Inspection system and method for sewage treatment

Abstract

The invention relates to the technical field of sewage inspection, in particular to an inspection system and method for sewage treatment. Comprising the following steps: collecting index data in sewage in real time as original sewage data, and preprocessing the original sewage data; performing feature extraction and weighted fusion processing on the preprocessed sewage data by using a multi-dimensional adaptive cross point feature fusion algorithm to obtain comprehensive sewage data; a sewage treatment effect evaluation algorithm with multi-scale fuzzy reasoning and multi-dimensional data weighted fusion is adopted, sewage historical data, comprehensive sewage data and external environment data are combined, the sewage treatment effect is comprehensively evaluated and analyzed, an analysis result is obtained, the severity level of the sewage quality is judged, and the sewage treatment effect is evaluated. Early warning signals and intelligent adjusting instructions of corresponding levels are sent out, and operation adjusting treatment of the sewage treatment equipment is executed. The technical problems that in the inspection of sewage treatment, the response to water quality change in a dynamic environment is not accurate enough, and sewage analysis is not comprehensive enough are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage inspection, and in particular to an inspection system and method for sewage treatment. Background Art

[0002] In the current sewage treatment field, water quality monitoring technology has always been the key to ensuring that water quality meets standards. Traditional sewage treatment methods mostly rely on static monitoring data and simple analysis models, focusing on several common water quality indicators, such as chemical oxygen demand (COD), ammonia nitrogen (NH3-N), suspended solids (SS), etc. However, these traditional methods have certain limitations, especially when faced with complex and dynamically changing water quality conditions, they cannot effectively deal with the diversity and variability of water quality pollutants.

[0003] With the acceleration of urbanization and the improvement of industrialization, the types of sewage and pollutants are becoming more and more complex, and traditional water quality monitoring methods are gradually exposed to the defects of being unable to meet the needs of modern sewage treatment. These defects are reflected in the following aspects: First, traditional water quality monitoring methods mostly rely on manual sampling and static analysis, and the monitoring period is long, resulting in the inability to reflect water quality changes in real time; second, the existing monitoring methods are mostly limited to the analysis of a single pollutant, while the pollutants in sewage are often multiple and complex, which makes it impossible for a single monitoring method to fully capture the overall changes in water quality; finally, the existing monitoring technology is often unable to dynamically adjust the monitoring algorithm to cope with sudden changes in water quality conditions.

[0004] At the same time, the existing sewage treatment inspection methods have the following technical problems: in the sewage treatment inspection, the response to water quality changes in a dynamic environment is not accurate enough and the sewage analysis is not comprehensive enough. Summary of the invention

[0005] The present invention provides a sewage treatment inspection system and method to solve the technical problems of insufficient precision in response to water quality changes in a dynamic environment and insufficient comprehensiveness in sewage analysis during sewage treatment inspection.

[0006] A sewage treatment inspection system and method of the present invention specifically includes the following technical solutions: A method for testing sewage treatment comprises the following steps: S1. Collect the index data in sewage in real time as raw sewage data, pre-process the raw sewage data to obtain pre-processed sewage data; use the multi-dimensional adaptive intersection feature fusion algorithm to extract features and perform weighted fusion processing on the pre-processed sewage data to obtain comprehensive sewage data; S2. Use a sewage treatment effect evaluation algorithm that combines multi-scale fuzzy reasoning with multi-dimensional data weighted fusion, combine sewage historical data, comprehensive sewage data and external environmental data, conduct a comprehensive evaluation and analysis of the sewage treatment effect, and obtain the analysis results; S3. Based on the analysis results, determine the severity level of the sewage water quality, and issue warning signals and intelligent adjustment instructions of corresponding levels, and perform operational adjustment processing of the sewage treatment equipment based on the intelligent adjustment instructions.

