Sewage treatment plant monitoring management method and system based on digital twinborn technology

Abstract

The invention belongs to the technical field of digital twinning, and provides a sewage treatment plant monitoring management method and system based on the digital twinning technology. The method comprises the following steps: determining coupling relation data among equipment of a sewage treatment plant and real-time sewage data of sewage input in a current operation period; extracting operation data of each device from a digital twinborn model corresponding to the sewage treatment plant, and predicting a plurality of virtual twinborn sub-models independent of the digital twinborn model based on each operation data, the coupling relation data and the real-time sewage data; obtaining potential fault equipment and affected associated equipment based on each virtual twin sub-model; and outputting prompt information related to the potential fault equipment and the influenced associated equipment in the digital twin model. According to the method, a fault prediction function is added to the digital twin model, and normal operation of the digital twin model is not interfered.

Description

Technical Field

[0001] The present invention belongs to the field of digital twin technology, and specifically relates to a sewage treatment plant monitoring and management method and system based on digital twin technology. Background Art

[0002] Currently, the application of digital twin technology in sewage treatment plant management has been gradually expanded. By constructing a virtual digital model that corresponds one-to-one with the physical entity and integrating real-time data from various monitoring devices, it can visualize the operating status of the sewage treatment plant and enable online management. Managers can intuitively view the operating parameters of sewage treatment plant equipment and the real-time progress of process flows, significantly improving the timeliness and comprehensiveness of information acquisition compared to traditional management models.

[0003] However, existing sewage treatment plant monitoring and management systems based on digital twin technology still have significant limitations. Their primary function is to simulate and display the operating status of sewage treatment plants in real time. These systems can only reflect the current operating conditions of equipment and systems, and are unable to proactively predict potential fault hazards. Sewage treatment plants contain numerous pieces of equipment, including pumps, aeration equipment, and sludge treatment equipment. Over long-term operation, these devices are subject to various factors, including mechanical wear, water corrosion, and electrical failures, leading to performance degradation and frequent failures. Relying solely on real-time simulation, it is impossible to detect subtle changes in equipment performance before a failure occurs, and it is impossible to take maintenance measures in advance. A sudden equipment failure not only interrupts the sewage treatment process and affects the effluent quality, but can also significantly increase costs due to emergency repairs and even pose environmental pollution risks.

[0004] In the context of pursuing efficient, stable and sustainable operation of sewage treatment plants, breaking through the bottleneck of existing digital twin technology that can only simulate in real time, achieving accurate prediction of equipment failures, and building a digital twin monitoring and management system with fault warning functions have become urgent needs for the intelligent management upgrade of sewage treatment plants. Summary of the Invention

[0005] In response to the above technical problems, the present invention proposes a sewage treatment plant monitoring and management method and system based on digital twin technology to solve at least one of the above technical problems.

[0006] In a first aspect, the present invention provides a sewage treatment plant monitoring and management method based on digital twin technology, comprising the following steps: Determine the coupling relationship data between various equipment in the sewage treatment plant, as well as the real-time sewage data of the sewage input during this operation cycle, including sewage flow and water quality indicators; Extracting the operating data of each device from the digital twin model corresponding to the sewage treatment plant, and using a plurality of virtual twin sub-models independent of the digital twin model to perform simulation prediction based on the operating data, the coupling relationship data, and the real-time sewage data, to obtain potential faulty devices and affected associated devices; Output prompt information related to potential faulty devices and affected associated devices in the digital twin model.

[0007] In a second aspect, the present invention provides a sewage treatment plant monitoring and management system based on digital twin technology, the system comprising an acquisition unit, a simulation unit, and a prompt unit; The acquisition unit determines the coupling relationship data between the various devices in the sewage treatment plant, as well as the real-time sewage data of the sewage input in the current operation cycle, including sewage flow and water quality indicators; The simulation unit extracts operating data of each device from the digital twin model corresponding to the sewage treatment plant, and uses a plurality of virtual twin sub-models independent of the digital twin model to perform simulation prediction based on the operating data, the coupling relationship data, and the real-time sewage data to obtain potential faulty devices and affected associated devices; The prompt unit outputs prompt information related to potential faulty devices and affected associated devices in the digital twin model.

[0008] In a third aspect of the present invention, an electronic device is provided, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements any of the methods described above when executed by the processor.

[0009] According to a fourth aspect of the present invention, a computer storage medium is provided, wherein the computer storage medium stores a computer program executable by a processor to implement any of the methods described above.

[0010] According to a fifth aspect of the present invention, a computer program product is provided, which comprises a computer program executable by a processor to implement any of the methods described above.

[0011] This invention achieves fault prediction by constructing independently running virtual twin models for high-risk equipment. This model combines coupling relationship data, real-time sewage data, and equipment operating data to simulate future states. This expands the fault warning capabilities of digital twin models. Furthermore, because the virtual twin models run in an independent backend unit, they do not interfere with the normal operation of the main model, ensuring continuous monitoring and management. This also improves the accuracy of fault prediction and the efficiency of equipment chain impact analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of a sewage treatment plant monitoring and management method based on digital twin technology disclosed in an embodiment of the present invention; Figure 2 Schematic diagram of the relative relationship between the digital twin model and the virtual twin sub-model disclosed in the embodiment of the present invention; Figure 3 It is a structural diagram of a sewage treatment plant monitoring and management system based on digital twin technology disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The following specific embodiments illustrate the implementation of this application. Those familiar with the art can easily understand the other advantages and functions of this application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0016] like Figure 1 As shown, the embodiment of the present invention discloses a sewage treatment plant monitoring and management method based on digital twin technology, including the following method steps: S10, determining the coupling relationship data between various devices in the sewage treatment plant, and the real-time sewage data of the sewage input in this operation cycle, including sewage flow and water quality indicators.

[0017] First, retrieve the pre-established coupling relationship data between the various devices in the sewage treatment plant, as follows: The series and parallel connections between equipment in the sewage treatment process were organized, such as the pre- and post-placement relationship between sewage lift pumps and screen machines, and the supply-demand relationship between aeration tanks and blowers, to create an equipment topology diagram. Furthermore, the weights of the parameters influencing each device were quantified, such as the impact coefficient of lift pump flow changes on the subsequent grit chamber level, and the correlation between aeration equipment air pressure fluctuations and dissolved oxygen concentration in the biochemical tank, to form a coupling relationship matrix. Furthermore, by combining historical operating data and process manuals, thresholds for coordinated changes in various equipment parameters were determined. For example, when the inlet flow rate exceeds 120% of the design value, the operating frequencies of the screen machine and lift pump must be adjusted synchronously.

[0018] The above-mentioned equipment topology diagram, coupling relationship matrix, linkage rules, etc. are integrated into coupling relationship data.

[0019] Then, obtain the real-time sewage data of the sewage input to the sewage treatment plant during this operation cycle. The real-time sewage data is collected in real time through the sensor network within the plant. The details are as follows: Sewage flow data: The flow rate per unit time obtained by the electromagnetic flow meter at the water inlet (unit: m 3 / h), and record the flow fluctuation range (such as the maximum deviation value within 5 minutes); Water quality index data: Key indicators such as COD (chemical oxygen demand), ammonia nitrogen concentration, pH value, and suspended solids (SS) content are collected using online monitoring equipment. The data sampling frequency is no less than 1 time / minute to ensure that sudden changes in water quality (such as a sudden increase in COD caused by the mixing of industrial wastewater) are captured.

[0020] The above-mentioned coupling relationship data and real-time sewage data are stored in the real-time database of the digital twin system, providing dynamic input parameters for the generation of the virtual twin sub-model in the following step S20.

[0021] S20, extracting the operating data of each device from the digital twin model corresponding to the sewage treatment plant, and using several virtual twin sub-models independent of the digital twin model to perform simulation prediction based on the operating data, the coupling relationship data and the real-time sewage data to obtain potential faulty equipment and affected associated equipment.

[0022] This step is based on the coupling relationship data determined in step S10 and the real-time sewage data, and a targeted virtual twin model is constructed through the background, such as Figure 2 As shown, the future operating status of high-risk equipment can be simulated to accurately identify potential failures and chain reactions without interfering with the normal operation of the main digital twin model.

[0023] First, the digital twin model synchronizes the real-time sensor data and historical performance data of each physical device through a real-time data interaction interface, including: Real-time operating parameters: such as the inlet and outlet pressures, real-time power, and vibration amplitude of the sewage lift pump; the aeration volume, fan speed, and outlet air pressure of the aeration equipment; the operating current of the screen machine and the actual value of the grid bar spacing (taking into account changes due to wear), etc. The data synchronization frequency should be consistent with the sensor sampling frequency (no less than 1 time / 10 seconds); Cumulative performance indicators: cumulative equipment operating time, average load rate in the past 30 days, performance recovery coefficient after historical fault repair (such as the ratio of pump efficiency after repair to that before repair), etc., provide a basis for the preliminary assessment of fault risk.

[0024] Then, high-risk equipment is screened using a risk assessment algorithm. For example, if a device's real-time operating parameters (such as the torque of an aeration tank agitator) exceed the normal range for the corresponding sewage flow rate in the coupling relationship matrix, and the deviation reaches the warning threshold set in the linkage rule (for example, exceeding 15%), it will be classified as high-risk equipment.

