A computer-aided wastewater treatment method and equipment

Abstract

This invention relates to the field of wastewater treatment technology, specifically to a computer-aided wastewater treatment method and equipment. The method includes: obtaining the stage data reliability of each sensor based on the data correlation between similar and different types of sensors in the target wastewater treatment stage during the current wastewater treatment process; obtaining the continuity data reliability of various types of sensors based on the data error of similar sensors in the target wastewater treatment stage and its adjacent wastewater treatment stages, combined with the difference from the preset standard data error; and accurately determining the degree of contamination of each sensor by pollutants in the wastewater by combining the overall level of wastewater pollution in the target wastewater treatment stage and the sensor maintenance time interval. This guides the implementation of relevant solutions for each sensor, enabling each sensor to accurately reflect changes in water quality in the wastewater treatment tank, thereby improving wastewater treatment accuracy and ensuring wastewater treatment effectiveness.

Description

Technical Field

[0001] This invention relates to the field of wastewater treatment technology, and specifically to a computer-aided wastewater treatment method and equipment. Background Technology

[0002] With the continuous development of computer technology, wastewater treatment has seen significant improvements in automation control, data detection and analysis, and remote monitoring and management. Existing methods involve deploying various sensors on the wastewater treatment line to monitor wastewater flow, water level, water quality parameters, and other data in real time, and automatically adjusting the process according to preset logic, thereby ensuring the stability and efficiency of the wastewater treatment process.

[0003] However, computer-aided wastewater treatment methods rely heavily on the accuracy of sensor data acquisition. Since wastewater has a wide range of sources and contains complex pollutants such as oily pollutants, suspended solids, and biofilms, sensor probes in wastewater are easily covered and contaminated by pollutants. This leads to the collected data deviating from the true value, and the collected data cannot reflect the real water quality changes in the wastewater treatment tank, affecting the accuracy of wastewater treatment and resulting in poor wastewater treatment effect. Summary of the Invention

[0004] To address the technical problem that the accuracy of wastewater treatment is affected when sensors are covered or contaminated by pollutants, the present invention aims to provide a computer-aided wastewater treatment method and equipment, the specific technical solution of which is as follows:

[0005] In a first aspect of the present invention, a computer-aided wastewater treatment method is provided, comprising:

[0006] Based on the data correlation between sensors of the same type and between sensors of different types in the current wastewater treatment process, the reliability of stage data of each sensor in each type is obtained.

[0007] Based on the data errors of the same type of sensors in the target wastewater treatment stage and its adjacent wastewater treatment stages, and combined with the differences from the preset standard data errors, the reliability of the continuous data of various types of sensors is obtained.

[0008] By integrating the reliability of the stage data and the reliability of the continuous data, the comprehensive data reliability of each sensor in various types is obtained. Combined with the overall level of sewage pollution in the target sewage treatment stage and the sensor maintenance time interval, the degree of pollution of each sensor is obtained.

[0009] In an exemplary embodiment, the process of obtaining the reliability of the stage data includes:

[0010] Based on the data correlation between each sensor in the target type and all other sensors in the target type, a first state consistency index is obtained for each sensor in the target type; the target type can be any type.

[0011] Obtain the data correlation between each sensor in the target type and other types of sensors to obtain the second state consistency index for each sensor in the target type for all other types of sensors;

[0012] By integrating the first state consistency index and the second state consistency index, the stage data reliability of each sensor in the target type is obtained.

[0013] In an exemplary embodiment, the process of obtaining the first state consistency index includes:

[0014] Based on the positional correlation and data change correlation coefficient between each sensor in the target type and other sensors in the target type, a first state consistency index is obtained for each sensor in the target type; the positional correlation is obtained from the distance between two sensors, and the positional correlation is inversely correlated with the distance.

[0015] In an exemplary embodiment, the process of obtaining the second state consistency index includes:

[0016] Acquire the correlation between target type and type data changes from other types of sensors;

[0017] Obtain the correlation coefficient of data change for each sensor in the target type with each sensor in other types, and calculate the average value to obtain the mean value of the correlation coefficient of data change for each sensor in the target type with other types of sensors.

[0018] By integrating the data change correlation performance and the mean of the data change correlation coefficient, a second state consistency index is obtained for each sensor in the target type.

[0019] In an exemplary embodiment, the process of obtaining the preset standard data error includes:

[0020] Acquire historical data errors from the same type of sensors used in the target wastewater treatment stage and its adjacent wastewater treatment stages during several historical wastewater treatment processes;

[0021] Obtain the sensor historical maintenance time intervals for the target wastewater treatment stage and its adjacent wastewater treatment stages for each historical wastewater treatment process;

[0022] The preset standard data error is obtained from the historical data error performance of each historical sewage treatment process; the historical data error performance is obtained by fusing the historical data error and the historical maintenance time interval of the sensor; the historical data error performance is positively correlated with the historical data error and negatively correlated with the historical maintenance time interval of the sensor.

