Safety production processing equipment information data management method and system

Abstract

The invention relates to the technical field of data management, in particular to a safety production and processing equipment information data management method and system, and the method comprises the steps: analyzing the trend intensity difference of all pieces of operation data between each piece of equipment and all other pieces of equipment within a preset duration before the current moment, and determining an abnormal discrimination value; determining a first characteristic value by analyzing the distance between different fitting points in each cluster under each operation data; determining a second characteristic value based on the distance between all adjacent inflection points on the fitted curve of each operation data, and determining a comprehensive characteristic value by combining the first characteristic value; and determining an abnormal discrimination coefficient based on the abnormal discrimination value and the comprehensive characteristic value, and managing information data of all equipment in the safety production and processing process. The invention aims to timely identify and process potential abnormity of equipment in the production process and improve the stability and efficiency of the vulcanization process in tire production.

Description

Technical Field

[0001] The present application relates to the technical field of data management, and in particular to a method and system for managing information data of safe production and processing equipment. Background Art

[0002] With the continuous development and progress of industrial control technology, factories have higher and higher requirements for the intelligence and informationization of equipment. Therefore, it is of great significance for production and processing enterprise users to carry out all-round and three-dimensional information and data management of industrial equipment, collect equipment data, store equipment information, and timely grasp the operating status of equipment. Among them, using the equipment information data management system to monitor the abnormal status of production equipment is one of the important applications at present.

[0003] In the tire production process, vulcanization is one of the important production processes. It can not only improve the mechanical properties and thermal stability of the tire, but also ensure the stability of the size and shape of the tire. Therefore, tire manufacturers will strictly control the vulcanization process parameters of the tire. If the vulcanization temperature, pressure or time is not properly controlled during the tire vulcanization process, there may be problems such as uneven tire vulcanization and vulcanization flash, which will lead to unstable tire performance and affect the appearance and dimensional accuracy of the tire. Therefore, monitoring and controlling the relevant parameters of the vulcanizer is one of the important methods to ensure tire quality.

[0004] At present, how to use the equipment information data management system to monitor the minor abnormal conditions of production and processing equipment has become a research hotspot. In the actual production process, when some processing parameters of the production equipment have slight abnormalities, it is difficult to detect during detection. The traditional method sets multiple thresholds to determine whether the equipment has potential defects. However, this method has certain defects. For example, taking tire production as an example, for tire production lines, there are many production equipment, large differences in automation, and complex processes. In addition, a factory may have more than one production line, and the types and sizes of tires produced may be different. Different production environments and seasons may also affect the parameter settings of production equipment. Therefore, the method of setting multiple thresholds alone may be difficult to adapt to various production conditions, reducing the stability and efficiency of the vulcanization process in tire production. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of this application is to provide a method and system for managing information data of safe production processing equipment. The technical solutions adopted are as follows: In a first aspect, an embodiment of the present application provides a method for managing information data of safe production processing equipment, the method comprising the following steps: S1: Real-time collection of various operating data of each device during the vulcanization process of tire production; S2: Fitting various operation data of each device within a preset time before the current moment, counting the number of all inflection points on the fitting curve of various operation data, and analyzing the difference in the trend intensity of various operation data between each device and all other devices within the preset time before the current moment, and determining the abnormal discrimination value of various operation data in each device at the current moment; S3: Clustering all fitting points on the fitting curve of each item of operation data of each device, and determining the first eigenvalue of each item of operation data in each device by analyzing the distance between different fitting points in each cluster under each item of operation data; determining the second eigenvalue of each item of operation data in each device based on the distance between all adjacent inflection points on the fitting curve of each item of operation data, and determining the comprehensive eigenvalue of each item of operation data in each device at the current moment in combination with the first eigenvalue; S4: Based on the abnormal discrimination value and the comprehensive characteristic value, determine the abnormal discrimination coefficient of each operation data in each device at the current moment, and manage the information data of all devices in the safe production processing process.

[0006] Preferably, the operating data at least includes: pressure data, temperature data, power data and vibration data.

[0007] Preferably, the method for determining the abnormality discrimination value of each operation data in each device at the current moment is: The differences in the trend strength of each operating data between each device and all other devices are averaged, and the differences in the total number of inflection points on the fitting curves of each operating data between each device and all other devices are averaged, and they are recorded as the first mean and the second mean respectively; The abnormality judgment value of each item of operating data in each device is the product of the first mean value and the second mean value of each item of operating data in each device.

[0008] Preferably, all fitting points on the fitting curve of each item of operating data of each device are clustered: the metric distance of the clustering algorithm in the clustering process is the Euclidean distance between different fitting points.

[0009] Preferably, the method for determining the first characteristic value of each item of operating data in each device is: For each item of operating data in each device, the mean of the distances between all fitting points in each cluster is calculated, recorded as the distance mean, and the cumulative result of the distance means of all clusters is taken as the first eigenvalue of each item of operating data in each device.

[0010] Preferably, the second characteristic value of each item of operating data in each device is the average value of the distances between all adjacent inflection points on the fitting curve of each item of operating data in each device.

[0011] Preferably, the comprehensive characteristic value of each item of operating data in each device at the current moment is the reciprocal of the sum of the first characteristic value and the second characteristic value of each item of operating data in each device.

[0012] Preferably, the expression of the abnormal discrimination coefficient of each operation data in each device at the current moment is: ; In the formula, represents the abnormal discrimination coefficient of the jth item of operating data in equipment i at the current moment; Indicates the abnormality judgment value of the jth item of operating data in device i at the current moment; Represents the comprehensive characteristic value of the j-th operating data in device i at the current moment.

[0013] Preferably, the management of information data of all equipment in the safe production process includes: The abnormal discrimination coefficients of the operation data of all devices at the current moment are used as the input of the threshold segmentation algorithm, and the segmentation thresholds of the operation data are output; If the abnormal discrimination coefficient of any item of operation data of device i at the current moment is greater than the segmentation threshold of the corresponding item of operation data, then device i is abnormal. At this time, the information data of device i is obtained, and the information data of device i is sent to the staff to repair device i. In the second aspect, the embodiment of the present application also provides a safe production and processing equipment information data management system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned safe production and processing equipment information data management methods are implemented.

[0014] This application has at least the following beneficial effects: This application constructs an abnormal discrimination value by analyzing the difference in the trend of the same operating data between different vulcanizers during the tire production process, which can more accurately monitor the minor abnormalities that occur during the operation of the equipment, and can help identify potential abnormal signs before the equipment fails, thereby reducing the losses caused by equipment failure and improving the stability and efficiency of the tire production process; further, by analyzing the distribution balance of each operating data in each device, a comprehensive characteristic value is constructed, which can further improve the stability of the production process and better adapt to the production environment that combines process manufacturing and discrete manufacturing; further, the abnormal discrimination value and the comprehensive characteristic value are integrated to construct an abnormal discrimination coefficient, which can reduce the downtime caused by equipment failure by timely identifying and handling potential abnormalities, and improve the overall production efficiency and stability. This application analyzes the changes in multiple operating data in the equipment, timely identifies and handles potential abnormalities of the equipment during the production process, and improves the stability and efficiency of the vulcanization process in tire production. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A flowchart of a method for managing information data of safe production and processing equipment provided in one embodiment of the present application; Figure 2 A schematic diagram of an abnormality discrimination coefficient extraction process provided for one embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of a method and system for managing information data of safe production and processing equipment proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0019] The following is a detailed description of a specific solution of a safe production processing equipment information data management method and system provided by the present application in conjunction with the accompanying drawings.

[0020] See also Figure 1 , which shows a flowchart of a method for managing information data of safe production and processing equipment provided by an embodiment of the present application, the method comprising the following steps: S1: Real-time collection of operating data of each device during the vulcanization process in tire production.

[0021] Vulcanization is one of the important processes in the tire production process to ensure tire performance, size and appearance. If the equipment information data management system cannot detect slight abnormalities in the vulcanizer parameters, it may cause uneven vulcanization and vulcanization flash during tire vulcanization, thereby affecting the quality of tire production. Therefore, this implementation collects and analyzes the pressure, temperature, power and vibration data of the vulcanizer on the production line.

[0022] In this embodiment, taking the tire production process as an example, through the Internet of Things sensing technology, each processing equipment on the production line is regarded as a monitoring point, wherein each monitoring point corresponds to a single operating equipment on the production line, thereby obtaining various operating data of each monitoring point in real time, the data sampling frequency is f, and the operating data at least includes: pressure data, temperature data, power data, vibration data and other parameter information. At the same time, the collected data is uploaded to the equipment information data management system, the information data management system first converts the received data into the corresponding format, and connects to the equipment information database, inserts the converted data into data, and finally checks the integrity of the inserted data to complete the data insertion into the database.

[0023] It should be noted that the value of the data sampling frequency f is artificially set. In this embodiment, the value of the data sampling frequency f is 1 Hz. The implementer can also set it by himself according to the specific situation. This embodiment does not impose any special restrictions.

[0024] S2: Fit the various operating data of each device within the preset time before the current moment, count the number of all inflection points on the fitting curve of each operating data, and analyze the change trend of each operating data of each device within the preset time before the current moment, and determine the abnormal discrimination value of each operating data in each device at the current moment.

[0025] During normal tire production and processing, there are many sizes and types of tires, so there will be multiple production lines in a factory. The equipment on multiple production lines is the same but the parameter settings are different. Therefore, the same operating data collected by the same equipment on multiple production lines will have certain size differences, but the change trend of the same operating data is relatively similar each time the processing is performed. For example: in the normal production process, the pressure data is first quickly increased to the required pressure, and the pressure is maintained until the pressure returns to the initial level after the vulcanization is completed. When the equipment has a slight abnormality, the speed of the pressure change will deviate to a certain extent, and the pressure may not be maintained at the same pressure throughout the vulcanization process due to slight abnormalities in the process of maintaining the pressure level.

[0026] Similarly, in normal production, the temperature data also shows that the temperature rises rapidly to the set temperature first, then remains constant during processing, and gradually cools down after processing is completed; the power consumption of the equipment should show a certain regularity, such as power increases during processing and power decreases during standby; in addition, the vibration of the equipment should be kept within a stable range. Different processing stages may cause changes in vibration intensity, but the overall trend should remain consistent; when the equipment has a slight abnormality, the temperature change rate may deviate; the regularity of power consumption may be disrupted, manifested as power fluctuations; and the vibration intensity may fluctuate abnormally, or the vibration frequency may change.

[0027] Therefore, when an abnormality occurs in a device, the change trend of the same operation data between different devices will be quite different. Therefore, by analyzing the change trend of each operation data in each device, the abnormality discrimination value is determined to determine whether the device has an abnormality. The specific process is as follows: the operation data of each device within the preset time before the current moment is used as the input of the time series decomposition algorithm, and the trend strength of each operation data is output.

[0028] The difference in the trend strength of each operating data between each device and all other devices is averaged and recorded as the first mean of each operating data in each device.

[0029] It should be noted that there are many commonly used time series decomposition algorithms. In this embodiment, the STL decomposition algorithm is used to analyze the trend of pressure data. In actual application, as other implementation methods, the implementer may also use other methods such as the SEATS decomposition method. Regarding the selection of the time series decomposition algorithm, this embodiment does not make any special restrictions.

[0030] Among them, the STL decomposition algorithm is a well-known technology, and its specific principle process will not be repeated here.

[0031] Furthermore, the operation data of each device within a preset time before the current moment are fitted to obtain a fitting curve of each operation data, and an inflection point detection algorithm is used to extract all inflection points on the fitting curve, and the number of all inflection points on the fitting curve of each operation data is counted.

[0032] It is additionally noted that the value of the preset time length is manually set. In this embodiment, the value of the preset time length is 5 minutes. The implementer may also set it by himself according to the specific situation. This embodiment does not impose any special restrictions.

[0033] It should be understood that there are many methods for curve fitting, such as: least squares method, polynomial function fitting, linear regression fitting, etc.; as an implementation method, the least squares method is used in this embodiment to fit various operating data. In actual application, as other implementation methods, the implementer may also use other fitting methods such as polynomial function fitting or linear regression fitting. Regarding the selection of curve fitting method, this embodiment does not impose any special restrictions.

[0034] In addition, regarding the selection of inflection point detection algorithm, the second-order derivative method is used in this embodiment to extract the inflection point on the fitting curve. In actual application, as other implementation methods, the implementer can also select a suitable method from a variety of methods such as sliding window method, Pelt algorithm or statistical-based method. Regarding the selection of inflection point detection algorithm, this embodiment does not impose too many restrictions.

[0035] Among them, the least square fitting and the second-order derivative method are both well-known technologies, and their specific implementation processes are not repeated here.

[0036] Furthermore, the difference in the total amount of inflection points on the fitting curves of the various operating data between each device and all other devices is averaged, and recorded as the second mean of the various operating data in each device; The abnormality judgment value of each item of operating data in each device is the product of the first mean value and the second mean value of each item of operating data in each device.

[0037] It should be noted that there are many methods for measuring the differences between data. In this embodiment, the method of taking the absolute value of the difference is adopted to calculate the difference in trend intensity between each device and all other devices, as well as the difference in the total number of inflection points between each device and all other devices. In actual application, as other implementation methods, the implementer may also adopt other methods for measuring the differences between data, such as the square or ratio of the difference. Regarding the selection of the method for measuring the differences between data, this embodiment does not impose any special restrictions.

[0038] Furthermore, by analyzing the abnormal discrimination values ​​of each operation data in each device, it can be obtained that: if the difference in the trend intensity between the current device and the other devices regarding the same operation data is greater, that is, the first mean is greater, it means that the difference in the change trend of the same operation data between different devices is greater, and the abnormal discrimination value is greater; and if the difference in the number of inflection points between the current device and the other devices regarding the same operation data is greater, that is, the second mean is greater, it indirectly means that the difference in the change trend of the same operation data between different devices is greater, then the abnormal discrimination value is greater, and the current device is more likely to have an abnormality; On the contrary, if the difference in trend intensity between the current device and the other devices regarding the same operating data is smaller, that is, the first mean is smaller, it means that the difference in the changing trend of the same operating data between different devices is smaller, and the abnormal discrimination value is smaller; and if the difference in the number of inflection points between the current device and the other devices regarding the same operating data is smaller, that is, the second mean is smaller, it indirectly means that the difference in the changing trend of the same operating data between different devices is smaller, then the abnormal discrimination value is smaller, and the possibility of abnormality in the current device is smaller.

[0039] At this point, by analyzing the differences in the changing trends of the same operating data between different devices, the abnormal discrimination values ​​of each operating data in each device are obtained.

[0040] S3: Cluster all fitting points on the fitting curve of each item of operating data of each device, and determine the first eigenvalue of each item of operating data in each device by analyzing the distance between different fitting points in each cluster under each item of operating data; determine the second eigenvalue of each item of operating data in each device based on the distance between all adjacent inflection points on the fitting curve of each item of operating data, and determine the comprehensive eigenvalue of each item of operating data in each device at the current moment in combination with the first eigenvalue.

[0041] Since tire production and processing involves many complex processes, and the time required for each process varies, tire production and processing is usually a combination of process manufacturing and discrete manufacturing. Therefore, there may be a situation where a process with a shorter time has to wait for the semi-finished product of the process with a longer time to be produced before it can continue processing, or there may be a situation where only some processes have semi-finished products for processing, while the other parts have no semi-finished products for processing. For example, the first process before tire vulcanization is tire molding. The tire molding requires first curling the cut cord into a cylindrical shape to form the main structure of the tire, and then pasting the sidewall rubber, shoulder rubber, tread rubber and other components to the tire body in turn to form a complete tire embryo. Finally, the appearance and quality of the tire embryo must be checked to ensure that there are no bubbles, wrinkles or component misalignment. The entire tire forming process takes a long time, and it takes a long time to produce semi-finished tires (i.e., a long process), while tire vulcanization only requires placing the formed tire embryo into the mold of the vulcanizer, vulcanizing it under high temperature and high pressure, and finally cooling it to complete the process, which takes a short time (i.e., a short process). Therefore, it is possible that the semi-finished tires produced during the tire forming stage are not enough to supply all vulcanizers, resulting in a situation where some vulcanizers are working while others are on standby. Judging equipment abnormalities only by the above method may lead to deviations in judgment due to the above situation, so further analysis is needed.

[0042] For the same equipment used for production and processing, the pressure parameters required for each processing on a normal production line are the same. Therefore, during the continuous processing, the pressure changes from a fixed initial value to a set value, and then decreases to the initial value after maintaining the set value for a period of time. In this process, the pressure change speed of each processing of the same equipment is similar, and the holding time is similar. Therefore, under normal circumstances, the pressure data collected by the equipment is relatively evenly distributed. Similarly, during normal production, the temperature data, power data, and vibration data of the same equipment are all relatively evenly distributed.

[0043] Therefore, by analyzing the distribution of various operating data in each device and determining the comprehensive characteristic value, it is possible to determine whether the device has any abnormality, specifically: All fitting points on the fitting curve of each operation data of each device are clustered to obtain multiple clusters of each operation data. In the clustering process, the Euclidean distance between different fitting points is used as the metric distance in the clustering algorithm during the clustering process.

[0044] In this embodiment, the DBSCAN clustering algorithm is used to cluster all fitting points on the fitting curve. In actual application, as other implementation methods, the implementer can also adopt other clustering algorithms according to specific circumstances, such as DPC density peak clustering algorithm, k-means clustering algorithm or fuzzy C-means clustering algorithm and other algorithms. Regarding the selection of clustering algorithm, this embodiment does not impose any special restrictions.

[0045] Among them, the calculation method of Euclidean distance and the DBSCAN clustering algorithm are both well-known technologies, and the calculation process of Euclidean distance and the specific clustering principle of the DBSCAN clustering algorithm are not described in detail.

[0046] Furthermore, for each item of operating data in each device, the mean of the distances between all fitting points in each cluster is calculated, recorded as the distance mean, and the cumulative result of the distance means of all clusters is used as the first eigenvalue of each item of operating data in each device.

[0047] The average value of the distances between all adjacent inflection points on the fitting curve of each item of operating data in each device is taken as the second eigenvalue of each item of operating data in each device.

[0048] The comprehensive characteristic value of each item of operating data in each device is the reciprocal of the sum of the first characteristic value and the second characteristic value of each item of operating data in each device.

[0049] It should be noted that in this embodiment, the distance between the fitting points in the first eigenvalue calculation process adopts the Euclidean distance, and the distance between the inflection points in the second eigenvalue calculation process also adopts the Euclidean distance. In actual application, as other implementation methods, the implementer may also adopt other methods such as DTW distance or Manhattan distance. Regarding the selection of distance calculation method, this embodiment does not make any special restrictions.

[0050] Further, according to the comprehensive characteristic value of each item of operation data in each device, it can be understood that: if the distance between the fitting points in each cluster of the j-th item of operation data in the current device is smaller, that is, the first characteristic value is smaller, it means that the difference between the data in the cluster is smaller, and the distribution of the j-th item of operation data is more balanced, then the comprehensive characteristic value is larger, indicating that the possibility of abnormality in the current device is smaller; and if the distance between adjacent inflection points on the fitting curve of the j-th item of operation data in the current device is smaller, it means that the degree of balance of the j-th item of operation data is higher, then the comprehensive characteristic value is larger, indicating that the possibility of slight abnormality in the current device is smaller; On the contrary, if the distance between the fitting points in each cluster of the j-th item of operating data in the current device is larger, that is, the first eigenvalue is larger, it means that the difference between the data in the cluster is larger, which means that the distribution of the j-th item of operating data is more balanced and the comprehensive eigenvalue is smaller, which means that the possibility of abnormality in the current device is greater; and if the distance between adjacent inflection points on the fitting curve of the j-th item of operating data in the current device is larger, it means that the degree of balance of the j-th item of operating data is lower, and the comprehensive eigenvalue is smaller, which means that the possibility of slight abnormality in the current device is greater.

[0051] At this point, by analyzing the balanced distribution of various operating data in each device, the comprehensive characteristic value of various operating data in each device is obtained.

[0052] S4: Based on the abnormal discrimination value and the comprehensive characteristic value, determine the abnormal discrimination coefficient of each operation data in each device at the current moment, and manage the information data of all devices in the safe production processing process.

[0053] The results of S2-S3 are integrated to derive the abnormality judgment coefficient used to measure the abnormal conditions of tire production and processing equipment. The specific relationship of the abnormality judgment coefficient is as follows: The abnormal discrimination coefficient of the jth operation data in the device i at the current moment The expression is: ; In the formula, Indicates the abnormality judgment value of the jth item of operating data in device i at the current moment; Represents the comprehensive characteristic value of the j-th operating data in device i at the current moment.

[0054] According to the abnormality discrimination coefficient of each operating data in each device at the current moment, it can be obtained that: if the abnormality discrimination value of the j-th operating data in device i at the current moment is larger, and the comprehensive characteristic value of the j-th operating data in device i at the current moment is smaller, then the abnormality discrimination coefficient of the j-th operating data in device i at the current moment is larger, indicating that the possibility of abnormality in device i at the current moment is greater; conversely, if the abnormality discrimination value of the j-th operating data in device i at the current moment is smaller, and the comprehensive characteristic value of the j-th operating data in device i at the current moment is larger, then the abnormality discrimination coefficient of the j-th operating data in device i at the current moment is smaller, indicating that the possibility of abnormality in device i at the current moment is smaller.

[0055] Preferably, the schematic diagram of the abnormality discrimination coefficient extraction process provided in this embodiment is as follows: Figure 2 shown.

[0056] Furthermore, the abnormal discrimination coefficients of various operation data of all equipment at the current moment are used as the input of the threshold segmentation algorithm, and the segmentation thresholds of various operation data are output; If the abnormal discrimination coefficient of any operating data of equipment i at the current moment is greater than the segmentation threshold of the corresponding operating data, then equipment i is abnormal. At this time, the information data of equipment i is obtained through the safe production processing equipment information data management system. The information data includes at least: equipment location, equipment number, equipment type, and historical operating data of the equipment. The information data and warning information of equipment i are sent to the staff to inspect and repair equipment i.

[0057] It should be noted that commonly used threshold segmentation algorithms include: Otsu threshold segmentation algorithm, histogram-based threshold segmentation algorithm or entropy-based threshold segmentation algorithm, etc. In this embodiment, Otsu threshold segmentation algorithm is used to obtain the segmentation threshold of the abnormal discrimination coefficient. In actual application, as other implementation methods, implementers may also adopt threshold segmentation methods such as histogram-based threshold segmentation algorithm or entropy-based threshold segmentation algorithm. Regarding the selection of threshold segmentation algorithm, this embodiment does not make any special restrictions.

[0058] Among them, the Otsu threshold segmentation algorithm is a well-known technology, and its specific principle process will not be repeated here.

[0059] So far, this embodiment has determined the abnormality discrimination coefficient by analyzing the parameter change trend characteristics of the equipment during the tire production and processing process and the characteristics of the operation data changes caused by the differences in long and short processes. Furthermore, the abnormality discrimination coefficient is used to detect abnormalities of the tire production and processing equipment, thereby solving the problem that setting multiple threshold detection is difficult to cover the differences in equipment parameters in most production scenarios, and improving the stability and efficiency of the tire production and processing process.