[0025] An independent virtual twin model is constructed for each high-risk device. The virtual twin model only contains the device and its directly associated devices in the topology diagram (such as the blower associated with the aeration tank agitator and the biochemical tank liquid level sensor), and runs in the background computing unit of the digital twin system. It is independent of the visualization display module of the digital twin model (i.e., the main model), that is, it does not participate in the visualization rendering of the main model.

[0026] The input parameters of the virtual twin model include: current equipment operating data (as the initial state), parameter influence weights in the coupling relationship matrix (such as the correlation coefficient between agitator torque and aeration volume), and real-time sewage data (such as current COD concentration and flow rate). The virtual twin model is driven to run at a simulation step size (such as 1 minute / step), generating simulated operating data for high-risk equipment at different time periods in the future. This includes: key parameter change curves (such as the rising trend of bearing temperature with operating time), and the coordinated change relationship between parameters of related equipment (such as the passive adjustment range of blower aeration volume when agitator torque is abnormal). The simulation process strictly adheres to the linkage rules in the coupling relationship data (such as the coordinated adjustment logic of equipment in response to flow fluctuations).

[0027] Then, after obtaining the simulation data of each virtual twin model, the potential faulty equipment and affected associated equipment can be determined through threshold judgment and correlation analysis of the simulation data.

[0028] For example, when the operating parameters of a device (such as the vibration amplitude of the lift pump) in the simulation data of the virtual twin model exceed the normal threshold value under the corresponding sewage working conditions in the coupling relationship matrix for three consecutive simulation steps, and are consistent with the parameter change pattern before the historical fault (such as the vibration amplitude increases in a step-by-step manner), the device is judged to be a potential fault device.

[0029] Based on the device topology diagram and coupling relationship matrix, the impact of parameter changes in potentially faulty devices on associated devices can be traced. For example, if the virtual twin model indicates that a lift pump has a flow rate drop due to impeller wear (a potential fault), then based on the pre-relationship of "lift pump → grit chamber" in the topology and the influence weights of flow rate and grit chamber level in the coupling relationship matrix, it is calculated that the measurement deviation of the grit chamber level sensor will exceed the normal range, which in turn will cause the scraper to operate at an abnormal frequency. Therefore, the grit chamber level sensor and the scraper are identified as affected associated devices.

[0030] In addition, based on the coordinated change threshold set in the linkage rules, the degree to which the parameters of the affected associated equipment deviate from the normal range (such as the percentage deviation of the sand scraper operating frequency compared to the normal operating conditions) can be calculated to quantify the degree of impact and provide a basis for setting the priority of subsequent prompt information.

[0031] S30: Output prompt information related to the potential faulty device and the affected associated devices in the digital twin model.

[0032] This step uses the digital twin system’s visual interface to present fault prediction results in an intuitive manner, helping managers make quick decisions. For example: Spatial positioning prompts: In the 3D digital twin model, potential faulty equipment and related equipment are highlighted and flashed, and the processing unit where the equipment is located is displayed (such as "Biochemical Pool Area - Blower No. G3"); Parameter abnormality prompt: A real-time data panel pops up to compare and display the deviation of the current device parameters from the normal threshold (e.g., "Blower air pressure: current 2.3kPa < standard 3.0kPa, deviation -23%), and correlates it with the parameter change curve predicted in the virtual twin model; Impact range indication: Dynamic arrows are used to mark the fault propagation path (e.g., "blower → biochemical tank agitator → secondary sedimentation tank scraper"), and the degree of impact is distinguished by color (red indicates high-impact equipment, yellow indicates medium-impact equipment); Handling suggestions: Based on historical fault handling solutions and virtual simulation results, push preliminary response measures (such as "it is recommended to reduce the lift pump flow to 80% of the design value and start the backup blower at the same time").

[0033] In addition, the prompt information can also be pushed synchronously to the terminal devices of managers (such as the large screen of the monitoring center and mobile APP) to ensure the timeliness and operability of fault warnings.

[0034] This invention achieves fault prediction by constructing independently running virtual twin models for high-risk equipment. This model combines coupling relationship data, real-time sewage data, and equipment operating data to simulate future states. This expands the fault warning capabilities of digital twin models. Furthermore, because the virtual twin models run in an independent backend unit, they do not interfere with the normal operation of the main model, ensuring continuous monitoring and management. This also improves the accuracy of fault prediction and the efficiency of equipment chain impact analysis.

