Intelligent fault diagnosis method and system for LED lighting equipment

Abstract

The invention relates to the technical field of lighting equipment, and provides an intelligent fault diagnosis method and system for LED lighting equipment, for each LED street lamp, extracting multi-dimensional data information of the LED street lamp in a first preset time period from a multi-dimensional state matrix, and determining whether the LED street lamp has a potential fault based on the multi-dimensional data information. If the potential fault exists, generating a pre-selected fault set of the LED street lamp based on the multi-dimensional data information; for each pre-selected fault in the pre-selected fault set, performing extension calendar analysis on the pre-selected fault based on extension structure information of the LED street lamp network to obtain fault influence node information corresponding to the pre-selected fault, and based on the state information of each fault influence node in the fault influence node information in a second preset time period, judging whether the pre-selected fault exists, and if so, determining that the pre-selected fault is a target fault corresponding to the LED street lamp. The method improves the accuracy of fault detection.

Description

Technical Field

[0001] This application relates to the field of lighting equipment technology, and in particular to an intelligent fault diagnosis method and system for LED lighting equipment. Background Technology

[0002] LED street light networks not only provide basic lighting but also integrate various smart city applications such as environmental monitoring, traffic management, and security monitoring, becoming an important node in the smart city's neural network. As the scale of LED street light networks continues to expand and their functions become increasingly complex, higher technical requirements are being placed on their real-time monitoring and fault diagnosis.

[0003] Existing LED street light fault diagnosis technologies mainly rely on the operating parameters of individual street light devices to determine faults. This diagnostic method is prone to misdiagnosis. Summary of the Invention

[0004] The main objective of this application is to provide an intelligent fault diagnosis method and system for LED lighting equipment, aiming to improve the accuracy of fault diagnosis results for LED lighting equipment.

[0005] In a first aspect, this application provides an intelligent fault diagnosis method for LED lighting equipment, the method comprising the following steps: Real-time acquisition of multi-source data information of each LED street light in the LED street light network, and storage of the multi-source data information into a preset multi-dimensional state matrix; For each of the LED streetlights, multidimensional data information of the LED streetlights within a first preset time period is extracted from the multidimensional state matrix, and the potential faults of the LED streetlights are determined based on the multidimensional data information. If potential faults exist, a pre-selected fault set of the LED streetlights is generated based on the multidimensional data information; wherein, the end time of the first preset time period is the current time. For each pre-selected fault in the pre-selected fault set, a topology epoch analysis is performed on the pre-selected fault based on the topology structure information of the LED street light network to obtain the fault-affected node information corresponding to the pre-selected fault. Based on the status information of each fault-affected node in the fault-affected node information within a second preset time period, it is determined whether the pre-selected fault exists. If it exists, the pre-selected fault is determined to be the target fault corresponding to the LED street light. The start time of the second preset time period is the current time.

[0006] In one possible implementation, determining whether the LED street light has a potential fault based on the multidimensional data information includes: For each detection parameter, single-parameter threshold detection and trend anomaly detection are performed on the detection parameter value sequence corresponding to the detection parameter in the multidimensional data information to obtain the single-parameter threshold detection result and trend anomaly detection result corresponding to the detection parameter; The potential faults of the LED streetlights are determined based on the single-parameter threshold detection results and trend anomaly detection results corresponding to each detection parameter.

[0007] In one possible implementation, determining whether the LED street light has a potential fault based on the single-parameter threshold detection results and trend anomaly detection results corresponding to each detection parameter includes: When the sequence of detection parameter values ​​corresponding to each detection parameter is within its corresponding threshold range, and the sequence of detection parameter values ​​corresponding to each detection parameter does not show an abnormal trend, it is determined that the LED street light does not have a potential fault. When any detection parameter value sequence corresponding to any detection parameter contains a detection parameter that is outside its corresponding threshold range, or when any detection parameter value sequence corresponding to any detection parameter shows an abnormal trend, it is determined that the LED street light has a potential fault.

[0008] In one possible implementation, generating the pre-selected fault set of the LED street light based on the multi-dimensional data information includes: For each detection parameter, single-parameter threshold detection and trend anomaly detection are performed on the sequence of detection parameter values ​​corresponding to the detection parameter in the multidimensional data information to obtain the anomaly information corresponding to the detection parameter; For each preset fault in the fault rule base corresponding to the LED street light, it is determined whether there is a preset abnormal parameter state corresponding to the preset fault in each abnormal information. If there is, the preset fault is determined to be a pre-selected fault; each pre-selected fault constitutes the pre-selected fault set.