[0007] Preferably, the S1 specifically includes: The multi-dimensional adaptive intersection feature fusion algorithm introduces an intersection feature selection mechanism, a multi-dimensional adaptive correction mechanism, and an intersection weight superposition to extract features and weighted fuse pretreated sewage data from different angles, and finally obtains comprehensive sewage data by combining multi-dimensional feature intersections.

[0008] Preferably, the S1 specifically includes: In the process of implementing the multi-dimensional adaptive intersection feature fusion algorithm, the intersection features are defined and extracted, and after the intersection feature extraction is completed, the adaptive correction stage is entered.

[0009] Preferably, the S1 specifically includes: In the process of implementing the multi-dimensional adaptive intersection feature fusion algorithm, an adaptive correction mechanism is introduced to obtain the adaptively corrected intersection feature. The specific implementation formula is: , in, is the first intersection features; It is intersection features; It is The initial weights of the intersection features; It is The sensitivity parameter of the intersection feature; It is the preset target water quality standard; It is the actual value of current sewage quality.

[0010] Preferably, the S1 specifically includes: In the process of implementing the multi-dimensional adaptive intersection feature fusion algorithm, the adaptively corrected intersection features are put into the feature fusion stage, and the adaptively corrected intersection features are fused by weighted fusion to generate comprehensive sewage data. The specific implementation formula is: , in, It is comprehensive sewage data; is the number of all intersection features; It is The weight coefficient of the intersection feature; is the first intersection features; It is The weighted adjustment factor for each intersection feature; It is The intersection feature and The cosine similarity between the features of the intersection points.

[0011] Preferably, the S2 specifically includes: In the process of implementing the sewage treatment effect evaluation algorithm of multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, the sewage historical data, comprehensive sewage data and external environment data are preprocessed, and the pretreated sewage historical data, comprehensive sewage data and external environment data are processed using a multi-scale fuzzy reasoning network. By defining different scales, short-term, medium-term and long-term evaluations are performed on the pretreated sewage historical data, comprehensive sewage data and external environment data.

[0012] Preferably, the S2 specifically includes: In the process of implementing the sewage treatment effect evaluation algorithm of multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, the pretreated sewage historical data, comprehensive sewage data and external environment data are used as input data. For each scale, the input data is subjected to fuzzy reasoning to obtain the weighted sum of the fuzzy reasoning output, thereby obtaining the evaluation results of the input data at different scales.

[0013] Preferably, the S2 specifically includes: In the process of implementing the sewage treatment effect evaluation algorithm of multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, based on the evaluation results of the input data at different scales, the multi-dimensional data is adaptively weighted and fused to obtain the comprehensive evaluation results after weighted fusion; the comprehensive evaluation results after weighted fusion are compared with the target emission standards, and the sewage treatment effect is comprehensively evaluated and analyzed to finally obtain the analysis results.

[0014] A sewage treatment inspection system includes the following parts: Data acquisition module, data intelligent processing module, data intelligent analysis module, intelligent early warning and decision support module, execution module; The data acquisition module collects the index data in the sewage in real time and sends the collected index data as raw sewage data to the data intelligent processing module; The data intelligent processing module pre-processes the raw sewage data to obtain pre-processed sewage data, performs feature extraction and weighted fusion processing on the pre-processed sewage data to obtain comprehensive sewage data, and sends the comprehensive sewage data to the data intelligent analysis module; The data intelligent analysis module uses a sewage treatment effect evaluation algorithm based on multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, combines sewage historical data, comprehensive sewage data and external environmental data, conducts a comprehensive evaluation and analysis of sewage treatment effects, and generates analysis results by comparing water quality parameters with standard emission requirements. The analysis results are then sent to the intelligent early warning and decision support module; The intelligent early warning and decision support module introduces a multi-level early warning mechanism. Based on the analysis results, it determines the severity level of sewage quality and issues early warning signals of corresponding levels. At the same time, it gives corresponding intelligent adjustment instructions and sends the intelligent adjustment instructions to the execution module. The execution module performs the operation adjustment processing of the sewage treatment equipment according to the intelligent adjustment instructions, and after the adjustment processing, collects the treated sewage samples for comparison with the expected indicators of the same period. When the treated sewage samples meet the expected indicators of the same period, subsequent processing is carried out. When the treated sewage samples do not meet the expected indicators of the same period, they continue to be processed by the data acquisition module, the data intelligent processing module, the data intelligent analysis module, and the intelligent early warning and decision support module to form a closed loop.

