A real-time monitoring method for the operation status of an intelligent manufacturing production line

Abstract

The present application relates to the field of image data processing, and specifically to a method for real-time monitoring of the operating status of an intelligent manufacturing production line, comprising: first, according to the temperature data of the initial temperature data point in the temperature-time data sequence corresponding to the production line, calculating the temperature anomaly degree corresponding to the initial temperature data point, confirming the abnormal temperature data point, and then calculating the current-temperature correlation coefficient corresponding to the target abnormal temperature data point based on the current data of the target current data point corresponding to the target abnormal temperature data point, and calculating the abnormal characteristic value corresponding to the target abnormal temperature data point through the temperature anomaly degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient, and finally confirming the operating status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point. Compared with the traditional production line operating status monitoring method, the monitoring accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to a method for real-time monitoring of the operating status of an intelligent manufacturing production line. Background Art

[0002] The intelligent manufacturing production line is a highly automated and intelligent production system that integrates sensors, autonomous control, information technology and Internet technology. The intelligent manufacturing production line has the ability to learn, control and optimize autonomously, and can respond quickly to market demand and continuously improve production efficiency and quality. Moreover, the production line realizes the automation, intelligence and flexibility of the production process through real-time data collection, online monitoring and automatic control. It also adopts fully automated and semi-automated control technology to digitize and automate the production process. By installing various sensors and intelligent devices, it collects data and information in the production process in real time for real-time monitoring and control.

[0003] When monitoring the operating status of the intelligent manufacturing production line, the intelligent production line is highly sensitive to temperature during its operation and temperature data is relatively easy to obtain. Therefore, the traditional method is usually to obtain the operating temperature of the intelligent manufacturing production line through a temperature sensor to reflect whether the operating status of the intelligent production line is abnormal. However, when the temperature of the intelligent manufacturing production line is collected through a temperature sensor in the traditional way, it is easily affected by the external temperature change and causes measurement errors, thereby leading to misjudgment of the operating status of the intelligent manufacturing production line. Summary of the invention

[0004] In view of the above, it is necessary to provide a real-time monitoring method for the operating status of an intelligent manufacturing production line, which improves the monitoring accuracy compared to the traditional real-time monitoring method for the operating status of an intelligent manufacturing production line.

[0005] The first aspect of the present application provides a real-time monitoring method for the operation status of an intelligent manufacturing production line, which is applied to the field of production line operation transition detection. The method comprises: calculating the degree of temperature anomaly corresponding to the initial temperature data point according to the temperature data of the initial temperature data point in the temperature-time data sequence corresponding to the production line; comparing the degree of temperature anomaly corresponding to the initial temperature data point with a preset temperature threshold to confirm the abnormal temperature data point; calculating the current-temperature correlation coefficient corresponding to the target abnormal temperature data point based on the current data of the target current data point corresponding to the target abnormal temperature data point, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line; calculating the abnormal characteristic value corresponding to the target abnormal temperature data point through the degree of temperature anomaly corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient; and confirming the operation status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point.

[0006] In one of the embodiments, the temperature abnormality degree corresponding to the initial temperature data point is calculated based on the temperature data of the initial temperature data point in the temperature-time data sequence corresponding to the production line, specifically including: calculating the average temperature influence degree corresponding to the target initial temperature data point based on the difference between the temperature data of the target initial temperature data point and the temperature data of other initial temperature data points in the temperature-time data sequence corresponding to the production line and a first distance; calculating the local temperature influence degree corresponding to the target initial temperature data point based on the difference between the temperature data of the target initial temperature data point and the nearest temperature extreme point and a second distance; inputting the average temperature influence degree and the local temperature influence degree corresponding to the target initial temperature data point into a preset temperature abnormality degree calculation formula to confirm the temperature abnormality degree corresponding to the target initial temperature data point.

[0007] In one embodiment, the inputting the average temperature influence degree and the local temperature influence degree corresponding to the target initial temperature data point into a preset temperature anomaly degree calculation formula to confirm the temperature anomaly degree corresponding to the target initial temperature data point specifically includes:

[0008]

[0009] Among them, b i is the temperature anomaly degree corresponding to the target initial temperature data point in the temperature time data sequence corresponding to the production line, S is the total number of other initial temperature data points s in the temperature time data sequence corresponding to the production line, t i is the temperature data corresponding to the target initial temperature data point i, t s is the temperature data of other initial temperature data points s, d(i,s) is the distance between the target initial temperature data point i and other initial temperature data points s, tk is the temperature data of the nearest temperature extreme point k that is closest to the target initial temperature data point i, d(i,k) is the distance value between the target initial temperature data point i and the nearest temperature extreme point k, and sigmoid is the normalization function.

[0010] In one of the embodiments, the temperature abnormality degree corresponding to the initial temperature data point is compared with a preset temperature threshold to confirm the abnormal temperature data point, specifically including: when the temperature abnormality degree corresponding to the initial temperature data point is greater than the preset temperature threshold, confirming that the initial temperature data point is an abnormal temperature data point; when the temperature abnormality degree corresponding to the initial temperature data point is less than or equal to the preset temperature threshold, confirming that the initial temperature data point is a normal temperature data point.

