Abnormality monitoring method and system for microwave drying equipment

Abstract

The present invention relates to the field of data processing technology, and in particular to an abnormality monitoring method and system for microwave drying equipment. The method comprises the following steps: obtaining data points of the microwave drying equipment at several moments, wherein the horizontal coordinate of the data point is humidity and the vertical coordinate is temperature; obtaining a preset observation window of the data point, determining the dispersion parameter of the data point, and the dispersion parameter is used to characterize the degree of deviation between the data point and the data point in the observation window; obtaining the difference between the dispersion parameter of the data point and other data points in the observation window, determining the degree of doubt of the data point, and the degree of doubt is positively correlated with the absolute value of the difference and the Euclidean distance between the data point and other data points; taking the corresponding data points on the left and right sides of the data point as a data pair, and calculating the degree of abnormality of the data point; obtaining the abnormality monitoring result of the microwave drying equipment through the comparison result of the degree of abnormality and the preset threshold, and effectively improving the accuracy of the abnormality monitoring result of the microwave drying equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an abnormality monitoring method and system for microwave drying equipment. Background Art

[0002] Microwave drying equipment is a highly efficient equipment that uses microwave energy to heat and dry dry products in a non-contact manner. It is used in the food industry, chemical industry and other fields. It directly acts on the inside of the dry product through microwave energy, thereby achieving rapid and uniform heating and reducing the humidity of the dry product. The working state of the microwave drying equipment directly affects the quality and stability of the dry product. By monitoring the abnormality of the microwave drying equipment, the equipment parameters can be adjusted or repaired in time to ensure the stability and consistency of product quality.

[0003] At present, the monitoring of drying equipment mainly tends to predict the drying time and avoid over-drying to ensure product quality. For example, the patent application document with publication number CN118520319A discloses an intelligent drying time prediction method based on big data analysis. The method collects environmental and food data through sensors and uploads them for processing; establishes a model to realize drying process control; among them, the data analysis and model building module is used to establish a reliable prediction model to guide the control of the drying process; the drying process control module is used to automatically control the drying process to ensure consistent drying effect and improve production efficiency and product quality; the environmental data acquisition module is used to ensure that the system can capture any changes in environmental temperature and humidity in real time.

[0004] Although the above-mentioned prior art solutions can realize abnormal monitoring of drying equipment to a certain extent, they do not solve how to accurately obtain abnormal monitoring results based on changes in ambient temperature and humidity, resulting in the inability to accurately adjust internal environmental parameters based on this.

[0005] Based on this, how to accurately obtain abnormal monitoring results based on the temperature and humidity changes of microwave drying equipment is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0006] In order to solve the technical problem of how to accurately obtain abnormal monitoring results based on the temperature and humidity changes of microwave drying equipment, the present invention provides an abnormal monitoring method and system for microwave drying equipment.

[0007] In a first aspect, the present invention provides a method for monitoring abnormalities of microwave drying equipment, which adopts the following technical solution:

[0008] A method for monitoring abnormality of microwave drying equipment, comprising the steps of:

[0009] The data points of the microwave drying equipment at several moments are obtained, wherein the horizontal coordinate of the data point is humidity and the vertical coordinate is temperature; the preset observation window of the data point is obtained, and the dispersion parameter of the data point is determined, and the dispersion parameter is used to characterize the degree of deviation of the data point from the data point in the observation window; the difference between the dispersion parameter of the data point and other data points in the observation window is obtained, and the doubt degree of the data point is determined, and the doubt degree is positively correlated with the absolute value of the difference and the Euclidean distance between the data point and other data points; the corresponding data points on the left and right sides of the data point are taken as a data pair, and the abnormality of the data point is calculated:

[0010] ;

[0011] In the formula, represents the abnormality of the i-th data point, represents the number of data pairs in the observation window of the ith data point, represents the doubt degree of the i-th data point, , Respectively represent , The degree of doubt of a data point, , Respectively represent The degree of doubt between one data point and the other data point in a data pair, , Respectively represent The degree of doubt between one data point and another data point in a data pair; the abnormal monitoring result of the microwave drying equipment is obtained by comparing the abnormality degree with the preset threshold.

