Intelligent Monitoring Method and System for the Operating Status of Pollution Control Equipment

Abstract

The present invention relates to the field of data processing. The present invention relates to an intelligent monitoring method and system for the operating state of pollution control equipment. The method includes: collecting pressure data in the pollution control equipment at multiple sampling moments to construct a first data set; setting the target data as other data in the first data set except for noise data; correcting the pressure values of all the target data to obtain corrected normal data; constructing a box plot on a second data set based on all the corrected normal data, and using the box plot to perform anomaly detection on the second data set; when at least one abnormal data is detected in the second data set, it is determined that the pollution control equipment is abnormal. By correcting the pressure value error caused by equipment deviation or environmental factors, the present invention creates a new data set, providing an accurate and effective data source for subsequent anomaly detection of pressure data using a box plot, thereby improving the accuracy of anomaly detection.

Description

Technical Field

[0001] The present invention relates to the field of data processing. The present invention relates to an intelligent monitoring method and system for the operating state of pollution treatment equipment. Background Art

[0002] Soil is a loose material layer on the earth's surface, mainly composed of minerals, organic matter, water and air. These components interact with each other to form the unique structure and function of the soil.

[0003] To ensure the effectiveness of soil pollution treatment, it is first necessary to ensure the stable operation of the pollution treatment equipment. Abnormal detection can be carried out on the pressure data of the internal pipeline of the pollution treatment equipment. If the detected pressure data does not match the normal pressure data, it can indicate that the equipment has an abnormality or a fault.

[0004] The box plot algorithm is an anomaly detection algorithm that can be used to detect whether there are anomalies in different categories of data. For a data set, a box plot is drawn, as Figure 1 shown, Q1 is the lower quartile, Q2 is the median, Q3 is the upper quartile, IQR is the interquartile range, Q3 + 1.5IQR is the upper limit, Q1 - 1.5IQR is the lower limit, and the hollow circles represent outliers.

[0005] In the drawn box plot, a standard for identifying outliers is provided for us: outliers are defined as values less than Q1 - 1.5IQR or greater than Q3 + 1.5IQR, so as to identify the outliers in the data set. However, when constructing a box plot according to the data set, some data in the data set may have numerical deviations due to external interference during data collection. When performing box plot anomaly detection, some data cannot meet the standard for identifying outliers, resulting in a decrease in the accuracy of anomaly detection. Summary of the Invention

[0006] To solve the technical problem that when constructing a box plot according to a data set, some data in the data set may have numerical deviations due to external interference during data collection, and when performing box plot anomaly detection, some data cannot meet the standard for identifying outliers, resulting in a decrease in the accuracy of anomaly detection, the present invention provides solutions in the following aspects.

[0007] In a first aspect, an intelligent monitoring method for the operating state of pollution treatment equipment includes:

[0008] Collecting pressure data in the pollution treatment equipment at multiple sampling times to construct a first data set; dividing the pressure data in the first data set into noise data and target data; the target data is other data in the first data set except the noise data;

[0009] Calibrate the pressure values of all the target data to obtain the calibrated normal data;

[0010] Based on all the calibrated normal data, construct a second data set, construct a box plot on the second data set, and use the box plot to perform outlier detection on the second data set;

[0011] When at least one outlier data is detected in the second data set, it is determined that the pollution treatment equipment is abnormal;

[0012] Among them, the pressure value of the calibrated normal data is obtained by subtracting the deviation value from the pressure value of the target data. The deviation value is the product of the difference between the pressure value of the target data and the average pressure value in the target data segment and the calibration coefficient. The target data segment is a corresponding data segment intercepted in the first data set centered on the corresponding target data; the calibration coefficient is used to adjust the pressure value corresponding to the target data.

[0013] Beneficial effects: First, denoise all the pressure data in the first data set to exclude the noise components that may affect the accuracy of the detection results. Then, further process all the denoised pressure data, apply the calibration coefficient to adjust the pressure values of the pressure data to correct the pressure value deviations caused by equipment deviations or environmental factors, and create a new data set that only contains the calibrated normal data, providing an accurate and effective data source for subsequent outlier detection using box plots, thereby improving the accuracy of outlier detection.

