Petrochemical engineering-oriented drainage pool water quality real-time monitoring method

Abstract

The invention relates to the technical field of data processing, in particular to a petrochemical engineering-oriented discharge pool water quality real-time monitoring method, which comprises the following steps: collecting water quality conductivity data and pH value data and the minimum operation positive period of a discharge pool wastewater treatment system, calculating local abnormal values of each conductivity data and pH value data, and calculating the minimum operation positive period of the discharge pool wastewater treatment system; obtaining the correlation difference value of all the conductivity data, obtaining the noise expression degree of each conductivity data in combination with the difference of the correlation difference values of the conductivity data at the same position in other periods, and further obtaining the prediction weight of each conductivity data; and obtaining a predicted value of each piece of conductivity data according to the predicted weight of each piece of conductivity data, thereby completing real-time monitoring on the water quality of the petrochemical discharge pool. The prediction weight is determined by analyzing the water quality conductivity data, interference of noise data is avoided, and the water quality of the petrochemical drain tank is accurately monitored in real time.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to a real-time monitoring method for water quality in a discharge pool for petrochemical industry. Background Art

[0002] Petrochemical discharge pools may contain a variety of chemicals and pollutants, including organic matter, heavy metals, salts, etc. Real-time monitoring can help timely detect excessive emissions or abnormal conditions of pollutants, protect the surrounding environment from pollution, and ensure that emissions meet the requirements and standards of laws and regulations. Water conductivity can reflect the electrolyte content in water. By real-time monitoring of conductivity changes, the changing trend of water pollution can be evaluated to provide accurate data support for the formulation of pollution prevention and control measures. At present, abnormal data of water conductivity in petrochemical discharge pools are often monitored in real time. The abnormal data of water conductivity reflects the water pollution in petrochemical discharge pools, and adaptive measures are then taken.

[0003] The existing technology often uses AR (Autoregression) models to make real-time predictions on water conductivity data at the most recent time, and judges abnormal water conductivity data by the difference between the predicted value and the actual value at the same time, thereby realizing real-time monitoring of water quality through abnormal water conductivity data. The prediction weights of each historical data in the traditional AR prediction model are determined by artificial experience values. Due to the influence of noise in the historical data, the prediction weights will be inaccurate, resulting in low prediction accuracy of the prediction value, and the water quality cannot be accurately detected in real time. Summary of the invention

[0004] The invention provides a real-time monitoring method for water quality in a discharge pool for petrochemical industry to solve the existing problems.

[0005] The present invention is a method for real-time monitoring of water quality in a petrochemical discharge pool using the following technical solutions: An embodiment of the present invention provides a method for real-time monitoring of water quality in a discharge pool for petrochemical industry, the method comprising the following steps: Collect water quality conductivity data and pH value data, each collection moment corresponds to one conductivity data and one pH value data; obtain the minimum positive operation cycle of the discharge pool wastewater treatment system; According to the difference between each conductivity data and the surrounding conductivity data, the local abnormal value of each conductivity data is obtained; the local abnormal value of each pH value data is obtained; according to the local abnormal value ratio of each conductivity data and the pH value data at the corresponding collection time, a local abnormal ratio curve is constructed, and the local abnormal ratio curve is segmented to obtain a number of segmented data; according to the local abnormal ratio difference and data correlation between the conductivity data of each segmented data and the pH value data at the corresponding collection time, the correlation difference value of all conductivity data is obtained; according to the difference in the correlation difference value of the minimum running positive cycle of each conductivity data and the correlation difference value of the conductivity data at the same position in other cycles, the noise performance degree of each conductivity data is obtained; The time interval between each conductivity data and the prediction moment is taken as a weight, and the prediction weight of each conductivity data is obtained in combination with the noise performance degree of each conductivity data; the predicted value of the conductivity data at each prediction moment is obtained through the prediction weight of each conductivity data; and the water quality of the petrochemical discharge pool is monitored in real time according to the predicted value of the conductivity data.

