CN113392936B - Oven fault diagnosis method based on machine learning - Google Patents

Oven fault diagnosis method based on machine learning Download PDF

Info

Publication number
CN113392936B
CN113392936B CN202110777869.7A CN202110777869A CN113392936B CN 113392936 B CN113392936 B CN 113392936B CN 202110777869 A CN202110777869 A CN 202110777869A CN 113392936 B CN113392936 B CN 113392936B
Authority
CN
China
Prior art keywords
oven
temperature
fault
heating
calculating
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
Application number
CN202110777869.7A
Other languages
Chinese (zh)
Other versions
CN113392936A (en
Inventor
李清华
张仁军
林涛
黄伟杰
艾克华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inno Circuits Ltd
Original Assignee
Inno Circuits Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Inno Circuits Ltd filed Critical Inno Circuits Ltd
Priority to CN202110777869.7A priority Critical patent/CN113392936B/en
Publication of CN113392936A publication Critical patent/CN113392936A/en
Application granted granted Critical
Publication of CN113392936B publication Critical patent/CN113392936B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass
    • G01M99/002—Thermal testing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass
    • G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass
    • G01M99/008—Subject matter not provided for in other groups of this subclass by doing functionality tests
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Electric Stoves And Ranges (AREA)

Abstract

The invention discloses an oven fault diagnosis method based on machine learning, which comprises the following steps: s1, acquiring temperature information of heating areas of a faultless oven in a plurality of heating states to form a characteristic data set P A (ii) a S2, collecting temperature information of heating areas of the faulty oven in a plurality of heating states to form a characteristic data set P B (ii) a S3, adding a label to each feature data of the two feature data sets; s4, constructing a classifier by adopting a machine learning method, and training the classifier to obtain a classifier with mature training; and S5, carrying out fault diagnosis on the oven to be detected based on the trained classifier, and judging whether the oven to be detected has faults or not. The invention can realize the fault diagnosis of the oven based on the high temperature condition of the oven, the temperature fluctuation condition within a certain time and the temperature fluctuation conditions of different heating points, and has higher diagnosis accuracy.