[0011] In one of the embodiments, the current data of the target current data point corresponding to the target abnormal temperature data point is used to calculate the current-temperature correlation coefficient corresponding to the target abnormal temperature data point, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line, specifically including: confirming the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line as the target current data point; calculating the current influence degree corresponding to the target abnormal temperature data point based on the current data of the target current data point and the corresponding nearest current extreme point, and the average current data of other current data points; and calculating the difference between the temperature abnormality degree and the current influence degree corresponding to the target abnormal temperature data point to confirm the current-temperature correlation coefficient corresponding to the target abnormal temperature data point.

[0012] In one embodiment, calculating the difference between the temperature abnormality degree and the current influence degree corresponding to the target abnormal temperature data point to determine the current-temperature correlation coefficient corresponding to the target abnormal temperature data point specifically includes:

[0013]

[0014] Among them, c o is the current-temperature correlation coefficient corresponding to the target abnormal temperature data point o, b o is the temperature anomaly degree corresponding to the target abnormal temperature data point o, a o is the current data of the target current data point corresponding to the target abnormal temperature data point o, a m is the current data of the nearest current extreme point m corresponding to the target current data point, d(o,m) is the distance between the target current data point and the nearest current extreme point, a j is the current data of other current data point j corresponding to the target current data point, J is the number of other current data points, and Norm is the normalization function.

[0015] In one embodiment, calculating the abnormal characteristic value corresponding to the target abnormal temperature data point by using the temperature abnormality degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient specifically includes:

[0016] p o =sigmoid[b o ×exp(-c o )]

[0017] Among them, p o is the abnormal characteristic value corresponding to the target abnormal temperature data point, b o is the temperature anomaly degree corresponding to the target abnormal temperature data point, c o is the current-temperature correlation coefficient corresponding to the target abnormal temperature data point, and sigmoid is the normalization function.

[0018] In one of the embodiments, the operation status of the production line is confirmed based on the abnormal characteristic value corresponding to the target abnormal temperature data point, specifically including: when the abnormal characteristic value corresponding to the target abnormal temperature data point is greater than a preset standard characteristic value, confirming that the operation status of the production line is an abnormal operation status; when the abnormal characteristic value corresponding to the target abnormal temperature data point is less than or equal to the preset standard characteristic value, confirming that the operation status of the production line is a normal operation status.

[0019] In one of the embodiments, the operation status of the production line is confirmed based on the abnormal characteristic value corresponding to the target abnormal temperature data point, specifically including: confirming the target abnormal temperature data point whose abnormal characteristic value is greater than the preset standard characteristic value as the final abnormal temperature data point; when the final abnormal temperature data point in the temperature-time data sequence is greater than the standard number, confirming that the operation status of the production line is an abnormal operation status; when the final abnormal temperature data point in the temperature-time data sequence is less than or equal to the standard number, confirming that the operation status of the production line is a normal operation status.

[0020] In one of the embodiments, before calculating the degree of temperature abnormality corresponding to the initial temperature data point in the temperature-time data sequence corresponding to the production line based on the temperature data of the initial temperature data point, the method further includes: acquiring the temperature-time data sequence and the current-time data sequence corresponding to the production line according to a preset sampling frequency.

[0021] The embodiment of the present application provides a method for real-time monitoring of the operating status of an intelligent manufacturing production line, which is applied to the field of production line operation transition detection. The method includes: first, according to the temperature data of the initial temperature data point in the temperature time data sequence corresponding to the production line, calculating the temperature anomaly degree corresponding to the initial temperature data point, then comparing the temperature anomaly degree corresponding to the initial temperature data point with a preset temperature threshold, confirming the abnormal temperature data point, and then calculating the current-temperature correlation coefficient corresponding to the target abnormal temperature data point based on the current data of the target current data point corresponding to the target abnormal temperature data point, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line, and calculating the abnormal characteristic value corresponding to the target abnormal temperature data point through the temperature anomaly degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient, and finally confirming the operating status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point. By calculating the correlation coefficient between the abnormal temperature data points and the corresponding current data points corresponding to the production line, it is confirmed whether the abnormal temperature data points can be used as the basis for judging the operating status of the production line. Compared with the traditional production line operating status monitoring method, the current data dimension is added for comprehensive judgment, which improves the accuracy of the data, thereby reducing the probability of misjudgment and improving the accuracy of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a method for real-time monitoring of the operating status of an intelligent manufacturing production line according to an embodiment of the present application.

[0023] Figure 2 It is a schematic diagram of the first sub-process of a method for real-time monitoring of the operating status of an intelligent manufacturing production line in an embodiment of the present application.

[0024] Figure 3 It is a schematic diagram of the second sub-process of a method for real-time monitoring of the operating status of an intelligent manufacturing production line in an embodiment of the present application.