[0015] The beneficial effects of the technical solution of the present invention are: 1. By using a multi-dimensional adaptive intersection feature fusion algorithm, comprehensive sewage characteristics can be extracted from different angles, and then the feature weights can be adjusted through an adaptive correction mechanism to make the final water quality assessment more accurate; this comprehensive sewage feature extraction and fusion method can capture the complexity of water quality changes in multiple dimensions, thereby improving the accuracy and timeliness of water quality analysis.

[0016] 2. A sewage treatment effect evaluation algorithm that uses multi-scale fuzzy reasoning and multi-dimensional data weighted fusion is used. Combined with sewage historical data, comprehensive sewage data and external environmental data, fuzzy reasoning and evaluation at different scales can be used to conduct detailed evaluations of sewage treatment effects from multiple levels, such as short-term, medium-term and long-term. Through this method, sewage treatment effects can be comprehensively evaluated at different levels and dimensions, thereby improving the understanding of the sewage treatment process and decision-making support. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a structural diagram of a sewage treatment inspection system according to the present invention; Figure 2 The present invention is a flow chart of a sewage treatment inspection method. 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 technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[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 a sewage treatment inspection system and method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] Refer to the attached Figure 1 , which shows a structural diagram of a sewage treatment inspection system provided by an embodiment of the present invention, the system includes the following parts: Data acquisition module, data intelligent processing module, data intelligent analysis module, intelligent early warning and decision support module, execution module; The data acquisition module collects various physical, chemical and biological index data in sewage in real time through sensors such as pH sensor, dissolved oxygen sensor, suspended solids sensor, temperature sensor, ammonia nitrogen concentration sensor, total phosphorus sensor, heavy metal sensor and bacteria concentration sensor, including pH value, dissolved oxygen concentration, suspended solids concentration, heavy metal content, bacteria concentration, etc., and sends the collected index data as raw sewage data to the data intelligent processing module; The data intelligent processing module performs preprocessing such as cleaning, denoising, anomaly detection, and standardization on the raw sewage data to obtain preprocessed sewage data, performs feature extraction and weighted fusion processing on the preprocessed sewage data to obtain comprehensive sewage data, and sends the comprehensive sewage data to the data intelligent analysis module; The data intelligent analysis module uses a sewage treatment effect evaluation algorithm based on multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, combines sewage historical data, comprehensive sewage data and external environmental data, conducts a comprehensive evaluation and analysis of sewage treatment effects, and generates analysis results by comparing water quality parameters with standard emission requirements. The analysis results are then sent to the intelligent early warning and decision support module; The intelligent early warning and decision support module introduces a multi-level early warning mechanism. Based on the analysis results, it determines the severity level of sewage quality and issues early warning signals of corresponding levels. At the same time, it gives corresponding intelligent adjustment instructions to guide sewage treatment equipment to perform adjustment instructions and sends the intelligent adjustment instructions to the execution module; The execution module performs the operation adjustment processing of the sewage treatment equipment according to the intelligent adjustment instructions, and after the adjustment processing, collects the treated sewage samples for comparison with the expected indicators of the same period. When the treated sewage samples meet the expected indicators of the same period, subsequent processing is carried out. When the treated sewage samples do not meet the expected indicators of the same period, they continue to be processed by the data acquisition module, the data intelligent processing module, the data intelligent analysis module, and the intelligent early warning and decision support module to form a closed loop.

