Equipment fault detection method and system

Abstract

The invention relates to the technical field of equipment fault detection, and discloses an equipment fault prediction and diagnosis method which is applied to an ATE system, and the method comprises the steps: collecting the real-time operation data of equipment through a plurality of sensors, and dynamically scheduling the sensors through an adaptive algorithm, so as to adjust the data collection frequency and range according to the state of the equipment; the collected data is preprocessed; training a plurality of machine learning models based on the historical fault data and the operation data, and deploying the models to an ATE system for real-time analysis; predicting an equipment fault according to the model, generating alarm information when a potential fault is detected, and sending the alarm information to an operator through a user interface or a notification system; generating a fault diagnosis report according to an analysis result and providing a repair suggestion; recording a fault instance and data, and updating and retraining the machine learning model to improve prediction and diagnosis accuracy; and generating a digital twin model of the equipment based on real-time and historical data, simulating the running state of the equipment, predicting future faults, and evaluating the health condition of the equipment.

Description

Technical Field

[0001] The present application relates to the field of equipment fault detection, and in particular to an equipment fault detection method and system for predicting and diagnosing faults in semiconductor automatic test equipment systems. Background Art

[0002] As the complexity of electronic equipment continues to increase, the detection and diagnosis of equipment failures are becoming increasingly difficult and time-consuming. Traditional fault detection methods rely on predefined rules and models, lack dynamic adjustment capabilities when collecting and analyzing multiple data, and cannot fully utilize real-time and historical data for efficient and accurate fault prediction and diagnosis; at the same time, these methods are difficult to cope with the diverse and rapidly changing fault modes in complex systems, affecting the accuracy of fault monitoring and self-optimization capabilities. Summary of the invention

[0003] In response to the defects in the prior art, this application proposes a method for equipment fault detection, which optimizes the efficiency of data acquisition through adaptive scheduling and multi-source data collection, and improves the real-time and accuracy of fault prediction. Combined with the dynamic training and deployment of machine learning models, the system can adapt to new fault modes in a timely manner to ensure efficient and continuous prediction and diagnosis. The digital twin model further enhances the equipment's health monitoring and future fault prediction capabilities, and realizes the simulation evaluation of the equipment's operating status.

[0004] To solve the above problems, on the one hand, an embodiment of the present application provides a device fault detection method, which is applied to an ATE system. The method includes:

[0005] S1. Data collection: Real-time operating data collected from various devices in the ATE system through multiple sensors. The sensors are dynamically scheduled by an adaptive algorithm to adjust the data collection frequency and range according to the current status of the device;

[0006] S2. Preprocessing: training various types of machine learning models based on historical fault data and historical operation data, and deploying the trained machine learning models into the ATE system;

[0007] S4. Fault monitoring: Use the deployed machine learning model to continuously analyze real-time operation data to predict potential equipment failures and send alarm information to operators through the user interface or notification system when potential failures are detected;

[0008] S5. Fault diagnosis: When a potential fault is detected, a fault diagnosis report is generated based on the analysis results of the machine learning model, and corresponding repair suggestions are provided;

[0009] S6. Model update: record the failure instances of the ATE system and the real-time operation data at the time of the failure, and add historical failure data to retrain the machine learning model; update the machine learning model to optimize the accuracy of prediction and diagnosis, and redeploy it to the ATE system;

[0010] S7. Digital simulation: Generate a digital twin model of the equipment based on real-time operation data and historical operation data, which is used to simulate the operating status of the equipment in real time, predict possible future failures, and evaluate the health status of the equipment.

[0011] In one possible embodiment, the real-time operating data includes electrical signals, environmental parameters, and operational data;

[0012] Electrical signals include voltage, current, and frequency;

[0013] Environmental parameters include temperature, humidity, and vibration;

[0014] Operational data includes operation logs, test steps, and test results.

[0015] In a possible embodiment, the preprocessing includes at least one of filtering, denoising, and normalization.

[0016] In one possible embodiment, the machine learning model includes a fault prediction model and a fault classification model.

[0017] In one possible embodiment, the algorithm used by the machine learning model includes at least one of a decision tree, a random forest, and a deep learning network.

[0018] In a possible embodiment, the diagnosis report includes the fault content, the cause of the fault, and the ATE system modules that may be affected.

[0019] In a possible embodiment, the alarm information includes a text message or an email.

