A coal preparation plant power supply energy consumption monitoring method and system based on the Internet of Things
By adopting IoT technology in coal preparation plants, combined with the weighted processing of isolated forest algorithms and related data items, the problem of inaccurate energy consumption monitoring of coal preparation plants in the existing technology is solved, and more accurate abnormal situation identification and safety are achieved. promote.
Patent Information
- Application Number
- CN202411055121.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-02
AI Technical Summary
The prior art cannot accurately identify abnormal situations in the energy consumption monitoring of coal preparation plants, which poses safety risks, especially because energy consumption is affected by multiple parameters, and a single energy consumption data is difficult to reflect the status of the equipment.
The power consumption monitoring method of coal preparation plants based on the Internet of Things is adopted. By obtaining power consumption data and related data items, local fluctuations and fault levels are calculated, data points with high fault levels are eliminated, and abnormal scores are obtained by combining the isolated forest algorithm. Weighted according to the degree of correlation, determine the monitoring results.
It improves the accuracy of the power consumption monitoring results of coal preparation plants, reduces safety risks, and ensures the reliability and accuracy of energy consumption data.
Smart Images

Figure CN118568649B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for monitoring power supply energy consumption of a coal preparation plant based on the Internet of Things. Background Art
[0002] A coal preparation plant is a coal processing plant that sorts coal, removes mineral impurities from raw coal, and separates it into products of different specifications. It consumes a huge amount of electricity and has high energy consumption, so it is necessary to monitor the energy consumption of the production process to improve energy efficiency. The Internet of Things technology can achieve interconnection between coal preparation plant equipment, monitor the power parameter data and environmental data of the coal preparation plant, and perform data analysis to obtain monitoring results, so as to make intelligent control of the monitoring results.
[0003] The patent application document with publication number CN111340357A discloses a method for identifying abnormal production energy consumption of an enterprise. The method combines the historical active electricity data of the enterprise's production energy consumption into a data set, and then screens and calculates the data set to obtain abnormal non-production energy consumption reference values and abnormal production energy consumption reference values. Then, based on the abnormal non-production energy consumption reference values, abnormal production energy consumption reference values, and the active electricity values of the energy consumption calculation period, the abnormal energy consumption conditions in the production period and the abnormal energy consumption conditions in the non-production period are identified.
[0004] The above-mentioned prior art solution identifies faults through abnormal reference values of non-production energy consumption, abnormal reference values of production energy consumption, and active electricity values during the energy consumption calculation period. However, the above-mentioned solution only obtains the energy consumption of each part during the calculation process. During the operation of the factory, the energy consumption is determined by multiple parameters, such as voltage and current. The degree of correlation between each factor and energy consumption is different. For example, excessive voltage may cause equipment damage, which may affect the energy consumption of the factory. The abnormality may have occurred but the abnormal monitoring result cannot be obtained through energy consumption, which poses a great safety hazard.
[0005] Based on this, how to accurately obtain the energy consumption monitoring results of the coal preparation plant is an urgent problem to be solved by technical personnel in this field. Summary of the invention
[0006] In order to solve the technical problem of how to accurately obtain the energy consumption monitoring results of a coal preparation plant, the present invention provides a method and system for monitoring power supply energy consumption of a coal preparation plant based on the Internet of Things.
[0007] In the first aspect, the present invention provides a method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things, which adopts the following technical solutions:
[0008] A method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things, comprising the steps of:
[0009] The power supply energy consumption data and sub-data of each related data item having correlation with the power supply energy consumption are obtained to determine a data set, wherein the data set includes data points at each sampling time, and the data points include sub-data of the related data item corresponding to the sampling time; the average value of the absolute value of the difference between the sub-data and the left and right adjacent sub-data is used as the local fluctuation degree of the sub-data; a local range of the sub-data is preset in the related data item, and the fault degree of the sub-data in the local range is determined, and the fault degree is positively correlated with the local fluctuation degree of the sub-data; any related data item is used as a target data item, and data points corresponding to the sub-data in the target data item whose fault degree is greater than a preset threshold are eliminated from the data set to obtain a target data set of the target data item; the correlation degree between the related data item and the power supply energy consumption data is determined, and the correlation degree is negatively correlated with the number of data points in the target data set of the related data item; the abnormal score of each data point is obtained by an isolation forest algorithm, the abnormal degree of the data point is calculated, and the monitoring result of the data point is determined, and the abnormal degree is positively correlated with both the abnormal score and the correlation degree.
