Predictive maintenance method and device for street lamp and electronic equipment

Abstract

The invention discloses a predictive maintenance method and device for a street lamp and electronic equipment. The method comprises the following steps: acquiring a first working characteristic of a light-emitting diode, a second working characteristic of a driving power supply, an environment characteristic of the current environment of the lamp and a use mode characteristic of the lamp; according to the preprocessed first working characteristics of the light emitting diode, the second working characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp and the use mode characteristics of the lamp, based on a pre-constructed hybrid prediction model, determining the residual life of each street lamp, and mapping the residual life into a standardized health score; and according to the health score and the remaining life of each street lamp and pre-stored geographical distribution and maintenance cost of each street lamp, grouping the street lamps by adopting a clustering algorithm, and generating a regional maintenance task list containing priorities and an optimal inspection route. The technical scheme provided by the embodiment of the invention can effectively improve the prediction precision of the residual life of the street lamp.

Description

Technical Field

[0001] This invention relates to the field of municipal facility operation and maintenance technology, and in particular to a predictive maintenance method, device and electronic equipment for streetlights. Background Technology

[0002] In recent years, light-emitting diode (LED) streetlights have become the mainstream replacement for traditional electric lights. Although their theoretical lifespan can reach tens of thousands of hours, in actual operation, some streetlights experience premature light decay, driver failure, intermittent flickering, or malfunction, bringing significant manual maintenance costs and the risk of blind spots to urban operations and maintenance. Most municipal units still operate and maintain them using a "fault report → manual inspection → replacement / repair" model, lacking proactive prediction and tiered handling capabilities.

[0003] Existing technologies provide asset management and simple health ratings based on operating time and power statistics, but they cannot accurately predict the remaining lifespan of streetlights or generate efficient maintenance plans. Summary of the Invention

[0004] This invention provides a predictive maintenance method, apparatus, and electronic device for streetlights to solve the problem that existing technologies cannot accurately predict the remaining lifespan of streetlights and generate efficient maintenance plans.

[0005] According to one aspect of the present invention, a predictive maintenance method for a street light is provided, the street light comprising a luminaire and a pole, the luminaire comprising a lamp panel and a driving power supply, the lamp panel having a light-emitting diode mounted thereon, the method comprising:

[0006] Acquire the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire;

[0007] Based on the first operating characteristics of the pre-processed light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp, the remaining lifespan of each street lamp is determined based on a pre-built hybrid prediction model, and the remaining lifespan is mapped to a standardized health score.

[0008] Based on the health score, remaining lifespan, and pre-stored geographical distribution and maintenance cost of each street light, a clustering algorithm is used to group the street lights, generating a regionalized maintenance task list with priorities and an optimal inspection route.

[0009] Optionally, the first operating characteristics of the light-emitting diode include the operating voltage, operating current, operating temperature, and dynamic internal resistance of the light-emitting diode calculated based on the operating voltage, the operating current, and the operating temperature;

[0010] The second operating characteristics of the drive power supply include the drive voltage, drive current, start-up time, and recovery time of the drive power supply, as well as the output ripple and total harmonic distortion of the drive power supply calculated based on the drive voltage.

[0011] The environmental characteristics include solar radiation intensity, relative humidity, and ambient temperature;

[0012] The usage pattern characteristics include average daily lighting duration, number of switching operations, and count of frequent start-stop events.

[0013] Optionally, the dynamic internal resistance of the LED is calculated as follows: Under normal LED illumination, a narrow-band sinusoidal or square-wave perturbation signal with an amplitude greater than the normal operating current is injected into the LED. The voltage drop and current changes of the LED before and after the injection are collected, and the result is calculated using the formula... The instantaneous small-signal internal resistance of the light-emitting diode is calculated; where, The instantaneous small-signal internal resistance of the light-emitting diode is... This represents the voltage change of the light-emitting diode. This represents the change in current of the light-emitting diode;

[0014] The instantaneous small-signal internal resistance of the LED is compensated for using a preset temperature compensation coefficient. The compensation formula is as follows: In the formula, The preset temperature compensation coefficient, This represents the temperature deviation between the current actual operating temperature and the reference temperature. This represents the dynamic internal resistance of the light-emitting diode.