[0023] In one exemplary embodiment, the process of obtaining the continued data credibility includes:

[0024] The historical consistency of various types of sensors in the target wastewater treatment stage is obtained. The historical consistency is based on the degree of difference in data error, which is the difference between the data error of the same type of sensor in the target wastewater treatment stage and its adjacent wastewater treatment stages and the preset standard data error.

[0025] Based on the historical consistency, the reliability of the continuous data from various types of sensors in the target wastewater treatment stage is obtained.

[0026] In one exemplary embodiment, obtaining the reliability of continuous data from various types of sensors at the target wastewater treatment stage based on the historical consistency includes:

[0027] Based on the historical consistency and the wastewater transport time between the target wastewater treatment stage and its adjacent wastewater treatment stages, the reliability of the continuous data of various types of sensors in the target wastewater treatment stage is obtained; the reliability of the continuous data is positively correlated with historical consistency and negatively correlated with wastewater transport time.

[0028] In an exemplary embodiment, the process of obtaining the overall level of wastewater pollution includes:

[0029] Obtain the sequence of wastewater pollution levels corresponding to the most recent sensor maintenance period in the target wastewater treatment stage;

[0030] Calculate the average level of wastewater pollution in the wastewater pollution degree sequence as the overall level of wastewater pollution.

[0031] In one exemplary embodiment, the computer-aided wastewater treatment method further includes:

[0032] Compare the contamination level of each sensor with the preset contamination level threshold;

[0033] The sensors corresponding to contamination levels greater than the preset contamination level threshold are marked to indicate that the corresponding sensors need maintenance.

[0034] In a second aspect of the present invention, a computer-aided wastewater treatment device is provided, comprising: a memory and a processor; the memory is connected to the processor; the memory is used to store program instructions; the processor is used to implement the above-described computer-aided wastewater treatment method when the program instructions are executed.

[0035] This invention offers the following advantages: First, it obtains the reliability of stage data from various sensors across different types for each target wastewater treatment stage, compensating for the deficiencies of single-sensor data and effectively determining whether sensors are contaminated. This avoids data deviations caused by sensor malfunctions or contamination, improving the accuracy of monitoring various water quality parameters during wastewater treatment. Second, based on the data correlation continuity between the target wastewater treatment stage and its adjacent stages, it obtains the reliability of continuous data from various types of sensors. By fusing these two data reliability metrics and cross-validating the data reliability of each sensor through data from multiple sensors of the same and different types, and finally combining the overall level of wastewater pollution in the target wastewater treatment stage with the sensor maintenance intervals, it accurately determines the degree of contamination of each sensor by pollutants in the wastewater. This guides the implementation of relevant solutions for the sensors, enabling them to accurately collect data from the wastewater treatment tank, thereby improving wastewater treatment accuracy and ensuring treatment effectiveness. Attached Figure Description

[0036] Figure 1 This is a flowchart of a computer-aided wastewater treatment method provided in one embodiment of the present invention;

[0037] Figure 2 This is a flowchart illustrating the process of obtaining the reliability of stage data according to an embodiment of the present invention;

[0038] Figure 3 This is a flowchart of the process for obtaining the second state consistency index provided in one embodiment of the present invention;

[0039] Figure 4 This is a flowchart illustrating the acquisition of preset standard data error according to an embodiment of the present invention;

[0040] Figure 5 This is a flowchart illustrating the process of obtaining the reliability of continuous data according to an embodiment of the present invention. Detailed Implementation

[0041] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the present invention are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0042] Unless otherwise defined, 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 pertains. All data and information collected in this application have been obtained with full consent.

[0043] When applying computer-aided wastewater treatment, this invention requires the use of various types of sensors to monitor various data in the wastewater treatment tank, thereby determining the degree of water pollution and the progress of wastewater treatment in real time, and thus monitoring and controlling the wastewater treatment process to achieve wastewater treatment.

[0044] It should be understood that wastewater treatment includes several stages, such as primary treatment (physical treatment), secondary treatment (biological treatment), and tertiary treatment (advanced treatment). Different treatment stages correspond to different treatment tanks. After treatment at a particular stage, the wastewater needs to be transferred from the current treatment tank to the next treatment stage via a wastewater transmission pipeline. Depending on the treatment objective of each stage, the functions of the sensors deployed may not be entirely the same. Sensors can be classified according to their working principles, such as optical sensors, electrochemical sensors, biological sensors, and ultrasonic sensors. During wastewater treatment, various types of sensors are used to comprehensively monitor the wastewater's condition, including turbidity sensors, pH sensors, flow sensors, and dissolved oxygen sensors. After the sensors collect data, the computer system preprocesses the data and stores it in a designated area of ​​the computer system.

