A Cable Equipment Location System and Method Based on Multi-Source Data Fusion

Abstract

The present invention relates to a cable equipment positioning system and method based on multi-source data fusion, wherein the system includes a reference state mining module, an inconsistent state identification module, a detector matching module, a signal confidence retrieval module and a fault location output module. The reference state mining module is used to obtain the normal operating reference state of the cable in the target area; the inconsistent state identification module is used to identify the abnormal area that deviates from the reference state; the detector matching module is used to select an adaptive detector array according to the characteristics of the abnormal area; the signal confidence retrieval module is used to establish the confidence interval of the detection signal; the fault location output module is used to accurately locate the distribution area of the faulty cable equipment and output the result to the user end. The present application pre-identifies the quasi-fault area through multi-source data fusion and deploys the detector array in a targeted manner, thereby improving the accuracy, timeliness and efficiency of cable equipment fault warning and positioning.

Description

Technical Field

[0001] The present invention relates to the field of equipment fault detection, and particularly to a cable equipment positioning system and method based on multi-source data fusion. Background Art

[0002] Cable equipment is an important part of power and communication systems, and its stable operation plays a crucial role in ensuring energy supply and information transmission. With the acceleration of urbanization and the continuous advancement of underground pipeline network construction, the number of various cable equipment buried is increasing day by day, its spatial distribution is more complex, and the working environment is more changeable. In this case, the fault detection and precise positioning of cable equipment have become key links in the operation and maintenance work.

[0003] At present, the fault positioning of cable equipment mainly adopts the method of post-fault detection, that is, after a fault occurs, the fault point is determined by means of manual inspection, traditional cable fault locators, etc. This method has obvious lag, and the detection work can only be carried out after the fault has occurred and caused certain impacts, often resulting in long-term power outages or communication interruptions, bringing inconvenience to social production and residents' lives. At the same time, traditional positioning methods usually require a comprehensive inspection of the entire cable line, with a large workload, low efficiency, and the positioning accuracy is greatly limited in complex environments. Summary of the Invention

[0004] Aiming at the technical problems of serious lag in fault positioning, low positioning efficiency and insufficient accuracy of cable equipment in the prior art, the present invention provides a cable equipment positioning system and method based on multi-source data fusion to solve.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides a cable equipment positioning system based on multi-source data fusion, including: a reference state mining module, configured to receive the operation control parameters, cable circuit topology, and environmental parameters of the cables in the target area, perform frequent mode mining, and obtain a reference state, wherein the reference state has a topology area identifier; a non-uniform state recognition module, configured to extract the non-uniform state topology area identifier of the reference state and the monitoring state from the topology area identifier, and set it as the distribution area of the quasi-fault cable equipment; a detector matching module, configured to match a detector array according to the type and distribution mode of the quasi-fault cable equipment in the distribution area of the quasi-fault cable equipment, wherein any detector in the detector array has a preset detection parameter label; a signal confidence retrieval module, configured to retrieve the backhaul signal confidence interval that meets the operation control parameters, the preset detection parameter label, and the cable circuit topology for each detector in the detector array; a fault location output module, configured to, when the backhaul signal acquisition value of the detector array does not belong to the backhaul signal confidence interval, extract the detection topology area, set it as the distribution area of the fault cable equipment, and send it to the user terminal.

[0007] Optionally, the reference state mining module includes: a first-level constraint construction unit, configured to construct a first-level mining constraint condition according to the operation control parameters, the cable circuit topology, and the environmental parameters; a first-level sample retrieval unit, configured to retrieve the first-level state record value of the first-level sample cable circuit topology that meets the first-level mining constraint condition, wherein the first-level state record value has a first topology area record identifier, and the first-level sample cable circuit topology has a first-level operation control parameter label and a first-level environmental parameter label; a second-level constraint construction unit, configured to construct a second-level mining constraint condition according to the first-level operation control parameter label, the cable circuit topology, and the first-level environmental parameter label; a second-level sample retrieval unit, configured to retrieve the second-level state record value of the second-level sample cable circuit topology that meets the second-level mining constraint condition, wherein the second-level state record value has a second topology area record identifier; an interval statistics identifier unit, configured to perform same-attribute centralized interval statistics on the first-level state record value and the second-level state record value to obtain the reference state, and configure the topology area identifier for the reference state according to the first topology area record identifier and the second topology area record identifier.

[0008] Optionally, the first-level constraint construction unit includes: a threshold configuration subunit for configuring a first Euclidean distance threshold, a topological similarity threshold, and a second Euclidean distance threshold; a condition satisfaction subunit for, when the first Euclidean distance between the sample operation control parameter and the operation control parameter is less than the first Euclidean distance threshold, and the topological similarity between the sample cable circuit topology and the cable circuit topology is greater than the topological similarity threshold, and the second Euclidean distance between the sample environmental parameter and the environmental parameter is less than the second Euclidean distance threshold, deeming that the first-level mining constraint condition is satisfied; a condition dissatisfaction subunit for otherwise deeming that the first-level mining constraint condition is not satisfied.

[0009] Optionally, the signal confidence retrieval module includes: a retrieval constraint construction unit for constructing a retrieval constraint condition according to the operation control parameter, the preset detection parameter label, and the cable circuit topology; a fault-free sample collection unit for collecting a set of first backhaul signal attribute record values of a cable fault-free sample group that satisfies the retrieval constraint condition until the Nth set of backhaul signal attribute record values; a signal trend analysis unit for traversing the first set of backhaul signal attribute record values until the Nth set of backhaul signal attribute record values for central tendency analysis to obtain a first backhaul signal confidence interval until the Nth backhaul signal confidence interval, and adding them to the backhaul signal confidence interval.