[0010] The anomaly score of each data point of the power supply energy consumption of the coal preparation plant can be obtained by the isolation forest algorithm. The present invention takes into account that the power supply energy consumption of the coal preparation plant is affected by multiple related data items, and the degree of correlation between each related data item and the power supply energy consumption is also different. If the degree of correlation between each related data item and the power supply energy consumption is not considered, the accuracy of the monitoring result of the data point obtained directly by the anomaly score is low. Based on this, the present invention weights the anomaly score of each data point of the power supply energy consumption by the degree of correlation between the related data items and the power supply energy consumption, and finally obtains the monitoring result of each data point of the power supply energy consumption, which can effectively improve the accuracy of the monitoring result of the obtained data point.
[0011] According to a method for monitoring power supply energy consumption of a coal preparation plant based on the Internet of Things provided by the present invention, the power supply energy consumption data and sub-data of each related data item that is correlated with the power supply energy consumption are obtained, including: obtaining the initial power supply energy consumption data at each sampling moment and the initial sub-data of the corresponding related data items through a sampling device; preprocessing the initial power supply energy consumption data and the initial sub-data to obtain the power supply energy consumption data and the sub-data of each related data item.
[0012] The present invention takes into account that the data quality of the original data is relatively poor, and therefore by preprocessing the initial data, the overall quality of the data can be improved to facilitate subsequent analysis and processing.
[0013] According to a method for monitoring power consumption of a coal preparation plant based on the Internet of Things provided by the present invention, the failure degree of the sub-data in a local range satisfies the relational expression:
[0014] ;
[0015] In the formula, represents the fault degree of the i-th sub-data of the j-th related data item, Indicates the local fluctuation degree of the i-th sub-data of the j-th related data item, Indicates the number of sub-data contained in the local range of the i-th sub-data of the j-th related data item, Indicates the jth related data item in the i-th sub-data local range The local fluctuation degree of individual sub-data.
[0016] The present invention provides an accurate method for calculating the fault degree of sub-data, which can accurately obtain the fault degree of each sub-data, so that data points with higher fault degrees can be accurately eliminated later.
[0017] According to a method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things provided by the present invention, the determining the degree of correlation between the relevant data item and the power supply energy consumption data comprises: acquiring energy consumption sub-data corresponding to the sub-data in the power supply energy consumption data;
[0018] ;
[0019] In the formula, Indicates the correlation between the jth related data item and the power supply energy consumption data, represents the number of data points in the target data set of the jth related data item, Indicates the jth related data item in the target data set. The sub-data of the j-th related data item of a data point, Indicates Energy consumption data, , Respectively represent the mean and standard deviation of the sub-data of the j-th related data item in the target data set, , Respectively represent the mean and standard deviation of power supply energy consumption data.
[0020] The present invention provides an accurate method for calculating the degree of correlation between relevant data items and power supply energy consumption data, which can accurately obtain the degree of correlation between relevant data items and power supply energy consumption data, so as to facilitate the subsequent accurate acquisition of the weight of each relevant data item to the power supply energy consumption data.
[0021] According to a method for monitoring power supply energy consumption of a coal preparation plant based on the Internet of Things provided by the present invention, the abnormal score of each data point is obtained by using an isolation forest algorithm, including: taking any sub-data of a target data item in the data point as a segmentation point, dividing all data points in the data set, and obtaining an isolated tree of the data point in the target data item; obtaining the path length of the data point in the isolated tree, and determining the abnormal score of the data point in the target data item, wherein the abnormal score is negatively correlated with the path length.