[0045] This embodiment monitors the contamination status of sensors during the current wastewater treatment process. Specifically, it monitors the contamination status of sensors corresponding to the target wastewater treatment stage. The target wastewater treatment stage can be randomly selected from several stages or specifically chosen. The type and number of sensors installed in the wastewater treatment tank of the target stage are determined by the treatment purpose of that stage, and the number of each type of sensor is determined based on the area of ​​the wastewater treatment tank. Sensors of each type are arranged at intervals and evenly distributed throughout the wastewater treatment tank. For example, in the physical treatment stage, turbidity sensors and pH sensors are typically installed, and the number of each type of sensor is determined while ensuring even distribution throughout the wastewater treatment tank. It should be understood that all types of sensors collect data at the same sampling frequency, thereby obtaining the data sequence corresponding to each sensor of each type in the target wastewater treatment stage.

[0046] like Figure 1 As shown, the computer-aided wastewater treatment method provided in this embodiment includes the following steps:

[0047] Step S1: Based on the data correlation between sensors of the same type in the current wastewater treatment process and the data correlation between sensors of different types, obtain the stage data reliability of each sensor in each type.

[0048] Step S2: Based on the data errors of the same type of sensors in the target wastewater treatment stage and its adjacent wastewater treatment stages, and combined with the differences from the preset standard data errors, the reliability of the continuous data of various types of sensors is obtained.

[0049] Step S3: Integrate the reliability of the stage data and the reliability of the continuation data to obtain the comprehensive data reliability of each sensor in various types. Combine the overall level of sewage pollution in the target sewage treatment stage and the sensor maintenance time interval to obtain the degree of pollution of each sensor.

[0050] The specific implementation process of each step is explained below with reference to the accompanying drawings.

[0051] Step S1: Based on the data correlation between sensors of the same type in the current wastewater treatment process and the data correlation between sensors of different types, obtain the stage data reliability of each sensor in each type.

[0052] In the current wastewater treatment process, various types of sensors in the wastewater treatment tank corresponding to the target wastewater treatment stage are identified. This allows for the determination of data correlation between sensors of the same type and between sensors of different types. Based on these two data correlations, cross-validation is performed on sensors of the same type and different types to obtain the stage data reliability of each sensor in each type.

[0053] In one exemplary embodiment, such as Figure 2 As shown below, a specific process for obtaining the reliability of stage data is given:

[0054] Step S1-1: Based on the data correlation between each sensor in the target type and other sensors in the target type, obtain the first state consistency index of each sensor in the target type.

[0055] For ease of explanation, the target type is set to any type, that is, the sensor of the target type is any type of sensor.

[0056] Since the target type of sensor includes multiple sensors, any one of them is designated as the target sensor. The data correlation between the target sensor and the other sensors of the target type is obtained to obtain the first state consistency index of the target sensor. In an exemplary embodiment, the data change correlation coefficient between the target sensor and the other sensors of the target type is obtained. Specifically, the data change correlation coefficient is the Pearson correlation coefficient, that is, the Pearson correlation coefficient of the data sequence of the target sensor and the other sensors of the target type is obtained, and then the first state consistency index of the target sensor is obtained based on the Pearson correlation coefficient of the data sequence of the target sensor and the other sensors of the target type. To facilitate subsequent processing, the Pearson correlation coefficient is normalized. Since the numerical range of the Pearson correlation coefficient is [-1, 1], the normalization method of the Pearson correlation coefficient in this embodiment is: (Pearson correlation coefficient + 1) / 2, and the resulting numerical range is [0, 1].

[0057] Because sensors of the same type may be significantly apart within a wastewater treatment tank, and the wastewater may be unevenly distributed, the data collected by the sensors may have inherent biases. Therefore, it is crucial to obtain the distances between the target sensor and other sensors of the same type within the wastewater treatment tank. This distance can be obtained by constructing a two-dimensional coordinate system on the plane of the wastewater treatment tank's cross-section, mapping each sensor of the target type onto this coordinate system, and thus obtaining the Euclidean distance between any two sensors. The positional correlation between the two sensors is then determined based on this distance; the greater the distance, the weaker the positional correlation, indicating an inverse correlation between positional correlation and distance. As a concrete example, the reciprocal of the distance between two sensors can be used as their positional correlation, meaning the closer the distance, the more reliable the positional correlation. Next, the sum of the positional correlations between the target sensor and other sensors of the same type is calculated. Finally, the ratio of the positional correlation between the target sensor and other sensors of the same type to this sum is calculated as the positional weight of the target sensor relative to the other sensors of the same type. Therefore, the closer the distance, the greater the positional weight, and the sum of the positional weights of the target sensor and other sensors of the same type is 1.

[0058] Based on the position weights of the target sensor and other sensors of the same target type, the normalized Pearson correlation coefficients of the data sequences of the target sensor and other sensors of the same target type are weighted and summed. The result is the first state consistency index of the target sensor, and the calculation formula is as follows:

[0059] ,

[0060] in, This represents the first state consistency index of the i-th sensor in the u-th type of sensor. Let represent the normalized Pearson correlation coefficient between the i-th sensor of type u and the j-th sensor of type u. This represents the number of sensors of type u other than the i-th sensor. This represents the position weight between the i-th sensor and the j-th sensor in the u-th type of sensor.

[0061] Using the above method, the first state consistency index of each sensor in the target type is obtained, and then the first state consistency index of each sensor in each type is obtained. The more consistent the state of the sensors, the more similar their degree of contamination. Furthermore, since the coverage state and form of sensors may differ when they are contaminated, the higher the first state consistency index, the lower the degree of contamination.

[0062] Step S1-2: Obtain the data correlation between each sensor in the target type and other types of sensors to obtain the second state consistency index for each sensor in the target type for all other types of sensors.

[0063] Because different types of sensors detect different objects (data), the interrelationships between different data dimensions may not be directly determined. For example, turbidity data in water does not have a clear direct relationship with pH. Therefore, it is necessary to determine the impact of data changes based on data variations during wastewater treatment. Thus, based on the data correlation between each sensor in the target type and other types of sensors, a second state consistency index is obtained for each sensor in the target type, relative to all other types of sensors.

[0064] In one exemplary embodiment, such as Figure 3 As shown, the following is a specific process for obtaining the second-state consistency index:

[0065] Step S1-2-1: Obtain the correlation between target type and type data changes of other types of sensors.

[0066] Since various types of sensors include multiple sensors, the data sequence for each sensor in each type is obtained. This data sequence is derived by arranging sensor data from multiple time points in chronological order. For multiple sensors of the same type, the average value of the sensor data from multiple sensors at the same time point is obtained as the sensor average data at that time point. This yields the sensor average data at each time point. Arranging these average data points in chronological order, the resulting data sequence is defined as the type data sequence for that sensor type. This process results in the type data sequences for various sensor types.

[0067] The Pearson correlation coefficients of the target type sensor type data sequence with the type data sequences of other types of sensors are obtained, and the Pearson correlation coefficients are normalized. The results show the correlation between the target type and the type data changes of other types of sensors.

[0068] Step S1-2-2: Obtain the correlation coefficient of data change for each sensor in the target type with each sensor in other types, and calculate the average value to obtain the mean value of the correlation coefficient of data change for each sensor in the target type with other types of sensors.

[0069] The reference type is set to any type other than the target type. The correlation coefficient of data change between the target sensor in the target type and each sensor in the reference type is obtained; specifically, the Pearson correlation coefficient. Since the reference type contains multiple sensors, the average Pearson correlation coefficient between the target sensor in the target type and each sensor in the reference type is calculated, and then normalized. The result is the mean correlation coefficient of data change between the target sensor and the sensors in the reference type. Thus, the mean correlation coefficient of data change between the target sensor in the target type and all other sensor types is obtained.

[0070] Step S1-2-3: Combine the correlation performance of data changes by type and the mean of correlation coefficients of data changes to obtain the second state consistency index of each sensor in the target type.

[0071] Based on the correlation performance of target type data changes with other types of sensors, and the average correlation coefficient of target sensor data changes with other types of sensors within the target type, a second state consistency index for the target sensor within the target type is obtained. A stronger correlation performance indicates a more similar trend in the data changes of the target type compared to other types of sensors, resulting in a stronger second state consistency index for the target sensor within the target type. Similarly, a higher average correlation coefficient indicates a more similar data changes in the target sensor within the target type compared to other types of sensors, also resulting in a stronger second state consistency index for the target sensor within the target type. Therefore, the second state consistency index is positively correlated with both the correlation performance and the average correlation coefficient. In an exemplary embodiment, a specific quantification method for the second state consistency index is given below:

[0072] ,

[0073] in, This represents the second state consistency index of the i-th sensor in the u-th type of sensor. This indicates the correlation between the type data changes of sensor type u and sensor type v. Let V represent the average correlation coefficient between the i-th sensor and the v-th sensor in the u-th type of sensor, and let V represent the number of other types of sensors besides the u-th type of sensor.

[0074] Step S1-3: Fuse the first state consistency index and the second state consistency index to obtain the stage data credibility of each sensor in the target type.

[0075] According to step S1-1, the first state consistency index of the target sensor in the target type is obtained. According to step S1-2, the second state consistency index of the target sensor in the target type is obtained. The first and second state consistency indices of the target sensor in the target type are fused. In an exemplary embodiment, the average value of the first and second state consistency indices of the target sensor in the target type is calculated. This average value is the stage data reliability of the target sensor in the target type. The stage data reliability represents the reliability of the sensor data of the target sensor in the target type. The higher the reliability, the higher the detection accuracy of the target sensor and the lower the degree of contamination of the target sensor. Thus, the stage data reliability of each sensor in various types of sensors is obtained.

