Predictive maintenance method and system for process equipment, equipment, storage medium and computer program product

Abstract

The invention discloses a predictive maintenance method and system for process equipment, equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring real-time operation data of the process equipment; analyzing the operation data, and predicting the operation state of the process equipment as a predicted operation state; and generating a maintenance plan of the process equipment based on the predicted operation state. The production efficiency is improved, and the maintenance cost is reduced.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of semiconductor manufacturing, and in particular to a predictive maintenance method and system, equipment, storage medium, and computer program product for process equipment. Background Art

[0002] In semiconductor manufacturing, the performance and reliability of process equipment are critical. Traditional maintenance methods rely on scheduled time intervals or repairs after equipment failure, resulting in unnecessary downtime and high repair costs.

[0003] To solve these problems, there is an urgent need for a maintenance system that can monitor equipment status in real time and predict potential failures. Summary of the Invention

[0004] The problem solved by the embodiments of the present invention is to provide a predictive maintenance method and system, equipment, storage medium and computer program product for process equipment, which are conducive to improving production efficiency and reducing maintenance costs.

[0005] To solve the above problems, an embodiment of the present invention provides a predictive maintenance method for process equipment, including: acquiring real-time operating data of the process equipment; analyzing the operating data and predicting the operating status of the process equipment as the predicted operating status; and generating a maintenance plan for the process equipment based on the predicted operating status.

[0006] Optionally, in acquiring real-time operating data of the process equipment, the operating data includes equipment status data and environmental status data of the process equipment.

[0007] Optionally, the equipment status data includes one or more of equipment temperature data, process pressure data, equipment vibration amplitude data and process gas flow data; the environmental status data includes one or more of environmental temperature data, environmental humidity data and environmental pressure data.

[0008] Optionally, in acquiring the real-time operating data of the process equipment, the operating data is collected through a sensor array on the process equipment.

[0009] Optionally, analyzing the operating data and predicting the operating status of the process equipment, before predicting the operating status, also includes: pre-processing the operating data of the process equipment and screening effective operating data.

[0010] Optionally, the operation data of the process equipment is preprocessed, including: cleaning the operation data of the process equipment to remove abnormal operation data; normalizing the operation data; and extracting features from the operation data to obtain reorganized operation data.

[0011] Optionally, the predictive maintenance method also includes: establishing a process equipment operating status prediction model, the process equipment operating status prediction model includes a mapping relationship between operating data and operating status; analyzing the operating data and predicting the operating status of the process equipment as the predicted operating status, including: using the process equipment operating status prediction model to analyze the operating data; and outputting the predicted operating status of the process equipment through the process equipment operating status prediction model.

[0012] Optionally, a process equipment operation status prediction model is established, including: collecting historical operation information of the process equipment, the historical operation information includes the historical operation status of the process equipment, and the historical operation data of the process equipment under different historical operation statuses; performing supervised learning training on the historical operation information of the process equipment to construct a process equipment operation status prediction model.

[0013] Optionally, a neural network model, a support vector machine model or a random forest model is used to perform supervised learning training on historical operation information of the process equipment.

[0014] Optionally, the operating data is analyzed to predict the operating status of the process equipment. The predicted operating status includes the predicted health status of the process equipment. The predicted health status includes normal, initial abnormality, and failure.

[0015] Optionally, the predicted health status also includes parameter drift of parameters corresponding to the operating data of the process equipment and / or an overall equipment health index of the process equipment.

[0016] Optionally, the operating data is analyzed to predict the operating status of the process equipment. The predicted operating status also includes a failure risk score of each component in the process equipment. The failure risk score includes a failure probability or an abnormality score.

[0017] Optionally, a maintenance plan for the process equipment is generated based on the predicted operating status, where the maintenance plan includes maintenance time, maintenance steps, and spare parts or resources required for maintenance.

[0018] Optionally, a maintenance plan for process equipment is generated based on the predicted operating status, including: judging the urgency of the failure of the process equipment based on the predicted operating status; obtaining the standard maintenance process of the process equipment; obtaining the production schedule of the process equipment; matching the urgency of the failure with the standard maintenance process of the process equipment, and generating a maintenance plan for the process equipment in combination with the production schedule.

[0019] Optionally, after generating a maintenance plan for the process equipment based on the predicted operating status, the method further includes: transmitting the maintenance plan for the process equipment to an operating system of the process equipment.

[0020] Optionally, a predictive maintenance method is applicable to etching process equipment.

