Method and system for diagnosing wastewater treatment plant based on multi-source heterogeneous diagnostic knowledge base

Abstract

The present application relates to sewage treatment technical field, especially to a kind of sewage treatment plant diagnosis method and system based on multi-source heterogeneous diagnosis knowledge base, comprising: S100, the historical operation data of sewage treatment plant is obtained, and the intelligent diagnosis system based on multi-source heterogeneous diagnosis knowledge base is established based on the historical operation data;S200, the operation state data of sewage treatment plant to be diagnosed is obtained, and the operation state data of the sewage treatment plant to be diagnosed is input into the intelligent diagnosis system, when there is fault, through the operation diagnosis based on biological modeling, the operation diagnosis based on operation rule, the operation diagnosis based on historical case, the operation diagnosis based on knowledge graph, obtain multiple fault solutions, the multiple fault solutions are analyzed by fuzzy comprehensive evaluation, and final diagnosis result is obtained;The present application can improve the precision and efficiency of diagnosis, and can also realize intelligent diagnosis.

Description

Technical Field

[0001] This invention relates to the field of wastewater treatment technology, and in particular to a diagnostic method and system for wastewater treatment plants based on a multi-source heterogeneous diagnostic knowledge base. Background Technology

[0002] By the end of 2022, my country had 6,910 urban wastewater treatment plants, including 2,827 city wastewater treatment plants, with an annual wastewater treatment capacity of 60 billion cubic meters and a wastewater treatment rate of 98%. With the continuous advancement and deepening of my country's urbanization strategy, urban wastewater treatment construction has entered a stage of high-quality development. In this stage, energy conservation, emission reduction, and efficient operation of urban wastewater treatment plants will become key technological capabilities for the water industry in the future. Furthermore, improving the quality and efficiency of wastewater treatment plants and resource recycling will also become future development directions.

[0003] However, in practice, urban wastewater treatment plants in my country still suffer from inefficient management, resulting in poor overall performance and a persistent problem of inconsistent effluent quality. Furthermore, a lack of skilled process engineers leads to delayed detection and inaccurate resolution of various malfunctions, severely impacting plant efficiency and causing high operating costs. Moreover, the complexity and numerous factors influencing effluent quality and malfunctions make it difficult for plant operators to accurately diagnose the causes of problems, potentially leading to significant safety accidents. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a diagnostic method and system for wastewater treatment plants based on a multi-source heterogeneous diagnostic knowledge base, which can improve the accuracy and efficiency of diagnosis and realize intelligent diagnosis.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0008] In a first aspect, embodiments of the present invention provide a diagnostic method for wastewater treatment plants based on a multi-source heterogeneous diagnostic knowledge base, comprising:

[0009] S100. Obtain historical operating data of the wastewater treatment plant, and establish an intelligent diagnostic system based on the historical operating data and a multi-source heterogeneous diagnostic knowledge base.

[0010] S200. Obtain the operational status data of the wastewater treatment plant to be diagnosed, input the operational status data of the wastewater treatment plant to be diagnosed into the intelligent diagnostic system, and when a fault exists, obtain multiple fault solutions through operational diagnosis based on biological modeling, operational diagnosis based on operational rules, operational diagnosis based on historical cases, and operational diagnosis based on knowledge graphs. Then, obtain the final diagnostic result by performing fuzzy comprehensive evaluation analysis on the multiple fault solutions.

[0011] The operational status data includes the water plant design data of the main equipment of the wastewater treatment plant, real-time monitoring data of water quality and quantity, process operation data, laboratory data, equipment operation data, and other operational data.

[0012] Optionally, S100 includes:

[0013] S110. Perform data preprocessing on the historical operation data to obtain the final preprocessed data;

[0014] S120. The final preprocessed data is stored in the comprehensive database and sent to the inference engine. The inference engine interprets the final preprocessed data based on the pre-set first operating rules to obtain diagnostic results.

[0015] S130. When the diagnosis result is no fault, the inference engine feeds back the diagnosis result to the human-computer interaction interface, and the human-computer interaction interface displays that the operation is normal.

[0016] Optionally, S100 further includes:

[0017] S140. When the diagnosis result indicates that a fault exists, the inference engine sends the final preprocessed data of the fault to the multi-source heterogeneous operation diagnosis knowledge base.

[0018] S150: The multi-source heterogeneous operation diagnostic knowledge base diagnoses the final preprocessed data of the fault, obtains multiple fault solutions, and feeds them back to the inference engine.

[0019] S160. The inference engine processes the multiple fault solutions based on the pre-set second operating rules, obtains the final fault solution, and sends the final fault solution to the human-computer interaction interface.

[0020] Alternatively, the final fault solution can be sent to a comprehensive database, which in turn sends the final fault solution to an interpreter, and the interpreter sends the final fault solution to a human-computer interaction interface.

[0021] S170. The human-computer interaction interface receives the final fault solution and displays a confirmation or denial button for the final fault solution.

[0022] Optionally, after S170, the following may also be included:

[0023] S180. The human-computer interaction interface receives the instruction from the user to click the final fault solution confirmation button, and sends the final fault solution to the interpreter, whereby the interpreter stores the final fault solution.

[0024] Alternatively, the human-computer interaction interface may receive a user's instruction to click the "deny final fault solution" button, and then feed back the final fault solution to the inference engine, re-execute S140 to S170, until the human-computer interaction interface receives a user's instruction to click the "confirm final fault solution" button.

[0025] Optionally, in S100,

[0026] The historical operational data includes:

[0027] Water plant design data, real-time water quality and quantity monitoring data, process operation data, laboratory data, equipment operation data, and other operation data.

[0028] Optionally, S110 includes:

[0029] S111. Based on data cleaning technology, identify and remove duplicate and erroneous data in the historical running data to obtain first preprocessed data;

[0030] S112. The first preprocessed data is classified according to different diagnostic methods, and each type of data is labeled with a corresponding data label to obtain the final preprocessed data.

[0031] Optionally, in S112,

[0032] The second preprocessed data is categorized according to different diagnostic methods, including:

[0033] Equipment operation data and other operation data are classified into operation diagnosis methods based on historical cases; process operation parameters are classified into operation diagnosis methods based on biological modeling; real-time water quality and quantity monitoring data are classified into operation diagnosis methods based on knowledge graphs; and water plant design data and laboratory data are classified into operation diagnosis methods based on operation rules.

[0034] Optionally, in S120,

[0035] The first operating rule is pre-set based on common sense and experience in the operation of wastewater treatment plants.

[0036] Optionally, in S160,

[0037] The second operating rule is:

[0038] S161. Perform fuzzy comprehensive evaluation analysis on each fault solution, including determining evaluation factors and indicators, and evaluation levels;

[0039] S162. The evaluation factors and indicators for each fault solution are divided into three evaluation indicators: technical feasibility, economic benefits, and application effect. The evaluation level is divided into four levels: excellent, good, relatively good, and average. Weights are assigned to different evaluation levels, with a value range of 0-1.

[0040] S163. The evaluation results of the solution are obtained by using matrix fuzzy operation on the evaluation factors, indicators and evaluation levels. The solution with the highest score is output as the final solution.

[0041] Secondly, embodiments of the present invention provide a wastewater treatment plant diagnostic system based on a multi-source heterogeneous diagnostic knowledge base, comprising:

[0042] A construction module is used to acquire historical operating data of a wastewater treatment plant and to build an intelligent diagnostic system based on a multi-source heterogeneous diagnostic knowledge base based on the historical operating data.

[0043] The diagnostic module is used to acquire the operational status data of the wastewater treatment plant to be diagnosed, input the operational status data of the wastewater treatment plant to be diagnosed into the intelligent diagnostic system, and when a fault exists, obtain multiple fault solutions through operational diagnosis based on biological modeling, operational diagnosis based on operational rules, operational diagnosis based on historical cases, and operational diagnosis based on knowledge graphs. The multiple fault solutions are then analyzed through fuzzy comprehensive evaluation to obtain the final diagnostic result.

[0044] The operational status data includes the water plant design data of the main equipment of the wastewater treatment plant, real-time monitoring data of water quality and quantity, process operation data, laboratory data, equipment operation data, and other operational data.

[0045] (III) Beneficial Effects

[0046] The beneficial effects of the present invention are as follows: The wastewater treatment plant diagnostic system based on a multi-source heterogeneous diagnostic knowledge base of the present invention, by adopting a multi-source heterogeneous diagnostic knowledge base, performs operational diagnostics based on biological modeling, operational diagnostics based on operational rule graphs, operational diagnostics based on historical cases, and operational diagnostics based on knowledge graphs. Compared with the prior art, it can improve the accuracy and efficiency of diagnosis and achieve intelligent diagnosis. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating the wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base according to Embodiment 1 of the present invention.

[0048] Figure 2This is a flowchart of the intelligent diagnostic system for the wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base, as described in Embodiment 2 of the present invention. Detailed Implementation

[0049] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0050] An expert system comprises several components, including a knowledge base, an inference engine, a database, an interpreter, and a human-computer interface. The most crucial component is the knowledge base, which is also the bottleneck of the entire system. It needs to collect as many potential problems as possible related to the object being diagnosed and identify the causes and solutions for each problem. The inference engine analyzes and interprets the user-input data using the knowledge base based on certain logic and reasoning rules. The database is the system's operational object, and the interpreter explains the user's queries. The human-computer interface is the interface through which the user communicates with the computer.

[0051] The wastewater treatment plant diagnostic method and system based on a multi-source heterogeneous diagnostic knowledge base proposed in this invention improves the accuracy and efficiency of diagnosis and enables intelligent diagnosis compared to existing technologies by employing a multi-source heterogeneous diagnostic knowledge base to perform operational diagnosis based on biological modeling, operational diagnosis based on operational rule graphs, operational diagnosis based on historical cases, and operational diagnosis based on knowledge graphs.

[0052] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0053] Detailed Description of Embodiments

[0054] Example 1

[0055] See Figure 1 The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base in this embodiment includes:

[0056] Step S100: Obtain historical operating data of the wastewater treatment plant, and establish an intelligent diagnostic system based on the historical operating data and a multi-source heterogeneous diagnostic knowledge base;

[0057] Step S200: Obtain the operating status data of the wastewater treatment plant to be diagnosed, input the operating status data of the wastewater treatment plant to be diagnosed into the intelligent diagnostic system, and when a fault exists, obtain multiple fault solutions through operation diagnosis based on biological modeling, operation diagnosis based on operation rules, operation diagnosis based on historical cases, and operation diagnosis based on knowledge graph. The multiple fault solutions are then analyzed through fuzzy comprehensive evaluation to obtain the final diagnostic result.

[0058] The operational status data includes the water plant design data of the main equipment of the wastewater treatment plant, real-time monitoring data of water quality and quantity, process operation data, laboratory data, equipment operation data, and other operational data.

[0059] In this embodiment, operation diagnosis based on biological modeling utilizes mathematical models or simulation software of the activated sludge process to simulate the operation status and parameters of the wastewater treatment plant, and provides diagnostic and optimization suggestions for the existing processes and operating parameters based on the simulation results. Operation diagnosis based on operational rules uses data from the wastewater treatment plant's operation and management to diagnose problems within the plant. Operation diagnosis based on historical cases uses historical operation and maintenance records and data of the plant's equipment and processes to diagnose problems in the wastewater treatment process. Operation diagnosis based on knowledge graphs uses the graphical and structured representation of knowledge to infer causal relationships during the operation of the wastewater treatment plant.

[0060] For example, the equipment operation data of the main equipment and other operation data of a wastewater treatment plant are categorized into operation diagnosis methods based on historical cases, resulting in a solution based on historical cases; process operation parameters are categorized into operation diagnosis methods based on biological modeling, resulting in a solution based on biological modeling; real-time water quality and quantity monitoring data are categorized into operation diagnosis methods based on knowledge graphs, resulting in a solution based on knowledge graphs; and water plant design data and laboratory data are categorized into operation diagnosis methods based on operation rules, resulting in a solution based on operation rules. Fuzzy comprehensive evaluation analysis is then performed on these four solutions—operation diagnosis based on historical cases, operation diagnosis based on biological modeling, operation diagnosis based on knowledge graphs, and operation diagnosis based on operation rules—to obtain the final solution in the final diagnostic result.

[0061] The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base in this embodiment combines multiple diagnostic methods, which can improve the accuracy and efficiency of diagnosis and achieve intelligent diagnosis.