[0009] In one possible implementation, the topology information includes electrical topology and network topology. The topology information based on the LED street light network is used to perform topology epoch analysis on the pre-selected faults to obtain fault-affected node information corresponding to the pre-selected faults, including: Based on the electrical topology structure, determine the electrical association node information corresponding to the LED street light; Based on the network topology, the network associated node information corresponding to the LED street light is determined; the electrical associated node information and the network associated node information constitute the fault-affected node information.

[0010] In one possible implementation, determining whether the pre-selected fault exists based on the status information of each fault-affected node in the fault-affected node information within a second preset time period includes: Based on electrical topology theory and the electrical associated node information, an electrical topology impact analysis is performed on the pre-selected fault to obtain the electrical predicted state information of each electrical associated node in the electrical associated node information within a second preset time period. Based on network topology theory and the network associated node information, a network topology impact analysis is performed on the preset fault to obtain the network predicted state information of each network associated node in the network associated node information within a second preset time period. For each electrical associated node in the electrical associated node information, after the second preset time period, the electrical status information of the electrical associated node within the second preset time period is obtained, and it is determined whether the electrical predicted status information corresponding to the electrical associated node matches the electrical status information. For each network-associated node in the network-associated node information, after the second preset time period, the network status information of the network-associated node within the second preset time period is obtained, and it is determined whether the network predicted status information corresponding to the network-associated node matches the network status information. If the electrical predicted status information and electrical status information of each electrical associated node match, and the network predicted status information and network status information of each network associated node match, it is determined that the pre-selected fault exists within the second preset time period.

[0011] Secondly, this application also provides an intelligent fault diagnosis system for LED lighting equipment, the intelligent fault diagnosis system for LED lighting equipment comprising: The acquisition module is used to acquire multi-source data information of each LED street light in the LED street light network in real time, and store the multi-source data information into a preset multi-dimensional state matrix; The judgment module is used to extract multi-dimensional data information of each LED street light within a first preset time period from the multi-dimensional state matrix, and to determine whether there is a potential fault in the LED street light based on the multi-dimensional data information. If there is a potential fault, a pre-selected fault set of the LED street light is generated based on the multi-dimensional data information; wherein, the end time of the first preset time period is the current time. The analysis module is used to perform topological epoch analysis on each pre-selected fault in the pre-selected fault set based on the topological structure information of the LED street light network, to obtain the fault-affected node information corresponding to the pre-selected fault, and to determine whether the pre-selected fault exists based on the status information of each fault-affected node in the fault-affected node information within a second preset time period. If it exists, the pre-selected fault is determined to be the target fault corresponding to the LED street light; wherein, the start time of the second preset time period is the current time.

[0012] This application provides an intelligent fault diagnosis method and system for LED lighting equipment. The method includes real-time acquisition of multi-source data information of each LED street light in an LED street light network, and storing the multi-source data information in a preset multi-dimensional state matrix; for each LED street light, extracting multi-dimensional data information of the LED street light within a first preset time period from the multi-dimensional state matrix, and determining whether the LED street light has a potential fault based on the multi-dimensional data information; if a potential fault exists, generating a pre-selected fault set for the LED street light based on the multi-dimensional data information; wherein, the end time of the first preset time period is the current time; for each pre-selected fault in the pre-selected fault set, performing topological epoch analysis on the pre-selected fault based on the topological structure information of the LED street light network to obtain fault-affected node information corresponding to the pre-selected fault, and determining whether the pre-selected fault exists based on the state information of each fault-affected node in the fault-affected node information within a second preset time period; if it exists, determining the pre-selected fault as the target fault corresponding to the LED street light; wherein, the start time of the second preset time period is the current time. This method, on the one hand, achieves comprehensive monitoring and structured data management of the operation status of a large-scale street light network by acquiring multi-source data information of each LED street light in the LED street light network in real time and storing it in a multi-dimensional state matrix. This provides a complete data foundation for subsequent fault analysis and overcomes the problems of single data source and incomplete information in traditional methods. On the other hand, it improves the comprehensiveness of fault identification by generating a pre-selected fault set based on multi-dimensional data information. Furthermore, it improves the shortcomings of traditional fault diagnosis methods by performing topology traversal analysis based on LED street light network topology information and verifying pre-selected faults using the state information of fault-affected nodes. This achieves the transformation from single-point fault judgment to network-based fault verification, improves the reliability of fault diagnosis, reduces the false alarm rate, and provides maintenance personnel with more accurate fault location information. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 A flowchart illustrating an intelligent fault diagnosis method for an LED lighting device provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an intelligent fault diagnosis system for LED lighting equipment provided in one embodiment of this application. Detailed Implementation

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0017] This application provides an intelligent fault diagnosis method and system for LED lighting equipment.