[0076] Step S2: Based on the data errors of the same type of sensors in the target wastewater treatment stage and its adjacent wastewater treatment stages, and combined with the differences from the preset standard data errors, the reliability of the continuous data of various types of sensors is obtained.

[0077] Since the various wastewater treatment stages in the wastewater treatment process have a temporal sequence, the wastewater treatment stages adjacent to the target wastewater treatment stage are determined. For the target wastewater treatment stage, the sensor data of its adjacent wastewater treatment stages should exhibit a certain degree of consistency with the sensor data of the target wastewater treatment stage. In an exemplary embodiment, the adjacent wastewater treatment stage is the next wastewater treatment stage after the target wastewater treatment stage; therefore, the sensor data of the wastewater at the end of the target wastewater treatment stage should be consistent with the sensor data of the wastewater at the beginning of the adjacent wastewater treatment stage.

[0078] Because different stages of wastewater treatment take place in different treatment tanks, and wastewater needs to be transferred from one treatment tank to the next, typically via equalization tanks or transmission pipelines, the wastewater may undergo natural changes (such as sedimentation or anaerobic fermentation) or be affected by external factors (such as rainwater dilution or gas release) during the transfer between treatment stages. Therefore, by obtaining the data errors from similar sensors at the target wastewater treatment stage and its adjacent stages, and combining these errors with preset standard data errors, the reliability of the continuity data from various types of sensors can be determined.

[0079] The sensor data for each sensor in the target type at the end of the target wastewater treatment stage is obtained, and then the average value is calculated to obtain the sensor data for the target type at the end of the target wastewater treatment stage. Similarly, the sensor data for each sensor in the target type at the beginning of the adjacent wastewater treatment stage is obtained, and then the average value is calculated to obtain the sensor data for the target type at the beginning of the adjacent wastewater treatment stage. The absolute value of the difference between the sensor data for the target type at the end of the target wastewater treatment stage and the sensor data for the target type at the beginning of the adjacent wastewater treatment stage is calculated as the data error of the sensor data for the target type between the target wastewater treatment stage and the adjacent wastewater treatment stage. It should be understood that the sensors for the target type exist simultaneously in the wastewater treatment tanks of both the target wastewater treatment stage and the adjacent wastewater treatment stage.

[0080] A preset standard data error is determined for the target type of sensor. Ideally, the data error between two adjacent wastewater treatment stages is 0, indicating absolute consistency of the sensor data for the target type in two adjacent wastewater treatment stages. Therefore, the preset standard data error for the target type of sensor can be directly set to 0. As another implementation, the preset standard data error for the target type of sensor is obtained based on the overall situation reflected by the historical data errors of the same type of sensor in the target wastewater treatment stage and its adjacent wastewater treatment stages during several historical wastewater treatment processes. Accordingly, as... Figure 4 As shown below, a specific process for obtaining the preset standard data error is given:

[0081] Step S2-1: Obtain historical data errors from the same type of sensors used in the target wastewater treatment stage and its adjacent wastewater treatment stages during several historical wastewater treatment processes.

[0082] In identifying several historical wastewater treatment processes that have been completed in the same scenario, it should be understood that the number of times a historical wastewater treatment process is selected is set according to actual needs. In order to ensure the reliability of the preset standard data error, the number of times a historical wastewater treatment process is selected can be more.

[0083] For any given historical wastewater treatment process, the target wastewater treatment stage and adjacent wastewater treatment stages in that process are determined. Then, the sensor data error between the target wastewater treatment stage and the adjacent wastewater treatment stages in that historical wastewater treatment process is obtained and defined as the historical data error.

[0084] Step S2-2: Obtain the sensor historical maintenance time interval between the target wastewater treatment stage and its adjacent wastewater treatment stages for each historical wastewater treatment process.

[0085] It should be understood that each sensor undergoes maintenance at regular intervals during each wastewater treatment stage, such as periodically wiping the sensor probes immersed in wastewater. The maintenance interval for each sensor in each wastewater treatment stage of each historical wastewater treatment process is determined, where the maintenance interval is the time interval between two adjacent maintenance sessions. Accordingly, the sensor maintenance interval for the target wastewater treatment stage of each historical wastewater treatment process, as well as the sensor maintenance interval for adjacent wastewater treatment stages, are defined as the historical sensor maintenance interval.

[0086] For any given historical wastewater treatment process, the longer the historical maintenance interval of the corresponding sensor, the lower the importance of the historical data error for that process, and the lower its weight needs to be assigned to reduce its impact. Therefore, the impact weight of historical data error is obtained based on the historical maintenance interval of the sensor, and the impact weight is inversely proportional to the historical maintenance interval of the sensor.