[0010] Optionally, the signal trend analysis unit includes: a characteristic value interval analysis subunit for traversing the first set of backhaul signal attribute record values until the Nth set of backhaul signal attribute record values for central tendency analysis to obtain a first backhaul signal characteristic value interval until the Nth backhaul signal characteristic value interval; a rated interval acquisition subunit for obtaining a first backhaul signal rated interval until the Nth backhaul signal rated interval; a confidence interval construction subunit for comparing the first backhaul signal characteristic value interval and the first backhaul signal rated interval, extracting the maximum value of the interval lower limit and the minimum value of the interval upper limit, and constructing the first backhaul signal confidence interval; a multi-signal interval construction subunit for until constructing the Nth backhaul signal confidence interval.

[0011] Optionally, the fault location output module includes: a signal deviation calculation unit for calculating a backhaul signal deviation vector matrix between the first backhaul signal acquisition value of the first detector of the detector array and the backhaul signal confidence interval; a fault probability discrimination unit for processing the backhaul signal deviation vector matrix through a fault probability discriminator associated with the detector model of the first detector to obtain a fault probability prediction value; a fault determination comparison unit for, when the fault probability prediction value is greater than or equal to the fault probability threshold, deeming that the first backhaul signal acquisition value is inconsistent with the backhaul signal confidence interval.

[0012] Optionally, the fault probability discriminator unit includes: a data set configuration sub-unit for configuring a data set of the return signal deviation vector matrix of the detector model, retrieving the proportion of the number of faults of the detection cable device that satisfies the data set of the return signal deviation vector matrix, and setting it as the fault probability identification data; a discriminator training sub-unit for supervising and training a number of pre-sub discriminators according to the data set of the return signal deviation vector matrix and the fault probability identification data; a fitting training sub-unit for supervising and training an output fitting according to the output results of the number of pre-sub discriminators and the fault probability identification data; a discriminator construction sub-unit for merging the output layer of the number of pre-sub discriminators and the input layer of the output fitting to obtain the fault probability discriminator.

[0013] In a second aspect, the present invention provides a cable device positioning method based on multi-source data fusion, including: receiving the operation control parameters, cable circuit topology, and environmental parameters of the cables in the target area, performing frequent mode mining to obtain a reference state, where the reference state has a topology area identifier; extracting the inconsistent state topology area identifier between the reference state and the monitoring state from the topology area identifier, and setting it as the distribution area of the quasi-fault cable device; matching a detector array according to the type and distribution mode of the quasi-fault cable device in the distribution area of the quasi-fault cable device, where any detector in the detector array has a preset detection parameter label; for each detector in the detector array, retrieving the confidence interval of the return signal that satisfies the operation control parameters, the preset detection parameter label, and the cable circuit topology; when the collected value of the return signal of the detector array does not belong to the confidence interval of the return signal, extracting the detection topology area and sending it to the user side as the distribution area of the fault cable device.

[0014] The beneficial effects of the present invention are:

[0015] The operation control parameters, cable circuit topology, and environmental parameters of the cables in the target area are received by the reference state mining module, and frequent mode mining is performed to obtain the reference state. Among them, the reference state has a topology area identifier, thereby establishing the reference operation modes of cable equipment in different areas, providing a reference basis for subsequent fault warnings. The inconsistent state identification module extracts the inconsistent state topology area identifiers of the reference state and the monitoring state from the topology area identifier, and sets them as the distribution areas of the quasi-fault cable equipment, thereby discovering the areas deviating from the normal operation state, initially determining the locations where potential fault hazards may exist, narrowing the full-line detection range to specific areas, and improving the detection efficiency. The detector matching module matches the detector array according to the types and distribution modes of the quasi-fault cable equipment in the distribution areas of the quasi-fault cable equipment. Any detector in the detector array has a preset detection parameter label, thereby realizing the customized configuration of detection means. The signal confidence retrieval module retrieves the confidence intervals of the feedback signals that meet the operation control parameters, preset detection parameter labels, and cable circuit topology for each detector in the detector array, thereby determining the normal change range of the detection signals according to the actual operation environment and characteristics of the cables, establishing a benchmark for signal evaluation, and providing a basis for the identification of abnormal signals. When the collected value of the feedback signal of the detector array does not belong to the confidence interval of the feedback signal, the fault location output module extracts the detection topology area, sets it as the distribution area of the fault cable equipment, and sends it to the user terminal, thereby accurately identifying the fault location and timely transmitting the fault information to the user for timely handling.

[0016] Through the above technical solutions, the present invention realizes the transformation from passive response to active warning, determines the quasi-fault area using the prior state, and then conducts precise detection for the quasi-fault area, improving the predictability, accuracy, and efficiency of cable equipment fault location, and effectively reducing the losses and impacts caused by faults. Description of the Drawings

[0017] Figure 1 It is a schematic structural diagram of a cable equipment positioning system based on multi-source data fusion provided by the present invention;

[0018] Figure 2 It is a schematic flow diagram of a cable equipment positioning method based on multi-source data fusion provided by the present invention.

[0019] In the drawings, the components represented by each reference numeral are as follows:

[0020] Reference state mining module 11, inconsistent state identification module 12, detector matching module 13, signal confidence retrieval module 14, fault location output module 15. Detailed Embodiments

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0023] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. The following description is provided to enable any person skilled in the art to make and use the present invention. Details are set forth for the purpose of explanation in the following description. It should be understood that those skilled in the art can recognize that the present invention can be implemented without these specific details. In other instances, well-known structures and processes are not described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0024] Embodiment 1, as Figure 1As shown in the figure, an embodiment of the present invention provides a cable equipment positioning system based on multi-source data fusion, including a reference state mining module 11, a non-uniform state recognition module 12, a detector matching module 13, a signal confidence retrieval module 14, and a fault location output module 15. Among them, the reference state mining module 11 is used to receive the operation control parameters, cable circuit topology, and environmental parameters of the cables in the target area, perform frequent mode mining, and obtain the reference state, where the reference state has a topology area identifier; the non-uniform state recognition module 12 is used to extract the non-uniform state topology area identifier of the reference state and the monitoring state from the topology area identifier, and set it as the distribution area of the quasi-fault cable equipment; the detector matching module 13 is used to match the detector array according to the type and distribution mode of the quasi-fault cable equipment in the distribution area of the quasi-fault cable equipment, where any detector in the detector array has a preset detection parameter label; the signal confidence retrieval module 14 is used to retrieve the return signal confidence interval that meets the operation control parameters, preset detection parameter labels, and cable circuit topology for each detector in the detector array; the fault location output module 15 is used to extract the detection topology area when the return signal acquisition value of the detector array does not belong to the return signal confidence interval, and set it as the distribution area of the fault cable equipment and send it to the user terminal.

[0025] Specifically, the reference state mining module 11 is responsible for modeling and mining the normal operation state of the cables in the target area. The reference state mining module 11 receives the operation control parameters, cable circuit topology structure information, and environmental parameters of the cables in the target area. Among them, the operation control parameters include, but are not limited to, electrical operation parameters such as the voltage level, load current, and power factor of the cable; the cable circuit topology characterizes the physical connection relationship, length, type distribution, and other structural features of the cables in the target area; the environmental parameters include external factors such as temperature, humidity, and geological conditions that may affect the operation state of the cables. The reference state mining module 11 extracts the operation characteristic mode of the cables in the target area under normal conditions from a large amount of historical operation data by performing frequent mode mining on these multi-source heterogeneous data, and forms the reference state. It should be noted that the obtained reference state has a topology area identifier, that is, each reference state corresponds to a specific area or section in the cable network, providing a spatial reference basis for subsequent fault location. Through the reference state mining module 11, the system can establish a reference model of the cable equipment under normal operation conditions, laying a foundation for subsequent abnormal state recognition.

[0026] The non - consistent state recognition module is responsible for comparing the current monitoring state of cable equipment with the reference state obtained by the reference state mining module 11, so as to identify the abnormal areas. Specifically, the non - consistent state recognition module 12 extracts the topological areas with significant differences between the reference state and the real - time monitoring state by analyzing the topological area identifiers. When the parameters of the monitoring state are inconsistent with those of the reference state, the topological area identifiers corresponding to these inconsistent states are extracted and set as the distribution areas of quasi - fault cable equipment. Among them, quasi - fault indicates that there is a potential fault risk in this area, but it has not developed into a complete fault state. Through the non - consistent state recognition module 12, the system can identify the areas in the cable network that may have problems before the fault is fully formed, thus providing the target areas for subsequent precise detection and fault prevention, narrowing the detection scope, and improving the efficiency and accuracy of fault location.

[0027] The detector matching module 13 is responsible for selecting the most suitable detection equipment according to the characteristics of quasi - fault cable equipment. This module receives the information about the distribution area of quasi - fault cable equipment determined by the non - consistent state recognition module 12, and analyzes the types and distribution modes of quasi - fault cable equipment in this area. The detector matching module 13 selects and deploys the most suitable detector array according to the characteristics of different types of quasi - fault cable equipment. For example, electromagnetic detectors are matched for metal cable equipment, acoustic positioning detectors are matched for directly buried cable equipment or cable equipment in pipes, and ground penetrating radar is matched for non - metal cable equipment. This targeted detector selection mechanism significantly improves the accuracy of fault location. Each detector in the detector array has a preset detection parameter label, which contains key information such as the technical parameters, applicable conditions, and sensitivity range of the detector, providing a necessary reference basis for subsequent signal processing and analysis. Through the detector matching module 13, the most suitable detection method can be selected according to the characteristics of different cable types, thus improving the pertinence and effectiveness of fault location.

[0028] The signal confidence retrieval module 14 is responsible for individually processing each detector in the detector array and establishing a standard reference interval for the return signal of each detector. Specifically, the signal confidence retrieval module 14 first establishes the constraint conditions for signal retrieval based on the operating control parameters of the current cable system, the preset detection parameter tags of the detectors, and the cable circuit topology structure information. Then, based on these constraint conditions, the module retrieves the historical data that matches the current situation and extracts the normal return signal characteristics of the detectors under specific combinations of conditions. Through statistical analysis and trend research on these historical return signal data, the signal confidence retrieval module 14 establishes a return signal confidence interval for each detector. These confidence intervals represent the reasonable variation range of the detector return signals under normal operating conditions and provide a reference standard for subsequent abnormal signal judgment. Through the signal confidence retrieval module 14, the system can accurately identify abnormal fluctuations in the detection signals, thereby improving the accuracy and reliability of fault judgment and laying a data foundation for the final fault location.

[0029] The fault location output module 15 is responsible for determining and outputting the accurate location information of the faulty cable equipment. This module realizes precise fault location by analyzing the actual signal data obtained from the detector array and comparing it with the return signal confidence interval established by the signal confidence retrieval module 14. Specifically, when the return signal value collected by the detectors in the detector array falls outside the preset return signal confidence interval, the fault location output module 15 will determine that there is an abnormality in the topological area corresponding to the detector. Subsequently, the module accurately extracts the topological area information corresponding to these abnormal detection signals and determines it as the distribution area of the faulty cable equipment. After the fault location output module 15 completes the fault area, it sends the location result to the user terminal through the system interface so that maintenance personnel can timely obtain the fault information and take corresponding maintenance measures. This real-time fault information transmission mechanism significantly improves the timeliness of cable system fault handling.

[0030] Through the collaborative work of the reference state mining module 11, the non-uniform state recognition module 12, the detector matching module 13, the signal confidence retrieval module 14, and the fault location output module 15, the pre-positioning of cable faults is realized. Different from traditional post-detection methods, the prior state is used to determine the quasi-fault area, and then an appropriate detector is selectively and precisely detected. For example, an electromagnetic detector is used for metal cables, an acoustic positioning detector is used for directly buried or in-pipe cables, and a ground penetrating radar is used for non-metal cables. Then, through the signal confidence interval and the fault discrimination mechanism, the precise analysis and abnormal judgment of the backhaul signal are realized. When the acquired value of the backhaul signal of the detector array does not belong to the preset backhaul signal confidence interval, the corresponding detection topology area can be accurately extracted and determined as the distribution area of the faulty cable equipment, thereby improving the pre-positioning, accuracy, and efficiency of fault location, reducing the false alarm rate and missed alarm rate, and providing support for the preventive maintenance and rapid fault handling of the power system.

