A filtering method and system for purification equipment for environmental protection
By building a distributed control module in the purification equipment and using a distributed microprocessor to make dynamic filtering decisions, the problems of low filtering efficiency and high energy consumption in the existing technology are solved, efficient purification and precise control are achieved, and environmental protection is met. Efficient purification needs.
Patent Information
- Application Number
- CN202411311617.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-20
AI Technical Summary
The filtration methods of existing purification equipment have problems such as low filtration efficiency, high energy consumption and unsatisfactory separation effect.
By determining the basic content information of the medium to be processed and the purification separation standards, integrating and determining the filter separation target, building a separation decision model based on the principle of filtration cycle dynamics, and forming a distributed control module, combining a distributed microprocessor to perform dynamic filter separation decisions and feedback regulation , realize accurate control of the filtering process and real-time feedback regulation.
It improves purification efficiency, reduces energy consumption, and realizes precise control and real-time feedback regulation of the filtration process, meeting the demand for efficient purification technology in environmental protection.
Smart Images

Figure CN118862694B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of separation technology, and specifically to a filtering method and system for purification equipment for environmental protection. Background Art
[0002] With the acceleration of industrialization and the development of urbanization, environmental protection and pollution control have become important challenges facing today's society. Among the many pollution sources, medium pollution poses a serious threat to the ecological environment and human health due to its extensiveness and complexity. In order to effectively treat impurities in the medium, achieve environmental protection and resource recovery, it is particularly urgent to develop efficient purification equipment and filtration technology. However, in the prior art, the filtration method of purification equipment has problems such as low filtration efficiency, high energy consumption, and unsatisfactory separation effect.
[0003] Therefore, the filtering method of the purification equipment in the prior art has the technical problems of low filtering efficiency, high energy consumption and unsatisfactory separation effect. Summary of the invention
[0004] This application provides a filtering method and system for purification equipment for environmental protection, which solves the technical problems of low filtering efficiency, high energy consumption and unsatisfactory separation effect in the filtering method of purification equipment in the prior art. It achieves the goal of improving purification efficiency, reducing energy consumption, and realizing precise control and real-time feedback regulation of the filtering process, thereby meeting the technical effect of the current environmental protection for efficient purification technology.
[0005] The present application provides a filtering method for a purification device for environmental protection, the method comprising: determining the basic content information of the medium to be treated and the purification and separation standard, integrating and determining the filtering and separation target, including the impurity type-removal ratio. Determine the basic configuration information of the purification device, and build a separation decision model based on the filter cycle power principle. A distributed control module is constructed with the functional module as the first layer of control distribution and the filtration system as the second layer of control distribution, and a communication connection between the separation decision model and the distributed control module is established, wherein the distributed control module is scalable. Based on the filtering and separation target, the filtering and separation decision and parameter control conversion processing of the dynamic purification cycle are carried out in combination with the separation decision model to determine the filtering and separation strategy. In combination with the distributed control module, a distributed microprocessor coordinated response based on the filtering and separation strategy and filtering and separation control based on the purification device are executed. Dynamic filtering monitoring is carried out simultaneously, and filtering feedback regulation is carried out based on the microprocessor mapped with deviation control data.
[0006] In the implementation, the separation decision model includes a filtering decision layer and a parameter control conversion layer. The filtering decision layer includes a circulation derivation block and a multi-objective optimization block. With high efficiency, low energy consumption, and high separation ratio as the optimization goals, the preset number of iterations as the optimization criteria, and the optimization principles of superior iteration and inferior retreat, a multi-objective optimization block is established.
[0007] In the implementation, the distributed control module is constructed, including: traversing the first-layer control distribution and the second-layer control distribution, training N microprocessors, and the microprocessors use the parameter control processing characteristics as the training benchmark. According to the working condition, the working condition coordination relationship of the N microprocessors is determined, and a high-speed data channel is built, wherein the working condition coordination includes the same frequency coordination and the order coordination. The N microprocessors are combined with the high-speed data channel to generate the distributed control module.
[0008] In the implementation, the distributed control module is scalable, including: retrieving the device filtering records of the predetermined period, mining the update control features that meet the preset frequency, and the update control features include optimization features and new features. Based on the optimization features, the mapping microprocessor is updated and learned. Based on the new features, the microprocessor is generated, and the distributed association position is determined, and the connection is based on the high-speed data channel.
