CN116485611A - Method and system for treating production wastewater of lithium battery anode material - Google Patents

Method and system for treating production wastewater of lithium battery anode material Download PDF

Info

Publication number
CN116485611A
CN116485611A CN202310451436.1A CN202310451436A CN116485611A CN 116485611 A CN116485611 A CN 116485611A CN 202310451436 A CN202310451436 A CN 202310451436A CN 116485611 A CN116485611 A CN 116485611A
Authority
CN
China
Prior art keywords
characteristic value
index
factor
emission
type
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310451436.1A
Other languages
Chinese (zh)
Inventor
钱薇
李初架
钟晓辉
盛振塔
吴涛
徐文磊
赵华
张敏君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Zhehang Energy Technology Co ltd
Original Assignee
Anhui Zhehang Energy Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Zhehang Energy Technology Co ltd filed Critical Anhui Zhehang Energy Technology Co ltd
Priority to CN202310451436.1A priority Critical patent/CN116485611A/en
Publication of CN116485611A publication Critical patent/CN116485611A/en
Pending legal-status Critical Current

Links

Classifications

    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F1/00—Treatment of water, waste water, or sewage
    • C02F1/008—Control or steering systems not provided for elsewhere in subclass C02F
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/001—Upstream control, i.e. monitoring for predictive control
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/08—Probabilistic or stochastic CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10—Energy storage using batteries

Abstract

The application discloses a method and a system for treating wastewater in lithium battery anode material production, which belong to the technical field of wastewater treatment, and the method comprises the following steps: obtaining a production wastewater discharge standard table; acquiring an emission factor type and a factor index emission characteristic value standard interval, and constructing an emission index anomaly detection model; acquiring a lithium battery anode material production process, and matching production wastewater index prediction data; optimizing and designing the wastewater treatment process parameters according to the production wastewater index prediction data to obtain characteristic values of the production wastewater treatment results; and inputting an emission index abnormality detection model, outputting an emission factor abnormality detection result, and generating a treatment result wastewater emission instruction when abnormal index information is detected. The method and the device solve the technical problems of low intelligent degree and low parameter accuracy of wastewater treatment parameter setting in the prior art, and achieve the technical effects of improving the automation degree of parameter setting, improving the accuracy degree of parameter setting and improving the wastewater treatment quality.

