Temperature monitoring method and system of electric heat conduction components for collaborative optimization

Abstract

The present application relates to the field of temperature monitoring technology, and specifically to a temperature monitoring method and system for an electric heat conduction component for collaborative optimization, the method comprising: collecting a temperature data sequence of the electric heat conduction component; obtaining a heat exchange adjustment factor for each mutation point in each temperature monitoring area in each temperature monitoring time period; then calculating a heat transfer anomaly coefficient; obtaining a heat load characteristic factor; then obtaining a temperature change correlation coefficient and a heat load difference coefficient; obtaining a temperature anomaly factor for each temperature monitoring time period, and monitoring the temperature of the electric heat conduction component. The present application improves the accuracy of temperature monitoring of the electric heat conduction component.

Description

Technical Field

[0001] The present application relates to the field of temperature monitoring technology, and in particular to a temperature monitoring method and system for an electric heat conduction component for collaborative optimization. Background Art

[0002] Vulcanizers, condensers and other devices are widely used in the fields of plastics and rubber, process industries, clothing manufacturing, etc., and the heat exchange efficiency and heat exchange uniformity of electric heat conduction components are closely related to the improvement of the efficiency of vulcanizers and condensers. Temperature monitoring of the coordinated optimized electric heat conduction components can lay a solid foundation for optimizing the operation of electric heat conduction components, improving energy utilization efficiency and safe and stable operation of equipment, and provide convenience for remote monitoring and automatic adjustment, which is of great practical significance.

[0003] When the heat transfer efficiency of the electric heat conduction component used for collaborative optimization is poor or the heat transfer is uneven during operation, it will cause large differences in the monitored temperatures in the temperature monitoring area. In the process of monitoring the temperature of the electric heat conduction component, the existing technology usually ignores the analysis of the interference phenomenon of external electromagnetic interference on the temperature data collection, and it is difficult to accurately evaluate the temperature abnormality of the electric heat conduction component as a whole based on the uneven distribution characteristics of the local heat load of the electric heat conduction component, and thus cannot provide scientific data support for the collaborative optimization of the electric heat conduction component, which may cause the disadvantages of related equipment not being able to operate normally and energy waste. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a temperature monitoring method and system for an electric heat conduction component for collaborative optimization. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a temperature monitoring method of an electric heat conduction component for collaborative optimization, the method comprising the following steps:

[0006] Collecting temperature data sequences of each temperature monitoring area on the electric heat conduction component in each temperature monitoring time period;

[0007] Obtain the mutation points of the temperature data sequence and the temperature fluctuation range of each mutation point;

[0008] Based on the difference between the temperature data of the mutation point and the mean value of the temperature data in its temperature fluctuation interval, the time length of the temperature fluctuation interval and the uncertainty of the trend change of the temperature data in the temperature fluctuation interval, the heat exchange adjustment factor of each mutation point in each temperature monitoring area in each temperature monitoring time period is obtained;

[0009] Based on the heat exchange adjustment factor, the heat load change point and the heat exchange fluctuation range of each heat load change point are obtained;

[0010] Based on the number of temperature data in the heat exchange fluctuation interval and the difference between the maximum and minimum values, the heat transfer anomaly coefficient of each heat load change point in each temperature monitoring time period of each temperature monitoring area is obtained;

[0011] Based on the time interval between the acquisition moments of each heat load change point and the difference between the heat transfer anomaly coefficients of each heat load change point, the heat load characteristic factor of each heat load change point in each temperature monitoring time period of each temperature monitoring area is obtained;

[0012] Based on the correlation between temperature data sequences and the correlation between heat load characteristic factors, the temperature change correlation coefficient and heat load difference coefficient of each cluster in each temperature monitoring time period are obtained;

[0013] Based on the temperature change correlation coefficient and the heat load difference coefficient, the temperature anomaly factor of each temperature monitoring time period is obtained, and the temperature of the electric heat conduction component is monitored based on the temperature anomaly factor.

[0014] Furthermore, the step of obtaining the mutation points of the temperature data sequence and the temperature fluctuation range of each mutation point includes:

[0015] The temperature data sequence of each temperature monitoring time period in each temperature monitoring area is taken as input, and a mutation point detection algorithm is used to obtain all mutation points in the temperature data sequence of each temperature monitoring time period in each temperature monitoring area; for each mutation point in each temperature data sequence, the time period between the collection time of the mutation point and the collection time of the next adjacent mutation point is taken as the temperature fluctuation range of each mutation point.

[0016] Furthermore, the method for obtaining the heat exchange adjustment factor is:

[0017] For each mutation point in each temperature monitoring time period of each temperature monitoring area, the mean of all temperature data in the temperature fluctuation interval of the mutation point is calculated, the absolute value of the difference between the temperature data of the mutation point and the mean is calculated, the ratio of the absolute value of the difference to the time length of the temperature fluctuation interval of the mutation point is calculated, the Shannon entropy of the intensity of the trend term of all temperature data in the temperature fluctuation interval of the mutation point is calculated, and the product of the ratio and the Shannon entropy is used as the heat exchange regulation factor of each mutation point in each temperature monitoring time period of each temperature monitoring area.

