A sewage treatment data traceability method and system

Abstract

The present application relates to the technical field of sewage treatment, and provides a sewage treatment data tracing method and system, the method comprising: adding a batch identifier of a whole sludge treatment process for sludge of several treatment units in a sludge treatment process of a sewage treatment plant; collecting operation data and operation information of the sludge during the process of flowing through the treatment units; after integrating the operation data and the operation information, binding the integrated operation data and operation information with the corresponding batch identifier to generate a material experience chain; monitoring an operation index of a terminal treatment link of the sludge treatment process in real time; when the operation index is abnormal, performing reverse query based on a batch identifier of sludge corresponding to the terminal treatment link; reading the corresponding material experience chain according to a result of the reverse query to determine a cause of the abnormal operation index. The present application has the effect of improving the efficiency of fault troubleshooting and process optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sewage treatment, and in particular to a sewage treatment data tracing method and system. BACKGROUND

[0002] A large sewage treatment plant is usually equipped with a complete sludge treatment and disposal chain, such as sludge concentration, mechanical dewatering, thermal drying, and final incineration, etc., aiming to achieve sludge reduction, stabilization treatment and resource utilization. In the entire sludge treatment process, corresponding online monitoring instruments are arranged at each key node to collect sludge flow, concentration, moisture content, temperature and other operation data. At the same time, the operating team also records in detail the brand, specification, batch number, consumption of the chemicals used, as well as the operating state, operation adjustment and other information of the main equipment. Part of these data and information is automatically collected through the automation system, and the other part is recorded and entered manually.

[0003] However, the prior art faces many challenges in processing these operation data and material information from different treatment units, different monitoring means, different recording formats and inconsistent time recording accuracy. The formats of these heterogeneous data are not unified, the accuracy of the time stamps is uneven, and there is a lack of internal and automatic logical correlation mechanism. When the end link of the sludge treatment process appears abnormal operation indicators, such as continuous increase of the auxiliary fuel consumption of the incinerator, the prior art has difficulty in effectively integrating and correlating the data of each upstream link, and in quickly and accurately constructing the complete influence chain from the front-end working condition change, sludge property evolution, auxiliary material use difference to equipment operating state change. The process of manually tracing and analyzing cross-link data is complex, time-consuming and prone to errors. Especially when the underlying data itself has potential errors or the manual records are incomplete, the reliability of the tracing analysis conclusion based on these data will be greatly reduced, and it is difficult to accurately find out the root cause of the abnormality or the result of the joint action of multiple situations, thereby affecting the efficiency of problem solving and the effect of process optimization.

[0004] The prior art needs to be improved in view of the above problems. SUMMARY

[0005] The purpose of the present application is to provide a sewage treatment data tracing method and system, which has the advantages of being able to effectively integrate and correlate heterogeneous data in the sludge treatment process, quickly construct a material experience chain, and efficiently and accurately trace back when the end indicators are abnormal, so as to quickly locate the problem cause and improve the efficiency of fault troubleshooting and process optimization.

[0006] The present application provides a sewage treatment data tracing method, and the technical solution is as follows:

[0007] Comprising:

[0008] A batch identifier of the sludge treatment whole process is added to the sludge of several treatment units in the sludge treatment process of the same batch;

[0009] Operation data and operation information of the sludge during the process of flowing through the treatment units are collected;

[0010] After the operation data and the operation information are integrated, the operation data and the operation information are bound to the corresponding batch identifier, and a material experience chain is generated;

[0011] Operation indexes of an end treatment link of the sludge treatment process are monitored in real time;

[0012] When the operation indexes are abnormal, the batch identifier of the sludge corresponding to the end treatment link is reversely queried;

[0013] According to the result of the reverse query, the corresponding material experience chain is read to determine the cause of the abnormal operation indexes.

[0014] Through the above scheme, heterogeneous data in the sludge treatment process can be effectively integrated and associated, the material experience chain can be quickly constructed, and efficient and accurate reverse tracing can be performed when the end indexes are abnormal, so that the problem cause can be quickly located, and the efficiency of fault troubleshooting and process optimization is improved.

[0015] Further, the application further proposes that the step of integrating the operation data and the operation information and binding the operation data and the operation information to the corresponding batch identifier to generate the material experience chain further comprises:

[0016] A sensitive period of sludge characteristics change of the sludge of the same batch in the sludge treatment process is identified;

[0017] If the operation data in the material experience chain are collected in the sensitive period of the sludge characteristics change, a first risk mark is added to the operation data;

[0018] The operation information in the material experience chain is compared with a preset auxiliary record, and if the comparison result shows inconsistency, a second risk mark is added to the operation information;

[0019] The step of reverse query comprises:

[0020] When the operation data with the first risk mark or the operation information with the second risk mark is queried, the operation data or the operation information with the mark is displayed differently;

[0021] Auxiliary verification information corresponding to the operation data or the operation information is called.

[0022] Through the above scheme, by identifying the sensitive period and adding the risk mark, and comparing the operation information with the auxiliary record and adding the risk mark, the potential risk points can be highlighted, and the accuracy and reliability of the traceability can be improved through the auxiliary verification information.

[0023] Further, the application also proposes that, according to the result of the reverse query, the step of reading the corresponding material experience chain to determine the cause of the abnormal operation index includes:

[0024] reading the auxiliary verification information and the unmarked data in the material experience chain;

[0025] According to the auxiliary verification information and the unmarked data in the material experience chain, the cause of the abnormal operation index is evaluated and determined.

[0026] Through the above scheme, combined with auxiliary verification information and unmarked data for evaluation, the abnormal cause can be more comprehensively and accurately determined, avoiding the one-sidedness caused by relying only on marked data.

[0027] Further, the application also proposes that the step of identifying the sensitive period of sludge characteristics change of sludge in the sludge treatment process includes:

[0028] Obtaining sludge characteristic change type data, online monitoring instrument type data, and historical record of reading deviation mode data of different online monitoring instrument types under different sludge characteristic change types in the sludge treatment process;

[0029] Based on the sludge characteristic change type data, the online monitoring instrument type data, and the reading deviation mode data, the corresponding relationship information between the data and the preset sensitive period identification rule is established;

[0030] When the preset trigger condition indicates that the sludge characteristics change, based on the corresponding relationship information, the sludge characteristic change type data and the online monitoring instrument type data at that time are used to find the matching sensitive period identification rule;

[0031] Using the sensitive period identification rule, the sensitive period of sludge characteristics change of sludge of the same batch is determined.

[0032] Through the above scheme, by establishing the corresponding relationship between the data and the sensitive period identification rule, and based on the trigger condition to find the rule, the sensitive period of sludge characteristics change can be automatically and intelligently identified, improving the accuracy and efficiency of sensitive period identification.

[0033] Further, the application also proposes that, based on the sludge characteristic change type data, the online monitoring instrument type data, and the reading deviation mode data, the step of establishing the corresponding relationship information between the data and the preset sensitive period identification rule includes:

[0034] Using the sludge characteristic change type data, the online monitoring instrument type data, and the reading deviation mode data, initial corresponding relationship data between the data and the preset sensitive period identification rule is formed;

[0035] Monitor changes in any of the following: the operating parameters of the wastewater treatment plant, the configuration information of online monitoring instruments, or the influent water quality indicators; when a change reaches a preset condition, record the change as a change event.

[0036] When a change event occurs, based on the preset association logic, the range of the change event affecting the sludge characteristic change type data and the online monitoring instrument type data is determined and mapped to the initial corresponding relationship data;

[0037] The specific entries generated by mapping in the initial correspondence data are updated based on the new sludge characteristic change type data, online monitoring instrument type data, and reading deviation pattern data, or the correspondence adjustment strategy preset for the change event type and impact range;

[0038] The initial correspondence data is adjusted by updating specific entries in the initial correspondence data, and the initial correspondence data with the adjusted specific entries is used as the correspondence information.

[0039] By monitoring change events and dynamically updating the corresponding relationship information, the above-mentioned scheme can make the sensitive period identification rules more adaptable to actual operational changes, thereby improving the accuracy and timeliness of the rules.

[0040] Furthermore, this application also proposes steps for adjusting the pre-defined correspondence strategy for the change event type and its scope of impact, including:

[0041] Configure source attributes for all preset adjustment strategies;

[0042] Analyze the content of the preset adjustment strategy and check for any conflicts.

