Intelligent online inspection system for water quality in and out of water plants

Abstract

The present invention relates to the technical field of water quality inspection, and specifically discloses an intelligent online inspection system for water quality of water inlet and outlet of a water plant, comprising: analyzing the heavy metal content and the number of heavy metal species in water at an inlet to obtain a quality performance value, judging whether it is necessary to process the heavy metals in the water at the inlet based on the quality performance value, generating a processing signal if processing is required, processing and analyzing the heavy metal removal rate within a processing cycle based on the processing signal to obtain a removal rate deviation, marking sub-regions based on the removal rate deviation, the marking result including an abnormal sub-region and a normal sub-region, analyzing the removal rate deviation and the abnormal sub-region of the removal abnormal sub-region to obtain a first inspection sequence table and a second sequence table. The present invention is conducive to optimizing the inspection route by conducting an in-depth analysis of the sub-region with abnormal removal rate in a heavy metal treatment pool, and by generating the first inspection sequence table and the second sequence table.

Description

Technical Field

[0001] The invention relates to the technical field of water quality inspection, and in particular to an intelligent online inspection system for inlet and outlet water quality of a water plant. Background Art

[0002] The Chinese invention patent with patent announcement number CN109382004B discloses a method for separating and recovering mixed heavy metals using a calcium alginate membrane, comprising: dissolving sodium alginate in water to obtain a casting solution, controlling the thickness of a scraping rod, and obtaining calcium alginate hydrogel membranes of different thicknesses through calcium ion crosslinking. Then, mixed aqueous solutions of heavy metal ions of different concentrations are prepared, the mixed aqueous solutions of heavy metal ions are used as a feed solution, and the calcium alginate hydrogel membrane is used as a filter membrane for filtration, and the different heavy metal ions are separated by using the difference in the exchange capacity between calcium alginate and different heavy metal ions. The heavy metal ions retained on the calcium alginate membrane are treated with an alkali solution hydrothermal method, filtered and burned to obtain recovered heavy metal oxides.

[0003] However, since the membrane separation performance of each sub-area inside the heavy metal treatment pool often varies, membrane pollution and clogging are the reasons for the unevenness of the heavy metal removal rate, which directly affects the heavy metal removal efficiency. In the above-mentioned prior art, there is a lack of analysis of the heavy metal treatment rate. The uneven heavy metal treatment rate may cause the heavy metal content and type in the water at the water plant outlet to not meet the requirements, and thus it is necessary to inspect the areas with uneven heavy metal treatment rates. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent online inspection system and system for the inlet and outlet water quality of a water plant to solve the technical problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The present invention provides an intelligent online inspection system for water quality of water inlet and outlet of a water plant, comprising:

[0007] Processing signal generation module: Analyze the heavy metal content and the number of heavy metal species in the water at the inlet to obtain the quality performance value CL, and determine whether the heavy metals in the water at the inlet need to be treated based on the quality performance value CL. If treatment is required, a treatment signal is generated;

[0008] Sub-area marking module: Based on the processing signal, the heavy metal removal rate is processed and analyzed within the processing cycle to obtain the removal rate deviation. The sub-area is marked based on the removal rate deviation. The marking results include abnormal sub-areas and normal sub-areas.

[0009] Abnormal signal generation module: Analyze and process the number of abnormal sub-areas removed and the removal rate deviation of the abnormal sub-areas removed to obtain the treatment performance value QJ. According to the treatment performance value QJ, it is judged whether the heavy metal removal rate in the heavy metal treatment pool is uniform. If it is not uniform, an abnormal signal is generated;

[0010] Recombination signal generation module: Based on the abnormal signal, the removal rate deviation of the abnormal sub-region is analyzed to obtain the first inspection sequence table, and the first inspection sequence table and the abnormal sub-region sequence table are analyzed to obtain the matching data group ratio. If 0≤matching data group ratio<1, a recombination signal is generated;

[0011] The second inspection sequence table generation module: based on the recombination signal, analyzes the elements in the unmatched data group to obtain the recombination number, and obtains the second sequence table based on the recombination number.