[0022] According to a method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things provided by the present invention, the calculation of the abnormality of the data point includes: obtaining the sum of the correlations between all relevant data items and the power supply energy consumption data, and taking the ratio of the correlation of the relevant data items to the sum of the correlations as the score weight of the relevant data items;
[0023] ;
[0024] In the formula, Indicates The degree of abnormality of the data point, Indicates the number of related data items, represents the score weight of the j-th related data item, Indicates The anomaly score of a data point in the jth related data item.
[0025] The present invention provides an accurate method for calculating the degree of abnormality of data points. By combining the degree of correlation between relevant data items and power supply energy consumption and the abnormality score, the degree of abnormality of each data point can be accurately obtained.
[0026] According to a method for monitoring power supply energy consumption of a coal preparation plant based on the Internet of Things provided by the present invention, determining the monitoring result of the data point includes: presetting an abnormality threshold; if the abnormality degree of the data point is greater than the abnormality threshold, the monitoring result of the data point is abnormal; if the abnormality degree of the data point is less than or equal to the abnormality threshold, the monitoring result of the data point is normal.
[0027] According to a method for monitoring power supply energy consumption of a coal preparation plant based on the Internet of Things provided by the present invention, after determining the monitoring result of the data point, it also includes: if the monitoring result of the data point is normal, storing the data point and the corresponding monitoring result in a normal database of the Internet of Things; if the monitoring result of the data point is abnormal, storing the data point and the corresponding monitoring result in an abnormal database of the Internet of Things, and issuing an early warning.
[0028] In the second aspect, the present invention provides a coal preparation plant power supply energy consumption monitoring system based on the Internet of Things, which adopts the following technical solutions:
[0029] A coal preparation plant power supply energy consumption monitoring system based on the Internet of Things 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 coal preparation plant power supply energy consumption monitoring method based on the Internet of Things is implemented.
[0030] By adopting the above technical solution, the above-mentioned method for monitoring power supply energy consumption of a coal preparation plant based on the Internet of Things is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.
[0031] The present invention has the following technical effects:
[0032] Based on the above scheme, the present invention obtains the fault degree of each sub-data by analyzing the change trend of each sub-data in the relevant data items, and removes the data points corresponding to the sub-data with a fault degree greater than a preset threshold. Then, the correlation degree between the relevant data items and the power supply energy consumption data is obtained, and the abnormal score of each data point obtained by the isolation forest algorithm is weighted according to the correlation degree. Finally, the monitoring result of the data point is obtained, which can effectively improve the accuracy of the power supply energy consumption monitoring result of the coal preparation plant. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] 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.
[0034] Figure 1 A schematic flow chart of a method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things is provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0035] 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.
[0036] 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.
[0037] It should be noted that during the operation of the coal preparation plant, the power supply energy consumption is affected by multiple related parameters, such as voltage, current and power. The degree of correlation between each related parameter and the power supply energy consumption is different. For example, the higher the total power of the equipment, the greater its power supply energy consumption, and the correlation between the two is relatively large; and excessive voltage causing equipment damage may affect the factory's power supply energy consumption. The correlation between the two is relatively small. The abnormality may have occurred but the abnormal monitoring results cannot be obtained through the power supply energy consumption, which poses a major safety hazard.
[0038] Based on this, the embodiment of the present invention discloses a method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things. By analyzing the relevant data items of various relevant parameters that are correlated with the power supply energy consumption data, the specific correlation degree between the power supply energy consumption data and each relevant data item is obtained. The anomaly score obtained by the isolation forest algorithm is weighted by the correlation degree, so as to obtain the true anomaly degree of each data point and monitor it. Please refer to Figure 1 As shown, Figure 1 A schematic flow chart of a method for monitoring power consumption of a coal preparation plant based on the Internet of Things provided by an embodiment of the present invention includes the following steps S1 to S5:
[0039] S1: Acquire power supply energy consumption data and sub-data of various related data items related to power supply energy consumption, and determine a data set.