[0022] Refer to the attached Figure 2 , which shows a flow chart of a sewage treatment inspection method provided by an embodiment of the present invention, the method comprising the following steps: S1. Collect the index data in sewage in real time as raw sewage data, pre-process the raw sewage data to obtain pre-processed sewage data; use the multi-dimensional adaptive intersection feature fusion algorithm to extract features and perform weighted fusion processing on the pre-processed sewage data to obtain comprehensive sewage data; Through sensors such as pH sensors, dissolved oxygen sensors, suspended matter sensors, temperature sensors, ammonia nitrogen concentration sensors, total phosphorus sensors, heavy metal sensors and bacteria concentration sensors, various indicator data in sewage are collected in real time, including physical, chemical and biological indicator data, such as pH value, dissolved oxygen concentration, suspended matter concentration, heavy metal content, bacteria concentration, etc., and various indicator data are used as raw sewage data; the raw sewage data is preprocessed such as cleaning, denoising, abnormal data processing, and standardization to obtain pretreated sewage data. The above pretreatment processes are all existing technologies well known to those skilled in the art and will not be elaborated here.

[0023] The pre-treated sewage data is subjected to feature extraction and weighted fusion processing using a multi-dimensional adaptive intersection feature fusion algorithm to obtain comprehensive sewage data. The multi-dimensional adaptive intersection feature fusion algorithm extracts and weightedly fuses the pre-treated sewage data from multiple angles by introducing an intersection feature selection mechanism, a multi-dimensional adaptive correction mechanism, and intersection weight superposition. It combines multi-dimensional feature intersections to finally fuse water quality assessment features with higher comprehensiveness. The specific implementation process is as follows: First, a series of intersections are defined to extract intersection features. Intersections refer to the relationship between various indicators, which are defined by the intersection of multiple water quality indicators at a specific time or under specific conditions. Intersection features are common features generated by the interaction between multiple water quality indicators, which can reflect the relationship between water quality in multiple dimensions. The extraction process of intersection features not only focuses on a single indicator, but also considers the common influence and interaction between water quality indicators, which enhances the depth of comprehensive analysis of sewage quality.

[0024] In order to extract the features of these intersections, the membership function of each water quality indicator is defined , indicating the index The degree to which a water quality belongs to a certain category under given conditions. Through the intersection of membership functions, the intersection features of multiple indicators can be extracted. The formula is as follows: , in, It is The index value corresponding to the pre-treated sewage data; It is The index value corresponding to the pre-treated sewage data is The membership function under the intersection feature indicates that the pretreated sewage data belongs to a given category. the degree of water quality; , is a parameter that controls the rate of change of the membership function, reflecting the The index value corresponding to the pre-treated sewage data is sensitivity of the relationship to water quality; It is The index value corresponding to the pre-treated sewage data is The central value under the intersection feature; It is The index value corresponding to the pre-treated sewage data is The categories or divisions in the intersection features are determined based on expert experience and are not limited here; is the total number of sewage data after pretreatment; It is to perform intersection operation on the membership functions of multiple water quality indicators. The minimum value method can be adopted to reflect the joint performance of multiple water quality indicators at a certain moment or under certain conditions. Represents the intersection of the membership functions of all pre-treated sewage data, indicating the area where multiple water quality indicators work together, thereby extracting the intersection features , .

[0025] The intersection characteristics reflect the coupling effects among different water quality indicators and help capture the complexity and nonlinear characteristics of water quality changes.

