Intelligent management method and equipment for rubber manufacturing and processing and medium

Abstract

The invention discloses an intelligent management method and equipment for rubber manufacturing and processing and a medium, and relates to the technical field of data processing, and the method comprises the steps: decomposing nodes of a rubber manufacturing and processing flow, and building an equipment cooperation relation; performing working condition monitoring identification on equipment of each processing flow node, and outputting a state monitoring data block of each node equipment; obtaining abnormal information of each node device; performing abnormal influence degree analysis to obtain abnormal processing flow nodes and abnormal influence degrees thereof; target optimization parameters are positioned; and optimizing to obtain equipment control information. The technical problem that in existing rubber manufacturing and processing management, it is difficult to monitor and accurately position abnormities according to mutual influence between processing and manufacturing equipment, so that processing control management and optimization are cooperatively carried out, and the rubber manufacturing and processing management effect is poor is solved. The technical effects of improving the rubber manufacturing and processing management collaboration and controlling the management effect are achieved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly relates to a smart management method, device and medium for rubber manufacturing and processing. Background Art

[0002] As an important industrial raw material, rubber is widely used in multiple fields such as automotive, aviation, medical, and construction. With the continuous development of the global economy and the continuous progress of technology, the demand for rubber products is increasing day by day, and the requirements for rubber manufacturing and processing are also getting higher and higher. With the continuous growth of the global demand for high-quality and high-performance rubber products, the traditional rubber manufacturing and processing methods are difficult to meet the requirements of modern production for high efficiency, precision, and environmental protection. Most of them are based on experience and manual operation, resulting in problems such as low production efficiency, unstable product quality, and serious resource waste. At the same time, it is impossible to carry out collaborative management and optimization of the production and manufacturing process according to the mutual influence between production processes, which not only affects the economic benefits of enterprises but also restricts the sustainable development of the rubber industry.

[0003] Therefore, in the current rubber manufacturing and processing management related technologies, there are technical problems that it is difficult to monitor and accurately locate abnormalities according to the mutual influence between processing and manufacturing equipment, and thus it is difficult to carry out collaborative processing control management and optimization, resulting in poor rubber manufacturing and processing management effects. Summary of the Invention

[0004] By providing a smart management method, device and medium for rubber manufacturing and processing, this application uses technical means such as collaborative analysis, anomaly recognition, and influence degree analysis to solve the technical problems existing in the existing rubber manufacturing and processing management, that is, it is difficult to monitor and accurately locate abnormalities according to the mutual influence between processing and manufacturing equipment, and thus it is difficult to carry out collaborative processing control management and optimization, resulting in poor rubber manufacturing and processing management effects, and achieves the technical effect of improving the collaboration and control management effect of rubber manufacturing and processing management.

[0005] The present application provides an intelligent management method for rubber manufacturing and processing. The method includes: decomposing the rubber manufacturing and processing process nodes, performing equipment collaboration analysis on the processing process nodes, and establishing equipment collaboration relationships; based on the processing process nodes and equipment collaboration relationships, monitoring and identifying the working conditions of the equipment at each processing process node, and outputting a status monitoring data block for each node's equipment, where the status monitoring data block includes an equipment monitoring data set, a processing process node identifier, and a collaboration relationship identifier; based on the processing process node identifier and collaboration relationship identifier, performing equipment anomaly identification according to the equipment monitoring data set to obtain the anomaly information of each node's equipment; according to the anomaly information, performing anomaly impact degree analysis according to the process connection relationship of the processing process nodes and the equipment collaboration relationship to obtain the abnormal processing process nodes and their anomaly impact degrees, where the anomaly impact degree includes a node anomaly impact degree and a full-process anomaly impact degree; according to the node anomaly impact degree and full-process anomaly impact degree, positioning the target optimization parameters; and performing optimization according to the target optimization parameters and their corresponding node anomaly impact relationships and full-process anomaly impact relationships to obtain equipment control information.

[0006] In a possible implementation, to perform equipment collaboration analysis on the processing process nodes and establish equipment collaboration relationships, the following processing is performed: performing correlation analysis on the processing equipment in each processing process node, including running time sequence correlation analysis and state impact correlation analysis; using the running time sequence correlation degree and state impact correlation degree to determine collaborative equipment, where the collaborative equipment is the processing equipment information for which both the running time sequence correlation degree and state impact correlation degree reach a preset threshold; establishing the collaborative impact relationship between the collaborative equipment as the equipment collaboration relationship, and the equipment collaboration relationship has a correlation degree identifier, where the correlation degree identifier is calculated and generated according to the running time sequence correlation degree and state impact correlation degree.

