A rubber and plastic product production line monitoring method and system

Abstract

The application relates to the technical field of production line monitoring, and discloses a rubber and plastic product production line monitoring method and system. The method comprises the following steps: obtaining a production item set according to the production process of a production line, and extracting a production line segment corresponding to each item; for each production line segment, obtaining a calibration cycle and a process cycle of a production object, analyzing the two to determine a device performance index; if the index shows that the device is suspected to be abnormal, obtaining running data of the device within a first preset time, including state index data and event record data, judging whether the device is abnormal, if the device is abnormal, determining a first abnormal mode of the device, and calculating an abnormal time length; identifying an abnormal device, extracting production data, abnormal behavior data and time data of the abnormal device, sorting the abnormal device based on the data, and performing an abnormality elimination operation accordingly. The application improves the monitoring efficiency and abnormality processing capacity of the production line.

Description

Technical Field

[0001] This application relates to the field of production line monitoring technology, and in particular to a method and system for monitoring rubber and plastic product production lines. Background Technology

[0002] Rubber and plastic products (including rubber and plastic products) are widely used in modern industry, and their production involves multiple complex technological steps. In traditional rubber and plastic product manufacturing, production line monitoring mainly relies on manual operation and simple automated equipment. This method has many problems, such as low efficiency and the tendency to miss issues. Furthermore, simple equipment alarm systems only issue alerts when serious equipment malfunctions occur, failing to provide early warnings of potential anomalies. With the rapid development of IoT technology, applying it to rubber and plastic product production line monitoring allows for real-time collection of equipment operating data. Big data analytics and artificial intelligence algorithms can then be used to deeply mine this data, thereby achieving intelligent monitoring of the production line.

[0003] A similar prior art is Chinese patent application CN116088381A, which discloses a method for processing equipment alarm data, a controller, and a storage medium. The method acquires first and second station status data of the equipment, with the first station status data being the previous status data of the second station status data. If the first station status data is operational status information, the second station status data is a first alarm message, and the equipment is in a repaired operational state, then third station status data is acquired. If, based on a preset anomaly database, the third station status data is determined to be a second alarm message, an alarm data processing instruction is determined based on the first and second alarm messages. The anomaly database is a database generated based on the alarm tag information of the programmable logic controller. This method determines the alarm processing instruction by comparing previous and subsequent alarm messages, but it lacks in-depth analysis of equipment operation and cannot pinpoint the cause of the anomaly or achieve accurate and efficient recovery. Another Chinese patent application, CN118211943A, discloses a method and system for production management of injection molded products. This method acquires production data from multiple production lines for injection molding products. The production data includes environmental parameters, ventilation equipment status parameters, and production equipment parameters related to each production line. Based on the environmental parameters, it determines the environmental anomaly level for each production line; based on the ventilation equipment status parameters and environmental anomaly level, it determines the ventilation anomaly level for each production line; based on the production equipment parameters, it determines the equipment anomaly level for each production line; based on the environmental anomaly level, ventilation anomaly level, and equipment anomaly level, it determines a comprehensive anomaly score for each production line and locates the abnormal production line; based on the comprehensive anomaly score for each production line, it generates corresponding anomaly handling strategies for the abnormal production line. While this method locates abnormal production lines and generates handling strategies by monitoring environmental, ventilation, and equipment parameters, it lacks in-depth analysis of equipment operation and cannot pinpoint the cause of the anomaly or achieve accurate and efficient recovery.

[0004] Therefore, providing a monitoring method and system for rubber and plastic product production lines to improve monitoring efficiency and anomaly handling capabilities is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a method and system for monitoring rubber and plastic product production lines, which improves the monitoring efficiency and fault recovery efficiency of production lines through comprehensive monitoring, intelligent analysis and system processing.

[0006] In a first aspect, this application provides a method for monitoring a rubber and plastic product production line, the method comprising: Step 1: Based on the production process of the rubber and plastic product production line, obtain the production item set of the rubber and plastic product production line, and extract the production line segment corresponding to each production item based on the production item set. Step 2: For any production line segment, obtain the calibration cycle corresponding to the production object and the process cycle for processing the production object, and analyze the process cycle and calibration cycle to determine the performance indicators of the production equipment in any production line segment. When the performance indicators indicate that the production equipment has a suspected abnormality, proceed to Step 3. Step 3: Obtain the operating data of the production equipment within the first preset time period. Based on the operating data, determine whether there is an abnormality in the production equipment. If there is, determine the first abnormality mode of the production equipment and calculate the abnormality time length of the production equipment. Then proceed to Step 4. The operating data includes status indicator data and event record data. Step 4: Define any abnormal production equipment as abnormal equipment, identify all abnormal equipment on the rubber and plastic product production line, and extract the production data, abnormal behavior data, and time data of each abnormal equipment. Sort the abnormal equipment based on the production data, abnormal behavior data, and time data, and perform anomaly elimination operations on all abnormal equipment based on the sorting.

[0007] In conjunction with the first aspect, in the first implementation of the first aspect of this application, when the production object is a fluid product, the calibration cycle and the process cycle are respectively the cycle for the production object to reach a predetermined state, and step 2 includes: The first preset algorithm is executed on the process cycle and calibration cycle to obtain the cycle energy efficiency ratio; Obtain all calibration cycles and all process cycles corresponding to the production equipment within a second preset time period, and define them as calibration cycle sequence and process cycle sequence, respectively. Identify the number of data in the calibration cycle sequence, and compare the values ​​in the process cycle sequence with the corresponding values ​​in the calibration cycle sequence in turn. Identify the number of times the process cycle does not meet the calibration cycle, and define it as the first deviation number. Execute the second preset algorithm on the first deviation number and the number of data to obtain the deviation occurrence rate. The cycle energy efficiency ratio and deviation rate are compared with the corresponding thresholds, and performance indicators are obtained based on the comparison results.

[0008] In conjunction with the first aspect, in the second implementation of the first aspect of this application, when the production object is a discrete product, step 2 includes: Extract the total number of production objects processed by the production equipment within the third preset time period, and accumulate all process cycles to obtain the sum. Execute the third preset algorithm on the sum, total number, and calibration cycle to obtain the cycle energy efficiency ratio. The process cycle of each production object is compared with the calibration cycle. The number of times the process cycle does not meet the calibration cycle is identified and defined as the second deviation number. The fourth preset algorithm is then applied to the second deviation number and the total number to obtain the deviation occurrence rate. The cycle energy efficiency ratio and deviation rate are compared with the corresponding thresholds, and performance indicators are obtained based on the comparison results.

