WO2020181759A1 - 微型变压器生产线的设备故障和潜在不良品智能预测系统 - Google Patents

微型变压器生产线的设备故障和潜在不良品智能预测系统 Download PDF

Info

Publication number
WO2020181759A1
WO2020181759A1 PCT/CN2019/107665 CN2019107665W WO2020181759A1 WO 2020181759 A1 WO2020181759 A1 WO 2020181759A1 CN 2019107665 W CN2019107665 W CN 2019107665W WO 2020181759 A1 WO2020181759 A1 WO 2020181759A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
equipment
software
production line
equipment failure
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.)
Ceased
Application number
PCT/CN2019/107665
Other languages
English (en)
French (fr)
Inventor
王健
谢晋
阮诗扬
万睿
叶棣中
王日森
何铨鹏
杨浩
梁嘉晋
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.)
Dongguan Jialong Haijie Electronic Technology Co Ltd
Guigang Jialong Haijie Electronic Technology Co Ltd
South China University of Technology SCUT
Original Assignee
Dongguan Jialong Haijie Electronic Technology Co Ltd
Guigang Jialong Haijie Electronic Technology Co Ltd
South China University of Technology SCUT
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 Dongguan Jialong Haijie Electronic Technology Co Ltd, Guigang Jialong Haijie Electronic Technology Co Ltd, South China University of Technology SCUT filed Critical Dongguan Jialong Haijie Electronic Technology Co Ltd
Publication of WO2020181759A1 publication Critical patent/WO2020181759A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Program-control systems
    • G05B19/02—Program-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01F—MAGNETS; INDUCTANCES; TRANSFORMERS; SELECTION OF MATERIALS FOR THEIR MAGNETIC PROPERTIES
    • H01F41/00—Apparatus or processes specially adapted for manufacturing or assembling magnets, inductances or transformers; Apparatus or processes specially adapted for manufacturing materials characterised by their magnetic properties
    • 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
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the invention relates to the field of micro-transformer manufacturing and equipment monitoring, in particular to an intelligent prediction system for equipment failure and potential defective products of a micro-transformer production line.
  • the existing micro-transformer product performance parameter detection equipment can realize product performance parameter detection and product classification functions, but cannot store production data online.
  • potential defective products cannot be screened out through artificially set test standard lines (potential defective products are defined as products whose performance parameters meet the test standards but the number of cycles has not yet met the requirements).
  • current equipment maintenance usually adopts the mode of post-repair, and the diagnosis of equipment faults mainly relies on human experience, resulting in a waste of production time.
  • the main purpose of the present invention is to provide an intelligent prediction system for equipment failures and potential defective products of a miniature transformer production line in view of the deficiencies in the prior art, which realizes the function of predicting equipment failures and potential defective products, thereby effectively reducing the factors
  • the downtime caused by the failure of production line equipment saves production management costs, improves production efficiency and the rate of quality of products out of the factory; in addition, data sharing can facilitate subsequent use by related personnel.
  • An intelligent prediction system for equipment failure and potential defective products of a micro transformer production line including product performance parameter testing equipment, testing instruments, vibration sensors, data acquisition software, data analysis software, workstations, experience databases and industrial control software;
  • the vibration sensor is connected to the product performance parameter detection equipment; the workstation installs the experience database and is respectively associated with the data acquisition software, data analysis software, and industrial control software; the test instrument is set in the product performance parameter detection equipment Above, the product performance parameter detection equipment is provided with a PLC; the data acquisition software communicates with the test instrument and the vibration sensor respectively; the industrial control software communicates with the PLC;
  • 2Data analysis software processes the collected equipment vibration signals, analyzes equipment operating conditions through equipment failure prediction models and synchronizes the results to the experience database;
  • the industrial control software sends control signals to the PLC according to the failure prediction results to realize the control of the equipment running/stopping state
  • the data analysis software compares the collected product performance parameters with the set standard values, and judges the product qualification. When the product is unqualified, skip to step 4, otherwise continue to the next step;
  • the data analysis software uses the product quality prediction model to further classify the qualified products judged in step 2 as good products or potentially defective products;
  • the data analysis software synchronizes the judgment results to the experience database, and instructs the industrial control software to send control signals to the PLC to realize product classification;
  • 5Data analysis software calculates production line efficiency based on statistical product data and monitors the overall quality of product batches in real time.
  • the product performance parameter detection equipment is provided with a slider, and the slider is provided with a test needle; in the equipment failure prediction function realization step 2, the equipment operating status includes the test on the slider Either the probe is working properly, is offset or damaged.
  • the equipment failure prediction model is:
  • ⁇ z is the equipment failure factor
  • A is the amplitude of the vibration signal
  • x is the product performance parameter detection index corresponding to the position of the vibration sensor
  • N is the number of times the product is tested
  • M Set the number of inspection data for qualified products
  • M and N are both positive integers and M ⁇ N.
  • the online collection product performance parameters include any one of inductance L, product value factor Q, waveform area difference S, and resistance R.
  • step 3 of implementing the function of predicting potential defective products the product quality prediction model is:
  • ⁇ d is the product quality factor
  • a 1 , a 2 , a 3 and a 4 are the weight values
  • max and min represent the upper and lower limits of the corresponding variables