[0035] As an example, the operating data of each device extracted from the digital twin model corresponding to the sewage treatment plant includes: Inputting the real-time sewage data into the equipment topology diagram and coupling relationship matrix in the coupling relationship data, and calculating the theoretical operating parameter range of each device under the current sewage working condition; Compare the real-time operating parameters of each device in the digital twin model with the theoretical operating parameter range, and select devices whose parameter deviation exceeds a preset threshold as the initial risk device set; Combined with the historical failure frequency, cumulative operating time, and maintenance records of each device, the comprehensive risk index of each initial risk device is calculated using the analytic hierarchy process. Initial risk devices with a comprehensive risk index higher than the risk threshold are selected as high-risk devices. In the digital twin model, extract real-time operating data of high-risk equipment and its directly associated upstream and downstream equipment.

[0036] There are many devices in a sewage treatment plant. If simulation is performed for each device, the computing processing load will be significantly increased. To this end, the present invention reduces the amount of data processing by focusing only on data extraction of high-risk equipment and its associated equipment, while ensuring the pertinence and accuracy of subsequent simulation using a virtual twin model.

[0037] First, the real-time sewage flow, COD concentration, ammonia nitrogen content and other parameters in the real-time sewage data are used as input variables and substituted into the predefined mathematical model (such as the multivariate linear regression equation) in the coupling relationship matrix to calculate the theoretical operating parameter benchmark values ​​of each device under the current sewage conditions.

[0038] Based on the series and parallel relationships between devices in the equipment topology diagram, an iterative algorithm transfers parameter influences. For example, when the inlet flow rate increases, the theoretical changes in downstream equipment parameters such as the booster pump outlet pressure, the grit chamber level, and the aeration volume of the aeration tank are calculated in sequence. The theoretical operating parameter baseline value is added to the theoretical change value to obtain the transferred and corrected theoretical operating parameter baseline value.

[0039] Based on the statistical analysis of historical operating data, a fluctuation range (such as ±5%) is set for each theoretical operating parameter benchmark value that has been transferred and corrected, forming a theoretical operating parameter range that includes an upper limit and a lower limit.

[0040] By dynamically adjusting the theoretical parameter range based on real-time sewage data, subsequent risk screening can be more in line with actual working conditions, avoiding misjudgments caused by fluctuations in sewage quality and water volume.

[0041] Then, based on the above theoretical operating parameter range, preliminary risk identification is performed on each device, specifically: The real-time operating parameters of each device in the digital twin model (such as boost pump current and aeration system air pressure) are compared point by point with the theoretical operating parameter range calculated above. The degree of deviation (exceeding the upper or lower limit) of the real-time operating parameter outside the theoretical range is calculated. Devices with parameter deviations exceeding a preset threshold (such as 10%) are marked as abnormal devices and all abnormal devices are included in the initial risk device set.

[0042] Then, a multi-dimensional risk assessment model is constructed through the Analytic Hierarchy Process (AHP) to achieve accurate risk classification. The specific process is as follows: Establish a risk assessment indicator system, including parameter deviation, historical failure frequency (number of failures in the past 12 months / number of operating days), cumulative operating time (current operating hours / design life hours), and maintenance records (time since the last overhaul / overhaul cycle).

[0043] Based on the experience of wastewater treatment experts, the relative importance weights of each indicator are determined. For example, parameter deviation is weighted at 0.4, historical failure frequency at 0.3, cumulative operating time at 0.2, and maintenance records at 0.1. After normalizing each indicator value, the weighted sum is substituted into the AHP model to calculate the comprehensive risk index for each initially risky device. A risk threshold (e.g., 0.6) is set, and devices with a comprehensive risk index above the threshold are designated as high-risk.

[0044] By comprehensively considering the real-time status, historical performance and maintenance status of the equipment, misjudgments caused by a single indicator can be avoided, thereby improving the reliability of risk identification.

[0045] At this point, based on the high-risk equipment list obtained above, key operating data can be extracted from the digital twin model to achieve accurate data acquisition. The specific implementation method is as follows: For each high-risk device, the following dimension data is extracted from the real-time database of the digital twin model: Physical parameters: such as bearing temperature, vibration frequency, inlet and outlet pressure difference, etc.; Performance parameters: such as treatment efficiency, energy consumption index, pollutant removal rate, etc.; Status parameters: such as start / stop status, fault code, operating mode, etc.

[0046] Synchronously extract the upstream and downstream device data directly associated with the high-risk device in the device topology diagram. The association level is determined based on the impact weight in the coupling relationship matrix (such as devices with an impact weight > 0.5).

[0047] The extraction time window is, for example, the current time and continuous data for 2 hours before, with a sampling interval of no more than 10 seconds to ensure the integrity and timing characteristics of the data.