[0009] In an implementation, the determining of the filtration separation strategy includes: determining the existing filtration principle of the purification equipment, wherein the existing filtration principle includes at least physical filtration, chemical adsorption filtration and biodegradation filtration. Based on the impurity type, determining the target filtration principle, wherein the target filtration principle is at least one of the existing filtration principles. Based on the target filtration principle, the whole process decision based on the filtration separation target is executed in combination with the separation decision model to determine the filtration separation strategy.
[0010] In the implementation method, the execution of the full-process decision based on the filtering separation target includes: based on the filtering decision layer, guided by the dynamic filtering trend based on filtering energy efficiency, determining the state separation trend. Iteratively optimizing the state separation trend to screen the energy efficiency decision plan with the highest global fitness. Combined with the parameter control conversion module, the control parameters of the energy efficiency decision plan are converted to determine the parameter control decision plan. Map the energy efficiency decision plan with the parameter control decision plan to determine the filtering separation strategy.
[0011] In the implementation, the filtering feedback control includes: determining the feedback decision node based on the risk probability and the key filtering point. Based on the feedback decision node, monitoring data is transmitted back and the deviation control data is verified and determined. Based on the deviation control data, deviation features are extracted, and parameter control and control decisions and filtering feedback control are performed in response to the microprocessor of the control mapping.
[0012] The present application also provides a filtering system for a purification device for environmental protection, comprising:
[0013] The separation target acquisition module is used to determine the basic content information and purification separation standards of the medium to be processed, and integrate the filtration separation targets, including the impurity type-removal ratio.
[0014] The decision model acquisition module is used to determine the basic configuration information of the purification equipment and build a separation decision model based on the filtration cycle power principle.
[0015] A control distribution construction module is used to form a distributed control module with the functional module as the first layer of control distribution and the filtering system as the second layer of control distribution, and to establish a communication connection between the separation decision model and the distributed control module, wherein the distributed control module is scalable.
[0016] The separation strategy acquisition module is used to perform filtration separation decision and parameter control conversion processing in a dynamic purification cycle based on the filtration separation target and in combination with the separation decision model to determine the filtration separation strategy.
[0017] The separation control module is used to combine with the distributed control module to execute the distributed microprocessor coordinated response based on the filtering and separation strategy and the filtering and separation control based on the purification equipment.
[0018] The feedback control module is used to synchronously perform dynamic filtration monitoring and filter feedback control based on the microprocessor mapped with deviation control data.
[0019] The present application proposes a filtering method and system for a purification device for environmental protection, by determining the basic content information of the medium to be treated and the purification and separation standard, and integrating and determining the filtering and separation target, including the impurity type-removal ratio. The basic configuration information of the purification device is determined, and a separation decision model is built based on the filtering cycle power principle. The functional module is used as a first-layer control distribution, and the filtering system is used as a second-layer control distribution to form a distributed control module, and a communication connection between the separation decision model and the distributed control module is established, wherein the distributed control module is scalable. Based on the filtering and separation target, the filtering and separation decision and parameter control conversion processing of the dynamic purification cycle are carried out in combination with the separation decision model to determine the filtering and separation strategy. In combination with the distributed control module, the distributed microprocessor coordinated response based on the filtering and separation strategy and the filtering and separation control based on the purification device are executed. Dynamic filtering monitoring is carried out simultaneously, and filtering feedback control is carried out based on the microprocessor mapped with the deviation control data. The technical problems of low filtering efficiency, high energy consumption and unsatisfactory separation effect in the filtering method of the purification device in the prior art are solved. It achieves the goal of improving purification efficiency, reducing energy consumption, and achieving precise control and real-time feedback regulation of the filtration process, thereby meeting the current environmental protection technical effects of high-efficiency purification technology. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.
[0021] Figure 1 A schematic flow chart of a filtering method for a purification device for environmental protection provided in an embodiment of the present application;
[0022] Figure 2 A schematic diagram of the structure of a filtration system of a purification device for environmental protection provided in an embodiment of the present application.
[0023] Explanation of the reference numerals: separation target acquisition module 11, decision model acquisition module 12, control distribution construction module 13, separation strategy acquisition module 14, separation control module 15, feedback regulation module 16. DETAILED DESCRIPTION
[0024] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.
[0025] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.
[0026] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.
[0027] The present application embodiment provides a filtering method and system for a purification device for environmental protection, such as Figure 1 As shown, the method includes:
[0028] Determine the basic content information and purification separation standards of the medium to be treated, and integrate to determine the filtration separation goals, including impurity type-removal ratio.