[0087] Therefore, based on the historical data error of each historical wastewater treatment process and the historical maintenance interval of the sensors, the historical data error performance of each historical wastewater treatment process is obtained. The historical data error performance is positively correlated with the historical data error and inversely correlated with the historical maintenance interval of the sensors. In an exemplary embodiment, the quantification method of the historical data error performance is given below:

[0088] ,

[0089] in, Indicates the first The first in the historical wastewater treatment process Historical data error performance of the u-th type of sensor in each wastewater treatment stage, i.e. The first in the historical wastewater treatment process The first stage of wastewater treatment and the second Historical data error performance of the uth type of sensor in each wastewater treatment stage; Indicates the first The first in the historical wastewater treatment process The historical data error of the u-th type of sensor in each wastewater treatment stage, i.e., the... The first in the historical wastewater treatment process The first stage of wastewater treatment and the second Historical data error of the uth type of sensor in each wastewater treatment stage; Indicates the first The first in the historical wastewater treatment process Historical maintenance intervals of sensors at each stage of wastewater treatment. Indicates the first The first in the historical wastewater treatment process The historical maintenance intervals of sensors in each wastewater treatment stage. It should be understood that in this embodiment, the historical maintenance intervals of all types of sensors are the same for a certain wastewater treatment stage in a certain historical wastewater treatment process; if the historical maintenance intervals of different types of sensors are different, then the quantification formula of the above-mentioned historical data error performance needs to determine the historical maintenance intervals of different types of sensors according to the different types of sensors.

[0090] Step S2-3: Obtain the preset standard data error from the historical data error performance of each historical sewage treatment process.

[0091] The average historical data error performance of each historical wastewater treatment process is calculated, and the result is the preset standard data error of the same type of sensor for the corresponding wastewater treatment stage. (The text then abruptly shifts to a different topic:) Taking the historical data error performance of the u-th type of sensor in the th stage of the th historical wastewater treatment process as an example, the th... The formula for calculating the preset standard data error of the u-th type of sensor in each wastewater treatment stage is as follows:

[0092] ,

[0093] in, For the first The preset standard data error of the u-th type of sensor in each wastewater treatment stage, i.e., the... The first stage of wastewater treatment and the second The preset standard data error of the u-th type of sensor in each wastewater treatment stage. m is the number of historical wastewater treatment processes.

[0094] Then, based on the data errors of similar sensors in the target wastewater treatment stage and its adjacent wastewater treatment stages, and combined with the differences from preset standard data errors, the continuity data reliability of various types of sensors is obtained. In an exemplary embodiment, such as... Figure 5 As shown, the following is a specific process for obtaining the credibility of continued data:

[0095] Step S2-4: Obtain the historical consistency of various types of sensors in the target wastewater treatment stage.

[0096] The difference between the data error of the target wastewater treatment stage and the data error of the adjacent wastewater treatment stages using similar sensors and the corresponding preset standard data error is obtained. Specifically, the difference is the absolute value of the difference, and the result is the degree of data error difference. For example, calculating the... The first stage of wastewater treatment and the second Data error of the uth type of sensor in each wastewater treatment stage , and the The first stage of wastewater treatment and the second The difference in preset standard data error of the u-th type of sensor in each wastewater treatment stage The absolute value of the difference is the first absolute value. The first stage of wastewater treatment and the second The degree of difference in data error between the u-th type of sensor in each stage of wastewater treatment.

[0097] According to the The first stage of wastewater treatment and the second The degree of data error difference of the u-th type of sensor in each stage of wastewater treatment is obtained. Historical consistency of the u-th type of sensor in each wastewater treatment stage. Higher historical consistency indicates better consistency in the current wastewater treatment process. The more similar the trend of the u-th type of sensor in each wastewater treatment stage is to historical data during wastewater transmission, the lower the likelihood of sensor contamination. Therefore, the u-th type of sensor in each wastewater treatment stage... The first stage of wastewater treatment and the second The degree of data error difference of the u-th type of sensor in each stage of wastewater treatment, compared with the... There is an inverse correlation between the historical consistency of the u-th type of sensor in each wastewater treatment stage. The following gives the... A specific way to quantify the historical consistency of the u-th type of sensor in each stage of wastewater treatment:

[0098] ,

[0099] in, Indicates the first Historical consistency of the u-th type of sensor in each wastewater treatment stage. Indicates the first The first stage of wastewater treatment and the second The data error of the u-th type of sensor in each wastewater treatment stage is denoted by exp, which represents an exponential function with the natural constant e as the base.

[0100] Step S2-5: Based on historical consistency, obtain the reliability of continuous data from various types of sensors in the target wastewater treatment stage.

[0101] Based on the The historical consistency of the u-th type of sensor in each wastewater treatment stage yields the... The reliability of continuous data from the u-th type of sensor in each wastewater treatment stage. Higher historical consistency indicates higher reliability of the sensor data, i.e., higher reliability of continuous data.