Description

Oven fault diagnosis method based on machine learning
Technical Field
The invention relates to oven fault diagnosis, in particular to an oven fault diagnosis method based on machine learning.
Background
The oven is a common household appliance in people's life, and before the oven leaves a factory from a manufacturer or after the oven is returned to the factory for maintenance, fault diagnosis needs to be carried out on the oven frequently to judge whether the oven can be used as a qualified product leaving the factory or a qualified product for maintenance; however, at present, the diagnosis method is often to see whether the temperature is higher than the threshold value when the oven is operated at the set temperature.
However, this diagnostic method can diagnose only a high temperature abnormality, cannot diagnose a temperature fluctuation abnormality at different heating points in the heating region, and cannot diagnose a temperature fluctuation abnormality during the heating continuation.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an oven fault diagnosis method based on machine learning, which can realize fault diagnosis of an oven based on the high-temperature condition of the oven, the temperature fluctuation condition within a certain time and the temperature fluctuation conditions of different heating points and has higher diagnosis accuracy.
The purpose of the invention is realized by the following technical scheme: a machine learning-based oven fault diagnosis method comprises the following steps:
s1, collecting temperature information of heating areas of a plurality of fault-free ovens in a heating state to obtain temperature data of each heating area of the fault-free ovens, extracting characteristic data of each fault-free oven according to the collected information to form a characteristic data set P A ；
S2, acquiring temperature information of the heating areas of the faulty ovens in a plurality of heating states to obtain temperature data of the heating areas of the faulty ovens, extracting characteristic data of each faulty oven according to the acquired information to form a characteristic data set P B ；
S3, characteristic data set P is subjected to A The label y is added to each feature data in the feature data set P, and the feature data set P is labeled with 0 B The tag y of each feature data in (1);
s4, adopting a machine learning method to construct a classifier, and according to the feature data set P A And a feature data set P B Training the classifier by the data to obtain a trained classifier;
and S5, carrying out fault diagnosis on the oven to be detected based on the trained classifier, and judging whether the oven to be detected has faults or not.
The step S1 includes the sub-steps of:
s101, for any fault-free oven, arranging a temperature detection array in a heating area of the fault-free oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting a fault-free oven, and entering a heating state after the fault-free oven is preheated for a set time;
s102, temperature acquisition is carried out on a heating area of the faultless oven in a heating state by using a temperature detection array, and an obtained temperature information matrix K A ：
Figure GDA0003760065500000021
Wherein the content of the first and second substances,
Figure GDA0003760065500000022
the signals which are collected by the temperature sensors in the ith row and the jth column are represented, i is 1,2, …, m, j is 1,2, …, n;
s103, calculating a temperature information matrix K A Average value of temperature in
Figure GDA0003760065500000023
Figure GDA0003760065500000024
Calculating the discrete degree p of the detection results of different temperature sensors A ：
Figure GDA0003760065500000025
S104, repeatedly executing the steps S102 to S103 for T times at different moments in the heating state of the fault-free oven to obtain T temperature average values
Figure GDA0003760065500000026
And calculating T discrete degrees
Figure GDA0003760065500000027
Wherein
Figure GDA0003760065500000028
Represents the average temperature value obtained by the t repeated execution process,
Figure GDA0003760065500000029
represents the discrete degree obtained by the T repeated execution process, T is 1,2, …, T;
s105, constructing characteristic data of the fault-free oven
Figure GDA00037600655000000210
S106, repeating the steps S101 to S105 for each fault-free oven to obtain corresponding characteristic data
Figure GDA00037600655000000211
Forming a feature data set P A ：
Figure GDA00037600655000000212
Where M represents the total number of non-faulty ovens.
The step S2 includes the following sub-steps:
s201, for any fault oven, arranging a temperature detection array in a heating area of the fault oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting a fault oven, and entering a heating state after the fault oven is preheated for a set time;
s202, temperature acquisition is carried out on a heating area of the fault oven in a heating state by using a temperature detection array, and an obtained temperature information matrix K B ：
Figure GDA0003760065500000031
Wherein the content of the first and second substances,
Figure GDA0003760065500000032
the signal collected by the temperature sensor in the ith row and the jth column is represented, i is 1,2, …, m, j is 1,2, …, n;
s203, calculating a temperature information matrix K B Average value of temperature in
Figure GDA0003760065500000033
Figure GDA0003760065500000034
Calculating the discrete degree p of the detection results of different temperature sensors B ：
Figure GDA0003760065500000035
S204, repeatedly executing the steps S202 to S203 for T times at different moments in the heating state of the fault oven to obtain T temperature average values
Figure GDA0003760065500000036
And calculating T discrete degrees
Figure GDA0003760065500000037
Wherein
Figure GDA0003760065500000038
Represents the average temperature value obtained by the t repeated execution process,
Figure GDA0003760065500000039
represents the discrete degree obtained by the T repeated execution process, T is 1,2, …, T;
s205, constructing characteristic data of a fault oven
Figure GDA00037600655000000310
S206, for each fault oven, repeating the steps S201 to S205 to obtain corresponding characteristic data