[0048] As an example, a plurality of virtual twin sub-models independent of the digital twin model are used to perform simulation prediction based on the operation data, the coupling relationship data, and the real-time sewage data, including: Calculate the deviation rate of each parameter of the real-time sewage data of this operation cycle and the historical sewage data of the recent period, determine the impact weight of each parameter deviation rate on each high-risk equipment based on the coupling relationship matrix, and calculate the comprehensive impact degree by weighting each impact weight; The simulation step length is determined based on the comprehensive impact degree, and the virtual twin model corresponding to each high-risk equipment is driven according to the simulation step length to perform simulation based on the operation data, the coupling relationship data and the real-time sewage data.

[0049] Because wastewater processing conditions are inherently random (e.g., a sudden increase in COD due to industrial wastewater flow), the degree to which equipment is impacted can change in real time. To address this, the present invention adaptively adjusts the simulation step size of the virtual twin model based on the deviation rate. This ensures accurate simulation even under drastic changes in processing conditions and efficient operation under stable conditions, balancing timeliness and reliability.

[0050] First, the impact of sewage data deviation on high-risk equipment is quantified to provide a basis for subsequent simulation step size decisions, including: For key parameters in real-time sewage data (such as flow rate, COD concentration, and ammonia nitrogen content), calculate the deviation rate from the recent historical sewage data (such as the average value of the last 24 or 48 hours). Deviation rate = (|real-time parameter value - historical parameter average value| / historical parameter average value) × 100%. For example, the real-time flow rate is 1200m 3 / h, the historical average is 1000 m 3 / h, the flow deviation rate is 20%.

[0051] Based on the preset parameter-equipment impact weights in the coupling relationship matrix (e.g., the impact weight of flow deviation on the lift pump is 0.7, the impact weight on the screen machine is 0.5; the impact weight of COD deviation on the aeration tank is 0.6), the deviation rate of each parameter is associated with the corresponding weight.

[0052] For a single high-risk device, the overall impact level is calculated by multiplying the deviation rates of each associated parameter by the corresponding impact weight. For example, if a lift pump has a flow deviation rate of 20% (weight 0.7) and a COD deviation rate of 5% (weight 0.2), the overall impact level is 20% × 0.7 + 5% × 0.2 = 15%.

[0053] Then, the simulation accuracy of the virtual twin model corresponding to each high-risk device is dynamically adjusted according to the comprehensive impact degree obtained above to achieve optimal resource allocation.

[0054] For example: preset simulation step rules, such as when the comprehensive impact degree is greater than 20%, use a fine step size of 0.5 minutes / step; when it is 10%-20%, use a standard step size of 1 minute / step; when it is less than 10%, use a simplified step size of 2 minutes / step.

[0055] Each virtual twin model of a high-risk piece of equipment is matched to a corresponding simulation step size. Operating data (i.e., real-time operating data for the high-risk piece of equipment and its directly connected upstream and downstream equipment), coupling relationship data, and real-time wastewater data are input, and the model simulation is driven by the step size. For example, for a boost pump model with a 15% impact, the operating state for the next 0.5 hours is simulated at a 1-minute step, with output data such as bearing temperature changes and outlet pressure fluctuations.

[0056] In addition, the present invention also designs a dynamic adjustment mechanism: if the real-time sewage data deviation rate changes suddenly (such as the flow deviation rate increases from 10% to 25%), the virtual twin model automatically recalculates the comprehensive impact degree and switches to the corresponding step size (such as adjusting from 1 minute / step to 0.5 minutes / step) to ensure that the simulation accuracy adapts to the changes in working conditions.

[0057] It's important to note that, in addition to relying on operational data and real-time wastewater data, the virtual twin model should also rely on historical data over a certain period of time. This includes historical operational and wastewater data for each device, such as the past hour. This specific period can be determined based on the model's historical prediction accuracy, but the details are omitted here.

[0058] As an example, the driving of the virtual twin model corresponding to each high-risk device according to the simulation step size to perform simulation based on the operation data, the coupling relationship data, and the real-time sewage data includes: During the simulation process, the instantaneous fluctuation parameters of the sewage data are monitored in real time. If there is an instantaneous fluctuation parameter higher than the fluctuation threshold, the remaining time between the current moment and the end of the simulation is calculated; Determining a corresponding impact estimation coefficient based on the association weight between the instantaneous fluctuation parameter and the high-risk device in the coupling relationship matrix and the remaining time evaluation; If the impact estimation coefficient is higher than the coefficient threshold, subsequent simulation is performed based on the instantaneous fluctuation parameter.

[0059] In the aforementioned embodiment, the virtual twin model simulates a specific period of historical data and real-time data (operational data of each device, real-time sewage data, and fixed coupling relationship data). However, during the simulation process, sewage data may experience abnormal fluctuations. In such cases, these fluctuations need to be incorporated into the simulation's baseline data to improve the accuracy of the simulation results. Otherwise, these fluctuations need not be incorporated into the simulation's baseline data to improve simulation efficiency. Furthermore, when the total simulation duration is long, the decision of whether to include abnormally fluctuating sewage data in the simulation's baseline data becomes even more significant.