[0062] Example 2

[0063] This embodiment of the wastewater treatment plant diagnostic method and system based on a multi-source heterogeneous diagnostic knowledge base includes:

[0064] Step S100: Obtain historical operating data of the wastewater treatment plant, and establish an intelligent diagnostic system based on the historical operating data and a multi-source heterogeneous diagnostic knowledge base;

[0065] Step S200: Obtain the operating status data of the wastewater treatment plant to be diagnosed, input the operating status data of the wastewater treatment plant to be diagnosed into the intelligent diagnostic system, and when a fault exists, obtain multiple fault solutions through operation diagnosis based on biological modeling, operation diagnosis based on operation rules, operation diagnosis based on historical cases, and operation diagnosis based on knowledge graph. The multiple fault solutions are then analyzed through fuzzy comprehensive evaluation to obtain the final diagnostic result.

[0066] The operational status data includes the water plant design data of the main equipment of the wastewater treatment plant, real-time monitoring data of water quality and quantity, process operation data, laboratory data, equipment operation data, and other operational data.

[0067] In this embodiment, step S100 includes:

[0068] Step S110: Perform data preprocessing on the historical running data to obtain the final preprocessed data;

[0069] Step S110 includes:

[0070] Step S111: Based on data cleaning technology, identify and remove duplicate and erroneous data in the historical running data to obtain the first preprocessed data;

[0071] Step S112: Classify the first preprocessed data according to different diagnostic methods, and affix corresponding data labels to each category of data to obtain the final preprocessed data.

[0072] The data cleaning techniques include data deduplication, data verification and evaluation, and data filtering.

[0073] The data deduplication method is based on sorting to remove duplicate data and solve the problem of data redundancy; the data verification and evaluation method is based on the operating principle of wastewater treatment process to identify and evaluate abnormal, missing, and distorted data for data analysis; the data filtering method is based on machine learning to delete invalid, incomplete, or unacceptable data.

[0074] In this embodiment, classifying the second preprocessed data according to different diagnostic methods includes:

[0075] Equipment operation data and other operation data are classified into operation diagnosis methods based on historical cases; process operation parameters are classified into operation diagnosis methods based on biological modeling; real-time water quality and quantity monitoring data are classified into operation diagnosis methods based on knowledge graphs; and water plant design data and laboratory data are classified into operation diagnosis methods based on operation rules.

[0076] Step S120: The final preprocessed data is stored in the comprehensive database and sent to the inference engine. The inference engine interprets the final preprocessed data based on the preset first operating rules to obtain the diagnostic results.

[0077] Step S130: When the diagnosis result is no fault, the inference engine feeds back the diagnosis result to the human-computer interaction interface, and the human-computer interaction interface displays no fault.

[0078] See Figure 2 Step S100 further includes:

[0079] Step S140: When the diagnosis result indicates that a fault exists, the inference engine sends the final preprocessed data of the fault to the multi-source heterogeneous operation diagnosis knowledge base.

[0080] Step S150: The multi-source heterogeneous operation diagnostic knowledge base diagnoses the final preprocessed data of the fault, obtains multiple fault solutions, and feeds them back to the inference engine.

[0081] Step S160: The inference engine processes the multiple fault solutions based on the pre-set second operating rules, obtains the final fault solution, and sends the final fault solution to the human-computer interaction interface;

[0082] Alternatively, the final fault solution can be sent to a comprehensive database, which in turn sends the final fault solution to an interpreter, and the interpreter sends the final fault solution to a human-computer interaction interface.

[0083] Step S170: The human-computer interaction interface receives the final fault solution and pops up a button to confirm or deny the final fault solution.

[0084] Step S180: The human-computer interaction interface receives the instruction from the user to click the final fault solution confirmation button, and sends the final fault solution to the interpreter, whereby the interpreter stores the final fault solution.

[0085] Alternatively, the human-computer interaction interface may receive a user's instruction to click the "deny final fault solution" button, and then feed back the final fault solution to the inference engine, re-execute S140 to S170, until the human-computer interaction interface receives a user's instruction to click the "confirm final fault solution" button.

