Industrial park water resource big data application supervision system
The industrial park water resources big data application and supervision system, with its dual cloud-based collaborative architecture, has solved the problems of supervision errors and data security in the context of frequent changes in enterprises, and has achieved precise water resources supervision and collaborative optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NINGBO DAHONGYING UNIV
- Filing Date
- 2026-03-27
- Publication Date
- 2026-06-23
Smart Images
Figure CN122264573A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of water resource monitoring technology in industrial parks, specifically a big data application monitoring system for water resources in industrial parks. Background Technology
[0002] With the acceleration of industrialization and the increasing prominence of water scarcity, industrial parks, as the core carriers of industrial agglomeration, are increasingly characterized by high water consumption, complex water use scenarios, and high regulatory difficulty, making the demand for refined and intelligent water resource supervision increasingly urgent. Currently, big data application monitoring systems for industrial park water resources are gradually being applied to park water resource management, attempting to achieve full-process monitoring and control of park water resources through big data, the Internet of Things, and other technologies. However, in actual application, frequent changes in enterprises and infrastructure in industrial parks, such as frequent factory expansions, pipeline renovations, and new enterprise entry, result in temporary water use without fixed metering points, random water usage times, and complex purposes, covering various types including construction washing, concrete curing, and equipment debugging. This significantly differs from normal production water use by enterprises, leading to substantial regulatory errors in routine water resource supervision under these circumstances.
[0003] In order to solve this problem, the present invention provides a big data application monitoring system for water resources in industrial parks. Summary of the Invention
[0004] To address the problems of the above solutions, this invention provides an industrial park water resources big data application monitoring system.
[0005] The objective of this invention can be achieved through the following technical solutions: The industrial park water resources big data application monitoring system includes a sensing terminal, a user cloud, and a platform cloud; Furthermore, there is communication connection between the user cloud and the sensing end, and communication connection between the platform cloud and each user cloud.
[0006] The sensing device is used to collect water resource data from the industrial park, including regular water data and temporary water data, and then sends the water resource data to the user's cloud.
[0007] The user includes a digital twin module, a temporary information module, and a monitoring module; The digital twin module is used to construct a digital twin model of the industrial park and dynamically update it based on water resource data from the sensing end.
[0008] The temporary information module is used for temporary water use management, determining temporary water use areas within the industrial area in real time; acquiring temporary area information of the temporary water use areas; marking the temporary water use areas as isolated areas in the digital twin model based on the temporary area information; and sharing the temporary area information and the digital twin model with the platform cloud.
[0009] Furthermore, in the temporary information module, no corresponding processing is performed when it is determined that there is no temporary water use area.
[0010] Furthermore, data security measures are implemented for the shared digital twin model.
[0011] The monitoring module is used for water resource monitoring and real-time identification of whether the digital twin model has isolated areas; When there are no isolated areas, standard water resource monitoring is conducted based on digital twin models; When there are isolated areas, identify the isolation correction data and water use assessment results corresponding to the isolated areas in the digital twin model, and carry out water resource supervision and management for temporary water use areas based on the water use assessment results; and carry out standard water resource supervision and management for normal areas in the industrial park based on the isolation correction data and digital twin model.
[0012] The cloud-based platform is managed by the system platform provider and includes a platform analysis module. The platform analysis module is used to perform platform analysis, obtain temporary area information and digital twin models shared by various users in the cloud, conduct regulatory analysis on temporary area information and digital twin models based on big data, and obtain water use assessment results for temporary water use areas. The digital twin model is optimized and adjusted based on the water use assessment results of the temporary water use area, and the digital twin model in the user's cloud is updated synchronously based on the optimized digital twin model.
[0013] Furthermore, regulatory analysis is conducted based on big data on temporary area information and digital twin models, including: Based on temporary area information and digital twin models, comparative analysis features are extracted, and reference matching is performed based on big data according to the comparative analysis features to obtain reference targets; Assess the compliance of the temporary water use area with each reference target; remove reference targets with compliance below the threshold X1; When the number of remaining reference targets is equal to 0, assess the water use anomalies in the temporary water use area; When the number of remaining reference targets is greater than 0, the temporary water use area is assessed as having normal water use.