[0015] Optionally, the hybrid prediction model is a dual-branch fusion architecture, including a temporal branch and a structured branch. The temporal branch uses a long short-term memory network to model the dynamic internal resistance of the light-emitting diode and the output ripple of the driving power supply. The structured branch uses a gradient boosting tree or random forest to perform correlation analysis on environmental features and usage pattern features. The outputs of the two branches are integrated to determine the remaining lifespan of each street light and map the remaining lifespan to a standardized health score.

[0016] Optionally, the clustering algorithm is the DBSCAN algorithm or the K-means algorithm, and the optimal inspection route is planned and generated using an improved genetic algorithm or a weighted Dijkstra algorithm.

[0017] Optionally, the hybrid prediction model is adaptively updated by combining actual failure events in the field through a pre-deployed incremental learning mechanism.

[0018] Optionally, after grouping the streetlights using a clustering algorithm based on their health score, remaining lifespan, and pre-stored geographical distribution and maintenance costs, and generating a prioritized regional maintenance task list and optimal inspection route, the method further includes:

[0019] When the remaining lifespan is greater than a preset threshold, a command is issued to derating the LED or driver power supply; when a lamp fault is detected, an isolation command is issued to isolate the faulty lamp.

[0020] Optionally, after obtaining the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire, the method further includes:

[0021] The first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire are preprocessed.

[0022] According to another aspect of the present invention, a predictive maintenance device for a street light is provided. The street light includes a luminaire and a pole. The luminaire includes a lamp panel and a driving power supply. A light-emitting diode is mounted on the lamp panel for performing the predictive maintenance method for a street light according to any embodiment of the present invention. The device includes:

[0023] The acquisition module is used to acquire the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp.

[0024] The determination module is used to determine the remaining lifespan of each street light based on a pre-built hybrid prediction model, according to the first operating characteristics of the pre-processed light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp, and to map the remaining lifespan to a standardized health score.

[0025] The generation module is used to group streetlights using a clustering algorithm based on the health score, remaining lifespan, and pre-stored geographical distribution and maintenance cost of each streetlight, and generate a regionalized maintenance task list with priorities and an optimal inspection route.

[0026] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0027] At least one processor; and

[0028] A memory communicatively connected to the at least one processor; wherein,

[0029] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the predictive maintenance method for streetlights according to any embodiment of the present invention.

[0030] This invention provides a predictive maintenance method, device, and electronic device for streetlights. The technical solution provided by this invention achieves precise perception of the physical state of the LEDs and driver power supply by real-time monitoring and acquiring the first operating characteristics of the LEDs, the second operating characteristics of the driver power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire. Based on a pre-built hybrid prediction model, potential faults of the LEDs and driver power supply can be predicted in advance, significantly improving the accuracy of remaining life prediction compared to existing technologies. By automatically generating a regionalized maintenance task list containing maintenance priorities and the optimal inspection route, inspection costs and the risk of streetlight outages are effectively reduced.

[0031] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 A flowchart illustrating a predictive maintenance method for streetlights provided in an embodiment of the present invention;

[0034] Figure 2 A schematic diagram of the structure of a predictive maintenance device for streetlights provided in an embodiment of the present invention;

[0035] Figure 3 A schematic diagram of another predictive maintenance device for streetlights provided in an embodiment of the present invention;

[0036] Figure 4 A flowchart of another predictive maintenance method for streetlights provided in an embodiment of the present invention;

[0037] Figure 5 A schematic diagram of the structure of another predictive maintenance device for streetlights provided in an embodiment of the present invention;

[0038] Figure 6This is a schematic diagram of the electronic device used in a predictive maintenance method for streetlights, as provided in an embodiment of the present invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0041] Figure 1 This is a flowchart illustrating a predictive maintenance method for streetlights according to an embodiment of the present invention. This embodiment is applicable to online monitoring of municipal road lighting systems. The method can be executed by a predictive maintenance device for streetlights, which can be implemented in hardware and / or software and can be configured in any electronic device with communication capabilities. The streetlight includes a luminaire and a pole; the luminaire includes a lamp panel and a driver power supply; light-emitting diodes are mounted on the lamp panel. (See also...) Figure 1 The method includes:

[0042] S110, Obtain the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire.