[0025] Figure 4 It is a schematic diagram of the third sub-process of a method for real-time monitoring of the operating status of an intelligent manufacturing production line in an embodiment of the present application.

[0026] Figure 5 It is a schematic diagram of the fourth sub-process of a method for real-time monitoring of the operating status of an intelligent manufacturing production line according to an embodiment of the present application.

[0027] Figure 6 This is a fifth sub-process diagram of a method for real-time monitoring of the operating status of an intelligent manufacturing production line in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field in this application. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. It should be understood that, unless otherwise specified in this application, " / " means or. For example, A / B can represent A or B. "And / or" in this application is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. "At least one" means one or more. "Multiple" means two or more than two. For example, at least one of a, b or c can represent: a, b, c, a and b, a and c, b and c, a, b and c seven situations.

[0030] It should also be noted that the terms "first" and "second" in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of this application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0031] The present application embodiment first proposes a real-time monitoring method for the operation status of an intelligent manufacturing production line, which is applied to the field of production line operation transition detection. Figure 1 , the method comprises the following steps:

[0032] S101. Calculate the temperature abnormality degree corresponding to the initial temperature data point according to the temperature data of the initial temperature data point in the temperature-time data sequence corresponding to the production line.

[0033] Among them, the temperature-time data sequence corresponding to the production line is the temperature data obtained by real-time acquisition of the temperature of the production line by a preset temperature acquisition device during the operation of the production line, and the corresponding temperature data is arranged in sequence according to the acquisition time. The initial temperature data point refers to the smallest component unit in the temperature-time data sequence, that is, the temperature-time data sequence is composed of a number of initial temperature data points. The temperature data of the initial temperature data point refers to the temperature value corresponding to the initial temperature data point. The temperature anomaly degree corresponding to the initial temperature data point refers to the probability of whether the initial temperature data point has an abnormal temperature change caused by a production line failure. In other words, the temperature anomaly degree corresponding to the initial temperature data point can characterize the operating state of the production line at the time when the initial temperature data point is located to a certain extent. When the temperature anomaly degree corresponding to the initial temperature data point is greater, it proves that the initial temperature data point is more likely to be a data point with abnormal temperature change caused by a production line failure. When the temperature anomaly degree corresponding to the initial temperature data point is smaller, it proves that the initial temperature data point is less likely to be a data point with abnormal temperature change caused by a production line failure.

[0034] It should be noted that, before calculating the temperature anomaly degree corresponding to the initial temperature data point in the temperature-time data sequence corresponding to the production line according to the temperature data of the initial temperature data point, the method further includes:

[0035] According to the preset sampling frequency, the temperature time data series and the current time data series corresponding to the production line are obtained.

[0036] The temperature-time data sequence corresponding to the production line is obtained by arranging high-precision temperature sensors on the production line to collect the temperature state on the production line, and at the same time, collecting the data of the current size of the production line through high-precision current sensors to obtain the current-time data sequence corresponding to the production line. The temperature data and current data are collected in real time, and the collection frequency can be designed according to actual needs, preferably 1 second (empirical value, specifically determined according to the accuracy of real-time monitoring of the actual production line).

[0037] S102: Compare the temperature anomaly degree corresponding to the initial temperature data point with a preset temperature threshold to confirm the abnormal temperature data point.

[0038] Among them, after obtaining the temperature anomaly degree corresponding to the initial temperature data point, the preset temperature threshold is called, the temperature anomaly degree corresponding to the initial temperature data point is compared with the preset temperature threshold, and whether the initial temperature data point is an abnormal temperature data point is confirmed according to the comparison result.

[0039] For details, please refer to the attached Figure 3, comparing the temperature anomaly degree corresponding to the initial temperature data point with a preset temperature threshold to confirm the abnormal temperature data point, specifically includes:

[0040] S301, when the temperature abnormality degree corresponding to the initial temperature data point is greater than a preset temperature threshold, confirming that the initial temperature data point is an abnormal temperature data point;

[0041] S302: When the temperature abnormality degree corresponding to the initial temperature data point is less than or equal to a preset temperature threshold, confirm that the initial temperature data point is a normal temperature data point.

[0042] The preset temperature threshold refers to the critical value between the normal temperature data point and the abnormal temperature data point set according to the empirical value. The abnormal temperature data point refers to the data point that is likely to be caused by abnormal temperature change due to production line failure according to the characterization of the temperature value.

[0043] It should be noted that the confirmation of the abnormal temperature data point is only judged from the temperature value representation of the data point in the temperature-time data sequence, that is, the temperature change caused by the ambient temperature of the production line is not excluded. In other words, judging the production line based on temperature data alone is easily affected by the temperature of the environment where the production line is located, resulting in misjudgment.

[0044] S103. Calculate the current-temperature correlation coefficient corresponding to the target abnormal temperature data point based on the current data of the target current data point corresponding to the target abnormal temperature data point, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line.

[0045] Among them, after obtaining the target abnormal temperature data point, the target current data point corresponding to the target abnormal temperature data point is searched in the current time series corresponding to the production line. The target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line. That is, the time value corresponding to the target abnormal temperature data point is the same as the time value corresponding to the target current data point. The current-temperature correlation coefficient corresponding to the target abnormal temperature data point refers to the correlation between the abnormal performance degree of the target abnormal temperature data point in the temperature time data series and the abnormal performance degree of the corresponding current data point in the current time data series at the same time. In other words, when the temperature data at a moment is abnormal, that is, (abnormal temperature data point) and the current data is also abnormal, it proves that the operation state of the current production line is likely to be an abnormal operation state. Because the equipment of the production line is abnormal in operation, its corresponding current data is a data that can be characterized in the first time. For example, if a device in the production line has a short circuit or open circuit fault, the current data at the corresponding fault moment will have a large increase or decrease.

[0046] It should be noted that by taking the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line, and calculating the correlation with the target abnormal temperature data point, the operating status of the production line can be judged from two dimensions of temperature and current, and misjudgment caused by changes in the ambient temperature of the production line can be avoided as much as possible, thereby improving the accuracy of the judgment of the operating status of the production line.

[0047] S104 , calculating an abnormal characteristic value corresponding to the target abnormal temperature data point by using the temperature abnormality degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient.

[0048] Among them, after obtaining the temperature anomaly degree and the current-temperature correlation coefficient corresponding to the target abnormal temperature data point, the two are used as calculation parameters, that is, further calculation is performed from the two dimensions of current data and temperature data to obtain the abnormal characteristic value corresponding to the target abnormal temperature data point. The abnormal characteristic value corresponding to the target abnormal temperature data point refers to the data point of whether the target abnormal temperature data point is a data point of abnormal temperature change caused by a production line failure after further calculation from the two dimensions of comprehensive current data and temperature data.

[0049] S105. Confirm the operating status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point.

[0050] Among them, after obtaining the abnormal characteristic value corresponding to the target abnormal temperature data point, it is compared with the preset standard characteristic value, and the operation status of the production line is confirmed according to the comparison result. It should be noted that the judgment of the operation status of the production line can be that the abnormal characteristic value corresponding to any target abnormal temperature data point in the temperature-time data sequence is greater than the preset standard characteristic value, and the operation status of the production line can be confirmed to be an abnormal operation status. It can also be that the number of target abnormal temperature data points in the temperature-time data sequence whose abnormal characteristic values ​​are greater than the preset standard characteristic value is greater than the preset standard number, and the operation status of the production line is confirmed to be an abnormal operation status. The judgment conditions of the former are relatively accurate, and the safety monitoring of the production line is more rigorous and safer. The judgment conditions of the latter are relatively universal, and can ensure the operation of the production line as much as possible, and the operation efficiency of the production line is higher.

[0051] The embodiment of the present application provides a method for real-time monitoring of the operating status of an intelligent manufacturing production line, which is applied to the field of production line operation transition detection. The method includes: first, according to the temperature data of the initial temperature data point in the temperature time data sequence corresponding to the production line, calculating the temperature anomaly degree corresponding to the initial temperature data point, then comparing the temperature anomaly degree corresponding to the initial temperature data point with a preset temperature threshold, confirming the abnormal temperature data point, and then calculating the current-temperature correlation coefficient corresponding to the target abnormal temperature data point based on the current data of the target current data point corresponding to the target abnormal temperature data point, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line, and calculating the abnormal characteristic value corresponding to the target abnormal temperature data point through the temperature anomaly degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient, and finally confirming the operating status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point. By calculating the correlation coefficient between the abnormal temperature data points and the corresponding current data points corresponding to the production line, it is confirmed whether the abnormal temperature data points can be used as the basis for judging the operating status of the production line. Compared with the traditional production line operating status monitoring method, the current data dimension is added for comprehensive judgment, which improves the accuracy of the data, thereby reducing the probability of misjudgment and improving the accuracy of monitoring.

[0052] In one embodiment of the present application, see Figure 2 The step S101: calculating the temperature abnormality degree corresponding to the initial temperature data point in the temperature time data sequence corresponding to the production line according to the temperature data of the initial temperature data point, specifically includes:

[0053] S201. Calculate the average temperature influence degree corresponding to the target initial temperature data point according to the difference between the temperature data of the target initial temperature data point and the temperature data of other initial temperature data points in the temperature-time data sequence corresponding to the production line and a first distance.