Description

Method and system for treating production wastewater of lithium battery anode material
Technical Field
The application relates to the technical field of wastewater treatment, in particular to a wastewater treatment method and system for lithium battery anode material production.
Background
With the rapid development of new energy technology, the demand of new energy batteries is also increased as an indispensable part. In the process of producing new energy batteries, a large amount of industrial wastewater is generated, wastewater treatment is needed, and otherwise, the environment of a river basin and the health of residents are affected to a certain extent.
At present, in the process of treating wastewater, parameter setting in the wastewater treatment process is mainly carried out according to the accumulated experience of staff by combining wastewater treatment equipment adopted by manufacturers according to the discharge standard of the places of the manufacturers and the wastewater treatment process as reference basis. And carrying out feedback adjustment on the processing parameters related to the project according to the project with the past emission exceeding standard.
However, by means of setting parameters of wastewater treatment through manual experience, human errors can exist in the setting process, and the wastewater treatment effect corresponding to the setting parameters can be verified after treatment, so that the feedback period is too long, and the production process is continuously fluctuated, and therefore the wastewater treatment effect cannot meet the standard, and the discharge exceeding standard results occur. The technical problems of low intelligent degree of wastewater treatment parameter setting and low parameter accuracy in the prior art exist.
Disclosure of Invention
The purpose of the application is to provide a method and a system for treating wastewater in lithium battery anode material production, which are used for solving the technical problems of low intelligent degree of wastewater treatment parameter setting and low parameter accuracy in the prior art.
In view of the above problems, the present application provides a method and a system for treating wastewater from the production of a positive electrode material of a lithium battery.
In a first aspect, the present application provides a method for treating wastewater from the production of a positive electrode material of a lithium battery, wherein the method comprises: obtaining a production wastewater discharge standard table; according to the production wastewater discharge standard table, a discharge factor type and a factor index discharge characteristic value standard interval are obtained, and a discharge index abnormality detection model is constructed; acquiring a lithium battery anode material production process, and matching production wastewater index prediction data, wherein the production wastewater index prediction data comprises emission factor type characteristic value prediction data and factor index characteristic value prediction data; optimizing design is carried out on the wastewater treatment process parameters according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data, and a wastewater treatment process optimization result is generated; carrying out production wastewater treatment according to the wastewater treatment process optimization result to obtain a production wastewater treatment result characteristic value; inputting the characteristic value of the production wastewater treatment result into the discharge index abnormality detection model, and outputting a discharge factor abnormality detection result; and when the abnormal detection result of the emission factor is no abnormal index information, generating a wastewater emission instruction of the treatment result.
In another aspect, the present application further provides a lithium battery cathode material production wastewater treatment system, wherein the system comprises: the standard table acquisition module is used for acquiring a production wastewater discharge standard table; the abnormality detection model construction module is used for acquiring a discharge factor type and a factor index discharge characteristic value standard interval according to the production wastewater discharge standard table and constructing a discharge index abnormality detection model; the prediction data matching module is used for acquiring a lithium battery anode material production process and matching production wastewater index prediction data, wherein the production wastewater index prediction data comprises emission factor type characteristic value prediction data and factor index characteristic value prediction data; the optimizing result obtaining module is used for optimally designing the wastewater treatment process parameters according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data to generate a wastewater treatment process optimizing result; the result characteristic value acquisition module is used for carrying out production wastewater treatment according to the wastewater treatment process optimization result to obtain a production wastewater treatment result characteristic value; the abnormal detection result output module is used for inputting the characteristic value of the production wastewater treatment result into the discharge index abnormal detection model and outputting an abnormal detection result of the discharge factor; and the emission instruction generation module is used for generating a wastewater emission instruction of a treatment result when the emission factor abnormality detection result is abnormal index information.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the method, an emission factor type and factor index emission characteristic value standard interval is obtained according to the production wastewater emission standard table, an emission index abnormality detection model is constructed, a lithium battery anode material production process is further obtained, production wastewater index prediction data are matched, the production wastewater index prediction data comprise emission factor type characteristic value prediction data and factor index characteristic value prediction data, then according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data, wastewater treatment process parameters are optimally designed, a wastewater treatment process optimization result is generated, production wastewater treatment is conducted according to the wastewater treatment process optimization result, a production wastewater treatment result characteristic value is obtained, then the production wastewater treatment result characteristic value is input into the emission index abnormality detection model to detect abnormal conditions in characteristic values, an emission factor abnormality detection result is output, and then when the emission factor abnormality detection result is abnormal index information-free, a treatment result wastewater emission instruction is generated. The method has the advantages that the wastewater treatment parameters are predicted, the wastewater treatment parameters are adaptively adjusted according to the prediction result, the accuracy and the intelligent degree of parameter setting are improved, and the technical effect of wastewater discharge quality is guaranteed.
Drawings
For a clearer description of the technical solutions of the present application or of the prior art, the drawings used in the description of the embodiments or of the prior art will be briefly described below, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained, without inventive effort, by a person skilled in the art from the drawings provided.
Fig. 1 is a schematic flow chart of a method for treating wastewater generated in the production of a positive electrode material of a lithium battery according to an embodiment of the present application;
fig. 2 is a schematic flow chart of constructing an abnormal emission index detection model in the method for treating wastewater in the production of lithium battery cathode material according to the embodiment of the present application;
fig. 3 is a schematic flow chart of matching production wastewater index prediction data in a method for treating production wastewater of a lithium battery cathode material according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a wastewater treatment system for lithium battery cathode material production.
Reference numerals illustrate: the system comprises a standard table acquisition module 11, an anomaly detection model construction module 12, a prediction data matching module 13, an optimization result acquisition module 14, a result characteristic value acquisition module 15, an anomaly detection result output module 16 and an emission instruction generation module 17.
Detailed Description
The application solves the technical problems of low intelligent degree of wastewater treatment parameter setting and low parameter accuracy in the prior art by providing the wastewater treatment method and the system for the lithium battery anode material production. The method achieves the technical effects of improving the accuracy of parameter setting and improving the intelligent and automatic level of parameter treatment by predicting the wastewater treatment effect and further adjusting the treatment parameters.
The data acquisition, storage, use, processing and the like in the technical scheme meet the relevant regulations of national laws and regulations.
In the following, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings, and it should be understood that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application, and the present application is not limited by the example embodiments described herein. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present application are shown.
Example 1
As shown in fig. 1, the application provides a method for treating production wastewater of a lithium battery cathode material, wherein the method comprises the following steps:
step S100: obtaining a production wastewater discharge standard table;
step S200: according to the production wastewater discharge standard table, a discharge factor type and a factor index discharge characteristic value standard interval are obtained, and a discharge index abnormality detection model is constructed;
further, as shown in the figure, the step S200 of the embodiment of the present application further includes:
step S210: according to the emission factor type, a first type emission factor and a second type emission factor are obtained until an N type emission factor is obtained;
step S220: according to the factor index emission characteristic value standard interval, a first type standard value interval and a second type standard value interval to an N type standard value interval are obtained;
step S230: constructing a first type abnormality detection tree according to the first type emission factor and the first type standard value interval, wherein the first type abnormality detection tree comprises a first type abnormality index identification node and a first type abnormality degree calculation node;
Step S240: constructing an N type abnormality detection tree according to the N type emission factor and the N type standard value interval, wherein the N type abnormality detection tree comprises an N type abnormality index identification node and an N type abnormality calculation node;
step S250: and setting a plurality of multithreading processing modules according to the first type abnormality detection tree, the second type abnormality detection tree and the N type abnormality detection tree to generate the emission index abnormality detection model.