[0014] In one embodiment, the steps for obtaining the target data are as follows:

[0015] The steps for obtaining the target data are as follows:

[0016] Collect the flow rate data of the leaching solution in the pollution treatment equipment at multiple sampling times to construct a flow rate data set;

[0017] Calculate the noise coefficient of any pressure data in the first data set. When the noise coefficient of the pressure data is greater than the preset threshold, determine that the pressure data is noise data, and then mark the other data in the first data set except the noise data as target data.

[0018] Beneficial effects: By calculating the noise coefficient of the pressure data and setting a threshold, noise data and valid data can be effectively distinguished, thereby improving the overall quality of the data set; marking the other data except the noise data as target data ensures the accuracy of subsequent processing and analysis and lays a foundation for the correct evaluation of the equipment status.

[0019] In one embodiment, the calculation process of the noise coefficient is as follows:

[0020] At the same sampling moment, a first data segment is obtained with the corresponding pressure data as the center, and a second data segment of the same length as the first data segment is obtained with the corresponding flow data as the center;

[0021] Calculate the first volatility of the pressure data in the first data segment, and calculate the second volatility between all the pressure data in the first data segment and the corresponding flow data;

[0022] Take the product of the first volatility and the second volatility as the noise coefficient.

[0023] Beneficial effects: Calculating the first volatility of the pressure data and the second volatility between pressure and flow helps to comprehensively evaluate the variability and correlation of the data. At the same time, taking the product of the first volatility and the second volatility as the noise coefficient can amplify the influence of noise, making the identification of noise data more sensitive and accurate.

[0024] In one embodiment, the second volatility is: ; where is the second volatility, is the percentile of the th pressure data in the first data segment, is the percentile of the th flow data in the second data segment, represents the mean of the differences between the percentiles of all the pressure data and the corresponding flow data in the first data segment and the second data segment; the percentile is used to characterize the degree of abnormality of the data.

[0025] Beneficial effects: By calculating the percentiles of the pressure data and the flow data, the position of the data in the overall distribution can be accurately characterized, thereby identifying those outliers that deviate from the normal range; calculating the absolute value of the difference between the percentiles of the pressure data and the flow data helps to capture the inconsistency and potential abnormal fluctuations between the two.

[0026] In one embodiment, the first volatility is the difference between the difference between the pressure value of the th pressure data and the maximum pressure value in the first data segment and the difference between the pressure value of the th pressure data and the minimum pressure value in the first data segment.

[0027]

[0028] Beneficial effects: By calculating the difference between the differences between the pressure value and the maximum and minimum pressure values in the data segment, abnormal fluctuations in the pressure data can be effectively identified, thereby improving the overall quality of the first data set.

[0028] In one embodiment, the correction coefficient is:

[0029] ; where represents the correction coefficient, represents the The minimum sampling time interval between a target data and surrounding noise data Denote the pressure value of the th target data Denote the pressure value of the noise data with the smallest sampling time interval from the th target data

[0030] In one embodiment, the step of using the box plot to perform anomaly detection on the second data set is as follows:

[0031] Segment the time series of the pressure data in the second data set to obtain multiple sub-data segments;

[0032] Sort the pressure data in any sub-data segment according to the magnitude of the pressure value to obtain the upper quartile, lower quartile, median, interquartile range, upper limit, and lower limit;

[0033] Determine the anomaly range, and regard the data smaller than the lower limit or larger than the upper limit as anomaly data.

[0034] In a second aspect, an intelligent monitoring system for the operating state of pollution treatment equipment includes: a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned intelligent monitoring method for the operating state of pollution treatment equipment is implemented. Description of the Drawings

[0035] By referring to the accompanying drawings and reading the following detailed description, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become easy to understand. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, where:

[0036] Figure 1 is a schematic diagram of a box plot.

