Monitoring method, device, computer equipment and storage medium for production line equipment

Abstract

The present application relates to a monitoring method, device, computer equipment and storage medium for production line equipment. The method includes: screening out target production line equipment from all production line equipment based on the operating status, key equipment parameters and working environment conditions of each production line equipment in the physical production line; configuring the data type required to be collected by the target production line equipment, and setting the transmission protocol, parsing method and collection cycle required for collecting data; based on the transmission protocol, the parsing method and the collection cycle, collecting the historical operating data, historical fault data, environmental parameters and process parameters of the target production line equipment from the configured data source; based on the collected data, training a fault diagnosis model, and using the fault diagnosis model to perform fault diagnosis on the target production line equipment. The use of this method can improve the timeliness and accuracy of production line equipment status monitoring.

Description

Technical Field

[0001] The present application relates to the technical field of operation and maintenance of production line equipment, and in particular to a monitoring method, device, computer equipment and storage medium for production line equipment. Background Art

[0002] Production line equipment is essential to the production process. As the manufacturing industry evolves, its functions and structures become increasingly complex, making it difficult to directly monitor its actual operating status. However, the actual operating status of production line equipment can significantly impact production efficiency, making effective monitoring of production line equipment imperative.

[0003] Existing monitoring methods for production line equipment mostly use manual inspections, which is not only time-consuming and labor-intensive, but also fails to monitor production line equipment in a timely manner, resulting in poor monitoring results. Summary of the Invention

[0004] Based on this, it is necessary to provide a monitoring method, device, computer equipment and storage medium for production line equipment that can improve the timeliness and accuracy of production line equipment status monitoring in response to the above technical problems.

[0005] In a first aspect, the present application provides a monitoring method for production line equipment. The method comprises:

[0006] Filter out target production line equipment from all production line equipment based on the operating status, key equipment parameters, and working environment conditions of each production line equipment in the actual production line;

[0007] Configure the data type that the target production line equipment needs to collect, and set the transmission protocol, parsing method and collection cycle required for the collected data;

[0008] Based on the transmission protocol, the parsing method and the collection period, collect historical operation data, historical fault data, environmental parameters and process parameters of the target production line equipment from the configuration data source;

[0009] Based on the collected data, a fault diagnosis model is trained to perform fault diagnosis on the target production line equipment using the fault diagnosis model.

[0010] In one embodiment, the collected data is collected in groups; and the training of a fault diagnosis model based on the collected data includes:

[0011] Perform attribute transformation, working condition identification, missing value processing, indicator filtering, correlation detection, outlier detection, data grafting identification and data normalization on the collected data;

[0012] Based on each set of processed data and the corresponding fault mode labels, the initial fault diagnosis model is trained to obtain a fault diagnosis model.

[0013] In one embodiment, the method further comprises:

[0014] Based on the transmission protocol, the parsing method and the collection period, collecting historical power supply parameters of the target production line equipment from a configuration data source;

[0015] A sample voltage ripple is extracted from the power supply historical parameters, and based on the sample voltage ripple, the remaining life of the power supply of the target production line equipment is predicted.

[0016] In one embodiment, the power supply historical parameters include historical voltage signals collected during different historical periods; and extracting the sample voltage ripple from the power supply historical parameters includes:

[0017] The voltage average value of the historical voltage signal is calculated, and the voltage average value is subtracted from the historical voltage signal to obtain a sample voltage ripple in a corresponding historical period.

[0018] In one embodiment, predicting the remaining life of the power supply of the target production line equipment based on the sample voltage ripple includes:

[0019] Performing Fourier transform on the sample voltage ripple to obtain a plurality of sub-sample voltage ripples, and a ripple frequency and a voltage amplitude corresponding to each sub-sample voltage ripple;

[0020] Obtaining an inherent ripple frequency and a voltage amplitude threshold of the power supply output voltage, and determining a ripple frequency having a voltage amplitude greater than the voltage amplitude threshold among the plurality of sub-sample voltage ripples as a ripple frequency set;

[0021] determining a ripple frequency value range based on the inherent ripple frequency and the frequency classification error radius, classifying ripple frequencies in the ripple frequency set that are within the ripple frequency value range as inherent ripple frequency categories, and classifying the remaining ripple frequencies in the ripple frequency set as degenerate ripple frequency categories;

[0022] Determine a first functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the inherent ripple frequency category, and determine a second functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the degenerate ripple frequency category;

[0023] Determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the inherent ripple frequency category as a first fault value, and determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the degraded ripple frequency category as a second fault value;

[0024] Based on the first functional relationship, predict the first required time for the voltage amplitude of the current voltage ripple to reach the first fault value. Based on the second functional relationship, predict the second required time for the voltage amplitude of the current voltage ripple to reach the second fault value. Compare the first required time with the second required time, and select the smaller value as the remaining life of the power supply.