[0043] The first operating characteristic refers to the core electrical parameters that directly reflect the physical state and aging degree of the LED. For example, the first operating characteristic of an LED may include its operating voltage, operating current, operating temperature, and the dynamic internal resistance calculated based on these parameters. The second operating characteristic refers to the core electrical quality parameters that directly reflect the physical state and aging degree of the internal components of the power supply. For example, the second operating characteristic of the power supply may include its drive voltage, drive current, start-up time, and recovery time, as well as the output ripple and total harmonic distortion calculated based on the drive voltage. Internal components of the power supply may include electrolytic capacitors and power metal-oxide-semiconductor field-effect transistors (MOSFETs). The environmental characteristics of the current environment in which the luminaire is located refer to the external environmental parameters during the luminaire's operation. For example, environmental characteristics may include solar irradiance, relative humidity, and ambient temperature. The usage pattern characteristics of the luminaire may include the average daily lighting duration, number of switching operations, and the count of frequent start-stop events.

[0044] Specifically, a health monitoring module is integrated into each street light. This module acquires the first operating characteristics of the LEDs and the second operating characteristics of the driver power supply. The environmental characteristics of the current environment in which the light fixture is located can be obtained by connecting to a third-party meteorological data interface. The usage mode characteristics of the light fixture can be obtained by retrieving the operation logs of the smart street light system.

[0045] S120. Based on the first operating characteristics of the pre-processed light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp, the remaining lifespan of each street lamp is determined based on the pre-built hybrid prediction model, and the remaining lifespan is mapped to a standardized health score.

[0046] Preprocessing involves filtering, denoising, outlier removal, and compression of the first operating feature, second operating feature, environmental features, and usage pattern features. The hybrid prediction model employs a dual-branch fusion architecture, including a temporal branch and a structured branch. The temporal branch uses a Long Short-Term Memory (LSTM) network to model the dynamic internal resistance of the LEDs and the output ripple of the driving power supply. The structured branch uses a Gradient Boosting Decision Tree (GBDT) or Random Forest (RF) to perform correlation analysis on the environmental features and usage pattern features. The outputs of both branches are integrated to determine the remaining lifespan of each street light and map this remaining lifespan to a standardized health score. The hybrid prediction model adaptively updates itself by incorporating actual failure events from the field through a pre-deployed incremental learning mechanism.

[0047] Specifically, firstly, using the dynamic internal resistance of LEDs containing a time-series relationship as the core degradation variable in the first operating characteristic of LEDs, a sliding window filter is applied to the dynamic internal resistance of LEDs containing a time-series relationship to obtain a smoothed sequence of dynamic internal resistances. Based on the smoothed sequence of LED dynamic internal resistances, the initial internal resistances of LEDs in newly installed lamps collected beforehand, and a failure internal resistance threshold preset through experimental data, the degradation index of the LEDs is calculated. The specific formula is as follows:

[0048] In the formula, This is a degradation indicator for light-emitting diodes (LEDs). When this indicator gradually approaches 1, it means that the LED is gradually approaching the end of its lifespan. The dynamic internal resistance of a smooth sequence of light-emitting diodes. The initial internal resistance of the LEDs in the newly installed lamps was collected in advance. The failure internal resistance threshold is preset based on experimental data.

[0049] Secondly, the output ripple containing timing relationships in the second operating characteristic of the drive power supply reflects the performance degradation of the electrolytic capacitors within the drive power supply; the total harmonic distortion containing timing relationships in the second operating characteristic of the drive power supply reflects the overall aging of the MOSFETs and filter networks within the drive power supply; and the start-up time and recovery time containing timing relationships in the second operating characteristic of the drive power supply reflect the drive control capability of the drive power supply. After normalizing the above characteristics, the degradation index of the drive power supply is calculated, as follows:

[0050] ;in, , , , These represent the baseline values ​​for output ripple, total harmonic distortion, startup time, and recovery time under healthy conditions, respectively. , , , Represents weight, , , , These are, respectively, the output ripple with timing relationship, the total harmonic distortion with timing relationship, the start-up time with timing relationship, and the recovery time with timing relationship; This is a degradation indicator for the power supply. This indicator can reflect the degree of aging of the power supply. When this indicator is close to 1, it means that the power supply is nearing the end of its life.

[0051] The degradation indices of LEDs and drivers are input into a pre-built hybrid prediction model. The time-series branch of the hybrid prediction model uses a Long Short-Term Memory (LSTM) network to perform correlation analysis on the degradation indices of LEDs and drivers, outputting the remaining lifetimes of the LEDs and drivers. The pre-processed environmental characteristics of the current environment in which the luminaire is located and the luminaire's usage pattern characteristics are input into the pre-built hybrid prediction model. The structured branch of the hybrid prediction model uses a gradient boosting tree or random forest to perform correlation analysis on the environmental characteristics and usage pattern characteristics, outputting the lifetime weights of LEDs and drivers under the current operating conditions. The outputs of the two branches are then weighted and fused to obtain the final remaining lifetime of each streetlight.

[0052] ;

[0053] in, For the final remaining lifespan of each street light, This represents the remaining lifespan of the LED. For the remaining lifespan of the drive power supply, As weight.

[0054] Finally, the remaining lifespan of each street light is mapped to a standardized health score (0–100 points).

[0055] S130. Based on the health score, remaining lifespan, and pre-stored geographical distribution and maintenance cost of each street light, a clustering algorithm is used to group the street lights, generating a regionalized maintenance task list containing maintenance priorities and the optimal inspection route.

[0056] The clustering algorithm is either DBSCAN or K-means, and the optimal inspection route is planned and generated using an improved genetic algorithm or a weighted Dijkstra algorithm.

[0057] Specifically, firstly, based on the health score, remaining lifespan, and pre-stored geographical distribution of each street light, a maintenance priority function is constructed. This function is used to uniformly quantify the maintenance urgency of each street light, as shown in the following formula:

[0058] ;

[0059] in, To determine the urgency of maintaining the i-th street light, The larger the scale, the more urgent the maintenance. Give the i-th street light a health score. Let be the remaining lifespan of the i-th street light. The importance of the geographical location of the i-th street light. , , As weight.

[0060] Secondly, based on the maintenance urgency of each street light and the pre-stored maintenance cost of each street light, a spatial-risk coupled clustering algorithm is used to group the street lights, outputting several maintenance task groups with "region + risk" dual labels. Each street light within a group is considered a node, and the actual road distance between street lights is considered an edge. A weighted graph model is constructed to generate a regionalized maintenance task list containing maintenance priorities and an optimal inspection route. The regionalized maintenance task list includes not only maintenance priorities but also suggested maintenance content, required spare parts types, and recommended execution time windows. The edge weights represent the comprehensive cost from one street light to another, as shown in the following formula:

[0061] ;

[0062] in, The total cost for inspection personnel to move from the i-th street light to the j-th street light. This represents the actual road distance traveled by the inspector from the i-th street light to the j-th street light. As a transportation cost factor, The urgency of maintaining the j-th street light, This is a risk-weighted factor.

[0063] Taking the maintenance station as the starting point and 10 streetlights in a certain area as inspection nodes as an example, the maintenance station and the 10 streetlights are considered as nodes. The road distance and risk weighting factor between the streetlights are transformed into weighted edges to construct an inspection path network. Starting from the starting point, the comprehensive cost from the starting point to each streetlight is calculated. The path with the lowest comprehensive cost and the highest risk streetlight is selected first, and the path is gradually expanded to all nodes. Finally, an optimal inspection route is formed that starts from the starting point, covers all streetlights that need to be inspected, has the lowest comprehensive cost, and prioritizes high-risk streetlights.

[0064] The technical solution provided by this invention achieves precise perception of the physical state of the LED and the driver power supply by real-time monitoring and acquiring the first operating characteristics of the LED, the second operating characteristics of the driver power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp. Based on a pre-built hybrid prediction model, potential faults of the LED and the driver power supply can be predicted in advance, and the remaining life prediction accuracy is significantly improved compared with the prior art. By automatically generating a regionalized maintenance task list containing maintenance priorities and the optimal inspection route, the inspection cost and the risk of lamp outage are effectively reduced.

[0065] The following is combined Figure 2 This invention introduces a predictive maintenance method for streetlights provided by an embodiment of the present invention. Figure 2 This is a schematic diagram of a predictive maintenance device for streetlights provided in an embodiment of the present invention. See also... Figure 2 The device includes a health monitoring module 210, a communication module 220, an edge / cloud platform 230, a local execution module 240, and an operation and maintenance scheduling and work order system 250.

[0066] The health monitoring module 210 acquires the first operating characteristics of the LEDs and the second operating characteristics of the driver power supply. It also obtains the environmental characteristics of the current environment of the lamps by connecting to a third-party meteorological data interface and the usage mode characteristics of the lamps by retrieving the operation logs of the municipal smart street light system. The health monitoring module 210 preprocesses the first operating characteristics, the second operating characteristics, the environmental characteristics of the current environment of the lamps, and the usage mode characteristics of the lamps. The health monitoring module 210 transmits the preprocessed first operating characteristics, the second operating characteristics, the environmental characteristics of the current environment of the lamps, and the usage mode characteristics of the lamps to the edge / cloud platform 230 via the communication module 220. Based on the preprocessed first operating characteristics of the LEDs, the second operating characteristics of the driver power supply, the environmental characteristics of the current environment of the lamps, and the usage mode characteristics of the lamps, the edge / cloud platform 230 determines the remaining lifespan of each street light based on a pre-built hybrid prediction model and maps the remaining lifespan to a standardized health score. Based on the health score, remaining lifespan, and pre-stored geographical distribution and maintenance costs of each street light, a clustering algorithm is used to group the street lights, generating a regionalized maintenance task list with maintenance priorities and an optimal inspection route. The edge / cloud platform 230 transmits the generated regionalized maintenance task list with maintenance priorities and the optimal inspection route to the operation and maintenance scheduling and work order system 250. The operation and maintenance scheduling and work order system 250, based on the regionalized maintenance task list and the optimal inspection route, controls the edge / cloud platform 230 to issue derated operation / isolation commands to the local execution module 240 to control the operation of the street lights, and simultaneously dispatches maintenance work orders to the inspection personnel.

[0067] Optionally, the first operating characteristics of the light-emitting diode include the operating voltage, operating current, operating temperature, and dynamic internal resistance of the light-emitting diode calculated based on the operating voltage, operating current, and operating temperature; the second operating characteristics of the driving power supply include the driving voltage, driving current, start-up time, and recovery time of the driving power supply, and the output ripple and total harmonic distortion of the driving power supply calculated based on the driving voltage; environmental characteristics include solar irradiance, relative humidity, and ambient temperature; and usage mode characteristics include average daily lighting duration, number of switching operations, and count of frequent start-stop events.

[0068] Specifically, see Figure 3 , Figure 3 This is a schematic diagram of another predictive maintenance device for streetlights provided in an embodiment of the present invention. The health monitoring module 210 includes a current acquisition unit, a voltage acquisition unit, a temperature acquisition unit, and a perturbation injection unit. The current acquisition unit, voltage acquisition unit, temperature acquisition unit, and perturbation injection unit acquire the operating current, operating voltage, and operating temperature of the light-emitting diode (LED). Specifically, the current acquisition unit uses a high-precision Hall effect sensor or a 0.01Ω precision shunt resistor to acquire the LED's operating current; the voltage acquisition unit uses a voltage sensor to acquire the LED's operating voltage; the temperature acquisition unit uses a thermistor or digital temperature sensor arranged on the heat sink surface and the printed circuit board (PCB) to acquire the LED's operating temperature in real time; the perturbation injection unit periodically injects a narrow-band sine wave or square wave perturbation signal with an amplitude greater than the normal operating current into the LED when it is normally lit, and acquires the voltage drop and current changes of the LED before and after the injection, and uses a formula... The instantaneous small-signal internal resistance of the light-emitting diode is calculated; where, The instantaneous small-signal internal resistance of the light-emitting diode is... This represents the voltage change of the light-emitting diode. Let be the change in current of the LED; a preset temperature compensation coefficient is used to compensate for the instantaneous small-signal internal resistance of the LED at temperature, and the compensation formula is as follows: In the formula, The preset temperature compensation coefficient, This represents the temperature deviation between the current actual operating temperature and the reference temperature. This refers to the dynamic internal resistance of the LED. The preset temperature compensation coefficient can be pre-set based on experimental values. This coefficient directly reflects the linear relationship between the LED's instantaneous small-signal internal resistance and its operating temperature. Through this linear relationship, the instantaneous small-signal internal resistance of the LED affected by operating temperature disturbances is corrected to the true dynamic internal resistance of the LED at the reference temperature, thus preventing temperature fluctuations from being misjudged as LED aging.