[0021] Correspondingly, an embodiment of the present invention also provides a predictive maintenance system for process equipment, including: an operation data acquisition module for acquiring the operation data of the process equipment; an operation status prediction module for analyzing the operation data and predicting the operation status of the process equipment as the predicted operation status; and a maintenance plan generation module for generating a maintenance plan for the process equipment based on the predicted operation status.

[0022] Accordingly, an embodiment of the present invention also provides a device comprising at least one memory and at least one processor, wherein the memory stores one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the predictive maintenance method for process equipment provided in an embodiment of the present invention.

[0023] Correspondingly, an embodiment of the present invention further provides a storage medium, which stores one or more computer instructions, and the one or more computer instructions are used to implement the predictive maintenance method of the process equipment provided by the embodiment of the present invention.

[0024] Accordingly, an embodiment of the present invention further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the predictive maintenance method for process equipment provided by an embodiment of the present invention.

[0025] Compared with the prior art, the technical solution of the embodiment of the present invention has the following advantages:

[0026] In the predictive maintenance method for process equipment provided in an embodiment of the present invention, real-time operating data of the process equipment is obtained, the operating data is analyzed, and the operating status of the process equipment is predicted as the predicted operating status. Based on the predicted operating status, a maintenance plan for the process equipment is generated. In an embodiment of the present invention, by collecting the operating data of the process equipment in real time and analyzing the operating data, the operating status of the process equipment is predicted in real time, potential failures or process deviations of the process equipment are obtained, and then a maintenance plan for the process equipment is generated based on the predicted operating status. This is conducive to identifying signs of failure in advance before the process equipment fails, thereby arranging maintenance activities in time before the failure occurs, preventing unplanned shutdown of the process equipment, and thus helping to improve production efficiency and reduce maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flow chart of an embodiment of a predictive maintenance method for process equipment of the present invention;

[0028] Figure 2 is a functional block diagram of an embodiment of a predictive maintenance system for process equipment of the present invention;

[0029] Figure 3 It is a hardware structure diagram of an embodiment of the device provided by the present invention. DETAILED DESCRIPTION

[0030] As can be seen from the background art, current maintenance methods for process equipment rely on repairs at predetermined time intervals or after equipment failure, resulting in unnecessary downtime and high maintenance costs.

[0031] In order to solve the above technical problems, an embodiment of the present invention provides a predictive maintenance method for process equipment. Figure 1 , showing a flow chart of an embodiment of a predictive maintenance method for process equipment of the present invention.

[0032] In this embodiment, the predictive maintenance method for process equipment includes the following basic steps:

[0033] Step S1: Acquire real-time operating data of process equipment;

[0034] Step S2: analyzing the operating data and predicting the operating status of the process equipment as the predicted operating status;

[0035] Step S3: Generate a maintenance plan for the process equipment based on the predicted operating status.

[0036] In an embodiment of the present invention, by collecting operating data of process equipment in real time and analyzing the operating data, the operating status of the process equipment is predicted in real time, potential failures or process deviations of the process equipment are obtained, and then a maintenance plan for the process equipment is generated based on the predicted operating status. This is conducive to identifying signs of failure in advance before the process equipment fails, thereby arranging maintenance activities in time before the failure occurs, preventing unplanned shutdown of the process equipment, and thus helping to improve production efficiency and reduce maintenance costs.

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below.

[0038] In the semiconductor manufacturing process, the performance and reliability of process equipment are crucial.

[0039] In this embodiment, the predictive maintenance method is suitable for etching process equipment.

[0040] The highly corrosive atmosphere, plasma environment and complex working conditions unique to the etching process make etching process equipment particularly in need of predictive maintenance. Therefore, the predictive maintenance method of this embodiment is particularly suitable for etching process equipment, and the optimization effect is particularly significant in the etching process scenario.

[0041] Execute step S1: obtain real-time operating data of process equipment.

[0042] Obtain real-time operating data of process equipment for real-time prediction of the operating status of process equipment.

[0043] In this embodiment, in acquiring the real-time operation data of the process equipment, the operation data includes equipment status data and environment status data of the process equipment.

[0044] Equipment status data and environmental status data can represent the real-time status of process equipment.

[0045] Specifically, in this embodiment, the equipment status data includes one or more of equipment temperature data, process pressure data, equipment vibration amplitude data and process gas flow data; the environmental status data includes one or more of environmental temperature data, environmental humidity data and environmental pressure data.