[0086] In this embodiment, knowledge tags and structural information of a multi-source heterogeneous diagnostic knowledge base are configured and run. A knowledge base model framework is constructed through the knowledge tags in the multi-source heterogeneous diagnostic knowledge base. A comprehensive database model is constructed through data tag association. The comprehensive database model is associated with the knowledge base model through the association between the knowledge tags and the data tags. Through the association between the comprehensive database model and the knowledge base model, the diagnostic methods of the multi-source heterogeneous diagnostic knowledge base are used to diagnose and analyze the comprehensive database, and the diagnostic results are displayed on the human-computer interaction interface.

[0087] In this embodiment, in step S160, the second operating rule is:

[0088] Step S161: Perform fuzzy comprehensive evaluation analysis on each fault solution, including determining evaluation factors and indicators, and evaluation levels;

[0089] Step S162: The evaluation factors and indicators for each fault solution are divided into three evaluation indicators: technical feasibility, economic benefits, and application effect. The evaluation level is divided into four levels: excellent, good, relatively good, and average. Weights are assigned to different evaluation levels, with a value range of 0-1.

[0090] Step S163: Use matrix fuzzy operation to obtain the evaluation results of the solution based on the evaluation factors, indicators and evaluation levels, and output the solution with the highest score as the final solution.

[0091] In this embodiment,

[0092] Each evaluation factor and indicator is divided into four evaluation levels: excellent, good, relatively good, and average. The scoring criteria are set according to the importance and influence of the factor.

[0093] For example, the multi-source heterogeneous diagnostic knowledge base provides four solutions and sends them to the inference engine; these four solutions are solution A, solution B, solution C, and solution D.

[0094] First, for each solution, determine the set of evaluation factors U and the set of evaluation levels Q, and then quantify and score the evaluation indicators:

[0095] U = {Technical feasibility, economic benefits, application effectiveness}, Q = {Excellent, Good, Fairly good, Average}

[0096] For example, a certain type of solution uses expert scoring to quantitatively evaluate the qualitative indicators of each solution;

[0097]

[0098] Next, calculate the fuzzy evaluation matrix P for each solution:

[0099] Px ={P ij}, where P ij The meaning is the membership degree of the evaluation object x to the j-th comment under the i-th evaluation index. The membership degree is represented by the proportion of each evaluation result. The shape (m,n) of the fuzzy evaluation matrix of an evaluation object satisfies m = size of the set of evaluation factors and n = size of the set of evaluation levels;

[0100] Based on the quantification results from the first step, the fuzzy evaluation matrix is ​​obtained:

[0101]

[0102]

[0103]

[0104]

[0105] Among them, P A Let P be the fuzzy evaluation matrix of scheme A. B Let P be the fuzzy evaluation matrix of scheme B. C Let P be the fuzzy evaluation matrix of scheme C. D Let be the fuzzy evaluation matrix of scheme D.

[0106] Next, determine the weight vector coefficients of the evaluation factors. For example, in this case, the evaluation factor vector coefficients W = {0.4, 0.2, 0.4}.

[0107] The evaluation result vector R is obtained by using matrix fuzzy operations.

[0108] R x =W·P x .

[0109] Among them, R x For each scheme, there is an evaluation result vector, where W is the coefficient of the evaluation factor vector, and P... x The fuzzy evaluation matrix for each scheme.

[0110] The evaluation results for this case are as follows:

[0111]

[0112]

[0113]

[0114]

[0115] Among them, R A Let R be the evaluation result vector of scheme A.B Let R be the evaluation result vector of scheme B. c Let R be the evaluation result vector of scheme C. D Let be the evaluation result vector for scheme D.

[0116] Based on the above analysis, it can be concluded that Scheme C is the scheme with the most excellent evaluation indicators, and the weight of excellence is 0.94. Therefore, the final solution selected is Scheme C.

[0117] The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base in this embodiment uses a multi-source heterogeneous diagnostic knowledge base to perform operational diagnostics based on biological modeling, operational diagnostics based on operational rule graphs, operational diagnostics based on historical cases, and operational diagnostics based on knowledge graphs. This can improve the accuracy and efficiency of diagnosis and achieve intelligent diagnosis.

[0118] Example 3

[0119] This embodiment of the wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base assumes that the main equipment of the wastewater treatment plant consists of a coarse screen, a lift pump, a grit chamber, and an aerated bioreactor; its real-time water quality and quantity monitoring data include:

[0120] The average COD was 210 mg / L, the average BOD was 110 mg / L, and the pH range was 7.0-8.0.