[0006] Furthermore, the local abnormal value of each conductivity data is obtained according to the difference between each conductivity data and the surrounding conductivity data, and the specific formula included is as follows: In the formula, Represents the local outlier of the i-th data in the conductivity data; Represents the conductivity value of the i-th data in the conductivity data; Represents the mean of the conductivity values ​​of all conductivity data; Represents the number of neighboring data of the i-th data in the conductivity data; Represents the conductivity value of the jth neighboring data of the i-th data in the conductivity data; Represents the standard deviation between the i-th data and the adjacent data in the conductivity data; represents the linear normalization function, Represents the absolute value function.

[0007] Furthermore, the method for obtaining the neighboring data includes the following specific steps: A neighborhood is constructed with the ith data in the conductivity data as the center, and the conductivity data points in the neighborhood are recorded as the neighboring data of the ith data.

[0008] Furthermore, the local abnormality ratio curve is constructed according to the local abnormality ratio of each conductivity data and the pH value data at the corresponding collection time, and the local abnormality ratio curve is segmented to obtain a plurality of segmented data, including the following specific steps: The ratio of the local abnormal value of each conductivity data to the local abnormal value of the pH value data at the corresponding acquisition time is recorded as the local abnormal ratio, and a curve space is constructed using all the local abnormal ratios. In the curve space, the conductivity data is used as the horizontal axis, and the value of the local abnormal ratio is used as the vertical axis. All the local abnormal ratios are projected into the curve space to obtain a local abnormal ratio curve; The local abnormal ratio curve is segmented according to the average of the acquisition time to obtain a number of segmented data.

[0009] Furthermore, according to the local abnormal ratio difference and data correlation between the conductivity data of each segmented data and the pH value data at the corresponding collection time, the correlation difference value of all conductivity data is obtained, including the specific formula as follows: In the formula, Represents the correlation difference value of the i-th data in the conductivity data; represents the i-th local anomaly ratio in the local anomaly ratio curve; Represents the mean of all local anomaly ratios in the local anomaly ratio curve; The number of segments representing the local anomaly ratio curve; Indicates the segmented data where the i-th local abnormal ratio value in the local abnormal ratio curve is located; Indicates the xth segment data in the local abnormal ratio curve, except for the segment data where the ith local abnormal ratio is located; is an exponential function with a natural constant as base; represents the function for calculating the Pearson correlation coefficient, Represents the absolute value function.

[0010] Furthermore, the noise performance degree of each conductivity data is obtained according to the difference between the correlation difference value of the minimum positive operation cycle of each conductivity data and the correlation difference value of the conductivity data at the same position in other cycles, and the specific formula included is as follows: In the formula, Indicates the degree of noise performance of the i-th data in the conductivity data; is the first parameter, is the second parameter; Represents the normalization function.

[0011] Furthermore, the specific steps of obtaining the first parameter and the second parameter are as follows: First parameter The calculation method is: Second parameter The calculation method is: In the formula, Represents the correlation difference value of the i-th data in the conductivity data; Indicates the number of all minimum operating cycles; It represents the correlation difference value of the conductivity data at the same collection time in the minimum operation cycle of the ith data in the yth cycle except the minimum operation cycle of the ith data in the conductivity data; Indicates the maximum value of the correlation difference value in the minimum operation cycle of the i-th data in the conductivity data; It represents the maximum value of the correlation difference value in the yth period of the conductivity data except the minimum operating period of the ith data. Represents the absolute value function.

[0012] Furthermore, the time interval between each conductivity data and the prediction time is used as a weight, and the prediction weight of each conductivity data is obtained in combination with the noise performance degree of each conductivity data, including the specific formula as follows: In the formula, Represents the prediction weight of the i-th data in the conductivity data; represents the initial weight; Indicates the degree of noise performance of the i-th conductivity data; Represents the time interval between the i-th data in the conductivity data and the predicted time; Represents the normalization function.

[0013] Furthermore, the predicted value of the conductivity data at each prediction moment is obtained by using the prediction weight of each conductivity data, and the specific steps include the following: Input each conductivity data and the prediction weight of the conductivity data into the AR model to obtain the kth data prediction value at the prediction moment; In the formula, Represents the k-th data prediction value at the prediction time; Represents the prediction weight of the i-th data in the conductivity data; Represents the conductivity value of the i-th data in the conductivity data; Indicates the number of conductivity data used for prediction.