[0012] As a further solution of the present invention: the quality performance value CL is obtained in the following manner:

[0013] Obtain the heavy metal content and number of heavy metal species in the water at the inlet, and analyze to obtain the heavy metal content percentage ZH and the heavy metal species percentage ZZ;

[0014] The heavy metal content percentage ZH and the heavy metal species percentage ZZ are processed by the formula: The quality performance value CL of the water quality at the water plant inlet is calculated, where s1 and s2 are preset proportional coefficients, and both s1 and s2 are greater than 0.

[0015] As a further solution of the present invention: the heavy metal content percentage ZH and the heavy metal species percentage ZZ are obtained by:

[0016] Obtain the heavy metal content in the water at the inlet, and perform ratio processing on it with the content of all substances in the water at the inlet to obtain the heavy metal content ratio ZH;

[0017] The number of heavy metal species in the inlet water is counted, and the ratio is processed with the number of all substance types in the inlet water to obtain the heavy metal species ratio ZZ.

[0018] As a further solution of the present invention: the removal rate deviation is obtained in the following manner:

[0019] The internal area of ​​the heavy metal treatment pool is divided into several sub-areas according to the distance from the water inlet. The heavy metal removal rate in the sub-area is subtracted from the standard value of the heavy metal removal rate, and the absolute value of the difference is taken to obtain the removal rate deviation in the sub-area.

[0020] As a further solution of the present invention: the processing performance value QJ is obtained in the following manner:

[0021] Obtain the abnormal area quantity ratio YQ and abnormality degree value YC;

[0022] The abnormal area ratio YQ and the abnormal degree value YC are processed by the formula A processing performance value QJ is obtained, wherein a1 and a2 are both preset proportional coefficients, and a1 and a2 are both greater than 0.

[0023] As a further solution of the present invention: the abnormal area quantity ratio YQ and the abnormality degree value YC are obtained in the following manner:

[0024] Count the number of abnormal sub-regions removed and compare it with the total number of sub-regions to obtain the abnormal region ratio YQ;

[0025] Obtain the removal rate deviation of the abnormal sub-region, and perform difference processing on it and the removal rate deviation threshold to obtain the removal rate relative deviation, and sum and average the removal rate relative deviations of all the abnormal sub-regions to obtain the removal rate relative deviation mean, and perform ratio processing on the removal rate deviation threshold to obtain the abnormality degree value YC.

[0026] As a further solution of the present invention: the first inspection sequence table is obtained in the following manner:

[0027] The removal rate deviations of the abnormal sub-areas are sorted from large to small to obtain a first inspection sequence table.

[0028] As a further solution of the present invention: the method for obtaining the proportion of the matching data group is:

[0029] Mark the abnormal sub-areas in the first inspection sequence list as the first inspection area, the second inspection area, ..., the i-th inspection area, where i represents the number of the inspection area in the first inspection sequence list;

[0030] The abnormal sub-regions are marked in order from near to far from the water inlet as the first abnormal sub-region, the second abnormal sub-region, ..., the jth abnormal sub-region, to obtain a sequence table of abnormal sub-regions, where j represents the number of the abnormal sub-region;

[0031] Combine the first inspection area and the first abnormal area, the second inspection area and the second abnormal area, ..., the i-th inspection area and the j-th inspection area into a comparison data group;

[0032] If the position corresponding to the inspection area in the comparison data group is the same as the position corresponding to the abnormal sub-area in the comparison data group, the corresponding comparison data group is marked as a matching data group;

[0033] The number of matching data groups is counted and compared with the total number of comparison data groups to obtain the proportion of matching data groups.

[0034] As a further solution of the present invention: the second inspection sequence table is obtained in the following manner:

[0035] If the position corresponding to the inspection area in the comparison data group is different from the position corresponding to the abnormal sub-area in the comparison data group, the corresponding comparison data group is marked as an unmatched data group;

[0036] The abnormal sub-region numbers and mapping numbers in all unmatched data groups are summed and averaged to obtain the reorganization numbers, and the reorganization numbers are sorted from large to small to obtain the second inspection sequence table, and the abnormal sub-regions are inspected according to the second inspection sequence table.