[0014] Furthermore, reference matching is performed based on big data comparative analysis features, including: Based on the temporary region information, the control analysis features are segmented to obtain several unit control features. Based on big data, reference matching is performed on each unit control feature to obtain the unit target corresponding to each unit control feature. By combining the objectives of each unit, several reference objectives are obtained.
[0015] Furthermore, the objectives of each unit are combined, including: Based on the comparison characteristics of each unit, the targets of each unit are arranged and combined to obtain several unit combinations. Each unit combination includes one unit target corresponding to the comparison characteristics of each unit. Each unit combination is filtered, and a reference target is generated based on the remaining unit combinations.
[0016] Furthermore, the digital twin model is optimized and adjusted based on the water use assessment results of the temporary water use area, including: Identify water use assessment results and supplement them into the isolated areas of the digital twin model; When the water use assessment result indicates abnormal water use, no optimization analysis will be performed; When the water use assessment result indicates that water use is normal, the isolation area is analyzed in real time based on the temporary area information and the digital twin model to obtain the isolation correction data corresponding to the isolation area, and the isolation correction data is added to the isolation area in the digital twin model.
[0017] Furthermore, based on temporary area information and digital twin models, the isolated area is analyzed and corrected in real time, including: Identify the individual targets corresponding to the isolated area, and assess whether each individual target has an impact on water resource supervision in the normal area of the industrial park based on the digital twin model; mark the units that have an impact as influential unit targets; Based on the reference target and digital twin model, the targets of each influential unit are analyzed to obtain isolation correction data.
[0018] Compared with the prior art, the beneficial effects of the present invention are: This invention effectively addresses the technical shortcomings of existing industrial park water resource monitoring systems, such as insufficient resource utilization due to a single cloud architecture, low accuracy in temporary water use monitoring, susceptibility to interference in normal area monitoring, lack of data security, and insufficient level of intelligent monitoring. It comprehensively improves the precision, intelligence, and collaboration of water resource monitoring in industrial parks by adopting a dual-cloud collaborative architecture to achieve complementary advantages and significantly enhance monitoring efficiency and resource utilization efficiency. This invention clearly distinguishes the functional positioning of the user cloud and the platform cloud. The user cloud focuses on daily water resource standard monitoring, data collection, and digital twin model construction, catering to the actual operational needs of park users with convenient and targeted operation. The platform cloud, relying on its ample GPU computing resources and LSTM algorithm model, focuses on in-depth analysis of temporary water use areas, judgment of park changes, and isolation correction data calculation, fully leveraging the platform's resource and technological advantages to solve the problems of insufficient computing power and low efficiency in complex scenario analysis in existing single cloud architectures.
[0019] By marking temporary water use areas as isolated areas in the digital twin model, precise segmentation between temporary and normal areas is achieved, ensuring that users can shield against interference from temporary water use data when conducting standard monitoring of normal areas in the cloud. At the same time, the platform identifies and removes insignificant target units and precisely corrects influential units to generate isolated and corrected data. Users apply this data to standard monitoring of normal areas in the cloud, effectively avoiding problems such as distorted water use statistics, water balance accounting deviations, and false or missed anomaly warnings caused by differences in temporary water use. This significantly improves the accuracy of water resource monitoring in normal areas and achieves synergistic optimization of monitoring between temporary and normal areas. Attached Figure Description
[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation
[0022] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0023] like Figure 1As shown, the industrial park water resources big data application monitoring system includes a sensing terminal, a user cloud, and a platform cloud. Communication connections between the user cloud and the sensing end, and between the platform cloud and each user cloud.
