Component early warning method and device for automated production line, electronic equipment, storage medium and program product

Abstract

Embodiments of the present application provide a component early warning method and device for an automated production line, electronic equipment, storage medium and program product. The method comprises: obtaining equipment action data of the automated production line; calculating execution times of a plurality of actions according to time stamps of the equipment action data of the automated production line; comparing the execution times of the plurality of actions with a standard beat range in a product processing model to obtain action state information; determining whether a component of the automated production line is abnormal according to the action state information; if the component of the automated production line is in an abnormal state, generating early warning information according to the action state information; collecting equipment action data in real time, calculating action execution times and comparing the action execution times with the standard beat range in the product processing model, then determining whether the component is abnormal and triggering early warning when the component is abnormal, discovering beat deviation caused by component wear, jamming or control abnormality in a timely manner, avoiding production line downtime caused by sudden failure, and improving the accuracy of component early warning.

Description

Technical Field

[0001] This application relates to the field of automation technology, and in particular to a component early warning method, device, electronic equipment, storage medium and program product for automated production lines. Background Technology

[0002] In the context of manufacturing digitalization, the level of automation of production lines is constantly improving. During the operation of automated production lines, multiple devices work together. Over long-term operation, abnormal problems of parts are prone to occur. The condition of the parts in automated production lines is the key to the reliable operation of automated production lines.

[0003] In existing technologies, component inspection methods in automated production lines mainly include fixed threshold alarms and human experience-based judgment.

[0004] However, existing methods rely on human experience, and fixed threshold detection and alarm methods are difficult to adapt to changes caused by equipment wear or process adjustments, resulting in inaccurate warnings for abnormal components. Summary of the Invention

[0005] This application provides a component early warning method, device, electronic device, storage medium, and program product for automated production lines, in order to solve the problem of inaccurate early warning of abnormal components in the prior art.

[0006] In a first aspect, embodiments of this application provide a component early warning method for automated production lines, including:

[0007] Acquire equipment movement data from automated production lines;

[0008] The execution time of multiple actions is calculated based on the timestamps of the equipment action data of the automated production line;

[0009] The execution time of the multiple actions is compared with the standard cycle time range in the product processing model to obtain action status information;

[0010] Determine whether the components of the automated production line are abnormal based on the aforementioned action status information;

[0011] If a component of the automated production line is in an abnormal state, an early warning message is generated based on the action status information.

[0012] In one possible implementation, if a component of the automated production line is in an abnormal state, generating an early warning message based on the action status information includes: jointly analyzing the equipment status parameters and action time data in the action status information to generate parsed data; performing fault mode identification on the action time data based on the parsed data to generate a fault identification result; determining the fault level based on the fault identification result, and generating a corresponding early warning message based on the fault level.

[0013] In one possible implementation, determining whether a component of the automated production line is abnormal based on the action status information includes: determining the deviation values ​​between the execution time of multiple actions and the corresponding standard cycle range in the product processing model based on the action status information; mapping the deviation values ​​of multiple actions to corresponding components based on a preset association relationship between components and actions, and calculating the cumulative deviation of multiple components; comparing the cumulative deviation of the multiple components with a component abnormality threshold to determine whether a component of the automated production line is abnormal.

[0014] In one possible implementation, before acquiring the equipment motion data of the automated production line, the method further includes: acquiring equipment model information of the automated production line; acquiring corresponding production process flow information based on the equipment model information; extracting the motion cycle time from the process flow information to obtain the standard motion cycle time of multiple components; acquiring historical process data of multiple components based on the equipment model information; and creating a product processing model based on the standard motion cycle time of the multiple components and the historical process data of the multiple components.

[0015] In one possible implementation, creating a product processing model based on the standard cycle time of the plurality of components and the historical process data of the plurality of components includes: filtering out abnormal data points in the historical process data of the plurality of components to obtain filtered historical data; calculating the mean and standard deviation of the filtered historical data, and fitting a time distribution curve based on the mean and standard deviation of the filtered historical data; determining the model parameters of the product processing model based on the time distribution curve and the standard cycle time of the plurality of components, and creating the product processing model based on the model parameters.