[0037] As a further solution of the present invention: the method for obtaining the reorganization number is:

[0038] The mismatched data group when generating the reorganization signal is obtained, and the numbers in the abnormal sub-area sequence table with the same corresponding positions of the inspection areas in the mismatched data group are marked as mapping numbers.

[0039] Beneficial effects of the present invention:

[0040] (1) The present invention obtains a quality performance value CL based on heavy metal parameter processing analysis, and determines whether heavy metals in the water at the water inlet need to be treated based on the quality performance value CL. If treatment is required, a treatment signal is generated. The present invention is conducive to determining whether the content and type of heavy metals in the water need to exceed the standard by analyzing the heavy metal parameters in the water at the water inlet, so as to facilitate the subsequent treatment of heavy metals in the water;

[0041] (2) Based on the processing signal, the present invention obtains the membrane separation data of each sub-region inside the heavy metal treatment pool when the heavy metal treatment pool performs heavy metal treatment in real time during the treatment cycle, wherein the membrane separation data includes the heavy metal removal rate. Based on the processing and analysis of the membrane separation data, the removal rate deviation is obtained. The sub-region is marked based on the removal rate deviation. The marking result includes abnormal sub-regions and normal sub-regions. The number of removed abnormal sub-regions and the removal rate deviation of removed abnormal sub-regions are analyzed and processed to obtain a treatment performance value QJ. According to the treatment performance value QJ, it is determined whether the heavy metal removal rate in the heavy metal treatment pool is uniform. If it is not uniform, an abnormal signal is generated. The present invention collects the heavy metal removal rate of each sub-region inside the heavy metal treatment pool in real time, and then processes and analyzes the heavy metal removal rate to identify the sub-region with abnormal treatment efficiency, which is conducive to realizing accurate monitoring of the treatment process;

[0042] (3) The present invention analyzes the removal rate deviation of the abnormal sub-region based on the abnormal signal to obtain a first inspection sequence table, analyzes the first inspection sequence table and the abnormal sub-region sequence table to obtain the matching data group ratio, if 0≤matching data group ratio<1, then generates a recombination signal, based on the recombination signal, analyzes the elements in the unmatched data group to obtain the recombination number, and obtains the second sequence table based on the recombination number. The present invention optimizes the inspection route by conducting an in-depth analysis of the sub-region with abnormal removal rate in the heavy metal treatment pool and generating the first inspection sequence table and the second sequence table. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention will be further described below in conjunction with the accompanying drawings.

[0044] Figure 1 It is a system block diagram of the intelligent online inspection system for the inlet and outlet water quality of the water plant according to the present invention;

[0045] Figure 2 It is a flowchart of the quality performance value acquisition process of the intelligent online inspection system for the inlet and outlet water quality of the water plant described in the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of 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.

[0047] Example 1

[0048] See also Figure 1 , Figure 2 The intelligent online inspection system for water quality of water plant inlet and outlet according to the embodiment of the present invention comprises the following specific methods:

[0049] Processing signal generation module: collects heavy metal parameters in the water at the water inlet in real time, wherein the heavy metal parameters include the heavy metal content and the number of heavy metal species, obtains the quality performance value CL based on the heavy metal parameter processing and analysis, and determines whether the heavy metals in the water at the water inlet need to be processed based on the quality performance value CL. If processing is required, a processing signal is generated;

[0050] In some embodiments, the heavy metal content in the water at the inlet is obtained, and the ratio of the content of all substances in the water at the inlet is processed to obtain the heavy metal content percentage ZH;

[0051] Count the number of heavy metal species in the water at the inlet, and compare it with the number of all substances in the water at the inlet to obtain the heavy metal species ratio ZZ;

[0052] The heavy metal content percentage ZH and the heavy metal species percentage ZZ are processed by the formula: The quality performance value CL of the water quality at the water plant inlet is calculated, where s1 and s2 are both preset proportional coefficients, and both s1 and s2 are greater than 0, s1 is 0.42, and s2 is 0.57;

[0053] The acquisition process of s1 and s2 is as follows:

[0054] Obtain multiple groups of historical qualified data on the proportion of heavy metal content and the proportion of heavy metal species, organize these groups of historical qualified data on the proportion of heavy metal content and the proportion of heavy metal species to construct an evaluation matrix, calculate the proportion of heavy metal content and the proportion of heavy metal species in the corresponding group according to the entropy weight method, calculate the entropy value and information redundancy corresponding to the proportion of heavy metal content and the proportion of heavy metal species based on the definition of entropy, normalize the information redundancy of the proportion of heavy metal content and the proportion of heavy metal species, and obtain the weight coefficients of the heavy metal content and the proportion of heavy metal species, that is, the preset proportional coefficients s1 and s2 in this application.

[0055] Compare the quality performance value CL with the quality performance value threshold:

[0056] If the quality performance value CL is greater than or equal to the quality performance value threshold, it means that the heavy metal content in the water at the inlet is high, and a treatment signal is generated;

[0057] If the quality performance value CL is less than the quality performance value threshold, it means that the heavy metal content in the water at the inlet is low, and a no-treatment signal is generated;

[0058] The technical solution of the embodiment of the present invention is mainly as follows: real-time collection of heavy metal parameters in the water at the water inlet, wherein the heavy metal parameters include heavy metal content and the number of heavy metal species, quality performance value CL is obtained based on heavy metal parameter processing and analysis, and whether it is necessary to treat the heavy metals in the water at the water inlet is determined based on the quality performance value CL; if treatment is required, a treatment signal is generated. The present invention analyzes the heavy metal parameters in the water at the water inlet, which is conducive to determining whether the heavy metal content and type in the water exceed the standard, thereby facilitating subsequent treatment of the heavy metals in the water.

[0059] Example 2

[0060] Based on Example 1, please refer to Figure 1 As shown, the intelligent online inspection system for water quality of water plant inlet and outlet according to the embodiment of the present invention further includes the following steps:

[0061] Sub-area marking module: Based on the processing signal, within the processing cycle, the membrane separation data of each sub-area inside the heavy metal treatment pool when the heavy metal treatment pool is performing heavy metal treatment work is obtained in real time, wherein the membrane separation data includes the heavy metal removal rate, and the removal rate deviation is obtained based on the processing and analysis of the membrane separation data, and the sub-area is marked based on the removal rate deviation, and the marking results include abnormal sub-areas and normal sub-areas;

[0062] In some embodiments, the internal area of ​​the heavy metal treatment pool is divided into several sub-areas according to the distance from the water inlet, the heavy metal removal rate in the sub-area is subjected to difference processing with the standard value of the heavy metal removal rate, and the absolute value of the difference is taken to obtain the removal rate deviation in the sub-area;

[0063] It should be noted that the standard value of heavy metal removal rate is set by the staff in this field based on previous experience;

[0064] Compare the removal rate deviation within the subregion to the removal rate deviation threshold:

[0065] If the removal rate deviation in the sub-region is not equal to the removal rate deviation threshold, the sub-region is marked as an abnormal sub-region;

[0066] If the removal rate deviation in the sub-region is equal to the removal rate deviation threshold, the sub-region is marked as a normal sub-region;

[0067] Abnormal signal generation module: Analyze and process the number of abnormal sub-areas removed and the removal rate deviation of the abnormal sub-areas removed to obtain the treatment performance value QJ. According to the treatment performance value QJ, it is judged whether the heavy metal removal rate in the heavy metal treatment pool is uniform. If it is not uniform, an abnormal signal is generated;

[0068] Count the number of abnormal sub-regions removed and compare it with the total number of sub-regions to obtain the abnormal region ratio YQ;

[0069] Obtain the removal rate deviation of the abnormal sub-region, and perform difference processing on it and the removal rate deviation threshold to obtain the removal rate relative deviation, and sum and average the removal rate relative deviations of all the abnormal sub-regions to obtain the removal rate relative deviation mean, perform ratio processing on the removal rate relative deviation mean and the removal rate deviation threshold to obtain the abnormality degree value YC;

[0070] The abnormal area ratio YQ and the abnormal degree value YC are processed by the formula The processing performance value QJ is obtained, wherein a1 and a2 are both preset proportional coefficients, and both a1 and a2 are greater than 0, a1 is 0.51, and a2 is 0.49;

[0071] The acquisition process of a1 and a2 is as follows:

[0072] Obtain multiple groups of historical qualified data on the proportion of the number of abnormal areas and the degree of abnormality, organize the data on the proportion of the number of abnormal areas and the degree of abnormality of so many groups of historical qualified data to construct an evaluation matrix, calculate the proportion of the number of abnormal areas and the proportion of the degree of abnormality in the corresponding group according to the entropy weight method, calculate the entropy value and information redundancy corresponding to the proportion of the number of abnormal areas and the degree of abnormality based on the definition of entropy, normalize the information redundancy of the proportion of the number of abnormal areas and the degree of abnormality, and obtain the weight coefficients of the proportion of the number of abnormal areas and the degree of abnormality, that is, the preset proportional coefficients a1 and a2 in this application.

[0073] In some embodiments, the processing performance value QJ is compared with the processing performance value, and the specific comparison process is as follows:

[0074] If the treatment performance value QJ is greater than or equal to the treatment performance threshold, it means that the heavy metal removal rate in the heavy metal treatment tank is uneven, and an abnormal signal is generated;

[0075] If the treatment performance value QJ is less than the treatment performance threshold, it means that the heavy metal removal rate in the heavy metal treatment tank is uniform, and a treatment normal signal is generated;

[0076] The technical solution of the embodiment of the present invention is mainly as follows: based on the processing signal, within the processing cycle, the membrane separation data of each sub-region inside the heavy metal treatment pool when the heavy metal treatment work is performed is obtained in real time, wherein the membrane separation data includes the heavy metal removal rate, based on the processing and analysis of the membrane separation data, the removal rate deviation is obtained, the sub-region is marked based on the removal rate deviation, the marking result includes the abnormal sub-region and the normal sub-region, the number of the removed abnormal sub-regions and the removal rate deviation of the removed abnormal sub-regions are analyzed and processed to obtain the processing performance value QJ, and the heavy metal removal rate in the heavy metal treatment pool is judged according to the processing performance value QJ. If it is not uniform, an abnormal signal is generated. The present invention collects the heavy metal removal rate of each sub-region inside the heavy metal treatment pool in real time, and then processes and analyzes the heavy metal removal rate to identify the sub-region with abnormal processing efficiency, which is conducive to realizing accurate monitoring of the processing process.

[0077] Example 3

[0078] Based on Example 2, please refer to Figure 1 The intelligent online inspection system for water quality of water plant inlet and outlet according to the embodiment of the present invention further includes the following specific methods:

[0079] Recombination signal generation module: Based on the abnormal signal, the removal rate deviation of the abnormal sub-region is analyzed to obtain the first inspection sequence table, and the first inspection sequence table and the abnormal sub-region sequence table are analyzed to obtain the matching data group ratio. If 0≤matching data group ratio<1, a recombination signal is generated;

[0080] Sort the removal rate deviations of the abnormal sub-areas from large to small to obtain a first inspection sequence list;

[0081] Mark the abnormal sub-areas in the first inspection sequence list as the first inspection area, the second inspection area, ..., the i-th inspection area, where i represents the number of the inspection area in the first inspection sequence list;

[0082] The abnormal sub-regions are marked in order from near to far from the water inlet as the first abnormal sub-region, the second abnormal sub-region, ..., the jth abnormal sub-region, to obtain a sequence table of abnormal sub-regions, where j represents the number of the abnormal sub-region;

[0083] Combine the first inspection area and the first abnormal area, the second inspection area and the second abnormal area, ..., the i-th inspection area and the j-th inspection area into a comparison data group;

[0084] If the position corresponding to the inspection area in the comparison data group is the same as the position corresponding to the abnormal sub-area in the comparison data group, the corresponding comparison data group is marked as a matching data group;

[0085] If the position corresponding to the inspection area in the comparison data group is different from the position corresponding to the abnormal sub-area in the comparison data group, the corresponding comparison data group is marked as an unmatched data group;

[0086] Count the number of matching data groups, and compare it with the total number of comparison data groups to obtain the proportion of matching data groups;

[0087] If 0≤the proportion of matching data groups<1, a recombination signal is generated;

[0088] If the matching data group ratio = 1, the abnormal sub-area is inspected according to the first inspection sequence list;

[0089] A second inspection sequence table generating module: based on the recombination signal, analyzing the elements in the unmatched data group to obtain the recombination number, and based on the recombination number, obtaining the second sequence table;

[0090] It should be noted that the elements of the unmatched data group include the inspection area and the abnormal sub-area;

[0091] Obtaining the mismatched data group when generating the reorganization signal, marking the number in the abnormal sub-area sequence table with the same corresponding position of the inspection area in the mismatched data group as the mapping number;

[0092] The abnormal sub-region numbers and the mapping numbers in all the unmatched data groups are summed and averaged to obtain the reorganization numbers, the reorganization numbers are sorted from large to small to obtain the second inspection sequence list, and the abnormal sub-regions are inspected according to the second inspection sequence list;

[0093] It should be noted that if the reorganization numbers are the same, the inspection areas corresponding to the reorganization numbers are sorted in the first inspection sequence table according to their numbering order;

[0094] The technical solution of the embodiment of the present invention is mainly as follows: based on the abnormal signal, the removal rate deviation of the abnormal sub-area is analyzed to obtain the first inspection sequence table, the first inspection sequence table and the abnormal sub-area sequence table are analyzed to obtain the matching data group ratio, if 0≤matching data group ratio<1, a recombination signal is generated, based on the recombination signal, the elements in the mismatching data group are analyzed to obtain the recombination number, and based on the recombination number, a second sequence table is obtained. The present invention is beneficial to optimizing the inspection route by conducting an in-depth analysis of the sub-area with abnormal removal rate in the heavy metal treatment pool and generating the first inspection sequence table and the second sequence table.

[0095] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. Intelligent online inspection system for water quality in and out of water plants, characterized by: include: Processing signal generation module: Analyze the heavy metal content and the number of heavy metal species in the water at the inlet to obtain the quality performance value CL, and determine whether the heavy metals in the water at the inlet need to be treated based on the quality performance value CL. If treatment is required, a treatment signal is generated; The quality performance value CL is obtained as follows: Obtain the heavy metal content and number of heavy metal species in the water at the inlet, and analyze to obtain the heavy metal content percentage ZH and the heavy metal species percentage ZZ; The heavy metal content percentage ZH and the heavy metal species percentage ZZ are processed by the formula: The quality performance value CL of the water quality at the water plant inlet is calculated, where s1 and s2 are both preset proportional coefficients, and both s1 and s2 are greater than 0; Sub-area marking module: Based on the processing signal, the heavy metal removal rate is processed and analyzed within the processing cycle to obtain the removal rate deviation. The sub-area is marked based on the removal rate deviation. The marking results include abnormal sub-areas and normal sub-areas. Abnormal signal generation module: Analyze and process the number of abnormal sub-areas removed and the removal rate deviation of the abnormal sub-areas removed to obtain the treatment performance value QJ. According to the treatment performance value QJ, it is judged whether the heavy metal removal rate in the heavy metal treatment pool is uniform. If it is not uniform, an abnormal signal is generated; The processing performance value QJ is obtained as follows: Obtain the abnormal area quantity ratio YQ and abnormality degree value YC; The abnormal area ratio YQ and the abnormal degree value YC are processed by the formula A processing performance value QJ is obtained, wherein a1 and a2 are both preset proportional coefficients, and a1 and a2 are both greater than 0; Recombination signal generation module: Based on the abnormal signal, the removal rate deviation of the abnormal sub-region is analyzed to obtain the first inspection sequence table, and the first inspection sequence table and the abnormal sub-region sequence table are analyzed to obtain the matching data group ratio. If 0≤matching data group ratio<1, a recombination signal is generated; The second inspection sequence table generation module: based on the recombination signal, analyzes the elements in the unmatched data group to obtain the recombination number, and obtains the second sequence table based on the recombination number.