[0060] To this end, the present invention conducts a quantitative analysis of the impact of abnormal fluctuations in sewage data monitored during the simulation process on the simulation results, and then decides whether to include the abnormally fluctuating sewage data in the simulation basic data. The details are as follows: First, during the virtual twin model's simulation at a set step size, instantaneous values ​​of wastewater data (such as flow rate, COD concentration, and ammonia nitrogen content) are collected in real time. The rate of change of these parameters between adjacent sampling moments is calculated, and this rate of change is defined as the instantaneous fluctuation parameter. When the instantaneous fluctuation parameter exceeds a preset fluctuation threshold (e.g., 20%), it is identified as an abnormal fluctuation requiring attention.

[0061] At the same time, the current time when the abnormal fluctuation occurs is recorded. Based on the preset total simulation period (e.g., 20 minutes), the remaining time from the current time to the end of the simulation is calculated (e.g., if an abnormal fluctuation occurs at the 10th minute of the simulation, the remaining time is 10 minutes). This remaining time reflects the potential impact period of the abnormal fluctuation on subsequent simulation processes. The longer the remaining time, the more significant the cumulative impact of the fluctuation may be.

[0062] Next, through the coupled analysis of the association weight and the remaining time, the potential impact of abnormal fluctuations on the simulation results is quantified, including: The association weights of the instantaneous fluctuation parameters and the corresponding high-risk equipment are retrieved from the coupling relationship matrix (for example, the association weight of flow fluctuation on the lift pump is 0.6, and the association weight on the screen machine is 0.4). This weight reflects the theoretical impact of parameter fluctuations on equipment operation.

[0063] A weighted formula is used to combine the impact estimation coefficient of the association weight and the remaining duration: Impact estimation coefficient = instantaneous fluctuation parameter × association weight × (remaining duration / total simulation period). For example, if the instantaneous fluctuation parameter is 25%, the association weight is 0.6, and the remaining duration is 10 minutes (total period is 20 minutes), the impact estimation coefficient = 25% × 0.6 × (10 / 20) = 7.5%.

[0064] The impact estimation coefficient is a comprehensive measure of the impact of fluctuation intensity, equipment correlation and impact duration on the simulation results of this round. The higher the value, the greater the potential impact on the simulation results of this round.

[0065] Set a coefficient threshold (such as 7%). If the impact estimation coefficient is higher than the coefficient threshold, it means that the fluctuation has a significant impact on the simulation cycle results, and the instantaneous fluctuation parameters need to be included in the subsequent simulation; if it is lower than the threshold, it is determined that the fluctuation impact is limited and does not need to be included. The virtual twin model continues to simulate based on the stable data before the fluctuation.

[0066] It is understandable that when deciding to incorporate instantaneous fluctuation parameters into subsequent simulations, the input boundary conditions of the virtual twin model are updated for the incorporated instantaneous fluctuation parameters, and the theoretical operating parameters of the high-risk equipment and its associated equipment after the fluctuation are recalculated based on the coupling relationship matrix (such as the theoretical outlet pressure of the boost pump after a sudden increase in flow), and the model is driven to continue running according to the originally set simulation step size to generate simulation data that includes the impact of fluctuations (such as the dynamic response curve of equipment parameters with fluctuations).

[0067] This embodiment achieves accurate inclusion of high-impact fluctuations by comprehensively evaluating fluctuation intensity, equipment correlation, and impact duration, thereby preventing minor fluctuations from interfering with simulation stability and ensuring that major operating condition changes are reflected in a timely manner, thereby improving the simulation reliability of the virtual twin model.

[0068] As an example, the driving of the virtual twin model corresponding to each high-risk device according to the simulation step size to perform simulation based on the operation data, the coupling relationship data and the real-time sewage data further includes: Determine the number of high-risk devices and their directly associated upstream and downstream devices contained in the real-time operation data, and selectively activate the lightweight model, standard model, or enhanced model in the virtual twin model based on the number of devices.

[0069] The present invention pre-builds a virtual twin model containing three types of models for each device in a sewage treatment plant, namely a lightweight model, a standard model, and an enhanced model.

[0070] Lightweight model: A simplified model is used to retain only the core parameters of the equipment (such as the flow rate and pressure of the lift pump) and key coupling relationships, ignoring minor parameters and weakly associated equipment to speed up the simulation rate; Standard model: Completely build the physical model of the equipment and the parameter association logic, using preset standard simulation algorithms (such as finite element analysis) to ensure simulation accuracy while maintaining reasonable computational efficiency; Enhanced model: A distributed computing framework is introduced to decompose the model into multiple sub-modules for parallel calculation. At the same time, reduced-order modeling techniques (such as the balanced truncation method) are used to simplify complex parameter relationships, reducing the computational load while ensuring high-precision simulation.