[0016] In one possible implementation, after generating early warning information based on the action status information if a component of the automated production line is in an abnormal state, the method further includes: performing cluster analysis on the abnormal component based on the early warning information to generate cluster parsing data of the abnormal component; generating a repair strategy for the abnormal component based on the cluster parsing data of the abnormal component; collecting equipment data after executing the repair strategy of the abnormal component in response to the operation of executing the repair strategy of the abnormal component; and determining the product processing model parameters to be adjusted if the equipment data after executing the repair strategy of the abnormal component does not exceed a preset fault threshold.

[0017] Secondly, embodiments of this application provide a component early warning device for an automated production line, comprising:

[0018] The data acquisition module is used to acquire equipment movement data from automated production lines;

[0019] The action time calculation module is used to calculate the execution time of multiple actions based on the timestamps of the equipment action data of the automated production line.

[0020] The beat comparison module is used to compare the execution time of the multiple actions with the standard beat range in the product processing model to obtain action status information;

[0021] The judgment module is used to determine whether a component of the automated production line is abnormal based on the action status information.

[0022] The early warning feedback module is used to generate early warning information based on the action status information if a component of the automated production line is in an abnormal state.

[0023] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0024] The memory stores computer-executed instructions;

[0025] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0026] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0027] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0028] The component early warning method, device, electronic equipment, storage medium, and program product for automated production lines provided in this application collect equipment action data in real time, calculate the action execution time, compare it with the standard cycle time range in the product processing model, generate action status information, and then determine whether the component is abnormal and trigger an early warning when abnormal. This achieves real-time, quantitative monitoring and proactive early warning of abnormalities in the production line operation status, timely detection of cycle time deviations caused by component wear, jamming, or control abnormalities, avoids production line downtime caused by sudden failures, and improves the accuracy of component early warning. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0030] Figure 1This is a schematic diagram of the system structure of a computer device provided in an embodiment of this application;

[0031] Figure 2 A flowchart illustrating the component early warning method for automated production lines provided in this application;

[0032] Figure 3 A flowchart illustrating the creation of the product processing model provided for this application;

[0033] Figure 4 A flowchart illustrating the implementation of the repair strategy provided in this application;

[0034] Figure 5 A schematic diagram of the component early warning device for the automated production line provided in this application;

[0035] Figure 6 A schematic diagram of the structure of the electronic device provided in this application.

[0036] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0037] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application.

[0038] In the context of manufacturing digitalization, production line automation is constantly increasing. Automated production lines involve multiple machines working collaboratively, and these machines are prone to component malfunctions during long-term operation. The condition of these components is crucial to the reliable operation of automated production lines. Current technologies for component detection in automated production lines mainly include fixed threshold alarms and human experience-based judgment. However, existing methods rely on human experience, and fixed threshold alarm methods are difficult to adapt to changes caused by equipment wear or process adjustments, leading to inaccurate warnings for abnormal components.

[0039] To address the aforementioned technical problems, this application proposes the following technical concept: The inventors considered constructing a product processing model, acquiring the motion data of the production line equipment, comparing the motion data with the standard cycle range in the product processing model, and determining whether a component is abnormal based on the compared motion status information, thereby avoiding production line downtime caused by sudden failures and improving the accuracy of component early warning.

[0040] Figure 1 This is a schematic diagram illustrating an application scenario of the component early warning method for automated production lines provided in this application embodiment. For example... Figure 1 As shown, this application scenario includes a system 101 and an automated production line 102 that apply a component early warning method to an automated production line.

[0041] Specifically, the system 101, which applies the component early warning method for automated production lines, acquires the equipment action data of automated production lines 102, calculates the execution time of multiple actions based on the timestamps of the equipment action data, compares the execution time of multiple actions with the standard cycle time range in the product processing model to obtain action status information, and determines whether the components of automated production lines 102 are abnormal based on the action status information. If they are abnormal, an early warning message is generated based on the action status information.

[0042] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the component early warning method for automated production lines. In other feasible embodiments of this application, the above architecture may include more or fewer components than illustrated, or combine some components, or split some components, or arrange different components, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of both.

[0043] Figure 2 A flowchart illustrating the component early warning method for automated production lines provided in this application is shown below. Figure 2 As shown, the method includes:

[0044] S201: Obtain equipment motion data from automated production lines.

[0045] Specifically, programmable logic controllers, industrial IoT sensors, and machine vision systems deployed on automated production lines are used to collect real-time data on equipment motion events.

[0046] In this embodiment, each action event is recorded as a piece of structured data, including device ID, action name, action start timestamp, action end timestamp, and key state parameters during the action execution process.

[0047] S202: Calculate the execution time of multiple actions based on the timestamps of the equipment action data of the automated production line.

[0048] Specifically, for the acquired action data, the difference between its end timestamp and start timestamp is calculated to obtain the single execution time of the action.

[0049] Specifically, for continuous actions, the time taken per unit stroke is calculated, and information such as the specific workstation where the action occurs and the batch number of the parts is recorded. The execution time is then added as an indicator to the raw data.

[0050] S203: Compare the execution time of multiple actions with the standard cycle time range in the product processing model to obtain action status information.

[0051] Specifically, for each action, the standard cycle time range of the corresponding component type in the generated product processing model is queried, the actual execution time is compared with the standard range, the deviation value is recorded, and the action status information is obtained.

[0052] In this embodiment, the action status information includes, but is not limited to, action ID, status label, deviation value, and timestamp.

[0053] S204: Determine whether the components of the automated production line are abnormal based on the action status information.

[0054] Specifically, based on the action status information, the execution time of multiple actions and the deviation value of the corresponding standard cycle range in the product processing model are determined. According to the preset association between components and actions, the deviation values ​​of multiple actions are mapped to the corresponding components. The cumulative deviation of multiple components is calculated. The cumulative deviation of multiple components is compared with the component abnormality threshold to determine whether the components of the automated production line are abnormal.

[0055] S205: If a component in an automated production line is in an abnormal state, an early warning message will be generated based on the action status information.

[0056] Specifically, the system performs joint analysis of equipment status parameters and action time data, identifies fault modes based on the analyzed data, determines the fault level based on the fault identification results, and generates corresponding early warning information.

[0057] As can be seen from the above embodiments, by collecting equipment action data in real time, calculating the action execution time and comparing it with the standard cycle time range in the product processing model, action status information is generated, thereby determining whether the component is abnormal and triggering an early warning when abnormal. This achieves real-time, quantitative monitoring and proactive early warning of abnormalities in the production line operation status, timely detection of cycle time deviations caused by component wear, jamming, or control abnormalities, avoids production line shutdowns caused by sudden failures, and improves the accuracy of component early warning.

[0058] In one embodiment of this application, step S205 includes:

[0059] S2051: Perform joint analysis on the device status parameters and action time data in the action status information to generate analytical data.

[0060] Specifically, when a component is determined to be abnormal, the system retrieves detailed action status information of that component before and after the abnormal time period.

[0061] In this embodiment, the action status information includes, but is not limited to, the time series data of each associated action and the device status parameters collected at the same time.

[0062] Specifically, through time alignment and correlation analysis, analytical data is generated to associate the times when execution time exceeds the limit with the times when pressure decreases.

[0063] S2052: Based on the parsed data, perform fault mode identification on the action time data and generate fault identification results.

[0064] Specifically, the parsed data is input into the fault mode recognition engine, and fault recognition results are generated through feature matching.

[0065] S2053: Determine the fault level based on the fault identification results, and generate corresponding early warning information based on the fault level.

[0066] Specifically, based on the impact of fault identification results on production, fault levels are preset, and the identified fault modes are mapped to the corresponding fault levels to generate structured early warning information.

[0067] In this embodiment, the warning information includes, but is not limited to, abnormal component ID, fault mode description, fault level, occurrence time, cumulative deviation value, and suggested preliminary troubleshooting measures.