  • the functions implemented potentially defective prediction step 5 comprises: calculating the rate of good product [eta], when ⁇ cr, industrial control software sent to the PLC control Signal, product performance parameter detection equipment stops testing and alarms; among them, ⁇ cr is a threshold set according to market and customer needs.
  • equipment failure prediction is first performed, and then potential defective products are predicted.
  • the data analysis software automatically generates reports based on statistical equipment failure predictions and product-related data, and shares them to the MES system in real time.
  • the present invention has the following beneficial effects:
  • the potential defective products can be further screened from qualified products to improve the good rate of manufactured products;
  • the equipment failure prediction and product data stored in the system can be shared to the MES system for subsequent use by relevant personnel.
  • Figure 1 is a schematic diagram of the structure of the intelligent prediction system for equipment failure and potential defective products of the micro transformer production line;
  • Figure 2 is a flow chart of the intelligent prediction system for equipment failure and potential defective products of the micro transformer production line
  • FIG. 3 is a flowchart of the equipment failure prediction function
  • Figure 4 is a flowchart of the function of predicting potential defective products
  • Figure 5a is the corresponding vibration signal diagram when the test probe is working normally
  • Figure 5b is the corresponding vibration signal diagram when the test probe is shifted
  • Figure 5c is the corresponding vibration signal diagram when the test probe is damaged
  • Figure 6 is the UI interface diagram of the system.
  • FIG. 1 to FIG. 6 show the specific structure of the embodiment of the present invention, but the embodiment of the present invention is not limited to this:
  • an intelligent prediction system for equipment failure and potential defective products of a micro transformer production line includes product performance parameter detection equipment 1, testing equipment 2, vibration sensors 4, data acquisition software 5, data analysis software 6, and workstation 7 , Experience database 8 and industrial control software 9;
  • the vibration sensor 4 is connected to the product performance parameter detection equipment 1; the workstation 7 installs the experience database 8 and is respectively associated with the data acquisition software 5, data analysis software 6, and industrial control software 9; the test instrument 2 Set on the product performance parameter detection device 1, the product performance parameter detection device 1 is provided with a PLC10; the data acquisition software 5 communicates with the test instrument 2, the vibration sensor 4 respectively; the industrial control software 9 communicates with the PLC10 ;
  • the data acquisition software 5 collects equipment vibration signals online through the vibration sensor 4 and stores them in the experience database 8;
  • the data analysis software 6 processes the collected equipment vibration signals.
  • Figure 5a, Figure 5b, Figure 5c analyze the equipment operation status through the equipment failure prediction model and synchronize the results to the experience database 8; the product performance parameter detection equipment 1 is set There is a slider 3, the vibration sensor 4 is fixed on the slider 3 of the product performance parameter detection device 1 by screw connection; the slider 3 is provided with a test pin; in the equipment failure prediction function realization step 2, the The operating conditions of the equipment include any of the test probes on the slider 3 working normally, offset or damaged; the reason for adopting the above-mentioned vibration sensor installation scheme is that the test probes are the key components of the product performance parameter testing equipment. Frequent and close contact with the surface of the tested part is prone to deviation and damage.
  • vibration sensor on the slider can directly collect the vibration signal of the test probe.
  • multiple vibration sensors can be installed on the equipment at key stations at the same time, and the vibration sensors can be used to predict equipment failures online to ensure production efficiency, and pass the optimized classification algorithm and online product performance parameters. Accurately judge product quality.
  • the equipment failure prediction model is:
  • ⁇ z is the equipment failure factor
  • A is the amplitude of the vibration signal
  • x is the product performance parameter detection index corresponding to the position of the vibration sensor
  • N is the number of times the product is tested
  • ⁇ z ⁇ z cr1 normal operation; when ⁇ z ⁇ z cr2, the test probe is damaged, or the test probe offset occurs; wherein, ⁇ z cr1 and ⁇ z cr2 and stability of the equipment is set according to the position of the vibration sensor The threshold.
  • the above ⁇ z cr1 ⁇ z cr2 and the setting mode Acquisition and processing a plurality of test probes work, damage to the vibration signal offset and device stability and position-related vibration sensors, calculates the corresponding [Delta] z appears and stores experience database, and to determine the range and ⁇ z cr2 ⁇ z cr1 through empirical data. Furthermore, a vibration signal apparatus system subsequent runs will continue to optimize the experience acquired in the database, and can ⁇ z cr1 ⁇ z cr2 more accurate range.
  • 3Industrial control software 9 sends a control signal to PLC10 according to the failure prediction result to realize the control of equipment running/stop status;
  • the online collection product performance parameters include inductance L and product value factor Q. Wave area difference S and resistance R.
  • the storage unit can be set on the data acquisition software according to user needs. Therefore, the collected product performance parameters include but are not limited to one or more of the inductance L, the product value factor Q, the waveform area difference S, and the resistance R.
  • the data analysis software 6 compares the collected product performance parameters with the set standard values, and judges the qualification of the product. When the product is unqualified, skip to step 4, otherwise continue to the next step;
  • the data analysis software 6 uses the product quality prediction model to further classify the qualified products judged in step 2 as good products or potential defective products; in step 3, the product quality prediction model is:
  • ⁇ d is the product quality factor
  • a 1 , a 2 , a 3 and a 4 are the weight values