[0024] The sensing end is used to collect water resource data from the industrial park. The water resource data includes regular water data and temporary water data. Regular water data refers to the water resource data generated by normal enterprises in the park, while temporary water data refers to the water resource data corresponding to areas of change such as new enterprise settlement and factory expansion in the park. Key nodes are deployed in the industrial park, including enterprise water inlets, drainage outlets, key points of the pipeline network, and temporary construction water points. Intelligent electromagnetic flow meters, multi-parameter water quality instruments, water pressure sensors, and portable metering devices are deployed to collect real-time monitoring data such as enterprise water flow, water quality, pipeline pressure, and temporary water flow. For example, the collection frequency is once every 5 minutes, and the water resource data is transmitted to the user's cloud in real time.
[0025] The user cloud platform is operated and used by the park management committee, including a digital twin module, a temporary information module, and a supervision module; The digital twin module is used to construct a digital twin model of the entire water resource process in the industrial park, covering core information such as the topology of the park's water supply and drainage network, enterprise water usage nodes, and the distribution of monitoring points. It synchronizes water resource data from the sensing end in real time, enabling a visual display of network operation and enterprise water usage.
[0026] The temporary information module is used for temporary water use management and to determine temporary water use areas within the industrial area in real time. Temporary water use areas can be marked by users themselves or determined intelligently based on relevant data, such as the area where a new enterprise is located. No action will be taken if it is determined that there is no area for temporary water use. When a temporary water use area is identified, real-time information about the temporary water use area is obtained. This includes information such as the start time, duration, type of construction, personnel, and equipment used, as determined by video surveillance. Information can also be provided by the construction company or other entities. This information is aggregated into real-time temporary water use area data to improve the accuracy of the cloud-based platform's analysis. It also includes information collected from other devices, such as flow rate, duration, and water quality. A digital twin model is then created based on the temporary water use area information. The temporary water use area in the digital twin model is marked as an isolated area. This includes clearly defining the spatial boundaries, pipeline connections, and spatial adjacency with normal water use areas. The area is then marked as an isolated area in the digital twin model and assigned a unique isolation marker to clearly distinguish it from normal water use areas. Temporary area information and digital twin models will be shared with the platform's cloud.
[0027] In one embodiment, data security processing is performed on the shared digital twin model to ensure the data security of the park.
[0028] For example, before sharing the digital twin model with the platform's cloud, the private information of the park in the model is first subjected to hierarchical anonymization processing, retaining only the core data required for the platform's cloud analysis and removing sensitive information. Specifically, this includes: performing coordinate offset processing on the core control points of the park's pipeline network (such as the location of main pipeline valves and emergency water source reserve points) and the core production water nodes of enterprises (such as water points for classified processes), replacing the real geographical coordinates with a fuzzy mapping method to avoid precise positioning; shielding or anonymizing sensitive enterprise information (such as enterprise capacity, production process parameters, and classified water quotas), retaining only non-sensitive identifiers such as "enterprise number + water node type"; and deleting private information in the digital twin model involving park security and control boundaries, retaining only basic data such as pipeline topology, monitoring point distribution, and water use relationships related to water resource supervision and change analysis, ensuring that the anonymized model meets the platform's cloud analysis needs without leaking any private information.
[0029] Alternatively, only non-sensitive information for analysis, such as the spatial boundaries and pipeline connection points of the isolated area, can be retained, while confidential content such as construction details and enterprise secrets within the area is removed before being shared synchronously to the platform's cloud. Simultaneously, isolation analysis parameters are set in the digital twin model, clearly defining the independent data channel for the analysis scope of the isolated area. This ensures that when conducting isolation analysis, the platform's cloud can only access the isolated area and its associated non-sensitive data, and cannot access the core regulatory data of the normal area. This guarantees data security and avoids data confusion between temporary and normal areas during the analysis process.
[0030] The monitoring module is used for water resource monitoring and real-time identification of whether the digital twin model has isolated areas; When there are no isolated areas, standard water resource monitoring is conducted based on digital twin models; When there are isolated areas, identify the isolation correction data and water use assessment results corresponding to the isolated areas in the digital twin model, and carry out water resource supervision and management for temporary water use areas based on the water use assessment results; and carry out standard water resource supervision and management for normal areas in the industrial park based on the isolation correction data and digital twin model.
[0031] In one embodiment, standard water resource supervision can be carried out, such as real-time monitoring data viewing, water consumption statistics, abnormal water consumption early warning, and routine water balance accounting. Alternatively, a digital twin model can be used for simulation to automatically update supervision parameters (early warning thresholds, water consumption quotas, etc.) and simulate the water resource operation status of the park, including scenarios such as pipeline water transmission loss, enterprise water consumption fluctuations, and water quality changes. When there are no isolation areas, the operation status of the entire area can be simulated; when there are isolation areas, only the normal areas can be simulated based on the isolation correction data to eliminate the interference of isolation areas. Alternatively, water resource supervision can be carried out based on existing water resource supervision methods and the digital twin model.
[0032] The cloud-based platform is managed by the system platform provider and includes a platform analysis module. The platform analysis module is used to perform platform analysis, obtain temporary area information and digital twin models shared by various users in the cloud, conduct regulatory analysis on the temporary area information and digital twin models based on big data, obtain water use assessment results for temporary water use areas, optimize and adjust the digital twin models based on the water use assessment results of temporary water use areas, and synchronously update the digital twin models in the user's cloud based on the optimized digital twin models.
[0033] In one embodiment, regulatory analysis based on big data of temporary area information and digital twin models includes: Based on temporary area information and digital twin models, comparative analysis features are extracted. These features consist of two parts: one part is accurate water resource information generated by the actual consumption and recycling of water resources in the temporary water use area; the other part is comparative features related to water resource consumption and recycling, such as data reflecting water resource consumption and recycling during a certain period, such as vehicle washing, area dust removal, or project construction. Based on big data, reference matching is performed according to the comparative analysis features to obtain historical cases with corresponding comparative analysis features or those that can be considered the same, which are then marked as reference targets. Assess the likelihood of implementing temporary water use in accordance with reference targets, and label it as compliance. This is determined based on the specific circumstances of the entity corresponding to the temporary water use area. For example, for newly established enterprises, their production and operation information is used to determine whether they will implement the reference targets. If a certain water recycling method requires significant costs, and the likelihood of the enterprise using this method is 0, then the compliance is 0. Analyze each unit separately to determine its likelihood. This can be done by combining historical data with similar entities to statistically analyze the percentage of implementation according to the reference targets, and then converting this into likelihood. For example, preset the compliance levels corresponding to different percentages, obtain several coordinate points (percentage, compliance), fit them to form a matching curve, and then perform matching. Alternatively, a compliance assessment model can be established based on machine learning, deep learning algorithms, etc., and trained manually using a training set. The training set includes input data and output data. The input data is the entity information of the temporary water use area and the reference targets, and the output data is the compliance. Reference targets with a compliance rate below the threshold X1 are removed; When the number of remaining reference targets is 0, the water use in the temporary water use area is assessed as abnormal, and an early warning is issued to the user. The user then inquires and performs calibration. If the application is actually carried out in accordance with the reference targets, it is marked accordingly, and its compliance can be assessed as not being lower than the threshold X1, such as 100. When the number of remaining reference targets is greater than 0, the temporary water use area is assessed as having normal water use.
[0034] In one embodiment, reference matching is performed based on big data and comparative analysis features, and matching is performed based on overall data, meaning that a historical case can be directly matched with the comparative analysis features.
[0035] In one embodiment, reference matching based on big data and comparative analysis features includes: Based on the temporary area information, the comparative analysis features are segmented to obtain several unit comparative features. Based on big data, reference matching is performed on each unit comparative feature to obtain the unit target corresponding to each unit comparative feature. That is, the analysis units with the same unit comparative features in other projects are marked as unit targets. In other words, big data is used to obtain unit targets with the same unit comparative features from various data sources. In other embodiments, a case library of each unit target can also be established in advance for direct matching later. By combining the targets of each unit, several reference targets corresponding to different combinations can be obtained. For example, if there are two unit contrast features, A and B, A corresponds to two unit targets, 1 and 2, and B corresponds to one unit target, 3, then there are two reference targets, 13 and 23.