[0040] The data set includes data points at each sampling moment, and the data points include sub-data of related data items corresponding to the sampling moment.
[0041] It should be noted that the power supply energy consumption of the coal preparation plant is related to multiple related data items, but the correlation between each related data item and the power supply energy consumption is different. If we only focus on the energy consumption data and ignore the correlation between the power supply energy consumption and each related data item, there may be a situation where some related data items have abnormal data but the energy consumption data is normal, resulting in the inability to accurately obtain the power supply energy consumption monitoring results of the coal preparation plant. Based on this, the embodiment of the present invention obtains the sub-data of the related data items of each parameter, and the sub-data of all related data items are combined into a data set, and the change trend of each sub-data in the data set is analyzed, and the sub-data that is significantly different from other sub-data is screened out as abnormal data and noise data, thereby obtaining the correlation between the related data items and the power supply energy consumption.
[0042] In order to obtain accurate monitoring results based on accurate sub-data and power consumption data, the embodiment of the present invention can pre-process the collected initial data:
[0043] By way of example, in an embodiment of the present invention, when obtaining power supply energy consumption data and sub-data of each related data item that is correlated with the power supply energy consumption, the initial power supply energy consumption data at each sampling moment and the initial sub-data of the corresponding related data items can be obtained through a sampling device; the initial power supply energy consumption data and the initial sub-data are preprocessed to obtain the power supply energy consumption data and the sub-data of each related data item.
[0044] Among them, the preprocessing method can be data cleaning, data integration, etc., which can be specifically set according to actual needs, and the embodiment of the present invention does not make too many restrictions here.
[0045] For example, the relevant data items correlated with power supply energy consumption can be one or more of voltage, current, power, temperature data of liquid medium and gaseous medium in the coal preparation plant, and ambient temperature and humidity data. The relevant data items can be set according to actual needs; the sampling parameters can be one or more of collection period, collection duration, collection frequency, etc.
[0046] Among them, the sampling equipment and the corresponding sampling parameters can be set according to actual needs.
[0047] It can be understood that at the same sampling time, the energy consumption sub-data of the power supply energy consumption data and the sub-data of each related data item can be collected simultaneously, and the energy consumption sub-data of the power supply energy consumption data and the sub-data of each related data item correspond to each other one by one.
[0048] Take an example to illustrate the relationship between relevant data items, sub-data, data points and data sets: if the relevant data items are voltage and power, obtain the sub-data of each relevant data item at three sampling moments, and obtain the sub-data of the relevant data item voltage as 377, 378, 376, in volts; the sub-data of the relevant data item power as 7.5, 7.3, 7.4, in kilowatts. The sub-data (377, 7.5) at the first sampling moment constitutes the first data point, the sub-data (378, 7.3) at the second sampling moment constitutes the second data point, and the sub-data (376, 7.4) at the third sampling moment constitutes the third data point. The above three data points together constitute the data set.
[0049] After obtaining the data set based on the above method, continue to analyze the change trends of each relevant data item and its sub-data in the data set:
[0050] S2: Determine the local fluctuation degree of each sub-data, and preset the local range of the sub-data in the relevant data items to determine the failure degree of the sub-data in the local range.
[0051] It should be noted that compared with normal data, abnormal data or noise data performs more prominently and has a large deviation from adjacent data and the overall data. Considering that there will be reasonable data fluctuations in the overall data, in order to more accurately obtain the fault degree of the sub-data and thus screen out abnormal data and noise data, the changing trend of each sub-data in the local range can be analyzed, and the changing trend of the sub-data in the local range can be used as the fault degree of the sub-data to reduce the error caused by the overall data fluctuation.