[0009] In conjunction with the first aspect, in the third implementation of the first aspect of this application, step 2 includes: Based on the product model, raw material information and process parameters of any production line segment of the rubber and plastic products, the adjustment weight is obtained, the calibration cycle is optimized based on the adjustment weight, and the optimized cycle is used as the new calibration cycle. Obtain the planned interruption interval corresponding to any production line segment within a third preset time period, optimize the process cycle based on the planned interruption interval, and use the optimized cycle as the new process cycle.

[0010] In conjunction with the first aspect, in the fourth implementation of the first aspect of this application, step 3 includes: Determine if any operational data is abnormal; if so, determine if the production equipment is abnormal. Extract any abnormal operational data and define it as the first data to be analyzed. Determine whether the first storage module stores operational data of another type that is within the effective monitoring period. If so, define it as the second data to be analyzed. Then, analyze the first and second data to be analyzed to determine the second abnormal mode. If not, store the first data to be analyzed in the first storage module and issue a temporary reminder. Then, continuously monitor the operational data until the effective monitoring period is exceeded. Obtain the operational data of another type within the effective monitoring period and define it as the third data to be analyzed. Determine whether the third data to be analyzed is abnormal. If so, analyze the first and third data to be analyzed to determine the second abnormal mode. Store the third data to be analyzed in the first storage module in a corresponding manner with the first data to be analyzed. If not, analyze the first data to be analyzed to determine the second abnormal mode. After traversing all the runtime data with anomalies, the first anomaly mode is determined based on all the second anomaly modes.

[0011] In conjunction with the first aspect, in the fifth implementation of the first aspect of this application, the effective monitoring period is the period after the acquisition time of the first data to be analyzed and the fourth preset time between the acquisition time and the acquisition time.

[0012] In conjunction with the first aspect, in the sixth implementation of the first aspect of this application, the production data is the ratio of the quantity of products to be processed to the planned quantity of products to be processed; the abnormal behavior data includes equipment status and the first abnormal mode; the time data includes abnormal time data and processing time data; and step 4 includes: Extract any abnormal device, obtain the production data and first abnormal mode of the abnormal device, identify the device status of the abnormal device based on the first abnormal mode, and extract all abnormal time lengths corresponding to the first abnormal mode within a fifth preset time period. Average all abnormal time lengths to obtain abnormal time data. At the same time, extract all processing cycles corresponding to any abnormal device within the fifth preset time period, and average all processing cycles to obtain processing time data. The time from when the production object enters to when it leaves any abnormal device is defined as the processing cycle. Subsequently, a status data sequence is generated based on the production data, device status, first abnormal mode, abnormal time data, and processing time data. After traversing all abnormal devices, input all state data sequences into the preset model and obtain the sorting.

[0013] In conjunction with the first aspect, in the seventh implementation of the first aspect of this application, step 4 is followed by: Step 51: Extract any abnormal device, obtain the first abnormal mode of any abnormal device, analyze the first abnormal mode, and determine whether there are multiple abnormal situations. If so, proceed to step 52. Step 52: Extract any abnormal situation, obtain the corresponding operating data for any abnormal situation, and calculate the failure probability of the abnormal device module based on the operating data, where the abnormal device module is the device module corresponding to any abnormal situation; Step 53: Obtain the functional objectives of the abnormal equipment modules, identify other equipment modules that have a causal relationship with the functional objectives, define them as the first equipment modules, and obtain the failure probabilities corresponding to all the first equipment modules; Step 54: Obtain the causal relationship graph corresponding to the functional objective. Based on the failure probability of the abnormal device module and all first device modules, as well as the causal relationship graph, calculate the failure probability of the functional objective. Step 55: Obtain the fault repair time corresponding to the abnormal device module, calculate the product of the fault repair time and the failure probability, and define it as a reference index value; Step 56: After traversing all abnormal situations, prioritize all abnormal situations based on reference index values, and perform abnormal situation elimination operations based on the priority ranking.

[0014] In conjunction with the first aspect, in the eighth implementation of the first aspect of this application, step 54 is followed by: Obtain the failure probability of the compensation measures corresponding to the functional objectives; Calculate the probability of any abnormal device stopping operation based on the failure probability and the failure probability, take the probability of stopping operation as the failure probability, and then proceed to step 55.

[0015] Secondly, this application provides a monitoring system for a rubber and plastic product production line, the system comprising: a production division module, a performance determination module, an anomaly identification module, and an anomaly elimination module; The production segmentation module is used to obtain the production item set of the rubber and plastic product production line according to the production process of the rubber and plastic product production line, and extract the production line segment corresponding to each production item based on the production item set. The performance determination module is used to obtain the calibration cycle corresponding to the production object and the process cycle for processing the production object for any production line segment, and analyze the process cycle and calibration cycle to determine the performance indicators of the production equipment in any production line segment. When the performance indicators indicate that the production equipment has a suspected abnormality, it enters the abnormality identification module. The anomaly identification module is used to acquire the operating data of the production equipment within a first preset time period, determine whether there is an anomaly in the production equipment based on the operating data, and if so, determine the first anomaly mode of the production equipment and calculate the anomaly time length of the production equipment. Then, it enters the anomaly elimination module. The operating data includes status indicator data and event log data. The anomaly elimination module is used to define production equipment with anomalies as abnormal equipment, identify all abnormal equipment on the rubber and plastic product production line, extract production data, abnormal behavior data, and time data for each abnormal equipment, sort the abnormal equipment based on the production data, abnormal behavior data, and time data, and perform anomaly elimination operations on all abnormal equipment based on the sorting.

[0016] Compared with the prior art, the beneficial effects of the technical solution of this application are at least as follows: 1. By analyzing the process cycle and calibration cycle to obtain the cycle energy efficiency ratio and deviation rate, a rapid anomaly identification phase can be initiated once a suspected anomaly is detected in the performance indicators determined by the obtained cycle energy efficiency ratio and deviation rate. This rapid response mechanism avoids the long-term accumulation of potential problems in the production process, thereby reducing production stoppages caused by equipment failures or production anomalies, improving the accuracy and reliability of detection, and effectively improving overall production efficiency.