[0018] Furthermore, the step of obtaining the heat load change point and the heat exchange fluctuation range of each heat load change point includes:

[0019] The heat exchange adjustment factors of all mutation points in each temperature monitoring time period of each temperature monitoring area are used as inputs of the threshold segmentation algorithm to obtain the optimal segmentation threshold;

[0020] For each temperature monitoring time period in each temperature monitoring area, the mutation point in the temperature monitoring time period where the heat exchange regulation factor is less than the optimal segmentation threshold is taken as the heat load change point. For each heat load change point in the temperature monitoring time period, the time period between the collection time of the heat load node and the collection time of the next heat load node is taken as the heat exchange fluctuation range of each heat load change point.

[0021] Furthermore, the method for obtaining the heat transfer anomaly coefficient is:

[0022] For each heat load change point in each temperature monitoring time period of each temperature monitoring area, the difference between the maximum value and the minimum value of the temperature data in the heat exchange fluctuation interval of the heat load change point is calculated, and the total number of temperature data in the heat exchange fluctuation interval of the heat load change point and the sum of the preset adjustment parameters are calculated, and the ratio of the difference to the sum is used as the heat transfer anomaly coefficient of each heat load change point in each temperature monitoring time period of each temperature monitoring area.

[0023] Furthermore, the method for obtaining the heat load characteristic factor is:

[0024] With each temperature monitoring area as the center, a rectangular window with a side length of a preset number of temperature monitoring areas as the side length is used as a neighborhood window of each temperature monitoring area;

[0025] For each temperature monitoring area, calculate the time interval between the collection time of the jth heat load change point of the temperature monitoring area in each temperature monitoring time period and the collection time of the jth heat load change point of each other temperature monitoring area in the neighborhood window of the temperature monitoring area, calculate the sum of all the time intervals of the temperature monitoring area in its neighborhood window, and use it as the sum of the change point intervals of the jth heat load change point of each temperature monitoring area in each temperature monitoring time period;

[0026] Calculate the heat transfer anomaly coefficient of the j-th heat load change point of the temperature monitoring area in each temperature monitoring time period, and the absolute value of the difference between the heat transfer anomaly coefficient of the j-th heat load change point of each other temperature monitoring area in the neighborhood window of the temperature monitoring area, and calculate the sum of all the absolute values ​​of the difference of the temperature monitoring area in its neighborhood window as the heat difference sum value of the j-th heat load change point of each temperature monitoring area in each temperature monitoring time period;

[0027] The heat load characteristic factor is a normalized value of the ratio of the change point interval and value of each heat load change point in each temperature monitoring time period of each temperature monitoring area to the heat difference and value.

[0028] Furthermore, the method for obtaining the temperature change correlation coefficient is:

[0029] For each temperature monitoring time period of each temperature monitoring area, a sequence of heat load characteristic factors of all heat load change points within the temperature monitoring time period is sorted in chronological order as the heat load characteristic sequence of the temperature monitoring time period of each temperature monitoring area;

[0030] For each temperature monitoring time period, the heat load characteristic sequences of all temperature monitoring areas in the temperature monitoring time period are used as nodes in the undirected graph to form an undirected graph, and the undirected graph is used as the input of the clustering algorithm to obtain each clustering cluster;

[0031] The calculation formula of the temperature change correlation coefficient is: ; In the formula, is the temperature change correlation coefficient of the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the total number of regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; , are the temperature data sequences of the xth and yth temperature monitoring areas in the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the temperature data series and The cosine similarity between .

[0032] Furthermore, the calculation formula of the heat load difference coefficient is: ; In the formula, is the heat load difference coefficient of the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the total number of regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; , are the heat load characteristic sequences corresponding to the xth and yth regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the heat load characteristic sequence , JS divergence between .

[0033] Furthermore, the step of obtaining the temperature anomaly factor in each temperature monitoring time period and monitoring the temperature of the electric heat conduction component based on the temperature anomaly factor includes:

[0034] Calculate the product of the temperature change correlation coefficient and the heat load difference coefficient of each cluster of the electric heat conduction component in each temperature monitoring time period, and use the normalized value of the accumulated result of all the products in the temperature monitoring time period as the temperature anomaly factor of each temperature monitoring time period;

[0035] When the temperature anomaly factor in the temperature monitoring period is less than the preset temperature anomaly threshold, the temperature of the electric heat conduction component is normal; when the temperature anomaly factor in the temperature monitoring period is greater than or equal to the preset temperature anomaly threshold, the temperature of the electric heat conduction component is abnormal.