Figure GDA00037600655000000311
Forming a feature data set P B ：
Figure GDA00037600655000000312
Where N represents the total number of failed ovens.
The step S5 includes:
s501, for an oven to be tested, arranging a temperature detection array in a heating area of the oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting the oven to be tested, and entering a heating state after the oven to be tested is preheated for a set time;
s502, temperature acquisition is carried out on a heating area of the oven to be detected in a heating state by utilizing a temperature detection array, and an obtained temperature information matrix K C ：
Figure GDA0003760065500000041
Wherein the content of the first and second substances,
Figure GDA0003760065500000042
the signal collected by the temperature sensor in the ith row and the jth column is represented, i is 1,2, …, m, j is 1,2, …, n;
s503, judging whether temperature information larger than a set threshold exists in the signals acquired by the temperature sensors:
if the temperature information larger than the set threshold exists, monitoring the temperature sensor corresponding to the temperature information within the duration h seconds, if the temperature value output by the temperature sensor within the h seconds does not recover below the set threshold, judging that the oven to be tested is in failure, and if the temperature value output by the temperature sensor within the h seconds recovers below the set threshold, entering the step S504;
if the temperature information larger than the set threshold does not exist, directly entering step S504;
s504, calculating a temperature information matrix K C Average value of temperature in
Figure GDA0003760065500000043
Figure GDA0003760065500000044
Calculating the discrete degree p of the detection results of different temperature sensors C ：
Figure GDA0003760065500000045
S505, repeatedly executing the steps S502 to S504 for T times at different moments of the oven to be tested in the heating state to obtain T temperature average values
Figure GDA0003760065500000046
And calculating T discrete degrees
Figure GDA0003760065500000047
Wherein
Figure GDA0003760065500000048
Represents the average temperature value obtained by the t-th repeated execution process,
Figure GDA0003760065500000049
represents the discrete degree obtained by the repeated execution process for the T time, wherein T is 1,2, …, T;
s506, constructing characteristic data of the oven to be tested
Figure GDA00037600655000000410
S507, calculating
Figure GDA00037600655000000411
Degree of dispersion Q:
Figure GDA00037600655000000412
wherein, the first and the second end of the pipe are connected with each other,
Figure GDA00037600655000000413
judging whether the dispersion degree Q is larger than a preset threshold value:
if so, determining that the oven to be tested has a fault;
if not, go to step S508;
s508, feature data are combined
Figure GDA0003760065500000051
And sending the data into a classifier with mature training, if the classifier outputs 0, determining that the oven to be tested has no fault, and if the classifier outputs 1, determining that the oven to be tested has fault.
The beneficial effects of the invention are: the invention can realize the fault diagnosis of the oven based on the high temperature condition of the oven, the temperature fluctuation condition within a certain time and the temperature fluctuation conditions of different heating points, and has higher diagnosis accuracy.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions of the present invention are further described in detail below with reference to the accompanying drawings, but the scope of the present invention is not limited to the following.
As shown in fig. 1, a method for diagnosing oven faults based on machine learning includes the following steps:
s1, collecting temperature information of heating areas of a plurality of fault-free ovens in a heating state to obtain temperature data of each heating area of the fault-free ovens, extracting characteristic data of each fault-free oven according to the collected information to form a characteristic data set P A ；
S2, acquiring temperature information of the heating areas of the faulty ovens in a plurality of heating states to obtain temperature data of the heating areas of the faulty ovens, extracting characteristic data of each faulty oven according to the acquired information to form a characteristic data set P B ；
S3, characteristic data set P is subjected to A Is added with a label y of 0, and the feature data set P is added B The tag y of each feature data in (1);
s4, adopting a machine learning method to construct a classifier and carrying out root feature data set P A And a feature data set P B Training the classifier by the data to obtain a trained classifier;
and S5, carrying out fault diagnosis on the oven to be detected based on the trained classifier, and judging whether the oven to be detected has faults or not.
The step S1 includes the sub-steps of:
s101, for any fault-free oven, arranging a temperature detection array in a heating area of the fault-free oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting a fault-free oven, and entering a heating state after the fault-free oven is preheated for a set time;
s102, temperature acquisition is carried out on a heating area of the faultless oven in a heating state by using a temperature detection array, and an obtained temperature information matrix K A ：
Figure GDA0003760065500000061
Wherein the content of the first and second substances,
Figure GDA0003760065500000062
the signal collected by the temperature sensor in the ith row and the jth column is represented, i is 1,2, …, m, j is 1,2, …, n;
s103, calculating a temperature information matrix K A Average temperature value of (1)
Figure GDA0003760065500000063
Figure GDA0003760065500000064
Calculating the discrete degree p of the detection results of different temperature sensors A ：
Figure GDA0003760065500000065
S104, repeatedly executing the steps S102 to S103 for T times at different moments in the heating state of the fault-free oven to obtain T temperature average values
Figure GDA0003760065500000066
And calculate accordinglyGiving T discrete degrees
Figure GDA0003760065500000067
Wherein
Figure GDA0003760065500000068