[0071] When a device is identified as high-risk, the system analyzes the number of devices in the corresponding associated group (i.e., the high-risk device and its associated upstream and downstream devices) and decides which of the three models to activate based on the number of devices. For example, if the number of devices is ≤ 5 (low complexity), the lightweight model is activated; if the number is ≤ 6 devices or ≤ 15 devices (medium complexity), the standard model is activated; and if the number of devices is > 15 (high complexity), the enhanced model is activated.

[0072] Therefore, by dynamically adjusting the architecture of the virtual twin model according to the number of devices involved in the simulation, when the number of devices is small and the simulation difficulty is low, a model architecture that is conducive to improving the simulation speed is adopted; when the devices are complex and the simulation difficulty is high, a model architecture that is conducive to improving the simulation accuracy is adopted. This can effectively solve the technical problem of balancing simulation accuracy and efficiency.

[0073] like Figure 3 As shown, the embodiment of the present invention further provides a sewage treatment plant monitoring and management system 100 based on digital twin technology, the system comprising an acquisition unit 1001, a simulation unit 1002, and a prompt unit 1003; The acquisition unit 1001 determines the coupling relationship data between the various devices in the sewage treatment plant, as well as the real-time sewage data of the sewage input in the current operation cycle, including sewage flow and water quality indicators; The simulation unit 1002 extracts operating data of each device from the digital twin model corresponding to the sewage treatment plant, and uses multiple virtual twin sub-models independent of the digital twin model to perform simulation prediction based on the operating data, the coupling relationship data, and the real-time sewage data to obtain potential faulty devices and affected associated devices; The prompt unit 1003 outputs prompt information related to the potential faulty device and the affected associated devices in the digital twin model.

[0074] As an example, the acquiring unit 1001 is configured to: Inputting the real-time sewage data into the equipment topology diagram and coupling relationship matrix in the coupling relationship data, and calculating the theoretical operating parameter range of each device under the current sewage working condition; Compare the real-time operating parameters of each device in the digital twin model with the theoretical operating parameter range, and select devices whose parameter deviation exceeds a preset threshold as the initial risk device set; Combined with the historical failure frequency, cumulative operating time, and maintenance records of each device, the comprehensive risk index of each initial risk device is calculated using the analytic hierarchy process. Initial risk devices with a comprehensive risk index higher than the risk threshold are selected as high-risk devices. In the digital twin model, extract real-time operating data of high-risk equipment and its directly associated upstream and downstream equipment.

[0075] As an example, the simulation unit 1002 is configured to: Calculate the deviation rate of each parameter of the real-time sewage data of this operation cycle and the historical sewage data of the recent period, determine the impact weight of each parameter deviation rate on each high-risk equipment based on the coupling relationship matrix, and calculate the comprehensive impact degree by weighting each impact weight; The simulation step length is determined based on the comprehensive impact degree, and the virtual twin model corresponding to each high-risk equipment is driven according to the simulation step length to perform simulation based on the operation data, the coupling relationship data and the real-time sewage data.

[0076] As an example, the simulation unit 1002 is configured to: During the simulation process, the instantaneous fluctuation parameters of the sewage data are monitored in real time. If there is an instantaneous fluctuation parameter higher than the fluctuation threshold, the remaining time between the current moment and the end of the simulation is calculated; Determining a corresponding impact estimation coefficient based on the association weight between the instantaneous fluctuation parameter and the high-risk device in the coupling relationship matrix and the remaining time evaluation; If the impact estimation coefficient is higher than the coefficient threshold, subsequent simulation is performed based on the instantaneous fluctuation parameter.

[0077] As an example, the simulation unit 1002 is further configured to: Determine the number of high-risk devices and their directly associated upstream and downstream devices contained in the real-time operation data, and selectively activate the lightweight model, standard model, or enhanced model in the virtual twin model based on the number of devices.

[0078] An embodiment of the present invention further provides an electronic device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements any of the aforementioned methods when executed by the processor.

[0079] An embodiment of the present invention further provides a computer storage medium storing a computer program that can be executed by a processor to implement any of the methods described above.

[0080] An embodiment of the present invention further provides a computer program product, which includes a computer program that can be executed by a processor to implement any of the methods described above.

[0081] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A sewage treatment plant monitoring and management method based on digital twin technology, characterized by: The method comprises the following steps: Determine the coupling relationship data between various equipment in the sewage treatment plant, as well as the real-time sewage data of the sewage input during this operation cycle, including sewage flow and water quality indicators; Extracting the operating data of each device from the digital twin model corresponding to the sewage treatment plant, and using a plurality of virtual twin sub-models independent of the digital twin model to perform simulation prediction based on the operating data, the coupling relationship data, and the real-time sewage data, to obtain potential faulty devices and affected associated devices; Output prompt information related to potential faulty devices and affected associated devices in the digital twin model.