[0046] Equipment temperature data, process pressure data, equipment vibration amplitude data and process gas flow data can characterize the equipment status of the process equipment, and ambient temperature data, ambient humidity data and ambient air pressure data can characterize the environmental status.

[0047] In this embodiment, in acquiring the real-time operating data of the process equipment, the operating data is collected by a sensor array on the process equipment.

[0048] Specifically, a comprehensive sensor array is installed on the process equipment to monitor the equipment status and environmental status of the process equipment in real time. The process equipment is monitored in real time through the sensor array, and the equipment status data and environmental status data of the process equipment are continuously collected through the data acquisition module.

[0049] In this embodiment, the subsequent analysis of the operating data and prediction of the operating status of the process equipment further includes: pre-processing the operating data of the process equipment and screening effective operating data before predicting the operating status.

[0050] Pre-process the operating data of process equipment and screen valid operating data to ensure the quality of the operating data of process equipment.

[0051] In this embodiment, pre-processing is performed on the operation data of the process equipment, including: performing data cleaning on the operation data of the process equipment to remove abnormal operation data.

[0052] Perform data cleaning on the operating data of process equipment to remove outliers and missing values ​​in the operating data to ensure the integrity and accuracy of the operating data.

[0053] In this embodiment, the operating data is normalized.

[0054] Normalizing the operating data and standardizing the operating data to a unified range will help improve the data calculation rate.

[0055] In this embodiment, feature extraction is performed on the operating data to obtain reorganized operating data.

[0056] Perform feature extraction on the operating data to extract important features from the original operating data for input into subsequent machine learning models to perform efficient and accurate data analysis.

[0057] In this embodiment, the predictive maintenance method further includes: establishing a process equipment operation status prediction model, where the process equipment operation status prediction model includes a mapping relationship between operation data and operation status.

[0058] Establish a process equipment operating status prediction model to analyze operating data and output the operating status of process equipment.

[0059] In this embodiment, establishing a process equipment operation state prediction model includes: collecting historical operation information of the process equipment, where the historical operation information includes the historical operation state of the process equipment and historical operation data of the process equipment under different historical operation states.

[0060] Collect historical operating information of process equipment for machine learning modeling. The historical operating information includes the historical operating status of the process equipment and the historical operating data of the process equipment under different historical operating statuses. That is, collect historical equipment status data and environmental status data collected by sensors, and each set of data corresponds to a real process equipment operating status label.

[0061] As an example, in this embodiment, the collected historical operation information includes two parts: feature data (X): equipment status data (such as temperature, pressure, vibration amplitude, gas flow, etc.), environmental status data (such as cavity temperature, humidity, external air pressure, etc.); label data (Y): the actual status of the process equipment corresponding to each set of data (such as normal, early anomaly, failure). Among them, the label can be a classification label (such as normal / abnormal / failure) or a continuous value (such as a health index score). Therefore, calibration data is required, that is, each section of historical sensor collected data must correspond to a label of the process equipment status in order to perform supervised learning training.

[0062] Accordingly, in this embodiment, supervised learning training is performed on the historical operation information of the process equipment to construct a process equipment operation status prediction model.

[0063] All models are built using historical operating information so that when the model is applied in real time in the future, it can predict potential failure risks based on new data collected in real time.

[0064] Specifically, in this embodiment, a neural network model, a support vector machine model or a random forest model is used to perform supervised learning training on the historical operation information of the process equipment.

[0065] Execute step S2: analyze the operation data and predict the operation status of the process equipment as the predicted operation status.

[0066] Obtain the predicted operating status of process equipment to determine whether the process equipment needs maintenance based on it.

[0067] In this embodiment, by collecting the operating data of the process equipment in real time and analyzing the operating data, the operating status of the process equipment is predicted in real time, the potential failures or process deviations of the process equipment are obtained, and then a maintenance plan for the process equipment is generated based on the predicted operating status. This is conducive to identifying signs of failure in advance before the process equipment fails, so that maintenance activities can be arranged in time before the failure occurs, preventing unplanned shutdown of the process equipment, and thus helping to improve production efficiency and reduce maintenance costs.

[0068] In this embodiment, the operating data is analyzed to predict the operating status of the process equipment. The predicted operating status includes the predicted health status of the process equipment. The predicted health status includes normal, initial abnormality, and failure.

[0069] Specifically, when the predicted health status of the process equipment is normal, no maintenance plan may be carried out. When the predicted health status of the process equipment is initial abnormality or failure, a maintenance plan will be carried out for the process equipment later.