[0012] The present invention can accurately obtain the degree of deviation of a data point from each data point in its observation window by analyzing the spatial position of the data point and each data point in its observation window on a rectangular coordinate system. At the same time, the present invention also takes into account that normal data fluctuations may be mixed with abnormal data, affecting the accuracy of abnormal monitoring results of microwave drying equipment. Therefore, by analyzing the difference in the degree of doubt of data points on both sides of the data point, the real abnormal data can be accurately screened out, thereby effectively improving the accuracy of abnormal monitoring results of microwave drying equipment.

[0013] According to a method for monitoring abnormalities of microwave drying equipment provided by the present invention, data points of the microwave drying equipment at several moments are obtained, which also includes: collecting temperature data and humidity data of the microwave drying equipment respectively through sensors, preprocessing the temperature data and humidity data, and taking points composed of temperature data and humidity data at the same moment as data points to obtain the temperature and humidity corresponding to each data point.

[0014] The present invention takes into account that the quality of the original data collected by the sensor is relatively low, and through preprocessing, the quality of the entire data can be effectively improved to prepare for subsequent data processing.

[0015] According to a method for monitoring abnormalities of microwave drying equipment provided by the present invention, the dispersed parameters of the data points satisfy the relationship:

[0016] ;

[0017] In the formula, represents the dispersion parameter of the ith data point, represents the number of data points in the observation window of the ith data point, represents the time interval between the ith data point and the data point closest to the ith data point in the observation window, It represents the maximum time interval between the i-th data point and other data points in the observation window.

[0018] According to a method for monitoring abnormalities of microwave drying equipment provided by the present invention, the degree of doubt of the data point satisfies the relationship:

[0019] ;

[0020] In the formula, represents the doubt degree of the i-th data point, represents the number of data points in the observation window of the ith data point, represents the Euclidean distance between the i-th data point and the j-th data point in the observation window, represents the dispersion parameter of the ith data point, represents the dispersion parameter of the jth data point in the observation window, represents the time interval between the i-th data point and the j-th data point in the observation window, Represents the absolute value symbol.

[0021] The present invention provides an accurate method for calculating the degree of doubt of a data point. By combining and comparing the data point with the dispersion parameters of the data point in its observation window, the deviation between the data point and the data point in the observation window can be comprehensively reflected, so that the abnormality of the data point can be accurately obtained based on this.

[0022] According to a method for monitoring an abnormality of a microwave drying device provided by the present invention, the abnormality monitoring result of the microwave drying device is obtained by comparing the abnormality degree with a preset threshold, including: a preset threshold; if the abnormality degree of the data point is greater than the preset threshold, the monitoring result of the data point is abnormal; if the abnormality degree of the data point is not greater than the preset threshold, the monitoring result of the data point is normal.

[0023] According to a method for monitoring abnormalities of microwave drying equipment provided by the present invention, obtaining abnormal monitoring results of the microwave drying equipment further includes: lossy compressing data points with normal monitoring results; and retaining data points with abnormal monitoring results.

[0024] The present invention can effectively improve the efficiency and accuracy of users in determining the positions of abnormal data points by compressing normal data points and retaining abnormal data points.

[0025] According to a method for monitoring abnormalities of microwave drying equipment provided by the present invention, the abnormality monitoring results of the microwave drying equipment are obtained, and then the method further includes: storing data points with abnormal monitoring results in an abnormality database and issuing an early warning.

[0026] The present invention takes into account that when an abnormal situation occurs in the microwave drying equipment, there may be a potential safety hazard. Therefore, by issuing an early warning to the outside, the user is notified in time to take measures, thereby reducing the potential safety hazard.

[0027] In a second aspect, the present invention provides an abnormality monitoring system for microwave drying equipment, which adopts the following technical solution:

[0028] A microwave drying equipment abnormality monitoring system comprises: 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 microwave drying equipment abnormality monitoring method is implemented.