[0007] In a possible implementation, to perform correlation analysis on the processing equipment in each processing process node, the following processing is performed: using the adjacent time sequence process as a screening condition to screen the processing equipment in each processing process node and establish a time sequence continuous equipment pair; obtaining the processing interval time of the time sequence continuous equipment pair, performing time sequence correlation degree conversion according to the processing interval time to obtain the running time sequence correlation degree, where the smaller the processing interval time, the greater the running time sequence correlation degree; based on the time sequence continuous equipment pair, obtaining an abnormal case set; and performing state anomaly correlation analysis on the time sequence continuous equipment pair according to the abnormal case set to obtain the state impact correlation degree.

[0008] In a possible implementation, based on the set of exception cases, a state exception correlation analysis is performed on the time-sequential continuous device pair to obtain the state impact correlation degree, and the following processing is also performed: taking the time-sequential continuous device pair as the target respectively, dividing the set of exception cases to construct a first collaborative device exception case and a second collaborative device exception case, where the first collaborative device and the second collaborative device are each other's time-sequential continuous device pair, and the first collaborative device exception case includes the abnormal state of the first collaborative device and the processing state of the second collaborative device, and the second collaborative device exception case includes the abnormal state of the second collaborative device and the processing state of the first collaborative device; respectively, based on the first collaborative device exception case and the second collaborative device exception case, calculating the synchronous support degree between the abnormal state and the processing state to obtain the state impact correlation degree.

[0009] In a possible implementation, to obtain the state impact correlation degree, the following processing is also performed: based on the first collaborative device exception case, fitting the first synchronous support degree between the processing state of the second collaborative device and the abnormal state of the first collaborative device; based on the second collaborative device exception case, fitting the second synchronous support degree between the processing state of the first collaborative device and the abnormal state of the second collaborative device; using the average calculation of the first synchronous support degree and the second synchronous support degree to obtain the state impact correlation degree.

[0010] In a possible implementation, based on the processing flow node identifier and the collaboration relationship identifier, device exception identification is performed according to the device monitoring data set to obtain the exception information of each node device, and the following processing is also performed: identifying the operating parameters of each device through a preset device exception identification model to obtain an exception identification result, where the preset device exception identification model is a mathematical model that constructs a labeled training data set through historical cases and converges through supervised training to be able to identify the abnormal operating state of the device; based on the processing flow node identifier and the collaboration relationship identifier, determining the device processing rate ratio; analyzing the operating states of the collaborative devices respectively according to the device monitoring data set to determine the operating processing speed; calculating the ratio using the respective operating processing speeds of the collaborative devices and comparing it with the device processing rate ratio, and when the tolerance threshold is not met, generating collaborative exception information, where the tolerance threshold is the threshold at which the device processing rate ratio meets the manufacturing processing requirements of the processing flow node within the maximum error range; combining the exception identification result and the collaborative exception information to generate the exception information of each node device.

[0011] In possible implementation manners, according to the node anomaly influence degree and the overall process anomaly influence degree, the target optimization parameter is located, and the following processing is further performed: tracing the node associated parameters according to the node anomaly influence degree; tracing the overall process associated process nodes and corresponding associated parameters according to the overall process anomaly influence degree; respectively configuring the weights of the node associated parameters, the overall process associated process nodes and corresponding associated parameters with their respective anomaly influence degrees; and locating the target optimization parameter based on the weights, where the target optimization parameter is a parameter whose weight reaches the influence threshold.

[0012] The present application further provides an electronic device, including: a memory for storing executable instructions; a processor, which, when executing the executable instructions stored in the memory, implements a rubber manufacturing and processing intelligent management method.

[0013] The present application further provides a computer-readable storage medium, including: a computer program stored thereon, which, when executed by a processor, implements a rubber manufacturing and processing intelligent management method.

[0014] It is intended to decompose the rubber manufacturing and processing process nodes through a rubber manufacturing and processing intelligent management method proposed in the present application, establish equipment collaboration relationships; perform condition monitoring and identification on the equipment of each processing process node, and output the status monitoring data block of the equipment of each node; obtain the abnormal information of the equipment of each node; perform abnormal influence degree analysis to obtain the abnormal processing process nodes and their abnormal influence degrees; locate the target optimization parameter; and optimize to obtain the equipment control information. This solves the technical problem that in the existing rubber manufacturing and processing management, it is difficult to monitor and accurately locate anomalies based on the mutual influence between processing and manufacturing equipment, and thus it is difficult to perform collaborative processing control management and optimization, resulting in poor rubber manufacturing and processing management effects, and achieves the technical effect of improving the collaboration and control management effects of rubber manufacturing and processing management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in the present application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0016] Figure 1 It is a flowchart of a rubber manufacturing and processing intelligent management method, device and medium provided by an embodiment of the present application; Figure 2Schematic flow diagram for establishing device collaboration relationships in a rubber manufacturing and processing intelligent management method, device, and medium provided by an embodiment of the present application; Figure 3 Schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0017] Explanation of reference numerals: input device 401, processor 402, memory 403, output device 404. Detailed implementation manners