[0020] On the other hand, the present invention also provides an equipment fault detection system, comprising:

[0021] A data acquisition module is used to collect real-time operation data from different ATE system modules through multiple types of sensors and data interfaces. The real-time operation data includes electrical signals, electrical signals, environmental parameters and operating data;

[0022] The sensor scheduling module is integrated into the data acquisition module. It is used to dynamically select the required sensors based on the current operating status and fault prediction requirements of the ATE system by analyzing the real-time and historical operating data of the equipment, and adjust the data acquisition frequency and range to optimize the data acquisition efficiency and reduce the generation of redundant data.

[0023] The edge computing module communicates with the data acquisition module and the sensor scheduling module, and is used to receive and process the real-time operation data from the data acquisition module on the local device of the ATE system, and pre-process the real-time operation data, including filtering, denoising and normalization, so as to optimize the data quality and reduce the delay of data transmission to the central processor;

[0024] A data processing unit is used to receive pre-processed real-time operation data from the edge computing unit, and perform further data cleaning, feature extraction and data fusion operations to generate structured prediction input data;

[0025] A model training and deployment module communicates with the data acquisition unit, obtains historical fault data and historical operation data from the data acquisition unit as training data to train the machine learning model, and deploys the trained machine learning model to the ATE system;

[0026] A fault warning module communicates with the model training and deployment module and the data processing unit, and is used to obtain the prediction input data sent by the data processing unit in real time, and analyze the prediction input data in real time based on the machine learning model deployed to the ATE system. When the machine learning model detects a potential fault, it generates corresponding fault alarm information and sends the alarm information to the operator through the user interface or notification system;

[0027] The diagnostic suggestion module is integrated and communicates with the fault warning module. When a potential fault is detected, it generates a fault diagnosis report based on the analysis results of the machine learning model, including the fault type, cause, and modules of the ATE system that may be affected. It also generates fault repair suggestions based on the knowledge base to provide operators with reference information for repair operations.

[0028] The self-learning module communicates with the model training and deployment module and the fault warning module, and is used to obtain the fault instance and the predicted input data at the time of the fault from the fault warning module to add the historical fault data; resend the new historical fault data to the model training and deployment module to retrain the machine learning model, so as to update the machine learning model and redeploy it to the ATE system.

[0029] Furthermore, it also includes a power consumption monitoring module. The power consumption detection module communicates with the data acquisition module and the edge computing module, and is used to collect the power consumption data of each device in the ATE system in real time through a power sensor, and combine it with the real-time operation data from the data acquisition module to perform power consumption characteristic analysis of each device in the ATE system, and integrate the power consumption analysis results with the fault prediction model to enhance the accuracy of fault prediction.

[0030] Furthermore, it also includes a digital twin module. The digital twin model communicates with the data acquisition module and the fault warning module. Based on the real-time operation data obtained from the data acquisition module and the fault instances and predicted input data at the time of failure obtained from the fault warning module, a virtual copy of the ATE system is created to execute the operation status simulation of each device in the ATE system and provide real-time equipment health monitoring.

[0031] Compared with the prior art, this application has the following advantages and beneficial effects:

[0032] The present invention provides a method for detecting equipment faults, which optimizes the efficiency of data acquisition through adaptive scheduling and multi-source data collection, and improves the real-time and accuracy of fault prediction. Combined with the dynamic training and deployment of machine learning models, the system can adapt to new fault modes in a timely manner, ensuring efficient and continuous prediction and diagnosis. The digital twin model further enhances the equipment's health monitoring and future fault prediction capabilities, and realizes the simulation evaluation of the equipment's operating status.

[0033] The present invention also provides an equipment fault detection system, through which data collection efficiency is optimized, the dynamic scheduling of sensors improves the accuracy of real-time data, and edge computing reduces data transmission delays; the self-learning function ensures the system's adaptability when facing new fault modes, and overall improves the real-time and accuracy of equipment fault prediction, and enhances the continuous monitoring of equipment operating status and fault warning capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A flowchart of the steps of the equipment fault monitoring and diagnosis method provided in this application;

[0036] Figure 2 A schematic diagram of the data flow of the equipment fault prediction and diagnosis system provided in this application. DETAILED DESCRIPTION

[0037] In the following, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0038] Hereinafter, the terms "include" or "may include" used in various embodiments of the present disclosure indicate the presence of disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present disclosure, the terms "include", "have", and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or a combination of the foregoing, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components, or a combination of the foregoing or the possibility of adding one or more features, numbers, steps, operations, elements, components, or a combination of the foregoing.

