WO2024092972A1 - Procédé et système de test de qualité de soudage par ultrasons - Google Patents

Procédé et système de test de qualité de soudage par ultrasons Download PDF

Info

Publication number
WO2024092972A1
WO2024092972A1 PCT/CN2022/139648 CN2022139648W WO2024092972A1 WO 2024092972 A1 WO2024092972 A1 WO 2024092972A1 CN 2022139648 W CN2022139648 W CN 2022139648W WO 2024092972 A1 WO2024092972 A1 WO 2024092972A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
welding quality
electric box
ultrasonic welding
vibration signal
Prior art date
Application number
PCT/CN2022/139648
Other languages
English (en)
Chinese (zh)
Inventor
卢其辉
廖泽宏
范鹏
Original Assignee
广东利元亨智能装备股份有限公司
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 广东利元亨智能装备股份有限公司 filed Critical 广东利元亨智能装备股份有限公司
Publication of WO2024092972A1 publication Critical patent/WO2024092972A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04—Analysing solids
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • 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
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • 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
    • 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

Definitions

  • the present invention relates to the technical field of ultrasonic welding, and in particular to an ultrasonic welding quality detection method and system.
  • Ultrasonic power supply also called ultrasonic generator, is used to convert electrical energy into high-frequency AC signals that match ultrasonic transducers. It is a device used to generate and provide ultrasonic energy to ultrasonic transducers.
  • Ultrasonic welding technology uses high-frequency vibration waves to transmit to the surfaces of two objects to be welded. Under pressure, the two surfaces of the objects rub against each other to form a fusion between the molecular layers.
  • ultrasonic metal welding has gradually been applied to industries such as lithium batteries and semiconductors. The ultrasonic welding process in these industries is crucial. If there are defects or hidden dangers in the welding quality, the welded parts will inevitably be used in products, which will inevitably lead to safety risks.
  • the battery cell tab is a raw material for lithium-ion polymer battery products. It is a metal conductor that leads the positive and negative electrodes from the battery cell.
  • the existing ultrasonic welding quality evaluation method for battery cell tabs often obtains quality test results through destructive tests such as strain testing, which is not conducive to promotion and use.
  • the present invention provides an ultrasonic welding quality detection method and system, which are used to solve the technical problem that the existing ultrasonic welding quality evaluation method of battery core tabs obtains quality detection results through destructive detection, which is not conducive to popularization and use.
  • a first aspect of the present invention provides an ultrasonic welding quality detection method, comprising:
  • Preprocessing the vibration signal data and the electric box data Preprocessing the vibration signal data and the electric box data, and extracting features from the preprocessed vibration signal data and the electric box data to obtain vibration feature data and electric box feature data;
  • the qualified probability values output by all target learning models are averaged to obtain the final ultrasonic welding quality inspection results.
  • it also includes:
  • the welding quality grades of the final ultrasonic welding quality inspection results are determined, wherein the welding quality grades include qualified, critically qualified, critically unqualified and unqualified.
  • vibration signal data and the electric box data are preprocessed, and feature extraction is performed on the preprocessed vibration signal data and the electric box data respectively to obtain vibration feature data and electric box feature data, including:
  • the vibration signal data is segmented to obtain the vibration signal data of the pressing and preheating stage, the dry friction stage and the plastic deformation welding stage corresponding to the ultrasonic welding process;
  • the vibration signal data of the pressing preheating stage, dry friction stage and plastic deformation welding stage after noise filtering are respectively subjected to time domain feature extraction, frequency domain feature extraction and time-frequency domain feature extraction;
  • the time domain characteristic data, frequency domain characteristic data and time-frequency domain characteristic data of the pressing and preheating stage, the dry friction stage and the plastic deformation welding stage are spliced to obtain the vibration characteristic data;
  • the electric box data includes power, three-phase current, three-phase voltage, phase difference and impedance angle.
  • the multiple target learning models include a random forest algorithm model.
  • the vibration feature data and the electric box feature data are respectively input into a plurality of target learning models to obtain a detection result output by each target learning model, and the above also includes:
  • Preprocessing the vibration signal data samples and the electric box data samples respectively extracting features from the preprocessed vibration signal data samples and the electric box data samples to obtain vibration feature sample data and electric box feature sample data;
  • the training set, validation set and test set are used to perform model training, model parameter adjustment and testing on all learning models to obtain the corresponding target learning model.
  • a second aspect of the present invention provides an ultrasonic welding quality detection system, comprising:
  • a data acquisition module is used to collect vibration signal data on the welding base of the ultrasonic welding machine and the electrical box data of the ultrasonic welding machine;
  • a feature extraction module is used to preprocess the vibration signal data and the electric box data, and respectively extract features from the preprocessed vibration signal data and the electric box data to obtain vibration feature data and electric box feature data;
  • the welding quality detection module is used to input the vibration characteristic data and the electric box characteristic data into multiple target learning models respectively to obtain the detection result output by each target learning model, wherein the detection result output by the target learning model is a qualified probability value;
  • the result output module is used to take the average of the qualified probability values output by all target learning models to obtain the final ultrasonic welding quality inspection results.
  • the result output module is further used to:
  • the welding quality grades of the final ultrasonic welding quality inspection results are determined, wherein the welding quality grades include qualified, critically qualified, critically unqualified and unqualified.
  • the feature extraction module is specifically used for:
  • the vibration signal data is segmented to obtain the vibration signal data of the pressing and preheating stage, the dry friction stage and the plastic deformation welding stage corresponding to the ultrasonic welding process;
  • the vibration signal data of the pressing preheating stage, dry friction stage and plastic deformation welding stage after noise filtering are respectively subjected to time domain feature extraction, frequency domain feature extraction and time-frequency domain feature extraction;
  • the time domain characteristic data, frequency domain characteristic data and time-frequency domain characteristic data of the pressing and preheating stage, the dry friction stage and the plastic deformation welding stage are spliced to obtain the vibration characteristic data;
  • a model training module is also included.
  • the model training module is used to:
  • Preprocessing the vibration signal data samples and the electric box data samples respectively extracting features from the preprocessed vibration signal data samples and the electric box data samples to obtain vibration feature sample data and electric box feature sample data;
  • the training set, validation set and test set are used to perform model training, model parameter adjustment and testing on all learning models to obtain the corresponding target learning model.
  • the ultrasonic welding quality detection method provided by the present invention obtains vibration signal data and electrical box data of ultrasonic welding, pre-processes and extracts features of the vibration signal data and the electrical box data, and then uses multiple learning models to perform welding quality detection, and finally takes the average of the detection results of multiple learning models as the final ultrasonic welding quality detection result.
  • the entire quality detection process is not destructive to the battery cell and the battery cell tabs.
  • the vibration signal data is process data
  • the electrical box data is result data.
  • the ultrasonic welding quality detection system provided by the present invention is used to execute the ultrasonic welding quality detection method provided by the present invention. Its principle and technical effects are the same as those of the ultrasonic welding quality detection method provided by the present invention, and will not be repeated here.
  • FIG1 is a schematic flow chart of an ultrasonic welding quality detection method provided in the present invention.
  • FIG2 is a schematic diagram of vibration signal data segmentation provided in the present invention.
  • FIG. 3 is a schematic structural diagram of an ultrasonic welding quality detection system provided in the present invention.
  • the present invention provides an embodiment of an ultrasonic welding quality detection method, including:
  • Step 101 collecting vibration signal data on the welding base of the ultrasonic welding machine and the electrical box data of the ultrasonic welding machine.
  • the electric box data of the ultrasonic welding machine is obtained through a PLC (Programmable Logic Controller), and the electric box data includes power, three-phase current, three-phase voltage, phase difference and impedance angle.
  • the vibration signal data is collected through an acceleration sensor and a data acquisition card installed on the welding base of the ultrasonic welding machine.
  • Step 102 pre-process the vibration signal data and the electric box data, and perform feature extraction on the pre-processed vibration signal data and the electric box data to obtain vibration feature data and electric box feature data.
  • the vibration signal data and electric box data directly obtained contain a lot of noise, so it is necessary to preprocess the vibration signal data and electric box data, and perform normalization on the electric box data to reduce the complexity of data processing and improve detection efficiency.
  • the vibration signal data is subjected to noise filtering and digital filtering to filter out noise data and intercept effective frequency band data.
  • noise filtering and digital filtering to filter out noise data and intercept effective frequency band data.
  • PCA dimension reduction operations are used for feature extraction to obtain electric box feature data.
  • time domain feature extraction, frequency domain feature extraction, and time-frequency domain feature extraction are performed respectively to obtain vibration feature data.
  • the time domain feature extraction of vibration signal data specifically extracts mean, variance, and deviation features
  • the frequency domain feature extraction specifically extracts frequency, amplitude, and center of gravity frequency
  • the video domain feature extraction specifically extracts real-time frequency and real-time amplitude.
  • the process of preprocessing the vibration signal data includes:
  • Data segmentation of the vibration signal is performed to obtain the vibration signal data of the pressing and preheating stage, dry friction stage, and plastic deformation welding stage corresponding to the ultrasonic welding process.
  • the ultrasonic welding process is divided into three stages: pressing and preheating stage, dry friction stage, and plastic deformation welding stage.
  • the vibration signal is segmented by a digital filter to segment the data of the pressing and preheating stage, dry friction stage, and plastic deformation welding stage in the vibration signal data.
  • the vibration signal data of the compression preheating stage, dry friction stage and plastic deformation welding stage after noise filtering are respectively subjected to time domain feature extraction, frequency domain feature extraction and time-frequency domain feature extraction. That is, the vibration signal data of the three stages in the ultrasonic welding process are subjected to time domain feature extraction, frequency domain feature extraction and time-frequency domain feature extraction.
  • the time domain characteristic data, frequency domain characteristic data and time-frequency domain characteristic data of the pressing and preheating stage, the dry friction stage and the plastic deformation welding stage are spliced to obtain vibration characteristic data.
  • the time domain characteristic data, frequency domain characteristic data and time-frequency domain characteristic data of the pressing and preheating stage, the dry friction stage and the plastic deformation welding stage are spliced to obtain the time domain characteristic data, frequency domain characteristic data and time-frequency domain characteristic data corresponding to the vibration signal data, which are collectively referred to as vibration characteristic data.
