A coating storage environment monitoring method and system based on data processing

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for monitoring a paint storage environment based on data processing. The method comprises the following steps: collecting a plurality of temperature data, dividing the temperature data sequence into a plurality of data intervals; obtaining the degree of change of the temperature data in each data interval; obtaining the confidence level of the degree of change of the temperature data in each data interval based on the difference in sampling time between adjacent temperature data in the temperature data sequence of each data interval; using the confidence level of the degree of change of the temperature data in each data interval and the degree of change of the temperature data, iteratively correcting each data interval to obtain the optimal correction interval for each data interval; and monitoring the paint storage environment using the optimal correction interval. The present invention improves the accuracy of abnormal temperature data monitoring in the paint storage environment.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a coating storage environment monitoring method and system based on data processing. Background Art

[0002] Excessively high temperatures can accelerate the evaporation of solvents in paints, increasing the paint's viscosity and reducing its fluidity, thus affecting its application performance. For example, some water-based paints may dry too quickly in high-temperature environments, resulting in an uneven coating and reduced smoothness and gloss. Excessively low temperatures can cause the water in the paint to freeze, disrupting its structure and causing demulsification and delamination. For example, latex paint can freeze at low temperatures, and upon thawing, the emulsion particles aggregate, causing the paint to degrade in performance or even become unusable.

[0003] The patent application document currently published with the publication number CN116608904A discloses a real-time monitoring method and system for the safety status of a hydrogen storage tank. The method collects temperature data sequences and strain data sequences of monitoring points in the hydrogen storage tank during an initial monitoring period; determines the compression moment when the hydrogen in the hydrogen storage tank begins to be compressed based on the strain data sequences of the monitoring points in the initial monitoring period; calculates a first interval division number based on the degree of temperature anomaly corresponding to the temperature data sequence after the compression moment; calculates a second interval division number based on the degree of strain anomaly corresponding to the strain data sequence after the compression moment; uses the HBOS anomaly monitoring algorithm to perform anomaly monitoring on the temperature data sequence based on the first interval division number, and uses the HBOS anomaly monitoring algorithm to perform anomaly monitoring on the temperature data sequence based on the second interval division number.

[0004] In the scenario of monitoring paint storage temperature, the Histogram-based Outlier Score (HBOS) algorithm sorts the temperature data and divides it into different data intervals according to a fixed interval width. It then obtains the density of each data interval. The higher the density of the data interval, the lower the temperature data anomaly score. However, temperature changes in the paint storage environment are often caused by weather changes or temperature control equipment failures. The abnormal data changes caused by such an abnormality are often relatively small when they first occur, and the difference between them and the changes in normal and stable temperature data is not obvious. As a result, the data intervals divided by the fixed interval width of the HBOS (Histogram-based Outlier Score) algorithm may contain both normal and abnormal data, and the abnormal data will be subsequently identified as normal data. Summary of the Invention

[0005] In order to solve the technical problem that the difference between the abnormal data generated when an abnormal situation just occurs and the normal and stable temperature data is not obvious, resulting in the data interval divided by the fixed interval width of the HBOS (Histogram-based Outlier Score) algorithm may contain normal and abnormal data, resulting in inaccurate anomaly detection, the present invention provides a coating storage environment monitoring method and system based on data processing.

[0006] In a first aspect, the present invention provides a coating storage environment monitoring method based on data processing, which adopts the following technical solutions:

[0007] A coating storage environment monitoring method based on data processing comprises the following steps:

[0008] Collect a number of temperature data, divide the temperature data sequence into several data intervals; obtain the degree of temperature data change in the data interval ; n represents the number of all temperature data in the data interval; Represents the i-th temperature data in the temperature data sequence of the data interval; Represents the jth temperature data in the temperature data sequence of the data interval; norm() represents the linear normalization function; obtains the confidence level of the temperature data change degree of the data interval:

[0009] , n represents the number of all temperature data in the data interval; Represents the sampling time corresponding to the i-th temperature data in the temperature data sequence of the data interval; Indicates the sampling time corresponding to the i+1th temperature data in the temperature data sequence of the data interval; Indicates taking the absolute value; exp() indicates an exponential function with a natural constant as the base;

[0010] The product of the confidence level of the temperature data change degree of the data interval and the temperature data change degree is used as the true temperature change degree of the data interval; based on the true temperature change degree, the data interval is iteratively corrected to obtain the optimal correction interval of the data interval; based on the optimal correction interval, the anomaly score of each temperature data is obtained, and the paint storage environment is monitored.

[0011] The innovation of the present invention lies in the introduction of a dynamic data interval width adjustment strategy. First, the temperature data is divided according to a fixed data interval width using the traditional HBOS algorithm to obtain several data intervals. The degree of change of the temperature data in the data interval and the credibility of the degree of change are evaluated and the width of the data interval is iteratively adjusted accordingly to obtain the optimal correction interval for each data interval. It ensures that the distribution of temperature data in the optimal correction interval can reasonably distinguish abnormal data changes, effectively reducing the possibility of some abnormal data being misdetected; the abnormal score of each temperature data obtained based on the distribution of temperature data in the optimal correction interval is more accurate, making subsequent abnormal monitoring of the paint storage environment more accurate.

[0012] Preferably, dividing the temperature data sequence into several data intervals includes:

[0013] The initial width of the preset data interval is Y. The temperature data sequence is input into the HBOS algorithm according to the initial width of the data interval, and the temperature data sequence is divided into several data intervals.

[0014] This facilitates subsequent analysis of the degree of change in temperature data within the data interval.

[0015] Preferably, obtaining the temperature data sequence of the data interval includes:

[0016] The temperatures in the data interval are sorted in ascending order according to their sampling time to obtain the temperature data sequence of the data interval.

[0017] Preferably, the iterative correction of the data interval according to the actual temperature change degree to obtain the optimal correction interval width of the data interval includes:

[0018] Preset correction parameter a and threshold parameter T1, the first correction interval of the first data interval , where Y represents the initial width of the data interval; Represents the actual temperature change degree of the first data interval; if The difference between the actual temperature change degree of the first correction interval of the first data interval and the actual temperature change degree of the first correction interval is greater than the threshold parameter T1. The second correction interval of the first data interval is obtained based on the first correction interval and the actual temperature change degree of the first correction interval; and so on, until the difference between the actual temperature change degree of the H-1th correction interval of the first data interval and its Hth correction interval is less than or equal to the threshold parameter T1, the Hth correction interval is used as the optimal correction interval of the first data interval; based on the optimal correction interval, several optimal correction intervals are obtained.

[0019] It ensures that the distribution of temperature data in the optimal correction interval can reasonably distinguish abnormal data changes, effectively reducing the possibility of some abnormal data being misdetected.

[0020] Preferably, obtaining a plurality of optimal correction intervals according to the optimal correction interval includes:

[0021] For the second data interval, the optimal correction interval of the first data interval is used as the initial width of the second data interval. According to the method for obtaining the optimal correction interval of the first data interval, the optimal correction interval of the second data interval is obtained. Similarly, the optimal correction interval of each data interval is obtained.

[0022] Preferably, obtaining the abnormality score of each temperature data according to the optimal correction interval and monitoring the paint storage environment includes:

[0023] All temperature data within the optimal correction interval are input into the HOBS algorithm to obtain the anomaly score of each temperature data. The anomaly score of each temperature data is used as the smoothing parameter value of each temperature data, and the exponential smoothing algorithm is used to obtain the predicted value of each temperature data.

[0024] A warning coefficient C is preset. For any temperature data, if the absolute value of the difference between the predicted value and the actual value of the temperature data is greater than the warning coefficient C, the warning mechanism is triggered to notify relevant personnel in a timely manner.

[0025] Improved the accuracy of abnormal monitoring of the paint storage environment.

[0026] Preferably, the collecting of a plurality of temperature data includes:

[0027] The preset sampling time is 1 minute / time, and the data is collected for a total of 24 hours. The temperature sensor is placed in the paint storage area to collect every temperature data in the paint storage environment in real time.

[0028] This facilitates subsequent analysis of temperature data.

[0029] In a second aspect, the present invention provides a paint storage environment monitoring system based on data processing, which adopts the following technical solutions:

[0030] A paint storage environment monitoring system based on data processing includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned paint storage environment monitoring method based on data processing is implemented.

[0031] By adopting the above technical solution, the above-mentioned data processing-based paint storage environment monitoring method is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is made based on the memory and the processor for easy use.

[0032] The present invention has the following technical effects: The purpose of the present invention is to introduce a dynamic data interval width adjustment strategy, first according to the fixed data interval width, use the traditional HBOS algorithm to divide the temperature data to obtain several data intervals, evaluate the degree of change of the temperature data in the data interval and the credibility of the degree of change and iteratively adjust the width of the data interval accordingly, to obtain the optimal correction interval for each data interval, ensure that the distribution of temperature data in the optimal correction interval can reasonably distinguish abnormal data changes, and effectively reduce the possibility of some abnormal data being misdetected; the abnormal score of each temperature data obtained based on the distribution of temperature data in the optimal correction interval is more accurate, so that subsequent abnormal monitoring of the paint storage environment is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] By reading the detailed description below with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding numbers represent the same or corresponding parts.

[0034] Figure 1 This is a flow chart of a method for monitoring a coating storage environment based on data processing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0036] It should be understood that when the terms "first," "second," and the like are used in the claims, description, and drawings of the present invention, they are merely used to distinguish between different objects, rather than to describe a specific order. The terms "comprise" and "comprising" used in the description and claims of the present invention indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0037] The embodiment of the present invention discloses a coating storage environment monitoring method based on data processing, referring to Figure 1, including steps S1 to S4:

[0038] S1: Collect some temperature data.

[0039] In the implementation of the present invention, the preset sampling time is 1 minute / time, and the data is collected for a total of 24 hours. The temperature sensor is placed in the paint storage area, and each temperature data in the paint storage environment is collected in real time. Each temperature data is sorted in turn to obtain a temperature data sequence.

[0040] S2: Divide the temperature data sequence into several data intervals; obtain the degree of change of the temperature data in each data interval based on the difference between the temperature data in each data interval; obtain the confidence level of the degree of change of the temperature data in each data interval based on the difference in sampling time between adjacent temperature data in the temperature data sequence of each data interval.

[0041] It should be noted that the temperature data of paint storage is easily affected by factors such as weather interference and internal temperature control equipment failure, which may lead to abnormal data in the temperature data. Anomalies need to be discovered in a timely manner. In the temperature monitoring scenario of paint storage, the traditional histogram anomaly detection algorithm sorts the temperature data and divides all the temperature data into different data intervals according to a fixed interval width. The density of the data interval where each temperature data is located is obtained. The higher the density of the data interval, the lower the anomaly score of the temperature data.

[0042] However, the temperature changes in the paint storage environment are often caused by temperature anomalies due to weather changes or temperature control equipment failures. The abnormal data changes generated when this abnormal situation first occurs are often relatively small, and the difference in changes from the normal and stable temperature data is not obvious. This leads to the fact that the data divided by a fixed interval width may contain normal and abnormal data, making subsequent anomaly detection inaccurate. Since the temperature data is relatively stable under normal circumstances, after using a fixed interval width to divide the temperature data into several data intervals, it is first necessary to analyze the degree of change of the temperature data in the data interval. If the degree of change of the temperature data in a certain data interval is large, it may mean that there may be abnormal change data in the temperature data in the data interval, that is, the degree of change of the temperature data in the data interval is large.

[0043] Specifically, the initial width of the data interval is preset to Y. Based on this initial width, the temperature data sequence is input into the HBOS algorithm to divide the temperature data sequence into a number of data intervals. The HBOS algorithm is conventional technology and will not be described in detail in this embodiment. In this embodiment of the present invention, the initial width of the data interval is preset to Y = 20 degrees Celsius. In other embodiments, the value of Y may be preset by the implementer based on the specific implementation.

[0044] According to the difference between the temperature data in each data interval, the specific operation of obtaining the degree of change of the temperature data in each data interval is:

[0045] This embodiment is described using any data interval as an example;

[0046] Sort the temperatures in the data interval in ascending order of their sampling time to obtain the temperature data sequence of the data interval;

[0047] ;

[0048] Where S represents the degree of change of temperature data in the data interval; n represents the number of all temperature data in the data interval; Represents the i-th temperature data in the temperature data sequence of the data interval; Represents the jth temperature data in the temperature data sequence of the data interval; norm() represents the linear normalization function.

[0049] It should be noted that the greater the degree of change in the temperature data in the data interval, the greater the difference between the temperature data in the data interval, that is, the change in the temperature data in the data interval is non-stationary, and there may be temperature data that suddenly deviates from the stationary state.

[0050] At this point, the degree of temperature data change in each data interval is obtained.

[0051] It should be noted that, since the data interval division is to divide the temperature data distributed in a temperature range into an interval, the temperature data in the data interval may be at different time periods of a day; the degree of change of the temperature data in the data interval represents the fluctuation of the temperature data in the overall data interval; since the characteristics of the abnormal data distribution are ignored, that is, the abnormal data caused by factors such as weather interference and equipment failure often appear continuously in a short period of time, it means that the data of abnormal temperature changes are relatively concentrated in a certain local time period; if the time interval between any temperature data and the previous temperature data in the temperature data sequence of the data interval is smaller, if the degree of change of the temperature data in the data interval is larger, the possibility of abnormal data in the data interval is greater, indicating that the temperature data in the data interval is more likely to be collected continuously for a period of time.

[0052] Preferably, in some embodiments of the present invention, based on the difference in sampling time between adjacent temperature data in the temperature data sequence of each data interval, a specific formula for obtaining the confidence level of the temperature data change degree of each data interval is:

[0053] ;

[0054] Where, Indicates the confidence level of the temperature data change within the data interval; n represents the number of all temperature data within the data interval; Represents the sampling time corresponding to the i-th temperature data in the temperature data sequence of the data interval; Indicates the sampling time corresponding to the i+1th temperature data in the temperature data sequence of the data interval; It means taking the absolute value; exp() means the exponential function with a natural constant as the base.

[0055] It should be noted that the smaller the difference in sampling time between adjacent temperature data in the temperature data sequence of the data interval, the smaller the difference in sampling time between adjacent temperature data, indicating that the adjacent temperature data were collected in a short time, and the degree of temperature change in the data interval is more likely to reflect the real temperature fluctuation, that is, the higher the credibility of the degree of temperature data change in the data interval.

[0056] At this point, the confidence level of the temperature data variation degree in each data interval is obtained.

[0057] S3: Using the confidence level and the degree of temperature data change in each data interval, iteratively correct each data interval to obtain the optimal correction interval for each data interval, and divide the temperature data sequence into several optimal correction intervals.

[0058] It should be noted that the fixed-width data interval in the traditional HBOS algorithm may not fully reflect the complex change patterns that may occur in the actual environment, especially the initial abnormal data is easily classified into the interval where the normal data is located, resulting in inaccurate calculation of the abnormal score; if there is obvious temperature data change in the data interval, and the higher the confidence level, it means that the data interval may have abnormal temperature data distribution, and then the width of the current data interval needs to be adjusted. After each correction, it is necessary to analyze whether there is a difference in the data changes in the data interval before and after the correction. If the difference is very small or equal, it means that the data change in the data interval tends to be stable and has reached the optimal interval width, and then through iterative calculation, the optimized data interval is obtained; the data distribution in the optimized data interval can reasonably distinguish abnormal data changes.

[0059] In the embodiment of the present invention, a correction parameter a=0.5 and a threshold parameter T1=0.03 are preset, the product of the confidence level of the temperature data change degree of the first data interval and the temperature data change degree thereof is recorded as the true temperature change degree of the first data interval; the sum of the true temperature change degree of the first data interval and the correction parameter a is recorded as the first sum value; the ratio of the preset initial width of the data interval to the first sum value is rounded up to an integer value, which is used as the first correction interval of the first data interval;

[0060] The specific formula is:

[0061] ;

[0062] Where, Represents the first correction interval of the first data interval; Y represents the initial width of the data interval; Represents the actual temperature change degree of the first data interval; Represents the ceiling symbol.

[0063] According to the method for obtaining the true temperature change degree of the data interval, the true temperature change degree of the first correction interval is obtained; if the difference between the true temperature change degree of the first data interval and the true temperature change degree of the first correction interval is greater than the threshold parameter T1, the sum of the true temperature change degree of the first correction interval and the correction parameter a is recorded as the second sum value, and the ratio of the first correction interval to the second sum value is rounded up as the second correction interval of the first data interval; and so on, until the difference between the true temperature change degree of the H-1th correction interval of the first data interval and its Hth correction interval is less than or equal to the threshold parameter T1, and the Hth correction interval is taken as the optimal correction interval of the first data interval;

[0064] It should be noted that Represents the actual temperature variation degree of the data interval. The larger the value, the more credible the fluctuation of temperature data in the data interval. In this case, abnormal temperature data exists in the data interval, and the interval width needs to be reduced to distinguish the abnormal temperature data. Conversely, the data interval width needs to be increased to ensure that more normal data is divided into this data interval.

[0065] It should be further explained that if the difference between the actual temperature change degree of the latest correction interval and the actual temperature change degree of the previous correction interval is less than or equal to the threshold parameter T1, it means that the data change in the data interval before and after correction has stabilized and has reached the optimal interval width; otherwise, it means that there is still abnormal data in the data interval after correction, and it is necessary to continue iterative correction.

[0066] Specifically, for the second data interval, the optimal correction interval of the first data interval is used as the initial width of the second data interval. The optimal correction interval of the second data interval is obtained through the above method. Similarly, the optimal correction interval of each data interval is obtained, and the temperature data sequence is divided into several optimal correction intervals using the optimal correction interval.

[0067] S4: Monitor the paint storage environment through the optimal correction interval.

[0068] Specifically, all temperature data within the optimal correction interval are input into the HOBS algorithm to obtain the anomaly score of each temperature data, and the anomaly score of each temperature data is used as the smoothing parameter value of each temperature data, and the exponential smoothing algorithm is used to obtain the predicted value of each temperature data;

[0069] A warning coefficient C=1 is preset. For any temperature data, if the absolute value of the difference between the predicted value and the actual value of the temperature data is greater than the warning coefficient, the warning mechanism is triggered to notify relevant personnel in time.

[0070] An embodiment of the present invention also discloses a paint storage environment monitoring system based on data processing, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a paint storage environment monitoring method based on data processing according to the present invention is implemented.

[0071] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0072] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory, dynamic random access memory, static random access memory, enhanced dynamic random access memory, high bandwidth memory, hybrid memory cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium may be part of, accessible to, or connectable to the device.

[0073] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

[0074] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A coating storage environment monitoring method based on data processing, characterized in that: Including steps: Collect a number of temperature data, divide the temperature data sequence into several data intervals; obtain the degree of temperature data change in the data interval ; n represents the number of all temperature data in the data interval; Represents the i-th temperature data in the temperature data sequence of the data interval; Represents the jth temperature data in the temperature data sequence of the data interval; norm() represents the linear normalization function; obtains the confidence level of the temperature data change degree of the data interval: , n represents the number of all temperature data in the data interval; Represents the sampling time corresponding to the i-th temperature data in the temperature data sequence of the data interval; Indicates the sampling time corresponding to the i+1th temperature data in the temperature data sequence of the data interval; Indicates taking the absolute value; exp() indicates an exponential function with a natural constant as the base; The product of the confidence level of the temperature data change degree in the data interval and the temperature data change degree is taken as the actual temperature change degree of the data interval; Iteratively correcting the data interval according to the actual temperature change degree to obtain the optimal correction interval width of the data interval, including: Preset correction parameter a and threshold parameter T1, the first correction interval of the first data interval , where Y represents the initial width of the data interval; Represents the actual temperature change degree of the first data interval; if If the difference between the actual temperature change degree of the first correction interval of the first data interval and the actual temperature change degree of the first correction interval is greater than the threshold parameter T1, the second correction interval of the first data interval is obtained based on the first correction interval and the actual temperature change degree of the first correction interval; and so on, until the difference between the actual temperature change degree of the H-1th correction interval of the first data interval and the Hth correction interval is less than or equal to the threshold parameter T1, the Hth correction interval is used as the optimal correction interval of the first data interval; and based on the optimal correction interval, several optimal correction intervals are obtained, including: For the second data interval, the optimal correction interval of the first data interval is used as the initial width of the second data interval. According to the method for obtaining the optimal correction interval of the first data interval, the optimal correction interval of the second data interval is obtained, and so on, the optimal correction interval of each data interval is obtained; according to the optimal correction interval, the abnormality score of each temperature data is obtained, and the paint storage environment is monitored.

2. The coating storage environment monitoring method based on data processing according to claim 1 is characterized in that: The temperature data sequence is divided into several data intervals, including: The initial width of the preset data interval is Y. The temperature data sequence is input into the HBOS algorithm according to the initial width of the data interval, and the temperature data sequence is divided into several data intervals.

3. The coating storage environment monitoring method based on data processing according to claim 1 is characterized in that: The acquisition of the temperature data sequence of the data interval includes: The temperatures in the data interval are sorted in ascending order according to their sampling time to obtain the temperature data sequence of the data interval.

4. The coating storage environment monitoring method based on data processing according to claim 1 is characterized in that: The method of obtaining an abnormality score of each temperature data according to the optimal correction interval and monitoring the paint storage environment includes: All temperature data within the optimal correction interval are input into the HOBS algorithm to obtain the anomaly score of each temperature data. The anomaly score of each temperature data is used as the smoothing parameter value of each temperature data, and the exponential smoothing algorithm is used to obtain the predicted value of each temperature data. A warning coefficient C is preset. For any temperature data, if the absolute value of the difference between the predicted value and the actual value of the temperature data is greater than the warning coefficient C, the warning mechanism is triggered to notify relevant personnel in a timely manner.

5. The coating storage environment monitoring method based on data processing according to claim 1 is characterized in that: The collecting of a plurality of temperature data includes: The preset sampling time is 1 minute / time, and the total sampling time is 24 hours. The temperature sensor is placed in the paint storage area to collect every temperature data in the paint storage environment in real time.

6. A coating storage environment monitoring system based on data processing, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a coating storage environment monitoring method based on data processing according to any one of claims 1 to 5 is implemented.

Images