[0070] In this embodiment, the predicted health status further includes parameter drift of parameters corresponding to the operating data of the process equipment and / or the overall equipment health index of the process equipment.

[0071] Specifically, the parameter drift output is the key parameter offset compared to the normal state (such as temperature drift, pressure change rate exceeding the standard, etc.), and the overall equipment health index (Health Index) output of the process equipment is the health index of the entire process equipment (such as HI = 78%, which is lower than the set threshold and requires maintenance).

[0072] In this embodiment, the operating data is analyzed to predict the operating status of the process equipment. The predicted operating status also includes a failure risk score of each component in the process equipment. The failure risk score includes a failure probability or an abnormality score.

[0073] Specifically, the failure risk score (Anomaly Score / Failure Probability) output is the anomaly score or failure probability of each monitored component of the process equipment. For example, the vacuum system failure probability = 85%; the gas flow anomaly score = 0.92 (score range 0-1).

[0074] Predicting the failure risk score of each component in process equipment can quantify the urgency and severity of failures and assist in maintenance priority sorting.

[0075] Accordingly, in this embodiment, analyzing the operating data and predicting the operating status of the process equipment as the predicted operating status includes: analyzing the operating data using a process equipment operating status prediction model.

[0076] That is, the real-time collected operating data is directly input into the trained process equipment operating status prediction model.

[0077] In this embodiment, the predicted operating status of the process equipment is outputted through the process equipment operating status prediction model.

[0078] Rapid inference of the process equipment operating status prediction model outputs the predicted operating status of the process equipment for use by the maintenance scheduling system.

[0079] Execute step S3: Generate a maintenance plan for the process equipment based on the predicted operating status.

[0080] It should be noted that, based on the predicted operating status, when the process equipment is normal, there is no need to generate a maintenance plan; when the process equipment is not normal, a maintenance plan for the process equipment is generated.

[0081] Specifically, in this embodiment, a maintenance plan for process equipment is generated using a maintenance scheduling system based on the predicted operating status.

[0082] The maintenance scheduling system is mainly implemented based on a rule engine and simple optimization logic. It takes existing empirical rules and predicted operating status as input and automatically derives maintenance plans through preset logic.

[0083] Specifically, in this embodiment, a maintenance plan for the process equipment is generated based on the predicted operating status. The maintenance plan includes maintenance time, maintenance steps, and spare parts or resources required for maintenance.

[0084] Maintenance time includes recommended maintenance timing, for example, immediately after the next production batch; maintenance steps including a detailed operation list; spare parts or resources required for maintenance, such as seals, flow controllers, etc.

[0085] In this embodiment, generating a maintenance plan for the process equipment based on the predicted operating status includes: determining the urgency of a failure of the process equipment based on the predicted operating status.

[0086] Determine the urgency of process equipment failures based on the predicted operating status and prioritize specific maintenance for the process equipment.

[0087] As an example, in this embodiment, based on the abnormality score, for example, greater than 80%, it is marked as a high priority.

[0088] In this embodiment, a standard maintenance procedure of process equipment is obtained.

[0089] Obtain the standard maintenance process for process equipment by matching the standard maintenance process template. For example, if a vacuum pump is abnormal, shut it down first, replace the seal, and then re-debug it.

[0090] In this embodiment, a production schedule of process equipment is obtained.

[0091] Obtain the production schedule of process equipment and combine it with the real-time production schedule of process equipment to avoid maintenance during peak production periods.

[0092] Accordingly, in this embodiment, the urgency of the fault is matched with the standard maintenance procedure of the process equipment, and combined with the production scheduling plan, a maintenance plan for the process equipment is generated.

[0093] In this embodiment, after generating a maintenance plan for the process equipment based on the predicted operating status, the method further includes: transmitting the maintenance plan for the process equipment to an operating system of the process equipment.

[0094] The maintenance plan of the process equipment is transmitted to the operating system of the process equipment. The maintenance scheduling system notifies the maintenance personnel to perform maintenance operations according to the plan to prevent equipment downtime and failure.

[0095] Correspondingly, the present invention also provides a predictive maintenance system for process equipment. Figure 2 It is a functional block diagram of an embodiment of a predictive maintenance system for process equipment of the present invention.

[0096] In this embodiment, the predictive maintenance system 50 for process equipment includes: an operation data acquisition module 501, which is used to obtain the operation data of the process equipment; an operation status prediction module 502, which is used to analyze the operation data and predict the operation status of the process equipment as the predicted operation status; and a maintenance plan generation module 503, which is used to generate a maintenance plan for the process equipment based on the predicted operation status.