[0029] Determine the basic configuration information of the purification equipment and build a separation decision model based on the filtration cycle dynamics principle.
[0030] A distributed control module is formed by taking the functional module as the first layer of control distribution and the filtering system as the second layer of control distribution, and a communication connection is established between the separation decision model and the distributed control module, wherein the distributed control module has scalability.
[0031] Determine the basic content information and purification and separation standards of the medium to be treated, that is, the treatment target. The basic content information is the content data of various substances in the treatment target, and the purification and separation standard is the impurity content target that needs to be achieved after purification. Perform difference processing on the corresponding impurities in the basic content information and the purification and separation standard, obtain the object to be filtered and separated in the basic content information and the corresponding removal amount data, construct the impurity type-removal ratio, the impurity type is the filtering and separation object, and the removal amount data is the removal ratio, and obtain the filtering and separation target. Subsequently, determine the basic configuration information of the purification equipment, and the basic configuration information is the hardware category equipped with the purification equipment, including: filtering hardware, etc. Based on the filtering cycle power principle, that is, the equipment filtering principle, the filtering cycle power principle is the working mode of the filtering hardware, such as permeation filtration, adsorption filtration, etc. Further, the environmental protection purification equipment includes a variety of functional modules, such as flow control module, filtration system, temperature control module, etc. The functional module is a layer of control distribution, and the layer of control distribution is the equipment control parameters of each module equipment in the functional module. The parameter distribution composed of the equipment control parameters of multiple devices is included in one layer of control distribution. The filtering system is a two-layer control distribution, and the two-layer control distribution is the device control parameters of each device in the filtering system, and the two-layer control distribution contains parameter distribution composed of device control parameters of multiple devices. A distributed control module is formed through the first-layer control distribution and the second-layer control distribution, and a communication connection is established between the separation decision model and the distributed control module, so that the output result of the separation decision model can directly interact and communicate with the distributed control module, wherein the distributed control module has scalability.
[0032] The method provided in the embodiment of the present application also includes:
[0033] The filtering decision layer includes a circulation derivation block and a multi-objective optimization block.
[0034] With high efficiency, low energy consumption and high separation ratio as optimization goals, a multi-objective optimization block is established.
[0035] The separation decision model includes a filtering decision layer and a parameter control conversion layer. The filtering decision layer includes a circulation derivation block and a multi-objective optimization block. The circulation derivation block is used to obtain the target filtering principle according to the existing filtering principle of the purification equipment and the corresponding impurity type. With high efficiency, low energy consumption and high separation ratio as the optimization goals, a multi-objective optimization block is established. And the filtering separation strategy is determined through the multi-objective optimization block according to the target filtering principle.
[0036] The method provided in the embodiment of the present application also includes:
[0037] The existing filtering principle of the purification device is determined, and the existing filtering principle at least includes physical filtration, chemical adsorption filtration and biodegradation filtration.
[0038] Based on the impurity type, a target filtering principle is determined, wherein the target filtering principle is at least one of the existing filtering principles.
[0039] Based on the target filtering principle and in combination with the separation decision model, a full-process decision based on the filtering and separation target is executed to determine the filtering and separation strategy.
[0040] Determine the existing filtering principles of the purification equipment, where the existing filtering principles are filtering principles included in the equipment, including at least physical filtration, chemical adsorption filtration and biodegradation filtration. Based on the obtained filtering and separation target, obtain the impurity types that need to be removed, each impurity type corresponds to one or more removal filtering principles, and determine the target filtering principles corresponding to all impurity types, wherein the target filtering principle is at least one of the existing filtering principles. Based on the target filtering principle, the full process decision based on the filtering and separation target is executed in combination with the separation decision model to determine the filtering and separation strategy.
[0041] The method provided in the embodiment of the present application also includes:
[0042] Based on the filtering decision layer, the state separation trend is determined with the dynamic filtering trend based on filtering energy efficiency as a guide.
[0043] The state separation trend is iteratively optimized to select the energy efficiency decision-making solution with the highest global fitness.
[0044] Combined with the parameter control conversion module, the control parameters of the energy efficiency decision-making scheme are converted to determine the parameter control decision-making scheme.
[0045] The energy efficiency decision-making scheme and the parameter control decision-making scheme are mapped to determine the filtering and separation strategy.
[0046] Based on the filtering decision layer, the impurity state separation trend corresponding to each filtering principle is stored in the filtering decision layer, guided by the dynamic filtering trend based on filtering energy efficiency, wherein the dynamic filtering trend of filtering energy efficiency is obtained through experiments, and the dynamic filtering trend of filtering energy efficiency reflects the different filtering amounts and corresponding filtering energy consumption data of various target filtering principles when filtering different concentrations of filterable impurity types. According to the target filtering principle, the state separation trend is determined, and the state separation trend contains the energy consumption parameters corresponding to the concentration of filterable impurity types and the filtering amount corresponding to each target filtering principle. The multi-objective optimization block is constructed based on the neural network model, and the sample state separation trend is obtained. The sample filtering separation target and the highest energy efficiency decision plan under the corresponding sample state separation trend are set. The decision plan includes internal and external pressure control, flow control, temperature control, etc., and training data is constructed. The neural network model is supervised and trained according to the training data until the highest energy efficiency decision plan output by the model meets the preset accuracy rate. The model training is completed to obtain the multi-objective optimization block. The filtering separation target and the state separation trend are input into the multi-objective optimization block to screen the energy efficiency decision plan with the highest global fitness, that is, to obtain the decision plan with the lowest energy consumption. Combined with the parameter control conversion module, the energy efficiency decision-making scheme is converted into actual equipment control parameters to determine the parameter control decision-making scheme.
[0047] The method provided in the embodiment of the present application also includes:
[0048] The first-layer control distribution and the second-layer control distribution are traversed to train N microprocessors, wherein the microprocessors use the parameter control processing characteristics as training benchmarks.
[0049] Based on the working conditions, the working condition coordination relationship of the N microprocessors is determined to build a high-speed data channel, wherein the working condition coordination includes same-frequency coordination and sequential coordination.
[0050] The N microprocessors are combined with the high-speed data channel to generate the distributed control module.
[0051] Traverse the first-layer control distribution and the second-layer control distribution, extract the parameter control processing features corresponding to the first-layer control distribution of the functional module, extract the parameter control processing features corresponding to the second-layer control distribution of the filtering system, the parameter control processing features are specific control parameters, train N microprocessors, each microprocessor is used to process the corresponding parameter control processing features, and N is the same as the number of parameter control processing features. When training the microprocessor, obtain the sample filtering and separation strategy of the parameter control processing features corresponding to each processor and the control analysis features obtained based on the strategy, that is, the specific control parameters during operation, use the sample filtering and separation strategy and the control analysis features obtained based on the strategy as training data, supervise the neural network model, obtain the converged model and obtain the corresponding microprocessor. Further, the working condition is the working order of the filtering and separation strategy workflow, and the working condition coordination relationship of the N microprocessors is determined to build a high-speed data channel, wherein the working condition coordination includes same-frequency coordination and sequential coordination, the same-frequency coordination is the coordinated data interaction at the same time node, and the sequential coordination is the coordinated data interaction at the adjacent time nodes. Among them, the interactive data includes: detection data of the control object obtained in real time by sensors, such as temperature, flow rate, etc., which are used to perform feedback control in combination with the output of the microprocessor, and combine the N microprocessors with the high-speed data channel to generate the distributed control module.
[0052] The method provided in the embodiment of the present application also includes:
[0053] Retrieve equipment filtering records of a predetermined period and mine update control features that meet a preset frequency, wherein the update control features include optimized features and newly added features.
[0054] Based on the optimization features, update learning of the mapping microprocessor is performed.
[0055] Based on the newly added features, a microprocessor is generated, and a distributed associated position is determined, and connectivity is achieved based on a high-speed data channel.
[0056] The distributed control module is scalable, including: retrieving the device filtering records of a predetermined period, mining the updated control features that meet the preset frequency, that is, obtaining the frequency of the control features updated within the predetermined period, and obtaining the updated control features that meet or are greater than or equal to the preset frequency. The updated control features include optimized features and newly added features. The optimized features are features for optimizing the parameters of the original control features, and the newly added features are newly added control features. Based on the optimized features, the updated learning of the mapping microprocessor is performed, that is, the microprocessor is updated and learned according to the optimized features, so that the microprocessor can adapt to the processing of the optimized features. For the newly added features, since they are newly added, a new microprocessor is constructed based on the corresponding data. Based on the newly added features, the microprocessor is generated, and the distributed associated position is determined, and connected based on the high-speed data channel.
[0057] Based on the filtration separation target, the filtration separation decision and parameter control conversion processing of the dynamic purification cycle are performed in combination with the separation decision model to determine the filtration separation strategy.
[0058] In combination with the distributed control module, a distributed microprocessor coordinated response based on the filtering and separation strategy and filtering and separation control based on the purification equipment are executed.
[0059] Dynamic filtration monitoring is carried out simultaneously, and filter feedback regulation is performed based on the microprocessor mapped with deviation control data.
[0060] Based on the filtering and separation target, the filtering and separation decision and parameter control conversion processing of the dynamic purification cycle are carried out in combination with the separation decision model to determine the filtering and separation strategy. After determining the filtering and separation strategy, the filtering and separation strategy is input into the distributed control module to execute the distributed microprocessor coordinated response based on the filtering and separation strategy, that is, coordinated response control is performed by the distributed microprocessor according to the filtering and separation strategy, and filtering and separation control based on the purification equipment. Finally, dynamic filtering monitoring is carried out synchronously, and filtering feedback control is performed based on the microprocessor based on the deviation control data mapping, that is, according to the data deviation generated by the microprocessor control parameters and the actual dynamic filtering monitoring data, so as to ensure the accurate implementation of the microprocessor control parameters. The technical problems of low filtering efficiency, high energy consumption and unsatisfactory separation effect in the filtering method of the purification equipment in the prior art are solved. It achieves the goal of improving purification efficiency and reducing energy consumption, and can also realize accurate control and real-time feedback control of the filtering process, thereby meeting the technical effect of the current environmental protection on efficient purification technology.
[0061] The method provided in the embodiment of the present application also includes:
[0062] Based on the risk probability and key filtering points, the feedback decision nodes are determined.
[0063] Based on the feedback decision node, monitoring data is fed back and the deviation control data is verified and determined.
[0064] Deviation features are extracted based on the deviation control data, and parameter control and regulation decisions and filtering feedback regulation are performed in response to the microprocessor of the control map.
[0065] The filtering feedback control includes: determining the feedback decision node based on the risk probability and the key filtering point, wherein the risk probability is the probability that the pre-set control parameter may be abnormal. The key filtering point is the key node in the filtering process, and the feedback decision node is determined, wherein the feedback decision node is the parameter with a higher risk probability corresponding to the key node. Based on the feedback decision node, the monitoring data is transmitted back and the deviation control data is verified to determine the difference between the transmitted monitoring data and the actual control parameter. Deviation features are extracted based on the deviation control data, and the deviation features are the corresponding control objects. In response to the microprocessor of the corresponding control mapping, parameter control and control decisions and filtering feedback control are performed.
[0066] In the above, refer to Figure 1 A filtering method for a purification device for environmental protection according to an embodiment of the present invention is described in detail. Figure 2 A filtering system of a purification device for environmental protection according to an embodiment of the present invention is described.
[0067] A filtering system for a purification device for environmental protection according to an embodiment of the present invention solves the technical problems of low filtering efficiency, high energy consumption, and unsatisfactory separation effect in the filtering method of the purification device in the prior art. It achieves the goal of improving purification efficiency and reducing energy consumption, and can also achieve precise control and real-time feedback regulation of the filtering process, thereby meeting the technical effects of the current environmental protection on efficient purification technology. A filtering system for a purification device for environmental protection includes: a separation target acquisition module 11, a decision model acquisition module 12, a control distribution construction module 13, a separation strategy acquisition module 14, a separation control module 15, and a feedback regulation module 16.
[0068] The separation target acquisition module 11 is used to determine the basic content information and purification separation standard of the medium to be processed, and integrate and determine the filtration separation target, including the impurity type-removal ratio.
[0069] The decision model acquisition module 12 is used to determine the basic configuration information of the purification equipment and build a separation decision model based on the filtering cycle power principle.
[0070] The control distribution construction module 13 is used to form a distributed control module with the functional module as the first layer of control distribution and the filtering system as the second layer of control distribution, and to establish a communication connection between the separation decision model and the distributed control module, wherein the distributed control module is scalable.
[0071] The separation strategy acquisition module 14 is used to perform filtration separation decision and parameter control conversion processing in a dynamic purification cycle based on the filtration separation target and in combination with the separation decision model to determine the filtration separation strategy.
[0072] The separation control module 15 is used to combine with the distributed control module to execute the distributed microprocessor coordinated response based on the filtering and separation strategy and the filtering and separation control based on the purification equipment.
[0073] The feedback control module 16 is used to synchronously perform dynamic filtration monitoring and perform filtration feedback control based on a microprocessor mapped with deviation control data.
[0074] The specific configuration of the decision model acquisition module 12 will be described in detail below. The decision model acquisition module 12 may further include: the separation decision model includes a filtering decision layer and a parameter control conversion layer. The filtering decision layer includes a circulation derivation block and a multi-objective optimization block. With high efficiency, low energy consumption, and high separation ratio as optimization goals, a preset number of iterations as the optimization standard, and superior iteration and inferior retreat as the optimization principle, a multi-objective optimization block is established.
[0075] The specific configuration of the control distribution construction module 13 will be described in detail below. The control distribution construction module 13 further includes: the construction of the distributed control module includes: traversing the first-layer control distribution and the second-layer control distribution, training N microprocessors, and the microprocessors use the parameter control processing characteristics as the training benchmark. According to the working conditions, the working condition coordination relationship of the N microprocessors is determined, and a high-speed data channel is built, wherein the working condition coordination includes co-frequency coordination and order coordination. Combine the N microprocessors with the high-speed data channel to generate the distributed control module.
[0076] The specific configuration of the control distribution construction module 13 will be described in detail below. The control distribution construction module 13 may further include: The distributed control module is scalable, including: retrieving the device filtering records of a predetermined period, mining the update control features that meet the preset frequency, and the update control features include optimized features and newly added features. Based on the optimized features, the updated learning of the mapping microprocessor is performed. Based on the newly added features, the microprocessor is generated, and the distributed associated position is determined, and the connection is based on the high-speed data channel.
[0077] The specific configuration of the separation strategy acquisition module 14 will be described in detail below. The separation strategy acquisition module 14 further includes: the determination of the filtration separation strategy includes: determining the existing filtration principle of the purification equipment, and the existing filtration principle includes at least physical filtration, chemical adsorption filtration and biodegradation filtration. Based on the impurity type, determine the target filtration principle, wherein the target filtration principle is at least one of the existing filtration principles. Based on the target filtration principle, the whole process decision based on the filtration separation target is executed in combination with the separation decision model to determine the filtration separation strategy.
[0078] The specific configuration of the separation strategy acquisition module 14 will be described in detail below. The separation strategy acquisition module 14 further includes: the execution of the full-process decision based on the filtering separation target, including: based on the filtering decision layer, guided by the dynamic filtering trend based on filtering energy efficiency, determine the state separation trend. Iterate and optimize the state separation trend to screen the energy efficiency decision plan with the highest global fitness. Combined with the parameter control conversion module, the control parameters of the energy efficiency decision plan are converted to determine the parameter control decision plan. Map the energy efficiency decision plan with the parameter control decision plan to determine the filtering separation strategy.
[0079] The specific configuration of the feedback control module 16 will be described in detail below. The feedback control module 16 further includes: the filtering feedback control includes: determining the feedback decision node based on the risk probability and the key filtering point. Based on the feedback decision node, monitoring data is transmitted back and the deviation control data is verified and determined. Based on the deviation control data, deviation features are extracted, and the microprocessor responds to the control mapping to make parameter control decisions and filtering feedback control.
[0080] A filtering system for a purification device for environmental protection provided by an embodiment of the present invention can execute a filtering method for a purification device for environmental protection provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.
[0081] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or the server, and the various units and modules included are only divided according to functional logic, but are not limited to the above divisions, as long as the corresponding functions can be achieved. In addition, the specific names of the functional units are only for the convenience of distinguishing from each other, and are not used to limit the scope of protection of the present invention.
[0082] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.
Claims
1. A filtering method for a purification device for environmental protection, characterized in that: The method comprises: Determine the basic content information and purification and separation standards of the medium to be treated, and integrate and determine the filtration and separation goals, including impurity type-removal ratio; Determine the basic configuration information of the purification equipment and build a separation decision model based on the filter cycle dynamic principle, which is the working method of the filter hardware; The functional module is used as a first-layer control distribution, and the filtering system is used as a second-layer control distribution to form a distributed control module, and a communication connection is established between the separation decision model and the distributed control module, wherein the distributed control module has scalability; Based on the filtration separation target, the filtration separation decision and parameter control conversion processing of the dynamic purification cycle are performed in combination with the separation decision model to determine the filtration separation strategy; In combination with the distributed control module, a distributed microprocessor coordinated response based on the filtration separation strategy and a filtration separation control based on the purification device are executed; Simultaneously carry out dynamic filtration monitoring and filter feedback control based on the microprocessor of deviation control data mapping; The separation decision model includes a filtering decision layer and a parameter control conversion layer; The filtering decision layer includes a circulation derivation block and a multi-objective optimization block. The circulation derivation block is used to obtain the target filtering principle according to the existing filtering principle of the purification equipment and the corresponding impurity type; The multi-objective optimization block is constructed based on the neural network model, obtains the sample state separation trend, sets the sample filtering separation target and the highest energy efficiency decision plan under the corresponding sample state separation trend, the decision plan includes internal and external pressure control, flow control, temperature control, constructs training data, and supervises the neural network model according to the training data until the highest energy efficiency decision plan output by the model meets the preset accuracy rate. The model training is completed to obtain the multi-objective optimization block; The determining of the filtration separation strategy comprises: Determine the existing filtering principle of the purification equipment, wherein the existing filtering principle at least includes physical filtration, chemical adsorption filtration and biodegradation filtration; Based on the impurity type, determining a target filtering principle, wherein the target filtering principle is at least one of the existing filtering principles; Based on the target filtering principle, combined with the separation decision model, a full-process decision based on the filtering and separation target is executed to determine the filtering and separation strategy; The execution is based on the full process decision of the filtration separation target, including: Based on the filtering decision layer, a state separation trend is determined guided by a dynamic filtering trend based on filtering energy efficiency; Iteratively optimizing the state separation trend to select the energy efficiency decision-making solution with the highest global fitness; Combined with the parameter control conversion module, the control parameters of the energy efficiency decision-making scheme are converted to determine the parameter control decision-making scheme; The energy efficiency decision-making scheme and the parameter control decision-making scheme are mapped to determine the filtering and separation strategy.
2. The method according to claim 1, characterized in that The distributed control module comprises: Traversing the first-layer control distribution and the second-layer control distribution, training N microprocessors, wherein the microprocessors use parameter control processing features as training benchmarks; According to the working condition, the working condition coordination relationship of the N microprocessors is determined to build a high-speed data channel, wherein the working condition coordination includes same-frequency coordination and order coordination; The N microprocessors are combined with the high-speed data channel to generate the distributed control module.
3. The method according to claim 2, characterized in that The distributed control module is scalable and includes Retrieving device filtering records of a predetermined period, and mining update control features that meet a preset frequency, wherein the update control features include optimized features and newly added features; Based on the optimization features, updating and learning the mapping microprocessor is performed; Based on the newly added features, a microprocessor is generated, and a distributed associated position is determined, and connectivity is achieved based on a high-speed data channel.
4. The method according to claim 1, characterized in that The filtering feedback regulation comprises: Determine the feedback decision nodes based on risk probability and key filtering points; Based on the feedback decision node, monitoring data is transmitted back and the deviation control data is verified and determined; Deviation features are extracted based on the deviation control data, and parameter control and regulation decisions and filtering feedback regulation are performed in response to the microprocessor of the control map.
5. A filtering system for a purification device for environmental protection, characterized in that: The system is used to execute the method according to any one of claims 1 to 4, and the system comprises: Separation target acquisition module, used to determine the basic content information and purification separation standards of the medium to be processed, and integrate to determine the filtration separation target, including impurity type-removal ratio; A decision model acquisition module is used to determine the basic configuration information of the purification equipment and build a separation decision model based on the filter cycle power principle, which is the working method of the filter hardware; A control distribution construction module, used to form a distributed control module with the functional module as a first-layer control distribution and the filtering system as a second-layer control distribution, and to establish a communication connection between the separation decision model and the distributed control module, wherein the distributed control module has scalability; A separation strategy acquisition module, used to perform filtration separation decision and parameter control conversion processing in a dynamic purification cycle based on the filtration separation target and in combination with the separation decision model, and determine the filtration separation strategy; A separation control module, used for combining with the distributed control module to execute a distributed microprocessor coordinated response based on the filtering and separation strategy and filtering and separation control based on the purification equipment; The feedback control module is used to synchronously perform dynamic filtration monitoring and filter feedback control based on the microprocessor mapped with deviation control data.