[0031] Further, the reference state mining module 11 includes a first-level constraint construction unit, a first-level sample retrieval unit, a second-level constraint construction unit, a second-level sample retrieval unit, and an interval statistics identification unit. Among them, the first-level constraint construction unit is used to construct first-level mining constraint conditions according to the operation control parameters, cable circuit topology, and environmental parameters; the first-level sample retrieval unit is used to retrieve the first-level state record values of the first-level sample cable circuit topologies that meet the first-level mining constraint conditions. Among them, the first-level state record values have the first topology area record identifier, and the first-level sample cable circuit topologies have the first-level operation control parameter label and the first-level environmental parameter label; the second-level constraint construction unit is used to construct second-level mining constraint conditions according to the first-level operation control parameter label, cable circuit topology, and first-level environmental parameter label; the second-level sample retrieval unit is used to retrieve the second-level state record values of the second-level sample cable circuit topologies that meet the second-level mining constraint conditions. Among them, the second-level state record values have the second topology area record identifier; the interval statistics identification unit is used to perform the same-attribute centralized interval statistics on the first-level state record values and the second-level state record values to obtain the reference state, and configure the topology area identifier for the reference state according to the first topology area record identifier and the second topology area record identifier.

[0032] In a preferred embodiment, the reference state mining module 11 includes a first-level constraint construction unit, a first-level sample retrieval unit, a second-level constraint construction unit, a second-level sample retrieval unit, and an interval statistics identification unit, so as to adopt a multi-level constraint construction and sample retrieval strategy to improve the accuracy and comprehensiveness of reference state mining.

[0033] The primary constraint construction unit is responsible for constructing preliminary excavation constraints, i.e., primary excavation constraints, based on the current operation control parameters, cable circuit topology, and environmental parameters. The primary excavation constraints define the basic condition framework for the system to search for similar cases in historical data and provide a screening basis for subsequent sample retrieval. Then, based on the primary constraints, the primary sample retrieval unit retrieves cable circuit samples that meet the primary excavation constraints from the historical database and extracts the status record values of these samples, i.e., primary status record values. Each primary status record value is associated with a specific topological region and is marked by the first topological region record identifier. In addition, the retrieved primary sample cable circuit topology is also attached with primary operation control parameter tags and primary environmental parameter tags, which provide a reference basis for secondary constraint construction.

[0034] The secondary constraint construction unit then constructs secondary excavation constraints using the primary operation control parameter tags, the current cable circuit topology, and the primary environmental parameter tags extracted from the primary samples. This hierarchical constraint construction method enables the system to perform sample retrieval under the secondary excavation constraints. Although the samples retrieved through the secondary excavation constraints have a relatively low direct similarity to the current state, they are similar to the primary samples and thus still have important reference value, which can effectively expand the sample pool available for benchmark state modeling. Subsequently, the secondary sample retrieval unit retrieves cable circuit samples based on the secondary excavation constraints and extracts the status record values of these samples as secondary status record values. Each secondary status record value also has a topological region identifier, i.e., the second topological region record identifier, which is used to mark the specific topological location corresponding to this status value.

[0035] After that, the interval statistical identification unit performs centralized interval statistical analysis of the status record values (primary status record values and secondary status record values) obtained from the two levels, extracts the parameter intervals that can represent the normal operation state, and forms the final benchmark state. At the same time, based on the first topological region record identifier and the second topological region record identifier, this unit configures the corresponding benchmark state configuration topological region identifier for each benchmark state and establishes the correspondence between the benchmark state and the cable network topological location.

[0036] Through the method of multi-level constraints and hierarchical retrieval, the benchmark state mining module 11 can effectively extract a parameter model from a large amount of historical data that can accurately represent the normal operation state of cable equipment, laying a data foundation for subsequent non-uniform state identification.

[0037] Further, the first-level constraint construction unit includes a threshold configuration subunit, a condition satisfaction subunit, and a condition dissatisfaction subunit. Among them, the threshold configuration subunit is used to configure the first Euclidean distance threshold, the topological similarity threshold, and the second Euclidean distance threshold; the condition satisfaction subunit is used to consider that the first-level mining constraint conditions are satisfied when the first Euclidean distance between the sample operation control parameters and the operation control parameters is less than the first Euclidean distance threshold, and the topological similarity between the sample cable circuit topology and the cable circuit topology is greater than the topological similarity threshold, and the second Euclidean distance between the sample environmental parameters and the environmental parameters is less than the second Euclidean distance threshold; the condition dissatisfaction subunit is used to consider otherwise that the first-level mining constraint conditions are not satisfied.

[0038] In a preferred embodiment, the first-level constraint construction unit includes a threshold configuration subunit, a condition satisfaction subunit, and a condition dissatisfaction subunit, which are used to complete the accurate evaluation of the similarity between historical samples and the current state.

[0039] The threshold configuration subunit is responsible for setting the key threshold parameters for judging whether the sample meets the constraint conditions, namely the first Euclidean distance threshold, the topological similarity threshold, and the second Euclidean distance threshold. Among them, the first Euclidean distance threshold is used to measure the similarity degree of the operation control parameters, the topological similarity threshold is used to measure the similarity degree of the cable circuit topological structure, and the second Euclidean distance threshold is used to measure the similarity degree of the environmental parameters.

[0040] The condition satisfaction subunit is used to implement the specific judgment logic of the first-level constraint conditions, that is, when and only when the following three conditions are simultaneously met, it is determined that the sample meets the first-level mining constraint conditions: First, the Euclidean distance between the sample operation control parameters and the current operation control parameters is less than the preset first Euclidean distance threshold, indicating that the two are close enough in electrical parameters; Second, the topological similarity between the sample cable circuit topology and the current cable circuit topology is greater than the preset topological similarity threshold, indicating that the two have sufficient similarity in physical structure; Third, the Euclidean distance between the sample environmental parameters and the current environmental parameters is less than the preset second Euclidean distance threshold, indicating that the two are close enough in external environmental conditions. The condition dissatisfaction subunit processes the situation where the sample does not meet the first-level mining constraint conditions, that is, when any one of the above three conditions is not met, the condition dissatisfaction subunit determines that the sample does not meet the first-level mining constraint conditions and is thus excluded from the scope of the first-level sample retrieval.

[0041] Through the constraint construction based on multi-dimensional similarity calculation, the first-level constraint construction unit can accurately identify historical samples highly similar to the current state, ensuring the accuracy and reliability of the first-level sample retrieval and laying a foundation for the accurate mining of the benchmark state.

[0042] Further, the signal confidence retrieval module includes a retrieval constraint construction unit, a fault-free sample acquisition unit, and a signal trend analysis unit. Among them, the retrieval constraint construction unit is used to construct retrieval constraint conditions according to the operation control parameters, preset detection parameter tags, and cable circuit topology; the fault-free sample acquisition unit is used to collect the first set of backhaul signal attribute record values of the cable fault-free sample group that meets the retrieval constraint conditions until the Nth set of backhaul signal attribute record values; the signal trend analysis unit is used to traverse the first set of backhaul signal attribute record values until the Nth set of backhaul signal attribute record values for central tendency analysis, obtain the first backhaul signal confidence interval until the Nth backhaul signal confidence interval, and add them to the backhaul signal confidence interval.

[0043] In a feasible implementation manner, the signal confidence retrieval module 14 includes a retrieval constraint construction unit, a fault-free sample acquisition unit, and a signal trend analysis unit, which jointly complete the establishment of the backhaul signal confidence interval, thereby ensuring the accuracy of the detection signal discrimination.

[0044] The retrieval constraint construction unit first comprehensively constructs retrieval constraint conditions according to the current operation control parameters, preset detection parameter tags of the detector, and cable circuit topology information. The retrieval constraint conditions define the screening criteria for finding similar fault-free cases in the historical data, ensuring that the retrieved samples have characteristics matching the current situation, thereby guaranteeing the applicability and effectiveness of the subsequently established signal confidence interval. The fault-free sample acquisition unit filters out the cable fault-free sample group that meets the conditions from the historical database based on the above retrieval constraint conditions. For these samples, the fault-free sample acquisition unit extracts their multi-dimensional backhaul signal attribute record values, forming a complete data set from the first set of backhaul signal attribute record values until the Nth set of backhaul signal attribute record values. Among them, N represents the number of backhaul signal attributes that the detector can collect, and different types of detectors may have different numbers of signal attributes. Subsequently, the signal trend analysis unit systematically traverses and analyzes the collected multi-dimensional signal attribute record value set. The signal trend analysis unit extracts the confidence interval that can characterize the change law of the signal attribute under normal conditions by performing central tendency analysis on the historical record values of each dimension of the signal attribute. Thus, a complete interval set from the first backhaul signal confidence interval until the Nth backhaul signal confidence interval is formed, and these intervals are added to the backhaul signal confidence interval.

[0045] By extracting the signal characteristics based on historical fault-free samples, the signal confidence retrieval module 14 establishes a backhaul signal judgment standard for each detector, enabling the system to accurately identify abnormal patterns in the detection signals and providing data support for the final fault location.

[0046] Furthermore, the signal trend analysis unit includes an eigenvalue interval analysis subunit, a rated interval acquisition subunit, a confidence interval construction subunit, and a multi-signal interval construction subunit. Among them, the eigenvalue interval analysis subunit is used to traverse the first set of backhaul signal attribute record values until the Nth set of backhaul signal attribute record values for central tendency analysis, obtaining the first backhaul signal eigenvalue interval until the Nth backhaul signal eigenvalue interval; the rated interval acquisition subunit is used to obtain the first backhaul signal rated interval until the Nth backhaul signal rated interval; the confidence interval construction subunit is used to compare the first backhaul signal eigenvalue interval and the first backhaul signal rated interval, extract the maximum value of the interval lower limit and the minimum value of the interval upper limit, and construct the first backhaul signal confidence interval; the multi-signal interval construction subunit is used to construct the Nth backhaul signal confidence interval until it is completed.

[0047] Specifically, the signal trend analysis unit includes an eigenvalue interval analysis subunit, a rated interval acquisition subunit, a confidence interval construction subunit, and a multi-signal interval construction subunit, which jointly complete the conversion process from sample data to confidence intervals to achieve accurate signal trend analysis.

[0048] The eigenvalue interval analysis subunit first systematically traverses the collected set of multi-dimensional backhaul signal attribute record values. For each dimension of signal attribute, the eigenvalue interval analysis subunit performs central tendency analysis on the historical record values and extracts the interval range that can characterize the signal change characteristics under normal conditions. Through a data-driven analysis method, a complete feature description from the first backhaul signal eigenvalue interval to the Nth backhaul signal eigenvalue interval is obtained. The rated interval acquisition subunit is responsible for extracting the rated working intervals of each dimension of backhaul signals, that is, the normal change range of signals specified according to equipment specifications, technical standards, or design parameters. The rated interval acquisition subunit obtains a complete set of rated intervals from the first backhaul signal rated interval to the Nth backhaul signal rated interval, providing a theoretical reference basis for subsequent confidence interval construction.