[0102] Because the longer the wastewater takes to travel between two adjacent wastewater treatment stages, the greater the likelihood of rainwater dilution and sedimentation, leading to lower reliability of the continuity data. Therefore, in a preferred embodiment, the wastewater travel time between the target wastewater treatment stage and its adjacent stages is also considered when obtaining the reliability of the continuity data. Based on the historical consistency of various types of sensors in the target wastewater treatment stage and the wastewater travel time between the target wastewater treatment stage and its adjacent stages, the reliability of the continuity data for various types of sensors in the target wastewater treatment stage is obtained. The reliability of the continuity data is inversely correlated with the wastewater travel time. In an exemplary embodiment, a specific quantification method for the reliability of the continuity data is given below:

[0103] ,

[0104] in, Indicates the first The reliability of continuous data from the u-th type of sensor in each stage of wastewater treatment. Indicates the first The first stage of wastewater treatment and the second The time consumed by wastewater transfer between each stage of wastewater treatment.

[0105] This allows us to obtain the reliability of continuous data from various types of sensors at the target wastewater treatment stage.

[0106] Step S3: Integrate the reliability of the stage data and the reliability of the continuation data to obtain the comprehensive data reliability of each sensor in various types. Combine the overall level of sewage pollution in the target sewage treatment stage and the sensor maintenance time interval to obtain the degree of pollution of each sensor.

[0107] By integrating the stage data reliability of various types of sensors in the target wastewater treatment stage and the corresponding continuation data reliability, a comprehensive data reliability of various types of sensors in the target wastewater treatment stage is obtained. In an exemplary embodiment, the calculation of the first... The reliability of the stage data from the i-th sensor in the u-th type of wastewater treatment stage and the... The average reliability of the continuous data of the u-th type of sensor in each wastewater treatment stage, which is the average value of the data of the u-th type of sensor. The reliability of the comprehensive data from the i-th sensor in the u-th type of wastewater treatment stage is calculated using the following formula:

[0108] ,

[0109] in, Indicates the first The overall data reliability of the i-th sensor in the u-th type of each wastewater treatment stage. Indicates the first The reliability of stage data from the i-th sensor in the u-th type of wastewater treatment stage.

[0110] Whether a sensor is contaminated is also affected by the overall level of wastewater pollution in the target wastewater treatment stage and the sensor maintenance interval. That is, the higher the level of wastewater pollution in the target wastewater treatment stage, the greater the possibility of sensor contamination. At the same time, the longer the time interval between the last maintenance of the sensor, the greater the possibility of sensor contamination.

[0111] In an exemplary embodiment, the most recent sensor maintenance time period in the target wastewater treatment stage is determined. The most recent sensor maintenance time period refers to the time period between the most recent sensor maintenance time and the previous sensor maintenance time. It should be understood that the sensor maintenance time period and the sensor maintenance interval are the same concept here.

[0112] The sensor maintenance period includes multiple moments, and a sequence of wastewater pollution levels is obtained for this maintenance period. This sequence includes the wastewater pollution level at each moment. The monitoring methods for wastewater pollution levels utilize existing technologies, such as: placing an ultraviolet probe above the wastewater surface at a close distance, emitting ultraviolet light towards the wastewater, and analyzing the reflectance spectral characteristics (e.g., absorbance at 254nm) to detect turbidity / suspended solids, thus monitoring the degree of wastewater pollution; or using image processing to acquire wastewater images, and based on the difference in grayscale values ​​between pollutants and the water itself, obtaining the distribution of pollutants in the wastewater image, and thus determining the degree of wastewater pollution based on the pollutant distribution, and so on.

[0113] Calculate the average value of all sewage pollution levels in the sewage pollution level sequence. This average value represents the overall level of sewage pollution.

[0114] Based on the overall reliability of data from various types of sensors in the target wastewater treatment stage, the overall level of wastewater pollution, and the most recent sensor maintenance period in the target wastewater treatment stage, the degree of contamination of various types of sensors in the target wastewater treatment stage is obtained. The degree of contamination is inversely correlated with the overall data reliability and positively correlated with the overall level of wastewater pollution and the length of the most recent sensor maintenance period. In an exemplary embodiment, a specific method for quantifying the degree of sensor contamination is given below:

[0115] ,

[0116] in, Indicates the first The degree of contamination of the i-th sensor in the u-th type of wastewater treatment stage. Indicates the first The length of the period between the most recent sensor maintenance for each stage of wastewater treatment. Indicates the first The overall level of wastewater pollution at each stage of wastewater treatment. `norm` represents the normalization function, for example... .

[0117] Having thus obtained the degree of contamination of each sensor across various types in the target wastewater treatment stage, relevant measures can be taken for each sensor based on its degree of contamination. In an exemplary embodiment, a preset contamination threshold is used to determine whether the degree of contamination of each sensor across various types is high. The preset contamination threshold ranges from 0 to 1, and the specific value is set according to the actual judgment needs. For example, if the judgment is more stringent, the preset contamination threshold can be set to a smaller value.