[0018] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0019] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an intelligent fault diagnosis method for LED lighting equipment provided in an embodiment of this application. This intelligent fault diagnosis method for LED lighting equipment can be used in a server, which can be a standalone server, a server cluster, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms.

[0020] like Figure 1 As shown, the intelligent fault diagnosis method for the LED lighting device includes steps S100 to S300.

[0021] Step S100: Acquire multi-source data information of each LED street light in the LED street light network in real time, and store the multi-source data information into a preset multi-dimensional state matrix.

[0022] The multi-source data information includes voltage, current, temperature, illuminance, and power factor. The multi-dimensional state matrix refers to a multi-dimensional data structure that uses LED street light identification as the row index and LED street light detection parameters (including voltage, current, temperature, illuminance, and power factor) as the column index, including the time dimension.

[0023] Specifically, multi-sensor fusion modules are deployed on each LED street light to collect multi-source data in real time. These modules integrate voltage, current, temperature, illuminance, and power factor detection units. For each LED street light, the multi-sensor fusion module collects the detection parameter values ​​corresponding to each detection parameter in real time and stores these values ​​in a sequence corresponding to the detection parameter values ​​in the multi-dimensional state matrix. This sequence is arranged sequentially based on the acquisition time of each detection parameter value. For each LED street light, each detection parameter corresponds to a unique sequence of detection parameter values ​​in the multi-dimensional state matrix.

[0024] Step S200: For each LED street light, extract the multi-dimensional data information of the LED street light within a first preset time period from the multi-dimensional state matrix, and determine whether there is a potential fault in the LED street light based on the multi-dimensional data information. If there is a potential fault, generate a pre-selected fault set for the LED street light based on the multi-dimensional data information; wherein, the end time of the first preset time period is the current time.

[0025] Specifically, for each of the LED streetlights, firstly, multi-dimensional data information of the LED streetlight within a first preset time period is extracted from the multi-dimensional state matrix. Specifically, the multi-dimensional data information corresponding to the first preset time period is traced back from the current time as the endpoint. Fault judgment adopts a multi-level detection strategy, including single-parameter threshold detection, trend anomaly detection, and multi-parameter correlation detection. For each detection parameter (including voltage, current, temperature, illuminance, and power factor), single-parameter threshold detection and trend anomaly detection are performed on the detection parameter value sequence corresponding to the detection parameter in the multi-dimensional data information to obtain the single-parameter threshold detection result and trend anomaly detection result corresponding to the detection parameter. Based on the single-parameter threshold detection result and trend anomaly detection result corresponding to each detection parameter, it is determined whether the LED streetlight has a potential fault. If a potential fault exists, the pre-selected fault set is generated based on the fault rule base corresponding to the LED streetlight and the single-parameter threshold detection result and trend anomaly detection result corresponding to each detection parameter. This step improves the comprehensiveness of fault detection, helps to effectively identify potential faults, and lays the foundation for accurate fault determination.

[0026] In some embodiments, determining whether the LED street light has a potential fault based on the multidimensional data information includes: Step S221: For each detection parameter, perform single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the detection parameter in the multidimensional data information to obtain the single-parameter threshold detection result and trend anomaly detection result corresponding to the detection parameter.

[0027] Specifically, for any given detection parameter value sequence, it is determined whether each detection parameter value in the sequence falls within the threshold range corresponding to the detection parameter. Detection parameter values ​​greater than the maximum value corresponding to the threshold range are marked with an ascending sign, and those less than the minimum value corresponding to the threshold range are marked with a descending sign. It is then determined whether the detection parameter value sequence exhibits a continuous decreasing, continuously increasing, or continuously fluctuating trend. If a continuous decreasing trend exists, the sequence is marked with "continuously decreasing," if a continuous increasing trend exists, it is marked with "continuously increasing," and if a continuous fluctuating trend exists, it is marked with "continuously fluctuating." This step provides comprehensive visualized data for the subsequent identification of potential faults, improving the efficiency and accuracy of potential fault identification.

[0028] For example, the threshold range of the current is [1.8A, 2.4A]. The detection parameter value sequence corresponding to the current in the multidimensional data information is 1.88A, 1.93A, 2.05A, 2.34A, 2.41A, 2.56A, 2.64A. After performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the current, the result is 1.88A, 1.93A, 2.05A, 2.34A, 2.41A↑, 2.56A↑, 2.64A↑ (continuously rising).

[0029] For example, the voltage threshold range is [200V, 230V], and the detection parameter value sequence corresponding to the voltage in the multidimensional data information is 225V, 223V, 220V, 215V, 213V, 210V, 205V. After performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the voltage, the result obtained is 225V, 223V, 220V, 215V, 213V, 210V, 205V (continuously decreasing).

[0030] For example, the threshold range of illuminance is [9000 lux, 10000 lux]. The detection parameter value sequence corresponding to illuminance in the multidimensional data information is 8999 lux↓, 9999 lux, 9001 lux, 9998 lux, 8997 lux↓, 9999 lux, 9001 lux. After performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to illuminance, the result obtained is 8999 lux, 9999 lux, 9001 lux, 9998 lux, 8997 lux, 9999 lux, 9001 lux (continuous fluctuation).

[0031] For example, the temperature threshold range is [0℃, 55℃]. The detection parameter value sequence corresponding to the temperature in the multidimensional data information is 55℃, 56℃, 58℃, 60℃, 62℃, 64℃, and 68℃. After performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the temperature, the result obtained is 55℃↑, 56℃↑, 58℃↑, 60℃↑, 62℃↑, 64℃↑, and 68℃↑ (continuously rising).

[0032] For example, the threshold range of the power factor is [0.9, 1]. The detection parameter value sequence corresponding to the power factor in the multidimensional data information is 0.98, 0.96, 0.95, 0.93, 0.90, 0.88, 0.85. After performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the power factor, the result obtained is 0.98, 0.96, 0.95, 0.93, 0.90, 0.88↓, 0.85↓ (continuously decreasing).

[0033] Step S222: Determine whether the LED street light has potential faults based on the single-parameter threshold detection results and trend anomaly detection results corresponding to each detection parameter.

[0034] Specifically, when the sequence of detection parameter values ​​corresponding to each detection parameter is within its corresponding threshold range, and the sequence of detection parameter values ​​corresponding to each detection parameter does not show an abnormal trend, the LED street light is determined to have no potential fault. When any detection parameter's sequence of values ​​is outside its corresponding threshold range, or when any detection parameter's sequence of values ​​shows an abnormal trend, the LED street light is determined to have a potential fault. This step, by combining single-parameter threshold detection and trend anomaly detection as dual judgment criteria, achieves multi-level capture of LED street light faults, helping to avoid missed detections by single-parameter threshold detection and improving the early warning capability of faults.

[0035] For example, when the sequence of detection parameter values ​​corresponding to each detection parameter does not contain any rising sign, falling sign, continuously rising sign, continuously falling sign, or continuously fluctuating sign, it is determined that the LED street light does not have a potential fault; when the sequence of detection parameter values ​​corresponding to any detection parameter contains any rising sign, falling sign, continuously rising sign, continuously falling sign, or continuously fluctuating sign, it is determined that the LED street light has a potential fault.

[0036] In some embodiments, generating a pre-selected fault set for the LED street light based on the multi-dimensional data information includes: Step S231: For each detection parameter, perform single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the detection parameter in the multidimensional data information to obtain the anomaly information corresponding to the detection parameter.

[0037] For example, if the threshold range of the current is [1.8A, 2.4A], and the detection parameter value sequence corresponding to the current in the multidimensional data information is 1.88A, 1.93A, 2.05A, 2.34A, 2.41A, 2.56A, 2.64A, then after performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the current, the result is 1.88A, 1.93A, 2.05A, 2.34A, 2.41A↑, 2.56A↑, 2.64A↑ (continuously rising). Then the abnormal information corresponding to the current is: greater than the maximum current threshold and the current is continuously rising.

[0038] For example, if the voltage threshold range is [200V, 230V], and the corresponding detection parameter value sequence for the voltage in the multidimensional data information is 225V, 223V, 228V, 223V, 220V, 222V, 218V, then after performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the voltage, the result obtained is 225V, 223V, 220V, 215V, 213V, 210V, 205V. Therefore, there is no abnormal information regarding the voltage.

[0039] For example, the threshold range of illuminance is [9000 lux, 10000 lux]. The detection parameter value sequence corresponding to illuminance in the multidimensional data information is 8999 lux, 9999 lux, 9001 lux, 9998 lux, 8997 lux, 9999 lux, 9001 lux. After performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to illuminance, the result is 8999 lux↓, 9999 lux, 9001 lux, 9998 lux, 8997 lux↓, 9999 lux, 9001 lux (continuous fluctuation). The abnormal information corresponding to illuminance is: less than the minimum illuminance threshold and continuous fluctuation of illuminance.

[0040] For example, the temperature threshold range is [0℃, 55℃]. The detection parameter value sequence corresponding to the temperature in the multidimensional data information is 55℃, 56℃, 58℃, 60℃, 62℃, 64℃, and 68℃. After performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the temperature, the result is 55℃↑, 56℃↑, 58℃↑, 60℃↑, 62℃↑, 64℃↑, and 68℃↑ (continuously rising). The abnormal information corresponding to the temperature is: greater than the maximum temperature threshold and the temperature is continuously rising.

[0041] For example, the threshold range of the power factor is [0.9, 1]. The detection parameter value sequence corresponding to the power factor in the multidimensional data information is 0.98, 0.96, 0.95, 0.93, 0.90, 0.88, 0.85. After performing single-parameter threshold detection and trend anomaly detection on the detection parameter value sequence corresponding to the power factor, the result is 0.98, 0.96, 0.95, 0.93, 0.90, 0.88↓, 0.85↓ (continuously decreasing). The abnormal information corresponding to the power factor is: less than the minimum power factor threshold and the power factor is continuously decreasing.

[0042] It should be noted that abnormal parameter states include current exceeding the maximum current threshold, current continuously rising, current falling below the minimum power factor threshold, and power factor continuously decreasing.

[0043] Step S232: For each preset fault in the fault rule base corresponding to the LED street light, determine whether there is a preset abnormal parameter state corresponding to the preset fault in each abnormal information. If there is, determine that the preset fault is a pre-selected fault; each pre-selected fault constitutes the pre-selected fault set.

[0044] It should be noted that the preset abnormal parameter states corresponding to each preset fault are obtained through simulation experiments.

[0045] Specifically, for each preset fault, if at least one preset abnormal parameter state corresponding to the preset fault exists in each abnormal information, the preset fault is determined as a pre-selected fault. This method of determining pre-selected faults helps improve the comprehensiveness of fault detection and prevents missed detections.

[0046] For example, the preset abnormal parameter states corresponding to the preset fault of drive circuit overload are temperature greater than the maximum temperature threshold, current continuously rising, and illuminance continuously decreasing. Since there are abnormal parameter states of temperature greater than the maximum temperature threshold and current continuously rising among the abnormal information, drive circuit overload is determined to be the pre-selected fault.

[0047] For example, the preset abnormal parameter states corresponding to the preset fault of capacitor failure are continuous current fluctuation, continuous power factor fluctuation and continuous illuminance fluctuation. Since there is an abnormal parameter state of continuous illuminance fluctuation among the abnormal information, capacitor failure is determined to be the pre-selected fault.

[0048] Step S300: For each pre-selected fault in the pre-selected fault set, perform topological epoch analysis on the pre-selected fault based on the topological structure information of the LED street light network to obtain the fault-affected node information corresponding to the pre-selected fault, and determine whether the pre-selected fault exists based on the status information of each fault-affected node in the fault-affected node information within a second preset time period. If it exists, determine that the pre-selected fault is the target fault corresponding to the LED street light; wherein, the start time of the second preset time period is the current time.

[0049] The topology information includes electrical topology and network topology.

[0050] Specifically, firstly, based on the electrical topology structure, the electrical associated node information corresponding to the LED street light is determined, and based on the network topology structure, the network associated node information corresponding to the LED street light is determined. The electrical associated node information and the network associated node information constitute the fault-affected node information. Then, based on electrical topology theory and the electrical associated node information, an electrical topology impact analysis is performed on the pre-selected fault to obtain the electrical predicted state information of each electrical associated node in the electrical associated node information within a second preset time period. Then, based on network topology theory and the network associated node information, a network topology impact analysis is performed on the preset fault to obtain the network predicted state information of each network associated node in the network associated node information within a second preset time period. Finally, regarding the electrical association... For each electrically associated node in the node information, after the second preset time period, the electrical status information of the electrically associated node within the second preset time period is obtained, and it is determined whether the electrical predicted status information corresponding to the electrically associated node matches the electrical status information. For each network associated node in the network associated node information, after the second preset time period, the network status information of the network associated node within the second preset time period is obtained, and it is determined whether the network predicted status information corresponding to the network associated node matches the network status information. If the electrical predicted status information and electrical status information of each electrically associated node match, and the network predicted status information and network status information of each network associated node match, it is determined that the pre-selected fault exists within the second preset time period. For each pre-selected fault, this step performs electrical topology analysis and network topology analysis on the pre-selected fault within the second preset time period to determine whether the pre-selected fault exists, which helps to improve the accuracy of the judgment results.

[0051] In some embodiments, the topology structure information based on the LED street light network is used to perform topology history analysis on the pre-selected faults to obtain fault-affected node information corresponding to the pre-selected faults, including: Step S311: Determine the electrical association node information corresponding to the LED street light based on the electrical topology structure.

[0052] For example, taking street light SL0287 as an example, the power supply relationship of street light SL0287 is queried from the electrical topology. The query results show that SL0287 is located on the northern section of the municipal avenue and is connected to distribution cabinet DC-15. The specific connection relationship is as follows: distribution cabinet DC-15 uses a three-phase four-wire power supply, and SL0287 is connected to the C-phase output circuit, which is a series power supply. In the electrical topology, the upstream node of SL0287 is distribution cabinet DC-15 (85 meters away), the directly upstream adjacent node is SL0286 (50 meters away), and the directly downstream adjacent node is SL0288 (50 meters away). The series circuit continues to extend, with SL0288 connected downstream of SL0289 (50 meters away), SL0290 (50 meters away), and SL0291 (50 meters away) in sequence, finally connecting to the end of the circuit, SL0292 (50 meters away). Therefore, the electrical associated node information corresponding to street light SL0287 is: power distribution cabinet DC-15, street light SL0286, street light SL0288, street light SL0289, street light SL0290, street light SL0291, and street light SL0292.

[0053] Step S312: Determine the network association node information corresponding to the LED street light based on the network topology; the electrical association node information and the network association node information constitute the fault-affected node information.

[0054] For example, taking street light SL0287 as an example, the network connection relationship of SL0287 is queried from the network topology structure. The query results show that the street light uses ZigBee mesh network communication, and SL0287 acts as a router node, undertaking the data forwarding function. Its parent node is SL0280 (120 meters away), which is a router. The grandparent node is the coordinator SL0270 (200 meters away), which is responsible for data aggregation and uploading for the entire network area. SL0287 has two child nodes: SL0295 (80 meters away) and SL0296 (85 meters away). Both of these nodes are terminal nodes. Therefore, the network associated node information corresponding to street light SL0287 is SL0280, SL0270, SL0295, and SL0296.

[0055] In some embodiments, determining whether the pre-selected fault exists based on the status information of each fault-affected node in the fault-affected node information within a second preset time period includes: Based on electrical topology theory and the electrical associated node information, an electrical topology impact analysis is performed on the pre-selected fault to obtain the electrical predicted state information of each electrical associated node in the electrical associated node information within a second preset time period. Based on network topology theory and the network associated node information, a network topology impact analysis is performed on the preset fault to obtain the network predicted state information of each network associated node in the network associated node information within a second preset time period. For each electrical associated node in the electrical associated node information, after the second preset time period, the electrical status information of the electrical associated node within the second preset time period is obtained, and it is determined whether the electrical predicted status information corresponding to the electrical associated node matches the electrical status information. For each network-associated node in the network-associated node information, after the second preset time period, the network status information of the network-associated node within the second preset time period is obtained, and it is determined whether the network predicted status information corresponding to the network-associated node matches the network status information. If the electrical predicted status information and electrical status information of each electrical associated node match, and the network predicted status information and network status information of each network associated node match, it is determined that the pre-selected fault exists within the second preset time period.

