | Online automatic detection and early warning method and system for abnormal operation of power grid regulation and control | |
| CN116380496B (en) | Automobile door fatigue endurance test method, system and medium | |
| CN112016193B (en) | Online prediction method and system for lubrication failure of shield tunneling machine system | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system | |
| Olsson et al. | Case-based reasoning combined with statistics for diagnostics and prognosis | |
| CN115788771A (en) | Intelligent operation and maintenance management system of wind power generation system based on Internet of things technology | |
| CN113487141B (en) | Bearing state evaluation method based on multisource information clustering fusion | |
| CN115034094A (en) | Prediction method and system for operation state of metal processing machine tool | |
| CN114780797A (en) | Method and system for cleaning multi-source heterogeneous big data in aircraft manufacturing process | |
| CN113168739B (en) | Method for checking at least one vehicle and electronic computing device | |
| CN114279728A (en) | Fault diagnosis method and system for vibrating screen body | |
| CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning | |
| CN113888775A (en) | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle | |
| CN117827621B (en) | Automatic test platform system and method for embedded software |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 315400 Zhejiang Yuyao Ningbo Economic Development Zone East New District Applicant after: Zhichang Technology Group Co.,Ltd. Address before: 315400 NO.175 Anshan Road, Yuyao City, Ningbo City, Zhejiang Province Applicant before: ZHEJIANG EMERGEN ROBOT TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |