Water supply equipment intelligent inspection system based on big data analysis

Abstract

The invention discloses a water supply equipment intelligent inspection system based on big data analysis, relates to the technical field of water supply equipment inspection, and solves the problems that in the prior art, the influence caused by bottom layer abnormity cannot be detected when abnormity of a water supply network is detected, and the influence on the bottom layer cannot be evaluated and detected after the abnormity of the water supply network is aggravated. The water supply network construction unit is used for carrying out physical network construction on water supply equipment and carrying out digital mapping on a pipe network according to data acquisition of each part of the physical network, so as to carry out model construction on the water supply network; the network step-by-step detection unit is used for carrying out step-by-step detection on the water supply network after the water supply network is constructed; the bottom layer extension influence analysis unit is used for carrying out influence analysis after operation transformation of branches or fulcrums in the water supply network; and the bottom layer feedback influence analysis unit performs bottom layer feedback influence analysis on the water supply network.

Description

Technical Field

[0001] This invention relates to the field of water supply equipment inspection technology, specifically to an intelligent water supply equipment inspection system based on big data analysis. Background Technology

[0002] Water supply equipment can be directly connected to the municipal water supply network, and directly pressurize the water supply based on the network pressure, saving energy. It has the advantages of being fully enclosed, pollution-free, small in size, and quick to install. It can also maintain constant water pressure by automatically changing the pump speed to meet water requirements. It is an energy-saving device and is suitable for high-rise buildings, office buildings, factories, service areas, schools, hospitals, hotels and other places.

[0003] However, in existing technologies, it is impossible to build a network based on the physical network and to digitally map the pipeline network based on data collection from various parts of the physical network. This reduces the efficiency of visual inspection of the network where the water supply equipment is located. At the same time, it is impossible to perform step-by-step inspection, which reduces the supply efficiency of the water supply network. In addition, when an anomaly is detected in the water supply network, it is impossible to detect the impact of the underlying anomaly, nor can it assess and detect the aggravation of the underlying impact after the water supply network anomaly occurs. This results in a decrease in inspection efficiency, an inability to quickly trace the source, and an inability to formulate inspection and maintenance strategies based on actual changes in impact, thus reducing the effectiveness of inspection.

[0004] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0005] The purpose of this invention is to solve the problems mentioned above by proposing an intelligent inspection system for water supply equipment based on big data analysis.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A smart inspection system for water supply equipment based on big data analysis includes a water supply equipment inspection platform, wherein the water supply equipment inspection platform has the following communication connections:

[0008] The water supply network construction unit builds a physical network for the water supply equipment and digitally maps the pipeline network based on data collected from various parts of the physical network, thereby constructing a model of the water supply network.

[0009] The network-level detection unit performs level-by-level detection of the water supply network after its construction.

[0010] The bottom-level extended impact analysis unit analyzes the impact of operational changes on branches or fulcrums within the water supply network.

[0011] The bottom-level feedback impact analysis unit performs bottom-level feedback impact analysis on the water supply network.

[0012] As a preferred embodiment of the present invention, the process of constructing a water supply network unit is as follows:

[0013] The system collects data on the water supply pipes connected to the water supply equipment in the current area, constructs a pipe network based on the pipe distribution, detects the distribution of the pipe network using GIS mapping technology, compares the actual mapped pipe network with the collected pipe network, determines the water supply network in use in real time, and divides the determined water supply network into branches, fulcrums, and pipe networks.

[0014] In a preferred embodiment of the present invention, the process of the network step-by-step detection unit is as follows:

[0015] The branch's own operating parameters are used as carrying parameters, while external parameters generated during the branch's water supply process are collected. During the water supply phase, the carrying parameters of each branch are recorded, and the parameter deviation is obtained based on the changes in the carrying parameters before and after water supply. A set of parameter deviations for water supply is constructed, and a data floating curve is constructed based on a subset of the parameter deviation set. When external parameters are generated, an external parameter set is constructed, and a data floating curve is constructed based on a subset of the external parameter set.

[0016] In a preferred embodiment of the present invention, the numerical fluctuation time of the parameter deviation set is recorded, and the fluctuation time of the data fluctuation curve of the external parameter set is also recorded. If the two types of numerical fluctuation times overlap or the interval duration continues to decrease, the current branch is marked as a high-load branch; if the two types of numerical fluctuation times are not adjacent or the interval duration fluctuates back and forth, the current branch is marked as a low-load branch.

[0017] When the high-load branch is running, the numerical fluctuation range of the external parameter and the numerical fluctuation range of the parameter deviation set are collected at the same time, and the numerical fluctuation range ratio is calculated based on the ratio and marked as the supply influence conversion coefficient. When the low-load branch is running, the numerical fluctuation frequency of the external parameter and the numerical fluctuation frequency of the parameter deviation set are collected at the same time, and the maximum growth range of the numerical fluctuation frequency of the parameter deviation set is obtained when the numerical fluctuation frequency of the external parameter does not increase, and it is marked as the load influence conversion coefficient.

[0018] In a preferred embodiment of the present invention, the supply impact conversion coefficient and the load impact conversion coefficient are analyzed:

[0019] If the supply impact conversion coefficient exceeds the supply impact conversion coefficient threshold and the load impact conversion coefficient is lower than the load impact conversion coefficient threshold, it is marked as a multi-load adaptive branch and its location is sent to the water supply equipment inspection platform; if the supply impact conversion coefficient does not exceed the supply impact conversion coefficient threshold, or the load impact conversion coefficient is higher than the load impact conversion coefficient threshold, it is marked as a multi-load unadaptable branch and its location is sent to the water supply equipment inspection platform.

[0020] As a preferred embodiment of the present invention, the fulcrum connected to the multi-load adaptation branch is analyzed:

[0021] The multi-load adaptation branches connected by the fulcrum are sorted according to the water supply order. The external parameter set of the multi-load adaptation branches is recorded in real time. The highest floating span of the external parameter set of adjacent water supply multi-load adaptation branches is obtained. The external satisfaction deviation of adjacent branches is calculated based on the difference of the highest floating span of the corresponding multi-load adaptation branches in the same time period.

[0022] When multiple branches cooperate to supply water, if the external satisfaction deviation corresponding to consecutive adjacent branches is within the set deviation range, it is marked as an efficient allocation fulcrum; if the external satisfaction deviation after the current fulcrum allocates water supply is not within the set deviation range, it indicates that the allocation efficiency of the current fulcrum has decreased, and it is marked as an inefficient allocation fulcrum; a qualified water supply network is constructed by performing step-by-step detection on branches and fulcrums.

[0023] As a preferred embodiment of the present invention, the process of the underlying extension effect analysis unit is as follows:

[0024] Transforming a multi-load adaptive branch into a multi-load non-adaptive branch is marked as a branch impact transformation; transforming an efficient allocation pivot into an inefficient allocation pivot is marked as a pivot impact transformation.

[0025] The system obtains the real-time setting parameters of the fulcrum covered by the corresponding water supply trajectory during the branch influence transformation process. Based on the setting time of the real-time setting parameters, the resetting frequency is obtained. The numerical increase rate of the resetting frequency is obtained during the current process and marked as the fulcrum extension influence data. The system obtains the water supply satisfaction of each location in the water supply network during the fulcrum influence transformation process. Based on the decrease in water supply satisfaction, the corresponding water supply network coverage area is obtained. The water supply satisfaction is expressed as the duration during which the water supply volume or water supply speed in the current coverage area of ​​the water supply network meets the set value.

[0026] In a preferred embodiment of the present invention, if the rate of increase of the reset frequency exceeds a set increase rate threshold, or the coverage area of ​​the water supply network where water supply satisfaction decreases exceeds a coverage area threshold, a water supply network extension impact signal is generated and sent to the water supply equipment inspection platform. Based on the collected data, the corresponding branch or fulcrum is taken as the inspection and maintenance object. If the rate of increase of the reset frequency does not exceed the set increase rate threshold, and the coverage area of ​​the water supply network where water supply satisfaction decreases does not exceed the coverage area threshold, a water supply network extension safety signal is generated and sent to the water supply equipment inspection platform.

[0027] In a preferred embodiment of the present invention, the process of the underlying feedback impact analysis unit is as follows:

[0028] During the inspection and maintenance of the target, the continuous decline duration of the support points corresponding to the area of ​​decreased water supply satisfaction in the water supply network and the rate of increase in the number of support points that first appear to decline in the area of ​​decreased water supply satisfaction are obtained and marked as the decline aggravation parameter and decline expansion parameter, respectively.

[0029] The duration during which external parameters remain stable after the current set parameters of the support points within the water supply network are obtained, as well as the deviation between the required external parameter values ​​and the actual satisfied values ​​after the set parameters are reset, and these are marked as supply stability information and supply satisfaction information, respectively.

[0030] In a preferred embodiment of the present invention, when either the aggravated drop parameter or the expanded drop parameter exceeds the corresponding set parameter threshold, or when either the stable supply information or the satisfied supply information does not exceed the set information threshold, a feedback impact abnormal signal is generated and sent to the water supply equipment inspection platform; when neither the aggravated drop parameter nor the expanded drop parameter exceeds the corresponding set parameter threshold, and both the stable supply information and the satisfied supply information exceed the set information threshold, a feedback impact normal signal is generated.

[0031] Compared with the prior art, the beneficial effects of the present invention are:

[0032] 1. In this invention, a physical network is built for the water supply equipment, and the pipeline network is digitally mapped based on the data collected from each part of the physical network, thereby constructing a model of the water supply network so that the pipeline network can be visualized and managed during the inspection process. At the same time, big data technology is integrated to compare data on the basis of the digitally mapped pipeline network during the inspection, so as to improve the accuracy of pipeline network detection.

[0033] 2. In this invention, the water supply network is tested step by step, and the components of the water supply network are branches, fulcrums and pipe networks from low to high. Through step-by-step testing, it is possible to infer whether the real-time supply efficiency of the water supply network is qualified, thereby inferring whether there is a fault in the current water supply network. Based on step-by-step testing, the cause of the fault can be accurately traced, and targeted maintenance can be carried out. At the same time, when a fault occurs, a rapid response can be made, a visual early warning can be given to the water supply network, and timely adjustments can be made according to the early warning situation to ensure the balanced and stable operation of the current water supply network.

[0034] 3. In this invention, the impact analysis is performed on the operation changes of branches or fulcrums within the water supply network to improve the real-time abnormal impact detection of the water supply network and increase the detection efficiency of the water supply network. At the same time, when abnormal impact occurs, the impact analysis of the water supply network can be performed based on extended impact analysis, and multi-point synchronous maintenance can be carried out based on the actual impact to avoid incomplete maintenance when the water supply network is inspected abnormally, which would increase the continuous range of water supply impact and affect the overall supply efficiency of the water supply network.

[0035] 4. In this invention, a bottom-level feedback impact analysis is performed on the water supply network to infer whether the impact will intensify and feed back to the bottom level after the bottom-level extended impact occurs, resulting in a vicious cycle that leads to a decrease in the supply efficiency of the water supply network. The feedback impact analysis improves the comprehensiveness of the inspection platform and further improves the inspection efficiency. Attached Figure Description

[0036] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0037] Figure 1 This is a system principle block diagram of the present invention;

[0038] Figure 2 This is a flowchart of the method of the present invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0041] Please see Figures 1-2 As shown, an intelligent inspection system for water supply equipment based on big data analysis includes a water supply equipment inspection platform, wherein the water supply equipment inspection platform is communicatively connected to a water supply network construction unit, a network hierarchical detection unit, a bottom-level extended impact analysis unit, and a bottom-level feedback impact analysis unit.

[0042] Example 1

[0043] The water supply equipment inspection platform generates a water supply network construction signal and sends it to the water supply network construction unit.

[0044] After receiving the water supply network construction signal, the water supply network construction unit builds a physical network for the water supply equipment and performs digital mapping of the pipeline network based on the data collected from each part of the physical network. This allows for the construction of a model of the water supply network, enabling visual management of the pipeline network during inspections. At the same time, during inspections, big data technology is integrated to compare data based on the digitally mapped pipeline network, thereby improving the accuracy of pipeline network detection.

[0045] The system collects data on the water supply pipes connected to the current water supply equipment in the area, constructs a pipe network based on the pipe distribution, detects the distribution of the pipe network using GIS mapping technology, compares the actual mapped pipe network with the collected pipe network to determine the water supply network in use in real time, and divides the determined water supply network into branches, fulcrums, and pipe networks. Branches represent pipes at various locations within the water supply network, fulcrums represent the fulcrums connected to various pipes within the water supply network, and pipe networks represent the water supply network constructed by the pipes connected to and running through the fulcrums.

[0046] After the water supply network is constructed, the real-time water supply network is sent to the water supply equipment inspection platform. When the platform receives a water supply equipment abnormality, it verifies the location based on the currently stored water supply network to ensure that there is no positional deviation between the current water supply equipment warning signal location and the network location. This ensures accurate visualization feedback of the water supply network during real-time inspection and improves inspection efficiency.

[0047] After the water supply network is constructed, a network hierarchical detection signal is generated and sent to the network hierarchical detection unit. Upon receiving the network hierarchical detection signal, the network hierarchical detection unit performs hierarchical detection on the water supply network. The components of the water supply network are branches, fulcrums, and pipe networks from low to high. Through hierarchical detection, it is possible to infer whether the real-time supply efficiency of the water supply network is up to standard, thereby inferring whether there is a fault in the current water supply network. Based on hierarchical detection, the cause of the fault can be accurately traced, and targeted maintenance can be carried out. At the same time, when a fault occurs, it is possible to respond quickly, provide visual early warning of the water supply network, and make timely adjustments based on the early warning situation to ensure the current water supply network operates in a balanced and stable manner.

[0048] The branch's own operating parameters are used as load-bearing parameters, and these parameters are continuously monitored. At the same time, external parameters generated during the branch's water supply process are collected. The load-bearing parameters are the branch's own pressure, surface deformation, and other pipeline parameters. The external parameters are the parameters generated during the branch's water supply, such as water supply speed and pressure fluctuation range during water supply.

[0049] During the water supply phase, the load-bearing parameters of each branch are recorded, and the parameter deviations are obtained based on the changes in load-bearing parameters before and after water supply. A set of parameter deviations for water supply is constructed, and a data fluctuation curve is built based on a subset of the parameter deviation set. When external parameters are generated, a set of external parameters is constructed, and a data fluctuation curve is built based on a subset of the external parameter set. It should be noted that during detection, the parameters that have the greatest impact on pipeline water supply are used as the curve acquisition parameters based on historical big data analysis.

[0050] Infer whether the water supply execution branch is affected by the comparison of the floating curves;

[0051] Record the time of fluctuation of the numerical values ​​of the parameter deviation set, and at the same time record the time of fluctuation of the data fluctuation curve of the external parameter set. If the two types of numerical fluctuation times overlap or the interval duration continues to decrease, it indicates that the current water supply has a high impact on the branch's load parameters, and the current branch is marked as a high-load branch. If the two types of numerical fluctuation times occur at non-adjacent times or the interval duration fluctuates back and forth, it indicates that the current water supply has a low impact on the branch's load parameters, and the current branch is marked as a low-load branch.

[0052] When the high-load branch is running, the numerical fluctuation range of the external parameters and the numerical fluctuation range of the parameter deviation set are collected at the same time, and the numerical fluctuation range ratio is calculated based on the ratio and marked as the supply impact conversion coefficient.

[0053] When the low-load branch is running, the numerical fluctuation frequency of the external parameter and the numerical fluctuation frequency of the parameter deviation set are collected at the same time. When the numerical fluctuation frequency of the external parameter does not increase, the maximum increase span of the numerical fluctuation frequency of the parameter deviation set is obtained and marked as the load influence conversion coefficient.

[0054] The conversion coefficients of supply impact and load impact will be analyzed:

[0055] If the supply impact conversion coefficient exceeds the supply impact conversion coefficient threshold and the load impact conversion coefficient is lower than the load impact conversion coefficient threshold, it is inferred that the current branch detection in the water supply network is normal, marked as a multi-load adaptation branch, and the location is sent to the water supply equipment inspection platform.

[0056] If the supply impact conversion coefficient does not exceed the supply impact conversion coefficient threshold, or the load impact conversion coefficient is higher than the load impact conversion coefficient threshold, it is inferred that the current branch detection in the water supply network is abnormal, marked as a multi-load unsuitable branch, and the location is sent to the water supply equipment inspection platform.

[0057] After receiving the data, the water supply equipment inspection platform will control the water supply load of multiple unsuitable branches to reduce load fluctuations and keep the real-time load within the suitable load range to ensure the stability of the water supply network. Branch detection will also be performed during load control.

[0058] Analysis of the fulcrums connected to the multi-load adaptation branches:

[0059] The multi-load adaptation branches connected by the fulcrum are sorted according to the water supply order. The external parameter set of the multi-load adaptation branches is recorded in real time. The highest floating span of the external parameter set of adjacent water supply multi-load adaptation branches is obtained. The external satisfaction deviation of adjacent branches is calculated based on the difference of the highest floating span of the corresponding multi-load adaptation branches in the same time period. In this scenario, the data collected by the external parameter set is the water supply speed or water supply volume, which are parameters that reflect the water supply efficiency.

[0060] When multiple branches cooperate to supply water, if the external satisfaction deviation of consecutive adjacent branches is within the set deviation range, it indicates that the fulcrum performance of the corresponding adjacent branches is consistent and meets the water supply requirements, and is marked as an efficient allocation fulcrum; if the external satisfaction deviation is not within the set deviation range after the current fulcrum allocates water supply, it indicates that the allocation efficiency of the current fulcrum decreases, and is marked as an inefficient allocation fulcrum.

[0061] The inefficient allocation fulcrum is sent to the water supply equipment inspection platform. The water supply equipment inspection platform performs equipment hardware maintenance on the fulcrum and adjusts the fulcrum allocation. If there is a deviation in the water supply, the opening of the valve and other hardware where the fulcrum is located is adjusted.

[0062] A qualified water supply network is constructed by conducting step-by-step testing of branches and fulcrums.

[0063] Example 2

[0064] The water supply equipment inspection platform generates an impact analysis signal and sends it to the underlying extended impact analysis unit.

[0065] After receiving the impact analysis signal, the bottom-level extended impact analysis unit performs impact analysis on the operation changes of branches or fulcrums within the water supply network to improve the real-time abnormal impact detection of the water supply network and increase the detection efficiency of the water supply network. At the same time, when abnormal impact occurs, it can perform impact analysis on the water supply network based on the extended impact analysis and perform multi-point synchronous maintenance based on the actual impact to avoid incomplete maintenance when the water supply network is inspected abnormally, which would increase the duration of water supply impact and affect the overall supply efficiency of the water supply network.

[0066] Transforming a multi-load adaptive branch into a multi-load non-adaptive branch is marked as a branch impact transformation; transforming an efficient allocation pivot into an inefficient allocation pivot is marked as a pivot impact transformation; it should be explained that the underlying extension impact represents the impact on the pivot when the branch is abnormal, and the pivot impact represents the impact on the network;

[0067] The system obtains the real-time setting parameters of the water supply trajectory covering the fulcrum during the branch influence transformation process. Based on the setting time of the real-time setting parameters, the resetting frequency is obtained. In the current process, the numerical increase rate of the resetting frequency is obtained and marked as the fulcrum extension influence data. It should be explained that the setting parameters represent parameters such as the opening degree of the valve and other hardware corresponding to the fulcrum. Resetting means that if the current setting parameters are not suitable for the current water supply, the parameters are readjusted, such as increasing or decreasing the valve opening.

[0068] The water supply satisfaction of each location in the water supply network during the transformation of the fulcrum influence is obtained. The corresponding water supply network coverage area is obtained based on the decrease in water supply satisfaction. The water supply satisfaction is expressed as the duration for which the water supply volume or water supply speed in the current coverage area of ​​the water supply network meets the set value.

[0069] An analysis was conducted on the rate of increase in the reset frequency and the area of ​​the water supply network that experienced a decline in water supply satisfaction:

[0070] If the rate of increase of the reset frequency exceeds the set rate of increase threshold, or if the coverage area of ​​the water supply network where the water supply satisfaction decreases exceeds the coverage area threshold, it is inferred that the underlying extension impact analysis is abnormal, a water supply network extension impact signal is generated and sent to the water supply equipment inspection platform, and the corresponding branch or fulcrum is taken as the inspection and maintenance object based on the collected data, and maintenance is carried out in a timely manner.

[0071] If the rate of increase of the reset frequency value does not exceed the set rate of increase threshold, and the coverage area of ​​the water supply network where the water supply satisfaction decreases does not exceed the coverage area threshold, then it is inferred that the bottom extension impact analysis is normal, and a water supply network extension safety signal is generated and sent to the water supply equipment inspection platform.

[0072] Example 3

[0073] Based on the previous embodiment, after the extended impact occurs, it is inferred whether there is a risk of the impact being aggravated by the underlying feedback impact analysis, and an underlying feedback impact analysis signal is generated and sent to the underlying feedback impact analysis unit.

[0074] After receiving the bottom-level feedback impact analysis signal, the bottom-level feedback impact analysis unit performs bottom-level feedback impact analysis on the water supply network. This allows it to infer whether the impact will intensify and feed back to the bottom level after the bottom-level extended impact occurs, creating a vicious cycle that leads to a decrease in the supply efficiency of the water supply network. The feedback impact analysis improves the comprehensiveness of the inspection platform and further enhances the inspection efficiency.

[0075] During the inspection and maintenance of the target, the continuous decline duration of the support points corresponding to the area of ​​decreased water supply satisfaction in the water supply network and the rate of increase in the number of support points that first appear to decline in the area of ​​decreased water supply satisfaction are obtained and marked as the decline aggravation parameter and decline expansion parameter, respectively.

[0076] The duration during which external parameters remain stable after the current set parameters of the support points within the water supply network are obtained, as well as the deviation between the required external parameter values ​​and the actual satisfied values ​​after the set parameters are reset, and these are marked as supply stability information and supply satisfaction information, respectively.

[0077] If either the parameter for aggravated decline or the parameter for expanded decline exceeds the corresponding set threshold, or if either the information for stable supply or the information for satisfied supply does not exceed the set information threshold, it is inferred that the underlying feedback impact analysis of the water supply network is abnormal. An abnormal feedback impact signal is generated and sent to the water supply equipment inspection platform. After receiving the abnormal feedback impact signal, if the maintenance period is extended during the water supply network inspection and maintenance, the water supply equipment inspection platform needs to reset the scope of maintenance or the hardware maintenance settings to avoid the impact from aggravating and causing the current maintenance to fail to meet the maintenance needs of the water supply network.

[0078] If neither the descent aggravation parameter nor the descent expansion parameter exceeds the corresponding set parameter threshold, and neither the supply stability information nor the supply satisfaction information exceeds the set information threshold, then it is inferred that the underlying feedback impact analysis of the water supply network is normal, a normal feedback impact signal is generated and sent to the water supply equipment inspection platform. After receiving the signal, the water supply equipment inspection platform performs maintenance according to the current inspection and maintenance settings.

[0079] In use, this invention comprises a water supply network construction unit that builds a physical network for the water supply equipment and digitally maps the pipeline network based on data collected from various parts of the physical network, thereby constructing a model of the water supply network; a network hierarchical detection unit that performs hierarchical detection on the water supply network after its construction; a bottom-level extension impact analysis unit that performs impact analysis on the operation changes of branches or fulcrums within the water supply network; and a bottom-level feedback impact analysis unit that performs bottom-level feedback impact analysis on the water supply network.

[0080] Thresholds, preset values, preset ranges, etc. are set for result comparison and analysis to determine whether they are good or bad. The value of these thresholds is determined by a combination of large-scale model analysis of sample data and human experience. They can also be adjusted appropriately based on seasonal or common-sense influences.

[0081] Furthermore, the settings for weighting ratios, influence factors, etc., are based on the magnitude of each parameter's influence on the results. The specific values ​​are allocated to ultimately reflect the impact on the results. The settings for input and storage are also determined by a combination of large-scale model analysis of sample data and human experience. Appropriate adjustments can also be made based on seasonal or rational influence conditions.

[0082] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent inspection system for water supply equipment based on big data analysis, characterized in that, This includes a water supply equipment inspection platform, whose communication connections include: The water supply network construction unit builds a physical network for the water supply equipment and digitally maps the pipeline network based on data collected from various parts of the physical network, thereby constructing a model of the water supply network. The network-level detection unit performs level-by-level detection of the water supply network after its construction. The bottom-level extended impact analysis unit analyzes the impact of operational changes on branches or fulcrums within the water supply network. The bottom-level feedback impact analysis unit performs bottom-level feedback impact analysis on the water supply network.

2. The intelligent inspection system for water supply equipment based on big data analysis according to claim 1, characterized in that, The process of constructing a water supply network unit is as follows: The system collects data on the water supply pipes connected to the water supply equipment in the current area, constructs a pipe network based on the pipe distribution, detects the distribution of the pipe network using GIS mapping technology, compares the actual mapped pipe network with the collected pipe network, determines the water supply network in use in real time, and divides the determined water supply network into branches, fulcrums, and pipe networks.

3. The intelligent inspection system for water supply equipment based on big data analysis according to claim 2, characterized in that, The process of network-level step-by-step detection unit is as follows: The branch's own operating parameters are used as carrying parameters, while external parameters generated during the branch's water supply process are collected. During the water supply phase, the carrying parameters of each branch are recorded, and the parameter deviation is obtained based on the changes in the carrying parameters before and after water supply. A set of parameter deviations for water supply is constructed, and a data floating curve is constructed based on a subset of the parameter deviation set. When external parameters are generated, an external parameter set is constructed, and a data floating curve is constructed based on a subset of the external parameter set.

4. The intelligent inspection system for water supply equipment based on big data analysis according to claim 3, characterized in that, Record the time of numerical fluctuation of the parameter deviation set, and at the same time record the time of fluctuation of the data fluctuation curve of the external parameter set. If the two types of numerical fluctuation times overlap or the interval duration continues to decrease, the current branch is marked as a high-load branch; if the two types of numerical fluctuation times are not adjacent or the interval duration fluctuates back and forth, the current branch is marked as a low-load branch. When the high-load branch is running, the numerical fluctuation range of the external parameter and the numerical fluctuation range of the parameter deviation set are collected at the same time, and the numerical fluctuation range ratio is calculated based on the ratio and marked as the supply influence conversion coefficient. When the low-load branch is running, the numerical fluctuation frequency of the external parameter and the numerical fluctuation frequency of the parameter deviation set are collected at the same time, and the maximum growth range of the numerical fluctuation frequency of the parameter deviation set is obtained when the numerical fluctuation frequency of the external parameter does not increase, and it is marked as the load influence conversion coefficient.

5. The intelligent inspection system for water supply equipment based on big data analysis according to claim 4, characterized in that, The conversion coefficients of supply impact and load impact will be analyzed: If the supply impact conversion coefficient exceeds the supply impact conversion coefficient threshold and the load impact conversion coefficient is lower than the load impact conversion coefficient threshold, it is marked as a multi-load adaptive branch and its location is sent to the water supply equipment inspection platform; if the supply impact conversion coefficient does not exceed the supply impact conversion coefficient threshold, or the load impact conversion coefficient is higher than the load impact conversion coefficient threshold, it is marked as a multi-load unadaptable branch and its location is sent to the water supply equipment inspection platform.

6. The intelligent inspection system for water supply equipment based on big data analysis according to claim 5, characterized in that, Analysis of the fulcrums connected to the multi-load adaptation branches: The multi-load adaptation branches connected by the fulcrum are sorted according to the water supply order. The external parameter set of the multi-load adaptation branches is recorded in real time. The highest floating span of the external parameter set of adjacent water supply multi-load adaptation branches is obtained. The external satisfaction deviation of adjacent branches is calculated based on the difference of the highest floating span of the corresponding multi-load adaptation branches in the same time period. When multiple branches cooperate to supply water, if the external satisfaction deviation corresponding to consecutive adjacent branches is within the set deviation range, it is marked as an efficient allocation fulcrum; if the external satisfaction deviation after the current fulcrum allocates water supply is not within the set deviation range, it indicates that the allocation efficiency of the current fulcrum has decreased, and it is marked as an inefficient allocation fulcrum; a qualified water supply network is constructed by performing step-by-step detection on branches and fulcrums.

7. The intelligent inspection system for water supply equipment based on big data analysis according to claim 6, characterized in that, The process of analyzing the impact of the bottom-level extension unit is as follows: Transforming a multi-load adaptive branch into a multi-load non-adaptive branch is marked as a branch impact transformation; transforming an efficient allocation pivot into an inefficient allocation pivot is marked as a pivot impact transformation. The system obtains the real-time setting parameters of the fulcrum covered by the corresponding water supply trajectory during the branch influence transformation process. Based on the setting time of the real-time setting parameters, the resetting frequency is obtained. The numerical increase rate of the resetting frequency is obtained during the current process and marked as the fulcrum extension influence data. The system obtains the water supply satisfaction of each location in the water supply network during the fulcrum influence transformation process. Based on the decrease in water supply satisfaction, the corresponding water supply network coverage area is obtained. The water supply satisfaction is expressed as the duration during which the water supply volume or water supply speed in the current coverage area of ​​the water supply network meets the set value.

8. The intelligent inspection system for water supply equipment based on big data analysis according to claim 7, characterized in that, If the rate of increase of the reset frequency exceeds the set increase rate threshold, or if the water supply network coverage area where water supply satisfaction decreases exceeds the coverage area threshold, a water supply network extension impact signal is generated and sent to the water supply equipment inspection platform. Based on the collected data, the corresponding branch or support point is designated as the inspection and maintenance object. If the rate of increase of the reset frequency does not exceed the set increase rate threshold, and the water supply network coverage area where water supply satisfaction decreases does not exceed the coverage area threshold, a water supply network extension safety signal is generated and sent to the water supply equipment inspection platform.

9. The intelligent inspection system for water supply equipment based on big data analysis according to claim 8, characterized in that, The process of analyzing the impact of bottom-level feedback on the unit is as follows: During the inspection and maintenance of the target, the continuous decline duration of the support points corresponding to the area of ​​decreased water supply satisfaction in the water supply network and the rate of increase in the number of support points that first appear to decline in the area of ​​decreased water supply satisfaction are obtained and marked as the decline aggravation parameter and decline expansion parameter, respectively. The duration during which external parameters remain stable after the current set parameters of the support points within the water supply network are obtained, as well as the deviation between the required external parameter values ​​and the actual satisfied values ​​after the set parameters are reset, and these are marked as supply stability information and supply satisfaction information, respectively.

10. The intelligent inspection system for water supply equipment based on big data analysis according to claim 9, characterized in that, If either the aggravated drop parameter or the expanded drop parameter exceeds its corresponding set threshold, or if either the stable supply information or the satisfied supply information does not exceed its set threshold, a feedback impact abnormal signal is generated and sent to the water supply equipment inspection platform; if neither the aggravated drop parameter nor the expanded drop parameter exceeds its corresponding set threshold, and both the stable supply information and the satisfied supply information exceed their set thresholds, a feedback impact normal signal is generated.

Images