[0069] Similarly, the drive current and drive voltage of the drive power supply are acquired through the current acquisition unit and voltage acquisition unit, respectively. Startup time refers to the time required for the drive voltage / drive current to rise from 0 to the normal operating threshold after the drive power supply is powered on; recovery time refers to the time required for the drive voltage / drive current to recover from its deviation from the normal operating threshold to the normal operating threshold after the drive power supply encounters a load disturbance. Startup time and recovery time are acquired simultaneously with the acquisition of drive voltage / drive current.

[0070] Figure 4 This is a flowchart illustrating another predictive maintenance method for a road lighting system provided by an embodiment of the present invention. This embodiment further refines the aforementioned embodiments. See also... Figure 4 Optionally, after step S110, the method further includes:

[0071] S310, preprocess the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp.

[0072] Specifically, a health monitoring module is integrated into each street light. This module filters, denoises, removes outliers, and compresses the first operating characteristic, the second operating characteristic, the environmental characteristics of the current environment, and the usage mode characteristics of the light. The health monitoring module then transmits the pre-processed first operating characteristic, second operating characteristic, environmental characteristics of the current environment, and usage mode characteristics to the edge / cloud platform 230 via communication module 220. The communication unit employs low-bandwidth wireless communication technology, which can be Narrow Band Internet of Things (NB-IoT), Long Range Wide Area Network (LoRaWAN), or 4G / 5G mobile communication technology; this invention does not limit the specific technology used.

[0073] Optionally, after step S130, the method further includes:

[0074] When the remaining lifespan of the S320 exceeds a preset threshold, it issues a command to derating the LED or driver power supply; when a lamp fault is detected, it issues an isolation command to isolate the faulty lamp.

[0075] The preset threshold can be set in advance based on the distribution of remaining lifespan.

[0076] Specifically, when the remaining lifespan exceeds a preset threshold, it indicates that the current aging level of the luminaire is controllable. However, continued full-load operation will accelerate aging. Therefore, a derating command is issued to extend the lifespan of the LEDs or driver power supply. The dynamic adjustment logic of the derating is not a one-time reduction. The hybrid prediction model recalculates the remaining lifespan every week. If the remaining lifespan extends to more than 1.5 times the preset threshold, some power is gradually restored; if the remaining lifespan remains near the preset threshold, the derating is maintained. Secondly, adjustments are made based on environmental characteristics—the derating is increased in high-temperature and salt spray environments, and decreased in normal-temperature environments, balancing lifespan and lighting effect. The operating status of the luminaire is monitored by a health monitoring module integrated inside each street light. When a luminaire malfunction is detected, an isolation command is issued to isolate the faulty luminaire, thereby preventing the impact on the lighting of the entire road section.

[0077] The criteria for determining whether each street light needs to be replaced are as follows:

[0078] Based on the pre-collected initial internal resistance of the LEDs of the newly installed lamps Calculate the relative rate of change of the dynamic internal resistance of the light-emitting diode over time. When the relative rate of change satisfies When the relative change rate reaches 15%, the system triggers a "light decay warning"; when the relative change rate meets the following conditions... When the light fixture's condition reaches 40%, it is determined that it needs to be replaced. Among these, , These are the first preset relative change rate threshold and the second preset relative change rate threshold, respectively. Both the first preset relative change rate threshold and the second preset relative change rate threshold can be preset based on empirical values.