[0018] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0019] In order to make the purpose, technical solution, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0021] An embodiment of the present application provides a rubber manufacturing and processing intelligent management method, as Figure 1 shown, the method includes: Step S100: Decompose the rubber manufacturing and processing process nodes, perform equipment collaborative analysis on the processing process nodes, and establish equipment collaborative relationships. The rubber manufacturing and processing process nodes include raw material preparation (such as raw rubber, paraffin wax, stearic acid and other compounding agents, fiber materials such as cotton, linen and wool, and metal steel wires), plasticating (transforming raw rubber from an elastic state to a plastic state through mechanical stress, heat, oxygen or adding chemical reagents), mixing (uniformly mixing various compounding agents into raw rubber on a rubber mixing mill to form a uniform mixture), calendering (calendering the mixed rubber into a rubber sheet with the required thickness and width through a calender), forming (manufacturing various rubber products from the rubber sheet by cutting, forming or molding, etc.), vulcanizing (during the vulcanization process, cross-linking occurs between rubber molecules to improve the strength, wear resistance and aging resistance of the product), post-treatment (trimming, cleaning, inspection and other links), etc. Perform equipment collaborative analysis on the processing process nodes. Specifically, after the raw rubber and compounding agents are prepared, they enter the rubber mixing mill for mixing. The rubber mixing mill ensures uniform mixing of various raw materials and provides a uniform rubber mixture for subsequent processing; the calender calenders the mixed rubber into a rubber sheet with the required thickness, and then these rubber sheets enter the forming equipment for cutting, forming or molding to form various rubber products; the formed rubber products enter the vulcanizing equipment, and the performance of the products is improved through vulcanization. The vulcanizing equipment needs to cooperate closely with the forming equipment to ensure that the products have reached the predetermined shape and size before vulcanization; the post-treatment equipment (such as a trimming machine, a cleaning machine, etc.) trims and cleans the vulcanized rubber products to ensure product quality. These equipment work in coordination with the entire production line to ensure the smooth progress of the entire production process from raw materials to finished products, establish equipment collaborative relationships, and achieve collaborative work and optimization of the entire production process.

[0022] In a possible implementation manner, such as Figure 2As shown, step S100 further includes step S110, which performs a correlation analysis on the processing equipment in each processing flow node, including an analysis of the correlation of operating time sequences and an analysis of the correlation of state impacts. The analysis of the correlation of operating time sequences refers to analyzing the relevance and synchronization of different processing equipment in terms of operating time to understand the operating coordination among the equipment. For the correlation analysis of the processing equipment in each processing flow node, collect the operating time series data of each processing equipment, including the start time, stop time, operating duration, etc. of the equipment, calculate the correlation coefficient between the operating time sequences of different equipment, quantify the time sequence relevance between the equipment, and based on the value of the correlation coefficient, determine whether there is an obvious time sequence correlation between the equipment. High correlation may mean that the equipment needs to coordinate or depend on each other in operation, while low correlation may indicate that the equipment operates relatively independently. The analysis of the correlation of state impacts refers to analyzing the mutual influence and dependence relationship of different processing equipment in terms of operating state to understand the state transfer and coupling among the equipment. Collect the operating state data of each processing equipment, such as equipment failure rate, repair times, production efficiency, etc., analyze the correlation between the state data of different equipment, identify the factors that have a significant impact on the equipment state, and based on the analysis results, determine which equipment states have a mutual influence or dependence relationship, and the specific manner and degree of this influence. It also includes step S120, which uses the operating time sequence correlation degree and the state impact correlation degree to determine the collaborative equipment. The collaborative equipment is the processing equipment information for which both the operating time sequence correlation degree and the state impact correlation degree reach a preset threshold. By calculating and analyzing the correlation of processing equipment in terms of both operating time sequence and state impact, those equipment that are mutually related, dependent, and whose correlation reaches the preset threshold in terms of operation and state can be identified, thereby optimizing production scheduling, improving equipment utilization rate, and enhancing production stability. It also includes step S130, which establishes the collaborative influence relationship between the collaborative equipment as the equipment collaborative relationship. The equipment collaborative relationship has a correlation degree identifier, where the correlation degree identifier is calculated and generated based on the operating time sequence correlation degree and the state impact correlation degree. By analyzing and calculating the operating time sequence correlation degree and the state impact correlation degree between the collaborative equipment, the degree of mutual dependence and association of these equipment in terms of operation and state is determined, and then a network structure describing their collaborative influence relationship is formed. In this structure, each collaborative relationship will be assigned a correlation degree identifier, and this identifier is calculated and generated based on the operating time sequence correlation degree and the state impact correlation degree of the equipment.

[0023] In a possible implementation, step S110 further includes step S111, which filters the processing devices in each processing flow node with adjacent timing processes as the screening condition to establish a pair of devices with continuous timing. According to the order of device operation in the processing flow, adjacent and timing-continuous devices are paired to form a series of device pairs. Specifically, by analyzing the operation records, production plans or process flowcharts of the devices, the timing of the entire processing flow is clarified, that is, the sequence of each processing flow node arranged in chronological order, and those devices that are adjacent and closely connected in operation time are identified. These devices are continuous in timing, that is, after one device finishes running, the next device starts running immediately. The devices that meet the adjacent timing process condition are screened out from all processing devices, and the screened devices are paired according to the timing order to form a pair of devices with continuous timing. Each device pair includes two devices, one running immediately before the other. It also includes step S112, which obtains the processing interval time of the pair of devices with continuous timing, and performs a timing correlation conversion according to the processing interval time to obtain the running timing correlation. The smaller the processing interval time, the greater the running timing correlation. In the analysis of the processing flow, when the processing interval time (also called the production interval time or waiting time) of the pair of devices with continuous timing is obtained, the timing relationship between the device pairs can be quantified based on this interval time to obtain a running timing correlation. The processing interval time refers to the time difference between the end of the processing task of one device and the start of the processing task of the next device. The length of the processing interval time reflects the tightness of the timing between the devices. Generally speaking, the smaller the processing interval time, the closer the timing between the two devices, and the higher the running timing correlation between them. A conversion function is defined to be able to map a smaller processing interval time to a higher running timing correlation value and a larger processing interval time to a lower correlation value. For example, a function f(t) is defined, where t is the processing interval time and f(t) is the running timing correlation. This function can be f(t) = 1 / (1 + t) or other similar functions. When t (the processing interval time) is small, f(t) (the running timing correlation) will be close to 1 or close to a set upper limit value, indicating that the timing relationship between the devices is very tight. When t is large, f(t) will gradually decrease, indicating that the timing relationship between the devices is relatively weak. It also includes step S113, which obtains an abnormal case set based on the pair of devices with continuous timing. The abnormal case set records various abnormal states and their related information that occur during the operation of the devices, including key information such as the type of device abnormality, the time of abnormality occurrence, the duration of abnormality, and the scope of abnormality influence. It also includes step S114, which performs a state abnormality correlation analysis on the pair of devices with continuous timing according to the abnormal case set to obtain the state influence correlation.State anomaly correlation analysis is an analysis of time-sequential continuous device pairs in terms of state anomalies, aiming to determine the degree of mutual influence of these devices in abnormal states, that is, the state influence correlation degree. Specifically, for each pair of time-sequential continuous devices, analyze the state anomaly relationship between them, check whether the next device also shows anomalies or is affected to a certain extent when one device shows an anomaly, and pay special attention to the time interval between the occurrences of anomalies and the relevance of anomaly types. Calculate the state influence correlation degree between device pairs based on the data in the anomaly case set. The state influence correlation degree is a quantitative indicator that represents the possibility or degree that another device shows an anomaly when one device shows an anomaly.

[0024] In a possible implementation, step S114 further includes step S1141 of dividing the abnormal case set respectively targeting the sequential device pairs to construct a first collaborative device abnormal case and a second collaborative device abnormal case, where the first collaborative device and the second collaborative device are each other's sequential device pairs. The first collaborative device abnormal case includes the abnormal state of the first collaborative device and the processing state of the second collaborative device, and the second collaborative device abnormal case includes the abnormal state of the second collaborative device and the processing state of the first collaborative device. According to the abnormal states of two devices that are sequential in time (i.e., the first collaborative device and the second collaborative device) and their mutual influence, the abnormal case set is divided into two subsets. These two subsets respectively focus on the abnormal state of one device and the processing state of the other device. Specifically, identify two devices that are sequential in the processing flow, define them as the first collaborative device and the second collaborative device, analyze the existing abnormal case set, determine the devices involved in each case and their abnormal states, target the sequential device pair (the first collaborative device and the second collaborative device), divide the abnormal case set, construct a first collaborative device abnormal case set that contains all cases where the first collaborative device has an abnormal state, and record the processing state of the second collaborative device in these cases; construct a second collaborative device abnormal case set that contains all cases where the second collaborative device has an abnormal state, and record the processing state of the first collaborative device in these cases. It further includes step S1142 of calculating the synchronous support degree between the abnormal state and the processing state respectively according to the first collaborative device abnormal case and the second collaborative device abnormal case to obtain the state influence correlation degree. The synchronous support degree refers to the frequency or probability that when one device (such as the first collaborative device) is in an abnormal state, another device (such as the second collaborative device) is in a specific processing state (such as normal, idle, standby, etc.). According to the calculation result of the synchronous support degree, different weights are assigned to different processing states, and the state influence correlation degree is obtained by weighted calculation. For example, if it is considered that when the first collaborative device is abnormal, the influence of the second collaborative device being in the normal state is small, while the influence of being in the idle or standby state is large, then higher weights can be assigned to the idle and standby states, and then the weighted average is calculated as the state influence correlation degree.

[0025] In a possible implementation, step S1142 further includes step S1143 of fitting a first synchronous support degree between the processing state of the second collaborative device and the abnormal state of the first collaborative device according to the first collaborative device abnormal case. The first synchronous support degree represents the probability that the second collaborative device is in a certain processing state when the first collaborative device is in a specific abnormal state. For each abnormal state of the first collaborative device, the frequencies of the second collaborative device being in different processing states (such as normal, idle, standby, etc.) are counted, and the first synchronous support degree between the processing state of the second collaborative device and the abnormal state of the first collaborative device is calculated. It further includes step S1144 of fitting a second synchronous support degree between the processing state of the first collaborative device and the abnormal state of the second collaborative device according to the second collaborative device abnormal case. The second synchronous support degree represents the probability that the first collaborative device is in a certain processing state when the second collaborative device is in a specific abnormal state. For each abnormal state of the second collaborative device, the frequencies of the first collaborative device being in different processing states (such as normal, idle, standby, etc.) are counted, and the second synchronous support degree between the processing state of the first collaborative device and the abnormal state of the second collaborative device is calculated. It further includes step S1145 of obtaining the state influence correlation degree by averaging the calculation using the first synchronous support degree and the second synchronous support degree.

[0026] Step S200: Based on the processing flow nodes and equipment collaboration relationships, conduct condition monitoring and identification on the equipment of each processing flow node, and output a status monitoring data block for the equipment of each node. The status monitoring data block includes an equipment monitoring data set, a processing flow node identifier, and a collaboration relationship identifier. Based on the rubber manufacturing process flow and equipment collaboration relationships, monitor and identify the equipment of each processing flow node. Each node's equipment corresponds to a status monitoring data block, and each status monitoring data block includes an equipment monitoring data set, a processing flow node identifier, and a collaboration relationship identifier. For example, the equipment in the raw material preparation stage is a rubber cutting machine and an oven. The monitoring data set includes the temperature record and time for softening raw rubber, rubber cutting size data, etc. The status monitoring data block includes the equipment monitoring data set (oven temperature curve, rubber cutting size), the processing flow node identifier (raw material preparation), and the collaboration relationship identifier (associated with the mixing equipment); the equipment in the plasticating stage is a rubber mixing mill, and the status monitoring data block includes the equipment monitoring data set (plasticating temperature curve, roller speed data, etc.), the processing flow node identifier (plasticating), and the collaboration relationship identifier (closely collaborating with the mixing equipment); the equipment in the mixing stage is a mixer, and the status monitoring data block includes the equipment monitoring data set (mixing temperature curve, pressure change data, speed data, etc.), the processing flow node identifier (mixing), and the collaboration relationship identifier (associated with the molding equipment and vulcanizing equipment); the equipment in the molding stage is a molding machine, a mold, etc., and the status monitoring data block includes the equipment monitoring data set (molding pressure curve, temperature data, etc.), the processing flow node identifier (molding), and the collaboration relationship identifier (associated with the vulcanizing equipment); the equipment in the vulcanizing stage is a vulcanizer, and the status monitoring data block includes the equipment monitoring data set (vulcanizing temperature curve, pressure data, etc.), the processing flow node identifier (vulcanizing), and the collaboration relationship identifier (associated with the post-processing equipment); the equipment in the post-processing stage is a trimming machine, a cleaning machine, etc., and the status monitoring data block includes the equipment monitoring data set (trimming size data, cleaning time, etc.), the processing flow node identifier (post-processing), and the collaboration relationship identifier (associated with the finished product inspection and packaging equipment). In each status monitoring data block, the collaboration relationship identifier clarifies the position and role of the equipment in the entire rubber manufacturing process flow, as well as its association relationship with other equipment.

[0027] Step S300: Based on the processing flow node identifier and the collaboration relationship identifier, perform equipment anomaly identification according to the equipment monitoring data set to obtain the anomaly information of each node device. By collecting and analyzing the operation data of each node device in the rubber manufacturing process, combined with the specific requirements of the nodes and the collaboration relationship between the devices, to detect and identify possible abnormal situations of the devices. Specifically, according to the normal operation parameters and historical data of the devices, set the anomaly thresholds for each monitoring parameter, and compare the data in the equipment monitoring data set with the set anomaly thresholds. If the monitoring data does not meet the set thresholds, it indicates that there is an abnormal situation with the device. According to the processing flow node identifier and the collaboration relationship identifier, combined with the real-time monitoring data, identify the specific abnormal devices and abnormal types. For example, during the mixing process, if the temperature data of the mixer increases abnormally and exceeds the set threshold, it may indicate that the mixer has an overheating fault. Finally, obtain the anomaly information of each node device, including abnormal devices, abnormal types, abnormal times, abnormal parameters, etc.

[0028] In a possible implementation, step S300 further includes step S310 of identifying the operating parameters of each device through a preset device anomaly recognition model to obtain an anomaly recognition result. The preset device anomaly recognition model is a mathematical model that can identify and process the abnormal operating state of a device, which is obtained by constructing a labeled training data set through historical cases and converging through supervised training. It also includes step S320 of determining the device processing rate ratio based on the processing flow node identifier and the collaboration relationship identifier. For each processing flow node (i.e., device), its processing data is collected, including actual processing time, theoretical processing time, processing quantity, processing quality, etc. The device processing rate refers to the amount of processing that a device can complete per unit time. Among them, the processing quantity is the number or weight of products processed per unit time, and the processing time is the actual processing time. After determining the processing rate of each device, the processing rate ratio between devices is further calculated. By comparing the processing rate ratios of different devices, their relative processing efficiency in the entire production process can be understood. It also includes step S330 of analyzing the operating states of collaborative devices respectively according to the device monitoring data set to determine the operating processing speed. Analyze the mutual influence and dependence relationship between them according to the device monitoring data set, evaluate and predict the operating state of the device, and calculate the processing speed of the device. For collaborative devices, the processing speed may affect each other. For example, in a production line, if the processing speed of a certain device is too slow, it may cause an increase in the waiting time of subsequent devices, thus affecting the efficiency of the entire production line. It also includes step S340 of calculating the ratio using the respective operating processing speeds of the collaborative devices and comparing it with the device processing rate ratio. When the tolerance threshold is not met, collaborative anomaly information is generated. The tolerance threshold is the threshold at which the device processing rate ratio meets the manufacturing processing requirements of the processing flow node within the maximum error range. The tolerance threshold is a range of allowable errors, indicating the range within which the device processing rate ratio can vary and still be considered to meet the manufacturing processing requirements of the processing flow node. If the ratio of the operating processing speeds of the collaborative devices exceeds the tolerance threshold, that is, the difference between the actual performance and the expected performance exceeds the allowable range, the system will generate collaborative anomaly information, which may include specific device identifiers, the time of anomaly occurrence, the type of anomaly (such as too slow speed, too fast speed, etc.), and possible reasons, etc. It also includes step S350 of combining the anomaly recognition result and the collaborative anomaly information to generate the anomaly information of each node device. Anomaly recognition includes the anomaly recognition of individual devices and the anomaly recognition of collaboration relationships. The normal speed ratio relationship between the processing of collaborative devices, that is, whether there is an anomaly in the proportional relationship between the two is identified through the operating states of the collaborative devices.

[0029] Step S400: Based on the abnormal information, perform an abnormal impact analysis according to the process connection relationship of the processing flow nodes and the equipment collaboration relationship, to obtain the abnormal processing flow nodes and their abnormal impact degrees. The abnormal impact degree includes the node abnormal impact degree and the overall process abnormal impact degree. The abnormal impact analysis is to further evaluate the impact of these abnormalities on the processing flow nodes and the entire production process after identifying the equipment abnormal information in the rubber manufacturing process. Specifically, according to the equipment abnormal information, determine the processing flow nodes where abnormalities occur, evaluate the process connection relationship between the abnormal nodes and their upstream and downstream nodes, identify potential problems such as raw material backlog in upstream nodes or production obstruction in downstream nodes caused by the abnormal nodes, and then perform an abnormal impact analysis in combination with the equipment collaboration relationship. That is, according to factors such as the production importance, fault duration, and influence range of the abnormal nodes, calculate the node abnormal impact degree, which represents the impact of the abnormality of this node on the entire production process; consider the position and role of the abnormal node in the entire production process, evaluate its impact on the overall process, calculate the overall process abnormal impact degree, and consider multiple factors such as production efficiency loss, product quality impact, delivery date delay, etc. For example, calculate the sum of the abnormal impact degrees of multiple nodes through the weighted average method to represent the overall impact on the entire production process due to equipment abnormalities.

[0030] Step S500: Locate the target optimization parameters according to the node abnormal impact degree and the overall process abnormal impact degree. Identify the key abnormal nodes with higher impact degrees according to the node abnormal impact degree, and deeply analyze the causes of the abnormalities in the key abnormal nodes, such as equipment failures, raw material problems, operation errors, etc. Determine the specific factors leading to the abnormalities by collecting and analyzing relevant equipment monitoring data sets, operation records and other information; evaluate the overall impact on the entire production process due to the abnormalities according to the overall process abnormal impact degree, analyze the composition of the overall process abnormal impact degree, and identify the key influencing factors that contribute more to the overall impact degree, such as equipment collaboration relationship, raw material supply stability, operation specification execution situation, etc. According to the analysis of the node abnormal impact degree and the overall process abnormal impact degree, determine the main direction of optimization. For example, if equipment failure is the main cause of the abnormality, then the optimization direction may include improving equipment reliability, improving maintenance strategies, etc. After determining the optimization direction, select specific optimization parameters, which may include equipment parameters (such as temperature, pressure, rotation speed, etc.), operation parameters (such as operation time, operation sequence, etc.), management parameters (such as maintenance cycle, quality standard, etc.).