[0054] Among them, the temperature data difference between the target initial temperature data point and the temperature data of other initial temperature data points refers to the temperature value difference between the target initial temperature data point and other data points in the temperature time data sequence. The first distance refers to the distance value between the target initial temperature data point and other data points in the temperature time data sequence on the corresponding fitting curve. The temperature value difference between the target initial temperature data point and other data points in the temperature time data sequence is summed up respectively, and the first distance between the target initial temperature data point and other data points in the temperature time data sequence is summed up, and then the ratio of the two is used as the average temperature influence degree corresponding to the target initial temperature data point. The average temperature influence degree corresponding to the target initial temperature data point refers to the difference degree of the temperature value of the target initial temperature data point in the temperature time data sequence where it is located. For example, when the target initial temperature data point is an extreme point in the temperature time data sequence, its difference degree in the temperature time data sequence is large, and the corresponding average temperature influence degree is large.

[0055] S202: Calculate the local temperature influence degree corresponding to the target initial temperature data point based on the temperature data difference between the target initial temperature data point and the nearest temperature extreme point and the second distance.

[0056] Among them, the nearest temperature extreme point refers to the extreme point with the shortest distance from the target initial temperature data point, the temperature data difference between the target initial temperature data point and the nearest temperature extreme point refers to the temperature difference between the target initial temperature data point and the nearest temperature extreme point, and the second distance refers to the distance between the target initial temperature data point and the nearest temperature extreme point. After obtaining the temperature data difference between the target initial temperature data point and the nearest temperature extreme point and the second distance, the difference between the two is calculated to obtain the local temperature influence degree corresponding to the target initial temperature data point. The local temperature influence degree corresponding to the target initial temperature data point refers to the proximity between the target initial temperature data point and the abnormal data point with the maximum possibility in the surrounding local area. It should be noted that the temperature extreme point is a data point with a greater possibility of temperature anomaly. When the target initial temperature data point is closer to the nearest temperature extreme point, the second distance corresponding to the target initial temperature data point and the nearest temperature extreme point is smaller, which proves that the target initial temperature data point is more likely to be an abnormal temperature data point.

[0057] S203, inputting the average temperature influence degree and the local temperature influence degree corresponding to the target initial temperature data point into a preset temperature anomaly degree calculation formula to confirm the temperature anomaly degree corresponding to the target initial temperature data point.

[0058] Among them, after obtaining the average temperature influence degree and the local temperature influence degree corresponding to the target initial temperature data point, the two are input as calculation parameters into the preset temperature anomaly degree calculation formula, so as to multiply the two and obtain the temperature anomaly degree corresponding to the target initial temperature data point. The temperature anomaly degree corresponding to the initial temperature data point refers to the probability of whether the initial temperature data point has an abnormal temperature change caused by a production line failure. When the temperature anomaly degree corresponding to the initial temperature data point is larger, it proves that the initial temperature data point is more likely to be a data point with abnormal temperature change caused by a production line failure. When the temperature anomaly degree corresponding to the initial temperature data point is smaller, it proves that the initial temperature data point is less likely to be a data point with abnormal temperature change caused by a production line failure.

[0059] Specifically, the inputting the average temperature influence degree and the local temperature influence degree corresponding to the target initial temperature data point into a preset temperature anomaly degree calculation formula to confirm the temperature anomaly degree corresponding to the target initial temperature data point specifically includes:

[0060]

[0061] Among them, b i is the temperature anomaly degree corresponding to the target initial temperature data point in the temperature time data sequence corresponding to the production line, S is the total number of other initial temperature data points s in the temperature time data sequence corresponding to the production line, t i is the temperature data corresponding to the target initial temperature data point i, t s is the temperature data of other initial temperature data point s, d(i,s) is the first distance between the target initial temperature data point i and other initial temperature data points s, t k is the temperature data of the nearest temperature extreme point k that is closest to the target initial temperature data point i, d(i,k) is the second distance between the target initial temperature data point i and the nearest temperature extreme point k, and sigmoid is the normalization function.

[0062] Furthermore, i -t s | is the temperature data difference between the temperature data of the target initial temperature data point i and the temperature data of the other initial temperature data points s, is the temperature influence degree of the target initial temperature data point i and other initial temperature data points s. i -t sThe larger the | is, the smaller the first distance d(i,s) is, which proves that the temperature value difference of the target initial temperature data point relative to other initial temperature data points s in the unit time period is large, which means that the target initial temperature data point i is more likely to be an abnormal temperature data point. Sum the temperature influence degree corresponding to the target initial temperature data point i and all other initial temperature data points s to obtain the average temperature influence degree corresponding to the target initial temperature data point It can further accurately characterize the probability of whether the target initial temperature data point i is an abnormal temperature data point. Therefore, when the average temperature influence degree corresponding to the target initial temperature data point is The larger the value is, the more likely the target initial temperature data point i is an abnormal temperature data point. Similarly, |t i -t k | is the temperature data difference between the temperature data of the target initial temperature data point i and the temperature data of the nearest temperature extreme point k, d(i,k) is the second distance between the target initial temperature data point i and the nearest temperature extreme point k, is the local temperature influence degree corresponding to the target initial temperature data point i. When the temperature data of the target initial temperature data point i and the temperature data of the nearest temperature extreme point k have a difference |t i -t k | is larger, and the second distance d(i, k) is smaller, which proves that the temperature data of the target initial temperature data point i relative to the temperature data of the nearest temperature extreme point k in the unit time period has a larger temperature change, and the target initial temperature data point i is more likely to be an abnormal temperature data point. Therefore, when the local temperature influence degree corresponding to the target initial temperature data point i is greater, the target initial temperature data point i is more likely to be an abnormal temperature data point. In summary, the temperature anomaly degree b corresponding to the target initial temperature data point in the temperature time data sequence corresponding to the production line i The larger the value, the more likely the target initial temperature data point i is an abnormal temperature data point.