[0017] 2. By conducting in-depth analysis of operational data, including status indicator data and event log data, the operating status of production equipment can be assessed more comprehensively, reducing false alarms and missed alarms caused by a single data source, accurately determining whether equipment anomalies exist, and identifying the causes of anomalies. Parallel detection of multi-source data and temporal correlation of data facilitates intervention in the early stages of equipment failure, preventing further escalation of the failure and significantly improving the reliability and maintainability of the monitoring system.

[0018] 3. Based on multi-dimensional information such as production data, abnormal behavior data, and time data, sorting is performed, and anomaly elimination operations are carried out based on this sorting. This ensures that maintenance resources are prioritized for handling abnormal equipment that has a significant impact on production, and that production resources (such as maintenance personnel and maintenance equipment) can be rationally allocated, thereby reducing production plan delays and optimizing the entire production process. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of an embodiment of a method for monitoring a rubber and plastic product production line according to this application. Figure 2 This is a schematic diagram of an embodiment of the method for determining the first abnormal mode of production equipment in this application. Figure 3 This is a schematic diagram of an embodiment of the exception priority sorting method in this application; Figure 4 This is a schematic diagram of one embodiment of a rubber and plastic product production line monitoring system in this application. Detailed Implementation

[0021] This application provides a method and system for monitoring a rubber and plastic product production line. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0022] For ease of understanding, the specific process of the embodiments of this application is described below. Please refer to [link / reference]. Figure 1 One embodiment of a method for monitoring a rubber and plastic product production line in this application includes: Step 1: Based on the production process of the rubber and plastic product production line, obtain the production item set of the rubber and plastic product production line, and extract the production line segment corresponding to each production item based on the production item set.

[0023] Specifically, the production process of rubber and plastic products includes raw material preparation, plasticizing, mixing, molding, vulcanization, finishing and inspection, etc. Based on this production process, each production step is defined as a production project, and the production segment corresponding to each production project is defined as a production line segment.

[0024] A production line segment is the physical manifestation of a production project. It breaks down a complex production line into multiple manageable units. By extracting production line segments, each production link can be monitored in detail.

[0025] Step 2: For any production line segment, obtain the calibration cycle corresponding to the production object and the process cycle for processing the production object, and analyze the process cycle and calibration cycle to determine the performance indicators of the production equipment in any production line segment. When the performance indicators indicate that the production equipment has a suspected abnormality, proceed to Step 3.

[0026] Specifically, the calibration cycle refers to the time required for production equipment to complete a standard production task under normal operating conditions. The calibration cycle is usually provided by the equipment manufacturer or derived from historical production data. The process cycle is the time required for production equipment to actually complete the same production task, which can be obtained through real-time monitoring.

[0027] By capturing latent anomalies that cannot be directly detected by traditional sensors or operating parameters (such as temperature and pressure), analyzing process cycles and calibration cycles to obtain performance indicators, and analyzing the degree of deviation of performance indicators, potential problems of equipment can be easily and promptly discovered. Only when there is a suspected anomaly in the equipment will subsequent anomaly detection steps be initiated. This not only enables early warning and quantitative evaluation of equipment performance, but also helps to optimize the allocation of monitoring resources and improve the efficiency of the monitoring system.

[0028] Step 3: Obtain the operating data of the production equipment within the first preset time period. Based on the operating data, determine whether there is an abnormality in the production equipment. If there is, determine the first abnormal mode of the production equipment and calculate the abnormal time length of the production equipment. Then proceed to Step 4. The operating data includes status indicator data and event record data.

[0029] Specifically, the first preset time is the time range considered when analyzing equipment operation data. It is set based on the experience of those skilled in the art or according to the actual application scenario, and this application embodiment does not limit it.

[0030] Status indicator data includes equipment temperature, pressure, vibration, voltage, current, etc. Event log data is text-based records generated during equipment operation, used to record various events, operations, errors, warnings, and other relevant information. This data can provide specific event information during equipment operation. Based on operational data (such as threshold exceeding limits, abnormal data fluctuations, equipment operating status messages (such as excessively high temperature), operation logs, etc.), it is determined whether there are any abnormalities in the equipment. If abnormalities are found, further analysis of the operational data is conducted to determine the primary abnormality mode (such as mechanical wear, sensor failure, process parameter misalignment, etc.).

[0031] By parallel detection of different types of monitoring data (status indicator data and event log data) and combining the correlation between the two, a comprehensive judgment can be made on data from different data sources. This enables a comprehensive judgment to be made in the early stages of anomalies, avoiding detection delays caused by latency from a single data source and improving the accuracy of anomaly detection.

[0032] Step 4: Define any abnormal production equipment as abnormal equipment, identify all abnormal equipment on the rubber and plastic product production line, and extract the production data, abnormal behavior data, and time data of each abnormal equipment. Sort the abnormal equipment based on the production data, abnormal behavior data, and time data, and perform anomaly elimination operations on all abnormal equipment based on the sorting.

[0033] Specifically, the entire rubber and plastics product production line is traversed to identify all production equipment marked as "abnormal equipment," ensuring that all equipment with problems at the same or similar times is included in the subsequent processing flow.

[0034] Production data includes the quantity of work-in-process (WIP) or the ratio of WIP to planned production. WIP refers to the number of workpieces being processed on various production lines. The ratio of WIP to planned production indicates the proportion of unfinished products at that particular production line. If a machine stoppage leads to a large backlog of work-in-process, it will significantly impact the production process. Considering the ratio of WIP to planned production when determining recovery priorities helps prioritize the recovery of equipment that has the greatest impact on the production process. Abnormal behavior data includes equipment status and primary abnormality patterns. Equipment status includes the current state of the production equipment, such as whether it is operating normally, whether there is a fault, and whether maintenance is required. Status information provides insight into the health and operational status of the production equipment. Considering status information when determining recovery priorities helps prioritize equipment with abnormal status to minimize the impact on the production process. Time data includes anomaly duration data and processing time data. Anomaly duration is the average time that production equipment stops operating due to a specific reason (first anomaly mode), reflecting the equipment's reliability and maintenance efficiency. A longer anomaly duration indicates lower equipment reliability and poorer maintenance efficiency; conversely, a shorter anomaly duration indicates higher equipment reliability and better maintenance efficiency. Considering anomaly duration when determining recovery priorities helps prioritize the recovery of equipment with the greatest impact on production. Processing time refers to the average time required for production equipment to complete the processing of one workpiece, directly reflecting the production efficiency of the equipment. A shorter processing time indicates higher production efficiency; conversely, a longer processing time indicates lower production efficiency. Considering processing time when prioritizing anomaly recovery helps prioritize the recovery of equipment with the greatest impact on production efficiency.