[0036] In one embodiment, reference targets are obtained by combining various unit targets to obtain several different combinations. Based on the above embodiment, the directly obtained reference targets are filtered to eliminate cases where unit target combinations are not performed in actual applications. A combination includes one unit target corresponding to each unit's comparative features. Even if a combination is actually performed, it is unreasonable and will be considered non-compliant in the subsequent process. Specifically, the judgment can be made in various ways. For example, information that can be combined can be preset and then matched later. The judgment can be made directly based on whether there are historical cases and whether the historical cases have been evaluated as not suitable for combination. The judgment can also be made based on intelligent models such as machine learning. Reference targets, i.e., combined cases, are generated based on the remaining unit combinations.
[0037] In one embodiment, the comparative analysis features are segmented based on the temporary area information. Specifically, based on the water resource management logic and scenario association characteristics, the temporary water use area is divided into several independent analysis units, each of which has a unique functional attribute, data boundary and analysis dimension. The analysis unit is the core carrier for temporary water use area segmentation. It refers to a single, independent water use / recycling scenario carrier, characterized by "unique function, independent data, and separate metering capability," and serves as the basic unit for constructing reference targets. It is divided into three categories based on water use / recycling type: Construction work unit: corresponds to a specific water-using operation in temporary construction, such as "concrete curing operation in the expansion of a factory", "pipeline flushing operation in a pipeline renovation section", "construction vehicle cleaning operation in a certain area", etc. Each unit corresponds to a unique operation type, construction location, and operation cycle, and can independently collect data such as water flow, operation duration, and water usage.
[0038] Dust removal and suppression unit: corresponding to dust removal / dehumidification operation scenarios in temporary areas of the park, such as "spraying dust suppression operation around a construction site fence" or "sprinkling dust suppression operation on exposed land". The unit definition includes operation location, operation time period, spraying / sprinkling equipment parameters, operation coverage area, and can independently collect data such as water consumption, operation frequency, and operation duration.
[0039] Recycling Unit: Corresponds to an independent recycling link within a temporary water use area, such as "Construction Washing Wastewater Collection and Recycling Unit", "Vehicle Washing Wastewater Sedimentation and Recycling Unit", "Dust Removal Wastewater Collection and Reuse Unit", etc.; The unit definition includes recycling location, recycling method (sedimentation / filtration / collection tank), recycled water volume, reuse destination, and treatment process parameters, and can independently collect data such as recycled water volume, water quality indicators, and reuse rate; The temporary region information is divided according to the above unit types to obtain several analysis units. The control analysis features are then segmented according to the analysis units to obtain the unit control features corresponding to each analysis unit.
[0040] For example, the "Water Use List" in the filing information is extracted and matched with the corresponding operation links one by one. For example, if the filing is "concrete curing + vehicle washing + pipe flushing", and there is one vehicle washing area, three concrete curing areas and one pipe flushing area in the temporary water use area, then there are 1+3+1=5 analysis units.
[0041] In one embodiment, regulatory analysis is performed on temporary area information and digital twin models based on big data, and the analysis is conducted using existing methods to determine whether the temporary water use area is abnormal.
[0042] For example, by acquiring water use registration information (estimated water consumption, water use period, water use purpose) and water resource data (flow rate, duration, water quality, etc.), the water use data of temporary water use areas can be analyzed over time using the LSTM algorithm model to uncover the time distribution patterns and flow fluctuation characteristics of water use in temporary water use areas. The actual water use data can be compared with the estimated water consumption and reasonable water use fluctuation thresholds in the registration to determine whether the water use in temporary water use areas exceeds the estimated range, the water use period does not match the registration, or there are abnormal changes in flow. At the same time, by combining auxiliary data such as construction progress and weather in temporary water use areas, the rationality of water use can be further verified, and abnormal problems such as disorderly water use and illegal water use in temporary water use areas can be accurately identified.
[0043] In one embodiment, optimizing the digital twin model based on water use assessment results for the temporary water use area includes: Identify water use assessment results; When the water use assessment result indicates abnormal water use, no optimization analysis will be performed; When the water use assessment result is normal, the isolation area is analyzed and corrected in real time based on the temporary area information and the digital twin model. The isolation correction data of the isolation area to the water resource supervision of the normal area in the park based on the digital twin model is obtained. The isolation correction data is added to the isolation area in the digital twin model to facilitate dynamic adjustment based on the isolation correction data.
[0044] In one embodiment, the isolated area is analyzed and corrected in real time based on temporary area information and digital twin model. Relying on its own GPU computing resources and LSTM algorithm model, the isolated area is analyzed and corrected in real time. The core purpose is to screen out the unit targets that have no impact on the normal area water resource supervision, focus on the affected units for precise correction, and provide support for subsequent acquisition of isolation correction data. Based on the unit targets of the previously segmented temporary water use areas, and combined with the pipeline topology relationship and water use interaction logic between the isolated area and the normal area in the digital twin model, we identify whether each unit target has an impact on the water resource supervision of the normal area, clarify the judgment criteria for unit targets without impact, and complete the elimination operation. For example, the judgment criteria for unit targets without impact are: the water use and water recycling behavior of the unit has no connection with the pipeline network of the normal area of the park, no water volume interaction, no water quality impact, and its water consumption and recycling process will not cause fluctuations in parameters such as pressure, flow, and water quality of the pipeline network in the normal area, and will not affect the water balance accounting and abnormal early warning of the normal area.
[0045] For the remaining impactful units after removing insignificant units, a multi-dimensional correction analysis is conducted using a digital twin model and reference target data. The core is to quantify the impact of the temporary water use behavior of the impactful unit on the water resource supervision of the normal area, thereby determining accurate isolation correction data. For example, each impactful unit is associated with the normal area pipeline network and water use nodes in the digital twin model to clarify the impact dimensions, which mainly include: the impact of normal area inflow, the impact of normal area water consumption accounting, the impact of normal area pipeline network pressure fluctuation, the potential impact of normal area water quality pollution, and the impact of normal area water balance accounting. Each impact dimension corresponds to a clear correction indicator. Based on the LSTM algorithm model, the real-time water use data (water consumption, consumption rate, water recovery volume, and water use period) of the affected unit target are compared with the corresponding unit target of the matched reference target to calculate the deviation value between the current temporary water use behavior and the reference target. At the same time, the digital twin model is combined to simulate the degree of influence of the water use behavior of the unit target on the relevant parameters of the normal area and obtain the initial impact quantification data. By combining real-time fluctuations in temporary water use (such as sudden changes in water consumption and adjustments to work schedules), the initial impact quantification data is dynamically corrected. Normal fluctuations in temporary water use (such as reasonable changes in water consumption due to adjustments in construction progress) are eliminated, while the impact of abnormal fluctuations (such as sudden increases in water consumption due to disordered water use) on normal areas is retained. At the same time, the simulation and deduction function of the digital twin model is used to simulate the impact of influencing unit targets on normal areas under different water use scenarios, calibrate and correct the data, and ensure the accuracy of the correction results. For each impact dimension, the corresponding isolation correction data is calculated. For example, in the normal area influent flow dimension, the deviation value of normal area influent flow caused by the water use of the impacted unit target is calculated as influent isolation correction data; in the normal area water consumption accounting dimension, the consumption accounting deviation value caused by the interaction between the impacted unit target and the normal area pipeline network is calculated as consumption isolation correction data; in the pipeline pressure dimension, the correction value of normal area pipeline pressure fluctuation caused by the water use of the impacted unit target is calculated as pressure isolation correction data.
[0046] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the industrial park water resources big data application monitoring system as described in the above embodiments.
[0047] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.
[0048] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.