Specifically, the production wastewater discharge standard table is a standard list to be observed when the production wastewater obtained according to the production discharge policy of the place of a production enterprise and the industry standard can be discharged, and comprises project indexes for detecting the wastewater and index value ranges corresponding to the indexes, and optionally comprises a construction project environment protection management strip column, a battery industry pollutant discharge standard GB 39031-2020, a town sewage treatment plant pollutant discharge standard and the like. Further, the emission factor type and the factor index emission characteristic value standard interval are obtained according to the production wastewater emission standard table. Wherein the emission factor type is the emission type contained in the production wastewater determined by combining the production wastewater emission standard table according to the production and manufacturing process of the lithium battery anode material, and exemplary emission factors include pH, SS, CODCr, ammonia nitrogen, TN, TP, petroleum, total organic carbon and the like. The factor index emission characteristic value standard interval is the concentration or content of the emission factors which are determined according to the production wastewater emission standard table and can be used for emission, and optionally comprises pH value 6-9, SS less than or equal to 400mg/L, CODCr less than or equal to 500mg/L, ammonia nitrogen less than or equal to 45mg/L, TN less than or equal to 70mg/L, TP less than or equal to 8mg/L, petroleum less than or equal to 20mg/L, total organic carbon less than or equal to 200mg/L and the like, wherein the factor emission characteristic value standard interval corresponds to the factor emission characteristic value one by one.
Specifically, the emission factor type and the factor index emission characteristic value standard interval are taken as model construction data, and the emission index abnormality detection model is constructed. The discharge index abnormality detection model is a functional model for intelligently detecting the discharge and the concentration of the discharge in the production wastewater of the anode material, and detecting whether the discharge exceeds the discharge standard or not and abnormality exists. Further, the first type emission factor, the second type emission factor, and up to the nth type emission factor are obtained according to the difference of the emission factor types. Wherein the emission factors of the first type and the second type are different types, and N is determined according to the number of types in the emission factor types. Based on the same principle, according to different emission factor types corresponding to the factor index emission characteristic value standard interval, the first type standard value interval, the second type standard value interval and the N type standard value interval are obtained. Thus, the aim of providing basic data for the subsequent construction of the anomaly detection tree is fulfilled.
Specifically, the first type abnormality detection tree is used for performing abnormality detection on the index of the first type emission factor. The first type abnormal index identification node is a node for identifying abnormal conditions of the first type emission factors, and is established according to the two endpoints of the first type standard value interval as construction basis. The first type abnormal degree calculation node is a node for calculating the degree of exceeding the standard of the first type emission factor according to the data difference value of the first type abnormal index identification node exceeded by the data of the identified first type emission factor. The first type anomaly detection tree is constructed by constructing a root node of the first type anomaly detection tree, acquiring related data of a first type emission factor, combining the first type anomaly index identification node and the first type anomaly degree calculation node, and outputting an output node of a first type anomaly detection result. Based on the same principle, constructing a root node of an N-th type anomaly detection tree, which is used for acquiring related data of an N-th type emission factor, combining the N-th type anomaly index identification node and the N-th type anomaly degree calculation node, and outputting an N-th type anomaly detection result to construct the N-th type anomaly detection tree. The N-th type abnormal index identification node is a node for identifying abnormal conditions of the N-th type emission factors, and is established according to the construction basis of two endpoints of the N-th type standard value interval. The N-th type abnormal degree calculating node is a node for calculating the degree of exceeding the standard of the N-th type emission factor according to the data difference value of the N-th type abnormal index identifying node which is exceeded by the data of the identified N-th type emission factor.
Specifically, a plurality of multithreading processing modules are set according to the first type abnormality detection tree, the second type abnormality detection tree and the N type abnormality detection tree, and a plurality of types of emission factors can be processed simultaneously to obtain the emission index abnormality detection model. Synchronous anomaly detection is carried out on a plurality of emission factors, and then the technical effects of improving the anomaly detection efficiency and the detection accuracy are achieved through intelligent anomaly detection.
Step S300: acquiring a lithium battery anode material production process, and matching production wastewater index prediction data, wherein the production wastewater index prediction data comprises emission factor type characteristic value prediction data and factor index characteristic value prediction data;
further, as shown in fig. 3, the process for obtaining the positive electrode material of the lithium battery matches production wastewater index prediction data, where the production wastewater index prediction data includes emission factor type characteristic value prediction data and factor index characteristic value prediction data, and step S300 in the embodiment of the present application further includes:
step S310: collecting lithium battery anode material production log data in a preset production time zone from a plurality of lithium battery anode material production factories based on cloud;
Step S320: training a production wastewater index prediction model according to the production log data of the lithium battery anode material;
step S330: and inputting the production process of the lithium battery anode material into the production wastewater index prediction model, and outputting the production wastewater index prediction data.
Further, according to the lithium battery positive electrode material production log data, training a production wastewater index prediction model, step S320 of the embodiment of the present application further includes:
step S321: extracting lithium battery production process record data, emission factor type record data and factor index characteristic value record data from the lithium battery anode material production log data;
step S322: performing supervised training according to the lithium battery production process record data and the emission factor type record data to generate an emission factor type prediction layer;
step S323: performing supervised training according to the lithium battery production process record data, the emission factor type record data and the factor index characteristic value record data to generate a factor index characteristic value prediction layer;
step S324: and connecting an output layer of the emission factor type prediction layer with an input layer of the factor index characteristic value prediction layer to generate a production wastewater index prediction model.
Specifically, the lithium battery cathode material production process refers to steps, procedures and methods for processing raw materials of the lithium battery cathode material, and the process comprises an iron phosphate production line (iron powder line) with the speed of 50m 3/h. The production wastewater index prediction data refers to data obtained by predicting the types of the emission factors and the corresponding characteristic values contained in the generated wastewater in the production process according to the production technology, and preferably, the numerical value of each emission factor in the generated wastewater is obtained according to the types of raw materials in the production technology, the corresponding treatment method and the added material quality and the conservation principle of the materials in the process treatment. The emission factor type characteristic value prediction data are numerical values obtained by performing prediction statistics on emission factor types contained in the production wastewater. The factor index characteristic value prediction data is obtained by predicting characteristic values corresponding to the types of the emission factors in the production wastewater, and the emission factor type characteristic value prediction data corresponds to the factor index characteristic value prediction data one by one.
Specifically, information acquisition is performed from the internet cloud to obtain production activity data of a plurality of lithium battery anode material factories within a preset time period, namely production log data of the lithium battery anode material. The lithium battery positive electrode material production log data particularly correspond to the production time respectively. The preset production time zone is a preset production and processing time period, so that the production and processing water products can be guaranteed to be kept similar to the greatest possible extent. The production wastewater index prediction model is a functional model for predicting wastewater indexes generated in the production process of the lithium battery anode material.
Specifically, multi-angle information extraction is carried out on the lithium battery anode material production log data to obtain the lithium battery production process record data, the emission factor type record data and the factor index characteristic value record data. The lithium battery production process recording data refer to recording the process adopted in the lithium battery production process, such as a solid phase method, a complex method and the like. The emission factor type record data is obtained by recording emission factor types contained in wastewater in the production process of a plurality of lithium battery anode material factories. The factor index characteristic value recording data are obtained by recording the content corresponding to the discharge factor contained in the waste water in the production process of a plurality of lithium battery anode material factories.
Specifically, the lithium battery production process record data and the emission factor type record data are used as training data, the lithium battery production process record data are used as input data for training an emission factor type prediction layer taking a neural network as a framework, the emission factor type record data are output data identification, the output result of the emission factor type prediction layer is supervised until the accuracy of the emission factor type prediction layer meets the requirement, the emission factor type prediction layer after training is obtained, and the factor types contained in the wastewater of production and processing are predicted.
