Underwater intelligent pipe network fault detection method and system based on sensor breakpoint detection

Abstract

The invention discloses an underwater intelligent pipe network fault detection method and system based on sensor breakpoint detection, and belongs to the technical field of fault detection, and the method comprises the steps: determining a fault sensor and a corresponding epitaxial sensor, and the radiation detection range of the epitaxial sensor comprises the center detection range of the fault sensor; determining non-transmitted data of the fault sensor at the current moment according to the historical transmission data of the fault sensor and the transmission data of the epitaxial sensor at the current moment; the fault type of the underwater intelligent pipe network is determined according to the untransmitted data and the fault association rule, and the fault association rule is determined according to the historical transmission data of the multiple sensors and the historical fault condition of the underwater intelligent pipe network. And the fault association rule is determined based on the historical fault condition, the accurate fault type of the pipe network is obtained through the fault association model, and the accuracy of fault detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and more specifically to an underwater intelligent pipe network fault detection method and system based on sensor breakpoint detection. Background Art

[0002] Underwater pipelines are widely used in many fields such as urban water supply, drainage, industrial water transportation, oil transportation, gas transportation, etc., and their safe and stable operation is crucial. However, due to the complex underwater environment, underwater pipelines face multiple failure risks, which makes the development of underwater pipeline fault detection technology an inevitable demand.

[0003] For example, a Chinese patent application with publication number CN114353886A discloses a method and system for detecting fault points in urban drainage pipe networks. The method calculates the difference between the flow mean curve in the period to be detected and the historical flow mean curve in the corresponding period, and determines the fault area and the fault point location based on the obtained flow error curve.

[0004] However, this method relies on the representativeness of historical flow data. If the operating conditions, water usage patterns or transport medium characteristics of the underwater pipeline network suddenly change, the historical data cannot accurately reflect the current situation. Therefore, the existing technology has shortcomings. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an underwater intelligent pipeline network fault detection method and system based on sensor breakpoint detection, which determines the pipeline network fault type through the transmission data of the extension sensor and the fault association rules, so as to solve the problem that historical data cannot accurately reflect the current situation in the event of a sudden fault, and thus cannot determine the fault type.

[0006] To achieve the above object, the present invention provides the following technical solutions: The present invention provides an underwater smart pipe network fault detection method based on sensor breakpoint detection, wherein a plurality of sensors are arranged in the underwater smart pipe network, each of the sensors corresponds to a central detection range and a radiation detection range, and the underwater smart pipe network fault detection method comprises: Determine a faulty sensor and its corresponding extension sensor, wherein the faulty sensor is a sensor whose data transmission is interrupted at the current moment, and the radiation detection range of the extension sensor includes the central detection range of the faulty sensor; Determine the non-transmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment; The fault type of the underwater smart pipe network is determined according to the non-transmitted data and the fault association rule, wherein the fault association rule is determined according to the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network.

[0007] As a further improvement of the present invention, determining the non-transmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment includes: Obtaining first prediction data and second prediction data according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment respectively; Determine the fault type of the fault sensor according to the historical transmission data of the fault sensor and the transmission data of the extension sensor at the current moment, wherein the fault type of the fault sensor includes a sudden fault and a gradual fault; The non-transmitted data is obtained according to the first prediction data, the second prediction data and the fault type.

[0008] As a further improvement of the present invention, obtaining the first prediction data and the second prediction data according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment respectively includes: Obtaining the first prediction data according to the historical transmission data of the faulty sensor and a time series model; The second prediction data is obtained according to the transmission data of the epitaxial sensor at the current moment and an interpolation algorithm.

[0009] As a further improvement of the present invention, the second prediction data is obtained according to the transmission data of the epitaxial sensor at the current moment and the interpolation algorithm, including: Determining a triangulated network structure according to the position of the epitaxial sensor; Determine the triangle to which the faulty sensor belongs according to the position of the faulty sensor and the triangulated network structure; Determine a plurality of sub-triangles according to the position of the fault sensor and the triangle; The second prediction data is obtained according to the areas of the multiple sub-triangles and the transmission data of the epitaxial sensor at the current moment.

[0010] As a further improvement of the present invention, the fault association rule is determined according to the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network, including: Obtaining a transaction data set according to the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network; determining preliminary association rules based on the item sets; The fault association rule is obtained according to the preset evaluation index and the preliminary association rule.

[0011] As a further improvement of the present invention, a transaction data set is obtained according to the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network, including: Determining factors affecting the operation status of the underwater smart pipe network based on the historical transmission data of the multiple sensors; determining a dynamic threshold value based on the factors and historical transmission data of the plurality of sensors; Performing dynamic discretization processing on the historical transmission data of the multiple sensors according to the dynamic threshold to obtain discretized data; According to the historical fault conditions of the underwater intelligent pipe network, the discretized data is organized into the transaction data set.

[0012] As a further improvement of the present invention, the determining of the preliminary association rule based on the transaction data set includes: Based on each item set in the transaction data set, gradually generate multiple candidate item sets; Calculating the support of the multiple candidate item sets, and determining multiple frequent item sets according to the support; A preliminary association rule is determined according to the frequent item sets.

[0013] As a further improvement of the present invention, the step of gradually generating multiple candidate item sets based on each item set in the transaction data set includes: Performing transaction compression processing based on each item set in the transaction data set to obtain multiple compressed transactions; The plurality of candidate item sets are gradually generated based on the plurality of compression transactions.

[0014] As a further improvement of the present invention, the preset evaluation indicators include confidence, improvement and certainty.

[0015] The present invention provides an underwater smart pipe network fault detection system based on sensor breakpoint detection, wherein a plurality of sensors are arranged in the underwater smart pipe network, each of the sensors corresponds to a central detection range and a radiation detection range, and the underwater smart pipe network fault detection system comprises: Positioning module: determining a faulty sensor and its corresponding extension sensor, wherein the faulty sensor is a sensor whose data transmission is interrupted at the current moment, and the radiation detection range of the extension sensor includes the central detection range of the faulty sensor; A calculation module: determining the non-transmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment; Detection module: determine fault association rules based on the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network, and determine the fault type of the underwater smart pipe network based on the non-transmitted data and the fault association rules.

[0016] When a breakpoint occurs in the sensor, the present invention effectively restores the non-transmitted data of the faulty sensor at the current moment based on the historical transmission data of the faulty sensor and the current transmission data of the extension sensor, thereby improving data quality, and accurately locates the fault type in combination with the fault association rules, thereby improving detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The figure is a flow chart of the method steps of the present invention.

[0018] Figure 2 Schematic diagram of the central detection range and the radiation detection range.

[0019] Figure 3 This is a schematic diagram of the triangulated network structure.

[0020] Figure 4 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations of the technical solution of the present invention.

[0022] The term "and / or" in the following text is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0023] like Figure 1 As shown, the embodiment of the present application provides a method for detecting faults in an underwater smart pipe network based on sensor breakpoint detection, comprising: Determine a faulty sensor and its corresponding extension sensor, the faulty sensor being a sensor whose data transmission is interrupted at the current moment; Determine the untransmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment; The fault type of the underwater smart pipe network is determined based on the non-transmitted data and the fault association rules. The fault association rules are determined based on the historical transmission data of multiple sensors and the historical fault conditions of the underwater smart pipe network.

[0024] Among them, the sensor whose data transmission is interrupted at the current moment can also be called a sensor with a breakpoint; each sensor transmits the detected data to the server for subsequent data analysis; the types of sensors include: pressure sensors, flow sensors, water quality sensors, etc.; the fault types of underwater smart pipelines include leakage faults, blockage faults, corrosion faults, etc.

[0025] And if Figure 2 As shown, multiple sensors are installed in the underwater smart pipe network, and each sensor corresponds to a central detection range and a radiation detection range. The central detection range refers to the core area where the sensor can obtain specific parameter information of the pipe network with high accuracy. For example, the central detection range of the pressure sensor is usually within 0.5 meters around the sensor installation point. The radiation detection range refers to a relatively large area extending from the sensor to the periphery, including the central detection range. This area enables the sensor to conduct more extensive monitoring and preliminary judgment of the pipe network parameters. For example, the radiation detection range of the pressure sensor can reach an area with a radius of 1 meter centered on the installation point. Figure 2 The solid circle in the middle represents the central detection range, and the dotted circle represents the radiation detection range. The central detection range of each sensor can be included in the radiation detection range of multiple sensors of the same type, so these multiple sensors are called the corresponding extended sensors of the sensor, such as the extended sensors of sensor A are sensor B, sensor C, sensor D, sensor E and sensor F. When there is no faulty sensor, the data transmitted by each sensor at each moment is used as the detection data within the corresponding central detection range.

[0026] In this embodiment, when a breakpoint occurs in the sensor, the historical transmission data of the faulty sensor and the current transmission data of the extended sensor are used to effectively restore the non-transmitted data of the faulty sensor at the current moment, thereby improving data quality, and accurately locating the fault type in combination with the fault association rules to improve detection efficiency.

[0027] Furthermore, this embodiment provides a step of determining the non-transmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment, including: Obtaining first prediction data and second prediction data according to historical transmission data of the faulty sensor and current transmission data of the extension sensor respectively; Determine the fault type of the faulty sensor according to the historical transmission data of the faulty sensor and the transmission data of the external sensor at the current moment, the fault type of the faulty sensor including sudden fault and gradual fault; The untransmitted data is obtained according to the first prediction data, the second prediction data and the fault type.

[0028] For example, if the performance of the pipeline area monitored by the faulty sensor gradually changes due to long-term corrosion, the historical transmission data of the faulty sensor will show a trend of gradually changing over time. In this case, the fault type is a progressive fault; if the historical transmission data of the faulty sensor does not show a trend of changing over time, and the historical transmission data are all within the normal range, but the current transmission data of the extension sensor has undergone a sudden change compared to the transmission data at the previous moment, then the fault type is a sudden fault, such as an underwater pipeline network suddenly ruptures due to external construction, resulting in a breakpoint in the pressure sensor; if the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment do not belong to the above situation, it is necessary to consider the cause of the breakpoint from the perspective of the sensor itself, such as hardware damage and power failure. This embodiment only considers sensor breakpoints caused by pipeline failures.

[0029] Furthermore, this embodiment provides a step of obtaining first prediction data and second prediction data according to historical transmission data of the faulty sensor and current transmission data of the extension sensor, respectively, including: Obtaining first prediction data according to historical transmission data of the faulty sensor and a time series model; The second prediction data is obtained according to the transmission data of the epitaxial sensor at the current moment and the interpolation algorithm.

[0030] Specifically, after obtaining the first prediction data and the second prediction data, different weights can be assigned to the first prediction data according to the fault type, that is, in the case of a sudden fault, a larger weight is assigned to the second prediction data, and in the case of a gradual fault, a larger weight is assigned to the first prediction data. Finally, the non-transmitted data is obtained by weighted fusion. Preferably, since the historical transmission data of the faulty sensor has a much smaller impact on the current non-transmitted data than the transmission data of the external sensor at the current moment, the weight corresponding to the second prediction data should be greater than 0.8 in this case.

[0031] Based on the first prediction data and the second prediction data, this embodiment can restore relatively accurate non-transmitted data under different fault types as a basis for subsequent analysis.

[0032] Furthermore, in addition to the above-mentioned weighted fusion method, a step of determining the untransmitted data of the faulty sensor at the current moment based on a hierarchical fusion method can also be used. The principle of hierarchical fusion is to first use one method for preliminary estimation, and then use the result as the input of another method for further optimization. Exemplarily, in the case of a progressive fault, the second prediction data and the historical transmission data of the faulty sensor can be input into the time series model together, and the result output by the time series model is used as the untransmitted data. This method inputs the second prediction data into the time series model as a feature, enhances the adaptability of the time series model to complex situations, and obtains a more accurate output result.

[0033] Furthermore, this embodiment provides a step of obtaining second prediction data according to the transmission data of the epitaxial sensor at the current moment and the interpolation algorithm, including: Determine the triangulated network structure according to the location of the epitaxial sensor; According to the position of the faulty sensor and the triangulated network structure, determine the triangle to which the faulty sensor belongs; Determine a plurality of sub-triangles according to the position of the fault sensor and the triangle; The second prediction data is obtained according to the areas of the multiple sub-triangles and the transmission data of the extension sensor at the current moment.

[0034] For example, Figure 3 As shown, the epitaxial sensors of sensor A are sensor B, sensor C, sensor D, sensor D and sensor F. First, for each epitaxial sensor, it is connected with the adjacent sensor corresponding to the epitaxial sensor to form a triangular network structure, where the corresponding adjacent sensor is defined as other epitaxial sensors with overlapping radiation detection ranges with the epitaxial sensor. Then, the triangle containing the faulty sensor is determined. When there are multiple triangles containing the faulty sensor, as shown in FIG. Figure 3 The triangle containing the faulty sensor A is and , calculate the overlapping area of ​​the area formed by the three extension sensors in the two triangles and the central detection range of sensor A respectively, and take the triangle corresponding to the larger area as the triangle to which the faulty sensor belongs. If the two calculated areas are the same, such as Figure 3 The areas formed by the three extension sensors in the two triangles can completely include the central detection range of sensor A, then one triangle is randomly selected from the two triangles as the triangle to which the faulty sensor belongs. In this embodiment, . Then connect sensor A with The three vertices of are connected to obtain three sub-triangles , and , and calculate , , and The area of ​​each sub-triangle is The second prediction data is determined by the area ratio of , the specific formula is: ; in, , , and Respectively , , and The area of , , They respectively represent the transmission data of the epitaxial sensors B, D and E at the current moment.

[0035] This embodiment considers the overall characteristics of the triangle area through the area of ​​the triangle, which can better reflect the spatial distribution of data and is more suitable for irregularly distributed sensors. For example, in the local area of ​​the underwater pipe network, the sensors are unevenly distributed due to the complexity of the underwater pipe network. The area ratio interpolation can reasonably distribute the impact of each vertex sensor data on the faulty sensor data according to the division of the triangle. In addition, if the extension sensor at the vertex of the triangle has an abnormal value due to the external environment or hardware aging, the calculation method based on the area ratio provided by this embodiment can alleviate the impact of the abnormal value and increase the accuracy of the calculation result compared to the traditional method of calculating based on distance to determine the weight.

[0036] For example, For example, if sensor E has an abnormal value due to electromagnetic interference, if the weight is determined based on distance, since sensor E is closest to the faulty sensor A, the abnormal value will be assigned a larger weight, and the accuracy of the second prediction data will be greatly affected. However, if the method provided in this embodiment is adopted, The area of ​​​​the outlier is the smallest, so the outlier will be assigned a smaller weight, thereby alleviating the impact of the outlier.

[0037] Furthermore, this embodiment provides a step of determining a fault association rule based on historical transmission data of multiple sensors and historical fault conditions of the underwater smart pipe network, including: According to the historical transmission data of multiple sensors and the historical fault conditions of the underwater smart pipe network, a transaction data set is obtained; Determine preliminary association rules based on item sets; According to the preset evaluation indicators and preliminary association rules, the fault association rules are obtained.

[0038] Furthermore, this embodiment provides a step of obtaining a transaction data set according to historical transmission data of multiple sensors and historical fault conditions of the underwater smart pipe network, including: Determine the factors that affect the operation status of the underwater smart pipe network based on the historical transmission data of multiple sensors; Determine dynamic thresholds based on factors and historical transmission data from multiple sensors; Performing dynamic discretization processing on historical transmission data of multiple sensors according to a dynamic threshold to obtain discretized data; According to the historical fault conditions of the underwater smart pipeline network, the discretized data are organized into transaction data sets.

[0039] Among them, the factors affecting the operating status of the underwater pipeline network may be seasons or operating conditions. For example, in spring and summer, the residents' domestic water consumption will increase significantly, which makes the underwater pipeline network face greater water supply pressure and the flow demand will also increase. Therefore, in spring and summer, the thresholds of the pressure sensor and the flow sensor should be higher than those in autumn and winter; similarly, under high-load operating conditions, the thresholds of the pressure sensor and the flow sensor should be higher than those under low-load operating conditions.

[0040] Exemplarily, this embodiment provides a method for determining a dynamic threshold when season is used as an influencing factor. Assume that the multiple sensors include multiple pressure sensors and multiple flow sensors. First, for multiple pressure sensors, their historical transmission data are classified according to season to obtain four subsets of pressure data. Then, the mean and standard deviation of each subset are calculated. Assume that the mean of one of the subsets is , the standard deviation is ,Will and As the threshold corresponding to this season, and are coefficients determined empirically, e.g. Repeat this step for the other three subsets to get different thresholds corresponding to each season. Repeat the above steps for multiple flow sensors to get different thresholds corresponding to the flow sensor in each season.

[0041] The method provided in this embodiment can dynamically adjust the appropriate threshold value to discretize the data according to different seasons or working conditions, so that the discretized sensor data can more accurately reflect the actual operating status of the current underwater pipeline network, providing a more effective data basis for subsequent association rule mining.

[0042] Furthermore, this embodiment provides a step of determining a preliminary association rule based on a transaction data set, including: Based on each item set in the transaction data set, multiple candidate item sets are gradually generated; Calculate the support of multiple candidate item sets, and determine multiple frequent item sets based on the support; Determine preliminary association rules based on frequent item sets.

[0043] Furthermore, this embodiment provides a step of gradually generating multiple candidate item sets based on each item set in the transaction data set, including: Perform transaction compression processing based on each item set in the transaction data set to obtain multiple compressed transactions; Based on multiple compression transactions, multiple candidate item sets are gradually generated.

[0044] For example, when it is necessary to detect faults in an underwater pipe network within a preset range, it is first necessary to establish fault association rules within the preset range. Assume that the preset range includes 3 pressure sensors and 3 flow sensors and this example assumes that the influencing factor is season. First, obtain the historical transmission data and influencing factors of the 6 sensors and discretize them based on the influencing factors. Specifically, for the pressure sensor, obtain the threshold value corresponding to the season according to the season corresponding to the current moment, and divide the data of the 3 pressure sensors into multiple intervals based on the threshold value. For example, divide the data less than The data is divided into the "low" interval, and the data greater than or equal to and less than The data is divided into the "normal" interval, which is greater than or equal to The data of the flow sensor can be divided into the "high" interval. Similarly, for the flow sensor, the data of the three flow sensors can be divided into the "low flow", "normal flow" and "high flow" intervals.

[0045] Then the discretized data is sorted to obtain a transaction data set, which includes multiple transactions. Each transaction includes the status of all sensors at a moment and information on whether a fault occurs. For example, one of the transactions is [pressure sensor 1=high, pressure sensor 2=normal, pressure sensor 3=low, flow sensor 1=normal flow, flow sensor 2=normal flow, flow sensor 3=low flow, pipe network fault=leakage fault], where each transaction includes multiple single item sets, such as [pressure sensor 1=high], [pressure sensor 2=low], [flow sensor 1=normal flow], etc. are all single item sets.

[0046] Then, transaction compression processing is performed based on each single item set. Specifically, the support of each single item set is first calculated. The support refers to the ratio of the number of transactions of the single item set to the total number of transactions in the transaction data set. The higher the support, the higher the frequency of the single item set. Then, the support of each single item set is compared with the preset support, and the single item set with a support greater than the preset support is taken as the preferred single item set. Then, transaction compression processing is performed on the transaction data set according to the preferred single item set, that is, only transactions including at least one preferred single item set are retained in the transaction data set, and these transactions are called compressed transactions.

[0047] Then, each preferred single item set is connected in pairs to obtain multiple candidate 2-item sets. For example, if the preferred single item set is [pressure sensor 1 = high], [pressure sensor 2 = low], [pipeline network failure = leakage failure], the three candidate 2-item sets obtained are [pressure sensor 1 = high, pressure sensor 2 = low], [pressure sensor 1 = high, pipe network failure = leakage failure], and [pressure sensor 2 = low, pipe network failure = leakage failure]. Then, the support of each candidate 2-item set is calculated according to the compression transaction, and the 2-item set with a support greater than the preset support is called the preferred 2-item set. Then, the above steps are repeated for the preferred 2-item set to obtain multiple candidate 3-item sets, and the support of each candidate 3-item set is judged. If the support of each 3-item set is less than the preset support, that is, there is no preferred 3-item set, then the preferred 2-item set is used as a frequent item set. If there is a preferred 3-item set, the above steps are repeated for the preferred 3-item set until no item set with a support greater than the preset support is generated, and multiple frequent item sets are obtained.

[0048] Finally, the frequent item sets are screened, and the frequent item sets containing single item sets related to pipeline network faults are taken as preliminary association rules. The preliminary association rules are further evaluated according to the preset evaluation indicators to obtain the fault association rules.

[0049] Among them, the preset evaluation indicators include confidence, lift and certainty. When the confidence, lift and certainty of the preliminary association rule are greater than the preset values, the preliminary association rule is used as the fault association rule. Confidence is used to measure the probability of the conclusion occurring when the premise condition occurs; lift measures the ratio of the probability of the conclusion occurring when the premise condition occurs to the probability of the conclusion occurring as a whole; certainty is used to measure the difference between the possibility of the conclusion not occurring when the premise condition occurs and the possibility of the conclusion not occurring as a whole.

[0050] For example, assuming that one of the preliminary association rules is [pressure sensor 1 = high, pressure sensor 3 = low, flow sensor 3 = low flow, pipe network failure = leakage failure], [pressure sensor 1 = high, pressure sensor 3 = low, flow sensor 3 = low flow] is recorded as Y, and [pipe network failure = leakage failure] is recorded as Z. The confidence of the preliminary association rule is ,in represents the support of the preliminary association rule, express Support; promotion ,in express degree of support; degree of confidence .

[0051] The method provided in this embodiment generates fault association rules based on the rules between historical transmission data and historical fault conditions of the pipeline network, reduces the amount of data processing through transaction compression steps, accelerates rule generation, and ultimately improves the quality of rules through multiple evaluation indicators, thereby accurately obtaining the fault type of the underwater pipeline network.

[0052] Furthermore, the present embodiment provides a method for determining the fault type of an underwater smart pipe network based on non-transmitted data and fault association rules. First, the central detection range of the sensor corresponding to the non-transmitted data is determined, the fault association rules corresponding to the range are obtained, and the current moment transmission data of other sensors involved in the fault association rules are obtained. The non-transmitted data and the current moment transmission data of other sensors are discretized, and finally, according to the rules corresponding to the discretization results, the fault of the underwater smart pipe network within the detection range is obtained.

[0053] Further, such as Figure 4 As shown, the embodiment of the present application provides an underwater intelligent pipe network fault detection system based on sensor breakpoint detection, comprising: Positioning module: determine the faulty sensor and its corresponding external sensor. The faulty sensor is the sensor whose data transmission is interrupted at the current moment. The radiation detection range of the external sensor includes the central detection range of the faulty sensor. Calculation module: determining the untransmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the external sensor at the current moment; Detection module: Determine the fault association rules based on the historical transmission data of multiple sensors and the historical fault conditions of the underwater smart pipe network, and determine the fault type of the underwater smart pipe network based on the non-transmitted data and the fault association rules.

[0054] Among them, the positioning module, calculation module and detection module are all located in the server. The server receives the data transmitted by the collection device and performs further analysis. The collection device includes different types of sensors.

[0055] The underwater smart pipe network fault detection method and system based on sensor breakpoint detection provided in the embodiments of the present application can accurately restore the non-transmitted data of the faulty sensor through the current transmission data of the extended sensor and the historical transmission data of the faulty sensor, and accurately identify the fault type of the underwater smart pipe network based on the non-transmitted data and fault association rules.

[0056] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0057] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0059] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for underwater intelligent pipe network fault detection based on sensor breakpoint detection, characterized in that: The underwater smart pipe network is provided with a plurality of sensors, each of which corresponds to a central detection range and a radiation detection range. The underwater smart pipe network fault detection method includes: Determine a faulty sensor and its corresponding extension sensor, wherein the faulty sensor is a sensor whose data transmission is interrupted at a current moment, and a radiation detection range of the extension sensor includes a central detection range of the faulty sensor; Determine the non-transmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment; The fault type of the underwater smart pipe network is determined according to the non-transmitted data and the fault association rule, wherein the fault association rule is determined according to the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network.

2. According to claim 1, a method for underwater intelligent pipe network fault detection based on sensor breakpoint detection is characterized in that: Determining the non-transmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment includes: Obtaining first prediction data and second prediction data according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment respectively; Determine the fault type of the fault sensor according to the historical transmission data of the fault sensor and the transmission data of the extension sensor at the current moment, wherein the fault type of the fault sensor includes a sudden fault and a gradual fault; The non-transmitted data is obtained according to the first prediction data, the second prediction data and the fault type of the faulty sensor.

3. The underwater intelligent pipe network fault detection method based on sensor breakpoint detection according to claim 2 is characterized in that: The obtaining of the first prediction data and the second prediction data according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment respectively comprises: Obtaining the first prediction data according to the historical transmission data of the faulty sensor and a time series model; The second prediction data is obtained according to the transmission data of the epitaxial sensor at the current moment and an interpolation algorithm.

4. The underwater intelligent pipe network fault detection method based on sensor breakpoint detection according to claim 3 is characterized in that: The second prediction data is obtained according to the transmission data of the epitaxial sensor at the current moment and the interpolation algorithm, including: Determining a triangulated network structure according to the position of the epitaxial sensor; Determine the triangle to which the faulty sensor belongs according to the position of the faulty sensor and the triangulated network structure; Determine a plurality of sub-triangles according to the position of the fault sensor and the triangle; The second prediction data is obtained according to the areas of the multiple sub-triangles and the transmission data of the epitaxial sensor at the current moment.

5. The underwater intelligent pipe network fault detection method based on sensor breakpoint detection according to claim 1 is characterized in that: The fault association rule is determined according to the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network, including: Obtaining a transaction data set according to the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network; determining preliminary association rules based on the transaction data set; The fault association rule is obtained according to the preset evaluation index and the preliminary association rule.

6. The underwater intelligent pipe network fault detection method based on sensor breakpoint detection according to claim 5 is characterized in that: According to the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network, a transaction data set is obtained, including: Determining factors affecting the operation status of the underwater smart pipe network based on the historical transmission data of the multiple sensors; determining a dynamic threshold value based on the factors and historical transmission data of the plurality of sensors; Performing dynamic discretization processing on the historical transmission data of the multiple sensors according to the dynamic threshold to obtain discretized data; According to the historical fault conditions of the underwater intelligent pipe network, the discretized data is organized into the transaction data set.

7. The underwater intelligent pipe network fault detection method based on sensor breakpoint detection according to claim 5 is characterized in that: The determining of a preliminary association rule based on the transaction data set includes: Based on each item set in the transaction data set, gradually generate multiple candidate item sets; Calculating the support of the multiple candidate item sets, and determining multiple frequent item sets according to the support; A preliminary association rule is determined according to the frequent item sets.

8. The underwater intelligent pipe network fault detection method based on sensor breakpoint detection according to claim 7 is characterized in that: The step of gradually generating multiple candidate item sets based on each item set in the transaction data set includes: Performing transaction compression processing based on each item set in the transaction data set to obtain multiple compressed transactions; The plurality of candidate item sets are gradually generated based on the plurality of compression transactions.

9. The underwater intelligent pipe network fault detection method based on sensor breakpoint detection according to claim 5 is characterized in that: The preset evaluation indicators include confidence, lift and certainty.

10. An underwater intelligent pipe network fault detection system based on sensor breakpoint detection, characterized in that: The underwater smart pipe network is provided with a plurality of sensors, each of which corresponds to a central detection range and a radiation detection range. The underwater smart pipe network fault detection system includes: Positioning module: determining a faulty sensor and its corresponding extension sensor, wherein the faulty sensor is a sensor whose data transmission is interrupted at the current moment, and the radiation detection range of the extension sensor includes the central detection range of the faulty sensor; A calculation module: determining the non-transmitted data of the faulty sensor at the current moment according to the historical transmission data of the faulty sensor and the transmission data of the extension sensor at the current moment; Detection module: determine fault association rules based on the historical transmission data of the multiple sensors and the historical fault conditions of the underwater smart pipe network, and determine the fault type of the underwater smart pipe network based on the non-transmitted data and the fault association rules.

Images