CN110716820A - Fault diagnosis method based on decision tree algorithm - Google Patents
Fault diagnosis method based on decision tree algorithm Download PDFInfo
- Publication number
- CN110716820A CN110716820A CN201910959230.3A CN201910959230A CN110716820A CN 110716820 A CN110716820 A CN 110716820A CN 201910959230 A CN201910959230 A CN 201910959230A CN 110716820 A CN110716820 A CN 110716820A
- Authority
- CN
- China
- Prior art keywords
- decision tree
- fault
- data
- method based
- tree algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/079—Root cause analysis, i.e. error or fault diagnosis
-
- 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
-
- 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
Abstract
The invention provides a fault diagnosis method based on a decision tree algorithm, and relates to the technical field of fault diagnosis. The fault diagnosis method based on the decision tree algorithm comprises the following steps: s1, collecting sample data; s2, classifying the collected samples to form a new set; s3, extracting key characteristic values of the sample set, fusing similar characteristics, and updating sample data; s4, establishing decision tree nodes and training a sample data set; s5, pruning the decision tree; s6, generating a final decision tree and diagnosing faults; and S7, testing the diagnosis accuracy and correcting the decision tree in time. The fault of the sports equipment is diagnosed by utilizing the decision tree algorithm, so that the diagnosis process is time-saving and labor-saving, a plurality of parts of the sports equipment do not need to be eliminated one by one, the position of the fault can be quickly found, much convenience is brought to the maintenance of the sports equipment, and the diagnosis and maintenance cost is reduced.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis method based on a decision tree algorithm.
Background
The decision tree algorithm constructs a decision tree to find out classification rules implied in data, how to construct the decision tree with high precision and small scale is the core content of the decision tree algorithm, the decision tree construction can be carried out in two steps, and the first step is the generation of the decision tree, namely, the process of generating the decision tree by a training sample set, wherein the training sample set is a data set which has history according to actual needs, has a certain comprehensive degree and is used for data analysis and processing in general; and secondly, pruning the decision tree, namely, the process of checking, correcting and repairing the decision tree generated at the previous stage by pruning the decision tree, wherein the process is mainly to prune branches influencing the accuracy of pre-balance by using a preliminary rule generated in the process of generating the decision tree by checking data in a new sample data set (called a test data set).
At present, the fault of the sports equipment is diagnosed by manpower mostly, the diagnosis process is time-consuming and labor-consuming, a plurality of parts of the sports equipment need to be eliminated one by one, a great amount of time is usually spent to find the position of the fault, much inconvenience is brought to the maintenance of the sports equipment, and the diagnosis and maintenance cost is improved, so that the fault diagnosis method based on the decision tree algorithm is provided to solve the defects in the prior art.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a fault diagnosis method based on a decision tree algorithm, which solves the problems that the fault of the sports equipment is diagnosed by manpower, the diagnosis process is time-consuming and labor-consuming, a plurality of parts of the sports equipment need to be eliminated one by one, the position of the fault can be found by spending a large amount of time, the maintenance of the sports equipment is inconvenient, and the diagnosis and maintenance cost is increased.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: a fault diagnosis method based on a decision tree algorithm comprises the following steps:
s1, collecting sample data;
s2, classifying the collected samples to form a new set;
s3, extracting key characteristic values of the sample set, fusing similar characteristics, and updating sample data;
s4, establishing decision tree nodes and training a sample data set;
s5, pruning the decision tree;
s6, generating a final decision tree and diagnosing faults;
and S7, testing the diagnosis accuracy and correcting the decision tree in time.
Preferably, in the step 1, a big data capture algorithm is used to capture historical failure analysis result samples, the failure analysis result samples account for more than 98% of the total database, and meanwhile, a keyword group extraction algorithm is used to extract collected effective samples and screen out samples of irrelevant content.
Preferably, in the step 2, all the collected samples are classified according to the same attribute value, the attribute value includes a key phrase, a fault type, a fault analysis result and an inefficacy factor, similar samples are divided into the same set, all the generated sets are marked as P1, P2, P3.. Pi and Pj, and meanwhile, sufficient sample amount is guaranteed to be available in all the sets P1, P2, P3.. Pi and Pj.
Preferably, in the step 3, all sample feature values in each set P are extracted, the similarity of the sample data is observed, the feature values of the samples with higher similarity are fused to optimize a new sample data, and simultaneously, all the samples in the sets P1, P2, P3.
Preferably, in step 4, the second largest deterministic feature in the set is found by using recursion until all data in the sub-data sets belong to the same class, one feature is selected from a plurality of features in the training data as a splitting criterion of the current node, assuming a sample space (X, Y) of a sorted set, X representing a sample, Y representing n classes, and possible values are W1, W2,.., Wn, and the probability of occurrence of each class is G (W1), G (W2.. G (Wn)), and the conditional gain ratio of the decision tree node is calculated by the following calculation formula:
preferably, when the decision tree is constructed in step 5, many branches reflect the abnormality in the training data due to noise or isolated points in the training data, and the classification of the data with unknown class is performed by using such decision tree, so that the classification accuracy is not high, and the unnecessary branches are detected and subtracted.
Preferably, a decision tree algorithm finally related to fault diagnosis is established in the step 6, and the algorithm is used for analyzing and diagnosing the faults of the sports equipment.
Preferably, in the step 7, the fault data is imported into the decision tree algorithm to diagnose the fault, and then the fault data is analyzed and compared with the manual diagnosis result, so as to compare the accuracy of the decision tree algorithm in diagnosing the fault and adjust the decision tree algorithm in time.
(III) advantageous effects
The invention provides a fault diagnosis method based on a decision tree algorithm. The method has the following beneficial effects:
1. according to the fault diagnosis method based on the decision tree algorithm, the fault of the sports equipment is diagnosed by utilizing the decision tree algorithm, so that the diagnosis process is time-saving and labor-saving, a plurality of parts of the sports equipment do not need to be eliminated one by one, the position of the fault can be quickly found, much convenience is brought to the maintenance of the sports equipment, and the diagnosis and maintenance cost is reduced.
2. According to the fault diagnosis method based on the decision tree algorithm, the accuracy of the decision tree algorithm is greatly improved through optimization and continuity test of the decision tree algorithm.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example (b):
as shown in fig. 1, an embodiment of the present invention provides a fault diagnosis method based on a decision tree algorithm, including the following steps:
s1, collecting sample data;
s2, classifying the collected samples to form a new set;
s3, extracting key characteristic values of the sample set, fusing similar characteristics, and updating sample data;
s4, establishing decision tree nodes and training a sample data set;
s5, pruning the decision tree;
s6, generating a final decision tree and diagnosing faults;
and S7, testing the diagnosis accuracy and correcting the decision tree in time.
In the step 1, a big data capturing algorithm is used for capturing historical fault analysis result samples, the fault analysis result samples account for more than 98% of the total database, meanwhile, a key phrase extracting algorithm is used for extracting collected effective samples, and samples with irrelevant contents are screened out.
In step 2, all collected samples are classified according to the same attribute value, the attribute value comprises a key phrase, a fault type, a fault analysis result and an inefficacy factor, similar samples are divided into the same set, all generated sets are marked as P1, P2, P3.
In step 3, all sample characteristic values in each set P are extracted, the similarity degree of sample data is observed, the samples with higher similarity degree are subjected to characteristic value fusion to be optimized into new sample data, and simultaneously, all samples in the sets P1, P2, P3.
In step 4, a second largest decisive feature in the set is found by using recursion until all data in the sub-data sets belong to the same class, one feature is selected from a plurality of features in the training data as a splitting standard of a current node, a sample space (X, Y) of a classified set is assumed, X represents a sample, Y represents n classes, possible values are W1, W2,.., Wn, the probability of occurrence of each class is G (W1), G (W2.. G (Wn), and the conditional gain rate of the nodes of the decision tree is calculated, wherein the calculation formula is as follows:
when the decision tree is constructed in the step 5, due to noise or isolated points in the training data, a plurality of branches reflect the abnormity in the training data, the decision tree is used for classifying the data with unknown classes, the classification accuracy is not high, and therefore the unnecessary branches are detected and subtracted.
And 6, establishing a final decision tree algorithm related to fault diagnosis, and analyzing and diagnosing the faults of the sports equipment by using the algorithm.
And 7, importing the fault data into a decision tree algorithm, diagnosing the fault, analyzing and comparing the result with a manual diagnosis result, comparing the accuracy of the decision tree algorithm on fault diagnosis, and adjusting the decision tree algorithm in time.