[0043] If the detection results indicate a conflict, the preset adjustment strategy with the highest priority is selected as the corresponding relationship adjustment strategy based on the priority determined by the source attribute of each preset adjustment strategy, or all preset adjustment strategies with conflicts are integrated and used as the corresponding relationship adjustment strategy according to the preset fusion rules.

[0044] By configuring source attributes, detecting conflicts, and handling conflicts according to priority or fusion rules, the effectiveness and consistency of the corresponding relationship adjustment strategy can be ensured, and problems caused by strategy conflicts can be avoided.

[0045] Furthermore, this application also proposes a step of integrating all conflicting preset adjustment strategies and using them as corresponding relationship adjustment strategies according to preset fusion rules, including:

[0046] Read all conflicting preset adjustment strategies;

[0047] The conflicting preset adjustment strategies are broken down into several strategy fragments;

[0048] identify conflict points between the policy fragments based on the policy fragments;

[0049] screen all the policy fragments based on the conflict points according to the preset conflict resolution rule and the confidence information or the applicability matching degree information of the policy fragments, and select conflict-free policy fragments or policy fragments whose conflicts have been resolved;

[0050] recombine the conflict-free policy fragments or the policy fragments whose conflicts have been resolved, and generate a new adjustment policy as the corresponding relationship adjustment policy according to a fusion rule.

[0051] Through the above scheme, through the decomposition of the policy fragments, the identification of the conflict points, the screening and recombination based on the rule and the confidence / applicability, the fine conflict resolution and fusion of the complex policy can be realized, and a better adjustment policy is generated.

[0052] Further, the application further proposes that the step of screening all the policy fragments based on the conflict points according to the preset conflict resolution rule and the confidence information or the applicability matching degree information of the policy fragments, and selecting conflict-free policy fragments or policy fragments whose conflicts have been resolved comprises:

[0053] define a quantitative evaluation index for the adjustment claim corresponding to the policy fragment;

[0054] According to the preset conflict resolution rule and the confidence information or the applicability matching degree information corresponding to the policy fragment, the quantitative evaluation index value of the corresponding adjustment claim is calculated for the conflict point.

[0055] According to a preset comparison criterion, the quantitative evaluation index values are compared to select conflict-free policy fragments or policy fragments whose conflicts have been resolved.

[0056] Through the above scheme, by defining the quantitative evaluation index and calculating and comparing, the advantages and disadvantages of different policy fragments can be objectively and quantitatively evaluated, and a scientific basis is provided for conflict resolution and screening.

[0057] Further, the application further proposes that the step of calculating the quantitative evaluation index value of the corresponding adjustment claim for the conflict point according to the preset conflict resolution rule and the confidence information or the applicability matching degree information corresponding to the policy fragment comprises:

[0058] obtain the confidence information, the applicability matching degree information corresponding to each policy fragment with conflicts, and the attribute value of the conflict point itself;

[0059] match the weights of the confidence information, the applicability matching degree information, and the attribute value of the conflict point itself;

[0060] Sum the confidence information after matching the weight, the applicability matching degree information and the attribute value of the conflict point itself to obtain the corresponding quantitative evaluation index value.

[0061] Through the above scheme, by acquiring the confidence, applicability and conflict point attributes and weighted summation, various factors can be considered comprehensively, the value of the strategy fragment is evaluated more comprehensively, and the accuracy of quantitative evaluation is improved.

[0062] As can be seen from the above, the sewage treatment data traceability method provided by the application solves the problems of difficult data association and difficult traceability in the prior art by adding batch identification to sludge, collecting data information, generating a material experience chain and performing reverse query when the end is abnormal, has the advantages that heterogeneous data in the sludge treatment process can be effectively integrated and associated, a material experience chain can be quickly constructed, and efficient and accurate reverse tracing can be performed when the end index is abnormal, so that the problem cause can be quickly located, and the efficiency of fault troubleshooting and process optimization is improved.

[0063] The application also provides a sewage treatment data traceability system, and the technical scheme is as follows:

[0064] A sewage treatment data traceability system for performing sewage treatment data traceability, comprising:

[0065] A batch identification adding module for adding batch identification of the whole sludge treatment process to the sludge of a plurality of treatment units in the sludge treatment process of the sewage treatment plant for the same batch;

[0066] A data information collecting module for collecting operation data and operation information of the sludge during the flow through the treatment units;

[0067] An experience chain generating module for binding the integrated operation data and operation information to the corresponding batch identification to generate a material experience chain;

[0068] An operation index monitoring module for monitoring the operation index of the end treatment link of the sludge treatment process in real time;

[0069] A reverse query module for performing reverse query based on the batch identification of the sludge of the end treatment link when the operation index is abnormal;

[0070] An abnormal reason confirming module for reading the corresponding material experience chain according to the result of reverse query to determine the cause of the abnormal operation index.

[0071] Through the above scheme, a system for implementing the above method is provided, which has a modular structure and is convenient to implement and deploy. BRIEF DESCRIPTION OF DRAWINGS

[0072] Figure 1A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0073] Figure 2 A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0074] Figure 3 A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0075] Figure 4 A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0076] Figure 5 A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0077] Figure 6 A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0078] Figure 7 A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0079] Figure 8 A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0080] Figure 9 A method flow chart of a sewage treatment data traceability method in one embodiment of the present application;

[0081] Figure 10 A system block diagram of a sewage treatment data traceability system in one embodiment of the present application. DETAILED DESCRIPTION

[0082] The technical solutions in the present application will be described below in conjunction with the drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. The components of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0083] It should be noted that similar reference numerals and letters refer to like items throughout the accompanying drawings, and once an item is defined in one drawing, it is not necessary to further define and explain it in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", and the like are only used to distinguish description, and cannot be understood as indicating or implying relative importance.

[0084] In the sludge treatment process of a conventional sewage treatment plant, the data acquisition mode, record format and timestamp precision of each unit are different due to the involvement of multiple treatment units, resulting in scattered and heterogeneous operation data and operation information. When the operation index of the end treatment link appears abnormal, it is difficult to effectively integrate these heterogeneous data and establish a clear traceability path, so as to quickly and accurately determine the root cause of the abnormality. This data island and lack of association problem seriously affects the problem positioning efficiency and processing timeliness under abnormal conditions.

[0085] To this end, the present application provides a sewage treatment data traceability method, which combines Figure 1 as shown, comprising:

[0086] S1, for the same batch of sludge in several treatment units in the sludge treatment process of a sewage treatment plant, adding a batch identifier of the whole sludge treatment process;

[0087] S2, collecting operation data and operation information of the sludge during flowing through the treatment units;

[0088] S3, after integrating the operation data and operation information, binding them with the corresponding batch identifier to generate a material experience chain;

[0089] S4, real-time monitoring the operation index of the end treatment link of the sludge treatment process;

[0090] S5, when the operation index appears abnormal, reverse query based on the batch identifier of the corresponding sludge of the end treatment link;

[0091] S6, according to the result of reverse query, reading the corresponding material experience chain to determine the cause of the abnormal operation index.

[0092] Wherein, the batch identification refers to an identity mark for uniquely identifying the same batch of sludge in the entire treatment process, which can be realized in the form of digital coding, letter coding, combination of digital and letter coding, or two-dimensional code, etc., for example, a string containing date, shift and processing unit sequence is used as the batch identification, which is mainly to realize the association and traceability of the relevant data of the specific batch of sludge; the processing unit refers to each process link or equipment in the sludge treatment process of the sewage treatment plant, which can be realized by thickening tank, dewatering machine, drying equipment or incinerator, etc., which is mainly used for physical, chemical or thermal treatment of sludge; the material experience chain refers to a data set formed by binding the operation data and operation information collected during the flow of the same batch of sludge through each processing unit with the corresponding batch identification, which can be stored and managed in the form of database records, data files or blockchains, etc., which is mainly used to record the complete process information of the specific batch of sludge in the treatment process; the end processing link refers to the last one or several process links of the sludge treatment process, which can be realized by drying unit, incineration unit or final disposal unit, etc., which is mainly used to evaluate the final effect of the entire sludge treatment process; the reverse query refers to the process of finding the data and information of the upstream processing link associated with the batch identification in the material experience chain according to the batch identification of the corresponding sludge of the end processing link, which can be realized by using database query statements, data indexing or graph analysis technology, etc., which is mainly used to trace the potential causes of abnormal end operation indicators.