[0079] The technical solution provided by this invention achieves real-time assessment of street light health status, prediction of remaining lifespan, and optimization of operation and maintenance by performing equal-weighted fusion analysis on the dynamic internal resistance of light-emitting diodes and the aging parameters of the driving power supply. This can effectively improve the reliability of urban lighting systems and reduce operation and maintenance costs. At the same time, it supports differentiated lifespan assessment and priority maintenance under harsh conditions such as high temperature, salt spray, and frequent power grid disturbances, providing intelligent operation and maintenance and energy efficiency optimization solutions for urban road lighting.

[0080] See also Figure 3The edge / cloud platform 230 of this device includes a data receiving and storage layer, an engineering layer, a hybrid predictive model layer, an operation and maintenance decision layer, and a security and management layer. The data receiving and storage layer receives and stores the first operating characteristics of the LEDs, the second operating characteristics of the driver power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire. The engineering layer further processes these characteristics to generate effective features that can be directly input into the model, such as performing a Fast Fourier Transform on the second operating characteristics of the driver power supply. The hybrid predictive model layer adopts a dual-branch architecture to determine the remaining lifespan of each street light based on the first operating characteristics of the LEDs, the second operating characteristics of the driver power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire, and maps the remaining lifespan to a standardized health score. The operation and maintenance decision layer uses a clustering algorithm to group the street lights based on the remaining lifespan, health score, and pre-stored geographical distribution and maintenance costs of each street light, generating a regionalized maintenance task list with priorities and an optimal inspection route. The security and management layer encrypts all data to ensure its integrity and security. (Continue to see...) Figure 3 The device also includes a monitoring and visualization module 260, which is used to display the following information on a map based on a Geographic Information System (GIS): the remaining lifespan of the streetlights, health score, geographical distribution, health level (A / B / C / D), and the progress of maintenance work orders.

[0081] Figure 5 A schematic diagram of the structure of another predictive maintenance device for streetlights provided in an embodiment of the present invention is shown below. Figure 5 The device includes an acquisition module 410, a determination module 420, and a generation module 430.

[0082] The acquisition module 410 is used to acquire the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp.

[0083] The determination module 420 is used to determine the remaining lifespan of each street light based on a pre-built hybrid prediction model, according to the first operating characteristics of the pre-processed light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp. The remaining lifespan is then mapped to a standardized health score.

[0084] The generation module 430 is used to group streetlights using a clustering algorithm based on the health score, remaining lifespan, and pre-stored geographical distribution and maintenance cost of each streetlight, and generate a regionalized maintenance task list with priority and the optimal inspection route.

[0085] The predictive maintenance device for streetlights provided in this embodiment of the invention can execute the predictive maintenance method for streetlights provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method, which will not be elaborated here.

[0086] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0087] At least one processor; and a memory communicatively connected to the at least one processor; wherein,

[0088] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform a predictive maintenance device method for streetlights provided in any embodiment of the present invention.

[0089] Figure 6 This is a schematic diagram of an electronic device for a predictive maintenance method for streetlights provided in an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0090] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, the ROM 12, and the RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0091] Multiple components in electronic device 10 are connected to input / output I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0092] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a predictive maintenance method for streetlights.

[0093] In some embodiments, a predictive maintenance method for a street light may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 10 via read-only memory ROM 12 and / or communication unit 19. When the computer program is loaded into random access memory RAM 13 and executed by processor 11, one or more steps of the predictive maintenance method for a street light described above may be performed. Alternatively, in other embodiments, processor 11 may be configured in any other suitable manner to perform a predictive maintenance method for a street light.

[0094] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0095] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0096] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0097] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to a user; and a keyboard and pointing device through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with a user; for example, feedback provided to the user can be any form of sensory feedback; and input from the user can be received in any form.

[0098] The systems and technologies described herein can be implemented in computing systems that include backend components, middleware components, or frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0099] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0100] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0101] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A predictive maintenance method for a street light, the street light comprising a luminaire and a pole, the luminaire comprising a lamp panel and a driver power supply, the lamp panel having light-emitting diodes mounted thereon, characterized in that, The method includes: Acquire the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire; Based on the first operating characteristics of the pre-processed light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp, the remaining lifespan of each street lamp is determined based on a pre-built hybrid prediction model, and the remaining lifespan is mapped to a standardized health score. Based on the health score, remaining lifespan, and pre-stored geographical distribution and maintenance cost of each street light, a clustering algorithm is used to group the street lights, generating a regionalized maintenance task list with priorities and an optimal inspection route.