[0037] Figure 2 is a flowchart of the methods of steps S1 - S4 in the intelligent monitoring method for the operating state of pollution treatment equipment according to the embodiment of the present invention. Detailed Embodiments

[0038] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0039] An embodiment of the present invention discloses an intelligent monitoring method for the operating state of pollution treatment equipment. Refer to Figure 2 , which includes steps S1 - S4, specifically as follows

[0040] S1: Collect pressure data in the pollution treatment equipment at multiple sampling times to construct a first data set; divide the pressure data in the first data set into noise data and target data; the target data is other data in the first data set except for the noise data.

[0041] In the embodiment of the present invention, a pressure sensor is used to collect the pressure data in the soil pollution treatment equipment, and a flowmeter is used to measure the flow rate data of the leaching solution at the outlet of the above equipment. The specific collection duration is thirty minutes, and the collection frequency is once per second. Then, an analog - to - digital conversion device is used to digitally convert the pressure data and the flow rate data to obtain the digital representations of the pressure data and the flow rate data, thereby constructing the corresponding first data set and second data set.

[0042] Since when collecting the pressure data, due to the influence of the external environment or the collection equipment, noise data appears in the first data set, and the existence of the noise data will cause the pressure values corresponding to the surrounding pressure data to be abnormal. Therefore, the pressure data in the first data set is divided into noise data and other data except for the noise data. The other data except for the noise data is marked as target data.

[0043] The steps for obtaining the above - mentioned target data are as follows:

[0044] At any sampling time, with the th pressure data in the first data set as the center, 50 pressure data are selected on each of its left and right sides as the first data segment. If there are less than 50 pressure data on one side of the th pressure data, they can be supplemented on the other side. Similarly, the second data segment of the th flow rate data at the same sampling time in the second data set can be obtained.

[0045] According to Bernoulli's law, when a fluid passes through a pipe or equipment, there is a balance relationship between the kinetic energy and the pressure energy of the fluid, and an increase in pressure will increase the kinetic energy of the fluid.

[0046] First, calculate the difference between the difference between the pressure value of the th pressure data and the maximum pressure value in the first data segment and the difference between the pressure value of the th pressure data and the minimum pressure value in the first data segment to obtain the first volatility of the pressure data in the first data segment.

[0047] Then, the expression of the above - mentioned first volatility is as follows:

[0048]

[0049] In the formula, is the first volatility of the th pressure data, is the th pressure value of the pressure data, , are respectively the maximum pressure value and the minimum pressure value in the first data segment.

[0050] The first volatility obtained through the above calculation reflects the volatility of the corresponding pressure data in its first data segment. If the value of the first volatility is larger, it indicates that the pressure data is closer to a certain extreme value, showing a larger volatility, and then the performance of the pressure data will be more abnormal.

[0051] Secondly, calculate the percentile of the th pressure data in the first data segment and the percentile of the corresponding th flow data to obtain the second volatility between the pressure data and the corresponding flow data.

[0052] Then the expression of the above second volatility is as follows:

[0053]

[0054] In the formula, is the second volatility, is the percentile of the th pressure data in the first data segment, is the percentile of the th flow data in the second data segment, represents the mean value of the differences between the percentiles of all pressure data and the corresponding flow data in the first data segment and the second data segment.

[0055] It should be noted that the percentile is a very crucial concept in statistics, which is used to characterize the position of a certain percentage in a data set. In the implementation of the present invention, by comparing the percentiles of data, outliers in the data set can be found. For example, in the first data set, if the value of the th pressure data is much lower than the 25th percentile or higher than the 75th percentile, then the th pressure data may be regarded as an outlier.

[0056] Take the product of the first volatility and the second volatility as the The noise coefficient of each pressure data can be obtained in the same way for all pressure data in the first dataset, and a threshold is set. The pressure data with a noise coefficient greater than or equal to the threshold is marked as noise data, and vice versa as target data. In the implementation of the present invention, the threshold is set to 0.85. In other embodiments, it can be set according to specific circumstances.