[0025] In one embodiment, the method further comprises:

[0026] Based on the transmission protocol, the parsing method, and the collection period, monitoring parameters of the physical production line are collected, wherein the monitoring parameters include the operating power of the production line and the temperature of at least one motor;

[0027] Based on the motor temperature of each line, the temperature health of each line is calculated, and based on the operating power of the production line, the power health is calculated;

[0028] The power health is integrated with the temperature health of each line to obtain the total health, which is used as the health assessment result of the physical production line.

[0029] In a second aspect, the present application also provides a monitoring device for production line equipment. The device includes:

[0030] The equipment screening module is used to screen target production line equipment from all production line equipment based on the operating status, key equipment parameters and working environment conditions of each production line equipment in the actual production line;

[0031] A data configuration module is used to configure the data type required to be collected by the target production line equipment, and set the transmission protocol, parsing method and collection cycle required for the collected data;

[0032] A data acquisition module, configured to collect historical operating data, historical fault data, environmental parameters, and process parameters of the target production line equipment from a configured data source based on the transmission protocol, the parsing method, and the acquisition cycle;

[0033] The model diagnosis module is used to train a fault diagnosis model based on the collected data, and perform fault diagnosis on the target production line equipment through the fault diagnosis model.

[0034] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0036] In a fifth aspect, the present application further provides a computer program product, which includes a computer program that implements the steps of any of the above methods when executed by a processor.

[0037] The above-mentioned monitoring method, device, computer equipment and storage medium for production line equipment determine the target production line equipment from the various production line equipment of the physical production line, configure the data type required to be collected by the target production line equipment, and configure the transmission protocol, parsing method and collection cycle related to data collection, perform data collection based on the configured transmission protocol, parsing method and collection cycle, obtain a fault diagnosis model through training with the collected data, and perform fault diagnosis on the target production line equipment through the fault diagnosis model. Compared with the traditional technology of monitoring the status of production line equipment through personnel inspections, which results in low timeliness and accuracy, the present application determines the target production line equipment from the various production line equipment of the physical production line, which is more targeted, and performs fault diagnosis on the target production line equipment through data collection and fault diagnosis models, thereby improving the timeliness and accuracy of monitoring the target production line equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of a monitoring method for production line equipment provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of a process for training a fault diagnosis model in one embodiment;

[0040] Figure 3 A schematic diagram of a process for predicting the remaining life of a power supply of a target production line device in one embodiment;

[0041] Figure 4 A schematic diagram of a sample voltage ripple and its spectrum provided in one embodiment;

[0042] Figure 5 A schematic diagram of a process for obtaining a health assessment result of a physical production line in one embodiment;

[0043] Figure 6 This is a structural block diagram of a monitoring device for production line equipment provided in an embodiment of the present application;

[0044] Figure 7 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0046] In this embodiment, a monitoring method for production line equipment is provided. This embodiment uses the method applied to a computer device as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a computer device and a server, and is implemented through the interaction between the computer device and the server.

[0047] Figure 1 This is a flow chart of a monitoring method for production line equipment provided in an embodiment of the present application. The method is applied to a computer device or a server. In one embodiment, Figure 1 As shown, the following steps are included:

[0048] S101, based on the working status, key equipment parameters and working environment conditions of each production line equipment in the actual production line, select the target production line equipment from all production line equipment.

[0049] The "physical production line equipment" includes all required production equipment, such as high-bay warehouses, raw material monitoring equipment, CNC machine tools, robots, motors, finished product quality monitoring boxes, AOI automated optical inspection (AOI) systems, environmental test chambers, and energy monitoring systems. The "operating status" of each production line equipment refers to its operating state. Key equipment parameters refer to parameters that must be monitored during operation, such as current, voltage, temperature, status, power, and vibration. Operating environmental conditions refer to the environment in which each production line equipment operates, including temperature, humidity, and other environmental factors that may affect its normal operation.

[0050] Target equipment is selected from all production line equipment to ensure monitoring efficiency. Monitoring is targeted at key equipment, including CNC machine tools, motors, AOI automated optical inspection (AOI) systems, environmental test chambers, energy monitoring systems, and SCARA robots. Specifically, key equipment parameters for CNC machine tools include temperature, vibration severity, vibration kurtosis, vibration velocity, current, frequency, and phase; key equipment parameters for six-axis robots (J1, J2, J3, J4, J5, and J6 axes) include temperature, ABC phase voltage, ABC phase current, power, energy, residual current RMS value, residual current channel status, and meter DI port status.

[0051] S102, configuring the data type required to be collected by the target production line equipment, and setting the transmission protocol, parsing method and collection cycle required to collect the data.

[0052] In this embodiment, the data type required to be collected by the target production line equipment is configured, that is, the data source of the data required to be collected by the target production line equipment is configured. The data source includes a SCADA system, an MES system, and an edge layer motor system, preferably a SCADA system and an MES system. The transmission protocols may include TCP, UDP, WebSocket, Http, and Socket, preferably WebSocket and Http. The parsing method is determined by the data source of the required data, and the collection period can be manually set.