[0093] The core innovation of the present application is that by binding the batch identification of the sludge treatment whole process with the collected operation data and operation information, the material experience chain is generated, so that when the end operation indicator is abnormal, the reverse query can be carried out based on the batch identification, achieving the effect of quickly locating the abnormal reason.

[0094] The scheme of the present application enables the operation data and operation information originally scattered in different processing units, different monitoring systems and different recording methods to be effectively associated by adding a batch identifier throughout the whole process for the same batch of sludge. Based on this association, the collected operation data and operation information are bound with the corresponding batch identifier, thereby constructing a complete material experience chain of the batch of sludge in the whole treatment process. Since the operation index of the end treatment link is a direct reflection of the treatment effect of the whole process, when the index is abnormal, the batch identifier corresponding to the abnormal sludge can be used to quickly trace back in the generated material experience chain. By reading and analyzing this specific material experience chain, the operation state and operation details of the batch of sludge in each processing unit can be clearly traced back, thereby systematically investigating the upstream factors that may cause the end index to be abnormal, and finally determining the root cause of the problem. It is precisely because of the establishment of this end-to-end data association and reverse tracing mechanism based on the batch identifier that the abnormal cause can be quickly and accurately located in the complex and variable sludge treatment process, avoiding inefficient manual investigation in massive heterogeneous data.

[0095] In some preferred embodiments, for the sludge discharged from the secondary sedimentation tank for the same batch, a unique batch identifier is assigned to it before it enters the thickening tank, for example, "20231026-A001". During the process of the sludge flowing through the processing units such as the thickening tank, the dewatering machine, the drying device and the incinerator in turn, the operation data and operation information such as the sludge flow, the concentration, the dosage of reagent, the running parameters of the equipment (such as speed, temperature, pressure), the adjustment records of the operators, etc. collected automatically or recorded manually are associated with the batch identifier "20231026-A001" and stored. These associated data collectively constitute the material experience chain of the batch "20231026-A001", which is stored in a central database. The end operation index such as the auxiliary fuel consumption of the incinerator is monitored in real time. When it is found that the auxiliary fuel consumption continues to abnormally increase, the batch identifier of the sludge currently entering the incinerator is obtained, for example, "20231026-A001". Based on this batch identifier, a reverse query is performed in the database to retrieve the complete material experience chain of the batch "20231026-A001". By analyzing the data such as the residence time of the thickening tank, the running parameters of the dewatering machine, the temperature curve of the drying device, the reagent dosage record, etc. recorded in the experience chain, it can be systematically investigated which link or factor may cause the sludge entering the incinerator to have a high moisture content, thereby determining the reason for the abnormal increase of the auxiliary fuel consumption.

[0096] Optionally, in combination with Figure 2 As shown in FIG. 3, after the step of S3 of integrating the operation data and operation information and binding with the corresponding batch identifier to generate the material experience chain, the method further includes:

[0097] S31, Identify the sensitive period of sludge characteristic changes in the same batch of sludge during the sludge treatment process;

[0098] S32, If the material experiences operational data collection during a sensitive period of sludge characteristic changes in the chain, then add a first risk marker to the operational data;

[0099] S33, compare the operation information in the material experience chain with the preset auxiliary records; if the comparison results show inconsistencies, add a second risk mark to the operation information;

[0100] The steps for reverse lookup in S5 include:

[0101] When querying operational data marked with the first risk or operational information marked with the second risk, the operational data or operational information marked with the risk will be displayed differently.

[0102] Retrieve auxiliary verification information corresponding to the running data or operation information.

[0103] The sensitive period for changes in sludge characteristics refers to a specific time period or treatment stage in the sludge treatment process where the physical, chemical, or biological characteristics of sludge are relatively prone to significant changes. This period can be identified using methods such as historical data analysis, process experience judgment, or online monitoring data fluctuation analysis. The first and second risk markers are identifiers used to identify operational data or information in the material journey chain that may contain inaccurate data or incorrect operation records. These can be implemented using specific flag bits in data fields, additional metadata tags, or independent risk level fields. Pre-set auxiliary records refer to other records or information sources that are pre-set and collected, in addition to normal automated data collection and operation information recording, to help verify the authenticity and accuracy of operational information in the material journey chain. These can include manually filled-out shift logs, paper or electronic reagent requisition forms, equipment maintenance records, laboratory sampling reports, on-site photos or video recordings, etc. Auxiliary verification information refers to supplementary data or records associated with specific operational data or information in the material journey chain, which can be used to further verify its accuracy or provide additional background information. This can include operational data from other related equipment within the same time period, cross-validation data of the same parameter from different monitoring instruments, historical trend data, detailed explanations from operators, and knowledge entries from expert experience bases. Differentiated display refers to presenting operational data or information with risk markers in a way that differs from conventional data or information in the user interface or report, in order to draw the user's special attention. This can be achieved by changing font color, background color, adding prominent labels, flashing prompts, or pop-up warning messages.

[0104] In some preferred embodiments, the application is implemented as follows. First, in the sludge treatment process, the sensitive period in which the sludge characteristics are prone to change, such as the sludge staying in the thickening tank for too long or the mixing being uneven after adding flocculants before dewatering, can be identified according to historical operation data analysis, process expert experience, or preset trigger conditions based on fluctuations in influent water quality, biochemical system adjustments, etc. For example, when the influent organic load suddenly increases, causing the biochemical system to adjust, the subsequent generated sludge may fluctuate in dewatering performance, and at this time, the time period during which the batch of sludge flows through the dewatering unit can be marked as the sensitive period. Then, when the material experience chain is generated, the system can check the collection timestamp of each piece of operation data, and if the timestamp falls within the identified sensitive period of sludge characteristic change, a first risk flag is automatically added to the piece of operation data, such as setting a Boolean field "SensitivePeriodFlag" in the database and setting its value to true. At the same time, the system can periodically or after the operation information is entered, compare the operation information (such as PAM dosage, equipment start-stop time) in the material experience chain with the preset auxiliary records (such as the shift log handwritten by the operator, the drug consumption record). This comparison can be achieved through keyword matching, time period checking, or numerical range checking. If the comparison result shows that the operation information is inconsistent with the auxiliary record (for example, the system records a large difference in PAM dosage compared to the consumption recorded in the manual log), a second risk flag is added to the piece of operation data, such as setting another Boolean field "AuxiliaryCheckFlag" in the database and setting its value to true. When the end operation index anomaly triggers the reverse query, the system can check whether each piece of data or operation information has the first risk flag or the second risk flag when displaying the material experience chain on the user interface. If it has a flag, the item is displayed in a prominent way, such as changing the background color to yellow or red, or displaying a warning icon next to it. When the user clicks on the data or information with the flag, the system can automatically retrieve the corresponding auxiliary verification information, such as displaying the laboratory mud cake moisture content inspection report, the operator's written description of the dewatering effect, or the mud cake photo taken on site at the same period, for the user to refer to and judge.

[0105] Optionally, in combination with Figure 3 As shown in S6, according to the results of the reverse query, the step of reading the corresponding material experience chain to determine the cause of the operation index anomaly includes:

[0106] S61, reading the auxiliary verification information and the unmarked data in the material experience chain;

[0107] S62, according to the auxiliary verification information and the unmarked data in the material experience chain, evaluating and determining the cause of the operation index anomaly.

[0108] wherein the auxiliary verification information refers to additional reference information called for further verifying or supplementing the operation data and operation information in the material experience chain, and can specifically include equipment maintenance records, historical operation data, laboratory analysis sheets, equipment shift reports, reagent replacement records, handwritten operation logs, etc., and the purpose thereof is to provide more comprehensive background information and external evidence to help analyze the reliability of the data in the material experience chain or explain the reasons for the changes; the unmarked data in the material experience chain refers to those operation data and operation information in the material experience chain that are not identified as risk data (i.e., not added with the first risk mark or the second risk mark), and can specifically include operation data collected in a non-sensitive period, operation information consistent with the preset auxiliary records, etc., and the purpose thereof is to provide the operation parameters and operation records of the sludge treatment process under normal or relatively normal conditions as a benchmark or reference when evaluating the reasons for the abnormality; evaluating and determining the reasons for the abnormality of the operation index refers to identifying one or more root causes or inducing conditions that cause the abnormality of the end operation index through comprehensive analysis, comparison and reasoning of the read auxiliary verification information and the unmarked data in the material experience chain, and can specifically be performed through cross-validation, trend analysis, correlation judgment, etc., and the purpose thereof is to accurately pinpoint the root cause of the problem from the complex data relationships.