2. The intelligent online inspection system for water quality in and out of a water plant according to claim 1 is characterized in that: The method for obtaining the heavy metal content percentage ZH and the heavy metal species percentage ZZ is as follows: Obtain the heavy metal content in the water at the inlet, and perform ratio processing on it with the content of all substances in the water at the inlet to obtain the heavy metal content ratio ZH; The number of heavy metal species in the inlet water is counted, and the ratio is processed with the number of all substance types in the inlet water to obtain the heavy metal species ratio ZZ.

3. The intelligent online inspection system for water quality of water plant inlet and outlet according to claim 1 is characterized in that: The removal rate deviation is obtained as follows: The internal area of ​​the heavy metal treatment pool is divided into several sub-areas according to the distance from the water inlet. The heavy metal removal rate in the sub-area is subtracted from the standard value of the heavy metal removal rate, and the absolute value of the difference is taken to obtain the removal rate deviation in the sub-area.

4. The intelligent online inspection system for water quality in and out of a water plant according to claim 1 is characterized in that: The abnormal area quantity ratio YQ and the abnormality degree value YC are obtained as follows: Count the number of abnormal sub-regions removed and compare it with the total number of sub-regions to obtain the abnormal region ratio YQ; Obtain the removal rate deviation of the abnormal sub-region, and perform difference processing on it and the removal rate deviation threshold to obtain the removal rate relative deviation, and sum and average the removal rate relative deviations of all the abnormal sub-regions to obtain the removal rate relative deviation mean, and perform ratio processing on the removal rate deviation threshold to obtain the abnormality degree value YC.

5. The intelligent online inspection system for water quality of water plant inlet and outlet according to claim 3 is characterized in that: The first inspection sequence table is obtained in the following manner: The removal rate deviations of the abnormal sub-areas are sorted from large to small to obtain a first inspection sequence table.

6. The intelligent online inspection system for water quality of water plant inlet and outlet according to claim 5 is characterized in that: The method for obtaining the proportion of the matching data group is as follows: Mark the abnormal sub-areas in the first inspection sequence list as the first inspection area, the second inspection area, ..., the i-th inspection area, where i represents the number of the inspection area in the first inspection sequence list; The abnormal sub-regions are marked in order from near to far from the water inlet as the first abnormal sub-region, the second abnormal sub-region, ..., the jth abnormal sub-region, to obtain a sequence table of abnormal sub-regions, where j represents the number of the abnormal sub-region; Combine the first inspection area and the first abnormal area, the second inspection area and the second abnormal area, ..., the i-th inspection area and the j-th inspection area into a comparison data group; If the position corresponding to the inspection area in the comparison data group is the same as the position corresponding to the abnormal sub-area in the comparison data group, the corresponding comparison data group is marked as a matching data group; The number of matching data groups is counted and compared with the total number of comparison data groups to obtain the proportion of matching data groups.

7. The intelligent online inspection system for water quality of water plant inlet and outlet according to claim 6 is characterized in that: The second inspection sequence table is obtained in the following manner: If the position corresponding to the inspection area in the comparison data group is different from the position corresponding to the abnormal sub-area in the comparison data group, the corresponding comparison data group is marked as an unmatched data group; The abnormal sub-region numbers and mapping numbers in all unmatched data groups are summed and averaged to obtain the reorganization numbers, and the reorganization numbers are sorted from large to small to obtain the second inspection sequence table, and the abnormal sub-regions are inspected according to the second inspection sequence table.

8. The intelligent online inspection system for water quality of water plant inlet and outlet according to claim 7 is characterized in that: The method for obtaining the reorganization number is as follows: The mismatched data group when generating the reorganization signal is obtained, and the numbers in the abnormal sub-area sequence table with the same corresponding positions of the inspection areas in the mismatched data group are marked as mapping numbers.

Images