[0026] After the intersection feature extraction is completed, the adaptive correction stage begins. The purpose of this stage is to dynamically adjust the weights of each intersection feature according to the actual changes in sewage quality, so that it is more in line with the changes in the preset target water quality. By introducing the adaptive correction mechanism, the intersection feature is not only static, but can also be adjusted according to the actual situation of water quality changes. The adaptive correction process adopts Function is used for adjustment, and its mathematical expression is as follows: , in, is the first intersection features; It is The initial weight of each intersection feature is used to control the contribution of the intersection feature to the final adaptive correction value. It reflects the initial weight of each intersection feature in the entire adaptive correction process. It is determined according to the expert experience method and is not limited here. It is The sensitivity parameter of the intersection feature is used to control the influence of the reaction speed of water quality difference. It is determined by experimental tuning and is not limited here. It is the preset target water quality standard, which is determined based on expert experience and is not limited here; is the actual value of the current sewage quality, which is expressed in The current measured value of the sewage index corresponding to the intersection feature reflects the actual situation of the current sewage quality and is obtained through sensor measurement; the above formula uses The function adjusts the weight of the intersection feature according to the difference between the preset target water quality standard and the actual value of the current sewage water quality, ensuring that the adaptively corrected intersection feature can better reflect the changing trend of water quality.

[0027] Furthermore, the adaptively corrected intersection features are put into the feature fusion stage. The adaptively corrected intersection features are fused by weighted fusion to generate comprehensive sewage data. Weighted fusion not only considers the contribution of each intersection feature, but also dynamically weights the intersection according to its importance in water quality assessment. In order to avoid over-reliance on certain features, cosine similarity is introduced to further optimize the weighting process so that the relationship between intersection features can be better captured. The feature fusion formula is as follows: , in, It is comprehensive sewage data; is the number of all intersection features; It is The weight coefficient of the intersection feature indicates the contribution of this feature to the comprehensive sewage data. , It is to adjust The parameter of the weighted sensitivity of the intersection feature is used to control the influence of the difference between the preset target water quality and the current water quality on the feature weighting, which is determined by experimental tuning; The target water quality standard is The value of the intersection feature is determined based on expert experience and is not limited here; is the first intersection features; It is The weighted adjustment factor of the intersection feature indicates the weight of the first The weight adjustment range of the intersection feature. The weight adjustment factor adjusts the final weight of the intersection feature, which is dynamically adjusted according to the actual situation and obtained according to the expert experience method; It is The intersection feature and The cosine similarity between the intersection features; S2. Use a sewage treatment effect evaluation algorithm that combines multi-scale fuzzy reasoning with multi-dimensional data weighted fusion, combine sewage historical data, comprehensive sewage data and external environmental data, conduct a comprehensive evaluation and analysis of the sewage treatment effect, and obtain the analysis results; The sewage treatment effect evaluation algorithm using multi-scale fuzzy reasoning and multi-dimensional data weighted fusion is used to comprehensively evaluate and analyze the sewage treatment effect in combination with sewage historical data, comprehensive sewage data and external environmental data to obtain analysis results; the sewage treatment effect evaluation algorithm using multi-scale fuzzy reasoning and multi-dimensional data weighted fusion aims to comprehensively consider the impact of changes in sewage historical data, comprehensive sewage data and external environmental data through multi-scale fuzzy reasoning mechanism and multi-dimensional data weighted fusion strategy, and conduct a more refined, hierarchical and dynamic evaluation of sewage treatment effect. The specific implementation process is as follows: First, the sewage historical data (taken from the existing database), comprehensive sewage data, and external environmental data (obtained through data acquisition equipment such as sensors) are preprocessed to eliminate noise and standardize the dimensions of data from different sources to obtain preprocessed sewage historical data, comprehensive sewage data, and external environmental data; the preprocessed sewage historical data, comprehensive sewage data, and external environmental data are further processed using a multi-scale fuzzy inference network. By defining multiple scales , respectively, short-term, medium-term and long-term evaluations are conducted on the pre-treated sewage historical data, comprehensive sewage data and external environmental data. The pre-treated sewage historical data, comprehensive sewage data and external environmental data are used as input data for further processing, and each scale corresponds to a fuzzy inference rule set , each fuzzy inference rule set generates corresponding fuzzy inference output according to different input data. , after the input data is subjected to fuzzy inference, the weighted sum of the fuzzy inference output is obtained It can be expressed as: , in, is the weighted sum of the fuzzy inference outputs, representing the Sewage treatment effects at different scales; It is the index of fuzzy inference rules. Fuzzy inference rule set is defined according to expert experience. Different inference results are generated according to different conditions of input data (such as pollutant concentration, pH value, temperature, etc.). from arrive Index all fuzzy inference rules; is the total number of fuzzy inference rules, which indicates the total number of fuzzy inference rules used in fuzzy inference. Each fuzzy inference rule represents a specific data pattern or logical reasoning relationship, which is defined according to expert experience. Is the input data In fuzzy reasoning rules The membership function value under , which is used to describe the relationship between input data and a set of fuzzy inference rules, is usually in the range of ; is the first data values; It is in Input data at scale The fuzzy reasoning result obtained after fuzzy reasoning.