Claims
1. An industrial park water resources big data application monitoring system, characterized in that, This includes the sensing end, user cloud, and platform cloud; The sensing device is used to collect water resource data from the industrial park. The water resource data includes regular water data and temporary water data, and then sends the water resource data to the user's cloud. The user includes a digital twin module, a temporary information module, and a monitoring module; the platform cloud includes a platform analysis module. The digital twin module is used to construct a digital twin model of the industrial park and dynamically update it based on water resource data from the sensing end. The temporary information module is used for temporary water use management, determining temporary water use areas within the industrial area in real time; acquiring temporary area information of the temporary water use areas; marking the temporary water use areas as isolated areas in the digital twin model based on the temporary area information; and sharing the temporary area information and the digital twin model with the platform cloud. The platform analysis module is used to perform platform analysis, obtain temporary area information and digital twin models shared by various users in the cloud, conduct regulatory analysis on temporary area information and digital twin models based on big data, and obtain water use assessment results for temporary water use areas. The digital twin model is optimized and adjusted based on the water use assessment results of the temporary water use area, and the digital twin model in the user's cloud is updated synchronously based on the optimized digital twin model. The monitoring module is used for water resource monitoring and real-time identification of whether the digital twin model has isolated areas; When there are no isolated areas, standard water resource monitoring is conducted based on digital twin models; When there are isolated areas, identify the isolation correction data and water use assessment results corresponding to the isolated areas in the digital twin model, and carry out water resource supervision and management of temporary water use areas based on the water use assessment results; Standard water resource monitoring is conducted in normal areas within the industrial park based on isolated and corrected data and digital twin models.
2. The industrial park water resources big data application monitoring system according to claim 1, characterized in that, Communication connections between the user cloud and the sensing end, and between the platform cloud and each user cloud.
3. The industrial park water resources big data application monitoring system according to claim 1, characterized in that, In the temporary information module, no action is taken if it is determined that there is no temporary water use area.
4. The industrial park water resources big data application monitoring system according to claim 1, characterized in that, Data security measures are implemented for shared digital twin models.
5. The industrial park water resources big data application monitoring system according to claim 1, characterized in that, Regulatory analysis based on big data of temporary area information and digital twin models includes: Based on temporary area information and digital twin models, comparative analysis features are extracted, and reference matching is performed based on big data according to the comparative analysis features to obtain reference targets; Assess the compliance of the temporary water use area with each reference target; remove reference targets with compliance below the threshold X1; When the number of remaining reference targets is equal to 0, assess the water use anomalies in the temporary water use area; When the number of remaining reference targets is greater than 0, the temporary water use area is assessed as having normal water use.
6. The industrial park water resources big data application monitoring system according to claim 5, characterized in that, Based on big data, reference matching is performed according to the characteristics of the comparative analysis, including: Based on the temporary region information, the control analysis features are segmented to obtain several unit control features. Based on big data, reference matching is performed on each unit control feature to obtain the unit target corresponding to each unit control feature. By combining the objectives of each unit, several reference objectives are obtained.
7. The industrial park water resources big data application monitoring system according to claim 6, characterized in that, The units are combined according to their respective objectives, including: Based on the comparison characteristics of each unit, the targets of each unit are arranged and combined to obtain several unit combinations. Each unit combination includes one unit target corresponding to the comparison characteristics of each unit. Each unit combination is filtered, and a reference target is generated based on the remaining unit combinations.
8. The industrial park water resources big data application monitoring system according to claim 6, characterized in that, The digital twin model was optimized and adjusted based on the water use assessment results of the temporary water use area, including: Identify water use assessment results and supplement them into the isolated areas of the digital twin model; When the water use assessment result indicates abnormal water use, no optimization analysis will be performed; When the water use assessment result indicates that water use is normal, the isolation area is analyzed in real time based on the temporary area information and the digital twin model to obtain the isolation correction data corresponding to the isolation area, and the isolation correction data is added to the isolation area in the digital twin model.
9. The industrial park water resources big data application monitoring system according to claim 8, characterized in that, Real-time correction analysis of the isolated area is performed based on temporary area information and a digital twin model, including: Identify the individual targets corresponding to the isolated area, and assess whether each individual target has an impact on water resource supervision in the normal area of the industrial park based on the digital twin model; mark the units that have an impact as influential unit targets; Based on the reference target and digital twin model, the targets of each influential unit are analyzed to obtain isolation correction data.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the industrial park water resources big data application monitoring system as described in any one of claims 1 to 9.