[0035] Production data, abnormal behavior data, and time data of abnormal equipment can comprehensively reflect the impact of equipment downtime on production efficiency and production processes. Based on systematic considerations of minimizing production efficiency losses and optimizing resource allocation, a reasonable recovery priority is determined based on the above factors. Prioritizing the handling of equipment with severe problems helps to maximize production efficiency, reduce downtime, and improve overall production performance.

[0036] In one specific embodiment, when the product being produced is a fluid product, the calibration cycle and the process cycle are the cycles during which the product reaches a predetermined state, respectively. Step 2 includes: (1) Execute the first preset algorithm on the process cycle and calibration cycle to obtain the cycle energy efficiency ratio.

[0037] (2) Obtain all calibration cycles and all process cycles corresponding to the production equipment within the second preset time period, and define them as calibration cycle sequence and process cycle sequence respectively. Identify the number of data in the calibration cycle sequence, and compare the values ​​in the process cycle sequence with the corresponding values ​​in the calibration cycle sequence in turn. Identify the number of times the process cycle does not meet the calibration cycle, and define it as the first deviation number. Execute the second preset algorithm on the first deviation number and the number of data to obtain the deviation occurrence rate.

[0038] (3) Compare the cycle energy efficiency ratio and deviation rate with the corresponding thresholds respectively, and obtain the performance indicators based on the comparison results.

[0039] Specifically, in the production process of rubber and plastic products, the product is in a fluid state at certain steps, such as plasticizing (transforming raw rubber from a highly elastic state to a plastic state) and mixing (the process of adding various compounding agents to the plasticized rubber to make it evenly dispersed). The production operation object is in a fluid state and is a whole. In the molding step (processing the mixed rubber into a semi-finished product with a certain shape and size), individual parts can be operated.

[0040] Fluid processing is a continuous process (not discrete component production). The production of fluid products (such as molten plastics and liquid rubber) is essentially a process of physical / chemical state transformation. The key to its quality control lies in whether the phase change (such as melting and vulcanization) is completed within a specified time or whether key physical properties (such as viscosity and temperature) are reached. Defining the cycle as "the time to reach a predetermined state" directly captures the core of fluid production technology. Therefore, when the production object is a fluid product, the planned state of the production object is divided into stages, a calibration cycle is set for each state stage, and the time for the production object to reach any state stage is taken as the process cycle.

[0041] The second preset time is used to define the time range considered when analyzing equipment performance indicators. Within this time range, the system collects all calibration cycle and process cycle data of the equipment, forming a calibration cycle sequence and a process cycle sequence. The specific settings are based on the experience of those skilled in the art or on the actual application scenario, and this application embodiment does not limit this. For example, fluid production is usually a continuous process, and its state changes (such as heating and cooling) require a certain amount of time to stabilize. The second preset time should cover several (at least 3 to 5) complete process cycles. For example, if the calibration cycle = 5 minutes, the second preset time ≥ 15 minutes.

[0042] The calculation formula for the first preset algorithm mentioned above is: Where R1 is the periodic efficiency ratio, T S1 For the process cycle, T PThe cycle efficiency ratio is used for calibration. It reflects the deviation between actual production time and ideal baseline time, indicating whether the overall production capacity of the equipment / production line meets the standard. It can detect slow performance degradation (such as bearing wear, belt loosening). These problems may not trigger real-time parameter alarms, but they can be detected early through the cycle efficiency ratio trend.

[0043] The calculation formula for the second preset algorithm mentioned above is: R² is the deviation incidence rate, where N1 is the first deviation number and N2 is the number of data points. The deviation incidence rate reflects the frequency of production cycle fluctuations. Based on the deviation incidence rate, occasional faults (such as sensor false triggering or brief material jams) can be detected. These faults may recover automatically without leaving any abnormal parameter records. At the same time, it can reflect the rhythm instability caused by equipment control logic or external intervention (such as manual adjustment). For example, if the calibration cycle sequence is [5, 5, 5, 5, 5, 5] and the process cycle sequence is [5.2, 4.8, 6.0, 5.5, 7.1, 5.0], then the deviation incidence rate R² is 5 / 6.

[0044] Specifically, the equipment is operating normally when both the cycle energy efficiency ratio and the deviation rate are less than their corresponding thresholds; otherwise, it indicates that there is an abnormality in the equipment operation.

[0045] Cycle efficiency ratio acts as an "efficiency microscope," revealing the overall compliance rate of production capacity; deviation rate acts as a "stethoscope of stability," capturing abnormal fluctuations in production rhythm. By combining these two methods through time-dimensional anomaly detection, they can cover the entire spectrum of monitoring, from gradual degradation to random failures, making up for the blind spots of traditional parameter monitoring. This is especially suitable for faults without direct parameter characterization (such as logic errors or minor mechanical jamming) and early warnings of gradual performance degradation, capturing latent anomalies that cannot be directly detected by traditional sensors or operating parameters (such as temperature and pressure).

[0046] In one specific embodiment, when the production object is a discrete product, step 2 includes: (1) Extract the total number of production objects processed by the production equipment within the third preset time period, and accumulate all process cycles to obtain the sum. Execute the third preset algorithm on the sum, total number and calibration cycle to obtain the cycle energy efficiency ratio.

[0047] (2) Compare the process cycle of each production object with the calibration cycle, identify the number of times the process cycle does not meet the calibration cycle, define it as the second deviation number, and execute the fourth preset algorithm on the second deviation number and the total number to obtain the deviation occurrence rate.

[0048] (3) Compare the cycle energy efficiency ratio and deviation rate with the corresponding thresholds respectively, and obtain the performance indicators based on the comparison results.