  • Step 103 Input the vibration characteristic data and the electric box characteristic data into a plurality of target learning models respectively to obtain the detection result output by each target learning model, wherein the detection result output by the target learning model is a qualified probability value.
  • the target learning model is a pre-trained and tested learning model, such as a random forest algorithm model, a BP neural network model, and a CNN model, etc. Its input is vibration feature data and electrical box features, and its output is a qualified probability value.
  • the training and testing process of the learning model includes:
  • the welding quality labels can be qualified, critically qualified, critically unqualified and unqualified.
  • the welding quality labels are obtained by performing a tear force test on the welding object. For example, for a welded battery cell tab, if the tensile force is greater than 45N, it can be considered qualified and indicated by OK; for a welded battery cell tab, if the tensile force is between 42N and 45N, it can be considered critically qualified and indicated by critical OK; for a welded battery cell tab, if the tensile force is between 38N and 41N, it can be considered critically unqualified and indicated by critical NG; for a welded battery cell tab, if the tensile force is less than 38N, it can be considered unqualified and indicated by NG.
  • sample data set consisting of vibration feature sample data, electrical box feature sample data, and corresponding welding quality labels, and divide the sample data set into a training set, a validation set, and a test set.
  • the ratio of the training set, the validation set, and the test set is 8:1:1.
  • Step 104 average the qualified probability values output by all target learning models to obtain the final ultrasonic welding quality detection result.
  • the welding quality level of the final ultrasonic welding quality test result can be determined, wherein the welding quality level includes qualified, critically qualified, critically unqualified and unqualified.
  • the corresponding relationship between the preset welding quality classification level and the qualified probability value is: greater than 60% corresponds to qualified, between 56% and 60% corresponds to critically qualified, between 50% and 55% corresponds to critically unqualified, and less than 50% is considered unqualified.
  • the ultrasonic welding quality detection method provided by the present invention obtains vibration signal data and electrical box data of ultrasonic welding, pre-processes and extracts features of the vibration signal data and the electrical box data, and then uses multiple learning models to perform welding quality detection, and finally takes the average of the detection results of multiple learning models as the final ultrasonic welding quality detection result.
  • the entire quality detection process is not destructive to the battery cell and the battery cell tabs.
  • the vibration signal data is process data
  • the electrical box data is result data.
  • an ultrasonic welding quality detection system including:
  • a data acquisition module is used to collect vibration signal data on the welding base of the ultrasonic welding machine and the electrical box data of the ultrasonic welding machine;
  • a feature extraction module is used to preprocess the vibration signal data and the electric box data, and respectively extract features from the preprocessed vibration signal data and the electric box data to obtain vibration feature data and electric box feature data;
  • the welding quality detection module is used to input the vibration characteristic data and the electric box characteristic data into multiple target learning models respectively to obtain the detection result output by each target learning model, wherein the detection result output by the target learning model is a qualified probability value;
  • the result output module is used to take the average of the qualified probability values output by all target learning models to obtain the final ultrasonic welding quality inspection results.
  • the result output module is also used to:
  • the welding quality grades of the final ultrasonic welding quality inspection results are determined, wherein the welding quality grades include qualified, critically qualified, critically unqualified and unqualified.
  • the feature extraction module is specifically used for:
  • the vibration signal data is segmented to obtain the vibration signal data of the pressing and preheating stage, the dry friction stage and the plastic deformation welding stage corresponding to the ultrasonic welding process;
  • the vibration signal data of the pressing preheating stage, dry friction stage and plastic deformation welding stage after noise filtering are respectively subjected to time domain feature extraction, frequency domain feature extraction and time-frequency domain feature extraction;
  • the time domain characteristic data, frequency domain characteristic data and time-frequency domain characteristic data of the pressing and preheating stage, the dry friction stage and the plastic deformation welding stage are spliced to obtain the vibration characteristic data;
  • the model training module is used to:
  • Preprocessing the vibration signal data samples and the electric box data samples respectively extracting features from the preprocessed vibration signal data samples and the electric box data samples to obtain vibration feature sample data and electric box feature sample data;
  • the training set, validation set and test set are used to perform model training, model parameter adjustment and testing on all learning models to obtain the corresponding target learning model.
  • the data of the electric box include power, three-phase current, three-phase voltage, phase difference and impedance angle.
  • Multiple target learning models include random forest algorithm models.
  • the ultrasonic welding quality detection system provided by the present invention is used to execute the ultrasonic welding quality detection method provided by the present invention. Its principle and technical effects are the same as those of the ultrasonic welding quality detection method provided by the present invention, and will not be repeated here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Chemical & Material Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • General Engineering & Computer Science (AREA)
  • Biochemistry (AREA)
  • Analytical Chemistry (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Electrochemistry (AREA)
  • Acoustics & Sound (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Signal Processing (AREA)
  • Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)