[0057] The noise coefficient of the above-mentioned th pressure data is expressed as follows:

[0058]

[0059] In the formula, is the noise coefficient of the th pressure data, is the normalization function, is the second volatility, is the first volatility.

[0060] S2: Correct the pressure values of all the target data to obtain the corrected normal data.

[0061] After obtaining all the target data in the previous step, analyze the numerical performance of the surrounding data of the target data. For a target data, the more noise data it contains in its data segment, the closer the sampling time interval to the noise data, and the smaller the numerical difference from the noise data, the greater the influence of the noise on the target data, and the more the pressure value of the target data needs to be corrected.

[0062] In the embodiment of the present invention, calculate the pressure value correction coefficient of the target data according to the actual difference between the target data and the surrounding noise data, and adjust the pressure value of the target data through the correction coefficient to correct the pressure value error caused by equipment deviation or environmental factors.

[0063] Specifically, for all target data, select the th target data in the first dataset and intercept its corresponding target data segment. The method of obtaining this target data segment is the same as that of obtaining the first data segment above, and will not be elaborated here.

[0064] Then the pressure value correction coefficient of the th target data is:

[0065]

[0066] In the formula, represents the pressure value correction coefficient of the th target data, represents the minimum sampling time interval between the th target data and the surrounding noise data, represents the The pressure value of a target data represents the pressure value of the noise data with the smallest sampling time interval from the th target data, represents the number of noise data in the target data segment.

[0067] The larger the pressure value correction coefficient of the th target data, the more the target data needs to be corrected.

[0068] It should be noted that in other embodiments, the method for correcting the pressure value of the target data can also be: mechanical correction method: calibrating the pressure sensor using a standard calibration device; static pressure calibration method: comparing the sensor with a standard device with known accuracy to determine the deviation of the sensor and perform correction, etc.

[0069] According to the above-mentioned method for obtaining the pressure value correction coefficient of the th target data, the pressure value correction coefficients of all target coefficients can be obtained. By correcting the pressure value of the corresponding target data using the correction coefficient, all corrected normal data can be obtained.

[0070] Specifically, taking the th target data as an example, the average pressure value in the target data segment is obtained, and the deviation value of the target data is calculated. Then, the expression of the pressure value of the corrected normal data is as follows:

[0071]

[0072] In the formula, is the pressure value of the corrected normal data, is the pressure value of the th target data, is the average pressure value in the target data segment, is the pressure value correction coefficient of the th target data. represents the deviation value of the th target data.

[0073] Among them, setting the value of 0.5 is to round the pressure value of the pressure correction.

[0074] S3: Based on all the corrected normal data, construct a second data set, construct a box plot on the second data set, and use the box plot to perform outlier detection on the second data set.

[0075] Construct a second data set with all the corrected normal data. At this time, all the data in the second data set are accurate and valid. Construct a box plot on the second data set and use the box plot to perform anomaly detection on the second data set.

[0076] The steps of using the box plot to perform anomaly detection on the second data set are as follows:

[0077] Segment the time series of the pressure data in the second data set, and use 200 data as a sub-data segment for anomaly detection;

[0078] Sort the pressure data in any sub-data segment according to the pressure value to obtain the upper quartile, lower quartile, median, interquartile range, upper limit, and lower limit;

[0079] Determine the anomaly range, and regard the data less than the lower limit or greater than the upper limit as anomaly data.

[0080] S4: When at least one anomaly data is detected in the second data set, it is determined that the pollution control equipment is abnormal.

[0081] Summarize the anomaly data detected by anomaly detection in step S3. When there is at least one anomaly data, the soil pollution control equipment is abnormal. Subsequently, an alarm can be issued to enable relevant technical personnel to discover and handle equipment failure problems in a timely manner, ensuring the efficiency and safety of soil pollution control.

[0082] By distinguishing noise data from other data, the present invention eliminates noise components that may affect the accuracy of detection results, applies a correction coefficient to adjust the pressure values of other data to correct the pressure value errors caused by equipment deviations or environmental factors, and creates a new data set that only contains corrected normal data, providing an accurate and valid data source for subsequent anomaly detection using a box plot, thereby improving the accuracy of anomaly detection.