  • max and min represent the upper and lower limits of the corresponding variable
  • ⁇ d cr is a threshold set according to market and customer needs.
  • 0.8 ⁇ d cr ⁇ 0.9.
  • the data analysis software 6 synchronizes the judgment results to the experience database 8, and instructs the industrial control software 9 to send control signals to the PLC 10 to realize product classification;
  • Forecasting potential defective implement step 5 the real-time monitoring of the overall quality of the product batch mode comprises: calculating the rate of good product [eta], when ⁇ cr, industrial control software 9 sends control signals to the PLC 10, product performance parameters
  • the detection device 1 stops the test and gives an alarm; where ⁇ cr is a threshold set according to market and customer requirements, usually 97% ⁇ ⁇ cr ⁇ 99%.
  • the equipment failure prediction is carried out first, and then the potential defective products are predicted.
  • the reason for giving priority to equipment failure prediction is that when the equipment is abnormal, the system can stop the test and give an alarm in time to improve the accuracy of product performance parameter detection and reduce the misjudgment rate of potential defective product prediction.
  • the data analysis software 6 automatically generates reports based on statistical equipment failure predictions and product-related data, and shares them to the MES system in real time.
  • Figure 2 is a flow chart of intelligent prediction of equipment failures and potential defective products of the miniature transformer production line. The specific steps are as follows:
  • the data collection software 5 collects equipment vibration signals on-line through the vibration sensor 4 and the testing instrument 2 to test the amplitude A and product performance parameters generated by the vibration of the probe.
  • the inductance L, quality factor, quality Q, and waveform area of the micro transformer The difference S and resistance R are stored in the experience database 8;
  • the data analysis software 6 processes and analyzes the collected equipment vibration signals and product performance parameters to realize equipment failure prediction and potential defective product prediction. The detailed steps are shown in Figure 3 and Figure 4;
  • FIG. 3 is a flowchart of the equipment failure prediction function. The specific steps are described as follows:
  • 3 further determines the type of equipment failure, when ⁇ z cr1 ⁇ z ⁇ When ⁇ z cr2, test probe offset occurs, when ⁇ z ⁇ z cr2, the test probe is damaged;
  • Figure 4 shows the detailed process of predicting potential defective products. The specific steps are as follows:
  • the vibration sensor EK-43797I is fixed on the energized current test slider of the product performance parameter detection equipment through a threaded connection.
  • the workstation is installed with an experience database and is associated with data acquisition software, data analysis software and industrial control software.
  • the acquisition software is associated with the vibration sensor of the product performance parameter detection equipment, and the industrial control software communicates with the product performance parameter detection equipment PLC.
  • set the upper and lower limits of the vibration signal amplitude to 10V and 0, and adjust the test probe artificially to sample time t 10s.
  • the test slider movement cycle is 2s.
  • the test probe works normally, and the vibration signals corresponding to the three equipment operating conditions of deviation and damage are shown in Figures 5a, 5b and 5c. Since the test probe is in close contact with the product surface during normal operation, the vibration signal amplitude A obtained in each cycle is always greater than 4V. However, due to the deviation and damage of the test probe and the reduced contact with the product surface, the corresponding vibration signal amplitude A drops to 4V and 2V, respectively.
  • the detected product performance parameters are related to the operating conditions of the equipment. Therefore, based on the characteristics of the above-mentioned vibration signal and product qualification, the equipment failure prediction model is established and its weight value is determined:
  • Equation 3 is only an example in the present invention.
  • the workstation installs an empirical database and associates it with data acquisition software, data analysis software, and industrial control software.
  • the data acquisition software is associated with product performance parameter testing equipment
  • industrial control software is associated with product performance parameters.
  • the system UI interface is shown in Figure 6, including display product performance parameters (measured values and corresponding dynamic data), product quality judgment results, product classification good products, potential defective products and unqualified products, production parameter efficiency and good rate, PLC port Window.
  • the data analysis software sends a signal to the industrial control software, through the M0 input terminal to control the Y0 output terminal of the PLC to realize product classification; through the M1 input terminal to control the Y1 output terminal of the PLC to realize the equipment failure Stop the test and alarm.
  • Product quality judgment standards are related to customer needs. Therefore, establish a product quality prediction model based on the standard values of product parameters and determine its weight value:
  • Equation 4 is only an example in the present invention.
  • the key point of the design of the present invention is that it mainly adopts the intelligent prediction system for equipment failure and potential defective products of the micro transformer production line, which can not only predict equipment failures, but also effectively shorten the downtime caused by production line equipment failures, and save production Manage costs, and can further screen out potential defective products from qualified products, and improve the rate of good and good products.
  • data sharing can facilitate subsequent use by related personnel.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Manufacturing & Machinery (AREA)
  • Power Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Quality & Reliability (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • General Factory Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种微型变压器生产线的设备故障和潜在不良品智能预测系统，包括产品性能参数检测设备(1)、测试仪器(2)、振动传感器(4)、数据采集软件(5)、数据分析软件(6)、工作站(7)、经验数据库(8)和工业控制软件(9)；通过在产品性能参数检测设备(1)上设置振动传感器(4)，工作站(7)安装经验数据库(8)并与数据采集软件(5)、数据分析软件(6)和工业控制软件(9)关联，数据采集软件(5)与测试仪器(2)、振动传感器(4)通讯，工业控制软件(9)与PLC(10)通讯，可实现设备故障和潜在不良品预测功能，进而有效缩短因产线设备故障导致的停机时间，节约生产管理成本，提高出厂产品优良率。此外，通过数据共享可方便相关人员的后续使用。