Specifically, the lithium battery production process record data, the emission factor type record data and the factor index characteristic value record data are used as training data, the lithium battery production process record data and the emission factor type record data are used as input data for training a factor index characteristic value prediction layer taking a neural network as a framework, the factor index characteristic value record data are output for data identification, the output result of the factor index characteristic value prediction layer is supervised, and the trained factor index characteristic value prediction layer is obtained until the accuracy of the factor index characteristic value prediction layer meets the requirement, and index characteristic values corresponding to different factor types in the produced and processed wastewater are predicted. And further, the production wastewater index prediction model is constructed by connecting an input layer, an emission factor type prediction layer and a factor index characteristic value prediction layer of the whole model. And inputting the production process of the lithium battery anode material into the production wastewater index prediction model by taking the production process of the lithium battery anode material as input data to obtain corresponding production wastewater index prediction data. The method has the advantages that the method can intelligently forecast the wastewater indexes of production and processing enterprises, determine the pollutant indexes in discharged wastewater, and improve the detection efficiency and shorten the wastewater treatment time by reducing the detection procedures.
Step S400: optimizing design is carried out on the wastewater treatment process parameters according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data, and a wastewater treatment process optimization result is generated;
further, the optimizing design is performed on the wastewater treatment process parameters according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data to generate a wastewater treatment process optimizing result, and step S400 of the embodiment of the present application further includes:
step S410: generating predicted abnormal emission factors and predicted index characteristic value abnormality according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data;
step S420: obtaining a wastewater treatment process device, wherein the wastewater treatment process flow comprises a filtrate treatment module, a pollutant treatment module and a sludge treatment module;
step S430: and carrying out wastewater treatment process parameter optimization design on the filtrate treatment module, the pollutant treatment module and the sludge treatment module according to the predicted abnormal emission factor and the abnormal degree of the predicted index characteristic value, and generating the wastewater treatment process optimization result.
Specifically, the wastewater treatment process optimization result is a process optimization result of optimally designing wastewater treatment process parameters according to predicted data and adjusting parameter data to ensure that the pollution discharge index of discharged wastewater is in a reasonable range. The process for treating the front-stage 3% phosphoric acid waste liquid generated by the MVR phosphoric acid concentration system process comprises the steps of collecting 50m < 3 >/h ferric phosphate production line filtrate into a filtrate collecting tank, lifting the filtrate to a ceramic membrane system through a pump, filtering and recovering components such as ferric phosphate in the filtrate, and simultaneously removing suspended matters in the filtrate to ensure the water quality of water entering an evaporation concentration system. Then ceramic membrane effluent enters an evaporation concentration system, filtrate is concentrated into 30% phosphoric acid through three-effect MVR evaporation concentration treatment, condensate generated by evaporation concentration is subjected to neutralization treatment and then is subjected to primary RO membrane treatment, pure water generated by the RO membrane is recycled to a workshop, and concentrated water generated by the RO membrane enters a wastewater treatment station for further treatment. The design water treatment amount of the wastewater treatment station is 36m < 3 >/h, after the concentrated water of the RO membrane in the MVR workshop is subjected to water quality and water amount adjustment in a concentrated water collecting tank, the concentrated water enters a dephosphorization sedimentation tank to remove pollutants such as phosphate in wastewater, and then enters a coagulation sedimentation tank to be pretreated to remove pollutants such as phosphate in wastewater. And then the wastewater from the coagulating sedimentation water automatically flows into an anaerobic reaction tank, and complex organic substances in the wastewater are converted into methane and carbon dioxide under the anaerobic environment by the action of anaerobic organisms and facultative organisms. Then the effluent of the anaerobic tank flows into a hydrolysis acidification tank, macromolecular organic pollutants which are difficult to degrade in the wastewater are subjected to open-chain degradation under the action of facultative bacteria in the tank, and are degraded into micromolecular organic matters, and then the effluent of the hydrolysis acidification tank automatically flows into an aerobic tank, and the tank is filled with fillers, so that the biomembrane is relatively stable, the effluent of the oxidation tank automatically flows into a biochemical sedimentation tank, part of precipitated sludge is returned and the residual sludge is discharged into a sludge tank, and finally the effluent of the biochemical sedimentation tank enters a discharge tank to reach the discharge standard.
Specifically, the emission is analyzed according to the predicted data, and the predicted abnormal emission factor and the abnormal degree of the characteristic value of the predicted index are obtained. Preferably, the emission factor type characteristic value prediction data and the factor index characteristic value prediction data are input into the emission index anomaly detection model to obtain the type of the emission factor and the corresponding anomaly degree. Wherein the predicted abnormal discharge factor is a type in which the discharged wastewater may contain an overstandard factor. The abnormal degree of the characteristic value of the predictive index is obtained by carrying out quantization calculation on the exceeding degree of the abnormal emission factor. Preferably, the outliers may be compared with the qualifying range values to obtain the outliers. The wastewater treatment process device is equipment for wastewater treatment and comprises: a filtrate collecting tank, a condensate water tank, an RO membrane, a belt dehydrator, a horizontal centrifuge, a diaphragm plate-and-frame filter press, and the like. The filtrate treatment module is a functional module for carrying out preliminary filtration on filtrate and removing suspended matters. The pollutant treatment module is a functional module for treating phosphate, complex organic matters, macromolecular organic matters and the like in the wastewater. The sludge treatment module is a functional module for dehydrating and filtering sludge.
Further, according to the predicted abnormal emission factor and the abnormality degree of the characteristic value of the predicted index, performing an optimization design on the wastewater treatment process parameters of the filtrate treatment module, the pollutant treatment module and the sludge treatment module to generate the wastewater treatment process optimization result, and step S430 of the embodiment of the present application further includes:
step S431: obtaining an optimized iteration function:
wherein P is m Characterizing probability of selection of mth set of process parameter record data, G (T m ,f m ) Characterizing fitness of mth set of process parameter record data, G (T m-1 ,f m-1 ) Representing the adaptability of the m-1 group of processing parameter record data, wherein T represents the selected interval duration characteristic value, f represents the selected frequency characteristic value, and alpha and beta are fusion indexes;
step S432: extracting filtrate treatment parameters according to the filtrate treatment module; extracting pollutant treatment parameters according to the pollutant treatment module; extracting sludge dewatering treatment parameters according to the sludge treatment module;
step S433: collecting filtrate processing module log data according to the filtrate processing parameters, the predicted abnormal emission factors and the abnormal degree of the predicted index characteristic values, wherein the filtrate processing module log data comprises a plurality of groups of filtrate processing parameter record data, a first selected frequency characteristic value and a first selected interval duration characteristic value;
Step S434: based on the optimized iteration function, the first selected frequency characteristic value and the first selected interval duration characteristic value iterate a first preset number of times on the plurality of groups of filtrate processing parameter record data to generate a filtrate processing parameter optimization result;
step S435: collecting pollutant processing module log data according to the pollutant processing parameters, the predicted abnormal emission factors, the predicted index characteristic value abnormality degree and the filtrate processing parameter optimization result, wherein the pollutant processing module log data comprises a plurality of groups of pollutant processing parameter record data, a second selected frequency characteristic value and a second selected interval duration characteristic value;
step S436: based on the optimized iteration function, the second selected frequency characteristic value and the second selected interval duration characteristic value iterate a second preset number of times on the plurality of groups of pollutant treatment parameter record data to generate a pollutant treatment parameter optimization result;
step S437: collecting log data of a sludge dewatering treatment module according to the sludge dewatering treatment parameters, the predicted abnormal emission factors, the abnormal degree of the predicted index characteristic values, the filtrate treatment parameter optimization result and the pollutant treatment parameter optimization result, wherein the log data of the sludge dewatering treatment module comprises a plurality of groups of sludge dewatering treatment parameter record data, a third selected frequency characteristic value and a third selected interval duration characteristic value;
Step S438: based on the optimized iteration function, the third selected frequency characteristic value and the third selected interval duration characteristic value iterate a third preset number of times on the multiple groups of sludge dewatering treatment parameter record data to generate a sludge dewatering treatment parameter optimization result;
step S439: and adding the filtrate treatment parameter optimization result, the pollutant treatment parameter optimization result and the sludge dewatering treatment parameter optimization result into the wastewater treatment process optimization result.
Specifically, the optimization iteration function is a calculation function for performing optimization iteration on the historical processing of each processing module, so as to obtain the processing parameters with the optimal processing effect. The m groups of processing parameter record data are data obtained according to historical production records of manufacturers. The adaptability of the treatment parameter record data is obtained after the treatment effect of wastewater treatment is evaluated according to the treatment parameter record data. The interval duration characteristic value is an average time difference value obtained by acquiring a time difference value set of a plurality of time nodes selected by the group of data from a current time node and carrying out mean value calculation on the time difference value set, reflects the reliability degree of the group of data for the current parameter setting, and indicates that the reliability degree of the group of data is higher as the interval duration characteristic value is smaller. The selected frequency characteristic value refers to the number of times the group of data is selected in the historical wastewater treatment process. The alpha and beta are fusion indexes, namely the alpha and beta have an association relation, the numerical value depends on the emphasis degree of time and frequency when parameter selection is carried out, and when the importance degree of the two parameters is the same, the numerical value of the alpha and the numerical value of the beta are the same. Illustratively, if more emphasis is placed on time, i.e., timeliness of the data, the value of α is greater than the value of β, and if more emphasis is placed on the number of times the data is selected, the higher the frequency indicates that the data is more suitable for the production needs of the manufacturer, the value of α is less than the value of β. The setting is performed according to actual demands, and is not limited herein.