2. The sewage treatment plant monitoring and management method based on digital twin technology according to claim 1 is characterized by: The operating data of each device is extracted from the digital twin model corresponding to the sewage treatment plant, including: Inputting the real-time sewage data into the equipment topology diagram and coupling relationship matrix in the coupling relationship data, and calculating the theoretical operating parameter range of each device under the current sewage working condition; Compare the real-time operating parameters of each device in the digital twin model with the theoretical operating parameter range, and select devices whose parameter deviation exceeds a preset threshold as the initial risk device set; Combined with the historical failure frequency, cumulative operating time, and maintenance records of each device, the comprehensive risk index of each initial risk device is calculated using the analytic hierarchy process. Initial risk devices with a comprehensive risk index higher than the risk threshold are selected as high-risk devices. In the digital twin model, extract real-time operating data of high-risk equipment and its directly associated upstream and downstream equipment.

3. The sewage treatment plant monitoring and management method based on digital twin technology according to claim 2 is characterized by: Using a plurality of virtual twin sub-models independent of the digital twin model to perform simulation prediction based on the operation data, the coupling relationship data and the real-time sewage data, including: Calculate the deviation rate of each parameter of the real-time sewage data of this operation cycle and the historical sewage data of the recent period, determine the impact weight of each parameter deviation rate on each high-risk equipment based on the coupling relationship matrix, and calculate the comprehensive impact degree by weighting each impact weight; The simulation step length is determined based on the comprehensive impact degree, and the virtual twin model corresponding to each high-risk equipment is driven according to the simulation step length to perform simulation based on the operation data, the coupling relationship data and the real-time sewage data.

4. The sewage treatment plant monitoring and management method based on digital twin technology according to claim 3 is characterized by: Driving the virtual twin model corresponding to each high-risk device to perform simulation based on the operation data, the coupling relationship data, and the real-time sewage data according to the simulation step size includes: During the simulation process, the instantaneous fluctuation parameters of the sewage data are monitored in real time. If there is an instantaneous fluctuation parameter higher than the fluctuation threshold, the remaining time between the current moment and the end of the simulation is calculated; Determining a corresponding impact estimation coefficient based on the association weight between the instantaneous fluctuation parameter and the high-risk device in the coupling relationship matrix and the remaining time evaluation; If the impact estimation coefficient is higher than the coefficient threshold, subsequent simulation is performed based on the instantaneous fluctuation parameter.

5. The sewage treatment plant monitoring and management method based on digital twin technology according to claim 4 is characterized by: Driving the virtual twin model corresponding to each high-risk device to perform simulation based on the operation data, the coupling relationship data and the real-time sewage data according to the simulation step size, further comprising: Determine the number of high-risk devices and their directly associated upstream and downstream devices contained in the real-time operation data, and selectively activate the lightweight model, standard model, or enhanced model in the virtual twin model based on the number of devices.

6. A sewage treatment plant monitoring and management system based on digital twin technology, characterized by: The system includes an acquisition unit, a simulation unit, and a prompt unit; The acquisition unit determines the coupling relationship data between the various devices in the sewage treatment plant, as well as the real-time sewage data of the sewage input in the current operation cycle, including sewage flow and water quality indicators; The simulation unit extracts operating data of each device from the digital twin model corresponding to the sewage treatment plant, and uses a plurality of virtual twin sub-models independent of the digital twin model to perform simulation prediction based on the operating data, the coupling relationship data, and the real-time sewage data to obtain potential faulty devices and affected associated devices; The prompt unit outputs prompt information related to potential faulty devices and affected associated devices in the digital twin model.

7. The sewage treatment plant monitoring and management system based on digital twin technology according to claim 6 is characterized by: The acquisition unit is configured to: Inputting the real-time sewage data into the equipment topology diagram and coupling relationship matrix in the coupling relationship data, and calculating the theoretical operating parameter range of each device under the current sewage working condition; Compare the real-time operating parameters of each device in the digital twin model with the theoretical operating parameter range, and select devices whose parameter deviation exceeds a preset threshold as the initial risk device set; Combined with the historical failure frequency, cumulative operating time, and maintenance records of each device, the comprehensive risk index of each initial risk device is calculated using the analytic hierarchy process. Initial risk devices with a comprehensive risk index higher than the risk threshold are selected as high-risk devices. In the digital twin model, extract real-time operating data of high-risk equipment and its directly associated upstream and downstream equipment.

Images