Description

微型变压器生产线的设备故障和潜在不良品智能预测系统 技术领域
本发明涉及微型变压器生产制造和设备监测领域，具体涉及一种微型变压器生产线的设备故障和潜在不良品智能预测系统。
背景技术
在现代工业中，生产智能化有利于保证产品质量及提高生产效率。然而，因实际中的设备多样性和生产过程不确定性使得设备与设备之间、设备与PC之间难以关联，导致生产智能化水平较低，生产数据浪费等问题。
针对微型变压器生产领域，现有的微型变压器产品性能参数检测设备可实现产品性能参数检测和产品分类功能，但无法在线存储生产数据。而且，在产品性能参数检测过程中，通过人为设定的测试标准线无法筛选出潜在不良品(潜在不良品定义为各项性能参数均达到测试标准但循环使用次数尚未满足要求的产品)。此外，目前的设备维护通常采取事后维修的模式，而且对设备故障诊断主要依赖于人为经验，导致生产时间的浪费。
因此，需要研究出一种新的技术方案来解决上述问题。
发明内容
有鉴于此，本发明针对现有技术存在之缺失，其主要目的是提供一种微型变压器生产线的设备故障和潜在不良品智能预测系统，其实 现设备故障和潜在不良品预测功能，进而有效缩短因产线设备故障导致的停机时间，节约生产管理成本，提高生产效率及出厂产品优良率；此外，通过数据共享可方便相关人员的后续使用。
本发明解决上述技术问题的技术方案是：
一种微型变压器生产线的设备故障和潜在不良品智能预测系统，包括产品性能参数检测设备、测试仪器、振动传感器、数据采集软件、数据分析软件、工作站、经验数据库和工业控制软件；
所述振动传感器连接在产品性能参数检测设备上；所述工作站安装所述经验数据库并分别与所述数据采集软件、数据分析软件、工业控制软件关联；所述测试仪器设置于产品性能参数检测设备上，所述产品性能参数检测设备上设置有PLC；所述数据采集软件分别与测试仪器、振动传感器通讯；所述工业控制软件与PLC通讯；
设备故障预测功能实现步骤为：
①设置系统参数，数据采集软件通过振动传感器在线采集设备振动信号并存储至经验数据库；
②数据分析软件处理采集的设备振动信号，通过设备故障预测模型分析设备运行状况并将结果同步至经验数据库；
③工业控制软件根据故障预测结果向PLC发出控制信号，实现设备运行/停止状态的控制；
潜在不良品预测功能实现步骤为：
①设置系统参数，数据采集软件通过测试仪器在线采集产品性能参数并存储至经验数据库；
②数据分析软件将采集的产品性能参数与设定的标准值比较，判断产品合格情况，当产品不合格时跳转至步骤④，否则继续执行下一步；
③数据分析软件通过产品质量预测模型，将步骤②中判断的合格产品进一步归类为优良品或潜在不良品；
④数据分析软件将判断的结果同步至经验数据库，并指示工业控制软件向PLC发出控制信号，实现产品分类；
⑤数据分析软件根据统计的产品数据计算产线效率并实时监测产品批次整体质量。
作为一种优选方案，所述产品性能参数检测设备上设置有滑块，所述滑块上设置有测试针；在设备故障预测功能实现步骤②中，所述设备运行状况包括滑块上的测试探针正常工作、出现偏移或损坏中任一种。
作为一种优选方案，在设备故障预测功能实现步骤②中，所述设备故障预测模型为：
Figure PCTCN2019107665-appb-000001
式中，Δz为设备故障因数，A为振动信号幅值，x为振动传感器位置对应的产品性能参数检测指数，取经验数据库最近N次的检测数据，N为设定检测产品数据次数，M为设定合格产品检测数据次数，M、N均为正整数且M≤N，当实际合格产品检测数据次数小于M时，x＝1；否则x＝0，k i和k 0为权重值，max和min代表对应变量的上限和下限；当Δz≤Δz cr1时，设备正常运行；当Δz≥Δz cr2时， 测试探针出现损坏，否则测试探针出现偏移；其中，Δz cr1和Δz cr2为根据设备稳定性和振动传感器位置设定的阈值。
作为一种优选方案，0.6≤Δz cr1≤0.7，0.8≤Δz cr2Δz cr1≤0.9。
作为一种优选方案，在潜在不良品预测功能实现步骤①中，所述在线采集产品性能参数包括电感L、品值因数Q、波形面积差S和电阻R中的任一种。
作为一种优选方案，在潜在不良品预测功能实现步骤③中，所述产品质量预测模型为：
Figure PCTCN2019107665-appb-000002
式中，Δd为产品质量因数，a 1，a 2，a 3和a 4为权重值，max和min代表对应变量的上限和下限；当Δd≤Δd cr时，将产品归类为优良品，否则归类为潜在不良品；其中，Δd cr为根据市场、客户需求设定的阈值。
作为一种优选方案，0.8≤Δd cr≤0.9。
作为一种优选方案，在潜在不良品预测功能实现步骤⑤中，所述实时监测产品批次整体质量的方式包括：计算产品优良率η，当η≤η cr时，工业控制软件向PLC发出控制信号，产品性能参数检测设备停止测试并报警；其中，η cr为根据市场、客户需求设定的阈值。
作为一种优选方案，在系统运行过程中，先进行设备故障预测，再进行潜在不良品预测。
作为一种优选方案，当系统运行至设定的时间节点时，数据分析 软件根据统计的设备故障预测和产品的相关数据自动生成报表，并实时共享至MES系统。
本发明与现有技术相比具有以下的有益效果：
1.与设备的事后维修模式相比，利用系统的设备故障预测功能，技术人员可根据事先预测的设备故障及时对设备进行维护，进而有效缩短因产线设备故障导致的停机时间，节约生产管理成本；
2.与现有的微型变压器产品分类方法相比，利用系统的潜在不良品预测功能，可从合格产品中进一步筛选出潜在不良品，以提高出厂产品的优良率；
3.通过系统存储的设备故障预测和产品数据，可共享至MES系统，以便相关人员的后续使用。
为更清楚地阐述本发明的结构特征和功效，下面结合附图与具体实施例来对本发明进行详细说明：
附图说明
图1为微型变压器生产线的设备故障和潜在不良品智能预测系统组成结构示意图；
图2为微型变压器生产线的设备故障和潜在不良品智能预测系统的流程图；