[0049] The third preset time is a dynamic time window used for statistical analysis of discrete product production data. Its setting needs to comprehensively consider production characteristics and monitoring objectives, and should be set based on the experience of those skilled in the art or according to the actual application scenario. This application embodiment does not limit this. For example, it can be determined according to the standard production cycle of the production equipment. For instance, if the calibration cycle of a single piece is 2 minutes, the third preset time can be greater than or equal to 10 times the cycle (20 minutes) to ensure statistical significance.

[0050] The calculation formula for the third preset algorithm mentioned above is: Where R1 is the periodic efficiency ratio, T A T is the sum of all process cycles within the third preset time period. S2 This is the product of the calibration period and the total number mentioned above. Preferably, the process period is the time from when one production object enters the production equipment to when the next production object enters the production equipment, or the time from when one production object enters the production equipment to when it leaves the production equipment.

[0051] Specifically, the process cycle does not meet the calibration cycle, meaning the process cycle and the calibration cycle are not equal. The calculation formula for the fourth preset algorithm is the same as that for the second preset algorithm, and will not be repeated here.

[0052] Specifically, the equipment is operating normally when both the cycle energy efficiency ratio and the deviation rate are less than their corresponding thresholds; otherwise, it indicates that there is an abnormality in the equipment operation.

[0053] In one specific embodiment, the process of performing step 2 may specifically include the following steps: (1) Based on the product model, raw material information and process parameters of any production line segment of the rubber and plastic products, obtain the adjustment weight, optimize the calibration cycle based on the adjustment weight, and use the optimized cycle as the new calibration cycle.

[0054] (2) Obtain the planned interruption interval corresponding to any production line segment within the third preset time, optimize the process cycle based on the planned interruption interval, and use the optimized cycle as the new process cycle.

[0055] Specifically, the calibration period is usually a static theoretical value. However, in actual production, many variables exist (such as equipment aging, batch differences in raw materials (different raw material characteristics and quality), changes in environmental temperature and humidity, and different process parameters), causing a fixed benchmark to fail to accurately reflect the current production capacity. If the original benchmark time is used directly, false alarms may be triggered due to non-fault delays (such as increased raw material viscosity) or real faults (such as equipment performance degradation). Therefore, using adjustment weights that take into account the above-mentioned factors to correct the calibration period, and using the corrected calibration period to determine the operating status of equipment or processes, can obtain more accurate judgment results. For example, historical data can be analyzed, and corresponding adjustment weights can be set based on raw material information, process parameters, etc., and the raw material information, process parameters, etc., can be stored in correspondence with the adjustment weights. When optimizing the calibration period, the corresponding calibration period is extracted based on the product model, and the product of the adjustment weight and the above calibration period is used as the new calibration period.

[0056] Planned interruption intervals are primarily used to account for planned downtime in the production process (such as mold changes, maintenance, shift handover, etc.). By accurately identifying planned interruptions, the impact of non-production time is reduced, ensuring that equipment status assessments, efficiency analyses, and production decisions are based on real and effective operational data. When producing fluid products, process cycle optimization is based on optimizing the process cycle to reach the predetermined state of the product, subtracting the planned interruption interval from that cycle to obtain a new process cycle. When producing discrete products, process cycle optimization is based on the sum of all process cycles, subtracting the planned interruption interval from the sum to obtain a new process cycle.

[0057] In one specific embodiment, the process of performing step 3 may specifically include the following steps: (1) Determine whether any running data is abnormal. If so, determine that the production equipment is abnormal.

[0058] (2) Extract any abnormal operating data and define it as the first data to be analyzed. Determine whether the first storage module stores operating data of another type that is within the effective monitoring period. If so, define it as the second data to be analyzed. Then analyze the first data to be analyzed and the second data to be analyzed to determine the second abnormal mode. If not, store the first data to be analyzed in the first storage module and issue a temporary reminder message. Then continuously monitor the operating data until the effective monitoring period is exceeded. Obtain the operating data of another type within the effective monitoring period and define it as the third data to be analyzed. Determine whether the third data to be analyzed is abnormal. If so, analyze the first data to be analyzed and the third data to be analyzed to determine the second abnormal mode. Store the third data to be analyzed in the first storage module in a corresponding manner with the first data to be analyzed. If not, analyze the first data to be analyzed to determine the second abnormal mode.

[0059] (3) After traversing all the running data with anomalies, determine the first anomaly mode based on all the second anomaly modes.

[0060] The flowchart for determining the first abnormal mode of production equipment is as follows: Figure 2 As shown.

[0061] Specifically, when the operational data is status indicator data, if any status indicator data exceeds its corresponding preset range, it indicates that there is an abnormality in the production equipment; when the operational data is event log data, the content of the event log data is compared with the content of the data under normal conditions. If there are format discrepancies (such as missing key fields, incorrect timestamp format), variable out of bounds (such as temperature values ​​exceeding the preset range), unknown log types, etc., it indicates that the operational data is abnormal and there is an abnormality in the production equipment.

[0062] When the first type of data to be analyzed is status indicator data, the other type of operational data is event log data; when the first type of data to be analyzed is event log data, the other type of operational data is status indicator data. The aforementioned effective monitoring period is a preset "certain time" serving as the time range for associating the other type of operational data. This effective monitoring period can be set based on the delay between an abnormal status indicator and an abnormal event log data occurrence in historical data, or the delay between an abnormal event log data occurrence and an abnormal status indicator occurrence. The effective monitoring periods corresponding to abnormal status indicators and abnormal event log data can be different. For status indicator data, for example, sensor data is collected in real time, but event log data needs to be processed and generated by the system, which will result in a certain delay. For event log data, for example, manual operation records (such as parameter modification, emergency stop button triggering, manual material feeding, etc.) cause abnormal status indicators. For example, [Operator ID: 007] manually closes the cooling water valve (the system automatically compares the operation value with the process standard, records the violation (such as the temperature set value exceeding the limit) and prompts that the event log data is abnormal). After the effective monitoring period, the equipment status indicators change (such as the heating power increasing to 100% due to manual temperature adjustment); the operator accidentally adds expired accelerator (log record), and 30 minutes later (i.e., the effective monitoring period), the vulcanizer detects an abnormal decrease in the crosslinking rate; the operator manually closes the exhaust valve (log alarm), and 5 minutes later (i.e., the effective monitoring period), the pressure sensor shows a sudden increase in the pressure inside the mold cavity.