[0031] In a possible implementation, step S500 further includes step S510 of tracing the node association parameters according to the node anomaly influence degree. In rubber manufacturing and processing production, when an anomaly occurs in a certain node device (a certain link of the device or production process), the degree of influence of the anomaly on other node devices or the entire production process is analyzed and traced to determine the parameters or factors associated with the anomalous node. It also includes step S520 of tracing the full-process associated process nodes and corresponding association parameters according to the full-process anomaly influence degree. After determining the anomalous node, it is necessary to analyze the position and role of the node in the entire process, as well as its association relationship with other nodes. Through process analysis, other process nodes associated with the anomalous node can be identified, including downstream nodes directly affected by the anomalous node, and also nodes indirectly affected through other channels. For each associated process node, it is necessary to evaluate the degree of its being affected by the anomalous node. For each associated process node, it is necessary to identify the process parameters or factors associated with it, analyze the association relationship between these parameters and the associated process nodes, understand which parameter changes may affect the associated process nodes, as well as their causal relationship and correlation. It also includes step S530 of configuring the weights of the node association parameters, the full-process associated process nodes and the corresponding association parameters with their respective anomaly influence degrees. According to the degree of influence of each node or process node on the entire process in case of an anomaly, that is, the anomaly influence degree, different weights are assigned to the weights of the node association parameters, the full-process associated process nodes and the corresponding association parameters. It also includes step S540 of positioning the target optimization parameter based on the weight, where the target optimization parameter is a parameter whose weight reaches the influence threshold. The influence threshold is a predefined value used to determine whether the weight of a certain parameter has reached the level that requires optimization or adjustment. By comparing the weight of each parameter with the set influence threshold, the target optimization parameter that has reached the level that requires optimization can be determined. After determining the target optimization parameter, corresponding optimization strategies are formulated, for example, adjusting the value of the parameter, changing the adjustment strategy of the parameter, adding or deleting certain parameters, etc.

[0032] Step S600: Optimize according to the target optimization parameters, their corresponding node anomaly influence relationships, and the whole-process anomaly influence relationships to obtain device control information. For the identified key anomaly nodes and key influencing factors in the whole process, through a series of optimization algorithms, find the best parameter settings or operation strategies, so as to effectively control the device, improve production efficiency and product quality. Specifically, according to the analysis results, clarify the specific optimization objectives, such as improving production efficiency, reducing failure rates, and enhancing product quality. According to the actual situation of rubber manufacturing and processing, set reasonable constraint conditions, such as the value range of device parameters and the limit of operation time. Initialize the values of the target optimization parameters, perform iterative calculations on the target optimization parameters to find the optimal solution. After each iteration, evaluate whether the optimization results meet the constraint conditions and optimization objectives. Finally, obtain a set of optimal target optimization parameter combinations, convert the optimal parameter combinations into specific device control instructions, such as adjusting device parameters and optimizing operation processes, and implement the control of the device.

[0033] Based on the foregoing embodiments, the embodiments of the present application further provide an electronic device and a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of the electronic device, it can implement the method described in any previous embodiment.

[0034] Figure 3 It is a schematic structural diagram of the electronic device provided by the embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiment of the present invention. Figure 3 The displayed electronic device is only an example and should not bring any limitations to the functions and usage scopes of the embodiments of the present invention. The electronic device is presented in the form of a general computing device, and its components may include, but are not limited to, an input device 401, a processor 402, a memory 403, and an output device 404. Among them, the processor 402 may be one or more; the memory 403 may include a computer-readable medium and at least one program product, and this program product has a set (at least one) of program modules, and these program modules are configured to execute the functions of the embodiments of the present application.

[0035] The memory 403 shown in the embodiments of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be, but is not limited to, infrared rays, semiconductor systems, devices or components, or any combination of the above, for storing software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to a rubber manufacturing and processing intelligent management method in the embodiments of the present invention. The processor 402 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 403, that is, implements the above-mentioned rubber manufacturing and processing intelligent management method.

[0036] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A rubber manufacturing and processing intelligent management method, characterized in that: The method comprises: Decompose the rubber manufacturing process nodes, perform equipment collaborative analysis on the process nodes, and establish equipment collaborative relationships; Based on the processing flow nodes and equipment collaborative relationships, the equipment at each processing flow node is monitored and identified for working conditions, and a status monitoring data block of each node equipment is output, wherein the status monitoring data block includes an equipment monitoring data set, a processing flow node identifier, and a collaborative relationship identifier; Based on the processing flow node identifier and the collaborative relationship identifier, equipment abnormality identification is performed according to the equipment monitoring data set to obtain abnormal information of each node equipment; According to the abnormal information, an abnormal impact analysis is performed according to the process connection relationship of the processing flow node and the equipment coordination relationship to obtain abnormal processing flow nodes and their abnormal impacts, wherein the abnormal impacts include node abnormal impacts and whole process abnormal impacts; According to the node abnormality impact and the whole process abnormality impact, locate the target optimization parameters; The target optimization parameters and their corresponding node abnormality impact relationships and full-process abnormality impact relationships are optimized to obtain equipment control information.