[0029] By adopting the above technical solution, the above-mentioned abnormality monitoring method of microwave drying equipment is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0030] The present invention has the following technical effects:

[0031] Based on the above technical scheme, when determining the abnormal monitoring results of the microwave drying equipment, the present invention can accurately obtain the degree of deviation between the data point and each data point in its observation window by analyzing the spatial position of the data point and each data point in its observation window on the rectangular coordinate system. At the same time, the present invention also takes into account that normal data fluctuations may be mixed with abnormal data, affecting the accuracy of the abnormal monitoring results of the microwave drying equipment. Therefore, by analyzing the difference in the degree of doubt of the data points on both sides of the data point, the real abnormal data can be accurately screened out, thereby effectively improving the accuracy of the abnormal monitoring results of the microwave drying equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, 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-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0033] Figure 1 A schematic flow chart of an abnormality monitoring method for microwave drying equipment provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0035] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0036] It should be noted that microwave drying equipment can dry materials of any shape, especially in food and chemical materials. The temperature and humidity in the microwave drying equipment can characterize the operating state of the microwave drying equipment. Under normal circumstances, when the temperature inside the drying chamber gradually increases, the humidity of the material to be processed will gradually decrease until it reaches the predetermined humidity and temperature.

[0037] Based on this, the embodiment of the present invention discloses a method for monitoring abnormalities of microwave drying equipment, which can obtain abnormal monitoring results of the microwave drying equipment by monitoring the temperature and humidity change trends of the microwave drying equipment. Figure 1 As shown, Figure 1 A schematic flow chart of an abnormality monitoring method for microwave drying equipment provided in an embodiment of the present invention, the method comprises the following steps S1 to S5.

[0038] S1: Obtain data points of the microwave drying equipment at several moments, where the horizontal coordinate of the data point is humidity and the vertical coordinate is temperature.

[0039] It should be noted that as the drying process of the microwave drying equipment proceeds, the temperature inside the drying chamber gradually increases, and the humidity of the material to be processed gradually decreases. There is a certain correlation and mutual influence between the two. When the microwave drying equipment fails or is abnormal, the change trend of humidity and temperature often deviates from the normal mode. For example, if the humidity suddenly rises without a corresponding increase in temperature, it means that the drying effect of the equipment may decrease or there may be a problem of moisture reflux; conversely, if the temperature rises abnormally and the humidity does not change much, it means that the heating system of the equipment may be out of control or there may be other thermal faults. Such abnormal trends will be manifested in the rectangular coordinate system as a cluster of data points that deviate from the normal.

[0040] Based on this, the embodiment of the present invention uses the humidity corresponding to each data point of the microwave drying equipment as the horizontal coordinate and the temperature corresponding to each data point as the vertical coordinate to construct a rectangular coordinate system. The trend distribution of the data points in the rectangular coordinate system is analyzed to obtain the abnormal monitoring results of the microwave drying equipment.

[0041] Specifically, the user puts the material to be dried into the microwave drying equipment, sets the corresponding parameters according to actual needs, such as microwave power, maximum drying temperature, etc., and starts the equipment to start the drying process. In the process of drying the material, the temperature data and humidity data of the microwave drying equipment are collected by sensors, and the temperature data and humidity data are preprocessed to obtain the temperature and humidity corresponding to each data point. Each collection moment corresponds to a data point, and each data point corresponds to a temperature and humidity. Finally, the position of each data point in the rectangular coordinate system is obtained by constructing a rectangular coordinate system.

[0042] Among them, the preprocessing method can be denoising, which can be set according to actual needs; the acquisition frequency of the sensor can be set according to actual needs.

[0043] After obtaining the data points of the microwave drying equipment at several moments based on the above steps, continue to perform the following steps.

[0044] S2: Obtain a preset observation window of data points and determine the dispersion parameters of the data points.

[0045] It should be noted that in the process of drying materials, the internal temperature of the microwave drying equipment changes gradually, and after changing to a certain degree (such as the maximum drying temperature), it will be in a relatively stable state. The change in humidity is usually more direct and clear. As the water evaporates, the humidity will gradually decrease. This process is relatively continuous and the trend is obvious. Therefore, the humidity data will show a more concentrated trend in the process of gradual change, while the temperature is more dispersed.

[0046] For example, in an embodiment of the present invention, when obtaining a preset observation window of the data point, the size of the observation window may be preset, and the observation window of the data point may be constructed with the data point as the center.

[0047] The size of the observation window may be preset to 5×5, and may be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0048] Based on this, the embodiment of the present invention sets an observation window for each data point, in which the data changes of the microwave drying equipment within a specific time period can be monitored, thereby avoiding indiscriminate analysis of the entire amount of data and improving the efficiency and pertinence of data processing.