[0039] In various embodiments of the present disclosure, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0040] The expressions (such as "first", "second", etc.) used in the various embodiments of the present disclosure may modify the various constituent elements in the various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing one element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of the present disclosure, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.

[0041] It should be noted that if it is described that one component element is “connected” to another component element, the first component element may be directly connected to the second component element, and a third component element may be “connected” between the first component element and the second component element. Conversely, when one component element is “directly connected” to another component element, it can be understood that there is no third component element between the first component element and the second component element.

[0042] The term “user” used in various embodiments of the present disclosure may indicate a person using an electronic device or a device (eg, an artificial intelligence electronic device) using the electronic device.

[0043] The terms used in the various embodiments of the present disclosure are only used for the purpose of describing specific embodiments and are not intended to limit the various embodiments of the present disclosure. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the meanings commonly understood by ordinary technicians in the field to which the various embodiments of the present disclosure belong. The terms (such as the terms defined in the generally used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the present disclosure.

[0044] Glossary: ​​ATE is the abbreviation of Automatic Test Equipment, which can be translated into Chinese as automatic test equipment; ATE system is the automatic test equipment system, also known as the integrated circuit tester system, which is an automated equipment system dedicated to the testing of integrated circuits and chip models.

[0045] Embodiment 1:

[0046] This embodiment provides a device fault detection method, which is applied to an ATE system, such as Figure 1 As shown, the steps of the method include:

[0047] S1. Data collection: Real-time operating data collected from various devices in the ATE system through multiple sensors. The sensors are dynamically scheduled by an adaptive algorithm to adjust the data collection frequency and range according to the current status of the device;

[0048] S2, preprocessing: preprocessing the collected real-time operation data;

[0049] S3, model training: train various types of machine learning models based on historical fault data and historical operation data, and deploy the trained machine learning models to the ATE system;

[0050] S4. Fault monitoring: Use the deployed machine learning model to continuously analyze real-time operation data to predict potential equipment failures and send alarm information to operators through the user interface or notification system when potential failures are detected;

[0051] S5. Fault diagnosis: When a potential fault is detected, a fault diagnosis report is generated based on the analysis results of the machine learning model, and corresponding repair suggestions are provided;

[0052] S6. Model update: record the failure instances of the ATE system and the real-time operation data at the time of the failure, and add historical failure data to retrain the machine learning model; update the machine learning model to optimize the accuracy of prediction and diagnosis, and redeploy it to the ATE system;

[0053] S7. Digital simulation: Generate a digital twin model of the equipment based on real-time operation data and historical operation data, which is used to simulate the operating status of the equipment in real time, predict possible future failures, and evaluate the health status of the equipment.

[0054] In this embodiment, the method optimizes the data acquisition efficiency through adaptive scheduling and multi-source data collection, and improves the real-time and accuracy of fault prediction. Combined with the dynamic training and deployment of machine learning models, the system can adapt to new fault modes in a timely manner to ensure efficient and continuous prediction and diagnosis. The digital twin model further enhances the health monitoring and future fault prediction capabilities of the equipment, and realizes the simulation evaluation of the equipment operation status.

[0055] Furthermore, the real-time operating data includes electrical signals, environmental parameters and operating data;

[0056] Electrical signals include voltage, current, and frequency;

[0057] Environmental parameters include temperature, humidity, and vibration;

[0058] Operational data includes operation logs, test steps, and test results.

[0059] Furthermore, the preprocessing includes at least one of filtering, denoising, and normalization.

[0060] Furthermore, the machine learning model includes a fault prediction model and a fault classification model.

[0061] Furthermore, the algorithm used by the machine learning model includes at least one of a decision tree, a random forest, and a deep learning network.

[0062] Furthermore, the diagnostic report includes the fault content, cause of occurrence and possible affected ATE system modules.

[0063] Furthermore, the alarm information includes text messages and emails.