[0052] For example, in an embodiment of the present invention, when determining the local fluctuation degree of sub-data, the difference between the sub-data and the left and right adjacent sub-data can be obtained respectively, and the average value of the absolute value of the difference between the sub-data and the left and right adjacent sub-data can be used as the local fluctuation degree of the sub-data.
[0053] For example, when obtaining the fault degree of sub-data, the local range of the sub-data can be preset in the relevant data item to which the sub-data belongs, and then the fault degree of the sub-data in the local range is determined, wherein the fault degree of the sub-data is positively correlated with the local fluctuation degree of the sub-data.
[0054] Among them, the local range of the sub-data It can be preset to 11. When obtaining the local range of the sub-data, 5 sub-data can be obtained on both sides of the sub-data with the sub-data as the center. If the number of sub-data on one side is insufficient, it can be supplemented on the other side. The sub-data and the sub-data on both sides together constitute the local range of the sub-data. The local range of the sub-data can be set specifically according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.
[0055] After the local range of the sub-data is preset, the fault degree of the sub-data in the local range can be determined by referring to the following formula:
[0056] ;
[0057] In the formula, represents the fault degree of the i-th sub-data of the j-th related data item, Indicates the local fluctuation degree of the i-th sub-data of the j-th related data item, Indicates the number of sub-data contained in the local range of the i-th sub-data of the j-th related data item, Indicates the jth related data item in the i-th sub-data local range The local fluctuation degree of individual sub-data.
[0058] It can be understood that the failure degree of sub-data in a local range is the failure degree of the sub-data. The higher the failure degree of the sub-data, the higher the possibility that the sub-data is abnormal data or noise data; conversely, the lower the failure degree of the sub-data, the lower the possibility that the sub-data is abnormal data or noise data.
[0059] After obtaining the fault degree of each sub-data based on the above method, the sub-data in the data set can be processed based on the fault degree of each sub-data:
[0060] S3: Take any relevant data item as the target data item, and remove data points corresponding to sub-data in the target data item whose fault degree is greater than a preset threshold from the data set to obtain a target data set of the target data item.
[0061] It should be noted that sub-data with a higher degree of fault are more likely to be abnormal data or noise data. In order to accurately analyze the correlation between the relevant data items and the power supply energy consumption data, the sub-data with a higher degree of fault in the relevant data items can be eliminated and the normal sub-data in the relevant data items can be retained.
[0062] For example, the preset threshold may be 1.7, which may be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.
[0063] It can be understood that after the data points corresponding to the sub-data in the target data item whose fault degree is greater than the preset threshold are eliminated in the data set, the sub-data of the target data item in the target data set of the target data item are all normal data, and the correlation degree between the target data item and the power supply energy consumption data can be accurately obtained based on the normal data.
[0064] S4: Determine the degree of correlation between the relevant data items and the power supply energy consumption data.
[0065] It should be noted that, since the correlation between the relevant data items and the power supply energy consumption data is not exactly the same, for the relevant data items with a higher correlation, when determining the abnormal situation of the power supply energy consumption data, it is necessary to assign a higher weight to avoid dilution of its importance; and for the relevant data items with a lower correlation, when determining the abnormal situation of the power supply energy consumption data, it is necessary to assign a lower weight to reduce its impact on the abnormal situation of the power supply energy consumption data. Based on this, the correlation between the target data item and the power supply energy consumption data can be obtained based on the following steps:
[0066] By way of example, in an embodiment of the present invention, when determining the degree of correlation between relevant data items and power supply energy consumption data, energy consumption sub-data corresponding to the sub-data can be first obtained in the power supply energy consumption data, and then the degree of correlation is calculated, wherein the degree of correlation between the relevant data items and the power supply energy consumption data is negatively correlated with the number of data points in the target data set.
[0067] For example, the correlation between the target data item and the power supply energy consumption data is determined, and the specific formula is as follows:
[0068] ;
[0069] In the formula, Indicates the correlation between the jth related data item and the power supply energy consumption data, represents the number of data points in the target data set of the jth related data item, Indicates the jth related data item in the target data set. The sub-data of the j-th related data item of a data point, Indicates Energy consumption data, , Respectively represent the mean and standard deviation of the sub-data of the j-th related data item in the target data set, , Respectively represent the mean and standard deviation of power supply energy consumption data.