[0063] In one embodiment of the present application, refer to the attached Figure 4 , step S103, based on the current data of the target current data point corresponding to the target abnormal temperature data point, the current-temperature correlation coefficient corresponding to the target abnormal temperature data point is calculated, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line, specifically including:

[0064] S401. Confirm the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line as the target current data point.

[0065] The target abnormal temperature data point and the corresponding target current data point have the same time value, in order to detect whether the target current data point corresponding to the same time is also in an abnormal state when the target abnormal temperature data point is in an abnormal state. When both are in an abnormal state, it can be further proved that the target abnormal temperature data point is caused by equipment failure in the production line, and is not caused by the influence of ambient temperature.

[0066] S402, calculating the current influence degree corresponding to the target abnormal temperature data point according to the current data of the target current data point and the corresponding nearest current extreme value point, and the average current data of other current data points.

[0067] After obtaining the target current data point corresponding to the target abnormal temperature data point, the nearest current extreme value point corresponding to the target current data point is obtained, and the current influence degree corresponding to the target abnormal temperature data point is calculated based on the current data of the nearest current extreme value point and the average current data of other current data points except the target abnormal temperature data point. The current influence degree corresponding to the target abnormal temperature data point refers to the abnormal degree of the target current data point in temperature data at the same time as the target abnormal temperature data point.

[0068] S403 , calculating the difference between the temperature abnormality degree corresponding to the target abnormal temperature data point and the current influence degree, and determining the current-temperature correlation coefficient corresponding to the target abnormal temperature data point.

[0069] Among them, after obtaining the temperature abnormality degree and current influence degree corresponding to the target abnormal temperature data point, the two are used as calculation parameters for difference calculation to obtain the current-temperature correlation coefficient corresponding to the target abnormal temperature data point. The current-temperature correlation coefficient corresponding to the target abnormal temperature data point refers to the similarity between the abnormality degree of the target abnormal temperature data point in the temperature-time data sequence and the abnormality degree of the corresponding target current data point in the current-time data sequence. When the current-temperature correlation coefficient corresponding to the target abnormal temperature data point is larger, the target abnormal temperature data point is more likely to be a data point with abnormal temperature change caused by a production line failure.

[0070] Specifically, the difference between the temperature abnormality degree corresponding to the target abnormal temperature data point and the current influence degree is calculated to determine the current-temperature correlation coefficient corresponding to the target abnormal temperature data point, specifically including:

[0071]

[0072] Among them, c o is the current-temperature correlation coefficient corresponding to the target abnormal temperature data point o, b ois the temperature anomaly degree corresponding to the target abnormal temperature data point o, a o is the current data of the target current data point corresponding to the target abnormal temperature data point o, a m is the current data of the nearest current extreme point m corresponding to the target current data point, d(o,m) is the distance between the target current data point and the nearest current extreme point, a j is the current data of other current data point j corresponding to the target current data point, J is the number of other current data points, and Norm is the normalization function.

[0073] Furthermore, a o -a m is the current data difference between the target current data point corresponding to the target abnormal temperature data point and the corresponding nearest current extreme point, d(o,m) is the distance between the target current data point and the nearest current extreme point, then The temperature change of the current data of the target current data point relative to the current extreme point within the unit time period is larger, which means that the target current data point is more likely to be the current data point corresponding to the abnormality caused by the production line equipment failure. is the average current data value of other current data points corresponding to the target current data point, Then is the ratio of the current data of the target current data point to the average current data of other current data points, which can characterize the influence of the current data of the target current data point on the entire current time data series. Therefore, The abnormal degree of the target current data point corresponding to the target abnormal temperature data point in the current time data sequence can be characterized, and the difference between the temperature abnormal degree corresponding to the target abnormal temperature data point and the target abnormal temperature data point can reflect the correlation between the two. Therefore, when the current-temperature correlation coefficient corresponding to the target abnormal temperature data point is larger, the target abnormal temperature data point is more likely to be a data point with abnormal temperature change caused by a production line failure.

[0074] Correspondingly, in one embodiment of the present application, step S104, calculating the abnormal characteristic value corresponding to the target abnormal temperature data point by the temperature abnormality degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient, specifically includes:

[0075] p0 = sigmoid[b o ×exp(-c o )]

[0076] Among them, p o is the abnormal characteristic value corresponding to the target abnormal temperature data point, b o is the temperature anomaly degree corresponding to the target abnormal temperature data point, c ois the current-temperature correlation coefficient corresponding to the target abnormal temperature data point, sigmoid is the normalization function, and exp is the exponential function with the constant e as the base.