[0049] It should be further explained that the abnormal data points in the observation window generally deviate from the normal data points. By obtaining the distribution of the data points in the rectangular coordinate system, the abnormality of the data points can be obtained.

[0050] Specifically, if the time interval difference between a data point and its nearest data point is small, it means that the data points are relatively clustered, and the current time period may be in a normal change in the drying process; if the time interval difference between a data point and its nearest data point is large, it means that there may be an abnormality between the data point and its nearest data point. For example, the temperature of the data point gradually increases, but the microwave drying equipment has an abnormal problem of moisture reflux, which causes the humidity of the data point to increase in the opposite direction, and is closer to the humidity value of one of the historical data points. At this time, in the rectangular coordinate system, the position of the data point and the data point where the humidity increases in the opposite direction will be closer, but the degree of abnormality of such data points may be large.

[0051] In addition, the more data points there are in the observation window, the closer the data distribution in the observation window is to the normal operation trend of the microwave drying equipment. The size of the observation window of each data point is fixed. If the number of data points in the observation window of a data point is more, the distribution of data points in the time period corresponding to the observation window is more normal, and the possibility that the data point belonging to the observation window is a normal data point is higher. Therefore, the number of data points in the observation window can be used to measure the difference between the data point and the data distribution in the corresponding observation window.

[0052] Based on this, the dispersion parameter of the data point can be obtained through the interval between the data point and the data points in the observation window and the number of data points. The dispersion parameter can be used to characterize the degree of deviation between the data point and the data points in the observation window.

[0053] For example, in the embodiment of the present invention, the dispersion parameter of the data point is determined, and the specific relationship can be as follows:

[0054] ;

[0055] In the formula, represents the dispersion parameter of the ith data point, represents the number of data points in the observation window of the ith data point, represents the time interval between the ith data point and the data point closest to the ith data point in the observation window, It represents the maximum time interval between the i-th data point and other data points in the observation window.

[0056] In the above formula, the smaller the maximum value of the time interval between the i-th data point and other data points in the observation window, the closer the data correlation is in the observation window of the i-th data point. The larger the dispersion parameter of the data point, the greater the possibility that the data point is an abnormal data point.

[0057] Based on the above steps, the distribution of data points and data points in the observation window can be analyzed to obtain the scattered parameters of each data point in the rectangular coordinate system, and then continue to perform the following steps.

[0058] S3: Obtain the difference between the scattered parameters of the data point and other data points in the observation window to determine the degree of doubt of the data point.

[0059] It should be noted that, based on the above steps, by analyzing the distribution of data points and the data points in their observation window in the rectangular coordinate system, the dispersion parameters of each data point can be obtained. However, the dispersion parameters can only obtain the abnormal situation of the data point through the distribution difference between the data point and other single data points, and cannot accurately and comprehensively describe the abnormal situation of the data point.

[0060] Based on this, the embodiment of the present invention accurately obtains the degree of doubt of the data point by analyzing the difference between the data point and each data point in its observation window. The degree of doubt of the data point can be used to characterize the characteristic difference between the data point and each data point in its observation window.

[0061] Specifically, the Euclidean distance can measure the physical distance of data points in a rectangular coordinate system. If a data point is far away from other data points in its observation window, it means that the data point has a significant difference in spatial distribution from other data points, which increases the possibility of its abnormality.

[0062] Dispersion parameters can be used to characterize the degree of deviation between a data point and the data points in the observation window. If the difference between the dispersion parameters of a data point and the data points in the observation window is large, it means that the distribution characteristics of the data point are significantly different from those of the surrounding data points, thereby increasing the possibility that the data point is abnormal.

[0063] Therefore, the degree of doubt is positively correlated with the absolute value of the difference between the dispersion parameters of the data point and other data points in the observation window; the degree of doubt is positively correlated with the Euclidean distance between the data point and other data points.

[0064] It can be understood that in the embodiment of the present invention, the observation window is constructed to better analyze the spatial distribution differences between the data point and the surrounding data points. Therefore, other data points in the observation window of the data point obtained based on the above steps do not include the data point itself, and the number of data points in the observation window finally obtained does not include the data point itself.