[0109] In some preferred embodiments, the present application is implemented as follows: when an abnormality is detected in an operation index of a treatment link at the end of a sludge treatment process, and a reverse query is performed based on the batch identification of the corresponding sludge, the system reads the material experience chain related to the query result. Assuming that during the reverse query, some operation data in the material experience chain (for example, the moisture content of the dewatered cake) are added with a first risk mark and displayed differently due to being in a sensitive period of sludge property change according to previous treatment, while auxiliary verification information related to the treatment of the batch of sludge is called, such as the maintenance record of the dewatering machine one week before the abnormality, the batch information of the PAM agent used for the batch of sludge, and the handwritten record of the operator about the viscosity of the batch of PAM. At this time, the present scheme reads these called auxiliary verification information, and reads the data in the material experience chain that are not marked, such as the sludge inlet flow of the dewatering machine, the drum rotation speed, the screw conveyor differential rotation speed, and other operation parameters, as well as the inlet and outlet temperatures of the drying equipment, the hot air flow and other parameters, which may not be identified as risks at that time. Subsequently, the system will comprehensively evaluate according to the read auxiliary verification information and unmarked data, combined with the marked risk data (such as the fluctuating moisture content of the cake), for example, by analyzing the maintenance record of the dewatering machine, it can be judged whether the maintenance may affect the equipment performance; by comparing the PAM batch information and the operator's record, it can be evaluated whether the properties of the agent have changed; by viewing the unmarked operation parameters of the dewatering machine and the drying equipment, it can be confirmed whether the equipment itself is running normally. By integrating these information, the root cause of the large fluctuation of the cake moisture content and the abnormality of the end operation index can be inferred, for example, it may be that the newly replaced PAM agent does not match the current sludge properties well, or the state of the equipment after maintenance needs to be fine-tuned.

[0110] Optionally, in combination with Figure 4 As shown in FIG. 6, the step S31 of identifying the sensitive period of sludge property change of the same batch of sludge in the sludge treatment process comprises:

[0111] S311, obtaining sludge property change type data, online monitoring instrument type data, and historically recorded reading deviation mode data of different online monitoring instrument types under different sludge property change types in the sludge treatment process;

[0112] S312, based on the sludge property change type data, the online monitoring instrument type data, and the reading deviation mode data, establishing a corresponding relationship information between the data and the preset sensitive period identification rule;

[0113] S313, when the preset trigger condition indicates that the sludge property changes, based on the corresponding relationship information, the matching sensitive period identification rule is found according to the sludge property change type data and the online monitoring instrument type data at that time;

[0114] S314, determining the sludge property change sensitive period of the sludge in the same batch by using the sensitive period identification rule.

[0115] wherein, the sludge property change type data refers to data reflecting the change of sludge physical, chemical or biological properties, which can be represented by data such as sludge organic matter content (such as VSS / TSS ratio), particle size distribution, dewatering performance indicators (such as specific resistance, capillary suction time), etc., and its purpose is to characterize the specific aspects of sludge property change; the online monitoring instrument type data refers to the specific category or model information of the instrument used to monitor the operating parameters in the sludge treatment process, which can be represented by flow meter model, concentration meter model, moisture content analyzer model, etc., and its purpose is to distinguish the data characteristic differences that different monitoring methods may bring; the reading deviation mode data refers to the systematic or regular deviation information of the reading of a specific type of online monitoring instrument relative to the actual or expected value under a specific sludge property change type in the historical record, which can be represented by historical calibration data, comparison analysis data or expert experience data, and its purpose is to quantify and record the potential data inaccuracy of the instrument under different working conditions; the sensitive period identification rule refers to the pre-set logic or standard set for judging the start and end time of the sludge property change sensitive period, which can be represented by expert experience-based conditional judgment rules, models or lookup tables established based on historical data analysis, and its purpose is to determine the sensitive period range according to the input data; the corresponding relationship information refers to the structured information associating the sludge property change type data, online monitoring instrument type data and reading deviation mode data with the corresponding sensitive period identification rule, which can be represented by database table, association graph or rule base index, and its purpose is to quickly locate the applicable rule according to specific data; the pre-set trigger condition refers to a specific event or data state that starts the sensitive period identification process, which can be represented by key online monitoring indicators (such as influent COD, sludge concentration) exceeding threshold values, manual input change events or upstream process parameter adjustment records, and its purpose is to start the identification in time when the sludge property may change.

[0116] In some preferred embodiments, specifically, when a batch of sludge is being treated, the sludge characteristic change type data indicates "increasing organic content", the online monitoring instrument type data indicates "A-type sludge concentration meter", and the historical record reading deviation pattern data shows that "the readings of A-type sludge concentration meter are generally low when treating sludge with increasing organic content". Based on these data, the system can establish or find the corresponding relationship information that can associate the data characteristics of "increasing organic content", "A-type sludge concentration meter", and "low readings" with a specific sensitive period identification rule. When the preset triggering condition (for example, the online monitoring value of influent COD continuously exceeds a certain threshold value, indicating that the organic load is increasing) is met, the system can find the matched sensitive period identification rule based on the current sludge characteristic change type data (increasing organic content) and online monitoring instrument type data (A-type sludge concentration meter) through the corresponding relationship information. The found rule can indicate that "when the increasing organic content occurs and A-type concentration meter is used, the sensitive period starts from the occurrence of the increasing organic content event and lasts until the batch of sludge passes through the thickening tank and dewatering unit". The system then determines the specific sensitive period time range by using this rule in combination with the flow information of the batch of sludge.

[0117] Optionally, in combination with Figure 5 As shown in FIG. 12, S312 includes the following steps:

[0118] S3121, using the sludge characteristic change type data, online monitoring instrument type data, and reading deviation pattern data, forming initial corresponding relationship data between the data and the preset sensitive period identification rule;

[0119] S3122, monitoring the changes of any one of the operation parameters of the wastewater treatment plant, the configuration information of the online monitoring instrument, or the influent water quality index; when the change reaches the preset condition, recording the change as a change event;

[0120] S3123, when the change event occurs, determining the range of the change event affecting the sludge characteristic change type data and the online monitoring instrument type data according to the preset association logic, and mapping to the initial corresponding relationship data;

[0121] S3124, updating the specific entries in the initial corresponding relationship data generated by mapping according to the new sludge characteristic change type data, online monitoring instrument type data, and reading deviation pattern data, or the preset corresponding relationship adjustment strategy for the change event type and the affected range;

[0122] In S3125, the initial correspondence data is adjusted by updating a specific entry of the initial correspondence data, and the initial correspondence data with the adjusted specific entry is used as the correspondence information.