[0063] After detecting the first piece of data to be analyzed, the system searches the first storage module to see if there is a second piece of data to be analyzed. This means that related abnormal data is read from the first storage module as expected future abnormal data. The core logic is based on historical correlations to predict potential future abnormal data. By recording the correlation between the "first piece of data to be analyzed" and subsequent "second piece of data to be analyzed" in historical data, when the same anomaly in the first piece of data to be analyzed is detected again, the system can predict the possible anomaly in the second piece of data to be analyzed, achieving early warning and shortening fault diagnosis time.

[0064] Single data sources have a high false alarm rate (such as sensor noise or false alarms from logs). By correlating status indicator data and event record data, the temporal correlation of multi-source data is used to reduce false alarms, improve the confidence of fault detection, and accurately locate the cause of the fault (equipment failure, operational reasons, equipment software system reasons, etc.).

[0065] Specific correlations exist between the measured values ​​of different sensors. Sensor combinations with specific relationships are identified based on historical data, and a correlation function corresponding to that sensor combination is constructed based on the historical data. As a preferred embodiment of this invention, when the operating data is status indicator data, the method for determining whether it is abnormal is as follows: extract the status indicator data of any sensor in the sensor combination, input it into the corresponding correlation function, obtain the output value, and compare this output value with the status indicator data of another sensor in the sensor combination. If they are inconsistent, the status indicator data is determined to be abnormal.

[0066] In one specific embodiment, the effective monitoring period is the period after the acquisition time of the first data to be analyzed and the fourth preset time remaining from the acquisition time.

[0067] For example, the fourth preset time is 5 minutes. If the acquisition time of the first data to be analyzed is 10:00, then the effective monitoring period is 10:00 to 10:05.

[0068] In one specific embodiment, the production data is the ratio of the quantity of products to be processed to the planned quantity of products to be processed; the abnormal behavior data includes equipment status and a first abnormal mode; the time data includes abnormal time data and processing time data; and step 4 includes: (1) Extract any abnormal device, obtain the production data and first abnormal mode of any abnormal device, identify the device status of any abnormal device based on the first abnormal mode, and extract all abnormal time lengths corresponding to the first abnormal mode within a fifth preset time period. Average all abnormal time lengths to obtain abnormal time data. At the same time, extract all processing cycles corresponding to any abnormal device within a fifth preset time period, and average all processing cycles to obtain processing time data. The time from when the production object enters to when it leaves any abnormal device is defined as the processing cycle. Subsequently, generate a status data sequence based on the production data, device status, first abnormal mode, abnormal time data and processing time data.

[0069] (2) After traversing all abnormal devices, input all state data sequences into the preset model and obtain the sorting.

[0070] Specifically, the aforementioned equipment status includes normal, fault, shutdown, waiting, and recovery. The fifth preset time is used to calculate the abnormal time data and processing time data of the faulty equipment. This setting is based on the experience of those skilled in the art or on the actual application scenario, and is not limited in this embodiment.

[0071] Preferably, the abnormal time length used to calculate the abnormal time data and all processing cycles used to calculate the processing time data are the times corresponding to the production of the same product model and / or the same batch of products.

[0072] By combining production data, abnormal behavior data, and time data, the status of abnormal equipment is comprehensively assessed. A pre-set model is used to dynamically calculate and prioritize equipment, ensuring that priorities match actual production needs. Equipment with the greatest impact on production is addressed first, minimizing downtime. For example, the pre-set model may be a neural network model or a support vector machine.

[0073] Before step 4, first determine if there is only one faulty device. If so, repair the faulty device directly and skip the faulty device sorting in step 4.

[0074] In one specific embodiment, step 4 is followed by: Step 51: Extract any abnormal device, obtain the first abnormal mode of any abnormal device, analyze the first abnormal mode, and determine whether there are multiple abnormal situations. If so, proceed to step 52.

[0075] Step 52: Extract any abnormal situation, obtain the corresponding operating data for any abnormal situation, and calculate the failure probability of the abnormal device module based on the operating data, where the abnormal device module is the device module corresponding to any abnormal situation.

[0076] Step 53: Obtain the functional target of the abnormal device module, identify other device modules that have a causal relationship with the functional target, define them as the first device module, and obtain the failure probability corresponding to all first device modules.

[0077] Step 54: Obtain the causal relationship graph corresponding to the functional objective. Based on the failure probability of the abnormal device module and all first device modules, as well as the causal relationship graph, calculate the failure probability of the functional objective.

[0078] Step 55: Obtain the fault repair time corresponding to the abnormal device module, calculate the product of the fault repair time and the failure probability, and define it as a reference index value.

[0079] Step 56: After traversing all abnormal situations, prioritize all abnormal situations based on reference index values, and perform abnormal situation elimination operations based on the priority ranking.

[0080] The flowchart for prioritizing abnormal situations is as follows: Figure 3 As shown.

[0081] Specifically, abnormal equipment may have multiple faults at the same time, that is, multiple abnormal situations, such as multiple modules of the equipment malfunctioning at the same time, equipment malfunctions coexisting with software malfunctions or human operation abnormalities. In order to improve the efficiency and accuracy of abnormal handling and ensure that abnormal equipment can quickly return to normal operation, it is necessary to refine the handling of multiple abnormal situations of abnormal equipment, so as to reasonably arrange the processing order and optimize resource allocation.

[0082] When calculating the failure probability, based on the operating data corresponding to the abnormal situation, statistical methods such as z-scores, quartile ranges, and Mahalanobis distance, or machine learning models such as cluster analysis and principal component analysis are used to calculate the degree of deviation between the current operating state and the normal operating state of the abnormal equipment module. Based on this degree of deviation, a mapping table is looked up to obtain the failure probability of the abnormal equipment module.