[0014] Furthermore, the real-time monitoring of the water quality of the petrochemical discharge pool according to the predicted value of the conductivity data includes the following specific steps: Obtain the residual data between the data prediction value and the conductivity value at each prediction moment, perform Z-score statistics on all residual data, and then use the Z-score statistical algorithm to obtain the Z score of each residual data. The residual data whose absolute value of the Z score is greater than the preset abnormal threshold is recorded as abnormal water quality conductivity data. When the number of abnormal water quality conductivity data exceeds the preset abnormal number, take water quality cleaning measures.

[0015] The beneficial effects of the technical solution of the present invention are: collecting water quality conductivity data and pH value data and the minimum positive operation cycle of the discharge pool wastewater treatment system, calculating the local abnormal value of each conductivity data and pH value data, and preliminarily reflecting the characteristics of the noise data; thereby obtaining the correlation difference value of all conductivity data, combining the difference in the correlation difference value of the conductivity data at the same position in other cycles, and obtaining the noise performance degree of each conductivity data, which is conducive to appropriately adjusting the prediction weight of each conductivity data, and then obtaining the prediction value of each conductivity data through the prediction weight of each conductivity data, avoiding the interference of noise data, and improving the accuracy of real-time monitoring of the water quality of the petrochemical discharge pool. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 The present invention is a flow chart of the steps of a method for real-time monitoring of water quality in a petrochemical discharge pool. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a real-time water quality monitoring method for a discharge pool for petrochemical industry proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of the real-time monitoring method of water quality in a discharge pool for petrochemical industry provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flow chart of the steps of a method for real-time monitoring of water quality in a discharge pool for petrochemical industry provided by an embodiment of the present invention, the method comprising the following steps: Step S001, collect water conductivity data and pH value data to obtain the minimum positive operation cycle of the discharge pool wastewater treatment system.

[0022] The main purpose of this embodiment is to predict the water conductivity data in the petrochemical discharge pool, and to realize abnormal monitoring according to the difference between the predicted result and the actual water conductivity. First, a water conductivity sensor is installed in the petrochemical discharge pool to be monitored, and the water conductivity data at each sampling time is acquired by using the sensor, and the water pH value is synchronously acquired by using the pH value detection instrument to acquire the water pH value data pH. The time interval of the wastewater treatment system for wastewater cleaning is recorded, and one wastewater cleaning is recorded as a treatment cycle. The mean of the number of conductivity data of all treatment cycles is taken as the minimum positive operation cycle of the wastewater treatment system of the petrochemical discharge pool. The interval of the collection time of the conductivity data and the pH value data is described in this embodiment by taking the measurement once every 10 minutes as an example, and the range of the collection time of the conductivity data and the pH value data is described in this embodiment by taking the recent 40 days as an example. The interval of the collection time and the range of the collection time can be set to other values ​​in other embodiments, and this embodiment does not specifically limit them. It should be noted that, since the neutral value of pH is 7, the pH value data in this embodiment is the absolute value of the difference between the value collected by the pH value detection instrument and the neutral value of 7.

[0023] Step S002: Obtain a local abnormal value of each conductivity data according to the difference between each conductivity data and surrounding conductivity data.

[0024] It should be noted that the purpose of this embodiment is to adapt the prediction weights of each historical data in the AR prediction model, and then obtain the predicted value of water quality conductivity from the prediction weights. The noise data will affect the predicted value in the AR prediction model, so it is necessary to judge the noise probability of each water quality conductivity data and reduce the prediction weight of the noise data. Since the noise data has the characteristics of sudden rise and fall in all data, this embodiment makes a preliminary judgment on the noise probability of water quality conductivity data based on the local characteristics of the data. The AR model described in this embodiment is a well-known technology, and this embodiment will not be repeated in detail.