[0123] The sludge characteristic change type data refers to the changes in physical, chemical, or biological properties of the sludge during the treatment process, such as viscosity, flocculation, dewatering performance, organic matter content, etc., which can be obtained through online monitoring, offline testing, or manual observation and recording. The online monitoring instrument type data refers to the types or model information of online monitoring instruments used to monitor various parameters in the sludge treatment process, such as sludge concentration meters, flow meters, moisture content meters, temperature sensors, etc., which can be obtained from equipment accounts or configuration management systems. The reading deviation pattern data refers to the deviation rules or characteristics of the readings of a specific type of online monitoring instrument under a specific sludge characteristic change type, such as continuous high, continuous low, increased fluctuation, delayed response, etc., which can be obtained from historical monitoring data analysis or expert experience summary. The preset sensitive period identification rule refers to the logic or model used to determine whether the sludge characteristic change has entered the sensitive period, which is based on the combination of sludge characteristic change type, online monitoring instrument type, and reading deviation pattern. It can be represented as a series of conditional statements, decision trees, machine learning models, or expert system rules. The initial correspondence relationship data refers to the association set between sludge characteristic change type data, online monitoring instrument type data, and reading deviation pattern data and the preset sensitive period identification rule at the initial stage of system operation or a certain reference state, which can be stored as a database table, rule base, or configuration file. The operating parameters refer to the process parameters that can be adjusted or monitored during the operation of the wastewater treatment plant, such as biochemical tank dissolved oxygen set value, sludge return ratio, aeration quantity, reagent dosage, etc. The configuration information of the online monitoring instrument refers to the non-real-time reading attribute information of the online monitoring instrument, such as installation location, range, calibration status, maintenance record, etc. The influent water quality indicators refer to various water quality parameters of the wastewater entering the wastewater treatment plant, such as COD, BOD, SS, ammonia nitrogen, total phosphorus, pH, temperature, etc. The preset conditions refer to the threshold values or logical judgments that trigger the recording of the change event, such as the change amplitude of the operating parameters exceeding a certain percentage, the modification of the instrument configuration information, the continuous exceeding of the normal range of the influent water quality indicators, etc. The change event refers to the change event of the operating parameters, instrument configuration, or influent water quality indicators that may affect the sludge characteristics or instrument data, which meets the preset conditions and is recorded. The preset association logic refers to the rule or model used to determine which sludge characteristic change type data and online monitoring instrument type data range will be affected by a specific change event, which can be established based on process principles, historical experience, or statistical analysis. The mapping refers to the process of associating the change event with the specific entries affected in the initial correspondence relationship data based on the preset association logic. The specific entry refers to the correspondence relationship record in the initial correspondence relationship data that is associated to the change event through mapping and needs to be checked or adjusted.The new sludge property change type data, the online monitoring instrument type data and the reading deviation mode data refer to the data reflecting the sludge property change, the instrument type and the reading deviation mode under the current running state which are collected in real time or re-collected after the change event occurs; the corresponding relationship adjustment strategy preset for the change event type and the influence range refers to the method or rule set for modifying or updating the specific entries in the initial corresponding relationship data which is preset for different types of change events and their influence range, which can include re-calculation based on new data, application of correction coefficient, switching to backup rules, etc.; the updating refers to the process of modifying the specific entries in the initial corresponding relationship data according to the new data or the adjustment strategy; the corresponding relationship information refers to the set reflecting the association between the data and the sensitive period identification rule under the current running state which is used for subsequent sensitive period identification after being updated and adjusted.

[0124] In some preferred embodiments, the application is implemented as follows: first, a database table can be constructed as initial correspondence data using historical operation data and expert experience. The table can include fields such as sludge property change type, online monitoring instrument type, reading deviation mode, and corresponding sensitive period identification rule identification. For example, a record can be: the sludge property change type is "viscosity increase", the instrument type is "sludge concentration meter", the reading deviation mode is "continuous low", and the corresponding sensitive period identification rule is "rule A". Then, the system can continuously obtain operation parameters, instrument configuration information, or influent water quality indicators from the central control system, equipment management system, or online monitoring platform of the sewage treatment plant. For example, the dissolved oxygen set value, sludge return ratio, influent COD, ammonia nitrogen, etc. of the biochemical tank are monitored. When the change amplitude of a certain parameter monitored exceeds the preset threshold value, for example, the influent COD exceeds the historical average value by a certain percentage for a continuous period of time, the system can record a "influent water quality abnormality" change event. When this change event occurs, the system can determine that "influent water quality abnormality" may affect "sludge property change type: organic matter content increase" and "online monitoring instrument type: sludge concentration meter, sludge flow meter" and the like according to the preset association logic, for example, a rule base constructed based on process experience. The system finds all entries related to these type combinations in the initial correspondence data table and marks them as specific entries that need to be updated. Then, for these specific entries, the system can update the new sludge property change type data, online monitoring instrument type data, and reading deviation mode data collected after the change event occurs. For example, it is analyzed whether the reading deviation mode of the sludge concentration meter has changed during the influent water quality abnormality, and the reading deviation mode field in the corresponding entry is updated. Alternatively, the system can modify the related entries according to the adjustment strategy preset for the "influent water quality abnormality" change event, such as "when the influent water quality is abnormal, adjust the threshold value related to the sludge concentration meter reading deviation mode judgment", and apply the strategy to modify the related entries. Through this updating process, the specific entries marked in the initial correspondence data table are corrected. Finally, the database table with the adjusted specific entries is used as the current correspondence information for the subsequent sensitive period identification process.

[0125] Optionally, in combination with Figure 6 As shown in FIG. 12, the step of presetting the correspondence adjustment strategy for the change event type and the influence range in step S3124 includes:

[0126] A1, configure the source attribute for all preset adjustment strategies;

[0127] A2, analyze the content of the preset adjustment strategy, and detect whether the content is in conflict;

[0128] A3, if the detection result indicates that there is a conflict, according to the priority of the source attribute of each preset adjustment strategy, selecting the preset adjustment strategy with the highest priority as the corresponding relationship adjustment strategy, or integrating all the preset adjustment strategies with conflicts according to the preset fusion rule and taking them as the corresponding relationship adjustment strategy.

[0129] Wherein, the source attribute refers to information used to identify the source or generation method of the preset adjustment strategy, which can adopt the form of tags, identifiers or metadata to record the source of the strategy, for example, based on historical data analysis, expert experience, supplier suggestions or simulation results, etc., the purpose of which is to provide a basis for subsequent conflict resolution strategies. Wherein, the content of the preset adjustment strategy refers to a specific rule or instruction set describing how to adjust the corresponding relationship information according to the change event, which can adopt the form of structured data, rule expression or algorithm model, etc. to represent, the purpose of which is to guide the update process of the corresponding relationship information. Wherein, the detection of whether the content exists conflict refers to judging whether the adjustment result or adjustment method of multiple preset adjustment strategies when applied to the same change event and influence range is contradictory or inconsistent, which can be realized by rule comparison, logic analysis or result simulation, etc. The purpose of which is to identify potential problem strategy combinations. Wherein, the priority confirmed by the source attribute refers to giving different priority levels to strategies with different source attributes according to preset rules or configurations, which can be determined by numerical sorting, hierarchical division or weight allocation, etc. The purpose of which is to provide a basis for selection when there is a conflict in the strategy. Wherein, the preset fusion rule refers to a rule set used to guide how to combine or integrate multiple preset adjustment strategies with conflicts to generate a new adjustment strategy without conflict or conflict has been eliminated, which can be realized by methods such as confidence-based weighting, applicability matching, conflict resolution algorithm or expert system, etc. The purpose of which is to comprehensively utilize the information of multiple strategies to generate a better adjustment scheme.

[0130] In some preferred embodiments, assuming that there are two preset adjustment strategies for the change event of replacing the flocculant batch of the sludge dewatering unit, strategy one is derived from historical operation data analysis, which suggests increasing the slope of the corresponding relationship curve between the cake moisture content and the flocculant dosage rate by 10%; strategy two is derived from the technical manual of the chemical supplier, which suggests temporarily increasing the flocculant dosage rate by 5% after replacing the new chemical, and then observing the operation effect for a week before determining the final adjustment. The source attribute of strategy one is configured as “internal data analysis”, and the source attribute of strategy two is configured as “external expert suggestion”. By analyzing the contents of the two strategies, it is found that they conflict in the adjustment method. If the preset priority rule sets the priority of “internal data analysis” higher than that of “external expert suggestion”, strategy one is selected as the corresponding relationship adjustment strategy, and the slope of the corresponding relationship curve is directly increased by 10%. Alternatively, if the preset fusion rule specifies that the trial verification method is preferred, the two strategies can be integrated to form a new adjustment strategy: first, temporarily increase the flocculant dosage rate by 5% (from strategy two), while monitoring the change of the cake moisture content, and then gradually determine the final corresponding relationship curve within a week based on the monitoring results (combined with the slope increase idea of strategy one).

[0131] Optionally, in combination with Figure 7 As shown in FIG. 13, the step of integrating all the preset adjustment strategies that conflict according to the preset fusion rule in step A3 to obtain the corresponding relationship adjustment strategy includes:

[0132] A31, reading all the preset adjustment strategies that conflict;

[0133] A32, decomposing the preset adjustment strategies that conflict into a plurality of strategy segments;

[0134] A33, identifying the conflict points between the strategy segments based on the strategy segments;

[0135] A34, based on the conflict points, filtering all the strategy segments according to the preset conflict resolution rule and the confidence information or the applicability matching degree information of the strategy segments, and selecting the strategy segments without conflicts or the strategy segments whose conflicts have been resolved;

[0136] A35, recombining the strategy segments without conflicts or the strategy segments whose conflicts have been resolved, and generating a new adjustment strategy as the corresponding relationship adjustment strategy according to the fusion rule.