[0097] In the semiconductor manufacturing process, the performance and reliability of process equipment are crucial.

[0098] In this embodiment, the predictive maintenance method is suitable for etching process equipment.

[0099] The highly corrosive atmosphere, plasma environment and complex working conditions unique to the etching process make etching process equipment particularly in need of predictive maintenance. Therefore, the predictive maintenance method of this embodiment is particularly suitable for etching process equipment, and the optimization effect is particularly significant in the etching process scenario.

[0100] The operation data acquisition module 501 is used to obtain real-time operation data of process equipment.

[0101] Obtain real-time operating data of process equipment for real-time prediction of the operating status of process equipment.

[0102] In this embodiment, in acquiring the real-time operation data of the process equipment, the operation data includes equipment status data and environment status data of the process equipment.

[0103] Equipment status data and environmental status data can represent the real-time status of process equipment.

[0104] Specifically, in this embodiment, the equipment status data includes one or more of equipment temperature data, process pressure data, equipment vibration amplitude data and process gas flow data; the environmental status data includes one or more of environmental temperature data, environmental humidity data and environmental pressure data.

[0105] Equipment temperature data, process pressure data, equipment vibration amplitude data and process gas flow data can characterize the equipment status of the process equipment, and ambient temperature data, ambient humidity data and ambient air pressure data can characterize the environmental status.

[0106] In this embodiment, in acquiring the real-time operating data of the process equipment, the operating data is collected by a sensor array on the process equipment.

[0107] Specifically, a comprehensive sensor array is installed on the process equipment to monitor the equipment status and environmental status of the process equipment in real time. The process equipment is monitored in real time through the sensor array, and the equipment status data and environmental status data of the process equipment are continuously collected through the data acquisition module.

[0108] In this embodiment, the subsequent analysis of the operating data and prediction of the operating status of the process equipment further includes: pre-processing the operating data of the process equipment and screening effective operating data before predicting the operating status.

[0109] Pre-process the operating data of process equipment and screen valid operating data to ensure the quality of the operating data of process equipment.

[0110] In this embodiment, pre-processing is performed on the operation data of the process equipment, including: performing data cleaning on the operation data of the process equipment to remove abnormal operation data.

[0111] Perform data cleaning on the operating data of process equipment to remove outliers and missing values ​​in the operating data to ensure the integrity and accuracy of the operating data.

[0112] In this embodiment, the operating data is normalized.

[0113] Normalizing the operating data and standardizing the operating data to a unified range will help improve the data calculation rate.

[0114] In this embodiment, feature extraction is performed on the operating data to obtain reorganized operating data.

[0115] Perform feature extraction on the operating data to extract important features from the original operating data for input into subsequent machine learning models to perform efficient and accurate data analysis.

[0116] In this embodiment, the predictive maintenance method further includes: establishing a process equipment operation status prediction model, where the process equipment operation status prediction model includes a mapping relationship between operation data and operation status.

[0117] Establish a process equipment operating status prediction model to analyze operating data and output the operating status of process equipment.

[0118] In this embodiment, establishing a process equipment operation state prediction model includes: collecting historical operation information of the process equipment, where the historical operation information includes the historical operation state of the process equipment and historical operation data of the process equipment under different historical operation states.

[0119] Collect historical operating information of process equipment for machine learning modeling. The historical operating information includes the historical operating status of the process equipment and the historical operating data of the process equipment under different historical operating statuses. That is, collect historical equipment status data and environmental status data collected by sensors, and each set of data corresponds to a real process equipment operating status label.

[0120] As an example, in this embodiment, the collected historical operation information includes two parts: feature data (X): equipment status data (such as temperature, pressure, vibration amplitude, gas flow, etc.), environmental status data (such as cavity temperature, humidity, external air pressure, etc.); label data (Y): the actual status of the process equipment corresponding to each set of data (such as normal, early anomaly, failure). Among them, the label can be a classification label (such as normal / abnormal / failure) or a continuous value (such as a health index score). Therefore, calibration data is required, that is, each section of historical sensor collected data must correspond to a label of the process equipment status in order to perform supervised learning training.

[0121] Accordingly, in this embodiment, supervised learning training is performed on the historical operation information of the process equipment to construct a process equipment operation status prediction model.

[0122] All models are built using historical operating information so that when the model is applied in real time in the future, it can predict potential failure risks based on new data collected in real time.