Specifically, the filtrate treatment parameters are control parameters determined according to the filtrate treatment process when the filtrate is treated, and include a waste liquid flow parameter, a ceramic membrane filtration parameter, a three-effect MVR evaporator treatment parameter, a condensation neutralization treatment parameter, an RO reverse osmosis membrane treatment parameter and the like. The waste liquid flow parameters correspondingly comprise the conditions of waste liquid collection parameters, including the pressure value of a pump valve, the waste liquid collection speed and the like. The ceramic membrane filtration parameters refer to temperature, density, pressure and flow rate when ceramic membrane filtration is used, and the temperature is in the range of 250-800 ℃, the density is 1.45-1.52kg/m3, and the flow rate is more than 20m3/h. The treatment parameters of the three-effect MVR evaporator comprise that the salt content of wastewater is 3.5-25%, the COD concentration is 2000-10000ppm, and the like. The condensation neutralization treatment parameters include humidity, temperature, etc. The RO reverse osmosis membrane treatment parameters include a pressure of less than 150psi. The pollutant treatment parameters comprise dephosphorization sedimentation tank treatment parameters, anaerobic reaction tank treatment parameters and biochemical sedimentation tank treatment parameters. The dephosphorization sedimentation tank treatment parameters comprise: settling time, guard height, buffer layer height, surface loading, etc. Preferably, the sedimentation time is 1.5-4h, the protection height is 1.0m, the buffer layer height is 0.7-1.0m, etc. The anaerobic reaction tank treatment parameters comprise an oxygen capacity value, preferably, the anaerobic section is between 0mg/L and 0.2mg/L, the anoxic section is between 0.2mg/L and 0.5mg/L, and the aerobic section is between 1.5mg/L and 3 mg/L. The sludge dewatering parameters mainly comprise related parameters of a belt dehydrator and a horizontal centrifuge. The working parameters of the belt dehydrator mainly comprise solid-liquid separation speed, pulp inlet concentration and the like. Preferably, the solid-liquid separation speed is 8-10 cubic meters per hour, and the pulp inlet concentration is higher than 3%. The working parameters of the horizontal centrifuge mainly comprise centrifuge rotation speed, temperature range and the like, preferably, the centrifuge rotation speed is 5000rpm, and the temperature range is-9-40 ℃.
Specifically, the log data of the filtrate processing module is processing parameter data generated when filtrate processing is performed, and the log data comprises a plurality of groups of filtrate processing parameter record data, a first selected frequency characteristic value and a first selected interval duration characteristic value. The first selected frequency characteristic value is obtained by collecting multiple groups of same parameters according to the multiple groups of filtrate processing parameter record data, and the selected times of the same parameters in log time are obtained. The first selected interval duration characteristic value is a difference value of a selected time point of the same processing parameter from a current time point when filtrate processing is carried out, and the average value of the difference values is obtained. And further, according to the optimized iteration function, iterating by combining the first selected frequency characteristic value and the first selected interval duration characteristic value, wherein the first preset times are preset optimized iteration times, and are set by a worker by themselves, so that the method is not limited. Thereby, the optimal treatment parameters are used as the filtrate treatment parameter optimization results. Preferably, in the optimization iteration process, when the fitness of the mth group of processing parameter record data is higher than the fitness of the mth-1 group of processing parameter record data, the mth group of processing parameter record data is reserved, and when the fitness of the mth group of processing parameter record data is lower than the fitness of the mth-1 group of processing parameter record data, the mth-1 group of processing parameter record data is reserved, so that the optimization iteration of the processing parameters is achieved, the optimal processing parameters are obtained, and the technical effect of wastewater treatment effect is improved.
Specifically, the log data of the pollutant treatment module is treatment parameter data generated when pollutant treatment is performed, and the log data comprises a plurality of groups of pollutant treatment parameter record data, a second selected frequency characteristic value and a second selected interval duration characteristic value. And the second selected frequency characteristic value is obtained by collecting a plurality of groups of same parameters according to the plurality of groups of pollutant processing parameter record data, and the selected times of the same parameters in the log time are obtained. The second selected interval duration characteristic value is a difference value of a selected time point of the same processing parameter from a current time point when the pollutant is processed, and the average value of the difference values is obtained. And further, according to the optimized iteration function, iterating by combining the second selected frequency characteristic value and the second selected interval duration characteristic value, wherein the second preset times are optimized iteration times when pollutant parameter selection is preset, and are set by a worker by themselves, and the method is not limited.
Specifically, the log data of the sludge dewatering treatment module is treatment parameter data generated when sludge dewatering treatment is carried out, and the log data comprises a plurality of groups of sludge dewatering treatment parameter record data, a third selected frequency characteristic value and a third selected interval duration characteristic value. And the third selected frequency characteristic value is obtained by collecting a plurality of groups of same parameters according to the plurality of groups of sludge dewatering treatment parameter record data, so as to obtain the selected times of the same parameters in log time. The third selected interval duration characteristic value is obtained by carrying out average value calculation on a plurality of difference values of the selected time points of the same treatment parameter from the current time point when the sludge dewatering treatment is carried out. And further, according to the optimized iteration function, iterating by combining the third selected frequency characteristic value and the third selected interval duration characteristic value, wherein the third preset times are optimized iteration times when pollutant parameter selection is preset, and are set by a worker by themselves, and the method is not limited.
Specifically, the filtrate treatment parameter optimization result, the pollutant treatment parameter optimization result and the sludge dewatering treatment parameter optimization result are added into the wastewater treatment process optimization result to obtain optimal parameters for filtrate, pollutant and sludge dewatering treatment, so that the technical effects of improving the automation degree of parameter setting, shortening the parameter setting time and improving the treatment efficiency and wastewater treatment quality are achieved.
Step S500: carrying out production wastewater treatment according to the wastewater treatment process optimization result to obtain a production wastewater treatment result characteristic value;
step S600: inputting the characteristic value of the production wastewater treatment result into the discharge index abnormality detection model, and outputting a discharge factor abnormality detection result;
specifically, the filtrate, pollutants and sludge of the production wastewater are dehydrated according to the process parameters in the wastewater treatment process optimization result, and finally the characteristic parameters of the treated discharged wastewater are obtained. Wherein, the characteristic value of the production wastewater treatment result reflects various index values after wastewater treatment. And inputting the characteristic value of the production wastewater treatment result into the discharge index abnormality detection model to obtain the discharge factor abnormality detection result, and detecting the actual wastewater treatment result. The technical effect of treating the production wastewater and eliminating the pollution factors is achieved.
Step S700: and when the abnormal detection result of the emission factor is no abnormal index information, generating a wastewater emission instruction of the treatment result.
Further, step S700 in the embodiment of the present application further includes: and when the abnormal detection result of the emission factor is abnormal index information, circulating wastewater treatment.
Specifically, when no abnormal index information exists, the wastewater treatment result can meet the requirements, no additional treatment is needed, the emission standard is met, and the wastewater can be directly discharged. The treatment result wastewater discharge instruction is an instruction to discharge wastewater. When abnormal index information exists, namely the treated wastewater can not meet the discharge standard, the wastewater is required to be circularly treated according to the wastewater treatment method, and the wastewater treatment parameters are readjusted according to the treated wastewater condition. Therefore, the technical effect of improving the wastewater treatment quality is achieved.
In summary, the method for treating the production wastewater of the lithium battery anode material provided by the application has the following technical effects:
according to the method, the production wastewater discharge standard table is obtained as a basis standard of wastewater treatment, the discharge factor type contained in wastewater and the corresponding characteristic value standard interval conforming to the standard are obtained according to the production wastewater discharge standard table, clear standards are established for wastewater discharge analysis, meanwhile, a discharge index abnormality detection model is also constructed to provide basic data, the production process of the lithium battery anode material is further obtained, production wastewater index prediction data after production according to the production process are correspondingly matched, then the wastewater treatment process parameters are optimized according to the discharge factor type characteristic value prediction data and the factor index characteristic value prediction data, the wastewater treatment process optimization result is generated, the production wastewater treatment is carried out, the characteristic values corresponding to all indexes in the wastewater are obtained and are used as input data, whether the discharge factors exist abnormality is detected in the discharge index abnormality detection model, and when abnormal index information is not available, a treatment result wastewater discharge instruction is generated. The technical effects of reducing the wastewater treatment parameter setting period, improving the parameter setting accuracy, shortening the feedback period and improving the wastewater treatment effect are achieved.