Abstract

La présente invention divulgue un procédé et un système de test de qualité de soudage par ultrasons. Le procédé consiste : à collecter des données de signal de vibration sur un siège de soudage d'une machine de soudage par ultrasons et des données de boîte électrique de la machine de soudage par ultrasons ; à prétraiter les données de signal de vibration et les données de boîte électrique et à effectuer respectivement une extraction de caractéristique sur les données de signal de vibration prétraitées et sur les données de boîte électrique prétraitées pour obtenir des données de caractéristique de vibration et des données de caractéristique de boîte électrique ; à entrer respectivement les données de caractéristique de vibration et les données de caractéristique de boîte électrique dans une pluralité de modèles d'apprentissage cibles pour obtenir un résultat de test qui est fourni en sortie par chaque modèle d'apprentissage cible, le résultat de test qui est fourni en sortie par le modèle d'apprentissage cible, étant une valeur de probabilité d'acceptation ; et à obtenir la valeur moyenne des valeurs de probabilité d'acceptation qui sont fournies en sortie par tous les modèles d'apprentissage cibles, de façon à obtenir un résultat final de test de qualité de soudage par ultrasons. Par conséquent, le problème technique d'un procédé d'évaluation de qualité de soudage par ultrasons existant pour une languette de cellule qui est défavorable à la popularisation et à l'utilisation en raison d'un résultat de test de qualité qui est obtenu au moyen d'un test destructif, est résolu.
PCT/CN2022/139648 2022-10-31 2022-12-16 Procédé et système de test de qualité de soudage par ultrasons WO2024092972A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211349462.5 2022-10-31
CN202211349462.5A CN115656327A (zh) 2022-10-31 2022-10-31 一种超声波焊接质量检测方法和系统

Publications (1)

Publication Number Publication Date
WO2024092972A1 true WO2024092972A1 (fr) 2024-05-10

Family

ID=84996095

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/139648 WO2024092972A1 (fr) 2022-10-31 2022-12-16 Procédé et système de test de qualité de soudage par ultrasons

Country Status (2)