2. A rubber manufacturing and processing intelligent management method as claimed in claim 1, characterized in that: Performing equipment collaborative analysis on the processing flow nodes and establishing equipment collaborative relationships includes: Conduct correlation analysis on the processing equipment in each processing flow node, including operation sequence correlation analysis and state impact correlation analysis; Determine the collaborative device by using the operation sequence correlation and the state impact correlation, wherein the collaborative device is processing equipment information whose operation sequence correlation and the state impact correlation both reach a preset threshold; The collaborative influence relationship between the collaborative devices is established as the device collaborative relationship, and the device collaborative relationship has a correlation identifier, wherein the correlation identifier is calculated and generated according to the runtime correlation and the state influence correlation.

3. A rubber manufacturing and processing intelligent management method as claimed in claim 2, characterized in that: The correlation analysis of the processing equipment in each processing flow node includes: Using adjacent time-series processes as screening conditions, screening the processing equipment in each processing process node to establish time-series continuous equipment pairs; Acquire the processing interval time of the sequentially continuous device pair, perform timing correlation conversion according to the processing interval time, and obtain the operation timing correlation, wherein the smaller the processing interval time, the greater the operation timing correlation; Based on the time-series continuous device pairs, obtaining an abnormal case set; According to the abnormal case set, a state abnormality correlation analysis is performed on the time-series continuous device pair to obtain the state impact correlation.

4. A rubber manufacturing and processing intelligent management method as claimed in claim 3, characterized in that: Performing state anomaly correlation analysis on the sequential continuous device pair according to the anomaly case set to obtain the state impact correlation includes: Taking the time-series continuous device pairs as targets respectively, the abnormal case set is divided to construct a first collaborative device abnormal case and a second collaborative device abnormal case, wherein the first collaborative device and the second collaborative device are the time-series continuous device pairs, wherein the first collaborative device abnormal case includes an abnormal state of the first collaborative device and a processing state of the second collaborative device, and the second collaborative device abnormal case includes an abnormal state of the second collaborative device and a processing state of the first collaborative device; According to the first collaborative device abnormality case and the second collaborative device abnormality case, the synchronization support degree of the abnormal state and the processing state is calculated to obtain the state impact correlation.

5. A rubber manufacturing and processing intelligent management method as claimed in claim 4, characterized in that: Obtaining the state impact relevance includes: According to the abnormal case of the first collaborative device, fitting a first synchronization support degree of the processing state of the second collaborative device and the abnormal state of the first collaborative device; According to the abnormal case of the second collaborative device, fitting a second synchronization support degree of the processing state of the first collaborative device and the abnormal state of the second collaborative device; The state impact correlation is obtained by averaging the first synchronization support and the second synchronization support.

6. A rubber manufacturing and processing intelligent management method as claimed in claim 1, characterized in that: Based on the processing flow node identifier and the collaborative relationship identifier, equipment abnormality identification is performed according to the equipment monitoring data set to obtain abnormal information of each node equipment, including: The operation parameters of each device are identified by a preset device abnormality identification model to obtain an abnormality identification result. The preset device abnormality identification model is a mathematical model that can identify and process abnormal operation states of the device by constructing a labeled training data set through historical cases and converging through supervised training; Determining a device processing rate ratio based on the processing flow node identifier and the collaborative relationship identifier; Analyze the operation status of the collaborative equipment respectively according to the equipment monitoring data set to determine the operation processing speed; The ratio is calculated by using the respective operating processing speeds of the collaborative equipment and compared with the equipment processing rate ratio. When the tolerance threshold is not met, collaborative abnormality information is generated. The tolerance threshold is the threshold at which the equipment processing rate ratio meets the manufacturing processing requirements of the processing flow node within the maximum error range. The abnormality identification result and the coordinated abnormality information are combined to generate the abnormality information of each node device.

7. A rubber manufacturing and processing intelligent management method as claimed in claim 1, characterized in that: According to the node abnormality impact and the whole process abnormality impact, the target optimization parameters are located, including: Tracing node association parameters according to the node abnormality impact; According to the abnormal impact of the whole process, the whole process is traced back to the process nodes and corresponding associated parameters; The node association parameters, the whole process association process nodes and the weights of the corresponding association parameters are configured according to their respective abnormal impacts; The target optimization parameter is located based on the weight, and the target optimization parameter is a parameter whose weight reaches an influence threshold.

8. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the intelligent management method for rubber manufacturing and processing as described in any one of claims 1 to 7 when executing the executable instructions stored in the memory.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a rubber manufacturing and processing intelligent management method as described in any one of claims 1 to 7 is implemented.

Images