Represents the average temperature value obtained by the t repeated execution process,
Figure GDA0003760065500000069
represents the discrete degree obtained by the repeated execution process for the T time, wherein T is 1,2, …, T;
s105, constructing characteristic data of the fault-free oven
Figure GDA00037600655000000610
S106, repeating the steps S101 to S105 for each fault-free oven to obtain corresponding characteristic data
Figure GDA00037600655000000611
Forming a feature data set P A ：
Figure GDA00037600655000000612
Where M represents the total number of non-faulty ovens.
The step S2 includes the following sub-steps:
s201, for any fault oven, arranging a temperature detection array in a heating area of the fault oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting a fault oven, and entering a heating state after the fault oven is preheated for a set time;
s202, temperature acquisition is carried out on a heating area of the fault oven in a heating state by using a temperature detection array, and an obtained temperature information matrix K B ：
Figure GDA0003760065500000071
Wherein the content of the first and second substances,
Figure GDA0003760065500000072
the signal collected by the temperature sensor in the ith row and the jth column is represented, i is 1,2, …, m, j is 1,2, …, n;
s203, calculating a temperature information matrix K B Average value of temperature in
Figure GDA0003760065500000073
Figure GDA0003760065500000074
Calculating the discrete degree p of the detection results of different temperature sensors B ：
Figure GDA0003760065500000075
S204, repeatedly executing the steps S202 to S203 for T times at different moments in the heating state of the fault oven to obtain T temperature average values
Figure GDA0003760065500000076
And calculating T discrete degrees
Figure GDA0003760065500000077
Wherein
Figure GDA0003760065500000078
Represents the average temperature value obtained by the t repeated execution process,
Figure GDA0003760065500000079
represents the discrete degree obtained by the repeated execution process for the T time, wherein T is 1,2, …, T;
s205, constructing characteristic data of a fault oven
Figure GDA00037600655000000710
S206, for each fault oven, repeating the steps S201 to S205 to obtain corresponding characteristic data
Figure GDA00037600655000000711
Forming a feature data set P B ：
Figure GDA00037600655000000712
Where N represents the total number of failed ovens.
In step S4, the feature data set P is extracted A And a feature data set P B The feature data in the method is used as the input of a classifier, the label corresponding to the feature data is used as the expected output of the classifier to realize the training of the classifier, and a feature data set P is adopted A And a feature data set P B After each feature data in the data is trained, a mature classifier is obtained;
the step S5 includes:
s501, for an oven to be tested, arranging a temperature detection array in a heating area of the oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting the oven to be tested, and entering a heating state after the oven to be tested is preheated for a set time;
s502, temperature acquisition is carried out on a heating area of the oven to be detected in a heating state by using a temperature detection array, and an obtained temperature information matrix K C ：
Figure GDA0003760065500000081
Wherein, the first and the second end of the pipe are connected with each other,
Figure GDA0003760065500000082
the signal collected by the temperature sensor in the ith row and the jth column is represented, i is 1,2, …, m, j is 1,2, …, n;
s503, judging whether temperature information larger than a set threshold exists in the signals collected by the temperature sensors:
if the temperature information larger than the set threshold exists, monitoring the temperature sensor corresponding to the temperature information within the duration h seconds, if the temperature value output by the temperature sensor within the h seconds does not recover below the set threshold, judging that the oven to be tested is in failure, and if the temperature value output by the temperature sensor within the h seconds recovers below the set threshold, entering the step S504;
if the temperature information larger than the set threshold does not exist, directly entering step S504;
s504, calculating a temperature information matrix K C Average value of temperature in
Figure GDA0003760065500000083
Figure GDA0003760065500000084
Calculating the discrete degree p of the detection results of different temperature sensors C ：
Figure GDA0003760065500000085
S505, repeatedly executing the steps S502 to S504 for T times at different moments of the oven to be tested in the heating state to obtain T temperature average values
Figure GDA0003760065500000086
And calculating T discrete degrees
Figure GDA0003760065500000087
Wherein
Figure GDA0003760065500000088
Represents the average temperature value obtained by the t-th repeated execution process,
Figure GDA0003760065500000089
represents the discrete degree obtained by the repeated execution process for the T time, wherein T is 1,2, …, T;
s506, constructing the oven to be testedSign data
Figure GDA00037600655000000810
S507, calculating
Figure GDA00037600655000000811
Degree of dispersion Q:
Figure GDA00037600655000000812
wherein, the first and the second end of the pipe are connected with each other,
Figure GDA00037600655000000813
judging whether the dispersion degree Q is greater than a preset threshold value:
if so, determining that the oven to be tested has a fault;
if not, go to step S508;
s508, feature data are combined
Figure GDA0003760065500000091
And sending the data into a classifier with mature training, if the classifier outputs 0, determining that the oven to be tested has no fault, and if the classifier outputs 1, determining that the oven to be tested has fault.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; the above embodiments are merely provided to help understand the method of the present invention and its core idea; meanwhile, for a person skilled in the art, according to the idea of the present invention, certain modifications or substitutions may be made in the specific embodiments and the application range; and these modifications or substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (3)