Country Link
CN (1) CN115656327A (fr)
WO (1) WO2024092972A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106735842A (zh) * 2017-03-24 2017-05-31 上海骄成机电设备有限公司 一种实时检测焊接质量的超声波焊机
CN206583741U (zh) * 2017-04-06 2017-10-24 贵阳白云中航紧固件有限公司 一种用于紧固件质量检测的设备
CN109900809A (zh) * 2019-03-20 2019-06-18 杭州成功超声设备有限公司 用于超声波焊接质量检测的底模、检测系统及方法
WO2021175552A1 (fr) * 2020-03-03 2021-09-10 Telsonic Holding Ag Dispositif de traitement à dispositif de mesure et procédé associé d'activation
CN113909667A (zh) * 2021-10-19 2022-01-11 厦门乃尔电子有限公司 一种基于振动数据的超声波焊接机的焊接质量评估方法
CN114623865A (zh) * 2021-08-24 2022-06-14 万向一二三股份公司 一种锂离子电池焊接质量的评估装置和方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106735842A (zh) * 2017-03-24 2017-05-31 上海骄成机电设备有限公司 一种实时检测焊接质量的超声波焊机
CN206583741U (zh) * 2017-04-06 2017-10-24 贵阳白云中航紧固件有限公司 一种用于紧固件质量检测的设备
CN109900809A (zh) * 2019-03-20 2019-06-18 杭州成功超声设备有限公司 用于超声波焊接质量检测的底模、检测系统及方法
WO2021175552A1 (fr) * 2020-03-03 2021-09-10 Telsonic Holding Ag Dispositif de traitement à dispositif de mesure et procédé associé d'activation
CN114623865A (zh) * 2021-08-24 2022-06-14 万向一二三股份公司 一种锂离子电池焊接质量的评估装置和方法
CN113909667A (zh) * 2021-10-19 2022-01-11 厦门乃尔电子有限公司 一种基于振动数据的超声波焊接机的焊接质量评估方法

Also Published As

Publication number Publication date
CN115656327A (zh) 2023-01-31

Similar Documents

Publication Publication Date Title
Yang et al. Vibration singularity analysis for milling tool condition monitoring
CN111354366B (zh) 一种异常声音检测方法及异常声音检测装置
CN104597124B (zh) 一种基于声音频谱拟合的金属罐装产品质量在线检测方法
US20120253694A1 (en) Method and apparatus for judging status of mechanical system
WO2021068983A1 (fr) Procédé et système de détermination de qualité d'impact de soudure soudée en fonction de la reconnaissance d'informations acoustiques intelligente
CN109142547B (zh) 一种基于卷积神经网络的声学在线无损检测方法
CN112660745B (zh) 托辊故障智能诊断方法、系统及可读存储介质
Zhou et al. A new method to classify railway vehicle axle fatigue crack AE signal
CN111160241B (zh) 一种基于深度学习的配电网故障分类方法、系统和介质
US20220023979A1 (en) Method for non-destructively testing a quality of an ultrasonic weld
CN111044621A (zh) 一种基于声音品质及声学特征的无损检测系统及方法
Dias et al. A histogram of oriented gradients approach for detecting broken bars in squirrel-cage induction motors
Lopez-Ramirez et al. Automatic early broken-rotor-bar detection and classification using Otsu segmentation
WO2024092972A1 (fr) Procédé et système de test de qualité de soudage par ultrasons
CN116778964A (zh) 一种基于声纹识别的变电设备故障监测系统及方法
CN111879514A (zh) 基于elm模型的无刷直流电机轴承故障诊断方法
CN117292713A (zh) 基于端边云协同的变压器声纹监测方法及系统
CN112420074A (zh) 一种汽车后视镜电机异响声音的诊断方法
CN115128130B (zh) 一种基于动态电阻信号的电阻点焊质量在线评估系统和方法
CN111860241A (zh) 一种基于小波包分析的电力设备放电故障识别方法
Miao et al. Sound-based improved densenet conveyor belt longitudinal tear detection
Shi et al. Anvil state identification based on acceleration signals in ultrasonic metal welding of lithium batteries
Florentino et al. Spectral Subband Centroid Energy Vectors Algorithm and Artificial Neural Networks for Acoustic Emission Pattern lassification.
Rex et al. A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networks
CN109633512B (zh) 一种全光纤电流互感器故障诊断方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22964267

Country of ref document: EP

Kind code of ref document: A1