The fault of the sports equipment is diagnosed by utilizing the decision tree algorithm, so that the diagnosis process is time-saving and labor-saving, a plurality of parts of the sports equipment do not need to be eliminated one by one, the position of the fault can be quickly found, much convenience is brought to the maintenance of the sports equipment, and the diagnosis and maintenance cost is reduced.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A fault diagnosis method based on decision tree algorithm is characterized in that: the method comprises the following steps:
s1, collecting sample data;
s2, classifying the collected samples to form a new set;
s3, extracting key characteristic values of the sample set, fusing similar characteristics, and updating sample data;
s4, establishing decision tree nodes and training a sample data set;
s5, pruning the decision tree;
s6, generating a final decision tree and diagnosing faults;
and S7, testing the diagnosis accuracy and correcting the decision tree in time.
2. The fault diagnosis method based on decision tree algorithm according to claim 1, characterized in that: in the step 1, a big data capture algorithm is used for capturing historical fault analysis result samples, the fault analysis result samples account for more than 98% of the total database, meanwhile, a key phrase extraction algorithm is used for extracting collected effective samples, and samples with irrelevant contents are screened out.
3. The fault diagnosis method based on decision tree algorithm according to claim 1, characterized in that: in the step 2, all the collected samples are classified according to the same attribute value, the attribute value includes a key phrase, a fault type, a fault analysis result and an inefficacy factor, similar samples are divided into the same set, all the generated sets are marked as P1, P2, P3.
4. The fault diagnosis method based on decision tree algorithm according to claim 1, characterized in that: in the step 3, all sample characteristic values in each set P are extracted, the similarity of the sample data is observed, the sample with higher similarity is subjected to characteristic value fusion to be optimized into a new sample data, and simultaneously, all samples in the sets P1, P2, P3.. Pi and Pj are updated, so that the sample capacity in all the sets is optimized.
5. The fault diagnosis method based on decision tree algorithm according to claim 1, characterized in that: in the step 4, a second largest decisive feature in the set is found by using recursion until all data in the sub-data sets belong to the same class, one feature is selected from a plurality of features in the training data as a splitting standard of the current node, a sample space (X, Y) of a classified set is assumed, X represents a sample, Y represents n classes, possible values are W1, W2,.., Wn, and the probability of occurrence of each class is G (W1), G (W2.. G (Wn), and a conditional gain rate of the decision tree node is calculated, wherein the calculation formula is as follows:
6. the fault diagnosis method based on decision tree algorithm according to claim 1, characterized in that: when the decision tree is constructed in the step 5, due to noise or isolated points in the training data, many branches reflect the abnormality in the training data, and the decision tree is used for classifying the data with unknown class, so that the classification accuracy is not high, and the unnecessary branches are detected and subtracted.
7. The fault diagnosis method based on decision tree algorithm according to claim 1, characterized in that: and 6, establishing a final decision tree algorithm related to fault diagnosis, and analyzing and diagnosing the faults of the sports equipment by using the algorithm.
8. The fault diagnosis method based on decision tree algorithm according to claim 1, characterized in that: and 7, importing the fault data into the decision tree algorithm to diagnose the fault, analyzing and comparing the fault data with a manual diagnosis result, comparing the accuracy of the decision tree algorithm on fault diagnosis, and adjusting the decision tree algorithm in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910959230.3A CN110716820A (en) | 2019-10-10 | 2019-10-10 | Fault diagnosis method based on decision tree algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910959230.3A CN110716820A (en) | 2019-10-10 | 2019-10-10 | Fault diagnosis method based on decision tree algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110716820A true CN110716820A (en) | 2020-01-21 |
Family
ID=69211364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910959230.3A Pending CN110716820A (en) | 2019-10-10 | 2019-10-10 | Fault diagnosis method based on decision tree algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110716820A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111562111A (en) * | 2020-06-05 | 2020-08-21 | 上海交通大学 | Engine cold state test fault diagnosis method |
| CN112733775A (en) * | 2021-01-18 | 2021-04-30 | 苏州大学 | Hyperspectral image classification method based on deep learning |