[0049] The confidence interval construction subunit constructs the first backhaul signal confidence interval that conforms to both the historical data statistical characteristics and the theoretical rated requirements by comparing the eigenvalue interval with the rated interval, extracting the maximum value of the interval lower limit and the minimum value of the interval upper limit. This double-insurance interval construction can improve the reliability and accuracy of the confidence interval. The multi-signal interval construction subunit is responsible for applying the above confidence interval construction process to the backhaul signals of all dimensions in sequence, from the first dimension to the Nth dimension, and finally completing the construction of the confidence intervals for all backhaul signals.

[0050] Through signal trend analysis that combines statistical characteristics with theoretical specifications, the signal trend analysis unit can establish a rigorous judgment standard for each dimension of backhaul signals, improving the accuracy and reliability of the system in identifying abnormal signals in complex environments.

[0051] Furthermore, the fault location output module includes a signal deviation calculation unit, a fault probability discrimination unit, and a fault determination comparison unit. Among them, the signal deviation calculation unit is used to calculate the signal return deviation vector matrix of the first signal return value collected by the first detector in the detector array and the signal return confidence interval; the fault probability discrimination unit is used to process the signal return deviation vector matrix through a fault probability discriminator associated with the detector model of the first detector to obtain a fault probability prediction value; the fault determination comparison unit is used to consider that the first signal return value collected is inconsistent with the signal return confidence interval when the fault probability prediction value is greater than or equal to the fault probability threshold.

[0052] In a preferred embodiment, the fault location output module 15 includes a signal deviation calculation unit, a fault probability discrimination unit, and a fault determination comparison unit, which jointly complete the whole process from signal anomaly detection to fault determination, realizing accurate fault determination and location output.

[0053] First, the signal deviation calculation unit processes each detector in the detector array. Taking the first detector as an example, this unit calculates the deviation degree between the first signal return value collected by the first detector and the pre-established signal return confidence interval. By quantifying this deviation relationship, a signal return deviation vector matrix is generated, which comprehensively characterizes the difference characteristics between the actual signal and the normal range, providing a data basis for subsequent fault probability assessment. The fault probability discrimination unit then processes the signal return deviation vector matrix in combination with the detector model characteristics. Specifically, the fault probability discrimination unit calls a fault probability discriminator specifically associated with the detector model of the first detector to deeply analyze the signal deviation characteristics and output a fault probability prediction value. This dedicated discrimination mechanism based on detector characteristics improves the accuracy and adaptability of fault recognition. Subsequently, the fault determination comparison unit performs the final fault determination by comparing the fault probability prediction value with a preset fault probability threshold. When the fault probability prediction value is greater than or equal to the fault probability threshold, it is determined that there is a substantial inconsistency between the first signal return value collected and the signal return confidence interval, that is, it is considered that there may be a fault in the topological area corresponding to the detector.

[0054] Through the fault determination based on probability assessment, the fault location output module 15 can effectively filter out the random noise in the signal fluctuation, improve the robustness and reliability of fault judgment, and provide an accurate basis for the final fault area location.

[0055] Furthermore, the failure probability discrimination unit includes a dataset configuration subunit, a discriminator training subunit, a fitting training subunit, and a discriminator construction subunit. Among them, the dataset configuration subunit is used to configure the dataset of the return signal deviation vector matrix of the detector model, retrieve the proportion of the number of failures of the detection cable device that meets the dataset of the return signal deviation vector matrix, and set it as the failure probability identification data; the discriminator training subunit is used to supervise and train several pre-sub discriminators according to the dataset of the return signal deviation vector matrix and the failure probability identification data; the fitting training subunit is used to supervise and train the output fitting according to the output results of several pre-sub discriminators and the failure probability identification data; the discriminator construction subunit is used to merge the output layer of several pre-sub discriminators and the input layer of the output fitting to obtain the failure probability discriminator.

[0056] In a preferred embodiment, the failure probability discrimination unit specifically includes a dataset configuration subunit, a discriminator training subunit, a fitting training subunit, and a discriminator construction subunit, so as to adopt the integrated method of machine learning to construct the failure probability discriminator, thereby improving the accuracy and reliability of the failure probability discrimination.

[0057] The dataset configuration subunit is responsible for establishing the data basis for model training. The dataset configuration subunit configures the historical return signal deviation vector matrix of a specific detector model as the training dataset. At the same time, by retrieving the historical failure records of the cable devices associated with these matrices, the proportion of the number of failures is calculated as the failure probability identification data. These identification data provide the mapping relationship between the signal deviation characteristics and the actual failure probability, providing a reference for subsequent supervised learning. Then, the discriminator training subunit trains multiple pre-sub discriminators based on the above-mentioned dataset of the return signal deviation vector matrix by using the supervised learning method. These pre-sub discriminators adopt different model structures or parameter configurations, and can capture the abnormal characteristics in the return signal deviation vector matrix from different angles or levels, providing multi-dimensional decision-making basis for the final failure probability judgment.

[0058] The fitting training subunit then uses the multi-channel output results of the pre-sub discriminators as new feature vectors, and combines the original failure probability identification data to train a dedicated output fitting. This fitting can effectively integrate the judgment results of multiple sub-discriminators, eliminate the deviation of a single model, and further improve the accuracy of the failure probability prediction. Then, the discriminator construction subunit structurally merges the output layer of several pre-sub discriminators and the input layer of the output fitting to form an end-to-end failure probability discriminator. This integrated learning architecture effectively combines the advantages of multiple models, improving the system's recognition ability and anti-interference ability for various failure modes.

[0059] Through the fault probability discrimination mechanism based on the machine learning integration method, a dedicated discrimination model can be established for detectors of different models to achieve accurate identification of complex cable fault modes, providing a highly reliable judgment basis for the fault location output module.