[0028] Each fuzzy inference rule Corresponding to a fuzzy reasoning result , is a fuzzy reasoning output, which indicates the estimated value of a certain aspect of sewage treatment effect at that scale (such as pollutant removal rate, treatment efficiency, etc.). For example, for the indicator COD (chemical oxygen demand), at a specific scale In general, the fuzzy reasoning rule set may generate an evaluation result based on the size of COD (such as "high", "medium", etc.) combined with other water quality parameters (such as pH, ammonia nitrogen concentration, etc.). Through this fuzzy reasoning, the uncertainty and ambiguity in the sewage treatment process can be handled.

[0029] Furthermore, the above process obtains the evaluation results of the pre-treated sewage historical data, comprehensive sewage data, and external environmental data at different scales. On this basis, the multi-dimensional data is fused by adaptive weighting to obtain the final evaluation result. To this end, the weights of the pre-treated sewage historical data, comprehensive sewage data, and external environmental data are calculated. , and , which correspond to the weighted proportions of the historical data of pretreated sewage, comprehensive sewage data, and external environment data, respectively.

[0030] The weight calculation uses a variance-based weighting method. The larger the variance, the more unstable the pre-treated sewage historical data, comprehensive sewage data, and external environment data are, and their weights should be reduced. Therefore, the weight calculation formula is: , , , in, , and They represent the weights of the pre-treated sewage historical data, comprehensive sewage data and external environment data respectively; , and They represent the variances of the pre-treated sewage historical data, comprehensive sewage data, and external environment data, respectively; , and They represent the historical data of pretreated sewage, comprehensive sewage data and external environment data respectively.

[0031] Through the weighted fusion mechanism, the influence of pre-treated sewage historical data, comprehensive sewage data and external environment data can be automatically adjusted according to their volatility, avoiding excessive influence of a certain type of data on the evaluation results. Comprehensive evaluation results after weighted fusion It is expressed as: , in, They are the outputs of pre-treated sewage historical data, comprehensive sewage data and external environment data in fuzzy reasoning. Through weighted fusion processing, the evaluation information of various data sources can be integrated to obtain a more accurate and reliable sewage treatment effect evaluation.

[0032] Furthermore, the comprehensive evaluation results after weighted fusion are and target emission standards Compare and calculate the difference in each water quality indicator: , in, It is Project emission standards; It is Comprehensive evaluation results after weighted fusion of items; It is The deviation between the comprehensive evaluation results after weighted fusion of the items and the target emission standard; a comprehensive evaluation and analysis of the sewage treatment effect is conducted, and the analysis results are finally obtained. The smaller the deviation of the analysis result, the better the sewage treatment effect is, otherwise it means the sewage treatment effect is not good.

[0033] S3. Based on the analysis results, determine the severity level of the sewage water quality, and issue warning signals and intelligent adjustment instructions of corresponding levels, and perform operational adjustment processing of the sewage treatment equipment based on the intelligent adjustment instructions.