[0056] For example, taking a drive circuit overload fault as an example, based on Kirchhoff's voltage law and power distribution principle of series circuits, the electrical prediction status information of each electrical associated node in the electrical associated node information within the second preset time period is predicted, resulting in: {Distribution cabinet: current increase of not less than 0.5A, voltage drop of not less than 1.5V; SL0286: current unchanged, voltage drop of not less than 1V; SL0288: voltage drop of not less than 4V, brightness decrease of not less than 5%; SL0289: voltage drop of not less than 4V, power factor decrease of not less than 0.} .02; SL0290-SL0292: Voltage drop of not less than 6V}, according to the routing protocol of the ZigBeemesh network, predict the network prediction state information of each network associated node in the network associated node information within the second preset time period, and obtain {SL0280: Data forwarding success rate decreases, retransmission count increases; SL0270: Routing table update frequency increases, network management packets increase; SL0295: Packet loss rate increases, latency increases; SL0296: Packet loss rate increases, latency increases}, assuming that in the first... After the second preset time period, the electrical status information of each electrically associated node obtained during the second preset time period is as follows: {Distribution cabinet: current increases by 0.56A, voltage decreases by 1.8V; SL0286: current remains unchanged, voltage decreases by 1.2V; SL0288: voltage decreases by 5V, brightness decreases by 5%; SL0289: voltage decreases by 5V, power factor decreases by 0.03; SL0290-SL0292: voltage decreases by at least 7V}. Assuming that after the second preset time period, the electrical status information of each network associated node obtained during the second preset time period... The network status information is {SL0280: Data forwarding success rate decreases, retransmission count increases; SL0270: Routing table update frequency increases, network management packets increase; SL0295: Packet loss rate increases, latency increases; SL0296: Packet loss rate increases, latency increases}. Since the electrical predicted status information and electrical status information corresponding to each electrical associated node match, and the network predicted status information and network status information corresponding to each network associated node match, a drive circuit overload fault exists during the second preset time period.

[0057] The method provided in this embodiment, on the one hand, achieves comprehensive monitoring and structured data management of the operating status of a large-scale street light network by acquiring multi-source data information of each LED street light in the LED street light network in real time and storing it in a multi-dimensional state matrix. This provides a complete data foundation for subsequent fault analysis and overcomes the problems of single data source and incomplete information in traditional methods. On the other hand, it improves the comprehensiveness of fault identification by generating a pre-selected fault set based on multi-dimensional data information. Furthermore, it improves the shortcomings of traditional fault diagnosis methods by performing topology traversal analysis based on LED street light network topology information and verifying pre-selected faults using the state information of fault-affected nodes. This improves the lack of network topology analysis in traditional fault diagnosis methods, realizes the transformation from single-point fault judgment to network-based fault verification, improves the reliability of fault diagnosis, reduces the false alarm rate, and provides maintenance personnel with more accurate fault location information.

[0058] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an intelligent fault diagnosis system for an LED lighting device provided in one embodiment of this application. Figure 2 As shown, the intelligent fault diagnosis system 100 for this LED lighting equipment includes: The acquisition module 110 is used to acquire multi-source data information of each LED street light in the LED street light network in real time, and store the multi-source data information into a preset multi-dimensional state matrix.

[0059] The judgment module 120 is used to extract multi-dimensional data information of each LED street light within a first preset time period from the multi-dimensional state matrix, and to determine whether there is a potential fault in the LED street light based on the multi-dimensional data information. If there is a potential fault, a pre-selected fault set of the LED street light is generated based on the multi-dimensional data information; wherein, the end time of the first preset time period is the current time.

[0060] The analysis module 130 is used to perform topological epoch analysis on each pre-selected fault in the pre-selected fault set based on the topological structure information of the LED street light network, to obtain the fault-affected node information corresponding to the pre-selected fault, and to determine whether the pre-selected fault exists based on the status information of each fault-affected node in the fault-affected node information within a second preset time period. If it exists, the pre-selected fault is determined to be the target fault corresponding to the LED street light; wherein, the start time of the second preset time period is the current time.

[0061] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0062] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, herein, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0063] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above descriptions are merely specific implementations of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for intelligent fault diagnosis of LED lighting equipment, characterized in that, include: Real-time acquisition of multi-source data information of each LED street light in the LED street light network, and storage of the multi-source data information into a preset multi-dimensional state matrix; For each of the LED streetlights, multidimensional data information of the LED streetlights within a first preset time period is extracted from the multidimensional state matrix, and the potential faults of the LED streetlights are determined based on the multidimensional data information. If potential faults exist, a pre-selected fault set of the LED streetlights is generated based on the multidimensional data information; wherein, the end time of the first preset time period is the current time. For each pre-selected fault in the pre-selected fault set, a topology epoch analysis is performed on the pre-selected fault based on the topology structure information of the LED street light network to obtain the fault-affected node information corresponding to the pre-selected fault. Based on the status information of each fault-affected node in the fault-affected node information within a second preset time period, it is determined whether the pre-selected fault exists. If it exists, the pre-selected fault is determined to be the target fault corresponding to the LED street light. The start time of the second preset time period is the current time.