[0065] For example, in the embodiment of the present invention, the degree of doubt of a data point is determined, and specifically, the following relationship can be referred to:

[0066] ;

[0067] In the formula, represents the doubt degree of the i-th data point, represents the number of data points in the observation window of the ith data point, represents the Euclidean distance between the i-th data point and the j-th data point in the observation window, represents the dispersion parameter of the ith data point, represents the dispersion parameter of the jth data point in the observation window, represents the time interval between the i-th data point and the j-th data point in the observation window, Represents the absolute value symbol.

[0068] In the above formula, It indicates the similarity between the i-th data point and the data points in its observation window. The smaller the value, the more clustered the data points in the observation window are. The possibility that the i-th data point is a normal data point is higher, and the possibility that it is an abnormal data point is lower.

[0069] It can represent the difference in the dispersion parameters between the ith data point and the jth data point in the observation window. The larger the value is, the more dissimilar the distributions of the ith data point and the jth data point are. In order to further verify the dissimilarity of the distributions, the Euclidean distance between the ith data point and the jth data point is combined to accurately obtain the characteristic difference between the ith data point and the jth data point.

[0070] In this way, the degree of doubt is combined with the spatial distance between data points, the difference in the dispersion parameters between data points, and the time interval between data points to comprehensively evaluate the degree of abnormality of data points. The obtained degree of doubt can more comprehensively reflect the abnormal characteristics of data points. That is, the higher the degree of doubt of a data point, the higher the possibility that the data point is an abnormal data point.

[0071] After obtaining the degree of doubt of each data point based on the above steps, continue to perform the following steps.

[0072] S4: Take the corresponding data points on the left and right sides of the data point as a data pair and calculate the abnormality of the data point.

[0073] It should be noted that the degree of doubt of the data point can be obtained by analyzing the distribution of the data point and the data point in its observation window based on the above steps. However, in the actual use of the microwave drying equipment, the user may manually adjust the temperature inside the microwave drying equipment according to actual needs, resulting in changes in the trend and spatial distribution of the data points in the rectangular coordinate system constructed based on temperature and humidity changes. The change in the position of the data point caused by such changes is a normal change. Directly determining the abnormal monitoring results of the data point based on the degree of doubt obtained in the above steps may determine the monitoring results of such normal changes as abnormal.

[0074] There will be a large deviation in the doubt degree between the abnormal data point and its adjacent data points, while the doubt degree of the normal data point changes relatively smoothly. In order to distinguish the normal data point fluctuations from the abnormal data points in the microwave drying equipment, the abnormal monitoring results of the data point can be obtained by obtaining the consistency of the data points on both sides of the data point; among them, the abnormal degree of the data point can be used to characterize the consistency of the data points on both sides of the data point.

[0075] For example, in an embodiment of the present invention, when determining the abnormality of a data point, the data points corresponding to each other on the left and right sides of the data point can be taken as a data pair to determine the number of data pairs in the observation window of the data point; the abnormal index of each data point is obtained, and the abnormality of the data point is obtained by the difference between the abnormal indexes of each data pair.

[0076] Take the i-th data point as the target. There are two data points on the left and right sides of the i-th data point in the observation window. Finally, there are two pairs of data in the observation window, namely data points and data points, and the data points and A data pair consisting of data points.

[0077] When obtaining data pairs, there may be some data points that have no corresponding data points on the other side of the data points. Such data points may not be processed.

[0078] It can be understood that the closer the data point is to the data point, the more reference it has. Based on this, in order to obtain the abnormality of the data point more accurately, the two data points closest to the left and right sides of the data point can be recorded as benchmark data points, and then the abnormal indicators of the data pairs on both sides of the data point except the benchmark data point are compared with their closest benchmark data points, so as to obtain the gap between the abnormal indicators of each data pair in the observation window.

[0079] Among them, based on the observation window of the current data point, when obtaining the abnormal index of the current data point, there are two possible situations:

[0080] In one possible case, the data point is located on the left side of the current data point. In this case, the sum of the doubt degree of the data point and the previous data point is used as the abnormal indicator of the data point.

[0081] In another possible case, the data point is located on the right side of the current data point. In this case, the sum of the doubt degree of the data point and the next data point is used as the abnormal indicator of the data point.

[0082] After obtaining the abnormal index of each data point based on the above steps, the abnormal degree of the data point can be obtained based on the abnormal index gap between each data pair in the observation window.