[0123] Specifically, in this embodiment, a neural network model, a support vector machine model or a random forest model is used to perform supervised learning training on the historical operation information of the process equipment.

[0124] The operation state prediction module 502 is used to analyze the operation data and predict the operation state of the process equipment as the predicted operation state.

[0125] Obtain the predicted operating status of process equipment to determine whether the process equipment needs maintenance based on it.

[0126] In this embodiment, by collecting the operating data of the process equipment in real time and analyzing the operating data, the operating status of the process equipment is predicted in real time, the potential failures or process deviations of the process equipment are obtained, and then a maintenance plan for the process equipment is generated based on the predicted operating status. This is conducive to identifying signs of failure in advance before the process equipment fails, so that maintenance activities can be arranged in time before the failure occurs, preventing unplanned shutdown of the process equipment, and thus helping to improve production efficiency and reduce maintenance costs.

[0127] In this embodiment, the operating data is analyzed to predict the operating status of the process equipment. The predicted operating status includes the predicted health status of the process equipment. The predicted health status includes normal, initial abnormality, and failure.

[0128] Specifically, when the predicted health status of the process equipment is normal, no maintenance plan may be carried out. When the predicted health status of the process equipment is initial abnormality or failure, a maintenance plan will be carried out for the process equipment later.

[0129] In this embodiment, the predicted health status further includes parameter drift of parameters corresponding to the operating data of the process equipment and / or the overall equipment health index of the process equipment.

[0130] Specifically, the parameter drift output is the key parameter offset compared to the normal state (such as temperature drift, pressure change rate exceeding the standard, etc.), and the overall equipment health index (Health Index) output of the process equipment is the health index of the entire process equipment (such as HI = 78%, which is lower than the set threshold and requires maintenance).

[0131] In this embodiment, the operating data is analyzed to predict the operating status of the process equipment. The predicted operating status also includes a failure risk score of each component in the process equipment. The failure risk score includes a failure probability or an abnormality score.

[0132] Specifically, the failure risk score (Anomaly Score / Failure Probability) output is the anomaly score or failure probability of each monitored component of the process equipment. For example, the vacuum system failure probability = 85%; the gas flow anomaly score = 0.92 (score range 0-1).

[0133] Predicting the failure risk score of each component in process equipment can quantify the urgency and severity of failures and assist in maintenance priority sorting.

[0134] Accordingly, in this embodiment, analyzing the operating data and predicting the operating status of the process equipment as the predicted operating status includes: analyzing the operating data using a process equipment operating status prediction model.

[0135] That is, the real-time collected operating data is directly input into the trained process equipment operating status prediction model.

[0136] In this embodiment, the predicted operating status of the process equipment is outputted through the process equipment operating status prediction model.

[0137] Rapid inference of the process equipment operating status prediction model outputs the predicted operating status of the process equipment for use by the maintenance scheduling system.

[0138] The maintenance plan generating module 503 is used to generate a maintenance plan for the process equipment based on the predicted operating status.

[0139] It should be noted that, based on the predicted operating status, when the process equipment is normal, there is no need to generate a maintenance plan; when the process equipment is not normal, a maintenance plan for the process equipment is generated.

[0140] Specifically, in this embodiment, a maintenance plan for process equipment is generated using a maintenance scheduling system based on the predicted operating status.

[0141] The maintenance scheduling system is mainly implemented based on a rule engine and simple optimization logic. It takes existing empirical rules and predicted operating status as input and automatically derives maintenance plans through preset logic.

[0142] Specifically, in this embodiment, a maintenance plan for the process equipment is generated based on the predicted operating status. The maintenance plan includes maintenance time, maintenance steps, and spare parts or resources required for maintenance.

[0143] Maintenance time includes recommended maintenance timing, for example, immediately after the next production batch; maintenance steps including a detailed operation list; spare parts or resources required for maintenance, such as seals, flow controllers, etc.

[0144] In this embodiment, generating a maintenance plan for the process equipment based on the predicted operating status includes: determining the urgency of a failure of the process equipment based on the predicted operating status.

[0145] Determine the urgency of process equipment failures based on the predicted operating status and prioritize specific maintenance for the process equipment.

[0146] As an example, in this embodiment, based on the abnormality score, for example, greater than 80%, it is marked as a high priority.

[0147] In this embodiment, a standard maintenance procedure of process equipment is obtained.