[0070] After obtaining the correlation between each relevant data item and the power supply energy consumption data based on the above formula, continue to perform the following steps:
[0071] S5: The anomaly score of each data point is obtained through the isolation forest algorithm, the degree of anomaly of the data point is calculated, and the monitoring result of the data point is determined. The degree of anomaly is positively correlated with the anomaly score and the correlation degree.
[0072] It should be noted that when the anomaly score of each data point is obtained by the isolation forest algorithm and the monitoring result of each data point is obtained directly based on the anomaly score, the influence of each related data item on the power consumption data is not considered, resulting in low accuracy of the monitoring result of the obtained data point. Based on this, the embodiment of the present invention obtains the degree of correlation between each related data item and the power consumption data to weight the anomaly score, thereby obtaining the monitoring result of each data point.
[0073] For example, in an embodiment of the present invention, when obtaining the anomaly score of each data point through the isolation forest algorithm, any sub-data of the target data item in the data point can be used as a segmentation point to divide all data points in the data set to obtain an isolated tree of the data point in the target data item; the path length of the data point in the isolated tree is obtained to determine the anomaly score of the data point in the target data item, and the anomaly score is negatively correlated with the path length.
[0074] It can be understood that the selection of the split point is random, and each split point can obtain an isolated tree by dividing the data point. The number of isolated trees for each data point in the target data item is the same as the number of split points in the target data item. The average of the anomaly scores of all decision trees of the target data item is taken as the anomaly score of the data point in the target data item.
[0075] The number of segmentation points in the target data item can be set according to actual needs.
[0076] In the isolation forest algorithm, abnormal data points are usually more likely to be isolated, and the shorter the path length of the data point in the isolation tree, the earlier it is isolated, and there is a large gap with the overall data point. The corresponding anomaly score is also higher, and the possibility that the data point is an abnormal data point is higher. The step of obtaining the anomaly score through the isolation forest algorithm is a prior art solution, and the embodiment of the present invention will not be repeated here.
[0077] Take an example to illustrate the anomaly score process of a data point in the target data item: if the target data item in the data point is power, randomly select the sub-data 7.5 and 7.3 of the power as split points, divide the data points in the data set respectively, and obtain the anomaly scores of isolated tree 1 corresponding to split point 7.5 and isolated tree 2 corresponding to split point 7.3. The average of the anomaly scores of isolated tree 1 and isolated tree 2 is taken as the anomaly score of the data point in the target data item power.
[0078] It can be understood that based on the above isolation forest algorithm, the abnormal score of each data point in the relevant data item can be obtained, and combined with the correlation between the relevant data item and the power supply energy consumption data, the abnormal degree of the data point can be determined:
[0079] For example, in an embodiment of the present invention, when calculating the degree of abnormality of a data point, the sum of the correlation degrees between all relevant data items and the power supply energy consumption data can be obtained, and the ratio of the degree of correlation of the relevant data items to the sum of the correlation degrees can be used as the score weight of the relevant data items to determine the degree of abnormality of the data point.
[0080] For example, the abnormality of a data point can be determined by referring to the following formula:
[0081] ;
[0082] In the formula, Indicates The degree of abnormality of the data point, Indicates the number of related data items, represents the score weight of the j-th related data item, Indicates The anomaly score of a data point in the jth related data item.
[0083] It can be understood that the higher the degree of abnormality of a data point, the higher the possibility of an abnormal situation occurring at the data point; conversely, the lower the degree of abnormality of a data point, the lower the possibility of an abnormal situation occurring at the data point.