[0121] Process operation data includes:

[0122] Aeration capacity is 10000 Nm 3 / h, the dissolved oxygen concentration in the reactor is 2.0 mg / L, and the sludge concentration is 8000 mg / L;

[0123] Laboratory data includes:

[0124] The sludge settling ratio is 30%, the nitrate nitrogen content is 10 mg / L, and the total phosphorus content is 4 mg / L.

[0125] Equipment operating data includes:

[0126] The booster pump motor current is 120A; the aeration blower runs for 20 hours; the hypochlorous acid disinfection device electrolysis current is 6A.

[0127] The above operational status data is input into the intelligent diagnostic system, and a diagnosis is performed in the multi-source heterogeneous diagnostic knowledge base, yielding the following fault information:

[0128] Operational diagnosis based on biological modeling: The system uses a mathematical model of the bioreactor to analyze parameters such as sludge concentration, dissolved oxygen level and reactor temperature, and finds that the sludge settling ratio is lower than expected, which may indicate a problem of decreased sludge activity.

[0129] Operational diagnostics based on operational rules: The system checks the difference between the designed influent water quality and the actual influent water quality, and whether the process parameters are within the normal range. The system detected that the actual influent COD and SS exceeded the designed influent standards.

[0130] Operational diagnosis based on historical cases: By comparing historical failure cases, the system found that foaming in the aerated bioreactor may be a signal of insufficient aeration or uneven aeration.

[0131] Knowledge graph-based operational diagnosis: Based on the causal relationships and process flow in the knowledge graph, the system infers that excessive COD in the influent may lead to increased processing pressure in subsequent treatment units.

[0132] Based on the fault situation, the following solutions are proposed:

[0133] Strengthen the operation of the pretreatment unit by increasing the efficiency of coarse screens and booster pumps to reduce the load of suspended solids and organic matter entering the biological treatment unit; adjust the aeration strategy and optimize the aeration rate to ensure that the dissolved oxygen concentration in the reactor reaches an appropriate level; increase the sludge discharge frequency of the biological treatment unit to improve sludge settling performance.

[0134] Based on the above multiple solutions, the final solution is derived through fuzzy comprehensive evaluation analysis: strengthen the operation of the pretreatment unit, increase the coarse screen and improve the operating efficiency of the pump to reduce the load of suspended solids and organic matter entering the biological treatment unit and improve the overall treatment efficiency.

[0135] The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base in this embodiment improves the accuracy and efficiency of diagnosis by using the multi-source heterogeneous diagnostic knowledge base.

[0136] Example 4

[0137] The wastewater treatment plant diagnostic system based on a multi-source heterogeneous diagnostic knowledge base in this embodiment includes:

[0138] A construction module is used to acquire historical operating data of a wastewater treatment plant and to build an intelligent diagnostic system based on a multi-source heterogeneous diagnostic knowledge base based on the historical operating data.

[0139] The diagnostic module is used to acquire the operational status data of the wastewater treatment plant to be diagnosed, input the operational status data of the wastewater treatment plant to be diagnosed into the intelligent diagnostic system, and when a fault exists, obtain multiple fault solutions through operational diagnosis based on biological modeling, operational diagnosis based on operational rules, operational diagnosis based on historical cases, and operational diagnosis based on knowledge graphs. The multiple fault solutions are then analyzed through fuzzy comprehensive evaluation to obtain the final diagnostic result.

[0140] The operational status data includes the water plant design data of the main equipment of the wastewater treatment plant, real-time monitoring data of water quality and quantity, process operation data, laboratory data, equipment operation data, and other operational data.

[0141] The wastewater treatment plant diagnostic system based on a multi-source heterogeneous diagnostic knowledge base in this embodiment can improve the accuracy and efficiency of diagnosis, and also achieve intelligent diagnosis.