[0034] Based on the analysis results, the threshold is set according to the expert experience method , , To judge the severity level of sewage quality, and trigger a multi-level early warning mechanism according to the severity level. Specifically, when the deviation between the comprehensive evaluation result after weighted fusion and the target emission standard is When the deviation between the comprehensive evaluation result after weighted fusion and the target emission standard is When the deviation between the comprehensive evaluation result after weighted fusion and the target emission standard is greater than or equal to It is a serious warning, indicating that the water quality seriously exceeds the standard and emergency measures need to be taken immediately.

[0035] According to the analysis results and the generated warning signals of the corresponding level, the corresponding intelligent adjustment instructions are generated by using the intelligent adjustment strategy pre-set by the expert experience method. The generation of the intelligent adjustment instructions is based on two aspects of input: the current operating state of the sewage treatment system, that is, the current operating efficiency, processing capacity, equipment failure information, etc. of the sewage treatment equipment; the severity level of the sewage water quality, and the corresponding intelligent adjustment instructions are generated by the existing rule engine or machine learning model, including equipment operation adjustment, operation parameter changes, chemical agent addition, etc. For example, when the water quality severity reaches the "serious warning" level, the following adjustment instructions can be issued: increase the aeration volume, increase the ventilation volume of the aeration tank to accelerate the supply of dissolved oxygen in the sewage and promote the degradation of organic matter; adjust the dosage of the agent, and when the water quality parameters are abnormal, calculate the optimal dosage of the agent according to the existing expert experience method; increase the sludge return flow, throttle the working state of the reflux pump, and increase the sludge return flow of the sedimentation tank to improve the sludge settling efficiency. The intelligent adjustment instructions are further transmitted to the sewage treatment equipment, the instructions are automatically executed, the operating state is adjusted, and the operation adjustment processing of the sewage treatment equipment based on the intelligent adjustment instructions is implemented.

[0036] In summary, a sewage treatment inspection system and method are completed.

[0037] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0038] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0039] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for testing sewage treatment, characterized in that: The following steps are involved: S1. Collect the index data in the sewage in real time as the raw sewage data, pre-process the raw sewage data, and obtain the pre-processed sewage data; The pre-treated sewage data is subjected to feature extraction and weighted fusion processing using a multi-dimensional adaptive intersection feature fusion algorithm to obtain comprehensive sewage data. S2. Use a sewage treatment effect evaluation algorithm that combines multi-scale fuzzy reasoning with multi-dimensional data weighted fusion, combine sewage historical data, comprehensive sewage data and external environmental data, conduct a comprehensive evaluation and analysis of the sewage treatment effect, and obtain the analysis results; S3. Based on the analysis results, determine the severity level of the sewage water quality, and issue warning signals and intelligent adjustment instructions of corresponding levels, and perform operational adjustment processing of the sewage treatment equipment based on the intelligent adjustment instructions.

2. A method for inspecting sewage treatment according to claim 1, characterized in that: The S1 specifically includes: The multi-dimensional adaptive intersection feature fusion algorithm introduces an intersection feature selection mechanism, a multi-dimensional adaptive correction mechanism, and an intersection weight superposition to extract features and weighted fuse pretreated sewage data from different angles, and finally obtains comprehensive sewage data by combining multi-dimensional feature intersections.

3. A method for inspecting sewage treatment according to claim 2, characterized in that: The S1 specifically includes: In the process of implementing the multi-dimensional adaptive intersection feature fusion algorithm, the intersection features are defined and extracted, and after the intersection feature extraction is completed, the adaptive correction stage is entered.

4. A method for inspecting sewage treatment according to claim 3, characterized in that: The S1 specifically includes: In the process of implementing the multi-dimensional adaptive intersection feature fusion algorithm, an adaptive correction mechanism is introduced to obtain the adaptively corrected intersection feature. The specific implementation formula is: ， in, is the first intersection features; It is intersection features; It is The initial weights of the intersection features; It is The sensitivity parameter of the intersection feature; It is the preset target water quality standard; It is the actual value of current sewage quality.