[0137] The policy fragment refers to a smaller and more basic adjustment unit obtained by splitting a complete preset adjustment strategy, which can be implemented by parsing the policy text or instructions based on syntax structure, semantic unit or key parameters. The conflict point refers to inconsistent, contradictory or mutually exclusive technical proposals or parameter settings between multiple policy fragments, which can be identified based on rule matching, semantic analysis or numerical comparison. The conflict resolution rule refers to a set of preset logic or algorithms for solving conflicts between policy fragments, which can be implemented based on priority sorting, majority voting, weighted average or expert system rule base. The confidence information refers to a quantitative evaluation of the reliability or accuracy of the policy fragment, which can be determined based on the authority of the policy source, statistical data of historical execution effect or prediction accuracy of machine learning model. The applicability matching degree information refers to a quantitative evaluation of the matching degree of the policy fragment with the current actual operating condition or data characteristics, which can be determined based on comparison of current parameters with policy applicable range, operating mode recognition or similarity calculation. The fusion rule refers to a preset logic or algorithm for recombining the screened policy fragments and generating a new adjustment strategy, which can be implemented based on sequential splicing, logical combination, parameter synthesis or template filling.

[0138] In some preferred embodiments, the following is implemented. Assume that the system detects that two preset adjustment strategies are in conflict. Strategy one suggests increasing PAM dosage when sludge moisture content increases, and strategy two suggests reducing the dewatering machine speed when sludge moisture content increases and the sludge inflow increases. The system reads these two conflicting strategies. Strategy one is decomposed into the conditional segment "when sludge moisture content increases" and the operation segment "increase PAM dosage", and strategy two is decomposed into the conditional segment "when sludge moisture content increases and sludge inflow increases" and the operation segment "reduce the dewatering machine speed". Based on these strategy segments, it is identified that there may be a conflict point between the operation segments "increase PAM dosage" and "reduce the dewatering machine speed" because they are different operations proposed for similar problems. Assume that the current working condition meets "when sludge moisture content increases and sludge inflow increases". According to the preset conflict resolution rules, for example, if the operations are in conflict and the conditions are both met, weighted fusion is performed according to the confidence information of the strategy segments. Assume that the confidence of the "increase PAM dosage" segment is 0.8 and the confidence of the "reduce the dewatering machine speed" segment is 0.6. According to the fusion rule, a new operation segment can be generated, for example, the adjustment amplitude of PAM dosage and the adjustment amplitude of the dewatering machine speed are weighted and averaged or proportionally distributed. Alternatively, according to another conflict resolution rule, if the operations are in conflict, the operation segment with higher confidence is selected, and all applicable conditional segments are retained. In this example, the "increase PAM dosage" segment is selected, and the two conditional segments "when sludge moisture content increases" and "when sludge moisture content increases and sludge inflow increases" are retained (which can be further combined or refined). The screened or resolved strategy segments without conflict or with conflict resolved are recombined, and a new adjustment strategy is generated according to the fusion rule. For example, the recombined new strategy can be: when sludge moisture content increases and sludge inflow increases, increase PAM dosage. Alternatively, if weighted fusion is used, the new strategy can be: when sludge moisture content increases and sludge inflow increases, moderately increase PAM dosage and moderately reduce the dewatering machine speed.

[0139] Optionally, in combination with Figure 8 As shown in FIG. 34, the step of A34 of selecting the strategy segments without conflict or with conflict resolved based on the conflict point, according to the preset conflict resolution rules and the confidence information or the applicability matching degree information of the strategy segments, includes:

[0140] A341, defining a quantitative evaluation index for the adjustment proposition corresponding to the strategy segment;

[0141] A342, for the conflict point, calculating the quantitative evaluation index value of the corresponding adjustment proposition according to the preset conflict resolution rules and the confidence information or the applicability matching degree information of the strategy segments;

[0142] A343, comparing the quantitative evaluation index values of each policy segment according to a preset comparison criterion to select a conflict-free policy segment or a policy segment whose conflict has been resolved.

[0143] Wherein, the adjustment claim corresponding to the policy segment refers to the specific modification suggestion or operation scheme proposed for a specific problem or parameter after the complete adjustment strategy is decomposed, which can be expressed in the form of text description, parameter value, logical judgment formula or rule set; the quantitative evaluation index refers to the numerical standard for measuring the effectiveness, reliability or optimization degree of the adjustment claim corresponding to the policy segment, which can be defined in the form of score, weight, probability value or comprehensive index; the conflict point refers to the place where there are contradictory, inconsistent or competitive adjustment claims for the same problem or parameter in multiple policy segments, which can be manifested as the difference of parameter setting value, the conflict of operation sequence or the opposition of logical judgment result; the preset conflict resolution rule refers to the principle, method or algorithm set for guiding how to handle and solve the conflict between policy segments, which can be preset in the form of priority-based rule, evidence weight-based rule, logic reasoning-based rule or machine learning model-based rule; the confidence information refers to the quantitative or qualitative information reflecting the reliability of the source of the policy segment itself, the effectiveness of historical verification or the support degree of expert experience, which can be expressed in the form of numerical score, grade division or probability value; the applicability matching degree information refers to the information reflecting the matching degree or relevance of the adjustment claim proposed by the policy segment to the current actual operating condition, equipment state or material characteristics, which can be expressed in the form of matching degree score, correlation coefficient or condition judgment result; the preset comparison criterion refers to the standard or rule for comparing the quantitative evaluation index values of different policy segments and selecting or sorting according to the comparison result, which can be preset in the form of selecting the one with the highest quantitative evaluation index value, selecting the one whose quantitative evaluation index value exceeds the threshold or sorting based on the multi-index weighted sum result.

[0144] In some preferred embodiments, the application is implemented as follows. When defining the quantitative evaluation index of an adjustment claim corresponding to a policy fragment, a comprehensive evaluation score can be defined to measure the preference degree of the policy fragment in solving a specific conflict point. For a specific conflict point, e.g., two policy fragments propose different setting values for the same parameter, when calculating the quantitative evaluation index value of the corresponding adjustment claim, the confidence information (e.g., the policy is derived from a verified expert system with a confidence of 0.9; derived from historical experience summary with a confidence of 0.7) and applicability matching degree information (e.g., the policy is applicable to the current sludge characteristics and equipment state with a matching degree of 0.8; applicable to another working condition with a matching degree of 0.5) of each policy fragment can be obtained. According to the preset conflict resolution rule (e.g., prefer to select the policy with higher confidence and applicability product), the confidence information and applicability matching degree information can be combined to calculate a preliminary evaluation value. This evaluation value can be further adjusted in combination with the attributes of the conflict point itself (e.g., the size of the parameter setting value difference, the greater the difference, the more serious the conflict), to finally obtain the quantitative evaluation index value. For example, the quantitative evaluation index value can be calculated as the product of the confidence and the applicability matching degree, and then subtract a penalty term related to the severity of the conflict. When comparing the quantitative evaluation index values according to the preset comparison criterion, the policy fragment with the highest quantitative evaluation index value can be simply selected as the final adopted fragment, or a threshold value can be set to select all policy fragments with quantitative evaluation index values exceeding the threshold value for further fusion processing. In this way, the optimal or conflict effectively resolved fragment can be systematically and data and rule based selected from the conflicting policy fragments.

[0145] Optionally, in combination with Figure 9 As shown, the step of calculating the quantitative evaluation index value of the corresponding adjustment claim in step A342 includes:

[0146] A3421, obtaining the confidence information, applicability matching degree information and attribute values of the conflict point corresponding to each policy fragment in conflict;

[0147] A3422, matching weights for the confidence information, applicability matching degree information and attribute values of the conflict point;

[0148] A3423, summing the confidence information, applicability matching degree information and attribute values of the conflict point after matching the weights to obtain the corresponding quantitative evaluation index value.

[0149] The confidence information refers to a measure of the reliability of the policy fragment, which can be derived from the generation method of the policy fragment, historical application effect, expert evaluation. The suitability matching degree information refers to the degree of fit between the policy fragment and the current conflict situation, which can be calculated based on factors such as the type of conflict point, the range of parameters involved, and the process stage. The attribute value of the conflict point itself refers to data describing the characteristics of the conflict point, such as the parameters involved in the conflict, the severity level of the conflict, the frequency of the conflict, and the duration of the conflict. The matching weight refers to the influence coefficient assigned to the evaluation dimension (confidence information, suitability matching degree information, and conflict point attribute value), which can be set according to pre-set rules, machine learning models, or artificial experience. The quantitative evaluation index value refers to the numerical value obtained by integrating the evaluation dimension information through calculation methods, which is used to measure the value or priority of the policy fragment in the current conflict situation.