[0060] Embodiment 2, as Figure 2 shown, based on the same inventive concept as the cable equipment positioning system based on multi-source data fusion provided in Embodiment 1, the embodiment of the present invention further provides a cable equipment positioning method based on multi-source data fusion, including:

[0061] Receiving the operation control parameters, cable circuit topology and environmental parameters of the cables in the target area, performing frequent mode mining to obtain a reference state, where the reference state has a topology area identifier;

[0062] Extracting the inconsistent state topology area identifiers of the reference state and the monitoring state from the topology area identifier, and setting it as the distribution area of the quasi-fault cable equipment;

[0063] According to the type and distribution mode of the quasi-fault cable equipment in the distribution area of the quasi-fault cable equipment, matching the detector array, where any detector in the detector array has a preset detection parameter label;

[0064] For each detector in the detector array, retrieving the confidence interval of the feedback signal that satisfies the operation control parameters, preset detection parameter label and cable circuit topology;

[0065] When the acquisition value of the feedback signal of the detector array does not belong to the confidence interval of the feedback signal, extracting the detection topology area and sending it to the user side as the distribution area of the fault cable equipment.

[0066] Further, receiving the operation control parameters, cable circuit topology and environmental parameters of the cables in the target area, and performing frequent mode mining to obtain a reference state, including:

[0067] Constructing a first-level mining constraint condition according to the operation control parameters, cable circuit topology and environmental parameters;

[0068] Retrieving the first-level state record value of the first-level sample cable circuit topology that satisfies the first-level mining constraint condition, where the first-level state record value has a first topology area record identifier, and the first-level sample cable circuit topology has a first-level operation control parameter label and a first-level environmental parameter label;

[0069] Constructing a second-level mining constraint condition according to the first-level operation control parameter label, cable circuit topology and first-level environmental parameter label;

[0070] Retrieving the second-level state record value of the second-level sample cable circuit topology that satisfies the second-level mining constraint condition, where the second-level state record value has a second topology area record identifier;

[0071] Perform interval statistics for the first-level status record values and the second-level status record values with the same attributes to obtain the reference status, and configure the topology region identifier for the reference status according to the first topology region record identifier and the second topology region record identifier.

[0072] Furthermore, according to the operation control parameters, the cable circuit topology, and the environmental parameters, construct the first-level mining constraint conditions, including:

[0073] Configure the first Euclidean distance threshold, the topology similarity threshold, and the second Euclidean distance threshold;

[0074] When the first Euclidean distance between the sample operation control parameters and the operation control parameters is less than the first Euclidean distance threshold, the topology similarity between the sample cable circuit topology and the cable circuit topology is greater than the topology similarity threshold, and the second Euclidean distance between the sample environmental parameters and the environmental parameters is less than the second Euclidean distance threshold, it is considered to meet the first-level mining constraint conditions;

[0075] Otherwise, it is considered not to meet the first-level mining constraint conditions.

[0076] Furthermore, for each detector in the detector array, retrieve the confidence interval of the feedback signal that meets the operation control parameters, the preset detection parameter tags, and the cable circuit topology, including:

[0077] Construct the retrieval constraint conditions according to the operation control parameters, the preset detection parameter tags, and the cable circuit topology;

[0078] Collect the first set of feedback signal attribute record values of the cable fault-free sample group that meets the retrieval constraint conditions until the Nth set of feedback signal attribute record values;

[0079] Traverse the first set of feedback signal attribute record values until the Nth set of feedback signal attribute record values for central tendency analysis to obtain the first feedback signal confidence interval until the Nth feedback signal confidence interval, and add them to the feedback signal confidence interval. It also includes:

[0080] Traverse the first set of feedback signal attribute record values until the Nth set of feedback signal attribute record values for central tendency analysis to obtain the first feedback signal eigenvalue interval until the Nth feedback signal eigenvalue interval;

[0081] Obtain the first feedback signal rated interval until the Nth feedback signal rated interval;

[0082] Compare the first feedback signal eigenvalue interval and the first feedback signal rated interval, extract the maximum value of the interval lower limit and the minimum value of the interval upper limit, and construct the first feedback signal confidence interval;

[0083] Until the Nth feedback signal confidence interval is constructed.

[0084] Further, when the acquired value of the feedback signal of the detector array does not belong to the feedback signal confidence interval, it includes:

[0085] Calculate the feedback signal deviation vector matrix between the first acquired value of the feedback signal of the first detector in the detector array and the feedback signal confidence interval;

[0086] Process the feedback signal deviation vector matrix through a failure probability discriminator associated with the detector model of the first detector to obtain a failure probability prediction value;

[0087] When the failure probability prediction value is greater than or equal to the failure probability threshold, it is regarded that the first acquired value of the feedback signal is inconsistent with the feedback signal confidence interval.

[0088] Further, processing the feedback signal deviation vector matrix through a failure probability discriminator associated with the detector model of the first detector to obtain a failure probability prediction value includes:

[0089] Configure the feedback signal deviation vector matrix data set of the detector model, retrieve the proportion of the number of failures of the detection cable device that meets the feedback signal deviation vector matrix data set, and set it as the failure probability identification data;

[0090] Supervise and train a number of pre-sub discriminators according to the feedback signal deviation vector matrix data set and the failure probability identification data;

[0091] Supervise and train an output fitting device according to the output results of a number of pre-sub discriminators and the failure probability identification data;

[0092] Merge the output layer of a number of pre-sub discriminators and the input layer of the output fitting device to obtain a failure probability discriminator.

[0093] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0094] Those skilled in the art should understand that the embodiments of the present invention can be provided as a system or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] The present invention is described with reference to the flowcharts and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general purpose computers, special purpose computers, embedded computers or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more blocks.

[0096] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more blocks.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more blocks.

[0098] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic inventive concept.