2. The intelligent fault diagnosis method for LED lighting equipment according to claim 1, characterized in that, The step of determining whether the LED street light has potential faults based on the multidimensional data information includes: For each detection parameter, single-parameter threshold detection and trend anomaly detection are performed on the detection parameter value sequence corresponding to the detection parameter in the multidimensional data information to obtain the single-parameter threshold detection result and trend anomaly detection result corresponding to the detection parameter; The potential faults of the LED streetlights are determined based on the single-parameter threshold detection results and trend anomaly detection results corresponding to each detection parameter.

3. The intelligent fault diagnosis method for LED lighting equipment according to claim 2, characterized in that, The method of determining whether the LED street light has potential faults based on the single-parameter threshold detection results and trend anomaly detection results corresponding to each detection parameter includes: When the sequence of detection parameter values ​​corresponding to each detection parameter is within its corresponding threshold range, and the sequence of detection parameter values ​​corresponding to each detection parameter does not show an abnormal trend, it is determined that the LED street light does not have a potential fault. When any detection parameter value sequence corresponding to any detection parameter contains a detection parameter that is outside its corresponding threshold range, or when any detection parameter value sequence corresponding to any detection parameter shows an abnormal trend, it is determined that the LED street light has a potential fault.

4. The intelligent fault diagnosis method for LED lighting equipment according to claim 1, characterized in that, The process of generating a pre-selected fault set for the LED streetlights based on the multi-dimensional data information includes: For each detection parameter, single-parameter threshold detection and trend anomaly detection are performed on the sequence of detection parameter values ​​corresponding to the detection parameter in the multidimensional data information to obtain the anomaly information corresponding to the detection parameter; For each preset fault in the fault rule base corresponding to the LED street light, it is determined whether there is a preset abnormal parameter state corresponding to the preset fault in each abnormal information. If there is, the preset fault is determined to be a pre-selected fault; each pre-selected fault constitutes the pre-selected fault set.

5. The intelligent fault diagnosis method for LED lighting equipment according to claim 1, characterized in that, The topology information includes electrical topology and network topology. The topology structure information based on the LED street light network is used to perform topology history analysis on the pre-selected faults to obtain fault-affected node information corresponding to the pre-selected faults, including: Based on the electrical topology structure, determine the electrical association node information corresponding to the LED street light; Based on the network topology, the network associated node information corresponding to the LED street light is determined; the electrical associated node information and the network associated node information constitute the fault-affected node information.

6. The intelligent fault diagnosis method for LED lighting equipment according to claim 5, characterized in that, The step of determining whether the pre-selected fault exists based on the status information of each fault-affected node in the fault-affected node information within a second preset time period includes: Based on electrical topology theory and the electrical associated node information, an electrical topology impact analysis is performed on the pre-selected fault to obtain the electrical predicted state information of each electrical associated node in the electrical associated node information within a second preset time period. Based on network topology theory and the network associated node information, a network topology impact analysis is performed on the preset fault to obtain the network predicted state information of each network associated node in the network associated node information within a second preset time period. For each electrical associated node in the electrical associated node information, after the second preset time period, the electrical status information of the electrical associated node within the second preset time period is obtained, and it is determined whether the electrical predicted status information corresponding to the electrical associated node matches the electrical status information. For each network-associated node in the network-associated node information, after the second preset time period, the network status information of the network-associated node within the second preset time period is obtained, and it is determined whether the network predicted status information corresponding to the network-associated node matches the network status information. If the electrical predicted status information and electrical status information of each electrical associated node match, and the network predicted status information and network status information of each network associated node match, it is determined that the pre-selected fault exists within the second preset time period.

7. An intelligent fault diagnosis system for LED lighting equipment, characterized in that, include: The acquisition module is used to acquire multi-source data information of each LED street light in the LED street light network in real time, and store the multi-source data information into a preset multi-dimensional state matrix; The judgment module is used to extract multi-dimensional data information of each LED street light within a first preset time period from the multi-dimensional state matrix, and to determine whether there is a potential fault in the LED street light based on the multi-dimensional data information. If there is a potential fault, a pre-selected fault set of the LED street light is generated based on the multi-dimensional data information; wherein, the end time of the first preset time period is the current time. The analysis module is used to perform topological epoch analysis on each pre-selected fault in the pre-selected fault set based on the topological structure information of the LED street light network, to obtain the fault-affected node information corresponding to the pre-selected fault, and to determine whether the pre-selected fault exists based on the status information of each fault-affected node in the fault-affected node information within a second preset time period. If it exists, the pre-selected fault is determined to be the target fault corresponding to the LED street light; wherein, the start time of the second preset time period is the current time.

Images