[0150] In some embodiments, for example, assuming that the system identifies a conflict point involving the flocculant dosage parameter in the sludge dewatering process. There are two policy fragments that can be used to adjust this parameter. Policy fragment A suggests increasing the flocculant dosage, and its confidence information can be based on the number of successful applications of this strategy in similar historical conflicts or expert experience ratings, such as 0.8. Its suitability matching degree information can be based on the matching degree of the sludge characteristics involved in the current conflict point and the applicable range of the policy fragment, such as 0.7. The attribute value of the conflict point itself can include the severity level of the conflict (e.g., high, corresponding to a value of 0.9) or the duration of the conflict. Policy fragment B suggests adjusting the type of flocculant, with a confidence information of 0.9, a suitability matching degree information of 0.6, and a conflict point attribute value (severity level) of 0.9. The system can pre-set or dynamically calculate the weights of the dimensions, such as a confidence weight of 0.4, a suitability weight of 0.3, and a conflict point attribute weight of 0.3. The quantitative evaluation index value of policy fragment A is calculated as 0.8 * 0.4 + 0.7 * 0.3 + 0.9 * 0.3 = 0.32 + 0.21 + 0.27 = 0.80. The quantitative evaluation index value of policy fragment B is calculated as 0.9 * 0.4 + 0.6 * 0.3 + 0.9 * 0.3 = 0.36 + 0.18 + 0.27 = 0.81. By comparing these quantitative evaluation index values, the system can determine that policy fragment B has a higher evaluation value, and thus is given priority in subsequent screening or sorting. The confidence information can be read from the metadata of the policy library; the suitability matching degree information can be obtained through a rule engine or similarity calculation; and the conflict point attribute value can be extracted from real-time monitoring data or alarm information. The weights can be pre-configured in the system or dynamically adjusted according to the conflict type. The weighted sum can be achieved through mathematical operations.

[0151] A sewage treatment data traceability system for performing sewage treatment data traceability, comprising Figure 10 as shown, comprising:

[0152] A batch identification adding module for adding a batch identification of a sewage treatment whole process for sewage of a plurality of treatment units in a sewage treatment plant sewage treatment process of the same batch;

[0153] A data information collecting module for collecting operation data and operation information of sewage during flowing through the treatment units;

[0154] An experienced chain generating module for binding the operation data and operation information after integration with the corresponding batch identification to generate a material experienced chain;

[0155] An operation index monitoring module for monitoring operation indexes of an end treatment link of the sewage treatment process in real time;

[0156] A reverse query module for reverse querying based on the batch identification of the sewage of the end treatment link when the operation indexes are abnormal;

[0157] An abnormal reason confirming module for reading the corresponding material experienced chain according to the reverse query result to determine the reason causing the operation index abnormality.

[0158] The batch identification adding module refers to a functional unit for adding a unique identification to the same batch of sludge, which can be realized by a software program, a hardware circuit or a combination of software and hardware, and the purpose is to realize the tracking of the whole process of sludge, to provide a basis for subsequent data integration and traceability; the data information acquisition module refers to a functional unit for obtaining operation data and operation information generated in the sludge treatment process, which can be realized by a sensor interface, a data bus interface, a manual input interface or a data interface with other systems, and the purpose is to ensure the comprehensiveness and accuracy of the traceability data, to provide data support for subsequent analysis; the experience chain generation module refers to a functional unit for integrating the collected data information and associating it with the batch identification to form a record of the sludge treatment process, which can be realized by a database management system, a data processing algorithm or a software program, and the purpose is to realize the visual traceability of the sludge treatment process, to facilitate users to quickly understand the flow path and state of the sludge; the operation index monitoring module refers to a functional unit for real-time monitoring of key parameters at the end of the sludge treatment process, which can be realized by a sensor interface, a data processing logic, an alarm triggering mechanism or a software program, and the purpose is to discover abnormal conditions in time, to provide a trigger condition for traceability; the reverse query module refers to a functional unit for tracing and finding relevant historical data according to the batch identification of the sludge at the end, which can be realized by a database query interface, an index mechanism or a software program, and the purpose is to quickly locate the sludge batch related to the abnormal operation index, to narrow the traceability range and improve the traceability efficiency; the abnormal reason confirmation module refers to a functional unit for analyzing the reverse query result and judging the specific reason for the abnormal operation index, which can be realized by a data analysis algorithm, a rule engine or a software program, and the purpose is to finally determine the reason for the abnormal operation index, to provide a basis for solving the problem.

[0159] In some preferred embodiments, the sewage treatment data traceability system can be deployed on top of or in parallel with the industrial control system. The batch identification adding module can be a functional button integrated into the operator station interface or linked with the sludge feeding system to automatically generate and associate batch identification. The data information collecting module can communicate with field instruments and control systems through an OPC server to automatically collect operating data such as flow, temperature, pressure, and energy consumption, while providing a table interface for operators to input reagent batch, equipment start-stop, and other operation information. The experience chain generating module can be a database service program running on a server that receives collected data and manually entered information, structures it, stores it in a relational database, and establishes a primary-foreign key association with the batch identification. The operating index monitoring module can be a background monitoring service that regularly reads key indicator data of the end link (such as the incinerator) in the database, compares it with the preset alarm logic, and triggers an alarm signal when an anomaly occurs. The reverse query module can be a Web service interface that receives query requests (including batch identification) from the user interface, performs database query operations, and returns relevant material experience chain data. The abnormal reason confirmation module can be a data analysis application program that loads query results, applies a preset expert rule base or machine learning model, analyzes data patterns and abnormal points in the experience chain, and outputs possible abnormal reason diagnosis reports.

[0160] Through the above technical solutions, the present application provides a sewage treatment data traceability system that can automatically complete data collection, integration, and tracing of the entire sludge treatment process. This enables quick and accurate positioning of relevant sludge batches when end operating indicators are abnormal, and efficient determination of the specific cause of the abnormality by analyzing the material experience chain. The systematic implementation reduces manual intervention, reduces data errors, improves the efficiency and reliability of traceability, and provides strong data support for process optimization, fault diagnosis, and risk management of sewage treatment plants.

[0161] The above only describes the embodiments of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A wastewater treatment data provenance method, characterized by, The method comprises the following steps: adding a batch identifier of a sludge treatment process to sludge from several treatment units of the same batch of sludge treated in a sewage treatment plant; collecting operation data and operation information of the sludge during the process of flowing through the treatment units; binding the operation data and the operation information after integration with the corresponding batch identifier to generate a material experience chain; the step of binding the operation data and the operation information after integration with the corresponding batch identifier to generate a material experience chain further comprises the following steps: identifying a sensitive period of sludge property change of sludge of the same batch during the sludge treatment process; if the operation data in the material experience chain is collected during the sensitive period of sludge property change, adding a first risk mark to the operation data; comparing the operation information in the material experience chain with a preset auxiliary record according to a keyword match, a time period check or a numerical range check to obtain a comparison result; if the comparison result shows inconsistency, adding a second risk mark to the operation information; wherein the sensitive period of sludge property change refers to a time period or a treatment link in which the physical, chemical or biological properties of the sludge relatively easily change significantly during the sludge treatment process; the material experience chain refers to a data set formed by binding the operation data and the operation information collected during the process of the same batch of sludge flowing through each treatment unit with the corresponding batch identifier; the preset auxiliary record refers to other records or information sources that can assist in verifying the authenticity and accuracy of the operation information in the material experience chain, which are preset and collected in addition to normal automated data collection and operation information recording; real-time monitoring of the operation index of the end treatment link of the sludge treatment process; when the operation index is abnormal, reverse querying based on the batch identifier of the sludge corresponding to the end treatment link; the step of reverse querying comprises: when the operation data with the first risk mark or the operation information with the second risk mark is queried, differentiating and displaying the operation data or the operation information with the mark; calling the auxiliary verification information corresponding to the operation data or the operation information; according to the result of the reverse query, reading the corresponding material experience chain to determine the cause of the abnormal operation index; the step of identifying the sensitive period of sludge property change of sludge of the same batch during the sludge treatment process comprises: obtaining sludge property change type data, online monitoring instrument type data, and historical record of reading deviation mode data of different online monitoring instrument types under different sludge property change types in the sludge treatment process; based on the sludge property change type data, the online monitoring instrument type data and the reading deviation mode data, establishing a corresponding relationship information between the data and a preset sensitive period identification rule; when a preset trigger condition indicates that the sludge property changes, based on the corresponding relationship information, finding the matching sensitive period identification rule according to the sludge property change type data and online monitoring instrument type data at that time. The sensitive period identification rule refers to a set of logic or standards pre-set for judging the start and end time of the sensitive period of sludge property change; The sensitive period identification rule is used to determine the sensitive period of sludge property change of the same batch of sludge; The step of establishing the corresponding relationship information between the data and the pre-set sensitive period identification rule based on the sludge property change type data, the online monitoring instrument type data and the reading deviation mode data comprises: The sludge property change type data, the online monitoring instrument type data and the reading deviation mode data are used to form initial corresponding relationship data between the data and the pre-set sensitive period identification rule; The change of any one of the operation parameters, the configuration information of the online monitoring instrument or the influent water quality index of the sewage treatment plant is monitored; when the change reaches a pre-set condition, the change is recorded as a change event; When the change event occurs, the range of the change event affecting the sludge property change type data and the online monitoring instrument type data is determined according to a pre-set association logic, and is mapped into the initial corresponding relationship data; The entries in the initial corresponding relationship data generated by mapping are updated according to new sludge property change type data, online monitoring instrument type data and reading deviation mode data or a corresponding relationship adjustment strategy pre-set for change event type and impact range; The initial corresponding relationship data with the adjusted entries is used as the corresponding relationship information through the updating process.