[0083] The aforementioned functional objective is the function to be achieved by the faulty equipment module. Taking a rubber extrusion equipment as an example, the technical solution of the present invention will be described. For example, the heating module of the rubber extrusion equipment is a faulty equipment module, and its functional objective is to maintain the stability of the molten rubber temperature. Other equipment modules that are causally related to maintaining the stability of the molten rubber temperature include the cooling system module (which counteracts overheating through air cooling / water cooling (such as cooling fans and circulating water valves)) and the temperature control algorithm module (which dynamically adjusts the heating power and cooling rate). A failure in either the cooling system module or the temperature control algorithm module will also cause the molten rubber temperature to become unstable. Based on this, the probability of the functional objective of "maintaining the stability of the molten rubber temperature" failing is P1+P2+P3, where P1 is the failure probability of the heating module, P2 is the failure probability of the cooling system module, and P3 is the failure probability of the temperature control algorithm module.

[0084] The failure probability of a functional objective represents the likelihood of unplanned downtime of production equipment due to a faulty module, reflecting the degree of risk of abnormal equipment status. Fault repair time is the time required for repair and maintenance after equipment failure. Multiplying the failure probability of a functional objective by the fault repair time can combine risk and cost, quantify the "expected maintenance burden of equipment failure", and thus find a balance between risk and cost, helping to develop a more scientific and economical maintenance plan.

[0085] After traversing all abnormal situations, a higher priority is set for abnormal equipment modules with large reference index values, which can quickly focus on high-risk and high-cost equipment modules.

[0086] The technical solution of this invention, by quantitatively analyzing the impact of faults, transforms complex multi-anomaly problems into an operable priority sequence, significantly improving industrial operation and maintenance efficiency.

[0087] In one specific embodiment, step 54 is followed by: (1) Obtain the failure probability of the compensation measures corresponding to the functional objectives.

[0088] (2) Calculate the probability of stopping operation of any abnormal device based on the failure probability and the failure probability, take the probability of stopping operation as the failure probability, and then proceed to step 55.

[0089] Specifically, the compensation measures corresponding to the functional objectives are measures to prevent the malfunction of abnormal equipment modules from progressing and to ensure the stability of the functional objectives. Taking the heating module as an example of an abnormal equipment module, its corresponding compensation measures include automatic switching to a backup heating module and dynamic resetting of PID parameters. The failure probability of the above compensation measures is P4+P5, where P4 is the failure probability of automatic switching to a backup heating module and P5 is the failure probability of dynamic resetting of PID parameters.

[0090] First, analyze the root cause of the failure, locate the key equipment modules, then consider compensation measures, and quantify the effectiveness of the response measures. This can provide highly reliable and transparent risk analysis and provide a scientific basis for prioritizing decisions on the elimination of abnormal situations.

[0091] The above describes a method for monitoring a rubber and plastic product production line according to an embodiment of this application. The following describes a monitoring system for a rubber and plastic product production line according to an embodiment of this application. Please refer to [link / reference]. Figure 4 One embodiment of a rubber and plastic product production line monitoring system in this application includes: a production division module 10, a performance determination module 20, an anomaly identification module 30, and an anomaly elimination module 40.

[0092] The production segmentation module 10 is used to obtain the production item set of the rubber and plastic product production line according to the production process of the rubber and plastic product production line, and extract the production line segment corresponding to each production item based on the production item set.

[0093] The performance determination module 20 is used to obtain the calibration cycle corresponding to the production object and the process cycle for processing the production object for any production line segment, and to analyze the process cycle and calibration cycle to determine the performance indicators of the production equipment in any production line segment. When the performance indicators indicate that the production equipment has a suspected abnormality, it enters the abnormality identification module 30.

[0094] The anomaly identification module 30 is used to acquire the operating data of the production equipment within a first preset time period, determine whether there is an anomaly in the production equipment based on the operating data, and if so, determine the first anomaly mode of the production equipment and calculate the anomaly time length of the production equipment, and then enter the anomaly elimination module 40. The operating data includes status indicator data and event record data.

[0095] The anomaly elimination module 40 is used to define production equipment with anomalies as abnormal equipment, identify all abnormal equipment on the rubber and plastic product production line, extract production data, abnormal behavior data and time data of each abnormal equipment, sort the abnormal equipment based on the production data, abnormal behavior data and time data, and perform anomaly elimination operations on all abnormal equipment based on the sorting.

[0096] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0097] If the integrated unit 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 application, in essence, or the part that contributes to the prior art, or all or 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 described in the various embodiments of this application. 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.

[0098] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for monitoring a rubber and plastic product production line, characterized in that, The method includes: Step 1: Based on the production process of the rubber and plastic product production line, obtain the production item set of the rubber and plastic product production line, and extract the production line segment corresponding to each production item based on the production item set. Step 2: For any production line segment, obtain the calibration cycle corresponding to the production object and the process cycle for processing the production object, and analyze the process cycle and the calibration cycle to determine the performance index of the production equipment in any production line segment. When the performance index indicates that the production equipment has a suspected abnormality, proceed to step 3. Step 3: Obtain the operating data of the production equipment within a first preset time period, determine whether there is an abnormality in the production equipment based on the operating data, if there is, determine the first abnormality mode of the production equipment, calculate the abnormality time length of the production equipment, and then proceed to step 4. The operating data includes status indicator data and event record data. Step 4: Define the production equipment with abnormalities as abnormal equipment, identify all abnormal equipment on the rubber and plastic product production line, and extract the production data, abnormal behavior data and time data of each abnormal equipment. Sort the abnormal equipment based on the production data, abnormal behavior data and time data, and perform anomaly elimination operation on all the abnormal equipment based on the sorting.

2. The method for monitoring a rubber and plastic product production line according to claim 1, characterized in that, When the production object is a fluid product, the calibration cycle and the process cycle are the cycles for the production object to reach a predetermined state, respectively. Step 2 includes: A first preset algorithm is executed on the process cycle and the calibration cycle to obtain the cycle energy efficiency ratio; All calibration cycles and all process cycles corresponding to the production equipment within a second preset time period are obtained and defined as calibration cycle sequence and process cycle sequence, respectively. The number of data in the calibration cycle sequence is identified, and the values ​​in the process cycle sequence are compared with the corresponding values ​​in the calibration cycle sequence in turn. The number of times the process cycle does not meet the calibration cycle is identified and defined as the first deviation number. A second preset algorithm is executed on the first deviation number and the number of data to obtain the deviation occurrence rate. The cycle energy efficiency ratio and the deviation occurrence rate are compared with the corresponding thresholds, and the performance indicators are obtained based on the comparison results.