[0084] For example, in an embodiment of the present invention, when determining the monitoring result of a data point, an abnormality threshold can be preset, and the monitoring result of the data point can be obtained by comparing the abnormality degree of the data point with the abnormality threshold; wherein, the abnormality threshold can be 1.9, and the abnormality threshold can be specifically set according to actual needs.
[0085] The comparison result of the abnormal degree of the data point and the abnormal threshold includes the following two possible situations:
[0086] In one possible case, the abnormal degree of the data point is greater than the abnormal threshold, in which case the monitoring result of the data point is abnormal.
[0087] In another possible case, the abnormal degree of the data point is less than or equal to the abnormal threshold value. In this case, the monitoring result of the data point is normal.
[0088] It can be seen that in the embodiment of the present invention, when obtaining the power supply energy consumption monitoring result of the coal preparation plant, the power supply energy consumption data and the sub-data of each relevant data item that is correlated with the power supply energy consumption can be obtained to determine a data set, the data set includes data points at each sampling time, and the data points include the sub-data of the relevant data item corresponding to the sampling time; the difference between each sub-data and the difference between the left and right adjacent sub-data is obtained in the relevant data item, and the local fluctuation degree of each sub-data is determined, and the local fluctuation degree is positively correlated with the absolute value of the difference; the local range of the sub-data is preset in the relevant data item, and the fault degree of the sub-data in the local range is determined, and the fault degree is positively correlated with the local fluctuation degree of the sub-data; any relevant data item is used as a target data item, and the data points corresponding to the sub-data in the target data item whose fault degree is greater than the preset threshold are eliminated from the data set to obtain a target data set of the target data item; the correlation degree between the relevant data item and the power supply energy consumption data is determined, and the correlation degree is negatively correlated with the number of data points in the target data set; the abnormal score of each data point is obtained by the isolation forest algorithm, the abnormal degree of the data point is calculated, and the monitoring result of the data point is determined, and the abnormal degree is positively correlated with both the abnormal score and the correlation degree.
[0089] In this way, the present invention obtains the anomaly score of each data point through the isolation forest algorithm, taking into account the different degrees of influence of each related data item on the power supply energy consumption data, based on this, by analyzing the change trend of each sub-data in the related data item, the fault degree of each sub-data is obtained, and after eliminating the data points corresponding to the sub-data with a fault degree greater than a preset threshold, the correlation degree between the related data item and the power supply energy consumption data is obtained. The monitoring result of the data point is obtained by combining the anomaly score of each data point and the correlation degree between the related data item and the power supply energy consumption data, which can effectively improve the accuracy of the power supply energy consumption monitoring result of the coal preparation plant.
[0090] After the monitoring results are obtained based on the above embodiments, different monitoring results may also be processed:
[0091] For example, if the monitoring result of the data point is normal, the data point and the corresponding monitoring result are stored in the normal database of the Internet of Things; if the monitoring result of the data point is abnormal, the data point and the corresponding monitoring result are stored in the abnormal database of the Internet of Things, and an early warning is issued.
[0092] In this way, by storing normal monitoring results in a normal database, subsequent data analysis can be facilitated; by issuing early warnings for abnormal monitoring results, it helps staff to deal with abnormal situations in a timely manner, thereby effectively reducing safety hazards.
[0093] An embodiment of the present invention also discloses a coal preparation plant power supply energy consumption monitoring system based on the Internet of Things, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a coal preparation plant power supply energy consumption monitoring method based on the Internet of Things according to the present invention is implemented.
[0094] 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.
[0095] 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.
[0096] 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.