[0118] Compare the contamination level of each sensor in various types with a preset contamination level threshold, obtain the contamination level that is greater than the preset contamination level threshold, and mark the sensors corresponding to the contamination level that is greater than the preset contamination level threshold. If the marked sensors have a high degree of contamination, these sensors need to be maintained immediately, such as wiping the contaminants on the sensor probe clean or replacing the sensor probe.

[0119] This embodiment also provides a computer-aided wastewater treatment device, including: a memory and a processor; the memory is connected to the processor, and the memory is used to store program instructions; the processor is used to implement the steps in the above-described embodiment of the computer-aided wastewater treatment method when the program instructions are executed.

[0120] In one exemplary embodiment, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the embodiment of the computer-aided wastewater treatment method.

[0121] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method of applying computer-aided sewage treatment, characterized by, include: Based on the data correlation between sensors of the same type and between sensors of different types in the current wastewater treatment process, the reliability of stage data of each sensor in each type is obtained. Based on the data errors of the same type of sensors in the target wastewater treatment stage and its adjacent wastewater treatment stages, and combined with the differences from the preset standard data errors, the reliability of the continuous data of various types of sensors is obtained. By integrating the reliability of the stage data and the reliability of the continuous data, the comprehensive data reliability of each sensor in various types is obtained. Combined with the overall level of sewage pollution in the target sewage treatment stage and the sensor maintenance time interval, the degree of pollution of each sensor is obtained. The process of obtaining the reliability of the stage data includes: Based on the data correlation between each sensor in the target type and all other sensors in the target type, a first state consistency index is obtained for each sensor in the target type; the target type can be any type. Obtain the data correlation between each sensor in the target type and other types of sensors to obtain the second state consistency index for each sensor in the target type for all other types of sensors; By fusing the first state consistency index and the second state consistency index, the stage data reliability of each sensor in the target type is obtained; The process of obtaining the first state consistency index includes: Based on the positional correlation and data change correlation coefficient between each sensor in the target type and other sensors in the target type, a first state consistency index is obtained for each sensor in the target type; the positional correlation is obtained from the distance between two sensors, and the positional correlation is inversely correlated with the distance; The process of obtaining the credibility of the continued data includes: The historical consistency of various types of sensors in the target wastewater treatment stage is obtained. The historical consistency is based on the degree of difference in data error, which is the difference between the data error of the same type of sensor in the target wastewater treatment stage and its adjacent wastewater treatment stages and the preset standard data error. Based on the historical consistency and the wastewater transport time between the target wastewater treatment stage and its adjacent wastewater treatment stages, the reliability of the continuous data of various types of sensors in the target wastewater treatment stage is obtained; the reliability of the continuous data is positively correlated with historical consistency and negatively correlated with wastewater transport time.

2. A method of computer-aided sewage treatment according to claim 1, characterized in that The process of obtaining the second state consistency index includes: Acquire the correlation between target type and type data changes from other types of sensors; Obtain the correlation coefficient of data change for each sensor in the target type with each sensor in other types, and calculate the average value to obtain the mean value of the correlation coefficient of data change for each sensor in the target type with other types of sensors. By integrating the data change correlation performance and the mean of the data change correlation coefficient, a second state consistency index is obtained for each sensor in the target type.

3. A method of computer-aided sewage treatment according to claim 1, characterized in that The process of obtaining the preset standard data error includes: Obtaining historical data error of the same type of sensor between the target sewage treatment stage and its adjacent sewage treatment stage in several historical sewage treatment processes; Obtaining the historical maintenance time interval of the sensor between the target sewage treatment stage and its adjacent sewage treatment stage in each historical sewage treatment process; The preset standard data error is obtained from the historical data error performance of each historical sewage treatment process; the historical data error performance is obtained by fusing the historical data error and the historical maintenance time interval of the sensor; the historical data error performance is positively correlated with the historical data error and inversely correlated with the historical maintenance time interval of the sensor.

4. A method of computer-aided sewage treatment according to claim 1, characterized in that, The obtaining process of the overall level of the sewage pollution degree comprises: Obtaining the sewage pollution degree sequence corresponding to the maintenance time period of the sensor in the target sewage treatment stage; Calculating the average value of the sewage pollution degree sequence as the overall level of the sewage pollution degree.

5. A method of computer-aided sewage treatment according to claim 1, characterized in that, The application computer-aided sewage treatment method further comprises: Comparing the contaminated degree of each sensor with the preset contaminated degree threshold value; Marking the sensor corresponding to the contaminated degree greater than the preset contaminated degree threshold value, for indicating that the corresponding sensor is maintained.

6. A computer-aided sewage treatment system, characterized by comprising: Comprise: Memory and processor; The memory is connected with the processor; The memory is used for storing program instructions; The processor is used for realizing the application computer-aided sewage treatment method in any one of claims 1-5 when the program instructions are executed.

Images