[0083] Specifically, the abnormality of a data point is determined, and the following relationship can be referred to:

[0084] ;

[0085] In the formula, represents the abnormality of the i-th data point, represents the number of data pairs in the observation window of the ith data point, represents the doubt degree of the i-th data point, , Respectively represent , The degree of doubt of a data point, , Respectively represent The degree of doubt between one data point and the other data point in a data pair, , Respectively represent The degree of doubt between one data point and the other data point in a data pair, Represents the absolute value symbol.

[0086] In the above formula, represents the doubt degree of the i-th data point, and the nearest benchmark data points to the i-th data point are data points and data points, Indicates The anomaly indicator of a data point in a data pair, Indicates The abnormality index of the other data point in the data pair is compared with the abnormality index of the data pairs on both sides of the ith data point and the benchmark data point closest to the ith data point, so the abnormality of the ith data point can be accurately obtained. The higher the abnormality of the data point, the worse the consistency of the data pairs on both sides of the data point, and the greater the possibility that the data point is an abnormal data point.

[0087] After the abnormality of all data points is obtained based on the above steps, the abnormality can be compared based on the following steps to obtain the abnormal monitoring result of the microwave drying equipment.

[0088] S5: Obtain the abnormal monitoring result of the microwave drying equipment by comparing the abnormality degree with the preset threshold value.

[0089] It should be noted that by comparing the abnormality of each data point during the operation of the microwave drying equipment with the preset threshold, the abnormal monitoring results of the microwave drying equipment can be obtained, so that potential fault signs can be discovered in time, and measures can be taken to intervene before the fault occurs, thereby ensuring production safety.

[0090] By way of example, in an embodiment of the present invention, an abnormal monitoring result of a microwave drying device is obtained by comparing the abnormality degree with a preset threshold value, including: a preset threshold value; if the abnormality degree of a data point is greater than the preset threshold value, the monitoring result of the data point is abnormal; if the abnormality degree of the data point is not greater than the preset threshold value, the monitoring result of the data point is normal.

[0091] The threshold value may be preset to 0.6, and may be set specifically according to actual needs.

[0092] For example, in an embodiment of the present invention, obtaining abnormal monitoring results of microwave drying equipment further includes: performing lossy compression processing on data points with normal monitoring results; and retaining data points with abnormal monitoring results.

[0093] The lossy compression may be mean lossy compression.

[0094] Specifically, when processing normal data points through mean lossy compression, the normal data points can be divided into multiple data segments through abnormal data points; the data mean of the normal data points in the data segment is determined, and the data mean is used as the compressed value of all normal data points in the data segment, thereby completing the compression of all normal data points.

[0095] In this way, the embodiment of the present invention can effectively improve the accuracy of users in determining the locations of abnormal data points by compressing normal data points and retaining abnormal data points.

[0096] In addition, in order to enable users to detect abnormal situations and deal with them in a timely manner, an early warning can be issued after the abnormal situation is monitored.

[0097] For example, in the embodiment of the present invention, after obtaining the abnormal monitoring result of the microwave drying equipment, the method further includes: storing the data points with abnormal monitoring results in an abnormal database, and issuing an early warning.

[0098] For example, the warning reminder duration can be set. If the user has not taken any action within the warning reminder duration after the warning is issued, the power connection of the microwave drying equipment can be interrupted.

[0099] Among them, the warning reminder duration can be set according to actual needs, and the embodiment of the present invention will not be described in detail here.

[0100] It can be seen that in the embodiment of the present invention, when determining the monitoring result of the microwave drying equipment, data points of the microwave drying equipment at several moments can be obtained, the horizontal coordinate of the data point is humidity, and the vertical coordinate is temperature; the preset observation window of the data point is obtained, and the dispersion parameter of the data point is determined, and the dispersion parameter is used to characterize the degree of deviation of the data point from the data point in the observation window; the difference between the dispersion parameters of the data point and other data points in the observation window is obtained, and the doubt degree of the data point is determined, and the doubt degree is positively correlated with the absolute value of the difference and the Euclidean distance between the data point and other data points; the corresponding data points on the left and right sides of the data point are taken as a data pair, and the abnormality of the data point is calculated; the abnormal monitoring result of the microwave drying equipment is obtained by comparing the abnormality with the preset threshold.