图3为设备故障预测功能的流程图；
图4为潜在不良品预测功能的流程图；
图5a为测试探针正常工作时对应的振动信号图；
图5b为测试探针出现偏移时对应的振动信号图；
图5c为测试探针出现损坏时对应的振动信号图；
图6为系统的UI界面图。
附图标示说明：
1、产品性能参数检测设备    2、测试仪器
3、滑块                    4、振动传感器
5、数据采集软件            6、数据分析软件
7、工作站                  8、经验数据库
9、工业控制软件            10、PLC
具体实施方式
请参照图1至图6所示，其显示出了本发明之实施例的具体结构，但本发明的实施方式不限于此：
本实施例中，以9108型号的微型变压器产品为例，详细说明本发明的微型变压器生产线的设备故障和潜在不良品智能预测系统的工作原理，进而验证本发明的技术效果。
如图1所示，一种微型变压器生产线的设备故障和潜在不良品智能预测系统，包括产品性能参数检测设备1、测试仪器2、振动传感器4、数据采集软件5、数据分析软件6、工作站7、经验数据库8和工业控制软件9；
所述振动传感器4连接在产品性能参数检测设备1上；所述工作站7安装所述经验数据库8并分别与所述数据采集软件5、数据分析 软件6、工业控制软件9关联；所述测试仪器2设置于产品性能参数检测设备1上，所述产品性能参数检测设备1上设置有PLC10；所述数据采集软件5分别与测试仪器2、振动传感器4通讯；所述工业控制软件9与PLC10通讯；
设备故障预测功能实现步骤为：
①设置系统参数，数据采集软件5通过振动传感器4在线采集设备振动信号并存储至经验数据库8；
②数据分析软件6处理采集的设备振动信号例如：图5a、图5b、图5c，通过设备故障预测模型分析设备运行状况并将结果同步至经验数据库8；所述产品性能参数检测设备1上设置有滑块3，所述振动传感器4通过螺丝连接固定在产品性能参数检测设备1的滑块3上；所述滑块3上设置有测试针；在设备故障预测功能实现步骤②中，所述设备运行状况包括滑块3上的测试探针正常工作、出现偏移或损坏中任一种；采用上述振动传感器安装方案的原因在于：测试探针作为产品性能参数检测设备的关键零部件，需频繁且紧密与被检测件表面接触，易出现偏移和损坏。因此，将振动传感器固定在滑块上可直接采集测试探针的振动信号。根据生产线中的设备故障预测需求，可同时安装多个振动传感器在关键工位的设备上,利用振动传感器在线预测设备故障以确保生产效率，并通过优化后的分类算法和在线测的产品性能参准确判断产品质量。
在设备故障预测功能实现步骤②中，所述设备故障预测模型为：
Figure PCTCN2019107665-appb-000003
式中，Δz为设备故障因数，A为振动信号幅值，x为振动传感器位置对应的产品性能参数检测指数，取经验数据库最近N次的检测数据，N为设定检测产品数据次数，M为设定合格产品检测数据次数，M、N均为正整数且M≤N，当实际合格产品检测数据次数小于M时，x＝1；否则x＝0；例如：取经验数据库最近10次的检测数据，合格产品的数量小于7时，x＝1；否则x＝0，k i和k 0为权重值，max和min代表对应变量的上限和下限。当Δz≤Δz cr1时，设备正常运行；当Δz≥Δz cr2时，测试探针出现损坏，否则测试探针出现偏移；其中，Δz cr1和Δz cr2为根据设备稳定性和振动传感器位置设定的阈值。通常，0.6≤Δz cr1≤0.7，0.8≤Δz cr2Δz cr1≤0.9。
在实际应用中，上述Δz cr1和Δz cr2的设定方式为：采集并处理若干个测试探针正常工作，出现偏移和损坏的振动信号与设备稳定性和振动传感器位置相关，计算对应的Δz并存储至经验数据库，进而通过经验数据确定Δz cr1和Δz cr2的范围。此外，系统后续运行中获取的设备振动信号将不断优化经验数据库，可使Δz cr1和Δz cr2取值范围更精确。
③工业控制软件9根据故障预测结果向PLC10发出控制信号，实现设备运行/停止状态的控制；
潜在不良品预测功能实现步骤为：
①设置系统参数，数据采集软件5通过测试仪器2在线采集产品性能参数并存储至经验数据库8；在潜在不良品预测功能实现步骤①中，所述在线采集产品性能参数包括电感L、品值因数Q、波形面 积差S和电阻R。在实际应用中，可根据使用者需求在数据采集软件上设定存储单元。因此，采集的产品性能参数包括且不仅限于电感L、品值因数Q、波形面积差S和电阻R中的一项或多项。
②数据分析软件6将采集的产品性能参数与设定的标准值比较，判断产品合格情况，当产品不合格时跳转至步骤④，否则继续执行下一步；
③数据分析软件6通过产品质量预测模型，将步骤②中判断的合格产品进一步归类为优良品或潜在不良品；在潜在不良品预测功能实现步骤③中，所述产品质量预测模型为：
Figure PCTCN2019107665-appb-000004
(2)式中，Δd为产品质量因数，a 1，a 2，a 3和a 4为权重值，max和min代表对应变量的上限和下限；当Δd≤Δd cr时，将产品归类为优良品，否则归类为潜在不良品；其中，Δd cr为根据市场、客户需求设定的阈值。通常，0.8≤Δd cr≤0.9。
④数据分析软件6将判断的结果同步至经验数据库8，并指示工业控制软件9向PLC10发出控制信号，实现产品分类；
⑤数据分析软件6根据统计的产品数据计算产线效率并实时监测产品批次整体质量。在潜在不良品预测功能实现步骤⑤中，所述实时监测产品批次整体质量的方式包括：计算产品优良率η，当η≤η cr时，工业控制软件9向PLC10发出控制信号，产品性能参数检测设备1停止测试并报警；其中，η cr为根据市场、客户需求设定的阈值，通 常97％≤η cr≤99％。
在系统运行过程中，先进行设备故障预测，再进行潜在不良品预测。优先进行设备故障预测的原因在于：当设备出现异常时，系统可及时停止测试并报警，以提高产品性能参数检测的准确性并降低潜在不良品预测的误判率。