[0053] S103 , based on the transmission protocol, parsing method and collection cycle, collect historical operation data, historical fault data, environmental parameters and process parameters of the target production line equipment from the configuration data source.

[0054] Among them, the historical operation data of the target production line equipment refers to the equipment parameters during the historical operation of the target production line equipment; the historical fault data refers to the basic data and equipment parameters of the target production line equipment when a fault occurred during the historical operation of the target production line equipment. The basic equipment data includes manufacturer information, production date, physical map, model, equipment number, and monitorable parameter information; environmental parameters refer to the parameters of the environment in which the target production line equipment is located; process parameters refer to the operating status parameters of the target production line equipment.

[0055] S104: Based on the collected data, a fault diagnosis model is trained and a fault diagnosis model is performed on the target production line equipment using the fault diagnosis model.

[0056] The monitoring method for production line equipment provided in this embodiment determines the target production line equipment from the various production line equipment of the physical production line, configures the data type required to be collected by the target production line equipment, and configures the transmission protocol, parsing method and collection cycle related to data collection. Data collection is performed based on the configured transmission protocol, parsing method and collection cycle, and a fault diagnosis model is obtained by training the collected data. The target production line equipment is then diagnosed for faults using the fault diagnosis model. Compared with the traditional technology of monitoring the status of production line equipment through personnel inspections, which results in low timeliness and accuracy, the present application determines the target production line equipment from the various production line equipment of the physical production line, which is more targeted, and performs fault diagnosis on the target production line equipment through data collection and fault diagnosis models, thereby improving the timeliness and accuracy of monitoring the target production line equipment.

[0057] In one embodiment, the collected data is collected in groups. Based on the collected data, a flow chart of a fault diagnosis model is trained, such as Figure 2 As shown, the following steps are included:

[0058] S201, performing attribute transformation, working condition identification, missing value processing, indicator filtering, correlation detection, outlier detection, data grafting identification and data normalization on the collected data.

[0059] The collected data includes historical operating data, historical fault data, environmental parameters, and process parameters of the target production line equipment. The collected data undergoes attribute transformation, operating condition identification, missing value processing, indicator filtering, correlation detection, outlier detection, data grafting identification, and data normalization to filter out noise data, extract feature data, and enhance the reliability of the collected data.

[0060] S202 : Based on each set of processed data and the corresponding fault mode labels, an initial fault diagnosis model is trained to obtain a fault diagnosis model.

[0061] Among them, the initial fault diagnosis model can be random forest regression, gradient boosting decision tree regression, ARIMA, classification xgboost, support vector machine, LightGBM algorithm, and the initial fault diagnosis model is selected according to the collected data type.

[0062] Taking the fault diagnosis of a CNC machine tool as an example, the equipment parameters of the CNC machine tool include XYZ-axis lubricating oil temperature, XYZ-axis guide vibration severity, XYZ-axis guide vibration kurtosis, XYZ-axis guide vibration velocity, XYZ-axis guide vibration kurtosis, XYZ-axis screw vibration kurtosis, XYZ-axis screw vibration velocity, XYZ-axis screw vibration severity, XYZ-axis current, XYZ-axis frequency, XYZ-axis phase, spindle current, spindle frequency, and spindle phase. These parameters correspond to the spindle, drive, feed, lubrication, and tool systems of the CNC machine tool. Using the SCADA system as the data source for the CNC machine tool, the collected parameter data is processed for operating condition identification, indicator filtering, outlier processing, and data grafting identification. Initial fault diagnosis models (random forest, Xgboost, and support vector machines) are selected and trained using the collected parameter data to obtain the optimal fault diagnosis model. The optimal fault diagnosis model is used to diagnose the fault of CNC machine tools by calculating the residual between the true value and the model predicted value.

[0063] See also Figure 3 , Figure 3 The flowchart for predicting the remaining life of the power supply of target production line equipment in one embodiment includes the following contents:

[0064] S301 , based on the transmission protocol, parsing method and collection cycle, collect historical power parameters of target production line equipment from the configuration data source.

[0065] The power supply historical parameters include historical voltage signals collected in different historical time periods.

[0066] The historical voltage signal may be collected by collecting the output voltage signal once every T days, with each collection time being L seconds to obtain a continuous output voltage signal.

[0067] S302 , extracting sample voltage ripples from historical power supply parameters, and predicting the remaining life of the power supply of target production line equipment based on the sample voltage ripples.

[0068] In this embodiment, the method for extracting the sample voltage ripple from the historical parameters of the power supply can be to calculate the voltage average of the historical voltage signal, subtract the historical voltage signal from the voltage average, and obtain the sample voltage ripple in the corresponding historical period. The sample voltage ripple is subjected to Fourier transform to obtain multiple sub-sample voltage ripples and the corresponding ripple frequency and voltage amplitude of each sub-sample voltage ripple. Figure 4 FIG. 1 is a schematic diagram of a sample voltage ripple and its spectrum provided in one embodiment. Figure 4 First, the historical voltage signal is collected, and the ripple is extracted from the historical voltage signal to obtain the sample voltage ripple. Finally, FFT transformation (Fourier transform) is performed to obtain multiple sub-sample voltage ripples and the corresponding ripple frequency and voltage amplitude of each sub-sample voltage ripple.