Example two
Based on the same inventive concept as the method for treating the production wastewater of the positive electrode material of the lithium battery in the foregoing embodiment, as shown in fig. 4, the present application further provides a system for treating the production wastewater of the positive electrode material of the lithium battery, wherein the system comprises:
the standard table acquisition module 11 is used for acquiring a production wastewater discharge standard table;
the abnormality detection model construction module 12 is used for acquiring a discharge factor type and a factor index discharge characteristic value standard interval according to the production wastewater discharge standard table, and constructing a discharge index abnormality detection model;
the prediction data matching module 13 is used for acquiring a lithium battery anode material production process and matching production wastewater index prediction data, wherein the production wastewater index prediction data comprises emission factor type characteristic value prediction data and factor index characteristic value prediction data;
the optimizing result obtaining module 14 is configured to optimally design the wastewater treatment process parameters according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data, and generate a wastewater treatment process optimizing result;
The result characteristic value acquisition module 15 is used for carrying out production wastewater treatment according to the wastewater treatment process optimization result to obtain a production wastewater treatment result characteristic value;
the abnormal detection result output module 16, wherein the abnormal detection result output module 16 is used for inputting the characteristic value of the production wastewater treatment result into the discharge index abnormal detection model and outputting a discharge factor abnormal detection result;
and a discharge instruction generation module 17, wherein the discharge instruction generation module 17 is used for generating a wastewater discharge instruction of a treatment result when the abnormal detection result of the discharge factor is abnormal index information.
Further, the system further comprises:
an emission factor acquisition unit for acquiring a first type emission factor, a second type emission factor, and up to an nth type emission factor according to the emission factor type;
the standard value interval acquisition unit is used for acquiring a first type standard value interval, a second type standard value interval and an N type standard value interval according to the factor index emission characteristic value standard interval;
the first detection tree construction unit is used for constructing a first type abnormal detection tree according to the first type emission factor and the first type standard value interval, wherein the first type abnormal detection tree comprises a first type abnormal index identification node and a first type abnormal degree calculation node;
An nth detection tree construction unit, configured to construct an nth type anomaly detection tree according to the nth type emission factor and the nth type standard value interval, where the nth type anomaly detection tree includes an nth type anomaly index identification node and an nth type anomaly calculation node;
the index anomaly detection model construction unit is used for setting a plurality of multithreading processing modules according to the first type anomaly detection tree, the second type anomaly detection tree and the N type anomaly detection tree to generate the emission index anomaly detection model.
Further, the system further comprises:
the production log data acquisition unit is used for acquiring production log data of lithium battery anode materials in a preset production time zone from a plurality of lithium battery anode material production factories based on cloud;
the index prediction model training unit is used for training a production wastewater index prediction model according to the lithium battery anode material production log data;
and the prediction data output unit is used for inputting the production process of the lithium battery anode material into the production wastewater index prediction model and outputting the production wastewater index prediction data.
Further, the system further comprises:
the recording data extraction unit is used for extracting lithium battery production process recording data, emission factor type recording data and factor index characteristic value recording data from the lithium battery positive electrode material production log data;
the prediction layer generation unit is used for performing supervised training according to the lithium battery production process record data and the emission factor type record data to generate an emission factor type prediction layer;
the characteristic value prediction layer generation unit is used for performing supervised training according to the lithium battery production process record data, the emission factor type record data and the factor index characteristic value record data to generate a factor index characteristic value prediction layer;
and the input layer connection unit is used for connecting the output layer of the emission factor type prediction layer with the input layer of the factor index characteristic value prediction layer to generate a production wastewater index prediction model.
Further, the system further comprises:
an abnormality degree generation unit for generating a predicted abnormal emission factor and a predicted index feature value abnormality degree from the emission factor type feature value prediction data and the factor index feature value prediction data;
The treatment process device acquisition unit is used for acquiring a wastewater treatment process device, wherein the wastewater treatment process flow comprises a filtrate treatment module, a pollutant treatment module and a sludge treatment module;
and the parameter optimization design unit is used for carrying out wastewater treatment process parameter optimization design on the filtrate treatment module, the pollutant treatment module and the sludge treatment module according to the predicted abnormal emission factor and the abnormal degree of the predicted index characteristic value, so as to generate the wastewater treatment process optimization result.
Further, the system further comprises:
the iterative function acquisition unit is used for acquiring an optimized iterative function:
wherein P is m Characterizing probability of selection of mth set of process parameter record data, G (T m ,f m ) Characterizing fitness of mth set of process parameter record data, G (T m-1 ,f m-1 ) Representing the adaptability of the m-1 group of processing parameter record data, wherein T represents the selected interval duration characteristic value, f represents the selected frequency characteristic value, and alpha and beta are fusion indexes;
the dehydration treatment parameter extraction unit is used for extracting filtrate treatment parameters according to the filtrate treatment module; extracting pollutant treatment parameters according to the pollutant treatment module; extracting sludge dewatering treatment parameters according to the sludge treatment module;
The log data acquisition unit is used for acquiring log data of the filtrate processing module according to the filtrate processing parameters, the predicted abnormal emission factors and the abnormal degrees of the predicted index characteristic values, wherein the log data of the filtrate processing module comprises a plurality of groups of filtrate processing parameter record data, a first selected frequency characteristic value and a first selected interval duration characteristic value;
the processing parameter optimization result generation unit is used for generating a filtrate processing parameter optimization result by iterating the plurality of groups of filtrate processing parameter record data for a first preset number of times based on the optimization iteration function, the first selected frequency characteristic value and the first selected interval duration characteristic value;
the processing module log data acquisition unit is used for acquiring the log data of the pollutant processing module according to the pollutant processing parameters, the predicted abnormal emission factors, the predicted index characteristic value abnormality degree and the filtrate processing parameter optimization result, wherein the log data of the pollutant processing module comprises a plurality of groups of pollutant processing parameter record data, a second selected frequency characteristic value and a second selected interval duration characteristic value;
The pollutant parameter optimization result generating unit is used for generating a pollutant treatment parameter optimization result by iterating the plurality of groups of pollutant treatment parameter record data for a second preset number of times based on the optimization iteration function, the second selected frequency characteristic value and the second selected interval duration characteristic value;
the module log data acquisition unit is used for acquiring log data of a sludge dewatering treatment module according to the sludge dewatering treatment parameter, the predicted abnormal emission factor, the abnormal degree of the predicted index characteristic value, the filtrate treatment parameter optimization result and the pollutant treatment parameter optimization result, wherein the log data of the sludge dewatering treatment module comprises a plurality of groups of sludge dewatering treatment parameter record data, a third selected frequency characteristic value and a third selected interval duration characteristic value;
the recorded data iteration unit is used for iterating the plurality of groups of sludge dewatering treatment parameter recorded data for a third preset times based on the optimized iteration function, the third selected frequency characteristic value and the third selected interval duration characteristic value to generate a sludge dewatering treatment parameter optimization result;
And the parameter optimization result adding unit is used for adding the filtrate treatment parameter optimization result, the pollutant treatment parameter optimization result and the sludge dewatering treatment parameter optimization result into the wastewater treatment process optimization result.
Further, the system further comprises: and when the abnormal detection result of the emission factor is abnormal index information, circulating wastewater treatment.
The embodiments in this specification are described in a progressive manner, and each embodiment focuses on the difference from the other embodiments, and the foregoing method and specific example for treating waste water from production of a lithium battery cathode material in the first embodiment of fig. 1 are equally applicable to the system for treating waste water from production of a lithium battery cathode material in this embodiment, and by the foregoing detailed description of the method for treating waste water from production of a lithium battery cathode material, those skilled in the art will clearly know that the system for treating waste water from production of a lithium battery cathode material in this embodiment is not described in detail herein for brevity of the specification. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. The method for treating the production wastewater of the lithium battery anode material is characterized by comprising the following steps of:
obtaining a production wastewater discharge standard table;
according to the production wastewater discharge standard table, a discharge factor type and a factor index discharge characteristic value standard interval are obtained, and a discharge index abnormality detection model is constructed;
acquiring a lithium battery anode material production process, and matching production wastewater index prediction data, wherein the production wastewater index prediction data comprises emission factor type characteristic value prediction data and factor index characteristic value prediction data;
optimizing design is carried out on the wastewater treatment process parameters according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data, and a wastewater treatment process optimization result is generated;
Carrying out production wastewater treatment according to the wastewater treatment process optimization result to obtain a production wastewater treatment result characteristic value;
inputting the characteristic value of the production wastewater treatment result into the discharge index abnormality detection model, and outputting a discharge factor abnormality detection result;
and when the abnormal detection result of the emission factor is no abnormal index information, generating a wastewater emission instruction of the treatment result.
2. The method of claim 1, wherein the step of obtaining the emission factor type and the factor index emission characteristic value standard interval according to the production wastewater emission standard table, and constructing an emission index anomaly detection model comprises the steps of:
according to the emission factor type, a first type emission factor and a second type emission factor are obtained until an N type emission factor is obtained;
according to the factor index emission characteristic value standard interval, a first type standard value interval and a second type standard value interval to an N type standard value interval are obtained;
constructing a first type abnormality detection tree according to the first type emission factor and the first type standard value interval, wherein the first type abnormality detection tree comprises a first type abnormality index identification node and a first type abnormality degree calculation node;
Constructing an N type abnormality detection tree according to the N type emission factor and the N type standard value interval, wherein the N type abnormality detection tree comprises an N type abnormality index identification node and an N type abnormality calculation node;
and setting a plurality of multithreading processing modules according to the first type abnormality detection tree, the second type abnormality detection tree and the N type abnormality detection tree to generate the emission index abnormality detection model.
3. The method of claim 1, wherein the obtaining the lithium battery cathode material production process matches production wastewater index prediction data, wherein the production wastewater index prediction data includes emission factor type characteristic value prediction data and factor index characteristic value prediction data, comprising:
collecting lithium battery anode material production log data in a preset production time zone from a plurality of lithium battery anode material production factories based on cloud;
training a production wastewater index prediction model according to the production log data of the lithium battery anode material;
and inputting the production process of the lithium battery anode material into the production wastewater index prediction model, and outputting the production wastewater index prediction data.
4. The method of claim 3, wherein training a production wastewater index prediction model based on the lithium battery positive electrode material production log data comprises:
extracting lithium battery production process record data, emission factor type record data and factor index characteristic value record data from the lithium battery anode material production log data;
performing supervised training according to the lithium battery production process record data and the emission factor type record data to generate an emission factor type prediction layer;
performing supervised training according to the lithium battery production process record data, the emission factor type record data and the factor index characteristic value record data to generate a factor index characteristic value prediction layer;
and connecting an output layer of the emission factor type prediction layer with an input layer of the factor index characteristic value prediction layer to generate a production wastewater index prediction model.
5. The method of claim 1, wherein optimizing the wastewater treatment process parameters based on the emission factor type characteristic value prediction data and the factor index characteristic value prediction data to generate a wastewater treatment process optimization result comprises:
Generating predicted abnormal emission factors and predicted index characteristic value abnormality according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data;
obtaining a wastewater treatment process device, wherein the wastewater treatment process flow comprises a filtrate treatment module, a pollutant treatment module and a sludge treatment module;
and carrying out wastewater treatment process parameter optimization design on the filtrate treatment module, the pollutant treatment module and the sludge treatment module according to the predicted abnormal emission factor and the abnormal degree of the predicted index characteristic value, and generating the wastewater treatment process optimization result.
6. The method of claim 5, wherein the optimizing the wastewater treatment process parameters to the filtrate treatment module, the pollutant treatment module, and the sludge treatment module based on the predicted abnormal emissions factor and the predicted index characteristic value anomaly, generating the wastewater treatment process optimization result comprises:
obtaining an optimized iteration function:
wherein P is m Characterizing probability of selection of mth set of process parameter record data, G (T m ,f m ) Characterizing fitness of mth set of process parameter record data, G (T m-1 ,f m-1 ) Representing the adaptability of the m-1 group of processing parameter record data, wherein T represents the selected interval duration characteristic value, f represents the selected frequency characteristic value, and alpha and beta are fusion indexes;
extracting filtrate treatment parameters according to the filtrate treatment module; extracting pollutant treatment parameters according to the pollutant treatment module; extracting sludge dewatering treatment parameters according to the sludge treatment module;
collecting filtrate processing module log data according to the filtrate processing parameters, the predicted abnormal emission factors and the abnormal degree of the predicted index characteristic values, wherein the filtrate processing module log data comprises a plurality of groups of filtrate processing parameter record data, a first selected frequency characteristic value and a first selected interval duration characteristic value;
based on the optimized iteration function, the first selected frequency characteristic value and the first selected interval duration characteristic value iterate a first preset number of times on the plurality of groups of filtrate processing parameter record data to generate a filtrate processing parameter optimization result;
collecting pollutant processing module log data according to the pollutant processing parameters, the predicted abnormal emission factors, the predicted index characteristic value abnormality degree and the filtrate processing parameter optimization result, wherein the pollutant processing module log data comprises a plurality of groups of pollutant processing parameter record data, a second selected frequency characteristic value and a second selected interval duration characteristic value;
Based on the optimized iteration function, the second selected frequency characteristic value and the second selected interval duration characteristic value iterate a second preset number of times on the plurality of groups of pollutant treatment parameter record data to generate a pollutant treatment parameter optimization result;
collecting log data of a sludge dewatering treatment module according to the sludge dewatering treatment parameters, the predicted abnormal emission factors, the abnormal degree of the predicted index characteristic values, the filtrate treatment parameter optimization result and the pollutant treatment parameter optimization result, wherein the log data of the sludge dewatering treatment module comprises a plurality of groups of sludge dewatering treatment parameter record data, a third selected frequency characteristic value and a third selected interval duration characteristic value;
based on the optimized iteration function, the third selected frequency characteristic value and the third selected interval duration characteristic value iterate a third preset number of times on the multiple groups of sludge dewatering treatment parameter record data to generate a sludge dewatering treatment parameter optimization result;
and adding the filtrate treatment parameter optimization result, the pollutant treatment parameter optimization result and the sludge dewatering treatment parameter optimization result into the wastewater treatment process optimization result.
7. The method as recited in claim 1, further comprising: and when the abnormal detection result of the emission factor is abnormal index information, circulating wastewater treatment.
8. A lithium battery cathode material production wastewater treatment system, the system comprising:
the standard table acquisition module is used for acquiring a production wastewater discharge standard table;
the abnormality detection model construction module is used for acquiring a discharge factor type and a factor index discharge characteristic value standard interval according to the production wastewater discharge standard table and constructing a discharge index abnormality detection model;
the prediction data matching module is used for acquiring a lithium battery anode material production process and matching production wastewater index prediction data, wherein the production wastewater index prediction data comprises emission factor type characteristic value prediction data and factor index characteristic value prediction data;
the optimizing result obtaining module is used for optimally designing the wastewater treatment process parameters according to the emission factor type characteristic value prediction data and the factor index characteristic value prediction data to generate a wastewater treatment process optimizing result;
The result characteristic value acquisition module is used for carrying out production wastewater treatment according to the wastewater treatment process optimization result to obtain a production wastewater treatment result characteristic value;
the abnormal detection result output module is used for inputting the characteristic value of the production wastewater treatment result into the discharge index abnormal detection model and outputting an abnormal detection result of the discharge factor;
and the emission instruction generation module is used for generating a wastewater emission instruction of a treatment result when the emission factor abnormality detection result is abnormal index information.
CN202310451436.1A 2023-04-25 2023-04-25 Method and system for treating production wastewater of lithium battery anode material Pending CN116485611A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310451436.1A CN116485611A (en) 2023-04-25 2023-04-25 Method and system for treating production wastewater of lithium battery anode material