[0068] As can be seen from the above embodiments, by jointly analyzing equipment status parameters and action time data and identifying fault modes, the fault level is determined and corresponding early warning information is generated. This enables different levels of response strategies to be matched with faults of different severity, improves the pertinence and operability of early warning information, facilitates maintenance personnel to quickly locate problems and take corresponding measures, and shortens fault response and handling time.

[0069] In one embodiment of this application, step S204 includes:

[0070] S2041: Determine the deviation between the execution time of multiple actions and the corresponding standard cycle range in the product processing model based on the action status information.

[0071] Specifically, the deviation value of each action is extracted from the generated action state information, and all the deviation values ​​of the actions are organized into a list and mapped.

[0072] In this embodiment, a positive deviation value indicates a delay, and a negative value indicates an advance.

[0073] S2042: Based on the preset association between components and actions, map the deviation values ​​of multiple actions to the corresponding components, and calculate the cumulative deviation of multiple components.

[0074] Specifically, the deviation value of each action is accumulated to the associated component through the correlation matrix to obtain the cumulative deviation of each component.

[0075] In this embodiment, the association matrix records the set of actions that each component participates in executing.

[0076] In this embodiment, the cumulative deviation represents the degree to which the component as a whole deviates from the standard beat.

[0077] S2043: Compare the cumulative deviation of multiple components with the component abnormality threshold to determine whether the components of the automated production line are abnormal.

[0078] Specifically, an abnormal threshold is preset for each component. The calculated cumulative deviation of the component is compared with the threshold. If the absolute value of the cumulative deviation of the component exceeds the threshold, the component is determined to be in an abnormal state, and the component ID, cumulative deviation value and time window exceeding the threshold are recorded.

[0079] As can be seen from the above embodiments, by calculating the deviation value between the execution time of each action and the standard beat, and mapping the deviation to the corresponding component according to the preset component action association relationship, calculating the cumulative deviation and comparing it with the threshold, the comprehensive evaluation of multiple actions and the accurate identification of component anomalies are realized, avoiding misjudgment caused by fluctuations in a single action, and improving the accuracy and robustness of anomaly diagnosis.

[0080] Figure 3 The flowchart for creating the product processing model provided in this application is as follows: Figure 3 As shown, before step S201, the following steps are also included:

[0081] S301: Obtain equipment model information for automated production lines.

[0082] In this embodiment, the device model information includes, but is not limited to, the device model, serial number, and manufacturing date.

[0083] S302: Obtain the corresponding production process information based on the equipment model information.

[0084] Specifically, using the equipment model as an index, a detailed description of the production process steps involved by the equipment is retrieved from the process knowledge base.

[0085] In this embodiment, the process flow information is stored in the form of a flowchart, which includes the operation sequence of each station, the logical relationship between each operation, and the theoretical action order and parallel constraints.

[0086] Specifically, the system analyzes the process flow information and extracts the expected time window for each action under the standard production cycle time.

[0087] S303: Extract the motion cycle time from the process flow information to obtain the standard motion cycle time of multiple parts.

[0088] Specifically, for each type of part being processed, the process flow information is used to decompose the standard sequence of actions required to be performed at each workstation. For each action, the theoretical execution time is determined based on the process design document.

[0089] Specifically, the theoretical times are summarized to obtain the standard action rhythm time of the component.

[0090] In this embodiment, the standard action beat schedule includes, but is not limited to, action name, standard duration, and allowed fluctuation range.

[0091] S304: Obtain historical process data for multiple components based on equipment model information.

[0092] Specifically, retrieve historical process data recorded when the same type of equipment processed the same parts within a historical period from the production line history database.

[0093] In this embodiment, historical process data includes the actual execution time of each action, equipment status parameters, and a tag indicating whether a fault has occurred.

[0094] S305: Create a product processing model based on the standard cycle time of multiple components and the historical process data of multiple components.

[0095] Specifically, outlier data points are filtered from the historical process data of multiple components. The mean and standard deviation of the filtered historical data are calculated, and a time distribution curve is fitted based on the mean and standard deviation of the filtered historical data. The model parameters of the product processing model are determined based on the time distribution curve and the standard action cycle time of multiple components, and the product processing model is created based on the model parameters.

[0096] As can be seen from the above embodiments, by obtaining the process flow information corresponding to the equipment model, extracting the standard action cycle time, and combining it with historical process data to build a model, the personalized and data-driven construction of the product processing model is realized, making the standard cycle range more in line with the actual production situation and improving the accuracy and adaptability of the comparison benchmark.

[0097] In one embodiment of this application, step S305 includes:

[0098] S3051: Filter out abnormal data points in the historical process data of multiple components to obtain the filtered historical data.

[0099] Specifically, the acquired historical process data is cleaned to remove extreme outliers caused by obvious equipment failures, sensor false alarms, or human intervention. The box plot method is used to identify and delete data points whose execution time exceeds the normal fluctuation range, resulting in filtered historical data that reflects the cycle time distribution under normal operating conditions.

[0100] S3052: Calculate the mean and standard deviation of the filtered historical data, and fit a time distribution curve based on the mean and standard deviation of the filtered historical data.

[0101] Specifically, for each action, the arithmetic mean and standard deviation of the historical execution time data after filtering are calculated, and the time distribution curve of the action is fitted using the arithmetic mean and standard deviation.

[0102] S3053: Determine the model parameters of the product processing model based on the time distribution curve and the standard action cycle time of multiple parts, and create the product processing model based on the model parameters.

[0103] Specifically, the time distribution curve is fused with the extracted standard motion beat time to determine the final parameters of the product processing model.

[0104] For example, the standard cycle time is used as the theoretical expected value, the mean of the distribution curve is used as the actual expected value, and the normal fluctuation range of the action is determined. The standard cycle range, expected value, and dependencies between actions of each action of each component are stored in a structured form to form a queryable product processing model.

[0105] As can be seen from the above embodiments, by screening outliers in historical process data, calculating the mean and standard deviation and fitting the time distribution curve, and combining the standard cycle time to determine the model parameters, abnormal interference in historical data is eliminated, and key parameters reflecting the statistical characteristics of normal production cycle time are extracted, making the established model more robust and accurate in representing the normal operation status of the production line, and improving the rationality of the standard cycle time range.

[0106] Figure 4 A flowchart illustrating the implementation of the repair strategy provided in this application is shown below. Figure 4 As shown, after step S205, the following steps are also included:

[0107] S401: Based on the early warning information, perform cluster analysis on abnormal components and generate cluster analysis data for abnormal components.

[0108] Specifically, the early warning information generated within a set time period is clustered and analyzed according to dimensions such as component type, failure mode, and workstation where it occurs.

[0109] In this embodiment, the clustering analysis data of abnormal components includes, but is not limited to, a list of high-frequency faulty components, a distribution of fault modes, and potential systemic causes.

[0110] S402: Generate a repair strategy for abnormal components based on the clustering analysis data of abnormal components.

[0111] Specifically, appropriate repair strategies are matched from the maintenance knowledge base based on the clustering analysis data.

[0112] For example, if the high-frequency fault mode is "seal ring wear", the repair strategy is to "replace the seal ring kit and check the surface finish of the cylinder barrel inner wall".

[0113] In this embodiment, the repair strategy is output in the form of a standard operating procedure, and the recorded content includes, but is not limited to, the required tools, spare parts, steps, and safety precautions.

[0114] S403: In response to the operation of executing the repair strategy for the abnormal component, collect device data after executing the repair strategy for the abnormal component.

[0115] Specifically, once the maintenance personnel complete the repair operation and it is confirmed by the system, the system automatically resumes real-time monitoring of the component and collects equipment data for a set period after the repair.

[0116] In this embodiment, the device data after executing the repair strategy for the abnormal component includes, but is not limited to, action execution time and device status parameters.

[0117] S404: If the equipment data after implementing the repair strategy for abnormal components does not exceed the preset fault threshold, then determine the product processing model parameters to be adjusted.

[0118] Specifically, the repaired equipment data is compared with the standard cycle time range in the product processing model. If the execution time of the associated actions all fall back to the normal range and the cumulative deviation does not exceed the threshold, then the repair is considered effective.

[0119] Specifically, the system analyzes whether the repaired data has a systematic deviation from the original model parameters. If there is a difference, the newly collected stable cycle time data is used as feedback and marked as the product processing model parameters to be adjusted for model optimization.

[0120] As can be seen from the above embodiments, by performing cluster analysis on abnormal components to generate repair strategies, and collecting equipment data for verification after the repair is performed, if the fault is eliminated, the product processing model parameters are adjusted so that the product processing model can be dynamically optimized as the production line status changes and maintenance experience is accumulated, thereby improving the accuracy of fault prediction.

[0121] Figure 5A schematic diagram of the component early warning device for the automated production line provided in this application is shown below. Figure 5 As shown, the component early warning device 50 for automated production lines provided in this embodiment includes: a data acquisition module 501, an action time calculation module 502, a cycle comparison module 503, a judgment module 504, and an early warning feedback module 505.

[0122] The data acquisition module 501 is used to acquire equipment motion data of the automated production line.

[0123] The action time calculation module 502 is used to calculate the execution time of multiple actions based on the timestamps of the equipment action data of the automated production line.

[0124] The beat comparison module 503 is used to compare the execution time of multiple actions with the standard beat range in the product processing model to obtain action status information.

[0125] The judgment module 504 is used to determine whether the components of the automated production line are abnormal based on the action status information.

[0126] The early warning feedback module 505 is used to generate early warning information based on the action status information if a component of the automated production line is in an abnormal state.

[0127] In one embodiment of this application, the early warning feedback module 505 includes:

[0128] The joint analysis unit is used to perform joint analysis on the equipment status parameters and action time data in the action status information to generate analytical data.

[0129] The fault identification unit is used to identify fault modes in action time data based on the parsed data and generate fault identification results.

[0130] The first determining unit is used to determine the fault level based on the fault identification result and generate corresponding early warning information based on the fault level.

[0131] In one embodiment of this application, the determination module 504 includes:

[0132] The second determining unit is used to determine the deviation between the execution time of multiple actions and the corresponding standard cycle range in the product processing model based on the action status information.

[0133] The mapping unit is used to map the deviation values ​​of multiple actions to the corresponding parts according to the preset association relationship between parts and actions, and to calculate the cumulative deviation of multiple parts.

[0134] The comparison unit is used to compare the cumulative deviation of multiple components with the component abnormality threshold to determine whether the components of the automated production line are abnormal.

[0135] In one embodiment of this application, the component early warning device 50 for automated production lines further includes:

[0136] The first acquisition module is used to acquire equipment model information for automated production lines.

[0137] The second acquisition module is used to obtain the corresponding production process information based on the equipment model information.

[0138] The extraction module is used to extract the action cycle time from the process flow information to obtain the standard action cycle time of multiple parts.

[0139] The third acquisition module is used to acquire historical process data of multiple components based on equipment model information.

[0140] Create a module to create a product processing model based on the standard cycle time of multiple components and the historical process data of multiple components.

[0141] In one embodiment of this application, the creation module includes:

[0142] The filtering unit is used to filter out abnormal data points in the historical process data of multiple parts to obtain the filtered historical data.

[0143] The calculation unit is used to calculate the mean and standard deviation of the filtered historical data, and to fit a time distribution curve based on the mean and standard deviation of the filtered historical data.

[0144] The third determining unit is used to determine the model parameters of the product processing model based on the time distribution curve and the standard action cycle time of multiple parts, and to create the product processing model based on the model parameters.

[0145] In one embodiment of this application, the component early warning device 50 for automated production lines further includes:

[0146] The clustering analysis module is used to perform clustering analysis on abnormal components based on early warning information and generate clustering parsing data for abnormal components.

[0147] The generation module is used to generate repair strategies for abnormal components based on the clustering parsing data of abnormal components.

[0148] The data acquisition module is used to collect device data after the execution of the repair strategy for the abnormal component in response to the operation.