1. A machine learning-based oven fault diagnosis method is characterized in that: the method comprises the following steps:
s1, collecting temperature information of heating areas of a faultless oven in a plurality of heating states,obtaining the temperature data of the heating areas of the fault-free ovens, extracting the characteristic data of each fault-free oven according to the collected information, and forming a characteristic data set P A ；
The step S1 includes the sub-steps of:
s101, for any fault-free oven, arranging a temperature detection array in a heating area of the fault-free oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting a fault-free oven, and entering a heating state after the fault-free oven is preheated for a set time;
s102, temperature acquisition is carried out on a heating area of the faultless oven in a heating state by using a temperature detection array, and an obtained temperature information matrix K A ：
Figure FDA0003760065490000011
Wherein the content of the first and second substances,
Figure FDA0003760065490000012
the signal is acquired by a temperature sensor in the ith row and the jth column, i is 1,2, and m, j is 1,2, n;
s103, calculating a temperature information matrix K A Average value of temperature in
Figure FDA0003760065490000013
Figure FDA0003760065490000014
Calculating the discrete degree p of the detection results of different temperature sensors A ：
Figure FDA0003760065490000015
S104, repeatedly executing the steps S102 to S103 for T times at different moments in the heating state of the fault-free ovenObtaining T temperature average values
Figure FDA0003760065490000016
And calculating T discrete degrees
Figure FDA0003760065490000017
Wherein
Figure FDA0003760065490000018
Represents the average temperature value obtained by the t repeated execution process,
Figure FDA0003760065490000019
represents the discrete degree obtained by the repeated execution process for the T time, wherein T is 1, 2.
S105, constructing characteristic data of the fault-free oven
Figure FDA00037600654900000110
S106, repeating the steps S101 to S105 for each fault-free oven to obtain corresponding characteristic data
Figure FDA00037600654900000111
Forming a feature data set P A ：
Figure FDA0003760065490000021
Wherein M represents the total number of non-faulty ovens;
s2, acquiring temperature information of the heating areas of the faulty ovens in a plurality of heating states to obtain temperature data of the heating areas of the faulty ovens, extracting characteristic data of each faulty oven according to the acquired information to form a characteristic data set P B ；
S3, characteristic data set P is subjected to A Is added with a label y of 0, and the feature data set P is added B Each feature data in (1) is added with a label y;
s4, adopting a machine learning method to construct a classifier, and according to the feature data set P A And a feature data set P B Training the classifier by the data to obtain a trained classifier;
and S5, carrying out fault diagnosis on the oven to be detected based on the trained classifier, and judging whether the oven to be detected has faults or not.
2. The machine learning-based oven fault diagnosis method according to claim 1, characterized in that: the step S2 includes the following sub-steps:
s201, for any fault oven, arranging a temperature detection array in a heating area of the fault oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting a fault oven, and entering a heating state after the fault oven is preheated for a set time;
s202, temperature acquisition is carried out on a heating area of the fault oven in a heating state by using a temperature detection array, and an obtained temperature information matrix K B ：
Figure FDA0003760065490000022
Wherein the content of the first and second substances,
Figure FDA0003760065490000023
the signal is acquired by a temperature sensor in the ith row and the jth column, i is 1,2, and m, j is 1,2, n;
s203, calculating a temperature information matrix K B Average temperature value of (1)
Figure FDA0003760065490000024
Figure FDA0003760065490000025
Calculating the dispersion of the detection results of different temperature sensorsDegree p B ：
Figure FDA0003760065490000026
S204, repeatedly executing the steps S202 to S203 for T times at different moments in the heating state of the fault oven to obtain T temperature average values
Figure FDA0003760065490000031
And calculating T discrete degrees
Figure FDA0003760065490000032
Wherein
Figure FDA0003760065490000033
Represents the average temperature value obtained by the t repeated execution process,
Figure FDA0003760065490000034
represents the discrete degree obtained by the T-th repeated execution process, wherein T is 1, 2.
S205, constructing characteristic data of a fault oven
Figure FDA0003760065490000035
S206, for each fault oven, repeating the steps S201 to S205 to obtain corresponding characteristic data
Figure FDA0003760065490000036
Forming a feature data set P B ：
Figure FDA0003760065490000037
Where N represents the total number of failed ovens.
3. The machine learning-based oven fault diagnosis method according to claim 1, characterized in that: the step S5 includes:
s501, for an oven to be tested, arranging a temperature detection array in a heating area of the oven, wherein the temperature detection array comprises m rows and n columns of m × n temperature sensors; starting the oven to be tested, and entering a heating state after the oven to be tested is preheated for a set time;
s502, temperature acquisition is carried out on a heating area of the oven to be detected in a heating state by using a temperature detection array, and an obtained temperature information matrix K C ：
Figure FDA0003760065490000038
Wherein the content of the first and second substances,
Figure FDA0003760065490000039
the signal is acquired by the temperature sensor in the ith row and the jth column, i is 1,2, …, m, j is 1,2,.
S503, judging whether temperature information larger than a set threshold exists in the signals collected by the temperature sensors:
if the temperature information larger than the set threshold exists, monitoring the temperature sensor corresponding to the temperature information within the duration h seconds, if the temperature value output by the temperature sensor within the h seconds does not recover below the set threshold, judging that the oven to be tested is in failure, and if the temperature value output by the temperature sensor within the h seconds recovers below the set threshold, entering the step S504;
if the temperature information larger than the set threshold does not exist, directly entering step S504;
s504, calculating a temperature information matrix K C Average temperature value of (1)
Figure FDA00037600654900000310
Figure FDA00037600654900000311
Calculating the discrete degree p of the detection results of different temperature sensors C ：
Figure FDA0003760065490000041
S505, repeatedly executing the steps S502 to S504 for T times at different moments of the oven to be tested in the heating state to obtain T temperature average values
Figure FDA0003760065490000042
And calculating T discrete degrees
Figure FDA0003760065490000043
Wherein
Figure FDA0003760065490000044
Represents the average temperature value obtained by the t repeated execution process,
Figure FDA0003760065490000045
represents the discrete degree obtained by the repeated execution process for the T time, wherein T is 1,2, …, T;
s506, constructing characteristic data of the oven to be tested
Figure FDA0003760065490000046
S507, calculating
Figure FDA0003760065490000047
Degree of dispersion Q:
Figure FDA0003760065490000048
wherein the content of the first and second substances,
Figure FDA0003760065490000049
judging whether the dispersion degree Q is larger than a preset threshold value:
if so, determining that the oven to be tested has a fault;
if not, go to step S508;
s508, feature data are combined
Figure FDA00037600654900000410
And sending the data into a classifier with mature training, if the classifier outputs 0, determining that the oven to be tested has no fault, and if the classifier outputs 1, determining that the oven to be tested has fault.
CN202110777869.7A 2021-07-09 2021-07-09 Oven fault diagnosis method based on machine learning Active CN113392936B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110777869.7A CN113392936B (en) 2021-07-09 2021-07-09 Oven fault diagnosis method based on machine learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110777869.7A CN113392936B (en) 2021-07-09 2021-07-09 Oven fault diagnosis method based on machine learning