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310451436.1A CN116485611A (en) 2023-04-25 2023-04-25 Method and system for treating production wastewater of lithium battery anode material

Publications (1)

Publication Number Publication Date
CN116485611A true CN116485611A (en) 2023-07-25

Family

ID=87220936

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310451436.1A Pending CN116485611A (en) 2023-04-25 2023-04-25 Method and system for treating production wastewater of lithium battery anode material

Country Status (1)

Country Link
CN (1) CN116485611A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117275615A (en) * 2023-10-31 2023-12-22 源康(东阿)健康科技有限公司 Intelligent treatment method and system for gelatin production wastewater
CN117401872A (en) * 2023-12-15 2024-01-16 江苏众瑞环保科技有限公司 Data processing method and system for lead-acid battery wastewater discharge control

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117275615A (en) * 2023-10-31 2023-12-22 源康(东阿)健康科技有限公司 Intelligent treatment method and system for gelatin production wastewater
CN117275615B (en) * 2023-10-31 2024-04-09 源康(东阿)健康科技有限公司 Intelligent treatment method and system for gelatin production wastewater
CN117401872A (en) * 2023-12-15 2024-01-16 江苏众瑞环保科技有限公司 Data processing method and system for lead-acid battery wastewater discharge control
CN117401872B (en) * 2023-12-15 2024-03-08 江苏众瑞环保科技有限公司 Data processing method and system for lead-acid battery wastewater discharge control

Similar Documents

Publication Publication Date Title
CN116485611A (en) Method and system for treating production wastewater of lithium battery anode material
CN201817356U (en) Coking wastewater advanced treatment and reuse device by using ozone, active carbon and double-membrane process
CN201817357U (en) Full-reuse treatment device for coking wastewater through Fenton oxidation and double-membrane process
CN102156406A (en) Expert system and method for preventing and controlling sludge bulking under the diagnosis based on operation condition of sewage disposal plant
US11484843B2 (en) Method of predicting membrane fouling in reverse osmosis process
Méndez‐Acosta et al. Monitoring anaerobic sequential batch reactors via fractal analysis of pH time series
CN106430806A (en) Modular integration process method for kitchen waste filtrate
Han et al. An intelligent detecting system for permeability prediction of MBR
CN101891349B (en) Hospital sewage processing process
William et al. Architecture for AI-Based Validation of Wastewater Management Using Open Data Exchange Technique
CN106442913A (en) Waste water pollution source monitoring system
CN114690700A (en) PLC-based intelligent sewage treatment decision optimization method and system
CN107935300B (en) Process device and method for treating landfill leachate by non-membrane method
Perendeci et al. Effects of phase vector and history extension on prediction power of adaptive-network based fuzzy inference system (ANFIS) model for a real scale anaerobic wastewater treatment plant operating under unsteady state
CN101891322A (en) Method for treating recycling water by combining electrochemical oxidation and double-membrane methods
CN116119877A (en) Sewage automatic treatment method and system based on Internet of things technology
CN116119874A (en) Wastewater treatment system for realizing resource recovery and carbon emission and related method
CN206476858U (en) A kind of circulating blowdown water treatment system
CN1323039C (en) Apparatus and method for disposing refuse leachate from household refuse burning factory
CN213171969U (en) Sewage treatment monitoring system
KR20230060646A (en) Industry assets manage and operate platform for integrating type digestion system based on artificial intelligence
KR20230038038A (en) Energy efficiency evaluation method and energy saving decision-making system of sewage treatment plant based on water treatment energy index
CN114149076A (en) Intelligent debugging system of anaerobic ammonia oxidation sewage treatment system
CN112875957A (en) Thermal power factory optimizes water consumption and waste water zero release processing system
CN116796905A (en) Prediction method for effluent index of microbial reactor in garbage leachate treatment process

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination