Filter unit coordinated water treatment method and device under multi-point water quality monitoring

Abstract

The present invention discloses a method and device for coordinated water treatment of filter units under multi-point water quality monitoring, which relates to the field of water treatment technology. The method includes: obtaining multiple types of continuous filter units, and performing post-filtration impact cost analysis under fault conditions to generate a first type of filter unit; performing redundant filter unit division configuration and marking for the first type of filter unit; configuring a set of monitoring points; performing water quality monitoring, matching multi-stage filter units and multi-stage filter parameters according to the monitoring results; performing collaborative filtering, and at the same time collecting filter monitoring data and performing fault analysis through a specific water quality sensor at the second monitoring point; switching the first type of redundant filter unit for filtering processing. The present invention solves the technical problems of unstable operation of the water treatment system and poor water quality treatment effect in the prior art, and achieves the technical effect of ensuring stable and efficient operation of the water treatment system and improving the ability to cope with filter unit failures and water quality treatment effects.

Description

Technical Field

[0001] The present invention relates to the technical field of water treatment, and in particular to a method and device for coordinated water treatment of filtering units under multi-point water quality monitoring. Background Art

[0002] Water treatment systems play a vital role in ensuring the safety of people's domestic and industrial water. However, traditional water treatment technologies face a series of technical problems in practical applications. In traditional water treatment systems, the design and management of filter units are often not perfect. On the one hand, in terms of filter unit failure handling, there is a lack of comprehensive analysis of the post-effect of filter unit failures in the entire water treatment process. Usually, a water treatment system contains multiple continuous filter units. A failure in a filter unit may have different degrees of impact on subsequent filtration links, but it is difficult for existing technologies to accurately assess the cost of such impacts, which leads to a lack of targeted strategies in dealing with failures, which may seriously affect the water quality of the entire water treatment system and even prevent it from operating normally. On the other hand, the configuration of redundant filter units lacks scientific basis. Most of the existing redundant designs are simple backups, without considering the criticality of different filter units in the entire system and the differences in the impact of failures on subsequent processes, which may lead to waste of resources or the inability of redundant units to effectively replace key filter units when they fail, thereby affecting the continuity of water treatment and the stability of water quality.

[0003] The existing technology has technical problems such as unstable operation of the water treatment system and poor water quality treatment effect. Summary of the invention

[0004] The present application provides a method and device for coordinated water treatment of filtration units under multi-point water quality monitoring, which is used to solve the technical problems of unstable operation of water treatment systems and poor water quality treatment effects in the prior art.

[0005] In view of the above problems, the present application provides a method and device for coordinated water treatment of filtration units under multi-point water quality monitoring.

[0006] In a first aspect of the present application, a filtration unit coordinated water treatment method under multi-point water quality monitoring is provided, the method comprising:

[0007] Acquire multiple types of continuous filtering units that are continuously executed in the water treatment system, and perform post-filtering impact cost analysis under fault conditions to generate a first type of filtering unit whose post-filtering cost index is greater than or equal to a preset cost index; divide and configure redundant filtering units for the first type of filtering units and mark them to generate a first type of main filtering unit and a first type of redundant filtering unit; configure a monitoring point set, wherein the monitoring point set includes a first monitoring point and a second monitoring point, wherein the first monitoring point is a source water inlet, configured with a multi-source water quality sensor, and the second monitoring point is a water inlet, a water outlet and a central processing area of ​​the multiple types of continuous filtering units, configured with a specific water quality sensor; perform water quality monitoring based on the multi-source water quality sensor at the first monitoring point, and match multi-stage filtering units and multi-stage filtering parameters in the multiple types of continuous filtering units according to the monitoring results; perform collaborative filtering based on the multi-stage filtering units and the multi-stage filtering parameters, and collect filtering monitoring data and perform fault analysis through the specific water quality sensor at the second monitoring point to generate a faulty filtering unit; if the faulty filtering unit belongs to the first type of main filtering unit, switch the first type of redundant filtering unit to perform filtering processing.

[0008] In a second aspect of the present application, a filtration unit coordinated water treatment device under multi-point water quality monitoring is provided, the device comprising:

[0009] A first-class filter unit acquisition module, the first-class filter unit acquisition module is used to acquire multiple types of continuous filter units continuously executed in the water treatment system, and perform post-filtration impact cost analysis under fault conditions to generate a first-class filter unit whose post-filtration cost index is greater than or equal to a preset cost index; a filter unit acquisition module, the filter unit acquisition module is used to perform redundant filter unit division configuration and marking for the first-class filter unit, and generate a first-class main filter unit and a first-class redundant filter unit; a water quality sensor configuration module, the water quality sensor configuration module is used to configure a monitoring point set, wherein the monitoring point set includes a first monitoring point and a second monitoring point, wherein the first monitoring point is a source water inlet, and a multi-source water quality sensor is configured, and the second monitoring point is the ... The water inlet, water outlet and central processing area of ​​the multiple types of continuous filtering units are equipped with specific water quality sensors; a water quality monitoring module, which performs water quality monitoring based on the multi-source water quality sensors at the first monitoring point, and matches multi-stage filtering units and multi-stage filtering parameters in the multiple types of continuous filtering units according to the monitoring results; a fault filtering unit generation module, which performs collaborative filtering based on the multi-stage filtering units and the multi-stage filtering parameters, and at the same time collects filtering monitoring data and performs fault analysis through the specific water quality sensors at the second monitoring point to generate a fault filtering unit; a filtering processing module, which is used to switch the first type of redundant filtering unit to perform filtering processing if the faulty filtering unit belongs to the first type of main filtering unit.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] Acquire multiple types of continuous filtering units that are continuously executed in the water treatment system, and perform post-filtering impact cost analysis under fault conditions to generate a first type of filtering unit whose post-filtering cost index is greater than or equal to a preset cost index; divide and configure redundant filtering units for the first type of filtering units and mark them; configure a set of monitoring points; perform water quality monitoring based on the multi-source water quality sensors at the first monitoring points, and match multi-stage filtering units and multi-stage filtering parameters in the multiple types of continuous filtering units according to the monitoring results; perform collaborative filtering based on the multi-stage filtering units and the multi-stage filtering parameters, and at the same time collect filtering monitoring data and perform fault analysis through the specific water quality sensors at the second monitoring points to generate a faulty filtering unit; if the faulty filtering unit belongs to the first type of main filtering unit, switch to the first type of redundant filtering unit for filtering processing. The technical effect of ensuring the stable and efficient operation of the water treatment system and improving the ability to cope with filtering unit failures and the water quality treatment effect is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic flow chart of a filtration unit coordinated water treatment method under multi-point water quality monitoring provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a filtration unit coordinated water treatment device under multi-point water quality monitoring provided in an embodiment of the present application.

[0015] Explanation of the reference numerals: first type filter unit acquisition module 10 , filter unit acquisition module 20 , water quality sensor configuration module 30 , water quality monitoring module 40 , faulty filter unit generation module 50 , filter processing module 60 . DETAILED DESCRIPTION

[0016] The present application provides a method and device for coordinated water treatment of filtration units under multi-point water quality monitoring, which is used to solve the technical problems of unstable operation of water treatment systems and poor water quality treatment effects in the prior art.

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a filtration unit coordinated water treatment method under multi-point water quality monitoring, the method comprising:

[0019] Step S100: obtaining multiple types of continuous filtering units continuously executed in the water treatment system, and performing post-filtration impact cost analysis under fault conditions to generate a first type of filtering unit whose post-filtration cost index is greater than or equal to a preset cost index.

[0020] Specifically, a comprehensive review of the water treatment system is conducted to obtain various types of continuous filtering units that are being continuously executed. These filtering units play a role in sequence in the water treatment process and jointly undertake the task of purifying water quality. Next, in order to evaluate the impact of each filtering unit on the subsequent filtering link under the condition of failure, it is necessary to conduct a post-filtration impact cost analysis under fault conditions. By simulating the scene of a certain filtering unit failure, the impact on the work efficiency and water purification effect of the subsequent filtering units is observed, and these impacts are converted into quantifiable indicators, namely, post-filtration cost indicators. Finally, the calculated post-filtration cost index is compared with the preset cost index, and those filtering units whose post-filtration cost index is greater than or equal to the preset cost index are screened out. They are defined as the first-class filtering units. These first-class filtering units are in a key position in the entire water treatment system. Once a failure occurs, it will have a more serious impact on the subsequent water quality treatment, so they need to be given special attention.

[0021] Step S200: performing division configuration and marking of redundant filter units for the first type of filter units to generate first type main filter units and first type redundant filter units.

[0022] Specifically, operations are carried out on the identified first-class filter units. In view of the fact that the first-class filter units have a greater impact on the post-filtration cost when they fail, in order to ensure the stability of the entire water treatment process, it is necessary to divide and configure redundant filter units. A small number of units are separated from the original first-class filter units. These separated units are usually in standby status and do not participate in routine water treatment work. The parts that operate normally and undertake the main filtration tasks are marked as first-class main filter units, and the standby units are marked as first-class redundant filter units. When the first-class main filter unit fails, the first-class redundant filter unit can be put into use in time, thereby effectively reducing the adverse effects of the failure of the main filter unit on subsequent processes, ensuring that the entire water treatment system can operate continuously and stably, and maintaining the effect and efficiency of water quality treatment.

[0023] Step S300: configure a monitoring point set, wherein the monitoring point set includes a first monitoring point and a second monitoring point, wherein the first monitoring point is a source water inlet, configured with a multi-source water quality sensor, and the second monitoring point is a water inlet, a water outlet and a central processing area of ​​the multiple types of continuous filtration units, configured with a specific water quality sensor.

[0024] Specifically, we set out to build a set of monitoring points to achieve comprehensive and accurate water quality monitoring of the water treatment system. The set of monitoring points includes two key parts, namely the first monitoring point and the second monitoring point. The source water inlet is determined as the first monitoring point, and a multi-source water quality sensor is configured at this location. The multi-source water quality sensor can detect the water quality of the source water from multiple dimensions. For example, it can simultaneously monitor multiple indicators such as pH, dissolved oxygen, various ion concentrations, and organic matter content in the water, so as to fully grasp the initial water quality of the raw water. The second monitoring point is set at the water inlet, water outlet, and central processing area of ​​multiple types of continuous filtration units. A specific water quality sensor is configured at the water inlet to detect the water quality parameters before entering the filtration unit. These parameters can reflect the effect of the previous treatment stage and the changes in the raw water quality; the corresponding sensor is configured at the water outlet to detect the degree of improvement of the water quality after being treated by the filtration unit; the sensor is configured in the central processing area to monitor the dynamic changes of water quality during the filtration process in real time. For specific substances removed by different filter units, sensors are configured to detect these substances. For example, for filter units that remove heavy metals, sensors are configured to detect the concentration of heavy metal ions. This configuration can provide accurate data support for subsequent water quality monitoring, filter unit matching, fault analysis and other operations, ensuring efficient and stable operation of the water treatment system.

[0025] Step S400: performing water quality monitoring based on the multi-source water quality sensors at the first monitoring point, and matching multi-stage filtering units and multi-stage filtering parameters in the multiple types of continuous filtering units according to the monitoring results.

[0026] Specifically, make full use of the multi-source water quality sensors equipped at the first monitoring point to carry out comprehensive water quality monitoring. The multi-source water quality sensors continuously monitor the water quality of the source water inlet in real time to obtain multi-dimensional water quality data, including but not limited to pH, temperature, turbidity, dissolved oxygen, various ion concentrations, and organic pollutant content. These data are quickly transmitted and analyzed in depth to form detailed water quality monitoring results. Then, based on the above monitoring results, accurate matching is performed among multiple types of continuous filtration units to determine the most suitable multi-stage filtration unit. Through a comprehensive assessment of the source water quality, for example, when the content of a certain pollutant in the source water is high, a specific filtration unit with high efficiency in removing the pollutant is selected from a large number of continuous filtration units, and the combination of multi-stage filtration units is determined according to their order and synergistic relationship in the water treatment process. After determining the multi-stage filtration unit, further match the corresponding multi-stage filtration parameters for each level of filtration unit according to the specific characteristics and requirements of the source water quality. This process involves in-depth mining and analysis of historical filtration data. By comparing the best operating parameters of each filtration unit under similar water quality conditions in the past, combined with the special water quality conditions in the current monitoring results, key parameters such as filtration speed, filtration pressure, backwashing cycle, etc. are set for each level of filtration unit. Through such a fine matching process, it is ensured that the entire water treatment system can perform efficient water quality treatment with the most optimized configuration and operating parameters according to the real-time changes in the source water quality, thereby improving the quality and efficiency of water resource purification.

[0027] Step S500: performing collaborative filtering based on the multi-stage filtering unit and the multi-stage filtering parameters, and collecting filtering monitoring data and performing fault analysis through the specific water quality sensor at the second monitoring point to generate a fault filtering unit.

[0028] Specifically, each level of filtration unit starts working according to the matching multi-level filtration parameters. In the order of water flow, the first-level filtration unit performs preliminary treatment on the incoming water according to the set parameters such as filtration speed and pressure to remove specific types of impurities. For example, if the filtration unit at this level is mainly for large suspended particles, its parameters such as filter mesh aperture and water flow rate will ensure the effective interception of these large particles. The water after the first level of filtration flows into the second-level filtration unit, and the second-level filtration unit further processes specific pollutants in the water according to its own filtration parameters, such as specific adsorption material characteristics, chemical reaction conditions, etc. The filtration units at each level cooperate with each other, and the output of the previous level filtration unit is used as the input of the next level filtration unit to form a continuous and collaborative filtration link, gradually improving the water purification effect. The specific water quality sensor at the second monitoring point continuously collects data throughout the collaborative filtration process. At the water inlet, central processing area and outlet of each filtration unit, the sensor collects water quality sample data at a set time interval (for example, every 5 minutes). These data cover parameters related to the target treatment material of the filter unit. For example, for the filter unit that removes heavy metals, the sensor will detect the concentration of heavy metal ions in the water; for the filter unit that removes organic matter, the sensor will detect indicators such as chemical oxygen demand (COD) and biochemical oxygen demand (BOD). After data collection, it is transmitted to the fault analysis module. For each filter unit, a water quality parameter model under normal operating conditions is established. The model is based on historical operating data and theoretical water quality change curves under fault-free conditions, and includes the expected value range of water quality parameters at each monitoring point at different time points. Then, the real-time collected filtration monitoring data is compared with the normal operating model of the corresponding filter unit, and the deviation between the actual measured value and the expected value at each monitoring point is calculated, for example, using the root mean square error (RMSE) as a deviation measurement indicator. For each filter unit, the deviation of its water inlet, central processing area and water outlet is evaluated comprehensively. If the deviation of at least one monitoring point of a filter unit exceeds the preset threshold (the threshold is set according to the type of filter unit and the degree of impact on water quality) at multiple consecutive time points (such as 10 consecutive data collections), the filter unit is determined to be a faulty filter unit. At the same time, the time of the fault, specific deviation data and other information are recorded to further analyze the cause of the fault and take corresponding measures in the future, so as to timely and accurately find the faulty filter unit and ensure the stable operation of the water treatment system.

[0029] Step S600: If the faulty filter unit belongs to the first type of main filter unit, switch to the first type of redundant filter unit for filtering processing.

[0030] Specifically, once it is determined that the faulty filter unit belongs to the first type of main filter unit, the switching mechanism is quickly started. First, the operation of the first type of main filter unit is stopped immediately to prevent it from continuing to have adverse effects or further damage. Then, the first type of redundant filter unit corresponding to the faulty main filter unit is put into use, and the status of related equipment such as pipeline valves is automatically adjusted to guide the water flow to smoothly switch from the faulty first type of main filter unit to the first type of redundant filter unit to ensure the continuity of the entire water treatment process. During the switching process, the startup and operation status of the first type of redundant filter unit is monitored in real time, including its filtering effect, pressure changes, flow stability and other key parameters, to ensure that it can normally take over the work of the faulty main filter unit, maintain the stable operation of the water treatment system, and effectively ensure that the quality and efficiency of water treatment are not greatly affected, while also buying time for the subsequent repair or replacement of the faulty main filter unit.

[0031] In a possible implementation, step S100 further includes:

[0032] Step S110: performing simulation modeling of the continuous filtration process for the multiple types of continuous filtration units to generate a continuous filtration simulation model.

[0033] Step S120: configuring the filtration test water quality sample under the whole process.

[0034] Step S130: loading the filtration test water quality sample into the continuous filtration simulation model, and performing fault control on any type of filtration unit to generate multiple groups of post-filtration impact test data sets corresponding to the multiple types of continuous filtration units.

[0035] Step S140: Calculate impact costs based on the multiple groups of post-filtering impact test data sets to generate multiple post-filtering cost indicators.

[0036] Step S150: Compare the multiple post-filtering cost indicators with the preset cost indicator to generate the first type of filtering unit.

[0037] Specifically, firstly, the principle of system dynamics is applied to treat multiple types of continuous filtration units as a dynamic system, and the relationship between the material flow, energy flow and information flow between each unit is analyzed to determine the boundaries and main variables of the system. For each continuous filtration unit, the finite element analysis method is used to discretize its internal structure, and the complex physical structure is converted into a combination of a finite number of units, so as to accurately calculate the flow state and pressure distribution of water flow in the unit. For example, when simulating the filter structure, the velocity change and impurity interception of water flowing through the filter can be accurately simulated through finite element meshing. When simulating the physical and chemical changes in the filtration process, with the help of chemical reaction kinetics model and mass transfer model, for filtration units involving chemical reactions, such as units that use chemical agents for disinfection or removal of specific pollutants, the corresponding kinetic model is established according to the chemical reaction equation to describe the change of reactant and product concentrations over time. At the same time, the mass transfer model is used to calculate the transfer rate of substances between the water phase and the solid phase (such as the adsorbent surface) to accurately simulate the removal process of pollutants. In order to realize the collaborative simulation between multiple types of continuous filtration units, the simulation model framework is constructed using object-oriented programming technology. Each filter unit is defined as an independent object, which encapsulates its own properties (such as filter parameters, structural parameters, etc.) and methods (such as filter operations, status updates, etc.). The message passing mechanism between objects is used to realize the interaction and collaborative work between different filter units, thereby constructing a complete continuous filtration simulation model that can truly simulate the continuous filtration process of multiple types of continuous filtration units under actual working conditions.

[0038] Based on the analysis of various water quality sources that may appear in actual water treatment scenarios, determine the types of impurities and pollutants that need to be covered. These impurities and pollutants include common suspended solids in natural water bodies, such as silt, algae, etc.; dissolved inorganic salts, including compounds formed by calcium, magnesium, iron, manganese and other ions, which may affect the hardness and corrosiveness of water; and various organic pollutants, such as pesticide residues, organic compounds contained in industrial wastewater discharge, etc., and possible microbial pollutants, such as bacteria, viruses, etc. Then, different water quality sample combinations are designed according to the characteristics of each stage of the water treatment process. For the initial stage, samples containing higher concentrations of suspended solids and some common dissolved impurities are configured to simulate the water quality of untreated raw water and test the initial filtration capacity of the front-end filtration unit. As the process progresses, the types and concentrations of impurities and pollutants in the samples are gradually adjusted, such as adding some difficult-to-remove organic pollutants or heavy metal ions in the intermediate stage to test the treatment effect of the intermediate filtration unit on specific pollutants. When approaching the end process, samples containing trace but complex pollutant combinations are configured to evaluate the purification capacity of the back-end fine filtration unit and the overall removal limit of low-concentration pollutants. During the configuration process, the concentration accuracy of each impurity and pollutant is strictly controlled to ensure that the test water quality samples have a high degree of accuracy and repeatability, providing a reliable and representative data basis for subsequent simulation tests.

[0039] Accurately load the configured full-process filtration test water quality samples into the built continuous filtration simulation model. This process needs to ensure that the flow characteristics, material distribution, etc. of the water quality samples in the model are consistent with the actual water treatment scenario. After loading, implement fault control operations for any type of filtration unit. For example, for a unit based on the principle of membrane filtration, fault conditions such as membrane pore blockage and membrane material damage can be simulated; for a unit that relies on chemical reactions for filtration, fault conditions such as insufficient reactants and catalyst deactivation can be simulated. Under each fault setting, the changes in the inlet water quality parameters, outlet water quality parameters, and key operating parameters of each unit in the subsequent filtration units are recorded in detail. By changing the fault type and fault severity multiple times, multiple sets of comprehensive and detailed data are obtained, thereby generating multiple sets of post-filtration impact test data sets corresponding to multiple types of continuous filtration units. These data sets will provide rich data support for the subsequent accurate evaluation of the impact of each type of filtration unit failure.

[0040] Multiple sets of post-filtration impact test data sets are collated and analyzed. For each set of data sets, key features are identified and extracted. These features cover changes in water quality parameters (such as changes in impurity concentration, fluctuations in pollutant content), changes in treatment efficiency (such as the degree of reduction in treated water volume per unit time, the magnitude of reduction in filtration speed), and changes in resource consumption (such as the increase in energy consumption and the magnitude of increase in chemical agent dosage). Through data standardization or normalization operations, these feature values ​​are converted into a numerical range suitable for calculation for subsequent unified processing. An impact cost calculation model is constructed based on the extracted features, and a weighted sum model is used here. Each feature is assigned a corresponding weight, and the determination of the weight is based on the professional understanding of the water treatment system and the analysis of historical data. For example, a higher weight is assigned to changes in the concentration of key pollutants that have a greater impact on water quality, while a lower weight is assigned to relatively minor changes in treatment efficiency. For some factors that are difficult to quantify directly but have a significant impact on the system, such as the increased difficulty of equipment maintenance due to failures, expert evaluation values ​​are introduced for quantitative processing. The qualitative evaluation given by experts based on experience is converted into quantitative values ​​and incorporated into the impact cost calculation model. According to the constructed model, the characteristic values ​​of each data set are substituted into the calculation to obtain the initial impact cost corresponding to each data set. For example, for a certain data set, the impurity concentration increases significantly, the processing efficiency decreases significantly, and the energy consumption increases dramatically. The model calculates a higher initial impact cost. In order to make the impact costs of different groups of data comparable, the initial impact costs are normalized. The maximum-minimum normalization method is used to map the impact costs of all groups to a specific interval (such as between 0 and 1) to obtain multiple post-filtering cost indicators. In this way, the cost indicators of different groups of data can be compared on the same scale, clearly reflecting the relative size of the impact of each filter unit failure on the post-filter. The model is verified using some data sets to compare the calculated post-filtering cost indicators with the actual observed impact. If it is found that there is a large deviation between the model calculation results and the actual situation, the weight parameters or feature selection of the model are adjusted and optimized to improve the accuracy and reliability of the model and ensure that the generated post-filtering cost indicators can truly reflect the actual impact of each filter unit failure.

[0041] The multiple post-filter cost indicators obtained by calculation are carefully compared with the preset cost indicators one by one. The preset cost indicator is a comprehensive measurement benchmark carefully set after fully considering the overall performance requirements of the water treatment system, economic cost constraints, water quality standards and specifications, and long-term stable operation requirements. During the comparison process, for each post-filter cost indicator, its size relationship with the preset cost indicator is judged. When a post-filter cost indicator is greater than or equal to the preset cost indicator, it means that in the event of a failure in the filter unit, the negative impact on the subsequent filtration process in terms of efficiency and water quality assurance has reached a level that cannot be ignored. At this time, this filter unit is marked and determined as a first-class filter unit. These first-class filter units will become the key objects for subsequent focus, redundant configuration, and targeted fault response strategy formulation to ensure that the entire water treatment system can still maintain a high level of operation stability, economy, and water quality treatment effect when facing possible failures.

[0042] In a possible implementation, step S130 further includes:

[0043] Step S131: Acquire a set of post-filtering units whose execution order is after any type of filtering unit.

[0044] Step S132: performing independent filtering function failure control on any type of filtering unit, and recording the impurity filtering data of the post-filtering unit set, to generate the plurality of post-filtering impact test data sets.

[0045] Specifically, in order to comprehensively evaluate the impact of a certain type of filter unit failure on the subsequent filtration process, it is first necessary to accurately locate all post-filtration units that are executed after any type of filter unit in the water treatment process. Through detailed combing and analysis of the filtration process of the entire water treatment system, the set of post-filtration units that are directly related to the faulty unit is determined. This process involves an in-depth understanding of the system process, including the direction of water flow, material transfer relationship, and collaborative working mechanism between each filter unit. For example, in a complex water treatment system with multi-stage filtration, if the current research is a primary physical filtration unit, then its post-filtration units may include chemical filtration units for removing specific dissolved pollutants, membrane filtration units for fine filtration, etc. These units together constitute a set of post-filtration units, and their working status and performance will be directly affected by the failure of the pre-filtration unit.

[0046] Independent filtering function failure control operation is carried out for any selected type of filter unit. By setting up a variety of simulated failure scenarios, the filter unit is accurately made to lose its original filtering function, such as simulating filter blockage, filter material damage or chemical reaction stagnation, so that it cannot effectively remove the specific impurities it is responsible for treating. Subsequently, the water flow state of the entire water treatment system is kept unchanged, and the water containing impurities that has not been effectively treated continues to flow to the subsequent filter units, that is, the second, third, fourth, etc. filter units, so as to observe and judge whether these post-filter units will be affected by the failure of the pre-filter unit. In this process, a series of advanced water quality monitoring instruments and equipment are used to measure and record the various impurity filtering data of the post-filter unit set when treating these waters containing additional impurities in real time and accurately. For each post-filter unit, the type, concentration and various related physical and chemical parameters of the impurities at its water inlet are recorded in detail, and the residual impurities at the water outlet after being treated by the unit are closely monitored, including the concentration of the remaining impurities, changes in composition and the total amount of impurities removed. By repeatedly changing the simulated failure mode of the pre-filter unit and adjusting the water quality conditions entering the system, the above test process was repeated to collect multiple sets of comprehensive and detailed impurity filtration data of the post-filter unit. Finally, the data obtained under different test conditions were sorted and classified to generate multiple sets of post-filter impact test data sets. These data sets will fully present the working performance of the post-filter unit set under different working conditions when the pre-filter unit fails, providing rich and reliable data basis for the subsequent in-depth evaluation of the post-filter impact cost, and helping to accurately grasp the performance change trend of the entire water treatment system when facing partial filter unit failures.

[0047] In a possible implementation, step S140 further includes:

[0048] Step S141: loading the filtration test water quality sample into the continuous filtration simulation model, performing a full-process simulation test, and recording multiple types of normal impurity filtration data corresponding to multiple types of continuous filtration units under normal conditions.

[0049] Step S142: performing filter unit alignment mapping on the multiple groups of post-filtering impact test data sets and the multiple types of normal impurity filtered data, and then calculating the reduction degree of the impurity removal rate to generate multiple reduction degree indicator sets.

[0050] Step S143: weighted fusion is performed on the indicator data in the plurality of descent degree indicator sets in sequence to generate the plurality of post-filtering cost indicators.

[0051] Step S144: wherein the indicator data in the plurality of descent degree indicator sets are proportional to the corresponding weights.

[0052] Specifically, the pre-configured filtration test water quality samples are loaded into the continuous filtration simulation model, and the full-process simulation test is started. In this process, the various types of continuous filtration units of the entire water treatment system operate according to the normal working mode and parameter settings to simulate the actual water treatment scenario. Using the data recording module in the simulation model, the filtration data of each type of continuous filtration unit for various impurities under normal conditions is comprehensively and in detail recorded. These data cover the concentration changes of different impurities at the inlet and outlet of each filtration unit, the identification of the types of impurities, and the removal amount of different impurities by each filtration unit. For example, for a system containing an activated carbon adsorption unit and an ultrafiltration membrane filtration unit, multiple types of normal impurity filtration data such as the adsorption amount of organic impurities by the activated carbon adsorption unit and the interception amount of tiny particle impurities by the ultrafiltration membrane filtration unit will be recorded separately to provide an accurate benchmark for subsequent comparative analysis.

[0053] The multiple groups of post-filter impact test data sets generated previously are accurately aligned and mapped with multiple types of normal impurity filter data. This means that the working data of the post-filter unit under fault simulation is matched one by one with the data of the corresponding filter unit under normal state to ensure the accuracy of comparative analysis. For each group of aligned and mapped data, the reduction degree of impurity removal rate is calculated. The difference between the impurity removal rate under normal state and the impurity removal rate under fault simulation is the reduction degree of impurity removal rate. Such calculation is performed for each type of impurity and each post-filter unit, thereby generating multiple reduction degree index sets. For example, in a certain group of data, under normal circumstances, the removal rate of a post-filter unit for heavy metal impurities is 90%. After the fault simulation of the pre-filter unit, its removal rate drops to 70%. Then the reduction degree of the impurity removal rate of the post-filter unit for heavy metal impurities is 20%. By analogy, the reduction degree index is calculated for each post-filter unit and each type of impurity to form a complete reduction degree index set.

[0054] The indicator data in multiple decline index sets are weighted and fused, and each decline index is assigned a corresponding weight according to the importance of different impurities on water quality and the criticality of different filter units in the entire water treatment system. For example, for those impurities that are more harmful to human health (such as heavy metal ions) or filter units that are in a critical position in the entire system (such as the last stage of fine filter units), their corresponding decline indicators will be assigned a higher weight. By multiplying each decline indicator with its corresponding weight and then adding all the products, the weighted fusion result is obtained to generate multiple post-filter cost indicators. This calculation method can comprehensively consider various factors, more accurately reflect the impact of the failure of the pre-filter unit on the entire system, and make the post-filter cost indicator more representative and practical.

[0055] It is clear that the indicator data in multiple decline index sets are proportional to the corresponding weights. The larger the indicator data, the larger the corresponding weight. The setting of this proportional relationship is based on a deep understanding of the operating principle and water quality requirements of the water treatment system. When the decline index data of a certain impurity removal rate is large, it means that the failure of the pre-filter unit has a more serious impact on the treatment of the impurity. If the impurity is crucial to the water quality or subsequent treatment process, then it should be given a greater weight to highlight its importance in the calculation of the post-filtration cost. In this way, it is ensured that when calculating the post-filtration cost index, the difference in the impact of different factors on the system can be reasonably reflected, so that the final post-filtration cost index can accurately guide the subsequent screening and formulation of treatment strategies for the first type of filter unit.

[0056] In a possible implementation, step S600 further includes:

[0057] Step S610: If the faulty filter unit does not belong to the first type of main filter unit, determine the previous adjacent filter unit and the next adjacent filter unit of the faulty filter unit.

[0058] Step S620: activating the flow pipeline from the previous adjacent filter unit to the next adjacent filter unit, skipping the faulty filter unit through the flow pipeline for filtering, and issuing a maintenance warning message marked with the faulty filter unit and a filtering stage return processing reminder message.

[0059] Specifically, when it is detected that the faulty filter unit does not belong to the first type of main filter unit, the corresponding response mechanism will be quickly activated. Since this type of faulty filter unit has a relatively small impact on the entire filtration process, the filtration link of the entire water treatment system will be comprehensively sorted out first, and the position of the faulty filter unit in the link will be accurately locked based on the pre-stored filter unit connection relationship diagram and real-time monitoring data. Subsequently, by retrieving and analyzing the information of adjacent filter units, the previous adjacent filter unit and the next adjacent filter unit of the faulty filter unit are accurately determined. This process is like accurately finding the key connection points upstream and downstream of a node in a complex water network, making full preparations for the subsequent construction of a temporary alternative filtration path, ensuring that the water treatment work is maintained without seriously interfering with the overall filtration process. The continuous operation, while also laying the foundation for notifying maintenance personnel to inspect and return to the processing after repair.

[0060] After the adjacent filter units are determined, the pre-designed flow pipes between the previous adjacent filter unit and the next adjacent filter unit are quickly activated. Through a series of operations such as the opening and closing of valves in the intelligent control pipeline system and the adjustment of water pump operating parameters, the water flow path is changed so that the water that should have flowed through the faulty filter unit flows directly from the previous adjacent filter unit to the next adjacent filter unit smoothly, thereby achieving the purpose of skipping the faulty filter unit and continuing the filtering process. This method of dynamically adjusting the water flow path effectively ensures the continuity of the entire water treatment process, avoiding downtime due to the failure of a single non-critical filter unit. At the same time, maintenance warning information containing detailed fault information is generated and issued in a timely manner, and various characteristics of the faulty filter unit are clearly marked, such as unit number, location, time of fault occurrence, and preliminary inference of possible fault causes, so that maintenance personnel can obtain accurate information in the first time, quickly organize maintenance resources and formulate maintenance plans. In addition, to ensure the integrity of the water quality and the reliability of the treatment effect during the entire water treatment process, a reminder message is sent to the filter stage to remind you that after the fault is repaired, a comprehensive inspection of the water quality during the period when the faulty unit is skipped is required to assess whether additional filtration or other necessary treatment operations are required to ensure that the final effluent water quality fully meets the established standards. Through such a series of measures, while ensuring the continuous operation of the system, clear guidance and basis are provided for subsequent maintenance and quality control.

[0061] In a possible implementation, step S500 further includes:

[0062] Step S510: collecting a multi-stage filtration monitoring data set corresponding to the multi-stage filtration unit through the specific water quality sensor at the second monitoring point, wherein the multi-stage filtration monitoring data set includes water inlet filtration monitoring data, central filtration monitoring data and water outlet filtration monitoring data.

[0063] Step S520: Based on the multi-stage filtration parameters, the distribution of impurity reduction from the water inlet to the central processing area and then to the water outlet is predicted to generate a multi-stage impurity reduction prediction result.

[0064] Step S530: performing a consistency comparison of the multi-stage filtration monitoring data set and the multi-stage impurity reduction prediction result in the same-stage filtration unit to generate a multi-stage consistency deviation.

[0065] Step S540: According to the multi-level consistency deviation, locate the faulty filtering unit whose consistency deviation is greater than the preset deviation.

[0066] Specifically, the specific water quality sensors equipped at the second monitoring point began to play a key role. These sensors are distributed at the water inlet, central processing area and water outlet of the multi-stage filtration unit, and can collect real-time and accurate filtration monitoring data of each level of the multi-stage filtration unit during operation, thus forming a complete multi-stage filtration monitoring data set. The inlet filtration monitoring data reflects the initial water quality of the water before it enters the filtration unit, including information such as the types, concentrations and physical and chemical properties of various impurities; the central filtration monitoring data reflects the changes in impurities when the water is in the central processing area of ​​the filtration unit, which is crucial for understanding the intermediate state of the filtration process; the outlet filtration monitoring data shows the quality of the water after treatment by the filtration unit, which is a key indicator for measuring the filtration effect. Through these comprehensive data collection, a rich and accurate data foundation is provided for the subsequent performance evaluation and fault analysis of the multi-stage filtration unit.

[0067] Based on the multi-stage filtration parameters, the distribution prediction of the impurity reduction from the water inlet to the central treatment area and then to the water outlet is carried out. For each level of filtration unit, its parameter characteristics are first analyzed. If it is a physical filtration unit, the parameters include the filter mesh aperture, material, filtration area, etc. Based on these parameters combined with the principles of fluid mechanics and particle filtration theory, the interception efficiency of impurities of different particle sizes at the filter is calculated. For example, based on the relationship between the filter mesh aperture and the impurity particle size, the filtration model is used to calculate the removal ratio of impurities of a specific particle size. For chemical filtration units, the type, concentration, reaction activity and reaction conditions of the chemical reactants are analyzed. According to the principles of chemical reaction kinetics, the rate and degree of reaction between impurities and reactants are calculated to determine the amount of impurities removed. Starting from the water inlet, the type, concentration and other information of the influent impurities are used as the initial conditions. Combined with factors such as water flow rate and the residence time of the filtration unit, the theoretical reduction of impurities in the process of passing through the central treatment area of ​​each level of filtration unit to the water outlet is gradually calculated. For example, for influent water containing multiple impurities, the concentration changes of each impurity in each filtration stage are calculated in turn, and finally the multi-stage impurity reduction prediction results at different positions of each level of filtration unit are formed. This result provides a reference standard under ideal conditions for subsequent analysis.

[0068] The consistency comparison of the multi-stage filtration monitoring data set and the multi-stage impurity reduction prediction results is carried out for the same-stage filtration units. For each stage of filtration unit, the actual filtration monitoring data collected at its water inlet, central processing area and outlet are compared with the corresponding data in the prediction results. For example, in the central processing area of ​​a certain level of physical filtration unit, the difference between the actual monitored impurity concentration and the predicted impurity concentration is calculated. For multiple impurities, the concentration deviation and removal deviation of each impurity are calculated separately. In addition to the concentration, the consistency of other relevant parameters is also considered, such as the influence of water flow pressure and temperature on the filtration effect. By comprehensively comparing these parameters, a multi-level consistency deviation is generated. This deviation reflects the degree of difference between the actual filtration process and the ideal prediction, covering the conditions of filtration units at different positions and different impurity treatments at different levels.

[0069] The faulty filter unit is located based on the multi-level consistency deviation, and a reasonable preset deviation value is pre-set. This value is determined based on a large amount of experimental data and the requirements for stable operation of the water treatment system. The multi-level consistency deviation of each filter unit at each position is compared with the preset deviation one by one. When the consistency deviation of a certain filter unit at its water inlet, central treatment area or outlet is greater than the preset deviation, it indicates that the filter unit has an abnormality during actual operation and is likely to be in a faulty state. In this way, those units that are not operating properly can be accurately found from the many filter units, providing a clear goal for subsequent maintenance and repair work, and ensuring the normal operation of the entire water treatment system.

[0070] In a possible implementation, step S520 further includes:

[0071] Step S521: collecting historical filtering data for the multiple types of continuous filtering units respectively to generate multiple filtering distribution sample data sets, wherein any filtering distribution sample data set contains multiple groups of filtering parameter samples and impurity reduction distribution samples with corresponding relationships.

[0072] Step S522: constructing a plurality of filter distribution prediction units based on the neural network training using the plurality of filter distribution sample data sets.

[0073] Step S523: According to the multi-stage filtering unit matching the target filtering distribution prediction unit in the multiple filtering distribution prediction units, the multi-stage filtering parameters are analyzed to generate the multi-stage impurity reduction prediction result.

[0074] Specifically, we focus on multiple types of continuous filtration units. In order to fully and deeply understand the characteristics and historical performance of these filtration units, we start the historical filtration data collection work. For each type of continuous filtration unit, we collect the filtration data under different working conditions in the past by connecting to the database of the water treatment system and the relevant data recording equipment. These data cover a wealth of information, including but not limited to the influent flow rate, influent impurity composition and concentration in different time periods, temperature and pressure conditions during the filtration process, and different filtration parameter settings adopted by each filtration unit. Each set of such data is associated with the corresponding impurity reduction distribution. For example, when a filter unit adopts a set of specific filtration parameters (such as filter mesh aperture, adsorption material dosage, chemical agent dosage, etc.) under specific influent conditions, the concentration changes of various impurities in the water after filtration by the unit constitute the impurity reduction distribution sample. In this way, for each type of continuous filtration unit, a filtration distribution sample data set is generated, which contains multiple sets of corresponding filtration parameter samples and impurity reduction distribution samples, which will become an important basis for subsequent analysis and prediction.

[0075] The multi-layer perceptron (MLP) neural network is used to construct the filter distribution prediction unit. For the multi-layer perceptron, its structure includes an input layer, several hidden layers and an output layer. The number of neurons in the input layer is determined according to the dimension of the filter parameter sample. For example, if the filter parameter sample includes six parameters: inlet flow rate, inlet impurity concentration, filter unit temperature, pressure, filter mesh aperture, and adsorbent dosage, then six neurons are set in the input layer. Each neuron receives the corresponding filter parameter value as input and processes the data through a suitable activation function. Common activation functions such as the ReLU (Rectified Linear Unit) function can increase the nonlinear expression ability of the neural network. For the input value x, when x>0, x is output; when x≤0, 0 is output. The number of hidden layers and the number of neurons in each layer need to be determined through experiments and adjustments. Assume that two hidden layers are set, the first hidden layer has 12 neurons and the second hidden layer has 8 neurons. The neurons in the hidden layers are connected by appropriate weights, and the weights are continuously adjusted during the training process. The number of neurons in the output layer depends on the dimension of the impurity reduction distribution sample. For example, if the decrease of three main impurities is of interest, three neurons are set in the output layer, and the output value of each neuron corresponds to the predicted decrease of one impurity. During the training process, the filter parameter samples in multiple filter distribution sample data sets are used as input, and the corresponding impurity decrease distribution samples are used as target outputs. The connection weights between neurons in the multi-layer perceptron neural network are continuously adjusted using training data. The training algorithm can choose the gradient descent algorithm, which calculates the gradient of the loss function (such as the mean square error loss function) with respect to the weight, and then updates the weight in the opposite direction of the gradient, so that the error between the predicted output and the target output gradually decreases. After a large number of training iterations, this multi-layer perceptron neural network can learn the complex mapping relationship between the filter parameters and the impurity decrease distribution, thereby forming an effective filter distribution prediction unit. For different types of continuous filter units, multiple such MLP neural networks can be trained according to their corresponding filter distribution sample data sets to form multiple filter distribution prediction units.

[0076] For the current multi-stage filtration unit, a matching target filtration distribution prediction unit is searched among the multiple filtration distribution prediction units that have been constructed. This matching process may be based on factors such as the type of the multi-stage filtration unit, its structural characteristics, or its functional positioning in the entire water treatment process. After finding a matching target filtration distribution prediction unit, the current multi-stage filtration parameters are input into the prediction unit. The target filtration distribution prediction unit conducts an in-depth analysis of the input multi-stage filtration parameters based on the mapping relationship it has learned. Through the complex calculation process within the neural network, the distribution of impurity reduction in the process of water from the water inlet of the multi-stage filtration unit to the central treatment area and then to the water outlet under these parameter settings is predicted. The final multi-stage impurity reduction prediction result will provide a key basis for subsequent evaluation and decision-making, and help determine whether the actual operating status of the multi-stage filtration unit meets expectations.

[0077] In a possible implementation, step S400 further includes:

[0078] Step S410: for the multiple types of continuous filtration units, multiple filtration parameter selection libraries are constructed by collecting historical filtration parameter records and historical water quality monitoring results.

[0079] Step S420: matching multiple stages of filtering units among the multiple types of continuous filtering units according to the impurity types in the monitoring results.

[0080] Step S430: inputting the monitoring result into the filtering parameter selection library corresponding to the multi-stage filtering unit to perform filtering parameter matching to generate the multi-stage filtering parameters.

[0081] Specifically, a comprehensive data analysis is carried out for multiple types of continuous filtration units. In-depth mining of historical data, including historical filtration parameter records and historical water quality monitoring results, covers the setting parameters of various types of filtration units in different operating periods in the past, such as the filter mesh aperture size of different filtration units, the type and amount of adsorbent materials, the concentration of chemical reagents, the water flow rate and pressure during filtration, and many other key parameter information. These parameters record in detail the operating conditions of each filtration unit under various working conditions. At the same time, the historical water quality monitoring results accurately reflect the water quality of the inlet and outlet water under the corresponding filtration parameter settings, including the type and concentration of various impurities in the water. By sorting and classifying these rich and detailed historical filtration parameter records and historical water quality monitoring results, a special filtration parameter selection library is built for each type of continuous filtration unit, which stores the effective filtration parameter combinations under different impurity conditions and processing requirements, providing a comprehensive reference for subsequent filtration parameter matching.

[0082] Carry out the matching work of multi-stage filtration units according to the current monitoring results, and carefully analyze the impurity type information presented in the monitoring results. These impurity types are diverse, including but not limited to suspended particles, dissolved organic matter, heavy metal ions, microorganisms and other different categories. According to the characteristics and distribution of these impurity types, select the corresponding multi-stage filtration units from the multiple types of continuous filtration units. For example, if the monitoring results show that the water contains a large number of suspended particles and some microorganisms, a continuous filtration unit with physical filtration function (such as filter filtration) and disinfection function will be selected as part of the multi-stage filtration unit; if there are still dissolved organic matter, a filtration unit with activated carbon adsorption or other chemical oxidation function will be further matched. In this way, the combination of multi-stage filtration units that can effectively handle the current impurity type can be accurately determined to prepare for subsequent parameter matching.

[0083] Input the current monitoring results into the filter parameter selection library corresponding to the matched multi-stage filter unit. In the filter parameter selection library, compare and match the specific water quality information in the monitoring results, such as impurity concentration, pH value, water temperature, etc., with the historical data stored in the library. Filter out the filter parameter combination that best suits the current monitoring results from the filter parameter selection library. These parameters will ensure that the multi-stage filter unit can achieve the best effect when treating the current water quality. For example, according to the impurity concentration and type of the incoming water, determine the optimal filter mesh aperture, appropriate amount of adsorption material, and corresponding chemical reaction conditions of a certain filter unit, thereby generating multi-stage filtration parameters for the current situation, providing accurate parameter support for the efficient operation of the entire filtration system.

[0084] Embodiment 2, based on the same inventive concept as the filtration unit coordinated water treatment method under multi-point water quality monitoring in the previous embodiment, Figure 2 As shown, the present application provides a filtration unit coordinated water treatment device under multi-point water quality monitoring, and the device and method embodiments in the embodiments of the present application are based on the same inventive concept. Among them, the device includes:

[0085] The first type of filter unit acquisition module 10 is used to acquire multiple types of continuous filter units continuously executed in the water treatment system, and perform post-filtration impact cost analysis under fault conditions to generate a first type of filter unit with a post-filtration cost index greater than or equal to a preset cost index.

[0086] The filter unit acquisition module 20 is used to divide, configure and mark the first type of filter units into redundant filter units to generate first type main filter units and first type redundant filter units.

[0087] A water quality sensor configuration module 30 is used to configure a monitoring point set, wherein the monitoring point set includes a first monitoring point and a second monitoring point, wherein the first monitoring point is a source water inlet, configured with a multi-source water quality sensor, and the second monitoring point is a water inlet, a water outlet and a central processing area of ​​the multiple types of continuous filtration units, configured with a specific water quality sensor.

[0088] The water quality monitoring module 40 performs water quality monitoring based on the multi-source water quality sensors at the first monitoring point, and matches the multi-stage filtering units and multi-stage filtering parameters in the multi-type continuous filtering units according to the monitoring results.

[0089] A fault filtering unit generation module 50 performs collaborative filtering based on the multi-stage filtering unit and the multi-stage filtering parameters, and at the same time collects filtering monitoring data and performs fault analysis through the specific water quality sensor at the second monitoring point to generate a fault filtering unit.

[0090] The filtering processing module 60 is used to switch the first-type redundant filtering unit to perform filtering processing if the faulty filtering unit belongs to the first-type main filtering unit.

[0091] Furthermore, the first type filtering unit acquisition module 10 further includes:

[0092] A continuous filtration simulation model generating unit is used to perform simulation modeling on the multiple types of continuous filtration units under a continuous filtration process to generate a continuous filtration simulation model.

[0093] A filtering test water quality sample configuration unit is used to configure the filtering test water quality sample under the whole process.

[0094] A fault control unit is used to load the filtration test water quality sample into the continuous filtration simulation model, and perform fault control on any type of filtration unit to generate multiple groups of post-filtration impact test data sets corresponding to the multiple types of continuous filtration units.

[0095] A post-filtering cost index generating unit is used to perform impact cost calculation according to the multiple groups of post-filtering impact test data sets to generate multiple post-filtering cost indexes.

[0096] The first type of filter unit generating unit is used for comparing the plurality of post-filtering cost indicators with the preset cost indicator to generate the first type of filter unit.

[0097] Furthermore, the fault control unit further includes:

[0098] A post-filtering unit set acquisition unit is used to acquire a post-filtering unit set whose execution order is after any type of filtering unit.

[0099] A post-filtering impact test data set generation unit is used to control the failure of independent filtering functions of any type of filtering unit, and record the impurity filtering data of the post-filtering unit set to generate the multiple groups of post-filtering impact test data sets.

[0100] Furthermore, the post-filtering cost index generating unit further includes:

[0101] A full-process simulation test unit is used to load the filtration test water quality sample into the continuous filtration simulation model, perform a full-process simulation test, and record multiple types of normal impurity filtration data corresponding to multiple types of continuous filtration units under normal conditions.

[0102] A reduction index set generation unit is used to calculate the reduction of impurity removal rate after filtering unit alignment mapping of the multiple groups of post-filtering impact test data sets and the multiple types of normal impurity filtering data, so as to generate multiple reduction index sets.

[0103] A weighted fusion unit, the weighted fusion unit is used to perform weighted fusion on the indicator data in the multiple descent degree indicator sets in sequence to generate the multiple post-filtering cost indicators.

[0104] The indicator data in the plurality of descent degree indicator sets are proportional to the corresponding weights.

[0105] Furthermore, the filtering processing module 60 also includes:

[0106] The adjacent filtering determination unit is used to determine the previous adjacent filtering unit and the next adjacent filtering unit of the faulty filtering unit if the faulty filtering unit does not belong to the first type of main filtering unit.

[0107] A flow pipeline activation unit, the flow pipeline activation unit is used to activate the flow pipeline from the previous adjacent filter unit to the next adjacent filter unit, skip the faulty filter unit through the flow pipeline for filtering processing, and issue a maintenance warning message marked with the faulty filter unit and a reminder message for returning to the filtering stage for processing.

[0108] Furthermore, the fault filtering unit generating module 50 further includes:

[0109] A multi-stage filtration monitoring data set acquisition unit, wherein the multi-stage filtration monitoring data set acquisition unit is used to collect the multi-stage filtration monitoring data set corresponding to the multi-stage filtration unit through the specific water quality sensor at the second monitoring point, wherein the multi-stage filtration monitoring data set includes inlet filtration monitoring data, center filtration monitoring data and outlet filtration monitoring data.

[0110] A multi-stage impurity reduction prediction result generating unit is provided, wherein the multi-stage impurity reduction prediction result generating unit predicts the impurity reduction distribution from the water inlet to the central processing area and then to the water outlet based on the multi-stage filtration parameters, and generates a multi-stage impurity reduction prediction result.

[0111] A multi-level consistency deviation generating unit is used to perform a consistency comparison of the multi-level filtration monitoring data set and the multi-level impurity reduction prediction result of the same-level filtration unit to generate a multi-level consistency deviation.

[0112] A consistency deviation locating unit is used to locate a fault filtering unit whose consistency deviation is greater than a preset deviation according to the multi-level consistency deviation.

[0113] Furthermore, the multi-level impurity reduction prediction result generating unit further includes:

[0114] A filtering distribution sample data set generation unit is used to collect historical filtering data for each of the multiple types of continuous filtering units to generate multiple filtering distribution sample data sets, wherein any filtering distribution sample data set contains multiple groups of corresponding filtering parameter samples and impurity reduction distribution samples.

[0115] A filter distribution prediction unit construction unit is used to construct a plurality of filter distribution prediction units based on neural network training using the plurality of filter distribution sample data sets.

[0116] A multi-level impurity reduction prediction result generation unit is used to match the target filter distribution prediction unit in the multiple filter distribution prediction units according to the multi-level filtering unit, analyze the multi-level filtering parameters, and generate the multi-level impurity reduction prediction result.

[0117] Furthermore, the water quality monitoring module 40 also includes:

[0118] A filtering parameter selection library construction unit is used to construct multiple filtering parameter selection libraries for the multiple types of continuous filtering units by collecting historical filtering parameter records and historical water quality monitoring results.

[0119] A matching multi-stage filtering unit is used to match a multi-stage filtering unit among the multiple types of continuous filtering units according to the impurity types in the monitoring results.

[0120] A multi-stage filtering parameter generating unit is used to input the monitoring result into a filtering parameter selection library corresponding to the multi-stage filtering unit for filtering parameter matching to generate the multi-stage filtering parameters.

[0121] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0123] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A filtration unit coordinated water treatment method under multi-point water quality monitoring, characterized in that: include: Obtain multiple types of continuous filtering units that are continuously executed in the water treatment system, and perform post-filtration impact cost analysis under fault conditions to generate a first type of filtering unit whose post-filtration cost index is greater than or equal to a preset cost index, specifically including: Perform simulation modeling under a continuous filtration process for the multiple types of continuous filtration units to generate a continuous filtration simulation model; Configure the filtration test water quality samples under the whole process; Loading the filtration test water quality sample into the continuous filtration simulation model, and performing fault control on any type of filtration unit to generate multiple groups of post-filtration impact test data sets corresponding to the multiple types of continuous filtration units; Performing impact cost calculation according to the multiple groups of post-filtering impact test data sets to generate multiple post-filtering cost indicators; comparing the plurality of post-filtering cost indicators with the preset cost indicator to generate the first type of filtering unit; For the first type of filter units, performing redundant filter unit division configuration and marking to generate first type main filter units and first type redundant filter units; A monitoring point set is configured, wherein the monitoring point set includes a first monitoring point and a second monitoring point, wherein the first monitoring point is a source water inlet, configured with a multi-source water quality sensor, and the second monitoring point is a water inlet, a water outlet and a central processing area of ​​the multiple types of continuous filtration units, configured with a water quality sensor; Performing water quality monitoring based on the multi-source water quality sensor at the first monitoring point, and matching multi-stage filtration units and multi-stage filtration parameters in the multiple types of continuous filtration units according to the monitoring results; Based on the multi-stage filtering unit and the multi-stage filtering parameters, collaborative filtering is performed, and filtering monitoring data is collected and fault analysis is performed through the water quality sensor at the second monitoring point, so as to generate a fault filtering unit, specifically including: The multi-stage filtration monitoring data set corresponding to the multi-stage filtration unit is collected by the water quality sensor at the second monitoring point, wherein the multi-stage filtration monitoring data set includes water inlet filtration monitoring data, center filtration monitoring data and water outlet filtration monitoring data; Based on the multi-stage filtration parameters, the distribution of impurity reduction from the water inlet to the central processing area and then to the water outlet is predicted to generate a multi-stage impurity reduction prediction result; Performing a consistency comparison of the multi-stage filtration monitoring data set and the multi-stage impurity reduction prediction result of the same-stage filtration unit to generate a multi-stage consistency deviation; According to the multi-level consistency deviation, locating the fault filtering unit whose consistency deviation is greater than the preset deviation; If the faulty filter unit belongs to the first type of main filter unit, the first type of redundant filter unit is switched to perform filtering processing.

2. The filtration unit coordinated water treatment method under multi-point water quality monitoring according to claim 1, characterized in that: The filtration test water quality sample is loaded into the continuous filtration simulation model, and the fault control of any type of filtration unit is performed to generate multiple groups of post-filtration impact test data sets corresponding to the multiple types of continuous filtration units, including: Acquire a set of post-filtering units whose execution order is after any type of filtering unit; Independent filtering function failure control is performed on any type of filtering unit, and impurity filtering data of the post-filtering unit set is recorded to generate the multiple groups of post-filtering impact test data sets.

3. The filtration unit coordinated water treatment method under multi-point water quality monitoring according to claim 2 is characterized in that: The impact cost is calculated according to the multiple groups of post-filtering impact test data sets to generate multiple post-filtering cost indicators, including: Loading the filtration test water quality sample into the continuous filtration simulation model, performing a full-process simulation test, and recording multiple types of normal impurity filtration data corresponding to multiple types of continuous filtration units under normal conditions; After filtering unit alignment mapping is performed on the multiple groups of post-filtering impact test data sets and the multiple types of normal impurity filtering data, a reduction degree of impurity removal rate is calculated to generate multiple reduction degree indicator sets; performing weighted fusion on the indicator data in the plurality of descent degree indicator sets in sequence to generate the plurality of post-filtering cost indicators; The indicator data in the plurality of descent degree indicator sets are proportional to the corresponding weights.

4. The filtration unit coordinated water treatment method under multi-point water quality monitoring according to claim 1, characterized in that: Also includes: If the faulty filter unit does not belong to the first type of main filter unit, determining the previous adjacent filter unit and the next adjacent filter unit of the faulty filter unit; Activate the flow pipeline from the previous adjacent filter unit to the next adjacent filter unit, skip the faulty filter unit through the flow pipeline for filtering, and issue maintenance warning information marked with the faulty filter unit and filtering stage return processing reminder information.

5. The filtration unit coordinated water treatment method under multi-point water quality monitoring according to claim 1, characterized in that: Based on the multi-stage filtration parameters, the distribution of impurity reduction from the water inlet to the central processing area and then to the water outlet is predicted to generate a multi-stage impurity reduction prediction result, including: Collecting historical filtering data for each of the multiple types of continuous filtering units to generate multiple filtering distribution sample data sets, wherein any filtering distribution sample data set includes multiple groups of filtering parameter samples and impurity reduction distribution samples having corresponding relationships; Using the plurality of filter distribution sample data sets, construct a plurality of filter distribution prediction units based on neural network training; According to the multi-stage filtering unit matching the target filtering distribution prediction unit in the multiple filtering distribution prediction units, the multi-stage filtering parameters are analyzed to generate the multi-stage impurity reduction degree prediction result.

6. The filtration unit coordinated water treatment method under multi-point water quality monitoring according to claim 1, characterized in that: Water quality monitoring is performed based on the multi-source water quality sensor at the first monitoring point, and multi-stage filtration units and multi-stage filtration parameters are matched in the multiple types of continuous filtration units according to the monitoring results, including: For the multiple types of continuous filtration units, multiple filtration parameter selection libraries are constructed by collecting historical filtration parameter records and historical water quality monitoring results; Matching a multi-stage filtering unit to the multiple types of continuous filtering units according to the impurity types in the monitoring results; The monitoring results are input into the filter parameter selection library corresponding to the multi-stage filter unit for filter parameter matching to generate the multi-stage filter parameters.

7. A filtration unit coordinated water treatment device under multi-point water quality monitoring, characterized in that: The filter unit coordinated water treatment device under multi-point water quality monitoring is used to implement the steps of the filter unit coordinated water treatment method under multi-point water quality monitoring according to any one of claims 1 to 6, including: A first type of filter unit acquisition module, the first type of filter unit acquisition module is used to acquire multiple types of continuous filter units that are continuously executed in the water treatment system, and perform a post-filter impact cost analysis under a fault condition to generate a first type of filter unit whose post-filter cost index is greater than or equal to a preset cost index; A filter unit acquisition module, the filter unit acquisition module is used to perform redundant filter unit division configuration and marking for the first type of filter units, and generate a first type of main filter unit and a first type of redundant filter unit; A water quality sensor configuration module, the water quality sensor configuration module is used to configure a monitoring point set, wherein the monitoring point set includes a first monitoring point and a second monitoring point, wherein the first monitoring point is a source water inlet, configured with a multi-source water quality sensor, and the second monitoring point is a water inlet, a water outlet and a central processing area of ​​the multiple types of continuous filtration units, configured with a water quality sensor; A water quality monitoring module, wherein the water quality monitoring module performs water quality monitoring based on a multi-source water quality sensor at the first monitoring point, and matches a multi-stage filtering unit and a multi-stage filtering parameter in the multi-type continuous filtering unit according to the monitoring result; A fault filtering unit generation module, wherein the fault filtering unit generation module performs collaborative filtering based on the multi-stage filtering unit and the multi-stage filtering parameters, and collects filtering monitoring data through the water quality sensor at the second monitoring point and performs fault analysis to generate a fault filtering unit; A filtering processing module, wherein the filtering processing module is used to switch the first type of redundant filtering unit to perform filtering processing if the faulty filtering unit belongs to the first type of main filtering unit.

Images