[0101] In this way, the embodiment of the present invention can accurately obtain the degree of deviation between the data point and each data point in its observation window by analyzing the spatial position of the data point and each data point in its observation window on the rectangular coordinate system. At the same time, the embodiment of the present invention also takes into account that normal data fluctuations may be mixed with abnormal data, affecting the accuracy of the abnormal monitoring results of the microwave drying equipment. Therefore, by analyzing the difference in the degree of doubt of the data points on both sides of the data point, the real abnormal data can be accurately screened out, thereby effectively improving the accuracy of the abnormal monitoring results of the microwave drying equipment.

[0102] An embodiment of the present invention further discloses an abnormality monitoring system for microwave drying equipment, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an abnormality monitoring method for microwave drying equipment according to the present invention is implemented.

[0103] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0104] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination 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 a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0105] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0106] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope 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 protection scope of the present invention.

Claims

1. A method for monitoring abnormality of microwave drying equipment, characterized in that: include: Obtain data points of the microwave drying equipment at several moments, with the horizontal coordinate of the data point being humidity and the vertical coordinate being temperature; obtain the preset observation window of the data point, determine the dispersion parameter of the data point, and the dispersion parameter is used to characterize the degree of deviation between the data point and the data point in the observation window; obtain the difference between the dispersion parameter of the data point and other data points in the observation window, and determine the degree of doubt of the data point: ; Indicates the degree of doubt of the i-th data point, represents the number of data points in the observation window of the i-th data point, represents the Euclidean distance between the ith data point and the jth data point in the observation window, represents the dispersion parameter of the ith data point, represents the dispersion parameter of the jth data point in the observation window, represents the time interval between the i-th data point and the j-th data point in the observation window, represents the absolute value sign. The doubt degree is positively correlated with the absolute value of the difference and the Euclidean distance between the data point and other data points. The corresponding data points on the left and right sides of the data point are taken as a data pair to calculate the abnormality of the data point: ； In the formula, represents the abnormality of the i-th data point, represents the number of data pairs in the observation window of the ith data point, , Respectively represent , The degree of doubt of a data point, , Respectively represent The degree of doubt between one data point and the other data point in a data pair, , Respectively represent There is doubt between one data point and another data point in a data pair; by comparing the abnormality and the preset threshold, the abnormal monitoring result of the microwave drying equipment is obtained.

2. The abnormality monitoring method of microwave drying equipment according to claim 1 is characterized in that: The method of obtaining data points of the microwave drying equipment at several moments also includes: The temperature data and humidity data of the microwave drying equipment are collected by sensors respectively. After the temperature data and humidity data are preprocessed, the points formed by the temperature data and humidity data at the same time are used as data points to obtain the temperature and humidity corresponding to each data point.

3. The abnormality monitoring method of microwave drying equipment according to claim 1 is characterized in that: The dispersion parameters of the data points satisfy the relationship: ； In the formula, represents the dispersion parameter of the ith data point, represents the number of data points in the observation window of the ith data point, represents the time interval between the ith data point and the data point closest to the ith data point in the observation window, It represents the maximum time interval between the i-th data point and other data points in the observation window.

4. The abnormality monitoring method of microwave drying equipment according to claim 1, characterized in that: The abnormality monitoring result of the microwave drying equipment is obtained by comparing the abnormality degree with the preset threshold value, including: Preset threshold value; If the abnormality of the data point is greater than a preset threshold, the monitoring result of the data point is abnormal; If the abnormality of the data point is not greater than a preset threshold, the monitoring result of the data point is normal.

5. The abnormality monitoring method of microwave drying equipment according to claim 4 is characterized in that: The abnormal monitoring result of the microwave drying equipment is obtained, and further includes: The data points with normal monitoring results are subjected to lossy compression processing; the data points with abnormal monitoring results are retained.

6. The abnormality monitoring method of microwave drying equipment according to claim 4, characterized in that: The abnormal monitoring result of the microwave drying equipment is obtained, and then the method further includes: The data points with abnormal monitoring results are stored in the abnormal database, and an early warning is issued externally.

7. An abnormality monitoring system for microwave drying equipment, 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, an abnormality monitoring method for microwave drying equipment according to any one of claims 1 to 6 is implemented.

Images