[0142] In the description of this invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0143] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0144] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first and second features are in direct contact, or that they are in indirect contact through an intermediate medium. Furthermore, "above," "over," or "on top" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," or "beneath" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0145] In the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0146] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make modifications, alterations, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base, characterized in that, include: S100. Obtain historical operating data of the wastewater treatment plant, and establish an intelligent diagnostic system based on the historical operating data and a multi-source heterogeneous diagnostic knowledge base. S200. Obtain the operational status data of the wastewater treatment plant to be diagnosed, input the operational status data of the wastewater treatment plant to be diagnosed into the intelligent diagnostic system, and when a fault exists, obtain multiple fault solutions through operational diagnosis based on biological modeling, operational diagnosis based on operational rules, operational diagnosis based on historical cases, and operational diagnosis based on knowledge graphs. Then, obtain the final diagnostic result by performing fuzzy comprehensive evaluation analysis on the multiple fault solutions. The operational status data includes the water plant design data, real-time water quality and quantity monitoring data, process operation data, laboratory data, equipment operation data, and other operational data of the main equipment of the wastewater treatment plant. S100 includes: S110. Perform data preprocessing on the historical operation data to obtain the final preprocessed data; S120. The final preprocessed data is stored in the comprehensive database and sent to the inference engine. The inference engine interprets the final preprocessed data based on the pre-set first operating rules to obtain diagnostic results. S130. When the diagnosis result is no fault, the inference engine feeds back the diagnosis result to the human-computer interaction interface, and the human-computer interaction interface displays a normal status. S110 includes: S111. Based on data cleaning technology, identify and remove duplicate and erroneous data in the historical running data to obtain first preprocessed data; S112. Classify the first preprocessed data according to different diagnostic methods, and affix corresponding data labels to each category of data to obtain the final preprocessed data; In S112, The first preprocessed data is classified according to different diagnostic methods, including: Equipment operation data and other operation data are classified into operation diagnosis methods based on historical cases; process operation parameters are classified into operation diagnosis methods based on biological modeling; real-time water quality and quantity monitoring data are classified into operation diagnosis methods based on knowledge graphs; and water plant design data and laboratory data are classified into operation diagnosis methods based on operation rules.

2. The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base according to claim 1, characterized in that, The S100 further includes: S140. When the diagnosis result indicates that a fault exists, the inference engine sends the final preprocessed data of the fault to the multi-source heterogeneous operation diagnosis knowledge base. S150: The multi-source heterogeneous operation diagnostic knowledge base diagnoses the final preprocessed data of the fault, obtains multiple fault solutions, and feeds them back to the inference engine. S160. The inference engine processes the multiple fault solutions based on the pre-set second operating rules, obtains the final fault solution, and sends the final fault solution to the human-computer interaction interface. Alternatively, the final fault solution can be sent to a comprehensive database, which in turn sends the final fault solution to an interpreter, and the interpreter sends the final fault solution to a human-computer interaction interface. S170. The human-computer interaction interface receives the final fault solution and displays a confirmation or denial button for the final fault solution.

3. The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base according to claim 2, characterized in that, Following S170, the following is also included: S180. The human-computer interaction interface receives the instruction from the user to click the final fault solution confirmation button, and sends the final fault solution to the interpreter, whereby the interpreter stores the final fault solution. Alternatively, the human-computer interaction interface may receive a user's instruction to click the "deny final fault solution" button, and then feed back the final fault solution to the inference engine, re-execute S140 to S170, until the human-computer interaction interface receives a user's instruction to click the "confirm final fault solution" button.

4. The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base according to claim 1, characterized in that, In S100, The historical operational data includes: Water plant design data, real-time water quality and quantity monitoring data, process operation data, laboratory data, equipment operation data, and other operation data.

5. The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base according to claim 1, characterized in that, In S120, The first operating rule is pre-set based on common sense and experience in the operation of wastewater treatment plants.

6. The wastewater treatment plant diagnostic method based on a multi-source heterogeneous diagnostic knowledge base according to claim 2, characterized in that, In S160, The second operating rule is: S161. Perform fuzzy comprehensive evaluation analysis on each fault solution, including determining evaluation factors and indicators, and evaluation levels; S162. The evaluation factors and indicators for each fault solution are divided into three evaluation indicators: technical feasibility, economic benefits, and application effect. The evaluation level is divided into four levels: excellent, good, relatively good, and average. Weights are assigned to different evaluation levels, with a value range of 0-1. S163. The evaluation results of the solution are obtained by using matrix fuzzy operation on the evaluation factors, indicators and evaluation levels. The solution with the highest score is output as the final solution.

Images