[0077] Furthermore, the abnormal characteristic value corresponding to the target abnormal temperature data point refers to the probability value that the target abnormal temperature data point is a data point with abnormal temperature change caused by a production line failure. The higher the abnormal characteristic value corresponding to the target abnormal temperature data point, the more likely the target abnormal temperature data point is to be a data point with abnormal temperature change caused by a production line failure.

[0078] In one embodiment of the present application, refer to the attached Figure 5 Step S105, confirming the operation status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point, specifically includes:

[0079] S501, when the abnormal characteristic value corresponding to the target abnormal temperature data point is greater than a preset standard characteristic value, confirming that the operation state of the production line is an abnormal operation state;

[0080] S502: When the abnormal characteristic value corresponding to the target abnormal temperature data point is less than or equal to a preset standard characteristic value, confirm that the operation state of the production line is a normal operation state.

[0081] It is necessary to analyze that, that is, when there is a target abnormal temperature data point in the temperature-time data sequence whose abnormal characteristic value is greater than the preset standard characteristic value, the operation state of the production line is determined to be an abnormal operation state. Because the judgment conditions are more rigorous and strict, this method can ensure the safety of the production line operation to a greater extent.

[0082] In some other embodiments, refer to the attached Figure 6 , the confirming the operation status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point specifically includes:

[0083] S601, confirming a target abnormal temperature data point whose abnormal characteristic value is greater than a preset standard characteristic value as a final abnormal temperature data point;

[0084] S602, when the final abnormal temperature data point in the temperature-time data sequence is greater than the standard number, confirming that the operation state of the production line is an abnormal operation state;

[0085] S603: When the final abnormal temperature data point in the temperature-time data sequence is less than or equal to the standard number, confirm that the operation status of the production line is a normal operation status.

[0086] Specifically, the target abnormal temperature data point whose abnormal characteristic value is greater than the preset standard characteristic value is confirmed as the final abnormal temperature data point, and only when the final abnormal temperature data point is greater than the standard number, the operation state of the production line is determined to be an abnormal operation state. Compared with the aforementioned method of determining that the operation state of the production line is an abnormal operation state as long as there is a final abnormal temperature data point in the temperature-time data sequence, the universality of the monitoring method is increased, and the production capacity of the production line can be further guaranteed.

[0087] The embodiment of the present application provides a method for real-time monitoring of the operating status of an intelligent manufacturing production line, which is applied to the field of production line operation transition detection. The method includes: first, according to the temperature data of the initial temperature data point in the temperature time data sequence corresponding to the production line, calculating the temperature anomaly degree corresponding to the initial temperature data point, then comparing the temperature anomaly degree corresponding to the initial temperature data point with a preset temperature threshold, confirming the abnormal temperature data point, and then calculating the current-temperature correlation coefficient corresponding to the target abnormal temperature data point based on the current data of the target current data point corresponding to the target abnormal temperature data point, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line, and calculating the abnormal characteristic value corresponding to the target abnormal temperature data point through the temperature anomaly degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient, and finally confirming the operating status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point. By calculating the correlation coefficient between the abnormal temperature data points and the corresponding current data points corresponding to the production line, it is confirmed whether the abnormal temperature data points can be used as the basis for judging the operating status of the production line. Compared with the traditional production line operating status monitoring method, the current data dimension is added for comprehensive judgment, which improves the accuracy of the data, thereby reducing the probability of misjudgment and improving the accuracy of monitoring.

[0088] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0089] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the attached claims rather than the above description, and therefore it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application.