[0036] In a second aspect, an embodiment of the present application also provides a temperature monitoring system for an electric heat conduction component for collaborative optimization, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0037] This application has at least the following beneficial effects:

[0038] The present application obtains the heat load characteristic factor by analyzing the heat transfer abnormality characteristics and the temperature abnormal fluctuation time lag characteristics when the heat load of each area of ​​the electric heat conduction component changes, more accurately divides the causes of temperature data fluctuations, and comprehensively considers the heat transfer abnormality characteristics and the temperature abnormal fluctuation time lag characteristics when the heat load of each area of ​​the electric heat conduction component changes, and more accurately reflects the temperature fluctuation caused by uneven heat transfer when the heat load of the electric heat conduction component changes; the temperature abnormality factor is obtained according to the heat load difference coefficient characteristics of the areas with similar temperature fluctuation conditions of the electric heat conduction component, and the temperature abnormality factor is obtained by analyzing the cluster areas of each cluster area of ​​the electric heat conduction component. On the basis of the uneven distribution of domain heat load, the correlation coefficient of temperature change in cluster cluster area is taken into consideration, which more accurately reflects the overall temperature anomaly characteristics of the electric heat conduction component during the temperature monitoring period, and uses this as a basis to evaluate the temperature anomaly of the electric heat conduction component used for collaborative optimization, which can provide scientific data auxiliary support for the collaborative optimization of the electric heat conduction component, avoid the disadvantages of poor heat exchange performance of the electric heat conduction component affecting the normal operation of related equipment, reducing production efficiency and causing energy waste, improve the accuracy of temperature monitoring of the electric heat conduction component, and realize a temperature monitoring method and system for electric heat conduction components for collaborative optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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.

[0040] Figure 1 A flowchart of the steps of a temperature monitoring method for a collaboratively optimized electric heat conduction component provided in one embodiment of the present application;

[0041] Figure 2A flow chart for obtaining anomaly temperature factors provided in one embodiment of the present application. DETAILED DESCRIPTION

[0042] 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 the temperature monitoring method and system of the electric heat conduction component for collaborative optimization 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.

[0043] 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.

[0044] The specific scheme of the temperature monitoring method and system of the electric heat conduction component for collaborative optimization provided by the present application is described in detail below with reference to the accompanying drawings.

[0045] See also Figure 1 , which shows a flow chart of the steps of a temperature monitoring method for a collaboratively optimized electric heat conduction component provided by an embodiment of the present application, the method comprising the following steps:

[0046] Step S1, collecting a temperature data sequence of each temperature monitoring area on the electric heat conduction component in each temperature monitoring time period.

[0047] The electric heat conduction component is divided into rectangular areas with a side length of N as each temperature monitoring area. In this embodiment, the value of N is 11, and the implementer can select other values ​​according to actual conditions. Use temperature sensors evenly distributed on the electric heat conduction component to collect temperature data of each rectangular area at each collection time. In this embodiment, the time interval between each collection time is 0.5s, and the implementer can select other values ​​according to actual conditions.

[0048] Each preset time period is used as each temperature monitoring time period. At this point, all temperature data of each temperature monitoring area in the electric heat conduction component in each temperature monitoring time period are obtained. For each temperature monitoring area, the temperature data of the temperature monitoring area in each temperature monitoring time period is sequenced in time order as the temperature data sequence of each temperature monitoring area in each temperature monitoring time period. In this embodiment, the length of the preset time period is 1 hour, and the implementer can select other values ​​according to actual conditions.

[0049] Step S2, obtaining the mutation points of the temperature data sequence and the temperature fluctuation range of each mutation point; obtaining the heat exchange adjustment factor of each mutation point in each temperature monitoring area in each temperature monitoring time period based on the difference between the temperature data of the mutation point and the mean value of the temperature data in its temperature fluctuation range, the time length of the temperature fluctuation range and the uncertainty of the trend change of the temperature data in the temperature fluctuation range; obtaining the heat load change point and the heat exchange fluctuation range of each heat load change point based on the heat exchange adjustment factor; obtaining the heat transfer anomaly coefficient of each heat load change point in each temperature monitoring time period of each temperature monitoring area based on the number of temperature data in the heat exchange fluctuation range and the difference between the maximum and minimum values; obtaining the heat load characteristic factor of each heat load change point in each temperature monitoring time period of each temperature monitoring area based on the time interval between the collection moments of each heat load change point and the difference between the heat transfer anomaly coefficients of each heat load change point.

[0050] In the process of temperature monitoring of the electric heat conduction components used for collaborative optimization, external electromagnetic interference will distort the output signal of the temperature sensor and cause abnormal fluctuations in the temperature data. When the heat load of the electric heat conduction components changes, the electric heat conduction components will collaboratively optimize the temperature of each area through dynamic feedback adjustment of heat exchange uniformity to improve the heat exchange efficiency of the electric heat conduction components. The dynamic feedback adjustment of heat exchange uniformity will also cause fluctuations in the temperature data.

[0051] Specifically, the temperature fluctuations caused by external electromagnetic interference usually present random temperature data jumps and are short-lived; while the temperature data fluctuations caused by the dynamic feedback regulation of heat exchange uniformity due to changes in thermal load have a strong trend of change, and the temperature data in the electric heat conduction component area will gradually tend to be stable; the data fluctuations caused by external electromagnetic interference will interfere with the analysis of the dynamic feedback regulation of heat exchange uniformity of the electric heat conduction component, thereby leading to inaccurate assessment of the thermal load change status of the electric heat conduction component.