| CN113256176A (en) * | 2021-07-06 | 2021-08-13 | 北京全路通信信号研究设计院集团有限公司 | Dispatching command compiling system and method for railway locomotive application state conversion |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104506340A (en) * | 2014-11-21 | 2015-04-08 | 河南中烟工业有限责任公司 | Creation method of decision tree in industrial Ethernet fault diagnosis method |
| US20180238951A1 (en) * | 2016-09-07 | 2018-08-23 | Jiangnan University | Decision Tree SVM Fault Diagnosis Method of Photovoltaic Diode-Clamped Three-Level Inverter |
| CN109218114A (en) * | 2018-11-12 | 2019-01-15 | 西安微电子技术研究所 | A kind of server failure automatic checkout system and detection method based on decision tree |
| CN109522957A (en) * | 2018-11-16 | 2019-03-26 | 上海海事大学 | The method of harbour gantry crane machine work status fault classification based on decision Tree algorithms |
| CN110188834A (en) * | 2019-06-04 | 2019-08-30 | 广东电网有限责任公司 | A kind of method for diagnosing faults of power telecom network, device and equipment |
-
2019
- 2019-10-10 CN CN201910959230.3A patent/CN110716820A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104506340A (en) * | 2014-11-21 | 2015-04-08 | 河南中烟工业有限责任公司 | Creation method of decision tree in industrial Ethernet fault diagnosis method |
| US20180238951A1 (en) * | 2016-09-07 | 2018-08-23 | Jiangnan University | Decision Tree SVM Fault Diagnosis Method of Photovoltaic Diode-Clamped Three-Level Inverter |
| CN109218114A (en) * | 2018-11-12 | 2019-01-15 | 西安微电子技术研究所 | A kind of server failure automatic checkout system and detection method based on decision tree |
| CN109522957A (en) * | 2018-11-16 | 2019-03-26 | 上海海事大学 | The method of harbour gantry crane machine work status fault classification based on decision Tree algorithms |
| CN110188834A (en) * | 2019-06-04 | 2019-08-30 | 广东电网有限责任公司 | A kind of method for diagnosing faults of power telecom network, device and equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111562111A (en) * | 2020-06-05 | 2020-08-21 | 上海交通大学 | Engine cold state test fault diagnosis method |
| CN112733775A (en) * | 2021-01-18 | 2021-04-30 | 苏州大学 | Hyperspectral image classification method based on deep learning |
| CN113256176A (en) * | 2021-07-06 | 2021-08-13 | 北京全路通信信号研究设计院集团有限公司 | Dispatching command compiling system and method for railway locomotive application state conversion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107301296B (en) | Data-based qualitative analysis method for circuit breaker fault influence factors | |
| CN110716820A (en) | Fault diagnosis method based on decision tree algorithm | |
| CN112766550B (en) | Random forest-based power failure sensitive user prediction method, system, storage medium and computer equipment | |
| CN111177655B (en) | Data processing method and device and electronic equipment | |
| CN113239365B (en) | Vulnerability repairing method based on knowledge graph | |
| CN114221790A (en) | BGP (Border gateway protocol) anomaly detection method and system based on graph attention network | |
| TW202038110A (en) | Classifying defects in a semiconductor specimen | |
| CN110825642B (en) | Software code line-level defect detection method based on deep learning | |
| CN111949480A (en) | Log anomaly detection method based on component perception | |
| CN112328499A (en) | Test data generation method, device, equipment and medium | |
| CN115800272A (en) | Power grid fault analysis method, system, terminal and medium based on topology identification | |
| CN114841789A (en) | Block chain-based auditing and auditing pricing fault data online editing method and system | |
| CN114416573A (en) | Defect analysis method, device, equipment and medium for application program | |
| CN113283973A (en) | Account checking difference data processing method and device, computer equipment and storage medium | |
| CN112687402A (en) | Intelligent medical internet big data processing method based on artificial intelligence and intelligent cloud service platform | |
| CN116522111A (en) | Automatic diagnosis method for remote power failure | |
| CN106569944A (en) | Constraint-tree-based onboard software test data analysis method | |
| CN115329663A (en) | Key feature selection method and device for processing power load monitoring sparse data | |
| CN116846837A (en) | Traffic identification method and device, electronic equipment and storage medium | |
| CN113726558A (en) | Network equipment flow prediction system based on random forest algorithm | |
| CN114547294A (en) | Rumor detection method and system based on comprehensive information of propagation process | |
| CN115904920A (en) | Test case recommendation method and device, terminal and storage medium | |
| CN113268419A (en) | Method, device, equipment and storage medium for generating test case optimization information | |
| CN114663102A (en) | Method, equipment and storage medium for predicting debt subject default based on semi-supervised model | |
| D’Orazio | Some Approaches to Outliers’ Detection in R |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |
|
| RJ01 | Rejection of invention patent application after publication |