Claims

1. A method for real-time monitoring of the operating status of an intelligent manufacturing production line, applied to the field of production line operation transition detection, characterized in that: The method comprises: Calculate the temperature abnormality degree corresponding to the initial temperature data point according to the temperature data of the initial temperature data point in the temperature time data sequence corresponding to the production line; Comparing the temperature anomaly degree corresponding to the initial temperature data point with a preset temperature threshold to confirm the abnormal temperature data point; Based on the current data of the target current data point corresponding to the target abnormal temperature data point, the current-temperature correlation coefficient corresponding to the target abnormal temperature data point is calculated, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line; Calculating the abnormal characteristic value corresponding to the target abnormal temperature data point through the temperature abnormality degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient; Confirming the operating status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point; The step of calculating the temperature abnormality degree corresponding to the initial temperature data point according to the temperature data of the initial temperature data point in the temperature time data sequence corresponding to the production line specifically includes: Calculate the average temperature influence degree corresponding to the target initial temperature data point according to the difference between the temperature data of the target initial temperature data point and the temperature data of other initial temperature data points in the temperature-time data sequence corresponding to the production line and the first distance; Calculating the local temperature influence degree corresponding to the target initial temperature data point based on the temperature data difference between the target initial temperature data point and the nearest temperature extreme point and the second distance; Inputting the average temperature influence degree and the local temperature influence degree corresponding to the target initial temperature data point into a preset temperature anomaly degree calculation formula to confirm the temperature anomaly degree corresponding to the target initial temperature data point; The step of inputting the average temperature influence degree and the local temperature influence degree corresponding to the target initial temperature data point into a preset temperature anomaly degree calculation formula to determine the temperature anomaly degree corresponding to the target initial temperature data point specifically includes: in, is the temperature anomaly degree corresponding to the target initial temperature data point in the temperature-time data sequence corresponding to the production line, Other initial temperature data points in the temperature-time data sequence corresponding to the production line The total number of is the target initial temperature data point The corresponding temperature data, For other initial temperature data points Temperature data, is the target initial temperature data point With other initial temperature data points The first distance, is the distance from the target initial temperature data point The nearest temperature extreme point Temperature data, Target initial temperature data point The nearest temperature extreme point The second distance, is the normalization function; The current data of the target current data point corresponding to the target abnormal temperature data point is used to calculate the current-temperature correlation coefficient corresponding to the target abnormal temperature data point, wherein the target current data point refers to the current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line, specifically including: The current data point at the same time as the target abnormal temperature data point in the current time series corresponding to the production line is confirmed as the target current data point; Calculate the current influence degree corresponding to the target abnormal temperature data point according to the current data of the target current data point and the corresponding nearest current extreme value point, and the average current data of other current data points; Calculate the difference between the temperature abnormality degree corresponding to the target abnormal temperature data point and the current influence degree, and determine the current-temperature correlation coefficient corresponding to the target abnormal temperature data point; The step of calculating the difference between the temperature abnormality degree and the current influence degree corresponding to the target abnormal temperature data point and determining the current-temperature correlation coefficient corresponding to the target abnormal temperature data point specifically includes: in, is the target abnormal temperature data point The corresponding current-temperature correlation coefficient is, is the target abnormal temperature data point The corresponding temperature anomaly degree, is the target abnormal temperature data point The current data of the corresponding target current data point, The nearest current extreme point corresponding to the target current data point Current data, is the distance between the target current data point and the nearest current extreme value point, Other current data points corresponding to the target current data point Current data, is the number of other current data points, is the normalization function.

2. The method for real-time monitoring of the operating status of an intelligent manufacturing production line according to claim 1 is characterized in that: The comparing the temperature abnormality degree corresponding to the initial temperature data point with a preset temperature threshold to confirm the abnormal temperature data point specifically includes: When the temperature abnormality degree corresponding to the initial temperature data point is greater than a preset temperature threshold, confirming that the initial temperature data point is an abnormal temperature data point; When the temperature abnormality degree corresponding to the initial temperature data point is less than or equal to the preset temperature threshold, the initial temperature data point is confirmed to be a normal temperature data point.

3. The real-time monitoring method for the operation status of an intelligent manufacturing production line according to claim 1 is characterized in that: The calculating the abnormal characteristic value corresponding to the target abnormal temperature data point by using the temperature abnormality degree corresponding to the target abnormal temperature data point and the current-temperature correlation coefficient specifically includes: in, is the abnormal characteristic value corresponding to the target abnormal temperature data point, is the temperature anomaly degree corresponding to the target abnormal temperature data point, is the current-temperature correlation coefficient corresponding to the target abnormal temperature data point, is the normalization function.

4. The real-time monitoring method for the operation status of an intelligent manufacturing production line according to claim 1 is characterized in that: The confirming the operation status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point specifically includes: When the abnormal characteristic value corresponding to the target abnormal temperature data point is greater than the preset standard characteristic value, confirming that the operation state of the production line is an abnormal operation state; When the abnormal characteristic value corresponding to the target abnormal temperature data point is less than or equal to the preset standard characteristic value, it is confirmed that the operation status of the production line is a normal operation status.

5. The real-time monitoring method for the operation status of an intelligent manufacturing production line according to claim 1 is characterized in that: The confirming the operation status of the production line based on the abnormal characteristic value corresponding to the target abnormal temperature data point specifically includes: The target abnormal temperature data point whose abnormal characteristic value is greater than the preset standard characteristic value is confirmed as the final abnormal temperature data point; When the final abnormal temperature data point in the temperature-time data sequence is greater than the standard number, it is confirmed that the operation status of the production line is an abnormal operation status; When the final abnormal temperature data point in the temperature-time data sequence is less than or equal to the standard number, it is confirmed that the operating status of the production line is a normal operating status.

6. The method for real-time monitoring of the operating status of an intelligent manufacturing production line according to any one of claims 1 to 5, characterized in that: Before calculating the temperature abnormality degree corresponding to the initial temperature data point in the temperature time data sequence corresponding to the production line according to the temperature data of the initial temperature data point, the method further includes: According to the preset sampling frequency, the temperature time data series and the current time data series corresponding to the production line are obtained.

Images