Publications (2)

Publication Number Publication Date
CN113392936A CN113392936A (en) 2021-09-14
CN113392936B true CN113392936B (en) 2022-09-02

Family

ID=77625688

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110777869.7A Active CN113392936B (en) 2021-07-09 2021-07-09 Oven fault diagnosis method based on machine learning

Country Status (1)

Country Link
CN (1) CN113392936B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116026889B (en) * 2022-12-30 2023-12-01 苏州春田机械有限公司 CCD detection device, system and control method for production line
CN117740083B (en) * 2024-02-19 2024-05-10 达斯玛环境科技（北京）有限公司 Method, system, equipment and storage medium for monitoring faults of stirrer

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106897542A (en) * 2017-04-18 2017-06-27 浙江中烟工业有限责任公司 Based on the cigarette cut tobacco segment fault diagnostic method that notable failure variable is extracted
CN108204892A (en) * 2018-01-24 2018-06-26 重庆邮电大学 Roller set equipment fault detection method based on array-type flexible pressure sensor
CN110361193A (en) * 2019-04-04 2019-10-22 浙江运达风电股份有限公司 Method for distinguishing is known for wind generating set pitch control bearing fault

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8868985B2 (en) * 2009-09-17 2014-10-21 Siemens Aktiengesellschaft Supervised fault learning using rule-generated samples for machine condition monitoring
CN106483449B (en) * 2016-09-09 2019-01-25 电子科技大学 Analog-circuit fault diagnosis method based on deep learning and Complex eigenvalues
US10409789B2 (en) * 2016-09-16 2019-09-10 Oracle International Corporation Method and system for adaptively imputing sparse and missing data for predictive models
CN108303264B (en) * 2017-01-13 2020-03-20 华为技术有限公司 Cloud-based vehicle fault diagnosis method, device and system
KR101967065B1 (en) * 2017-10-18 2019-04-08 울산대학교 산학협력단 Fault diagnosis apparatus and method for robust to environmental change
CN108414923A (en) * 2018-02-05 2018-08-17 武汉大学 A kind of analog-circuit fault diagnosis method based on the extraction of depth confidence network characterization
CN108875796A (en) * 2018-05-28 2018-11-23 福州大学 Diagnosing failure of photovoltaic array method based on linear discriminant analysis and support vector machines
CN110108431B (en) * 2019-05-22 2021-07-16 西安因联信息科技有限公司 Mechanical equipment fault diagnosis method based on machine learning classification algorithm
CN110334740A (en) * 2019-06-05 2019-10-15 武汉大学 The electrical equipment fault of artificial intelligence reasoning fusion detects localization method
CN111327271B (en) * 2020-01-20 2021-11-26 福州大学 Photovoltaic array fault diagnosis method based on semi-supervised extreme learning machine
CN111948487A (en) * 2020-07-17 2020-11-17 国网上海市电力公司 High-voltage power equipment fault diagnosis method and system based on artificial intelligence
CN111967535B (en) * 2020-09-04 2023-11-14 安徽大学 Fault diagnosis method and device for temperature sensor of grain storage management scene
CN112734055A (en) * 2020-12-25 2021-04-30 华帝股份有限公司 Fault prediction method of cooking equipment
CN112785016B (en) * 2021-02-20 2022-06-07 南京领行科技股份有限公司 New energy automobile maintenance and fault monitoring and diagnosis method based on machine learning

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106897542A (en) * 2017-04-18 2017-06-27 浙江中烟工业有限责任公司 Based on the cigarette cut tobacco segment fault diagnostic method that notable failure variable is extracted
CN108204892A (en) * 2018-01-24 2018-06-26 重庆邮电大学 Roller set equipment fault detection method based on array-type flexible pressure sensor
CN110361193A (en) * 2019-04-04 2019-10-22 浙江运达风电股份有限公司 Method for distinguishing is known for wind generating set pitch control bearing fault

Also Published As

Publication number Publication date
CN113392936A (en) 2021-09-14

Similar Documents

Publication Publication Date Title
CN113392936B (en) Oven fault diagnosis method based on machine learning
CN109446187B (en) Method for monitoring health state of complex equipment based on attention mechanism and neural network
CN111737909B (en) Structural health monitoring data anomaly identification method based on space-time graph convolutional network
CN110334740A (en) The electrical equipment fault of artificial intelligence reasoning fusion detects localization method
CN110110768B (en) Rolling bearing fault diagnosis method based on parallel feature learning and multiple classifiers
CN106404441B (en) A kind of failure modes diagnostic method based on non-linear similarity index
CN109543743B (en) Multi-sensor fault diagnosis method for refrigerating unit based on reconstructed prediction residual error
CN111289250A (en) Method for predicting residual service life of rolling bearing of servo motor
CN111397902B (en) Rolling bearing fault diagnosis method based on feature alignment convolutional neural network
CN110533167B (en) Fault diagnosis method and system for electric valve actuating mechanism
CN104880217B (en) A kind of fault sensor signal reconstruct method based on the measured value degree of association
CN105445646A (en) Testing method of analog-digital circuit fault diagnosis based on neural network expert system
CN115455746B (en) Nuclear power device operation monitoring data anomaly detection and correction integrated method
CN110243497A (en) A kind of sensor fault diagnosis method and system based on principal component analysis
CN115950609B (en) Bridge deflection anomaly detection method combining correlation analysis and neural network
CN108872852A (en) A kind of wind-driven generator fault diagnosis system and method
CN116295948A (en) Abnormality detection method, system and storage medium of industrial temperature sensor in large temperature difference environment
CN114091600A (en) Data-driven satellite associated fault propagation path identification method and system
US11308408B2 (en) Fault signal recovery system and method
CN106195247B (en) A kind of control system of speed variator based on big data management mode
CN108226762A (en) A kind of diagnostic circuit for multiplexed signal sampling circuit
CN207516518U (en) A kind of lithium dynamical battery system fault diagnosis device
CN116578922A (en) Valve cooling system fault diagnosis method and device based on multichannel convolutional neural network
CN112213103A (en) Fault diagnosis method, device, system and medium for rail transit rolling stock bearing
CN206656749U (en) Heat-engine plant sensor fault diagnosis system

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