[0052] Based on the above analysis, the temperature data sequence of each temperature monitoring time period of each temperature monitoring area is used as input, and the SNHT (Standard Normal Homogeneity Test) mutation point detection algorithm is used to obtain each mutation point in the temperature data sequence; for each mutation point in each temperature data sequence, the time period between the acquisition time of the mutation point and the acquisition time of the next adjacent mutation point is used as the temperature fluctuation range of each mutation point; it should be noted that when the mutation point is the last mutation point in the temperature data sequence, the time period between the acquisition time of the mutation point and the last acquisition time in the temperature data sequence is used as the temperature fluctuation range of each mutation point. Among them, the SNHT (Standard Normal Homogeneity Test) mutation point detection algorithm is a well-known technology and will not be described in detail in this embodiment.

[0053] According to the above analysis, in order to reflect the fluctuation of the temperature data in the electric heat conduction component area, based on the difference between the temperature data at the mutation point and the mean value of the temperature data in its temperature fluctuation interval, the time length of the temperature fluctuation interval and the uncertainty of the trend change of the temperature data in the temperature fluctuation interval, the heat exchange adjustment factor of each mutation point in each temperature monitoring area in each temperature monitoring time period is calculated. The calculation formula is: ; In the formula, is the heat exchange adjustment factor of the i-th mutation point in each temperature monitoring area in each temperature monitoring time period; is the absolute value of the difference between the temperature data of the i-th mutation point in each temperature monitoring time period in each temperature monitoring area and the average value of all temperature data in its temperature fluctuation interval; is the time length of the temperature fluctuation interval of the i-th mutation point in each temperature monitoring area in each temperature monitoring time period; It is the Shannon entropy of the trend item strength of all temperature data in the temperature fluctuation interval of the i-th mutation point in the temperature monitoring time period; wherein, the calculation method of the trend item strength and the Shannon entropy is a well-known technology and will not be repeated in this embodiment.

[0054] It should be noted that when the fluctuation of the temperature data in the electric heat conduction component area is more likely to be caused by external electromagnetic interference rather than by the dynamic feedback adjustment of the heat exchange uniformity of the electric heat conduction component after the heat load changes, the temperature data jump degree is larger, the temperature fluctuation duration is shorter, the trend of the temperature data fluctuation is weaker, and the heat exchange adjustment factor is larger, that is, the difference between the temperature value corresponding to the mutation point and the average value of all data in the corresponding temperature fluctuation interval is larger, the time interval of the temperature fluctuation interval corresponding to the mutation point is smaller, and the Shannon entropy of the intensity of the trend item of all data in the temperature fluctuation interval corresponding to the mutation point is larger.

[0055] Furthermore, for each temperature monitoring time period in each temperature monitoring area, the heat exchange adjustment factors of all mutation points in the temperature monitoring time period are used as inputs of the threshold segmentation algorithm to obtain the optimal segmentation threshold. The threshold segmentation algorithm selected in this embodiment is the OTSU threshold segmentation algorithm, and the implementer may select other threshold segmentation algorithms according to actual conditions. Among them, the OTSU threshold segmentation algorithm is a well-known technology and will not be described in detail in this embodiment.

[0056] Furthermore, for each temperature monitoring time period in each temperature monitoring area, the mutation point in the temperature monitoring time period where the heat exchange regulation factor is less than the optimal segmentation threshold is taken as the heat load change point, and for each heat load change point in the temperature monitoring time period, the time period between the heat load node and the next heat load node is taken as the heat exchange fluctuation range of each heat load change point; it should be noted that when the heat load node is the last heat load node in the temperature monitoring time period, the time period between the heat load node and the last collection time in the temperature monitoring time period is taken as the heat exchange fluctuation range of the heat load node.

[0057] Normally, during the dynamic feedback adjustment process of the heat transfer uniformity of the electric heat conduction component, when the heat load changes frequently or the heat load changes greatly, the dynamic feedback adjustment of the heat transfer uniformity may not be able to respond in time, resulting in the failure to transfer heat in a certain area of ​​the electric heat conduction component in time, resulting in excessive temperature difference.

[0058] According to the above analysis, in order to reflect the frequent changes in the heat load of the electric heat conduction component or the changes in the heat load, based on the number of temperature data in the heat exchange fluctuation range and the difference between the maximum and minimum values, the heat transfer anomaly coefficient of each temperature monitoring period in each temperature monitoring area is obtained. The calculation formula is: ; In the formula, is the heat transfer anomaly coefficient of the jth heat load change point in each temperature monitoring period of each temperature monitoring area; is the difference between the maximum and minimum values ​​of the temperature data in the heat exchange fluctuation interval of the jth heat load change point in each temperature monitoring time period of each temperature monitoring area; is the total number of temperature data in the heat exchange fluctuation interval of the jth heat load change point in each temperature monitoring time period of each temperature monitoring area; For preset adjustment parameters, the value is 1 in this application to prevent the abnormal heat transfer coefficient from being unable to be calculated due to the adjacent heat load change points in the temperature monitoring time period.

[0059] It should be noted that when the heat load of the electric heat conduction component changes frequently or the heat load changes greatly, the heat transfer uniformity effect will be worse due to the inability of the heat exchange uniformity feedback adjustment to respond in time, the temperature range of the electric heat conduction component will be larger, the regional heat exchange time will be shorter, and the heat transfer anomaly coefficient will be larger, that is, the difference between the maximum temperature value and the minimum temperature value in the heat exchange fluctuation range corresponding to the heat load change point will be larger, and the total number of data in the heat exchange fluctuation range corresponding to the heat load change point will be smaller.

[0060] In the temperature monitoring process of the electric heat conduction component for collaborative optimization, when the abnormal temperature change caused by uneven heat transfer due to the change of heat load of the electric heat conduction component is more significant, the hysteresis of the abnormal fluctuation time of similar temperature data corresponding to each area within the neighborhood of the electric heat conduction component is stronger.

[0061] Based on the above analysis, with each temperature monitoring area as the center, a rectangular window with M temperature monitoring areas as the side length is used as the neighborhood window of each temperature monitoring area. In this embodiment, the value of M is 3, and the implementer can select other values ​​according to actual conditions.

[0062] Furthermore, for each temperature monitoring area, the time interval between the collection time of the j-th heat load change point of the temperature monitoring area in each temperature monitoring time period and the collection time of the j-th heat load change point of other temperature monitoring areas in the neighborhood window of the temperature monitoring area is calculated, and the sum of all the time intervals of the temperature monitoring area in its neighborhood window is calculated as the sum of the change point intervals of the j-th heat load change point of each temperature monitoring area in each temperature monitoring time period.

[0063] Furthermore, for each temperature monitoring area, the heat transfer anomaly coefficient of the j-th heat load change point of the temperature monitoring area in each temperature monitoring time period is calculated, and the absolute value of the difference between the heat transfer anomaly coefficient of the j-th heat load change point of other temperature monitoring areas in the neighborhood window of the temperature monitoring area is calculated, and the sum of all the absolute values ​​of the differences of the temperature monitoring area in its neighborhood window is calculated as the sum of the heat differences of the j-th heat load change point of each temperature monitoring area in each temperature monitoring time period.

[0064] Furthermore, in order to reflect the uneven heat transfer of the electric heat conduction component when the heat load changes, the heat load characteristic factor of each heat load change point in each temperature monitoring time period of each temperature monitoring area is obtained based on the change point interval and the heat difference. The calculation formula is: ; In the formula, is the heat load characteristic factor of the jth heat load change point in each temperature monitoring time period of each temperature monitoring area; is the change point interval and value of the jth heat load change point in each temperature monitoring area in each temperature monitoring time period; It is the heat difference and value of the jth heat load change point in each temperature monitoring area in each temperature monitoring time period.

[0065] It should be noted that when the uneven heat transfer presented by the electric heat conduction component when the heat load changes is more obvious, the hysteresis conditions of the abnormal fluctuations of the temperature data of each area within the neighborhood of the electric heat conduction component are more similar, and the time interval between the moments when similar uneven heat transfer characteristics appear in each area within the neighborhood is longer, that is, the larger the change point interval and value, and the smaller the difference in the heat transfer anomaly coefficient of the heat load change point between any area of ​​the electric heat conduction component and the corresponding temperature data sequence of all other areas in its neighborhood window, that is, the smaller the heat difference and value, the larger the heat load characteristic factor; conversely, the larger the heat load characteristic factor.

[0066] At this point, the heat load characteristic factor of each heat load change point in each temperature monitoring time period of each temperature monitoring area is obtained.

[0067] Step S3, based on the correlation between temperature data sequences and the correlation between heat load characteristic factors, obtain the temperature change correlation coefficient and heat load difference coefficient of each cluster in each temperature monitoring time period; based on the temperature change correlation coefficient and heat load difference coefficient, obtain the temperature anomaly factor of each temperature monitoring time period.

[0068] The overall temperature condition of the electric heat conduction component cannot be evaluated only by the heat load characteristic factors of all heat load change points in each area of ​​the electric heat conduction component during the temperature monitoring period, and the temperature correlation change characteristics between the various areas of the electric heat conduction component are ignored, which makes the temperature evaluation of the electric heat conduction component inaccurate, thereby affecting the accurate judgment of the heat exchange performance and heat exchange efficiency of the electric heat conduction component.

[0069] Based on the above analysis, for each temperature monitoring time period in each temperature monitoring area, a sequence composed of heat load characteristic factors of all heat load change points within the temperature monitoring time period is sorted in chronological order as the heat load characteristic sequence of the temperature monitoring time period in each temperature monitoring area.

[0070] Furthermore, for each temperature monitoring time period, the heat load characteristic sequences of all temperature monitoring areas in the temperature monitoring time period are used as nodes in the undirected graph to form an undirected graph, and the undirected graph is used as the input of the clustering algorithm to cluster the nodes in the undirected graph, and the inverse of the correlation coefficient between the heat load characteristic sequences of each node is used as the metric distance between the nodes to obtain each cluster cluster. The clustering algorithm selected in this embodiment is the Chameleon clustering algorithm, and the correlation coefficient is the Pearson correlation coefficient. The implementer can select other clustering algorithms and correlation coefficients according to actual conditions; among which, the Pearson correlation coefficients of the Chameleon clustering algorithm are well-known technologies and are not described in detail in this embodiment.

[0071] The beneficial effect of using the Chameleon clustering algorithm in this embodiment to obtain clusters of each area of ​​the electric heat conduction component is that: compared with the traditional data clustering algorithm, the Chameleon clustering algorithm can process clusters with various shapes, and can more accurately divide the areas with similar thermal load characteristics of the electric heat conduction component. The Chameleon clustering algorithm uses dynamic modeling to determine the similarity between a pair of clusters, so that the local thermal load characteristics of each area of ​​the electric heat conduction component can be fully considered by the algorithm.

[0072] Further, according to the above analysis, in order to reflect the temperature synergistic change characteristics between the various regions of the electric heat conduction component, based on the correlation between the temperature data sequences, the temperature change correlation coefficient of each cluster in each temperature monitoring time period is obtained, and the calculation formula is: ; In the formula, is the temperature change correlation coefficient of the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the total number of regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; , are the temperature data sequences of the xth and yth temperature monitoring areas in the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the temperature data series and The cosine similarity between .

[0073] It should be noted that when the temperature synergistic change characteristics between the various regions of the electric heat conduction component are more obvious, the similarity of the temperature data change conditions between the various regions of the electric heat conduction component due to the change in heat load is higher, and the temperature change correlation coefficient is stronger, that is, the cumulative cosine similarity between the corresponding temperature data sequences of all regions in the cluster in the electric heat conduction component is greater.

[0074] Under normal circumstances, when the difference in heat load characteristics between areas with similar temperature fluctuation conditions of the electric heat conduction component is greater, it means that the phenomenon that heat at the corresponding position of the electric heat conduction component in the area with similar temperature fluctuation conditions cannot be transferred in time is more obvious, and the heat exchange efficiency of the electric heat conduction component in the similar area is lower.

[0075] Based on the above analysis, in order to reflect the heat transfer efficiency of the electric heat conduction component, based on the correlation between the heat load characteristic sequences of each cluster, the heat load difference coefficient of each cluster in each temperature monitoring time period is obtained. The calculation formula is: ; In the formula, is the heat load difference coefficient of the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the total number of regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; , are the heat load characteristic sequences corresponding to the xth and yth regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the heat load characteristic sequence , JS divergence between .

[0076] It should be noted that when the phenomenon that the heat of the electric heat conduction component cannot be transferred in time is more significant, the greater the difference between the heat load characteristics between the areas with similar temperature fluctuation conditions in the electric heat conduction component, the greater the heat load difference coefficient of the cluster, that is, the greater the JS divergence accumulation result between the corresponding heat load characteristic sequences of all areas in the same cluster in the electric heat conduction component, the greater the heat load difference coefficient obtained at this time, and the lower the heat exchange efficiency of the electric heat conduction component at the corresponding position of the cluster; conversely, the smaller the heat load difference coefficient obtained. Among them, JS divergence is a well-known technology and is not described in detail in this embodiment.

[0077] When the temperature abnormal fluctuation degree of each position of the electric heat conduction component corresponding to the cluster with a strong temperature change correlation coefficient in the temperature monitoring time period is greater, it means that the heat load distribution at each area of ​​the electric heat conduction component is more uneven, and further, it means that the heat exchange performance of the electric heat conduction component used for collaborative optimization is worse.

[0078] Further, according to the above analysis, in order to reflect the uneven distribution of heat load in the area with a strong temperature change correlation coefficient in the electric heat conduction component, the temperature anomaly factor of each temperature monitoring time period is calculated based on the temperature change correlation coefficient and the heat load difference coefficient. The calculation method is: calculate the product of the temperature change correlation coefficient and the heat load difference coefficient of each cluster of the electric heat conduction component in each temperature monitoring time period, and use the normalized value of the accumulated result of all the products in the temperature monitoring time period as the temperature anomaly factor of each temperature monitoring time period. Among them, the flow chart for obtaining the temperature anomaly factor is as follows: Figure 2 shown.

[0079] When the heat transfer performance of the electric heat conduction component is lower and the heat transfer efficiency is worse during the temperature monitoring period, the uneven distribution of heat load in the area with a strong temperature change correlation coefficient in the electric heat conduction component is more significant, and the temperature anomaly factor of the electric heat conduction component is larger, that is, the product of the temperature change correlation coefficient corresponding to all clusters in the electric heat conduction component and the heat load difference coefficient of the clusters is larger.

[0080] At this point, the temperature anomaly factor of the electric heat conduction component in each temperature monitoring time period is obtained.

[0081] Step S4, monitoring the temperature of the electric heat conduction component based on the temperature anomaly factor.

[0082] A preset temperature abnormality threshold H of the electric heat conduction component is set. When the temperature abnormality factor of the electric heat conduction component in the temperature monitoring time period is less than the preset temperature abnormality threshold H, it is considered that the electric heat conduction component in the current temperature monitoring time period operates well, heat can be transferred in time, heat exchange performance is strong, and heat exchange efficiency is high, that is, the temperature of the electric heat conduction component is normal; when the temperature abnormality factor of the electric heat conduction component in the temperature monitoring time period is greater than or equal to the preset temperature abnormality threshold H, it is considered that the heat load distribution at each position of the electric heat conduction component in the current temperature monitoring time period is relatively uniform, the heat transfer effect at each position of the electric heat conduction component is poor, and the heat exchange efficiency is low, that is, the temperature of the electric heat conduction component is abnormal. At this time, the operation of the electric heat conduction component used for collaborative optimization should be stopped in time, and relevant personnel should be notified to repair the electric heat conduction component to avoid damage to related equipment components caused by poor heat exchange performance of the electric heat conduction component, which will reduce production efficiency and waste energy. In this embodiment, the preset temperature abnormality threshold H is 0.6, and the implementer can select other values ​​according to actual conditions.

[0083] Thus, a temperature monitoring method and system of an electric heat conduction component for collaborative optimization can be realized through the above-mentioned method.

[0084] Based on the same inventive concept as the above method, an embodiment of the present application also provides a temperature monitoring system for an electric heat conduction component for collaborative optimization, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the temperature monitoring methods for electric heat conduction components for collaborative optimization are implemented.

[0085] 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.

[0086] The various embodiments in the present application 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.

[0087] 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 temperature monitoring method for an electric heat conduction component for collaborative optimization, characterized in that: The method comprises the following steps: Collecting temperature data sequences of each temperature monitoring area on the electric heat conduction component in each temperature monitoring time period; Obtain the mutation points of the temperature data sequence and the temperature fluctuation range of each mutation point; Based on the difference between the temperature data of the mutation point and the mean value of the temperature data in its temperature fluctuation interval, the time length of the temperature fluctuation interval and the uncertainty of the trend change of the temperature data in the temperature fluctuation interval, the heat exchange adjustment factor of each mutation point in each temperature monitoring area in each temperature monitoring time period is obtained; Based on the heat exchange adjustment factor, the heat load change point and the heat exchange fluctuation range of each heat load change point are obtained; Based on the number of temperature data in the heat exchange fluctuation interval and the difference between the maximum and minimum values, the heat transfer anomaly coefficient of each heat load change point in each temperature monitoring time period of each temperature monitoring area is obtained; Based on the time interval between the acquisition moments of each heat load change point and the difference between the heat transfer anomaly coefficients of each heat load change point, the heat load characteristic factor of each heat load change point in each temperature monitoring time period of each temperature monitoring area is obtained; Based on the correlation between temperature data sequences and the correlation between heat load characteristic factors, the temperature change correlation coefficient and heat load difference coefficient of each cluster in each temperature monitoring time period are obtained; Based on the temperature change correlation coefficient and the heat load difference coefficient, the temperature anomaly factor of each temperature monitoring time period is obtained, and the temperature of the electric heat conduction component is monitored based on the temperature anomaly factor.

2. The temperature monitoring method of an electric heat conduction component for collaborative optimization according to claim 1, characterized in that: The step of obtaining the mutation points of the temperature data sequence and the temperature fluctuation range of each mutation point includes: The temperature data sequence of each temperature monitoring time period in each temperature monitoring area is taken as input, and a mutation point detection algorithm is used to obtain all mutation points in the temperature data sequence of each temperature monitoring time period in each temperature monitoring area; for each mutation point in each temperature data sequence, the time period between the collection time of the mutation point and the collection time of the next adjacent mutation point is taken as the temperature fluctuation range of each mutation point.

3. The temperature monitoring method of an electric heat conduction component for collaborative optimization according to claim 1, characterized in that: The method for obtaining the heat exchange adjustment factor is: For each mutation point in each temperature monitoring time period of each temperature monitoring area, the mean of all temperature data in the temperature fluctuation interval of the mutation point is calculated, the absolute value of the difference between the temperature data of the mutation point and the mean is calculated, the ratio of the absolute value of the difference to the time length of the temperature fluctuation interval of the mutation point is calculated, the Shannon entropy of the intensity of the trend term of all temperature data in the temperature fluctuation interval of the mutation point is calculated, and the product of the ratio and the Shannon entropy is used as the heat exchange regulation factor of each mutation point in each temperature monitoring time period of each temperature monitoring area.

4. The temperature monitoring method of an electric heat conduction component for collaborative optimization according to claim 1, characterized in that: The step of obtaining the heat load change point and the heat exchange fluctuation range of each heat load change point includes: The heat exchange adjustment factors of all mutation points in each temperature monitoring time period of each temperature monitoring area are used as inputs of the threshold segmentation algorithm to obtain the optimal segmentation threshold; For each temperature monitoring time period in each temperature monitoring area, the mutation point in the temperature monitoring time period where the heat exchange regulation factor is less than the optimal segmentation threshold is taken as the heat load change point. For each heat load change point in the temperature monitoring time period, the time period between the collection time of the heat load node and the collection time of the next heat load node is taken as the heat exchange fluctuation range of each heat load change point.

5. The temperature monitoring method of an electric heat conduction component for collaborative optimization according to claim 1, characterized in that: The method for obtaining the heat transfer anomaly coefficient is: For each heat load change point in each temperature monitoring time period of each temperature monitoring area, the difference between the maximum value and the minimum value of the temperature data in the heat exchange fluctuation interval of the heat load change point is calculated, and the total number of temperature data in the heat exchange fluctuation interval of the heat load change point and the sum of the preset adjustment parameters are calculated, and the ratio of the difference to the sum is used as the heat transfer anomaly coefficient of each heat load change point in each temperature monitoring time period of each temperature monitoring area.

6. The temperature monitoring method of an electric heat conduction component for collaborative optimization according to claim 1, characterized in that: The method for obtaining the heat load characteristic factor is: With each temperature monitoring area as the center, a rectangular window with a side length of a preset number of temperature monitoring areas as the side length is used as a neighborhood window of each temperature monitoring area; For each temperature monitoring area, calculate the time interval between the collection time of the jth heat load change point of the temperature monitoring area in each temperature monitoring time period and the collection time of the jth heat load change point of each other temperature monitoring area in the neighborhood window of the temperature monitoring area, calculate the sum of all the time intervals of the temperature monitoring area in its neighborhood window, and use it as the sum of the change point intervals of the jth heat load change point of each temperature monitoring area in each temperature monitoring time period; Calculate the heat transfer anomaly coefficient of the j-th heat load change point of the temperature monitoring area in each temperature monitoring time period, and the absolute value of the difference between the heat transfer anomaly coefficient of the j-th heat load change point of each other temperature monitoring area in the neighborhood window of the temperature monitoring area, and calculate the sum of all the absolute values ​​of the difference of the temperature monitoring area in its neighborhood window as the heat difference sum value of the j-th heat load change point of each temperature monitoring area in each temperature monitoring time period; The heat load characteristic factor is a normalized value of the ratio of the change point interval and value of each heat load change point in each temperature monitoring time period of each temperature monitoring area to the heat difference and value.

7. The temperature monitoring method of an electric heat conduction component for collaborative optimization according to claim 1, characterized in that: The method for obtaining the temperature change correlation coefficient is: For each temperature monitoring time period of each temperature monitoring area, a sequence of heat load characteristic factors of all heat load change points within the temperature monitoring time period is sorted in chronological order as the heat load characteristic sequence of the temperature monitoring time period of each temperature monitoring area; For each temperature monitoring time period, the heat load characteristic sequences of all temperature monitoring areas in the temperature monitoring time period are used as nodes in the undirected graph to form an undirected graph, and the undirected graph is used as the input of the clustering algorithm to obtain each clustering cluster; The calculation formula of the temperature change correlation coefficient is: ; In the formula, is the temperature change correlation coefficient of the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the total number of regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; , are the temperature data sequences of the xth and yth temperature monitoring areas in the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the temperature data series and The cosine similarity between .

8. The temperature monitoring method of an electric heat conduction component for collaborative optimization according to claim 7, characterized in that: The calculation formula of the heat load difference coefficient is: ; In the formula, is the heat load difference coefficient of the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the total number of regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; , are the heat load characteristic sequences corresponding to the xth and yth regions in the pth cluster of the electric heat conduction component in each temperature monitoring time period; is the heat load characteristic sequence , JS divergence between .

9. The temperature monitoring method of an electric heat conduction component for collaborative optimization according to claim 1, characterized in that: The step of obtaining the temperature anomaly factor of each temperature monitoring time period and monitoring the temperature of the electric heat conduction component based on the temperature anomaly factor includes: Calculate the product of the temperature change correlation coefficient and the heat load difference coefficient of each cluster of the electric heat conduction component in each temperature monitoring time period, and use the normalized value of the accumulated result of all the products in the temperature monitoring time period as the temperature anomaly factor of each temperature monitoring time period; When the temperature anomaly factor in the temperature monitoring period is less than the preset temperature anomaly threshold, the temperature of the electric heat conduction component is normal; when the temperature anomaly factor in the temperature monitoring period is greater than or equal to the preset temperature anomaly threshold, the temperature of the electric heat conduction component is abnormal.

10. An electric heat conduction component temperature monitoring system for collaborative optimization, 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 the temperature monitoring method of an electric heat conduction component for collaborative optimization as described in any one of claims 1 to 9 are implemented.

Images