[0083] The embodiment of the present invention also discloses an intelligent monitoring system for the operating state of a pollution control equipment, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent monitoring method for the operating state of the pollution control equipment according to the present invention is implemented.

[0084] The system also includes other components well-known to those skilled in the art such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be described in detail here.

[0085] In the present invention, the foregoing memory may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the 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 program, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0086] In the description of this specification, the meanings of "a plurality of" and "several" are at least two, for example, two, three, or more, etc., unless otherwise specifically defined.

[0087] Although this specification has shown and described multiple 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 think of many changes, alterations, and alternative ways without departing from the spirit and concept of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in the practice of the present invention.

Claims

1. An intelligent monitoring method for the operation status of pollution control equipment, characterized in that: include: Collect pressure data in the pollution control equipment at multiple sampling times to construct a first data set; dividing the pressure data in the first data set into noise data and target data; The target data is other data in the first data set except the noise data; The steps for obtaining the target data are as follows: Collect flow data of the eluent in the pollution control equipment at multiple sampling times to construct a flow data set; Calculate the noise coefficient of any pressure data in the first data set, and when the noise coefficient of the pressure data is greater than a preset threshold, determine that the pressure data is noise data, and then mark the other data in the first data set except the noise data as target data; Correcting the pressure values ​​of all the target data to obtain corrected normal data; Based on all the corrected normal data, construct a second data set, construct a box plot on the second data set, and perform anomaly detection on the second data set using the box plot; When at least one abnormal data is detected in the second data set, it is determined that the pollution control equipment is abnormal; The calculation process of the noise coefficient is as follows: At the same sampling time, a first data segment is obtained with the corresponding pressure data as the center, and a second data segment of the same length as the first data segment is obtained with the corresponding flow data as the center; Calculating a first volatility of the pressure data in the first data segment, and calculating a second volatility between all the pressure data and the corresponding flow data in the first data segment; Taking the product of the first volatility and the second volatility as the noise coefficient; The second volatility is: ; In the formula, is the second volatility, The first data segment Percentile of pressure data, The second data segment The percentile of the flow data, represents the mean of the percentile differences between all the pressure data and the corresponding flow data in the first data segment and the second data segment; the percentile is used to characterize the degree of abnormality of the data; The pressure value of the corrected normal data is obtained by subtracting the deviation value from the pressure value of the target data. The deviation value is the product of the difference between the pressure value of the target data and the average pressure value in the target data segment and the correction coefficient. The target data segment is centered on the corresponding target data and the corresponding data segment is intercepted in the first data set; the correction coefficient is used to adjust the pressure value corresponding to the target data.

2. The method for intelligently monitoring the operating status of pollution control equipment according to claim 1, characterized in that: The first volatility is The difference between the pressure value of the pressure data and the maximum pressure value in the first data segment and the minimum pressure value.

3. The method for intelligently monitoring the operating status of pollution control equipment according to claim 2, characterized in that: The correction factor is: ; In the formula, represents the correction coefficient, Indicates The minimum sampling time interval between the target data and the surrounding noise data, Indicates The pressure value of the target data, Indicates The pressure value of the noise data with the smallest sampling time interval of the target data, Indicates the number of noise data in the target data segment.

4. The method for intelligently monitoring the operating status of pollution control equipment according to claim 3 is characterized in that: The step of using the box plot to perform anomaly detection on the second data set is: Segmenting the time series of the pressure data in the second data set to obtain a plurality of sub-data segments; The pressure data in any sub-data segment are sorted according to the pressure value to obtain the upper quartile, lower quartile, median, interquartile range, upper limit and lower limit; Determine the abnormal range and treat data that is less than the lower limit or greater than the upper limit as abnormal data.

5. Intelligent monitoring system for the operation status of pollution control 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, the method for intelligently monitoring the operating status of pollution control equipment according to any one of claims 1 to 4 is implemented.

Images