[0148] Obtain the standard maintenance process for process equipment by matching the standard maintenance process template. For example, if a vacuum pump is abnormal, shut it down first, replace the seal, and then re-debug it.

[0149] In this embodiment, a production schedule of process equipment is obtained.

[0150] Obtain the production schedule of process equipment and combine it with the real-time production schedule of process equipment to avoid maintenance during peak production periods.

[0151] Accordingly, in this embodiment, the urgency of the fault is matched with the standard maintenance procedure of the process equipment, and combined with the production scheduling plan, a maintenance plan for the process equipment is generated.

[0152] In this embodiment, after generating a maintenance plan for the process equipment based on the predicted operating status, the method further includes: transmitting the maintenance plan for the process equipment to an operating system of the process equipment.

[0153] The maintenance plan of the process equipment is transmitted to the operating system of the process equipment. The maintenance scheduling system notifies the maintenance personnel to perform maintenance operations according to the plan to prevent equipment downtime and failure.

[0154] The embodiment of the present invention further provides a device that can implement the predictive maintenance method for process equipment provided by the embodiment of the present invention by loading the predictive maintenance method for process equipment in the form of a program. An optional hardware structure of the terminal device provided by the embodiment of the present invention can be as follows Figure 3 As shown, it includes: at least one processor 01, at least one communication interface 02, at least one memory 03 and at least one communication bus 04.

[0155] In this embodiment, the number of processor 01, communication interface 02, memory 03, and communication bus 04 is at least one, and the processor 01, communication interface 02, and memory 03 communicate with each other through the communication bus 04. The communication interface 02 can be an interface of a communication module for network communication, such as an interface of a GSM module. The processor 01 may be a central processing unit CPU, or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement an embodiment of the present invention. The memory 03 may include a high-speed RAM memory, and may also include a non-volatile memory (NVM), such as at least one disk storage. The memory 03 stores one or more computer instructions, and the one or more computer instructions are executed by the processor 01 to implement the predictive maintenance method of the process equipment provided in an embodiment of the present invention.

[0156] It should be noted that the above-mentioned terminal device may also include other devices (not shown) that may not be necessary for understanding the contents disclosed in the embodiments of the present invention; given that these other devices may not be necessary for understanding the contents disclosed in the embodiments of the present invention, the embodiments of the present invention will not introduce them one by one.

[0157] An embodiment of the present invention further provides a storage medium storing one or more computer instructions, wherein the one or more computer instructions are used to implement the predictive maintenance method for process equipment provided by the embodiment of the present invention.

[0158] An embodiment of the present invention further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the predictive maintenance method for process equipment provided by an embodiment of the present invention.

[0159] In an embodiment of the present invention, by collecting operating data of process equipment in real time and analyzing the operating data, the operating status of the process equipment is predicted in real time, potential failures or process deviations of the process equipment are obtained, and then a maintenance plan for the process equipment is generated based on the predicted operating status. This is conducive to identifying signs of failure in advance before the process equipment fails, thereby arranging maintenance activities in time before the failure occurs, preventing unplanned shutdown of the process equipment, and thus helping to improve production efficiency and reduce maintenance costs.

[0160] The embodiments of the present invention described above are combinations of elements and features of the present invention. Unless otherwise mentioned, the elements or features may be considered as optional. Each element or feature may be put into practice without being combined with other elements or features. In addition, the embodiments of the present invention may be constructed by combining some elements and / or features. The order of operations described in the embodiments of the present invention may be rearranged. Some configurations of any one embodiment may be included in another embodiment and may be replaced by the corresponding configuration of another embodiment. It is obvious to those skilled in the art that claims that do not have a clear reference relationship to each other in the appended claims may be combined into embodiments of the present invention, or may be included as new claims in amendments after submitting this application.

[0161] The embodiments of the present invention can be implemented by various means such as hardware, firmware, software or a combination thereof. In a hardware configuration, the method according to the exemplary embodiment of the present invention can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, etc. In a firmware or software configuration, the embodiments of the present invention can be implemented in the form of modules, processes, functions, etc. The software code can be stored in a memory unit and executed by a processor. The memory unit is located inside or outside the processor and can send data to the processor and receive data from the processor via various known means.

[0162] The above description of the disclosed embodiments will enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

[0163] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be based on the scope defined by the claims.

Claims

1. A predictive maintenance method for process equipment, characterized in that: include: Acquiring real-time operating data of the process equipment; Analyzing the operating data to predict an operating state of the process equipment as a predicted operating state; A maintenance plan for the process equipment is generated based on the predicted operating status.

2. The predictive maintenance method according to claim 1, wherein: In acquiring the real-time operation data of the process equipment, the operation data includes equipment status data and environmental status data of the process equipment.

3. The predictive maintenance method according to claim 2, wherein: The equipment status data includes one or more of equipment temperature data, process pressure data, equipment vibration amplitude data, and process gas flow data; The environmental status data includes one or more of environmental temperature data, environmental humidity data and environmental air pressure data.

4. The predictive maintenance method according to claim 1, wherein: In acquiring the real-time operating data of the process equipment, the operating data is collected by a sensor array on the process equipment.

5. The predictive maintenance method according to claim 1, wherein: The operation data is analyzed to predict the operation status of the process equipment. Before predicting the operation status, the method further includes: pre-processing the operation data of the process equipment to screen effective operation data.

6. The predictive maintenance method according to claim 5, wherein: Preprocessing the operating data of the process equipment includes: cleaning the operating data of the process equipment to remove abnormal operating data; performing normalization processing on the operating data; Feature extraction is performed on the operation data to obtain reorganized operation data.

7. The predictive maintenance method according to claim 1, wherein: The predictive maintenance method further includes: establishing a process equipment operating state prediction model, wherein the process equipment operating state prediction model includes a mapping relationship between operating data and operating state; Analyzing the operating data to predict the operating state of the process equipment as the predicted operating state includes: analyzing the operating data using the process equipment operating state prediction model; The predicted operating state of the process equipment is outputted through the process equipment operating state prediction model.

8. The predictive maintenance method according to claim 7, wherein: Establishing a process equipment operation state prediction model, comprising: collecting historical operation information of the process equipment, the historical operation information including the historical operation state of the process equipment and historical operation data of the process equipment under different historical operation states; Supervised learning training is performed on the historical operation information of the process equipment to build a prediction model for the operation status of the process equipment.

9. The predictive maintenance method according to claim 8, wherein: A neural network model, a support vector machine model or a random forest model is used to perform supervised learning training on the historical operation information of the process equipment.

10. The predictive maintenance method according to claim 1, wherein: The operating data is analyzed to predict the operating state of the process equipment. The predicted operating state includes a predicted health state of the process equipment, and the predicted health state includes normal, initial abnormality, and failure.

11. The predictive maintenance method according to claim 10, wherein: The predicted health status also includes parameter drift of parameters corresponding to the operating data of the process equipment and / or an overall equipment health index of the process equipment.

12. The predictive maintenance method according to claim 1, wherein: The operating data is analyzed to predict the operating state of the process equipment. As the predicted operating state, the predicted operating state also includes a failure risk score of each component in the process equipment, and the failure risk score includes a failure probability or an abnormality score.

13. The predictive maintenance method according to claim 1, wherein: Based on the predicted operating status, a maintenance plan for the process equipment is generated, wherein the maintenance plan includes maintenance time, maintenance steps, and spare parts or resources required for maintenance.

14. The predictive maintenance method according to claim 1, wherein: Generating a maintenance plan for the process equipment based on the predicted operating status, including: determining a failure urgency of the process equipment based on the predicted operating status; Obtain standard maintenance procedures for the process equipment; Obtaining a production schedule for the process equipment; The fault urgency is matched with the standard maintenance procedure of the process equipment, and combined with the production schedule to generate a maintenance plan for the process equipment.

15. The predictive maintenance method according to claim 1, wherein: After generating a maintenance plan for the process equipment based on the predicted operating status, the method further includes: transmitting the maintenance plan for the process equipment to an operating system of the process equipment.

16. The predictive maintenance method according to claim 1, wherein: The predictive maintenance method is suitable for etching process equipment.

17. A predictive maintenance system for process equipment, characterized in that: include: An operation data acquisition module, used for acquiring the operation data of the process equipment; an operating state prediction module, configured to analyze the operating data and predict the operating state of the process equipment as a predicted operating state; A maintenance plan generating module is used to generate a maintenance plan for the process equipment based on the predicted operating status.

18. A device, characterized in that The method comprises at least one memory and at least one processor, wherein the memory stores one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the predictive maintenance method of the process equipment according to any one of claims 1 to 16.

19. A storage medium, characterized in that The storage medium stores one or more computer instructions, and the one or more computer instructions are used to implement the predictive maintenance method of the process equipment according to any one of claims 1 to 16.

20. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the predictive maintenance method for process equipment according to any one of claims 1 to 16 is implemented.

Images