[0025] Specifically, if the difference between a certain conductivity data and the data mean of the overall conductivity data is larger, it means that the noise probability of the conductivity data is larger; at the same time, if the numerical difference between a certain conductivity data and the adjacent data is larger, and the standard deviation of the local data segment formed by the conductivity data and the adjacent data is larger, it means that the conductivity data is more likely to be noise data. Then the calculation method of the local outlier value of the i-th data in the conductivity data is as follows: In the formula, Represents the local outlier of the i-th data in the conductivity data; Represents the conductivity value of the i-th data in the conductivity data; Represents the mean of the conductivity values ​​of all conductivity data; represents the number of neighboring data of the i-th data in the conductivity data, wherein the neighboring data is obtained by constructing a neighborhood with the i-th data in the conductivity data as the center, and the conductivity data in the neighborhood is recorded as the neighboring data of the i-th data. In this embodiment, 8 conductivity data are selected with the i-th conductivity data as the center for description. In other implementations, it can be set to other values, which are not limited in this embodiment; Represents the conductivity value of the jth neighboring data of the i-th data in the conductivity data; Represents the standard deviation between the i-th data and the adjacent data in the conductivity data; represents the linear normalization function, Represents the absolute value function.

[0026] It indicates the numerical difference between the ith data in the conductivity data and the overall conductivity data. The larger the value, the greater the difference in the mean level between the ith conductivity data and the overall conductivity data, which means the greater the probability of noise in the conductivity data. It indicates the difference between the conductivity values ​​of the ith conductivity data and the adjacent data. The larger the value, the more obvious the local anomaly of the ith conductivity data is, and the more likely it is noise data. The larger the value is, the more obvious the fluctuation characteristics of the local data segment corresponding to the i-th conductivity data are, and the greater the noise probability of the i-th conductivity data is.

[0027] Similarly, according to the difference between each pH value data and the surrounding pH value data, the local abnormal value of each pH value data is obtained. It should be noted that the calculation method of the local abnormal value of the pH value data is the same as the calculation method of the conductivity data.

[0028] At this point, the local outlier value of each conductivity data and the local outlier value of each pH value data are obtained.

[0029] Step S003, constructing a local anomaly ratio curve, and evenly segmenting the local anomaly ratio curve; obtaining the correlation difference value of all conductivity data according to the local anomaly ratio difference and data correlation of the conductivity data and pH value data of each segmented data.

[0030] It should be noted that when analyzing the characteristics of water quality conductivity data, the pH value of water quality will affect the water quality conductivity data, thereby affecting the prediction weight of the predicted value in the AR prediction model. The correlation characteristics of water quality pH value and water quality conductivity can be combined for analysis. pH value is an indicator of the acidity and alkalinity of water. Hydrogen ions in acidic solutions and hydroxide ions in alkaline solutions can increase conductivity. When the water body is acidic or alkaline, its conductivity is usually higher. When the pH value of water quality tends to be acidic or alkaline, the conductivity data of water quality is larger; when the pH value of water quality tends to be neutral, the conductivity data of water quality is smaller. Therefore, the correlation difference value of water quality conductivity data can be obtained based on the difference between local outliers in water quality conductivity data and water quality pH value data.

[0031] Specifically, the ratio of the local anomaly value of each conductivity data to the local anomaly value of the pH data at the corresponding collection time is recorded as the local anomaly ratio, all local anomaly ratios are obtained and a curve space is constructed, in which the conductivity data is used as the horizontal axis and the local anomaly ratio value is used as the vertical axis, and all local anomaly ratios are projected into the curve space to obtain a local anomaly ratio curve.

[0032] Further, the local abnormal ratio curve is evenly divided into M segments according to the acquisition time to obtain M segmented data. In this embodiment, M , this is used as an example for description, and other values ​​may be set in other implementation modes, and this embodiment does not limit this.

[0033] Then the calculation method of the correlation difference value of the i-th data in the conductivity data is as follows: In the formula, Represents the correlation difference value of the i-th data in the conductivity data; represents the i-th local anomaly ratio in the local anomaly ratio curve; Represents the mean of all local anomaly ratios in the local anomaly ratio curve; The number of segments representing the local anomaly ratio curve; Indicates the segmented data where the i-th local abnormal ratio value in the local abnormal ratio curve is located; Indicates the xth segment data in the local abnormal ratio curve, except for the segment data where the ith local abnormal ratio is located; is an exponential function with a natural constant as base; represents the function for calculating the Pearson correlation coefficient, Represents the absolute value function. It indicates the difference between the i-th ratio in the local abnormal ratio curve and the mean level of all ratios. The larger the value, the less the ratio satisfies the correlation between the conductivity data and the water quality pH data, and the smaller the correlation difference value. It represents the mean of the Pearson correlation coefficient between the segment where the ith local anomaly ratio is located and the other segments in the local anomaly ratio curve. The smaller the value, the worse the correlation between the segment where the ith local anomaly ratio is located and the other segments in the local anomaly ratio curve. The greater the noise probability of the ith conductivity data, the smaller the correlation difference value.