当系统运行至设定的时间节点时，数据分析软件6根据统计的设备故障预测和产品的相关数据自动生成报表，并实时共享至MES系统。
具体而言：
图2为微型变压器生产线的设备故障和潜在不良品智能预测流程图，具体步骤如下：
①系统参数设置：系统运行前，根据产品工艺卡设置测试仪器2的工作参数，并在数据采集软件5上设定待采集对象，测试条件参数和信号/数据存储类型等；
②数据在线采集：数据采集软件5分别通过振动传感器4和测试仪器2在线采集设备振动信号测试探针振动所产生的幅值A和产品性能参数微型变压器的电感L、品因数质Q、波形面积差S和电阻R并存储至经验数据库8；
③数据处理与分析：数据分析软件6通过处理并分析采集的设备振动信号和产品性能参数，实现设备故障预测和潜在不良品预测功能详细步骤参见图3和图4说明；
④数据共享：当系统停止测试或达到设定时间时，数据分析软 件6根据统计/计算的设备故障预测和产品的相关数据自动生成报表，并共享至MES系统。
图3为设备故障预测功能流程图，具体步骤说明如下：
①提取经验数据库8设备振动信号幅值和前10次合格产品数量，根据设备故障预测模型计算设备故障因数Δz；
②将设备故障因数Δz与阈值Δz cr1和Δz cr2进行比较，当Δz≤Δz cr1时，测试探针正常工作，否则设备出现故障；
③进一步判断设备故障类型，当Δz cr1＜Δz＜Δz cr2时，测试探针出现偏移，当Δz≥Δz cr2时，测试探针出现损坏；
④将设备故障预测结果同步至经验数据库8，若系统预测设备出现故障，指示工业控制软件9向PLC10发出控制信号，产品性能参数检测设备1停止测试并报警。
图4为潜在不良品预测详细流程，具体步骤说明如下：
①提取经验数据库8产品性能参数，根据设定的标准值判断产品合格情况，当产品不合格时跳转至步骤③，否则继续执行下一步；
②根据产品质量预测模型计算合格产品的产品质量因数Δd并与阈值Δd cr进行比较，当Δd≤Δd cr时，归类为优良品，当Δd＞Δd cr时，归类为潜在不良品；
③将产品质量判断结果同步至经验数据库8，并指示工业控制软件9向PLC10发出控制信号，实现产品分类；
④根据判断结果计算优良率η并与阈值η cr进行比较，若产品质量异常η≤η cr，指示工业控制软件9向PLC10发出控制信号，产品性 能参数检测设备1停止测试并报警。
下面通过实施例分别说明本发明中的设备故障预测和潜在不良品预测功能。
实施例1
在设备故障预测中，将振动传感器EK-43797I通过螺纹连接固定在产品性能参数检测设备的加电流测试滑块上，工作站安装经验数据库并与数据采集软件、数据分析软件和工业控制软件关联，数据采集软件与产品性能参数检测设备振动传感器相关联，工业控制软件与产品性能参数检测设备PLC通讯。为了获取测试探针正常工作，出现偏移和损坏三种设备运行状况下的振动信号，设置振动信号的幅值上下限为10V和0，并人为调节测试探针后以采样时间t＝10s进行测试滑块移动周期为2s。
测试探针正常工作，出现偏移和损坏三种设备运行状况对应的振动信号如图5a、5b和5c所示。由于测试探针正常工作时与产品表面紧密接触，每个周期下获取的振动信号幅值A始终大于4V。然而，由于测试探针出现偏移和损坏后与产品表面接触减少，相应的振动信号幅值A分别下降至4V和2V。
检测的产品性能参数与设备运行状况相关。因此，根据上述振动信号的特征和产品合格情况，建立设备故障预测模型并确定其权重值：
Figure PCTCN2019107665-appb-000005
需说明的是，当振动传感器安装位置改变时，设备故障预测模型的权重值和幅值上下限也可能发生变化，但结构形式不变，即式3仅 作为本发明中的一个例子。
此外，通过多次采集和分析三种设备运行状况下的振动信号，优化经验数据库并确定判断测试探针出现偏移和损坏的故障预测因数阈值分别为Δz cr1＝0.65和Δz cr2＝0.85。
实施例2
类似的，在潜在不良品预测中，工作站安装经验数据库并与数据采集软件、数据分析软件和工业控制软件关联，数据采集软件与产品性能参数检测设备测试仪器相关联，工业控制软件与产品性能参数检测设备PLC通讯。系统运行前，根据产品工艺卡设置测试仪器的产品测试的工作参数。其中，电感L标准值上下限为0.9mH和0.8mH；品质因数Q标准值下限为50，电阻R标准值上下限为5.2Ω和3Ω，波形面积差S标准值上下限为18％和-18％。
系统UI界面如图6所示，包括显示产品性能参数(实测值和对应动态数据)、产品质量判断结果、产品分类优良品、潜在不良品和不合格品、生产参数效率和优良率、PLC端口的窗口。其中，在PLC端口的显示窗口中，数据分析软件向工业控制软件发出信号，通过M0输入端控制PLC的Y0输出端实现产品分类；通过M1输入端控制PLC的Y1输出端实现设备在出现故障时停止测试并报警。
产品质量判断标准与客户需求相关。因此，根据产品参数标准值建立产品质量预测模型并确定其权重值：
Figure PCTCN2019107665-appb-000006
需说明的是，当检测的性能参数项改变时，产品质量预测模型的 项数和权重值也可能发生变化，但结构形式不变，即式4仅作为本发明中的一个例子。
此外，通过多次采集和分析产品性能参数，优化经验数据库并确定判断潜在不良品的产品质量因数阈值为Δd cr＝0.85。
综上所述，本发明的设计重点在于，其主要是采用微型变压器生产线的设备故障和潜在不良品智能预测系统，不仅可预测设备故障，有效缩短因产线设备故障导致的停机时间，节约生产管理成本，而且能够从合格产品中进一步筛选出潜在不良品，提高出厂产品的优良率。此外，通过数据共享可方便相关人员的后续使用。
以上所述，仅是本发明的较佳实施例而已，并非对本发明的技术范围作任何限制，故凡是依据本发明的技术实质对以上实施例所作的任何细微修改、等同变化与修饰，均仍属于本发明技术方案的范围内。

Claims (10)

  1. 一种微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：包括产品性能参数检测设备(1)、测试仪器(2)、振动传感器(4)、数据采集软件(5)、数据分析软件(6)、工作站(7)、经验数据库(8)和工业控制软件(9)；
    所述振动传感器(4)连接在产品性能参数检测设备(1)上；所述工作站(7)安装所述经验数据库(8)并分别与所述数据采集软件(5)、数据分析软件(6)、工业控制软件(9)关联；所述测试仪器(2)设置于产品性能参数检测设备(1)上，所述产品性能参数检测设备(1)上设置有PLC(10)；所述数据采集软件(5)分别与测试仪器(2)、振动传感器(4)通讯；所述工业控制软件(9)与PLC(10)通讯；
    设备故障预测功能实现步骤为：
    ①设置系统参数，数据采集软件(5)通过振动传感器(4)在线采集设备振动信号并存储至经验数据库(8)；
    ②数据分析软件(6)处理采集的设备振动信号，通过设备故障预测模型分析设备运行状况并将结果同步至经验数据库(8)；
    ③工业控制软件(9)根据故障预测结果向PLC(10)发出控制信号，实现设备运行/停止状态的控制；
    潜在不良品预测功能实现步骤为：
    ①设置系统参数，数据采集软件(5)通过测试仪器(2)在线采集产品性能参数并存储至经验数据库(8)；
    ②数据分析软件(6)将采集的产品性能参数与设定的标准值比 较，判断产品合格情况，当产品不合格时跳转至步骤④，否则继续执行下一步；
    ③数据分析软件(6)通过产品质量预测模型，将步骤②中判断的合格产品进一步归类为优良品或潜在不良品；
    ④数据分析软件(6)将判断的结果同步至经验数据库(8)，并指示工业控制软件(9)向PLC(10)发出控制信号，实现产品分类；
    ⑤数据分析软件(6)根据统计的产品数据计算产线效率并实时监测产品批次整体质量。
  2. 根据权利要求1所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：所述产品性能参数检测设备(1)上设置有滑块(3)，所述滑块(3)上设置有测试针；在设备故障预测功能实现步骤②中，所述设备运行状况包括滑块(3)上的测试探针正常工作、出现偏移或损坏中任一种。
  3. 根据权利要求1所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：在设备故障预测功能实现步骤②中，所述设备故障预测模型为：
    Figure PCTCN2019107665-appb-100001
    式中，Δz为设备故障因数，A为振动信号幅值，x为振动传感器位置对应的产品性能参数检测指数，取经验数据库最近N次的检测数据，N为设定检测产品数据次数，M为设定合格产品检测数据次数，M、N均为正整数且M≤N，当实际合格产品检测数据次数小于M时，x＝1；否则x＝0，k i和k 0为权重值，max和min代表对应变量 的上限和下限；当Δz≤Δz cr1时，设备正常运行；当Δz≥Δz cr2时，测试探针出现损坏，否则测试探针出现偏移；其中，Δz cr1和Δz cr2为根据设备稳定性和振动传感器位置设定的阈值。
  4. 根据权利要求3所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：0.6≤Δz cr1≤0.7，0.8≤Δz cr2Δz cr1≤0.9。
  5. 根据权利要求1所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：在潜在不良品预测功能实现步骤①中，所述在线采集产品性能参数包括电感L、品值因数Q、波形面积差S和电阻R中的任一种。
  6. 根据权利要求1所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：在潜在不良品预测功能实现步骤③中，所述产品质量预测模型为：
    Figure PCTCN2019107665-appb-100002
    式中，Δd为产品质量因数，a 1，a 2，a 3和a 4为权重值，max和min代表对应变量的上限和下限；当Δd≤Δd cr时，将产品归类为优良品，否则归类为潜在不良品；其中，Δd cr为根据市场、客户需求设定的阈值。
  7. 根据权利要求6所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：0.8≤Δd cr≤0.9。
  8. 根据权利要求1所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：在潜在不良品预测功能实现步骤⑤ 中，所述实时监测产品批次整体质量的方式包括：计算产品优良率η，当η≤η cr时，工业控制软件(9)向PLC(10)发出控制信号，产品性能参数检测设备(1)停止测试并报警；其中，η cr为根据市场、客户需求设定的阈值。
  9. 根据权利要求1所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：在系统运行过程中，先进行设备故障预测，再进行潜在不良品预测。
  10. 根据权利要求1所述微型变压器生产线的设备故障和潜在不良品智能预测系统，其特征在于：当系统运行至设定的时间节点时，数据分析软件(6)根据统计的设备故障预测和产品的相关数据自动生成报表，并实时共享至MES系统。
PCT/CN2019/107665 2019-03-14 2019-09-25 微型变压器生产线的设备故障和潜在不良品智能预测系统 Ceased WO2020181759A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910194092.4A CN109741927B (zh) 2019-03-14 2019-03-14 微型变压器生产线的设备故障和潜在不良品智能预测系统
CN201910194092.4 2019-03-14

Publications (1)

Publication Number Publication Date
WO2020181759A1 true WO2020181759A1 (zh) 2020-09-17

Family

ID=66370458

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/107665 Ceased WO2020181759A1 (zh) 2019-03-14 2019-09-25 微型变压器生产线的设备故障和潜在不良品智能预测系统

Country Status (2)

Country Link
CN (1) CN109741927B (zh)
WO (1) WO2020181759A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109741927B (zh) * 2019-03-14 2020-08-07 贵港市嘉龙海杰电子科技有限公司 微型变压器生产线的设备故障和潜在不良品智能预测系统
CN110673556B (zh) * 2019-09-23 2021-03-02 珠海格力电器股份有限公司 一种用于胀管过程的质量管控方法及系统
CN111212434B (zh) * 2019-12-31 2023-06-13 宁波奥克斯电气股份有限公司 一种wifi模组质量预测方法、装置、设备及存储介质
CN113066655B (zh) * 2021-03-26 2023-03-14 安徽工业大学 一种自主学习的高硅钢软磁复合铁芯智能化生产系统及生产方法
CN114625097B (zh) * 2022-05-16 2022-08-02 时代云英(深圳)科技有限公司 一种基于工业互联网的生产工艺控制方法
CN115808911B (zh) * 2023-02-02 2023-04-28 成都秦川物联网科技股份有限公司 用于生产线产生不良品时的工业物联网调控方法及系统
CN117869196B (zh) * 2023-11-29 2025-01-24 国能联合动力技术(赤峰)有限公司 风电机组生产线的装配测试数据处理系统及方法
CN121069943A (zh) * 2025-11-06 2025-12-05 南通蝶绣纺织有限公司 一种智能化纺织品生产线控制方法及系统
CN121212912B (zh) * 2025-11-25 2026-02-10 安德佳（福建）铝饰科技有限公司 一种生产线良品率智能管理方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06163293A (ja) * 1992-11-19 1994-06-10 Mitsubishi Electric Corp 生産管理方法
CN101403915A (zh) * 2008-11-07 2009-04-08 同济大学 一种可重组生产线产品质量预测方法
CN105940354A (zh) * 2014-02-10 2016-09-14 欧姆龙株式会社 品质管理装置及其控制方法
CN107194826A (zh) * 2017-06-16 2017-09-22 北京航空航天大学 一种基于质量状态任务网的制造系统健康诊断与预测方法
CN108038553A (zh) * 2017-12-13 2018-05-15 科大集智数据科技（武汉）有限公司 轧机设备状态在线监测与诊断系统及监测诊断方法
CN108345275A (zh) * 2017-01-25 2018-07-31 中芯国际集成电路制造(上海)有限公司 设备监控系统及设备监控方法
CN108388237A (zh) * 2018-04-16 2018-08-10 广东工业大学 一种离散制造设备的故障诊断方法、装置、设备及介质
CN109741927A (zh) * 2019-03-14 2019-05-10 贵港市嘉龙海杰电子科技有限公司 微型变压器生产线的设备故障和潜在不良品智能预测系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3441111B2 (ja) * 1993-06-17 2003-08-25 松下電器産業株式会社 実装基板生産システムおよびメンテナンス指示システム
CN105206410B (zh) * 2015-11-03 2017-09-15 信华科技（厦门）有限公司 车载变压器自动化生产线
CN205789481U (zh) * 2016-05-20 2016-12-07 东莞市力能电子科技有限公司 变压器自动化生产线
CN108388950A (zh) * 2018-01-29 2018-08-10 杭州安脉盛智能技术有限公司 基于大数据的变压器智能运维方法及系统
CN109127450A (zh) * 2018-09-19 2019-01-04 深圳市景方盈科技有限公司 一种变压器自动化分拣生产线

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06163293A (ja) * 1992-11-19 1994-06-10 Mitsubishi Electric Corp 生産管理方法
CN101403915A (zh) * 2008-11-07 2009-04-08 同济大学 一种可重组生产线产品质量预测方法
CN105940354A (zh) * 2014-02-10 2016-09-14 欧姆龙株式会社 品质管理装置及其控制方法
CN108345275A (zh) * 2017-01-25 2018-07-31 中芯国际集成电路制造(上海)有限公司 设备监控系统及设备监控方法
CN107194826A (zh) * 2017-06-16 2017-09-22 北京航空航天大学 一种基于质量状态任务网的制造系统健康诊断与预测方法
CN108038553A (zh) * 2017-12-13 2018-05-15 科大集智数据科技（武汉）有限公司 轧机设备状态在线监测与诊断系统及监测诊断方法
CN108388237A (zh) * 2018-04-16 2018-08-10 广东工业大学 一种离散制造设备的故障诊断方法、装置、设备及介质
CN109741927A (zh) * 2019-03-14 2019-05-10 贵港市嘉龙海杰电子科技有限公司 微型变压器生产线的设备故障和潜在不良品智能预测系统

Also Published As

Publication number Publication date
CN109741927A (zh) 2019-05-10
CN109741927B (zh) 2020-08-07

Similar Documents

Publication Publication Date Title
CN109741927B (zh) 微型变压器生产线的设备故障和潜在不良品智能预测系统
WO2025086414A1 (zh) 一种适用于分布式电源的配电网故障检测方法
CN118653969B (zh) 一种风力发电设备的润滑系统实时检测系统及预警方法
CN107844067B (zh) 一种水电站闸门在线状态监测控制方法及监测系统
CN115685050B (zh) 一种电能表故障检测方法及系统
CN116028887B (zh) 一种连续性工业生产数据的分析方法
CN115528810A (zh) 一种基于电力设备的测温数据运检分析管理系统
CN116611953A (zh) 基于物联网的电能表生产制造实时数据管理方法和系统
CN120214466A (zh) 一种充电桩故障在线检测方法及系统
CN116720091A (zh) 一种电机故障分析方法
CN119510929A (zh) 一种考虑互感器宽频传输特性的电能质量监测方法及系统
CN109240253B (zh) 一种在线设备诊断及预防性维护方法及系统
CN119089249A (zh) 基于多源数据融合的在线户变关系识别方法及系统
CN120297952A (zh) 一种基于智慧工业园区的数据采集与监视控制方法
CN118444619A (zh) 基于物联网的硼硅玻璃加工用智能管理系统
CN118311496A (zh) 一种多个电能表检定装置在线切换测试方法及系统
CN118052482A (zh) 一种用于半导体生产检测的分析管理方法
CN117571354A (zh) 一种有机废气容量实时监控系统
CN115265635B (zh) 一种基于数据分析的工业机器视觉检测管理系统
CN119148045B (zh) 用于计量箱的维修检测方法
CN120045216A (zh) 可视化设备元件配置系统
CN117196590B (zh) 一种面向通讯设备运维的维修效率智能评估系统
CN119618444A (zh) 一种基于lstm神经网络的电压互感器在线热应力监测系统
CN119986181A (zh) 一种测试电力管线贯通的装置及方法
CN114895137B (zh) 一种供电设备供电质量测试方法

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: 19919254

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19919254

Country of ref document: EP

Kind code of ref document: A1