2. The method according to claim 1, characterized in that, The first operating characteristics of the light-emitting diode include the operating voltage, operating current, operating temperature, and dynamic internal resistance of the light-emitting diode calculated based on the operating voltage, the operating current, and the operating temperature; The second operating characteristics of the drive power supply include the drive voltage, drive current, start-up time, and recovery time of the drive power supply, as well as the output ripple and total harmonic distortion of the drive power supply calculated based on the drive voltage. The environmental characteristics include solar radiation intensity, relative humidity, and ambient temperature; The usage pattern characteristics include average daily lighting duration, number of switching operations, and count of frequent start-stop events.

3. The method according to claim 2, characterized in that, The dynamic internal resistance of the LED is calculated as follows: Under normal LED illumination, a narrow-band sinusoidal or square-wave perturbation signal with an amplitude greater than the normal operating current is injected into the LED. The voltage drop and current changes of the LED before and after the injection are collected, and the result is calculated using the formula... The instantaneous small-signal internal resistance of the light-emitting diode is calculated; where, The instantaneous small-signal internal resistance of the light-emitting diode is... This represents the voltage change of the light-emitting diode. This represents the change in current of the light-emitting diode; The instantaneous small-signal internal resistance of the LED is compensated for using a preset temperature compensation coefficient. The compensation formula is as follows: In the formula, The preset temperature compensation coefficient, This represents the temperature deviation between the current actual operating temperature and the reference temperature. This represents the dynamic internal resistance of the light-emitting diode.

4. The method according to claim 2, characterized in that, The hybrid prediction model is a dual-branch fusion architecture, including a timing branch and a structured branch; the timing branch uses a long short-term memory network to model the dynamic internal resistance of the light-emitting diode and the output ripple of the driving power supply. The structured branch uses gradient boosting trees or random forests to perform correlation analysis on environmental features and usage pattern features. The outputs of the two branches are integrated to determine the remaining lifespan of each street light and map the remaining lifespan to a standardized health score.

5. The method according to claim 1, characterized in that, The clustering algorithm is either the DBSCAN algorithm or the K-means algorithm, and the optimal inspection route is planned and generated using an improved genetic algorithm or a weighted Dijkstra algorithm.

6. The method according to claim 1, characterized in that, The hybrid prediction model is adaptively updated by combining actual failure events in the field through a pre-deployed incremental learning mechanism.

7. The method according to claim 1, characterized in that, After grouping the streetlights using a clustering algorithm based on their health score, remaining lifespan, and pre-stored geographical distribution and maintenance costs, and generating a prioritized regional maintenance task list and optimal inspection routes, the process further includes: When the remaining lifespan is greater than a preset threshold, a command is issued to derating the LED or driver power supply; when a lamp fault is detected, an isolation command is issued to isolate the faulty lamp.

8. The method according to claim 1, characterized in that, After obtaining the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire, the following are also included: The first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the luminaire, and the usage mode characteristics of the luminaire are preprocessed.

9. A predictive maintenance device for a street light, the street light comprising a luminaire and a pole, the luminaire comprising a lamp panel and a driver power supply, the lamp panel having light-emitting diodes mounted thereon, characterized in that, For performing the predictive maintenance method for streetlights as described in any one of claims 1-8, the apparatus comprises: The acquisition module is used to acquire the first operating characteristics of the light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp. The determination module is used to determine the remaining lifespan of each street light based on a pre-built hybrid prediction model, according to the first operating characteristics of the pre-processed light-emitting diode, the second operating characteristics of the driving power supply, the environmental characteristics of the current environment of the lamp, and the usage mode characteristics of the lamp, and to map the remaining lifespan to a standardized health score. The generation module is used to group streetlights using a clustering algorithm based on the health score, remaining lifespan, and pre-stored geographical distribution and maintenance cost of each streetlight, and generate a regionalized maintenance task list with priorities and an optimal inspection route.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the predictive maintenance method for streetlights according to any one of claims 1-8.

Images