[0034] Similarly, the correlation difference value of all conductivity data is obtained according to the difference and correlation between the conductivity data and the pH value data on the local abnormal ratio curve.

[0035] Step S004: Obtain the noise performance degree of all data in the conductivity data according to the difference between the correlation difference value of the minimum positive operation cycle of each conductivity data and the correlation difference value of the conductivity data at the same position in other cycles.

[0036] It should be noted that the operation periodicity of the wastewater treatment system in the discharge pool may affect the concentration of various chemical substances in the wastewater, thereby affecting the conductivity value of the water quality. Because the petrochemical production process often operates according to a certain periodicity, the composition and properties of the wastewater change periodically, which in turn causes the water conductivity data in the discharge pool to show periodic changes.

[0037] Specifically, for the minimum positive operation cycle of the discharge pool wastewater treatment system, the greater the data difference at the corresponding position in each cycle, the greater the noise performance of the data. The calculation method of the noise performance of the i-th data in the conductivity data is as follows: Among them, the first parameter The calculation method is: Second parameter The calculation method is: In the formula, Indicates the degree of noise performance of the i-th data in the conductivity data; Represents the correlation difference value of the i-th data in the conductivity data; Indicates the number of all minimum operating cycles; It represents the correlation difference value of the conductivity data at the same collection time in the minimum operation cycle of the ith data in the yth cycle except the minimum operation cycle of the ith data in the conductivity data; Indicates the maximum value of the correlation difference value in the minimum operation cycle of the i-th data in the conductivity data; Indicates the maximum value of the correlation difference value in the yth period of the conductivity data except the minimum operating period where the ith data is located; represents the normalization function, Represents the absolute value function.

[0038] First parameter It indicates the numerical difference between the i-th data and other corresponding periodic positions in the conductivity data. The larger the value, the greater the abnormality of the correlation difference value of the i-th data, and the greater the noise probability of the i-th conductivity data; It represents the difference between the correlation difference value of the i-th data in the conductivity data and the maximum value of the large correlation difference value in the period, which is recorded as the difference characteristic value of the i-th data; Indicates the conductivity data except the period where the i-th data is located. The correlation difference value of the conductivity data at the same position of the ith data in the other cycles is The difference characteristic value of the maximum value of the correlation difference value in other periods, then the second parameter It represents the difference between the difference characteristic value of the i-th data in the conductivity data and the difference characteristic value of the data at the same position in other periods. The larger the difference value is, the greater the correlation of the i-th data is in different periods, and the greater the degree of the i-th noise performance is.

[0039] Similarly, according to the correlation difference value of each data in the conductivity data, the noise performance degree of all data in the conductivity data is obtained.

[0040] Step S005: obtain the prediction weight of each data in the conductivity data according to the noise performance degree of each data in the conductivity data and the time interval with the prediction time; obtain the prediction value of each data at the prediction time through the prediction weight, and monitor the water quality of the petrochemical discharge pool in real time.

[0041] It should be noted that if the noise performance of a certain conductivity data is greater and the interval from the prediction time is farther, then when using the AR model for prediction, since the conductivity may change greatly over time, the conductivity data that is farther away from the prediction time will have a lower reference value when making predictions, that is, the conductivity data that is farther away from the prediction time will have a smaller prediction weight for the predicted value, so the prediction weight of this conductivity data will be reduced in the AR prediction model.

[0042] Specifically, the prediction weight of the i-th data in the conductivity data is calculated according to the noise performance degree of the i-th data in the conductivity data and the time interval with the prediction time, and each conductivity data and the prediction weight of the conductivity data are input into the AR model to obtain the prediction value of the k-th data at the prediction time.