5. A sewage treatment inspection method according to claim 4, characterized in that: The S1 specifically includes: In the process of implementing the multi-dimensional adaptive intersection feature fusion algorithm, the adaptively corrected intersection features are put into the feature fusion stage, and the adaptively corrected intersection features are fused by weighted fusion to generate comprehensive sewage data. The specific implementation formula is: ， in, It is comprehensive sewage data; is the number of all intersection features; It is The weight coefficient of the intersection feature; is the first intersection features; It is The weighted adjustment factor for each intersection feature; It is The intersection feature and The cosine similarity between the features of the intersection points.

6. A sewage treatment inspection method according to claim 1, characterized in that: The S2 specifically includes: In the process of implementing the sewage treatment effect evaluation algorithm of multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, the sewage historical data, comprehensive sewage data and external environment data are preprocessed, and the pretreated sewage historical data, comprehensive sewage data and external environment data are processed using a multi-scale fuzzy reasoning network. By defining different scales, short-term, medium-term and long-term evaluations are performed on the pretreated sewage historical data, comprehensive sewage data and external environment data.

7. A sewage treatment inspection method according to claim 6, characterized in that: The S2 specifically includes: In the process of implementing the sewage treatment effect evaluation algorithm of multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, the pretreated sewage historical data, comprehensive sewage data and external environment data are used as input data. For each scale, the input data is subjected to fuzzy reasoning to obtain the weighted sum of the fuzzy reasoning output, thereby obtaining the evaluation results of the input data at different scales.

8. A method for inspecting sewage treatment according to claim 7, characterized in that: The S2 specifically includes: In the process of implementing the sewage treatment effect evaluation algorithm of multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, based on the evaluation results of the input data at different scales, the multi-dimensional data is adaptively weighted and fused to obtain the comprehensive evaluation results after weighted fusion; the comprehensive evaluation results after weighted fusion are compared with the target emission standards, and the sewage treatment effect is comprehensively evaluated and analyzed to finally obtain the analysis results.

9. A sewage treatment inspection system, applied to the sewage treatment inspection method according to claim 1, characterized in that: Includes the following parts: Data acquisition module, data intelligent processing module, data intelligent analysis module, intelligent early warning and decision support module, execution module; The data acquisition module collects the index data in the sewage in real time and sends the collected index data as raw sewage data to the data intelligent processing module; The data intelligent processing module pre-processes the raw sewage data to obtain pre-processed sewage data, performs feature extraction and weighted fusion processing on the pre-processed sewage data to obtain comprehensive sewage data, and sends the comprehensive sewage data to the data intelligent analysis module; The data intelligent analysis module uses a sewage treatment effect evaluation algorithm based on multi-scale fuzzy reasoning and multi-dimensional data weighted fusion, combines sewage historical data, comprehensive sewage data and external environmental data, conducts a comprehensive evaluation and analysis of sewage treatment effects, and generates analysis results by comparing water quality parameters with standard emission requirements. The analysis results are then sent to the intelligent early warning and decision support module; The intelligent early warning and decision support module introduces a multi-level early warning mechanism. Based on the analysis results, it determines the severity level of sewage quality and issues early warning signals of corresponding levels. At the same time, it gives corresponding intelligent adjustment instructions and sends the intelligent adjustment instructions to the execution module. The execution module performs the operation adjustment processing of the sewage treatment equipment according to the intelligent adjustment instructions, and after the adjustment processing, collects the treated sewage samples for comparison with the expected indicators of the same period. When the treated sewage samples meet the expected indicators of the same period, subsequent processing is carried out. When the treated sewage samples do not meet the expected indicators of the same period, they continue to be processed by the data acquisition module, the data intelligent processing module, the data intelligent analysis module, and the intelligent early warning and decision support module to form a closed loop.

Images