2. The wastewater treatment data provenance method of claim 1, wherein, The step of reading the corresponding material experience chain to determine the cause of the operation index anomaly according to the result of the reverse query comprises: Reading the auxiliary verification information and the unmarked data in the material experience chain; According to the auxiliary verification information and the unmarked data in the material experience chain, the cause of the operation index anomaly is evaluated and determined.

3. The wastewater treatment data provenance method of claim 1, wherein, The step of pre-setting the corresponding relationship adjustment strategy for the change event type and the impact range comprises: Configuring a source attribute for all pre-set adjustment strategies; Analyzing the content of the pre-set adjustment strategy to detect whether there is a conflict in the content; If the detection result indicates that there is a conflict, the pre-set adjustment strategy with the highest priority is selected as the corresponding relationship adjustment strategy according to the priority confirmed by the source attribute of each pre-set adjustment strategy, or all the pre-set adjustment strategies in conflict are integrated according to a pre-set fusion rule and are used as the corresponding relationship adjustment strategy.

4. The wastewater treatment data provenance method of claim 3, wherein, The step of integrating all the pre-set adjustment strategies in conflict according to a pre-set fusion rule and using them as the corresponding relationship adjustment strategy comprises: Reading all the pre-set adjustment strategies in conflict; Decomposing the pre-set adjustment strategies in conflict into a plurality of strategy fragments; Identifying the conflict points between the strategy fragments based on the strategy fragments; According to the preset conflict resolution rule and the confidence information or the applicability matching degree information of the policy fragment, all the policy fragments are screened based on the conflict point to select a conflict-free policy fragment or a policy fragment whose conflict has been resolved. The conflict-free policy fragment or the policy fragment whose conflict has been resolved is recombined, and a new adjustment policy is generated as the corresponding relationship adjustment policy according to the fusion rule.

5. The wastewater treatment data provenance method of claim 4, wherein, The step of screening all the policy fragments based on the conflict point according to the preset conflict resolution rule and the confidence information or the applicability matching degree information of the policy fragment to select a conflict-free policy fragment or a policy fragment whose conflict has been resolved comprises: Defining a quantitative evaluation index value for the adjustment claim corresponding to the policy fragment; According to the preset conflict resolution rule and the confidence information or the applicability matching degree information of the policy fragment corresponding to the conflict point, calculating the quantitative evaluation index value of the corresponding adjustment claim; According to the preset comparison criterion, comparing each quantitative evaluation index value to select a conflict-free policy fragment or a policy fragment whose conflict has been resolved.

6. The wastewater treatment data provenance method of claim 5, wherein, The step of calculating the quantitative evaluation index value of the corresponding adjustment claim according to the preset conflict resolution rule and the confidence information or the applicability matching degree information of the policy fragment corresponding to the conflict point comprises: Obtaining the confidence information, the applicability matching degree information corresponding to each policy fragment with conflict, and the attribute value of the conflict point itself; Matching weights for the confidence information, the applicability matching degree information, and the attribute value of the conflict point itself; Summing the confidence information, the applicability matching degree information, and the attribute value of the conflict point itself after matching the weights to obtain the corresponding quantitative evaluation index value.

7. A wastewater treatment data traceability system, used to perform wastewater treatment data traceability, characterized in that, It comprises: A batch identification adding module is configured to add a batch identification of a sludge treatment whole process for sludge of a plurality of treatment units in a sludge treatment process of a sewage treatment plant in the same batch; A data information collecting module is configured to collect operation data and operation information of the sludge during the process of flowing through the treatment units; An experience chain generating module is configured to integrate the operation data and the operation information, bind the corresponding batch identification, and generate a material experience chain; after the step of integrating the operation data and the operation information, binding the corresponding batch identification, and generating a material experience chain, the method further comprises: Identifying a sensitive period of sludge property change of sludge in the same batch during the sludge treatment process; if the operation data in the material experience chain is collected in the sensitive period of sludge property change, a first risk mark is added to the operation data; the operation information in the material experience chain is compared with a preset auxiliary record according to key matching, time period checking, or value range checking to obtain a comparison result; if the comparison result shows inconsistency, a second risk mark is added to the operation information; The sludge characteristic change sensitive period refers to a time period or a treatment link in which physical, chemical, or biological characteristics of sludge relatively easily change significantly in the sludge treatment process; the material experienced chain refers to a data set formed by binding operation data and operation information collected during the flow of the same batch of sludge through each treatment unit to the corresponding batch identifier; and the preset auxiliary record refers to other records or information sources that can assist in verifying the authenticity and accuracy of operation information in the material experienced chain, which are preset and collected in addition to normal automated data collection and operation information recording. The sludge characteristic change type data, the online monitoring instrument type data, and the historically recorded reading deviation mode data of different online monitoring instrument types under different sludge characteristic change types in the sludge treatment process are also acquired. Based on the sludge characteristic change type data, the online monitoring instrument type data, and the reading deviation mode data, a corresponding relationship information between data and preset sensitive period identification rules is established. When a preset trigger condition indicates that the sludge characteristics change, based on the corresponding relationship information, the sludge characteristic change type data and the online monitoring instrument type data at that time are used to find a matching sensitive period identification rule. The sensitive period identification rule refers to a set of preset logic or standards for judging the start and end time of the sludge characteristic change sensitive period. The sludge characteristic change sensitive period of the same batch of sludge is determined using the sensitive period identification rule. The sludge characteristic change type data, the online monitoring instrument type data, and the reading deviation mode data are also used to form initial corresponding relationship data between the data and the preset sensitive period identification rules. Changes in any of the operation parameters, online monitoring instrument configuration information, or influent water quality indicators of the sewage treatment plant are monitored; when the changes reach a preset condition, the changes are recorded as change events. When the change events occur, according to a preset association logic, the range of the change events affecting the sludge characteristic change type data and the online monitoring instrument type data is determined and mapped to the initial corresponding relationship data. Entries in the initial corresponding relationship data generated by mapping are updated according to new sludge characteristic change type data, online monitoring instrument type data, and reading deviation mode data or preset corresponding relationship adjustment strategies for change event types and affected ranges. The entries of the initial corresponding relationship data are adjusted through the updating process, and the initial corresponding relationship data with the adjusted entries are used as the corresponding relationship information. An operation index monitoring module is used to monitor the operation index of the end treatment link of the sludge treatment process in real time. The reverse query module is configured to perform reverse query on the batch identifier of the sludge corresponding to the end processing link when the operation index is abnormal. The reverse query includes: when the operation data with the first risk mark or the operation information with the second risk mark is queried, the operation data or the operation information with the mark is displayed differently; and the auxiliary verification information corresponding to the operation data or the operation information is called. The abnormal reason confirmation module is configured to read the corresponding material experience chain according to the result of the reverse query to determine the reason causing the operation index to be abnormal.

Images