[0097] 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 power supply energy consumption in a coal preparation plant based on the Internet of Things, characterized in that: include: Acquire power supply energy consumption data and sub-data of each relevant data item having correlation with power supply energy consumption, determine a data set, the data set includes data points at each sampling time, and the data points include sub-data of the relevant data item corresponding to the sampling time; The average of the absolute values of the differences between the sub-data and the adjacent sub-data on the left and right is used as the local fluctuation degree of the sub-data; the local range of the sub-data is preset in the relevant data item, and the fault degree of the sub-data in the local range is determined, and the fault degree is positively correlated with the local fluctuation degree of the sub-data; Take any relevant data item as the target data item, and remove the data points corresponding to the sub-data in the target data item whose fault degree is greater than a preset threshold from the data set to obtain the target data set of the target data item; determine the correlation degree between the relevant data item and the power supply energy consumption data, and the correlation degree is negatively correlated with the number of data points in the target data set of the relevant data item; The abnormality score of each data point is obtained by the isolation forest algorithm, and the abnormality degree of the data point is calculated, including: obtaining the sum of the correlation degrees between all relevant data items and the power supply energy consumption data, and taking the ratio of the correlation degree of the relevant data item to the sum of the correlation degrees as the score weight of the relevant data item; ; In the formula, Indicates The degree of abnormality of the data point, Indicates the number of related data items, represents the score weight of the j-th related data item, Indicates The anomaly score of a data point in the jth related data item is calculated, and the monitoring result of the data point is determined. The degree of anomaly is positively correlated with both the anomaly score and the degree of correlation.
2. The method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things according to claim 1 is characterized in that: The obtaining of power supply energy consumption data and sub-data of each relevant data item having correlation with power supply energy consumption includes: Acquire the initial data of power consumption at each sampling moment and the initial sub-data of the corresponding related data items through the sampling device; The power supply energy consumption initial data and initial sub-data are preprocessed to obtain the power supply energy consumption data and sub-data of each related data item.
3. The method for monitoring power consumption of a coal preparation plant based on the Internet of Things according to claim 1 is characterized in that: The failure degree of the sub-data in the local range satisfies the relationship: ; In the formula, represents the fault degree of the i-th sub-data of the j-th related data item, Indicates the local fluctuation degree of the i-th sub-data of the j-th related data item, Indicates the number of sub-data contained in the local range of the i-th sub-data of the j-th related data item, Indicates the jth related data item in the i-th sub-data local range The local fluctuation degree of individual sub-data.
4. The method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things according to claim 1 is characterized in that: Determining the degree of correlation between the relevant data item and the power supply energy consumption data includes: Acquire energy consumption sub-data corresponding to the sub-data from the power supply energy consumption data; ; In the formula, Indicates the correlation between the jth related data item and the power supply energy consumption data, represents the number of data points in the target data set of the jth related data item, Indicates the jth related data item in the target data set. The sub-data of the j-th related data item of a data point, Indicates Energy consumption data, , Respectively represent the mean and standard deviation of the sub-data of the j-th related data item in the target data set, , Respectively represent the mean and standard deviation of power supply energy consumption data.
5. The method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things according to claim 1 is characterized in that: The method of obtaining the abnormal score of each data point by using the isolation forest algorithm includes: Taking any sub-data of the target data item in the data point as a split point, all the data points in the data set are divided to obtain an isolated tree of the data point in the target data item; The path length of the data point in the isolation tree is obtained, and an anomaly score of the data point in the target data item is determined, where the anomaly score is negatively correlated with the path length.
6. The method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things according to claim 1, characterized in that: Determining monitoring results of the data points includes: Preset abnormal thresholds; If the abnormality degree of the data point is greater than the abnormality threshold, the monitoring result of the data point is abnormal; If the abnormality degree of the data point is less than or equal to the abnormality threshold, the monitoring result of the data point is normal.
7. A method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things according to claim 6, characterized in that: After determining the monitoring result of the data point, the following step further includes: If the monitoring result of the data point is normal, the data point and the corresponding monitoring result are stored in a normal database of the Internet of Things; If the monitoring result of the data point is abnormal, the data point and the corresponding monitoring result are stored in the abnormal database of the Internet of Things, and an early warning is issued.
8. A coal preparation plant power supply energy consumption monitoring system based on the Internet of Things, 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 method for monitoring power supply energy consumption in a coal preparation plant based on the Internet of Things according to any one of claims 1 to 7 is implemented.