3. The method for monitoring a rubber and plastic product production line according to claim 1, characterized in that, When the production object is a discrete product, step 2 includes: Extract the total number of production objects processed by the production equipment within a third preset time period, and accumulate all process cycles to obtain the sum. Execute the third preset algorithm on the sum, the total number, and the calibration cycle to obtain the cycle energy efficiency ratio. The process cycle of each production object is compared with the calibration cycle to identify the number of times the process cycle does not meet the calibration cycle, which is defined as the second deviation number. The fourth preset algorithm is then applied to the second deviation number and the total number to obtain the deviation occurrence rate. The cycle energy efficiency ratio and the deviation occurrence rate are compared with the corresponding thresholds, and the performance indicators are obtained based on the comparison results.

4. The method for monitoring a rubber and plastic product production line according to claim 1, characterized in that, Step 2 includes: Based on the product model, raw material information and process parameters of any of the production line segments, an adjustment weight is obtained, and the calibration cycle is optimized based on the adjustment weight. The optimized cycle is then used as the new calibration cycle. Obtain the planned interruption interval corresponding to any of the production line segments within a third preset time period, optimize the process cycle based on the planned interruption interval, and use the optimized cycle as the new process cycle.

5. The method for monitoring a rubber and plastic product production line according to claim 1, characterized in that, Step 3 includes: Determine if any operational data is abnormal; if so, determine that the production equipment is abnormal. Extract any abnormal operational data and define it as the first data to be analyzed. Determine whether the first storage module stores operational data of another type that is within the effective monitoring period. If so, define it as the second data to be analyzed. Then, analyze the first data to be analyzed and the second data to be analyzed to determine the second abnormal mode. If not, store the first data to be analyzed in the first storage module and issue a temporary reminder. Then, continuously monitor the operational data until the effective monitoring period is exceeded. Obtain the operational data of the other type within the effective monitoring period and define it as the third data to be analyzed. Determine whether the third data to be analyzed is abnormal. If so, analyze the first data to be analyzed and the third data to be analyzed to determine the second abnormal mode. Store the third data to be analyzed in the first storage module corresponding to the first data to be analyzed. If not, analyze the first data to be analyzed to determine the second abnormal mode. After traversing all the runtime data that contains anomalies, the first anomaly pattern is determined based on all the second anomaly patterns.

6. The method for monitoring a rubber and plastic product production line according to claim 5, characterized in that, The effective monitoring period is the period after the acquisition time of the first data to be analyzed and the fourth preset time from the acquisition time.

7. The method for monitoring a rubber and plastic product production line according to claim 1, characterized in that, The production data is the ratio of the quantity of products to be processed to the planned quantity of products to be processed; the abnormal behavior data includes equipment status and the first abnormal mode; the time data includes abnormal time data and processing time data; and step 4 includes: Extract any abnormal device, obtain the production data and the first abnormal mode of any abnormal device, identify the device status of any abnormal device based on the first abnormal mode, and extract all abnormal time lengths corresponding to the first abnormal mode within a fifth preset time period. Average all abnormal time lengths to obtain abnormal time data. Simultaneously, extract all processing cycles corresponding to any abnormal device within the fifth preset time period, and average all processing cycles to obtain processing time data. The time from when a production object enters to when it leaves any abnormal device is defined as a processing cycle. Subsequently, a status data sequence is generated based on the production data, the device status, the first abnormal mode, the abnormal time data, and the processing time data. After traversing all the abnormal devices, input all state data sequences into a preset model to obtain the sorting.

8. The method for monitoring a rubber and plastic product production line according to claim 1, characterized in that, Step 4 is followed by: Step 51: Extract any abnormal device, obtain the first abnormal mode of any abnormal device, analyze the first abnormal mode, and determine whether there are multiple abnormal situations. If so, proceed to step 52. Step 52: Extract any abnormal situation, obtain the operating data corresponding to any of the abnormal situations, and calculate the failure probability of the abnormal device module based on the operating data, wherein the abnormal device module is the device module corresponding to any of the abnormal situations; Step 53: Obtain the functional target of the abnormal device module, identify other device modules that have a causal relationship with the functional target, define them as first device modules, and obtain the fault probability corresponding to all first device modules; Step 54: Obtain the causal relationship graph corresponding to the functional objective; and calculate the failure probability of the functional objective based on the failure probability of the abnormal device module and all the first device modules, as well as the causal relationship graph. Step 55: Obtain the fault repair time corresponding to the abnormal device module, calculate the product of the fault repair time and the failure probability, and define it as a reference index value; Step 56: After traversing all abnormal situations, prioritize all the abnormal situations based on the reference index value, and perform abnormal situation elimination operations based on the priority ranking.

9. A method for monitoring a rubber and plastic product production line according to claim 8, characterized in that, Step 54 is followed by: Obtain the failure probability of the compensation measures corresponding to the stated functional objective; Calculate the probability of stopping operation for any of the abnormal devices based on the failure probability and the failure probability, use the probability of stopping operation as the failure probability, and then proceed to step 55.

10. A monitoring system for a rubber and plastic product production line, characterized in that, The system includes: a production division module, a performance determination module, an anomaly identification module, and an anomaly elimination module; The production segmentation module is used to obtain the production item set of the rubber and plastic product production line according to the production process of the rubber and plastic product production line, and extract the production line segment corresponding to each production item based on the production item set. The performance determination module is used to obtain the calibration cycle corresponding to the production object and the process cycle for processing the production object for any production line segment, and to analyze the process cycle and the calibration cycle to determine the performance index of the production equipment in any production line segment. When the performance index indicates that the production equipment has a suspected abnormality, the module enters the abnormality identification module. The anomaly identification module is used to acquire the operating data of the production equipment within a first preset time period, determine whether there is an anomaly in the production equipment based on the operating data, and if there is, determine the first anomaly mode of the production equipment and calculate the anomaly time length of the production equipment, and then enter the anomaly elimination module. The operating data includes status indicator data and event record data. The anomaly elimination module is used to define the production equipment with anomalies as abnormal equipment, identify all abnormal equipment on the rubber and plastic product production line, extract the production data, abnormal behavior data and time data of each abnormal equipment, sort the abnormal equipment based on the production data, the abnormal behavior data and the time data, and perform anomaly elimination operation on all the abnormal equipment based on the sorting.

Images