[0149] The determination module is used to determine the product processing model parameters to be adjusted if the equipment data after implementing the repair strategy for abnormal components does not exceed the preset fault threshold.

[0150] The component early warning device for automated production lines provided in this embodiment can execute the method provided in the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0151] Figure 6 A schematic diagram of the structure of the electronic device provided in this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the electronic device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus.

[0152] In the specific implementation process, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to execute the above-mentioned component early warning method for automated production lines.

[0153] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0154] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0155] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0156] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0157] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned component early warning method for automated production lines.

[0158] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned component early warning method for automated production lines.

[0159] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0160] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0161] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0162] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0163] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0164] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0165] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0166] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A component early warning method for an automated production line, characterized in that, include: Acquire equipment movement data from automated production lines; The execution time of multiple actions is calculated based on the timestamps of the equipment action data of the automated production line; The execution time of the multiple actions is compared with the standard cycle time range in the product processing model to obtain action status information; Based on the action status information, determine the deviation values ​​between the execution time of multiple actions and the corresponding standard cycle range in the product processing model; Based on the preset association between components and actions, the deviation values ​​of multiple actions are mapped to the corresponding components, and the cumulative deviation of multiple components is calculated. The cumulative deviation of the multiple components is compared with the component abnormality threshold to determine whether the components of the automated production line are abnormal. If a component of the automated production line is in an abnormal state, an early warning message is generated based on the action status information.

2. The method according to claim 1, characterized in that, If a component of the automated production line is in an abnormal state, an early warning message is generated based on the action status information, including: The device status parameters and action time data in the action status information are jointly analyzed to generate parsed data; Based on the parsed data, fault mode identification is performed on the action time data to generate fault identification results; The fault level is determined based on the fault identification results, and corresponding early warning information is generated based on the fault level.

3. The method according to claim 1, characterized in that, Before acquiring the equipment motion data of the automated production line, the process also includes: Obtain equipment model information for automated production lines; Obtain the corresponding production process information based on the equipment model information; The process flow information is used to extract the action cycle time to obtain the standard action cycle time of multiple components; Historical process data for multiple components are obtained based on the equipment model information; A product processing model is created based on the standard cycle time of the multiple components and the historical process data of the multiple components.

4. The method according to claim 3, characterized in that, The step of creating a product processing model based on the standard cycle time of the multiple components and the historical process data of the multiple components includes: Anomaly points are filtered out from the historical process data of multiple components to obtain the filtered historical data. Calculate the mean and standard deviation of the filtered historical data, and fit a time distribution curve based on the mean and standard deviation of the filtered historical data; The model parameters of the product processing model are determined based on the time distribution curve and the standard action cycle time of multiple components, and the product processing model is created based on the model parameters.

5. The method according to any one of claims 1 to 4, characterized in that, If a component of the automated production line is in an abnormal state, after generating a warning message based on the action status information, the method further includes: Based on the early warning information, cluster analysis is performed on the abnormal components to generate cluster analysis data of the abnormal components; A repair strategy for the abnormal components is generated based on the clustering analysis data of the abnormal components; In response to the operation of executing the repair strategy for the abnormal component, device data after executing the repair strategy for the abnormal component is collected; If the equipment data after implementing the repair strategy for the abnormal component does not exceed the preset fault threshold, then the product processing model parameters to be adjusted are determined.

6. A component early warning device for an automated production line, characterized in that, include: The data acquisition module is used to acquire equipment movement data from automated production lines; The action time calculation module is used to calculate the execution time of multiple actions based on the timestamps of the equipment action data of the automated production line. The beat comparison module is used to compare the execution time of the multiple actions with the standard beat range in the product processing model to obtain action status information; The judgment module is used to determine whether a component of the automated production line is abnormal based on the action status information. The early warning feedback module is used to generate early warning information based on the action status information if a component of the automated production line is in an abnormal state.

7. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the component early warning method for an automated production line as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the component early warning method for an automated production line as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the component early warning method for an automated production line as described in any one of claims 1 to 5.

Images