[0060] Based on the same inventive concept as the above method, an embodiment of the present application also provides a safe production and processing equipment information data management system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements the steps of any one of the above-mentioned safe production and processing equipment information data management methods.

[0061] It should be noted that the above sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0062] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0063] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for managing information data of safe production and processing equipment, characterized in that: The method comprises the following steps: S1: Real-time collection of various operating data of each device during the vulcanization process of tire production; S2: Fitting various operation data of each device within a preset time before the current moment, counting the number of all inflection points on the fitting curve of various operation data, and analyzing the difference in the trend intensity of various operation data between each device and all other devices within the preset time before the current moment, and determining the abnormal discrimination value of various operation data in each device at the current moment; S3: Clustering all fitting points on the fitting curve of each item of operation data of each device, and determining the first eigenvalue of each item of operation data in each device by analyzing the distance between different fitting points in each cluster under each item of operation data; determining the second eigenvalue of each item of operation data in each device based on the distance between all adjacent inflection points on the fitting curve of each item of operation data, and determining the comprehensive eigenvalue of each item of operation data in each device at the current moment in combination with the first eigenvalue; S4: Based on the abnormal discrimination value and the comprehensive characteristic value, determine the abnormal discrimination coefficient of each operation data in each device at the current moment, and manage the information data of all devices in the safe production processing process.

2. A method for managing information data of safe production and processing equipment according to claim 1, characterized in that: The operating data at least includes: pressure data, temperature data, power data and vibration data.

3. A method for managing information data of safe production and processing equipment according to claim 1, characterized in that: The method for determining the abnormal discrimination value of each operation data in each device at the current moment is: The differences in the trend strength of each operating data between each device and all other devices are averaged, and the differences in the total number of inflection points on the fitting curves of each operating data between each device and all other devices are averaged, and they are recorded as the first mean and the second mean respectively; The abnormality judgment value of each item of operating data in each device is the product of the first mean value and the second mean value of each item of operating data in each device.

4. A method for managing information data of safe production and processing equipment according to claim 1, characterized in that: The clustering of all fitting points on the fitting curve of each item of operating data of each device: in the clustering process, the metric distance of the clustering algorithm is the Euclidean distance between different fitting points.

5. A method for managing information data of safe production and processing equipment according to claim 1, characterized in that: The method for determining the first characteristic value of each operation data in each device is: For each item of operating data in each device, the mean of the distances between all fitting points in each cluster is calculated, recorded as the distance mean, and the cumulative result of the distance means of all clusters is taken as the first eigenvalue of each item of operating data in each device.

6. A method for managing information data of safe production and processing equipment according to claim 1, characterized in that: The second characteristic value of each item of operating data in each device is the average value of the distances between all adjacent inflection points on the fitting curve of each item of operating data in each device.

7. A method for managing information data of safe production and processing equipment according to claim 1, characterized in that: The comprehensive characteristic value of each item of operating data in each device at the current moment is the reciprocal of the sum of the first characteristic value and the second characteristic value of each item of operating data in each device.

8. A method for managing information data of safe production and processing equipment according to claim 1, characterized in that: The expression of the abnormal discrimination coefficient of each operating data in each device at the current moment is: ; In the formula, represents the abnormal discrimination coefficient of the jth item of operating data in equipment i at the current moment; Indicates the abnormality judgment value of the jth item of operating data in device i at the current moment; Represents the comprehensive characteristic value of the j-th operating data in device i at the current moment.

9. A method for managing information data of safe production and processing equipment according to claim 1, characterized in that: The management of information data of all equipment in the safe production process includes: The abnormal discrimination coefficients of the operation data of all devices at the current moment are used as the input of the threshold segmentation algorithm, and the segmentation thresholds of the operation data are output; If the abnormal discrimination coefficient of any item of operating data of device i at the current moment is greater than the segmentation threshold of the corresponding item of operating data, then device i is abnormal. At this time, the information data of device i is obtained and sent to the staff to inspect and repair device i.

10. A safe production processing equipment information data management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of a method for managing information data of safe production and processing equipment as described in any one of claims 1-9 are implemented.

Images