[0043] Then the prediction weight calculation method of the i-th data in the conductivity data is: The calculation method of the kth data prediction value at the prediction time is: In the formula, Represents the k-th data prediction value at the prediction time; Represents the prediction weight of the i-th data in the conductivity data; Represents the conductivity value of the i-th data in the conductivity data; Indicates the number of conductivity data used for prediction; represents the initial weight; Indicates the degree of noise performance of the i-th conductivity data; Represents the time interval between the i-th data in the conductivity data and the predicted time; The number of conductivity data selected for prediction in this embodiment is is 80, and the initial weight is , this is used as an example for description, and other values ​​may be set in other implementation modes, and this embodiment does not limit this.

[0044] When the conductivity value at the prediction time is collected, the residual data between the data prediction value and the conductivity value at each prediction time is obtained, and all the residual data are subjected to Z-score statistics, and then the Z-score of each residual data is obtained by the Z-score statistical algorithm, and the residual data whose absolute value of the Z-score is greater than the preset abnormal threshold is recorded as abnormal water quality conductivity data. When the number of abnormal water quality conductivity data exceeds the preset abnormal number, it indicates that the water quality of the current petrochemical drainage pool is abnormal, and water quality cleaning measures are taken. In this embodiment, the preset abnormal threshold is 3, and the preset abnormal number is 8. This example is used for description. Other values ​​can be set in other implementations, and this embodiment does not limit it. The Z-score algorithm is an existing well-known technology and will not be described in detail in this embodiment.

[0045] It should be noted that the The model only shows negative correlation and the output of the constraint model is in In the range, As the input of this model, it can be replaced by other models with the same purpose in specific implementation. The model is used as an example for description without any specific limitation.

[0046] So far, the present invention is completed.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time monitoring method for water quality in a petrochemical discharge pool, characterized in that: The method comprises the following steps: Collect water quality conductivity data and pH value data, each collection moment corresponds to one conductivity data and one pH value data; obtain the minimum positive operation cycle of the discharge pool wastewater treatment system; According to the difference between each conductivity data and the surrounding conductivity data, the local abnormal value of each conductivity data is obtained; the local abnormal value of each pH value data is obtained; according to the local abnormal value ratio of each conductivity data and the pH value data at the corresponding collection time, a local abnormal ratio curve is constructed, and the local abnormal ratio curve is segmented to obtain a number of segmented data; according to the local abnormal ratio difference and data correlation between the conductivity data of each segmented data and the pH value data at the corresponding collection time, the correlation difference value of all conductivity data is obtained; according to the difference in the correlation difference value of the minimum positive operation cycle of each conductivity data and the correlation difference value of the conductivity data at the same position in other cycles, the noise performance degree of each conductivity data is obtained; The time interval between each conductivity data and the prediction moment is taken as a weight, and the prediction weight of each conductivity data is obtained in combination with the noise performance degree of each conductivity data; the predicted value of the conductivity data at each prediction moment is obtained through the prediction weight of each conductivity data; and the water quality of the petrochemical discharge pool is monitored in real time according to the predicted value of the conductivity data.

2. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 1, characterized in that: The local abnormal value of each conductivity data is obtained according to the difference between each conductivity data and the surrounding conductivity data, and the specific formula included is as follows: In the formula, Represents the local outlier of the i-th data in the conductivity data; Represents the conductivity value of the i-th data in the conductivity data; Represents the mean of the conductivity values ​​of all conductivity data; Represents the number of neighboring data of the i-th data in the conductivity data; Represents the conductivity value of the jth neighboring data of the i-th data in the conductivity data; Represents the standard deviation between the i-th data and the adjacent data in the conductivity data; represents the linear normalization function, Represents the absolute value function.

3. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 2, characterized in that: The method for obtaining the neighboring data includes the following specific steps: A neighborhood is constructed with the ith data in the conductivity data as the center, and the conductivity data points in the neighborhood are recorded as the neighboring data of the ith data.

4. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 1, characterized in that: The local abnormality ratio curve is constructed according to the local abnormality ratio of each conductivity data and the pH value data at the corresponding collection time, and the local abnormality ratio curve is segmented to obtain a plurality of segmented data, including the following specific steps: The ratio of the local abnormal value of each conductivity data to the local abnormal value of the pH value data at the corresponding acquisition time is recorded as the local abnormal ratio, and a curve space is constructed using all the local abnormal ratios. In the curve space, the conductivity data is used as the horizontal axis, and the value of the local abnormal ratio is used as the vertical axis. All the local abnormal ratios are projected into the curve space to obtain a local abnormal ratio curve; The local abnormal ratio curve is segmented according to the average of the acquisition time to obtain a number of segmented data.

5. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 1, characterized in that: According to the local abnormal ratio difference and data correlation between the conductivity data of each segmented data and the pH value data at the corresponding acquisition time, the correlation difference value of all conductivity data is obtained, and the specific formula included is as follows: In the formula, Represents the correlation difference value of the i-th data in the conductivity data; represents the i-th local anomaly ratio in the local anomaly ratio curve; Represents the mean of all local anomaly ratios in the local anomaly ratio curve; The number of segments representing the local anomaly ratio curve; Indicates the segmented data where the i-th local abnormal ratio value in the local abnormal ratio curve is located; Indicates the xth segment data in the local abnormal ratio curve, except for the segment data where the ith local abnormal ratio is located; is an exponential function with a natural constant as base; represents the function for calculating the Pearson correlation coefficient, Represents the absolute value function.

6. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 1, characterized in that: The noise performance degree of each conductivity data is obtained according to the difference between the correlation difference value of the minimum positive operation cycle of each conductivity data and the correlation difference value of the conductivity data at the same position in other cycles, and the specific formula included is as follows: In the formula, Indicates the degree of noise performance of the i-th data in the conductivity data; is the first parameter, is the second parameter; Represents the normalization function.

7. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 6, characterized in that: The specific steps for obtaining the first parameter and the second parameter are as follows: First parameter The calculation method is: Second parameter The calculation method is: In the formula, Represents the correlation difference value of the i-th data in the conductivity data; Indicates the number of all minimum operating cycles; It represents the correlation difference value of the conductivity data at the same collection time in the minimum operation cycle of the ith data in the yth cycle except the minimum operation cycle of the ith data in the conductivity data; Indicates the maximum value of the correlation difference value in the minimum operation cycle of the i-th data in the conductivity data; It represents the maximum value of the correlation difference value in the yth period of the conductivity data except the minimum operating period of the ith data. Represents the absolute value function.

8. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 1, characterized in that: The time interval between each conductivity data and the prediction time is used as a weight, and the prediction weight of each conductivity data is obtained in combination with the noise performance degree of each conductivity data. The specific formula included is as follows: In the formula, Represents the prediction weight of the i-th data in the conductivity data; represents the initial weight; Indicates the degree of noise performance of the i-th conductivity data; Represents the time interval between the i-th data in the conductivity data and the predicted time; Represents the normalization function.

9. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 1, characterized in that: The method of obtaining the predicted value of the conductivity data at each prediction moment by using the prediction weight of each conductivity data comprises the following specific steps: Input each conductivity data and the prediction weight of the conductivity data into the AR model to obtain the kth data prediction value at the prediction moment; In the formula, Represents the k-th data prediction value at the prediction time; Represents the prediction weight of the i-th data in the conductivity data; Represents the conductivity value of the i-th data in the conductivity data; Indicates the number of conductivity data used for prediction.

10. A method for real-time monitoring of water quality in a discharge pool for petrochemical industry according to claim 1, characterized in that: The real-time monitoring of the water quality of the petrochemical discharge pool according to the predicted value of the conductivity data includes the following specific steps: Obtain the residual data between the data prediction value and the conductivity value at each prediction moment, perform Z-score statistics on all residual data, and then use the Z-score statistical algorithm to obtain the Z score of each residual data. The residual data whose absolute value of the Z score is greater than the preset abnormal threshold is recorded as abnormal water quality conductivity data. When the number of abnormal water quality conductivity data exceeds the preset abnormal number, take water quality cleaning measures.

Images