[0099] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A cable equipment positioning system based on multi-source data fusion, characterized in that, Including: A reference state mining module, which is used to receive the operation control parameters, cable circuit topology and environmental parameters of the cables in the target area, perform frequent mode mining to obtain a reference state, where the reference state has a topology area identifier; A non-uniform state identification module, which is used to extract the non-uniform state topology area identifier between the reference state and the monitoring state from the topology area identifier, and set it as the distribution area of the quasi-fault cable equipment; A detector matching module, which is used to match a detector array according to the type and distribution mode of the quasi-fault cable equipment in the distribution area of the quasi-fault cable equipment, where any detector in the detector array has a preset detection parameter label; A signal confidence retrieval module, which is used to retrieve the backhaul signal confidence interval that meets the operation control parameters, the preset detection parameter label and the cable circuit topology for each detector in the detector array; A fault location output module, which is used to extract the detection topology area when the backhaul signal acquisition value of the detector array does not belong to the backhaul signal confidence interval, and set it as the distribution area of the fault cable equipment and send it to the user terminal; Wherein, the signal confidence retrieval module includes: A retrieval constraint construction unit, which is used to construct retrieval constraint conditions according to the operation control parameters, the preset detection parameter label and the cable circuit topology; A fault-free sample acquisition unit, which is used to acquire the first backhaul signal attribute record value set to the Nth backhaul signal attribute record value set of the cable fault-free sample group that meets the retrieval constraint conditions; A signal trend analysis unit, which is used to traverse the first backhaul signal attribute record value set to the Nth backhaul signal attribute record value set for centralized trend analysis, obtain the first backhaul signal confidence interval to the Nth backhaul signal confidence interval, and add them to the backhaul signal confidence interval; Wherein, the signal trend analysis unit includes: An eigenvalue interval analysis subunit, which is used to traverse the first backhaul signal attribute record value set to the Nth backhaul signal attribute record value set for centralized trend analysis, and obtain the first backhaul signal eigenvalue interval to the Nth backhaul signal eigenvalue interval; A rated interval acquisition subunit, which is used to obtain the first backhaul signal rated interval to the Nth backhaul signal rated interval; A confidence interval construction subunit, which is used to compare the first backhaul signal eigenvalue interval and the first backhaul signal rated interval, extract the maximum value of the interval lower limit and the minimum value of the interval upper limit, and construct the first backhaul signal confidence interval; A multi-signal interval construction subunit, which is used to construct the Nth backhaul signal confidence interval until; 2. The system according to claim 1, wherein The reference state mining module includes: A first-level constraint construction unit, which is used to construct first-level mining constraint conditions according to the operation control parameters, the cable circuit topology and the environmental parameters; A first-level sample retrieval unit, which is used to retrieve the first-level state record values of the first-level sample cable circuit topology that meet the first-level mining constraint conditions, where the first-level state record values have a first topology area record identifier, and the first-level sample cable circuit topology has a first-level operation control parameter label and a first-level environmental parameter label; The secondary constraint construction unit is used to construct secondary mining constraint conditions according to the primary operation control parameter label, the cable circuit topology, and the primary environment parameter label; The secondary sample retrieval unit is used to retrieve the secondary state record values of the secondary sample cable circuit topology that meet the secondary mining constraint conditions, where the secondary state record values have second topology region record identifiers; The interval statistical identification unit is used to perform the same-attribute centralized interval statistics on the primary state record values and the secondary state record values to obtain the reference state, and configure the topology region identifier for the reference state according to the first topology region record identifier and the second topology region record identifier.

3. The system according to claim 2, wherein The primary constraint construction unit includes: The threshold configuration sub-unit is used to configure the first Euclidean distance threshold, the topology similarity threshold, and the second Euclidean distance threshold; The condition satisfaction sub-unit is used to consider that the primary mining constraint conditions are met when the first Euclidean distance between the sample operation control parameter and the operation control parameter is less than the first Euclidean distance threshold, the topology similarity between the sample cable circuit topology and the cable circuit topology is greater than the topology similarity threshold, and the second Euclidean distance between the sample environment parameter and the environment parameter is less than the second Euclidean distance threshold; The condition non-satisfaction sub-unit is used to otherwise, consider that the primary mining constraint conditions are not met.

4. The system according to claim 1, wherein The fault location output module includes: The signal deviation calculation unit is used to calculate the signal deviation vector matrix of the first backhaul signal acquisition value of the first detector of the detector array and the backhaul signal confidence interval; The fault probability discrimination unit is used to process the signal deviation vector matrix through a fault probability discriminator associated with the detector model of the first detector to obtain a fault probability prediction value; The fault determination comparison unit is used to consider that the first backhaul signal acquisition value is inconsistent with the backhaul signal confidence interval when the fault probability prediction value is greater than or equal to the fault probability threshold.

5. The system according to claim 4, wherein The fault probability discrimination unit includes: The data set configuration sub-unit is used to configure the data set of the signal deviation vector matrix of the detector model, retrieve the proportion of the number of faults of the detected cable equipment that meets the data set of the signal deviation vector matrix, and set it as the fault probability identification data; The discriminator training sub-unit is used to supervise and train a number of pre-sub discriminators according to the data set of the signal deviation vector matrix and the fault probability identification data; The fitting training sub-unit is used to supervise and train the output fitting according to the output results of the number of pre-sub discriminators and the fault probability identification data; The discriminator construction sub-unit is used to merge the output layer of the number of pre-sub discriminators and the input layer of the output fitting to obtain the fault probability discriminator.

6. A cable device positioning method based on multi-source data fusion, characterized in that, Applied to the system according to any one of claims 1 to 5, including: Receiving the operation control parameter, the cable circuit topology, and the environment parameter of the target area cable, performing frequent mode mining to obtain a reference state, where the reference state has a topology region identifier; Extract the inconsistent state topology region identifier of the reference state and the monitoring state from the topology region identifier, and set it as the distribution region of the quasi-fault cable equipment; Match the detector array according to the type and distribution mode of the quasi-fault cable equipment in the distribution region of the quasi-fault cable equipment, wherein any detector of the detector array has a preset detection parameter label; For each detector of the detector array, retrieve the confidence interval of the feedback signal that satisfies the operation control parameter, the preset detection parameter label, and the cable circuit topology; When the collected value of the feedback signal of the detector array does not belong to the confidence interval of the feedback signal, extract the detection topology region, set it as the distribution region of the fault cable equipment, and send it to the user terminal.

Images