[0069] Based on the sample voltage ripple, the remaining life of the power supply of the target production line equipment is predicted, including:

[0070] Obtaining the inherent ripple frequency and voltage amplitude threshold of the power supply output voltage, and determining the ripple frequency of the plurality of sub-sample voltage ripples whose voltage amplitude is greater than the voltage amplitude threshold as the ripple frequency set;

[0071] The inherent ripple frequency of the power supply output voltage is set to Fw. The value of Fw can be determined according to the working principle of the power supply or after Fourier transforming the actually collected output voltage ripple. The voltage amplitude threshold is set to Ar.

[0072] Based on the inherent ripple frequency and the frequency classification error radius, a ripple frequency value range is determined, ripple frequencies within the ripple frequency value range in the ripple frequency set are classified as inherent ripple frequency categories, and the remaining ripple frequencies in the ripple frequency set are classified as degraded ripple frequency categories;

[0073] The frequency classification error radius is set to Fe, and the ripple frequency that is not greater than the value of Fe is classified as the inherent ripple frequency category, the inherent ripple frequency category is recorded as Aw, and the degraded ripple frequency category is recorded as Awd.

[0074] Determine a first functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the inherent ripple frequency category, and determine a second functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the degenerate ripple frequency category;

[0075] Determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the inherent ripple frequency category as a first fault value, and determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the degraded ripple frequency category as a second fault value;

[0076] Based on the first functional relationship, predict the first required time for the voltage amplitude of the current voltage ripple to reach the first fault value. Based on the second functional relationship, predict the second required time for the voltage amplitude of the current voltage ripple to reach the second fault value. Compare the first required time with the second required time, and select the smaller value as the remaining life of the power supply.

[0077] See also Figure 5 , Figure 5 The flowchart for obtaining the health assessment results of a physical production line in one embodiment includes the following contents:

[0078] S501, based on the transmission protocol, parsing method and collection cycle, collect monitoring parameters of the actual production line, the monitoring parameters including the production line operating power and the motor temperature of at least one line.

[0079] Specifically, examples of the monitoring parameters collected for a physical production line are shown in Table 1 below. Table 1 is the monitoring parameters for a physical production line.

[0080] Table 1 Physical production line monitoring parameters

[0081] parameter healthy Alarm Fault Channel 1 temperature T1 (°C) T1＜53 53≤T1＜60 T1≥60 2nd channel temperature T2(℃) T1＜53 53≤T2＜60 T2≥60 Production line operating power P (kW) P≥2 1.3≤P＜2 P＜1.3

[0082] S502: Calculate the temperature health of each line based on the motor temperature of each line, and calculate the power health based on the production line operating power.

[0083] Specifically, based on the above example, the temperature health of the first channel is calculated by formula (1), the temperature health of the second channel is calculated by formula (2), and the power health is calculated by formula (3). Formulas (1)-(3) are as follows:

[0084]

[0085]

[0086]

[0087] Among them, H1, H2, and H3 represent the temperature health of the first channel, the temperature health of the second channel, and the power health, respectively. T1 represents the temperature of the first channel, T2 represents the temperature of the second channel, and P represents the operating power of the production line.

[0088] S503 : Integrate the power health and the temperature health of each line to obtain the total health, which is used as the health assessment result of the physical production line.

[0089] Specifically, the total health is calculated using the following formula (4):

[0090]

[0091] Among them, H represents the overall health, S represents the status of the monitoring parameter, and when the status is faulty, S=0. H1, H2, and H3 represent the temperature health of the first channel, the temperature health of the second channel, and the power health, respectively.

[0092] According to the total health degree corresponding to the following Table 2, the health assessment results are obtained. Table 2 shows the corresponding relationship between health degree and health status.

[0093] Table 2 Correspondence between health degree and health status

[0094] Total health H H≥0.8 0.2≤H＜0.8 H＜0.2 Health status healthy Alarm Fault

[0095] Based on the fault diagnosis results and health assessment results, combined with the set maintenance method, maintenance type, maintenance plan (cycle), maintenance personnel and maintenance spare parts content, a maintenance plan can be obtained.

[0096] The monitoring method for production line equipment provided in this embodiment comprehensively considers the differences in working conditions between actual production lines and workshops, key equipment parameters, and environmental conditions, and combines it with a fault diagnosis model to achieve real-time health status monitoring and fault diagnosis of key equipment on the production line, and can predict the remaining life of production line equipment. It also takes into account environmental conditions and can reduce the impact of relevant environmental parameters on the life and health status of production line equipment.

[0097] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0098] Based on the same inventive concept, the embodiments of the present application also provide a monitoring device for production line equipment for implementing the aforementioned monitoring method for production line equipment. The solution to the problem provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in the embodiments of one or more monitoring devices for production line equipment provided below can be found in the above-mentioned limitations on the monitoring method for production line equipment, and will not be repeated here.

[0099] See also Figure 6 , Figure 6 This is a structural block diagram of a monitoring device for production line equipment provided in an embodiment of the present application. The device 600 includes: an equipment screening module 601, a data configuration module 602, a data acquisition module 603, and a model diagnosis module 604, wherein:

[0100] The equipment screening module 601 is used to screen target production line equipment from all production line equipment based on the working status, key equipment parameters and working environment conditions of each production line equipment in the actual production line;

[0101] Data configuration module 602, used to configure the data type required to be collected by the target production line equipment, and set the transmission protocol, parsing method and collection cycle required for the collected data;

[0102] The data collection module 603 is used to collect historical operating data, historical fault data, environmental parameters, and process parameters of the target production line equipment from the configured data source based on the transmission protocol, parsing method, and collection cycle;

[0103] The model diagnosis module 604 is used to train a fault diagnosis model based on the collected data, and perform fault diagnosis on the target production line equipment through the fault diagnosis model.

[0104] The monitoring device for production line equipment provided in this embodiment determines the target production line equipment from the various production line equipment of the physical production line, configures the data type required to be collected by the target production line equipment, and configures the transmission protocol, parsing method and collection period related to data collection. Data collection is performed based on the configured transmission protocol, parsing method and collection period, and a fault diagnosis model is obtained through training with the collected data. The target production line equipment is then diagnosed for faults using the fault diagnosis model. Compared with the traditional technology of monitoring the status of production line equipment through personnel inspections, which results in low timeliness and accuracy, the present application determines the target production line equipment from the various production line equipment of the physical production line, which is more targeted, and performs fault diagnosis on the target production line equipment through data collection and fault diagnosis models, thereby improving the timeliness and accuracy of monitoring the target production line equipment.

[0105] Optionally, the collected data is collected in groups, and the model diagnosis module 604 includes:

[0106] Data processing unit, used to perform attribute transformation, working condition identification, missing value processing, indicator filtering, correlation detection, outlier detection, data grafting identification and data normalization on the collected data;

[0107] The model training unit is used to train the initial fault diagnosis model based on each group of processed data and the corresponding fault mode label to obtain a fault diagnosis model.

[0108] Optionally, the device 600 further includes:

[0109] The parameter collection module is used to collect historical power parameters of target production line equipment from the configuration data source based on the transmission protocol, parsing method and collection cycle;

[0110] The life prediction module is used to extract sample voltage ripples from the historical parameters of the power supply and predict the remaining life of the power supply of the target production line equipment based on the sample voltage ripples.

[0111] Optionally, the power supply historical parameters include historical voltage signals collected at different historical periods, and the life prediction module includes:

[0112] The voltage calculation subunit is used to calculate the voltage average value of the historical voltage signal, subtract the historical voltage signal from the voltage average value, and obtain the sample voltage ripple in the corresponding historical period.

[0113] Optionally, the lifespan prediction module also includes:

[0114] A voltage conversion subunit, configured to perform Fourier transform on the sample voltage ripple to obtain a plurality of sub-sample voltage ripples, and a ripple frequency and voltage amplitude corresponding to each sub-sample voltage ripple;

[0115] a ripple frequency determination subunit, configured to obtain the inherent ripple frequency of the power supply output voltage and the voltage amplitude threshold, and determine the ripple frequency of the multiple subsample voltage ripples whose voltage amplitude is greater than the voltage amplitude threshold as the ripple frequency set;

[0116] a ripple frequency classification subunit, configured to determine a ripple frequency value range based on the inherent ripple frequency and the frequency classification error radius, classify the ripple frequencies in the ripple frequency set that are within the ripple frequency value range into the inherent ripple frequency category, and classify the remaining ripple frequencies in the ripple frequency set into the degraded ripple frequency category;

[0117] a function determination subunit, configured to determine a first functional relationship of a voltage amplitude varying with time based on the voltage amplitude corresponding to each ripple frequency belonging to the inherent ripple frequency category, and to determine a second functional relationship of a voltage amplitude varying with time based on the voltage amplitude corresponding to each ripple frequency belonging to the degraded ripple frequency category;

[0118] a fault value determination subunit, configured to determine a maximum voltage amplitude from the voltage amplitudes corresponding to the ripple frequencies belonging to the inherent ripple frequency category as a first fault value, and to determine a maximum voltage amplitude from the voltage amplitudes corresponding to the ripple frequencies belonging to the degraded ripple frequency category as a second fault value;

[0119] The life determination subunit is used to predict the first required time when the voltage amplitude of the current voltage ripple reaches the first fault value based on the first functional relationship, and predict the second required time when the voltage amplitude of the current voltage ripple reaches the second fault value based on the second functional relationship, compare the first required time with the second required time, and select the smaller value as the remaining life of the power supply.

[0120] Optionally, the device 600 further includes:

[0121] The monitoring parameter acquisition module is used to collect monitoring parameters of the actual production line based on the transmission protocol, analysis method and acquisition cycle. The monitoring parameters include the production line operating power and the motor temperature of at least one line;

[0122] The health calculation module is used to calculate the temperature health of each motor based on the temperature of each motor and the power health based on the operating power of the production line;

[0123] The health assessment module is used to integrate the power health and the temperature health of each channel to obtain the overall health, which is used as the health assessment result of the physical production line.

[0124] Each module in the aforementioned production line equipment monitoring device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0125] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, memory, communication interface, display screen and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a monitoring method for production line equipment is implemented. The display screen of the computer device can be a liquid crystal display or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0126] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0127] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the production line equipment monitoring method provided in the above embodiment are implemented:

[0128] Filter out target production line equipment from all production line equipment based on the operating status, key equipment parameters, and working environment conditions of each production line equipment in the actual production line;

[0129] Configure the data type that the target production line equipment needs to collect, and set the transmission protocol, parsing method, and collection cycle required for the collected data;

[0130] Based on the transmission protocol, parsing method and collection cycle, the historical operation data, historical fault data, environmental parameters and process parameters of the target production line equipment are collected from the configured data source;

[0131] Based on the collected data, a fault diagnosis model is trained and used to diagnose faults of the target production line equipment.

[0132] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0133] Perform attribute transformation, working condition identification, missing value processing, indicator filtering, correlation detection, outlier detection, data grafting identification and data normalization on the collected data;

[0134] Based on each set of processed data and the corresponding fault mode labels, the initial fault diagnosis model is trained to obtain a fault diagnosis model.

[0135] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0136] Collect historical power parameters of target production line equipment from the configured data source based on the transmission protocol, parsing method, and collection cycle;

[0137] Extract sample voltage ripple from historical power supply parameters and predict the remaining life of the power supply of the target production line equipment based on the sample voltage ripple.

[0138] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0139] The voltage average value of the historical voltage signal is calculated, and the historical voltage signal is subtracted from the voltage average value to obtain the sample voltage ripple in the corresponding historical period.

[0140] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0141] Performing Fourier transform on the sample voltage ripple to obtain a plurality of sub-sample voltage ripples and a ripple frequency and a voltage amplitude corresponding to each sub-sample voltage ripple;

[0142] Obtaining the inherent ripple frequency and voltage amplitude threshold of the power supply output voltage, and determining the ripple frequency of the plurality of sub-sample voltage ripples whose voltage amplitude is greater than the voltage amplitude threshold as the ripple frequency set;

[0143] Based on the inherent ripple frequency and the frequency classification error radius, the ripple frequency value range is determined, the ripple frequencies in the ripple frequency set that are within the ripple frequency value range are classified as the inherent ripple frequency category, and the remaining ripple frequencies in the ripple frequency set are classified as the degraded ripple frequency category;

[0144] Determine a first functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the inherent ripple frequency category, and determine a second functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the degenerate ripple frequency category;

[0145] Determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the inherent ripple frequency category as a first fault value, and determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the degraded ripple frequency category as a second fault value;

[0146] Based on the first functional relationship, predict the first required time for the voltage amplitude of the current voltage ripple to reach the first fault value. Based on the second functional relationship, predict the second required time for the voltage amplitude of the current voltage ripple to reach the second fault value. Compare the first required time with the second required time, and select the smaller value as the remaining life of the power supply.

[0147] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0148] Based on the transmission protocol, analysis method, and collection cycle, the monitoring parameters of the actual production line are collected. The monitoring parameters include the production line operating power and the temperature of at least one motor.

[0149] Calculate the temperature health of each line based on the motor temperature of each line, and calculate the power health based on the production line operating power;

[0150] Integrate the power health with the temperature health of each channel to obtain the overall health, which is used as the health assessment result of the physical production line.

[0151] The implementation principle and technical effects of the above embodiment are similar to those of the above method embodiment and will not be repeated here.

[0152] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the production line equipment monitoring method provided in the above embodiment are implemented:

[0153] Filter out target production line equipment from all production line equipment based on the operating status, key equipment parameters, and working environment conditions of each production line equipment in the actual production line;

[0154] Configure the data type that the target production line equipment needs to collect, and set the transmission protocol, parsing method, and collection cycle required for the collected data;

[0155] Based on the transmission protocol, parsing method and collection cycle, the historical operation data, historical fault data, environmental parameters and process parameters of the target production line equipment are collected from the configured data source;

[0156] Based on the collected data, a fault diagnosis model is trained and used to diagnose faults of the target production line equipment.

[0157] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0158] Perform attribute transformation, working condition identification, missing value processing, indicator filtering, correlation detection, outlier detection, data grafting identification and data normalization on the collected data;

[0159] Based on each set of processed data and the corresponding fault mode labels, the initial fault diagnosis model is trained to obtain a fault diagnosis model.

[0160] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0161] Collect historical power parameters of target production line equipment from the configured data source based on the transmission protocol, parsing method, and collection cycle;

[0162] Extract sample voltage ripple from historical power supply parameters and predict the remaining life of the power supply of the target production line equipment based on the sample voltage ripple.

[0163] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0164] The voltage average value of the historical voltage signal is calculated, and the historical voltage signal is subtracted from the voltage average value to obtain the sample voltage ripple in the corresponding historical period.

[0165] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0166] Performing Fourier transform on the sample voltage ripple to obtain a plurality of sub-sample voltage ripples and a ripple frequency and a voltage amplitude corresponding to each sub-sample voltage ripple;

[0167] Obtaining the inherent ripple frequency and voltage amplitude threshold of the power supply output voltage, and determining the ripple frequency of the plurality of sub-sample voltage ripples whose voltage amplitude is greater than the voltage amplitude threshold as the ripple frequency set;

[0168] Based on the inherent ripple frequency and the frequency classification error radius, the ripple frequency value range is determined, the ripple frequencies in the ripple frequency set that are within the ripple frequency value range are classified as the inherent ripple frequency category, and the remaining ripple frequencies in the ripple frequency set are classified as the degraded ripple frequency category;

[0169] Determine a first functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the inherent ripple frequency category, and determine a second functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the degenerate ripple frequency category;

[0170] Determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the inherent ripple frequency category as a first fault value, and determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the degraded ripple frequency category as a second fault value;

[0171] Based on the first functional relationship, predict the first required time for the voltage amplitude of the current voltage ripple to reach the first fault value. Based on the second functional relationship, predict the second required time for the voltage amplitude of the current voltage ripple to reach the second fault value. Compare the first required time with the second required time, and select the smaller value as the remaining life of the power supply.

[0172] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0173] Based on the transmission protocol, analysis method, and collection cycle, the monitoring parameters of the actual production line are collected. The monitoring parameters include the production line operating power and the temperature of at least one motor.

[0174] Calculate the temperature health of each line based on the motor temperature of each line, and calculate the power health based on the production line operating power;

[0175] Integrate the power health with the temperature health of each channel to obtain the overall health, which is used as the health assessment result of the physical production line.

[0176] The implementation principle and technical effects of the above embodiment are similar to those of the above method embodiment and will not be repeated here.

[0177] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps of the production line equipment monitoring method provided in the above embodiment are implemented:

[0178] Filter out target production line equipment from all production line equipment based on the operating status, key equipment parameters, and working environment conditions of each production line equipment in the actual production line;

[0179] Configure the data type that the target production line equipment needs to collect, and set the transmission protocol, parsing method, and collection cycle required for the collected data;

[0180] Based on the transmission protocol, parsing method and collection cycle, the historical operation data, historical fault data, environmental parameters and process parameters of the target production line equipment are collected from the configured data source;

[0181] Based on the collected data, a fault diagnosis model is trained and used to diagnose faults of the target production line equipment.

[0182] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0183] Perform attribute transformation, working condition identification, missing value processing, indicator filtering, correlation detection, outlier detection, data grafting identification and data normalization on the collected data;

[0184] Based on each set of processed data and the corresponding fault mode labels, the initial fault diagnosis model is trained to obtain a fault diagnosis model.

[0185] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0186] Collect historical power parameters of target production line equipment from the configured data source based on the transmission protocol, parsing method, and collection cycle;

[0187] Extract sample voltage ripple from historical power supply parameters and predict the remaining life of the power supply of the target production line equipment based on the sample voltage ripple.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0189] The voltage average value of the historical voltage signal is calculated, and the historical voltage signal is subtracted from the voltage average value to obtain the sample voltage ripple in the corresponding historical period.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0191] Performing Fourier transform on the sample voltage ripple to obtain a plurality of sub-sample voltage ripples and a ripple frequency and a voltage amplitude corresponding to each sub-sample voltage ripple;

[0192] Obtaining the inherent ripple frequency and voltage amplitude threshold of the power supply output voltage, and determining the ripple frequency of the plurality of sub-sample voltage ripples whose voltage amplitude is greater than the voltage amplitude threshold as the ripple frequency set;

[0193] Based on the inherent ripple frequency and the frequency classification error radius, the ripple frequency value range is determined, the ripple frequencies in the ripple frequency set that are within the ripple frequency value range are classified as the inherent ripple frequency category, and the remaining ripple frequencies in the ripple frequency set are classified as the degraded ripple frequency category;

[0194] Determine a first functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the inherent ripple frequency category, and determine a second functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the degenerate ripple frequency category;

[0195] Determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the inherent ripple frequency category as a first fault value, and determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the degraded ripple frequency category as a second fault value;

[0196] Based on the first functional relationship, predict the first required time for the voltage amplitude of the current voltage ripple to reach the first fault value. Based on the second functional relationship, predict the second required time for the voltage amplitude of the current voltage ripple to reach the second fault value. Compare the first required time with the second required time, and select the smaller value as the remaining life of the power supply.

[0197] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0198] Based on the transmission protocol, analysis method, and collection cycle, the monitoring parameters of the actual production line are collected. The monitoring parameters include the production line operating power and the temperature of at least one motor.

[0199] Calculate the temperature health of each line based on the motor temperature of each line, and calculate the power health based on the production line operating power;

[0200] Integrate the power health with the temperature health of each channel to obtain the overall health, which is used as the health assessment result of the physical production line.

[0201] The implementation principle and technical effects of the above embodiment are similar to those of the above method embodiment and will not be repeated here.

[0202] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0203] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0204] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A monitoring method for production line equipment, characterized in that: The method comprises: Filter out target production line equipment from all production line equipment based on the operating status, key equipment parameters, and working environment conditions of each production line equipment in the actual production line; Configure the data type that the target production line equipment needs to collect, and set the transmission protocol, parsing method and collection cycle required for the collected data; Based on the transmission protocol, the parsing method and the collection period, collect historical operation data, historical fault data, environmental parameters and process parameters of the target production line equipment from the configuration data source; Based on the collected data, a fault diagnosis model is trained to diagnose the fault of the target production line equipment using the fault diagnosis model; Based on the transmission protocol, the parsing method and the collection period, collecting historical power supply parameters of the target production line equipment from a configuration data source; Extracting sample voltage ripples from the power supply historical parameters, and predicting the remaining life of the power supply of the target production line equipment based on the sample voltage ripples; The predicting of the remaining life of the power supply of the target production line equipment based on the sample voltage ripple includes: Performing Fourier transform on the sample voltage ripple to obtain a plurality of sub-sample voltage ripples, and a ripple frequency and a voltage amplitude corresponding to each sub-sample voltage ripple; Obtaining an inherent ripple frequency and a voltage amplitude threshold of the power supply output voltage, and determining a ripple frequency having a voltage amplitude greater than the voltage amplitude threshold among the plurality of sub-sample voltage ripples as a ripple frequency set; determining a ripple frequency value range based on the inherent ripple frequency and the frequency classification error radius, classifying ripple frequencies in the ripple frequency set that are within the ripple frequency value range as inherent ripple frequency categories, and classifying the remaining ripple frequencies in the ripple frequency set as degenerate ripple frequency categories; Determine a first functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the inherent ripple frequency category, and determine a second functional relationship of the voltage amplitude over time based on the voltage amplitude corresponding to each ripple frequency belonging to the degenerate ripple frequency category; Determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the inherent ripple frequency category as a first fault value, and determining a maximum voltage amplitude from voltage amplitudes corresponding to ripple frequencies belonging to the degraded ripple frequency category as a second fault value; Based on the first functional relationship, predict the first required time for the voltage amplitude of the current voltage ripple to reach the first fault value. Based on the second functional relationship, predict the second required time for the voltage amplitude of the current voltage ripple to reach the second fault value. Compare the first required time with the second required time, and select the smaller value as the remaining life of the power supply.

2. The method according to claim 1, characterized in that The collected data is collected in groups; the fault diagnosis model is trained based on the collected data, including: Perform attribute transformation, working condition identification, missing value processing, indicator filtering, correlation detection, outlier detection, data grafting identification and data normalization on the collected data; Based on each set of processed data and the corresponding fault mode labels, the initial fault diagnosis model is trained to obtain a fault diagnosis model.

3. The method according to claim 1, characterized in that The power supply historical parameters include historical voltage signals collected in different historical time periods; and extracting the sample voltage ripple from the power supply historical parameters includes: The voltage average value of the historical voltage signal is calculated, and the voltage average value is subtracted from the historical voltage signal to obtain a sample voltage ripple in a corresponding historical period.

4. The method according to claim 1, wherein The method further comprises: Based on the transmission protocol, the parsing method, and the collection period, monitoring parameters of the physical production line are collected, wherein the monitoring parameters include the operating power of the production line and the temperature of at least one motor; Based on the motor temperature of each line, the temperature health of each line is calculated, and based on the operating power of the production line, the power health is calculated; The power health is integrated with the temperature health of each line to obtain the total health, which is used as the health assessment result of the physical production line.

5. A monitoring device for production line equipment, characterized in that: For performing the method according to any one of claims 1 to 4, the apparatus comprises: The equipment screening module is used to screen target production line equipment from all production line equipment based on the operating status, key equipment parameters and working environment conditions of each production line equipment in the actual production line; A data configuration module is used to configure the data type required to be collected by the target production line equipment, and set the transmission protocol, parsing method and collection cycle required for the collected data; A data acquisition module, configured to collect historical operating data, historical fault data, environmental parameters, and process parameters of the target production line equipment from a configured data source based on the transmission protocol, the parsing method, and the acquisition cycle; The model diagnosis module is used to train a fault diagnosis model based on the collected data, and perform fault diagnosis on the target production line equipment through the fault diagnosis model.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images