[0064] Embodiment 2:

[0065] This embodiment provides a device fault detection system, such as Figure 2 As shown, the direction of the arrow indicates the transmission direction of data or instructions, including:

[0066] A data acquisition module is used to collect real-time operation data from different ATE system modules through multiple types of sensors and data interfaces. The real-time operation data includes electrical signals, electrical signals, environmental parameters and operating data;

[0067] The sensor scheduling module is integrated into the data acquisition module. It is used to dynamically select the required sensors based on the current operating status and fault prediction requirements of the ATE system by analyzing the real-time and historical operating data of the equipment, and adjust the data acquisition frequency and range to optimize the data acquisition efficiency and reduce the generation of redundant data.

[0068] The edge computing module communicates with the data acquisition module and the sensor scheduling module, and is used to receive and process the real-time operation data from the data acquisition module on the local device of the ATE system, and pre-process the real-time operation data, including filtering, denoising and normalization, so as to optimize the data quality and reduce the delay of data transmission to the central processor;

[0069] A data processing unit is used to receive pre-processed real-time operation data from the edge computing unit, and perform further data cleaning, feature extraction and data fusion operations to generate structured prediction input data;

[0070] A model training and deployment module communicates with the data acquisition unit, obtains historical fault data and historical operation data from the data acquisition unit as training data to train the machine learning model, and deploys the trained machine learning model to the ATE system;

[0071] A fault warning module communicates with the model training and deployment module and the data processing unit, and is used to obtain the prediction input data sent by the data processing unit in real time, and analyze the prediction input data in real time based on the machine learning model deployed to the ATE system. When the machine learning model detects a potential fault, it generates corresponding fault alarm information and sends the alarm information to the operator through the user interface or notification system;

[0072] The diagnostic suggestion module is integrated and communicates with the fault warning module. When a potential fault is detected, it generates a fault diagnosis report based on the analysis results of the machine learning model, including the fault type, cause, and modules of the ATE system that may be affected. It also generates fault repair suggestions based on the knowledge base to provide operators with reference information for repair operations.

[0073] The self-learning module communicates with the model training and deployment module and the fault warning module, and is used to obtain the fault instance and the predicted input data at the time of the fault from the fault warning module to add the historical fault data; resend the new historical fault data to the model training and deployment module to retrain the machine learning model, so as to update the machine learning model and redeploy it to the ATE system.

[0074] In this embodiment, the data collection efficiency of the system is optimized, the dynamic scheduling of sensors improves the accuracy of real-time data, and edge computing reduces data transmission delays. The self-learning function ensures the system's adaptability when facing new failure modes, improves the real-time and accuracy of equipment failure prediction as a whole, and enhances the continuous monitoring of equipment operating status and fault warning capabilities.

[0075] Furthermore, it also includes a power consumption monitoring module. The power consumption detection module communicates with the data acquisition module and the edge computing module, and is used to collect the power consumption data of each device in the ATE system in real time through a power sensor, and combine it with the real-time operation data from the data acquisition module to perform power consumption characteristic analysis of each device in the ATE system, and integrate the power consumption analysis results with the fault prediction model to enhance the accuracy of fault prediction.

[0076] Furthermore, it also includes a digital twin module. The digital twin model communicates with the data acquisition module and the fault warning module. Based on the real-time operation data obtained from the data acquisition module and the fault instances and predicted input data at the time of failure obtained from the fault warning module, a virtual copy of the ATE system is created to execute the operation status simulation of each device in the ATE system and provide real-time equipment health monitoring.

[0077] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present invention.

[0078] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0079] The above serial numbers of the present invention are only for description and do not represent the advantages or disadvantages of the implementation scenarios.

[0080] The above disclosure is only a few specific implementation scenarios of the present invention, but the present invention is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present invention.

Claims

1. A device fault detection method, applied to an ATE system, characterized in that: The method comprises the following steps: S1. Data collection: real-time operating data collected from various devices in the ATE system through multiple sensors, which are dynamically scheduled by an adaptive algorithm to adjust the data collection frequency and range according to the current status of the device; S2, preprocessing: preprocessing the collected real-time operation data; S3. Model training: training various types of machine learning models based on historical fault data and historical operation data, and deploying the trained machine learning models into the ATE system; S4. Fault monitoring: continuously analyzing the real-time operation data using the deployed machine learning model to predict potential equipment failures, and sending alarm information to operators through a user interface or notification system when a potential failure is detected; S5. Fault diagnosis: when a potential fault is detected, a fault diagnosis report is generated based on the analysis results of the machine learning model, and corresponding repair suggestions are provided; S6. Model update: record the fault instance of the ATE system and the real-time operation data at the time of the fault, and add the historical fault data to retrain the machine learning model; update the machine learning model to optimize the accuracy of prediction and diagnosis, and redeploy it to the ATE system; S7. Digital simulation: Generate a digital twin model of the equipment based on real-time operation data and historical operation data, which is used to simulate the operating status of the equipment in real time, predict possible future failures, and evaluate the health status of the equipment.

2. The device fault detection method according to claim 1, characterized in that: The real-time operation data includes electrical signals, environmental parameters and operation data; The electrical signal includes voltage, current and frequency; The environmental parameters include temperature, humidity and vibration; The operation data includes operation logs, test steps and test results.

3. The device fault detection method according to claim 2, characterized in that: The preprocessing includes at least one of filtering, denoising, and normalization.

4. The device failure detection method according to claim 1, characterized in that: The machine learning model includes a fault prediction model and a fault classification model.

5. The device fault detection method according to claim 4, characterized in that: The algorithm used by the machine learning model includes at least one of a decision tree, a random forest, and a deep learning network.

6. The device fault detection method according to claim 1, characterized in that: The diagnostic report includes the fault content, cause of occurrence and the ATE system modules that may be affected.

7. The device fault detection method according to claim 6, characterized in that: The alarm information includes text messages and emails.

8. A device fault detection system, characterized in that: include: A data acquisition module for collecting real-time operation data from different ATE system modules through multiple types of sensors and data interfaces, wherein the real-time operation data includes electrical signals, electrical signals, environmental parameters and operating data; A sensor scheduling module, integrated in the data acquisition module, is used to dynamically select the required sensors to be called based on the current operating status and fault prediction requirements of the ATE system by analyzing the real-time operating data and historical operating data of the equipment, and adjust the data acquisition frequency and range to optimize data acquisition efficiency and reduce the generation of redundant data; an edge computing module, communicating with the data acquisition module and the sensor scheduling module, for receiving and processing the real-time operation data from the data acquisition module on a local device of the ATE system, and preprocessing the real-time operation data, wherein the preprocessing includes filtering, denoising and normalization, so as to optimize data quality and reduce the delay of data transmission to a central processor; A data processing unit, configured to receive pre-processed real-time operation data from the edge computing unit, and perform further data cleaning, feature extraction and data fusion operations to generate structured prediction input data; A model training deployment module communicates with the data acquisition unit, obtains historical fault data and historical operation data from the data acquisition unit as training data to train the machine learning model, and deploys the trained machine learning model to the ATE system; a fault warning module, communicating with the model training deployment module and the data processing unit, for acquiring the predicted input data sent by the data processing unit in real time, and analyzing the predicted input data in real time based on the machine learning model deployed to the ATE system, and generating corresponding fault alarm information when the machine learning model detects a potential fault, and sending the alarm information to the operator through a user interface or a notification system; a diagnosis suggestion module, which is integrated and communicates with the fault warning module, and when a potential fault is detected, generates a fault diagnosis report based on the analysis results of the machine learning model, including the fault type, cause of occurrence, and modules of the ATE system that may be affected, and generates fault repair suggestions based on the knowledge base to provide reference information for repair operations to operators; A self-learning module communicates with the model training deployment module and the fault warning module, and is used to obtain the fault instance and the predicted input data at the time of the fault from the fault warning module to add the historical fault data; and resend the new historical fault data to the model training deployment module to retrain the machine learning model, so as to update the machine learning model and redeploy it to the ATE system.

9. The equipment fault detection system according to claim 8, characterized in that: It also includes a power consumption monitoring module, which communicates with the data acquisition module and the edge computing module, and is used to collect power consumption data of each device in the ATE system in real time through a power sensor, and combine the real-time operation data from the data acquisition module to perform power consumption feature analysis on each device in the ATE system, and integrate the power consumption analysis results with the fault prediction model to enhance the accuracy of fault prediction.

10. The equipment fault detection system according to claim 8 or 9, characterized in that: It also includes a digital twin module, and the digital twin model communicates with the data acquisition module and the fault warning module. Based on the real-time operation data obtained from the data acquisition module and the fault instance and the predicted input data at the time of failure obtained from the fault warning module, a virtual copy of the ATE system is created to perform operation status simulation of each device of the ATE system and provide real-time device health monitoring.

Images