A method and system for predictive maintenance of a lighting device

Abstract

The application provides a predictive maintenance method and system for a lighting device, comprising: constructing a lighting work rule of the lighting device according to a plurality of real-time parameter information of the lighting device, determining a plurality of normal working time periods of the lighting device, using an autoregressive model to predict historical working data corresponding to each normal working time period, determining a predicted remaining life of the lighting device, constructing a real-time working damage of the lighting device using the real-time parameter information, determining a cumulative damage feature corresponding to each lighting device in the lighting device, marking a device full damage time corresponding to each lighting device in the predicted remaining life, determining a device maintenance time corresponding to each lighting device, and performing predictive maintenance on the lighting device by monitoring the lighting device, so that the failure time period and the failed device of the lamp can be predicted, workers can replace the device in advance, and the risk of lighting loss is reduced.

Description

Technical Field

[0001] This invention relates to the field of lighting maintenance technology, and in particular to a predictive maintenance method and system for lighting devices. Background Technology

[0002] In recent years, with economic growth, my country's urban lighting technology and scale have developed rapidly. Lighting devices are no longer just simple lighting fixtures; most are equipped with lighting controllers and have functions such as electronic switches and sensor dimming. While lighting controllers are widely used, monitoring their malfunctions still relies on whether the lighting is "on" or "off," making it difficult to effectively diagnose faults. Generally, regular manual inspections along the lines by specialized personnel are used to manually pinpoint the fault location for maintenance and repair. However, this method is inefficient and costly, and maintenance personnel often struggle to detect controller malfunctions promptly. Even when a fault is found, it's difficult to quickly determine the type of fault, such as a lighting device malfunction, a controller malfunction, or a power line malfunction. This often leads to untimely maintenance, resulting in partial lighting loss and inconvenience for residents.

[0003] Therefore, the present invention provides a predictive maintenance method and system for lighting devices. Summary of the Invention

[0004] This invention provides a predictive maintenance method and system for lighting devices. By monitoring the lighting devices and performing predictive maintenance, the system predicts the time period of failure and the faulty components, allowing workers to replace components in advance and reducing the risk of lighting outages.

[0005] This invention provides a predictive maintenance method for lighting devices, comprising:

[0006] Step 1: Based on several real-time parameter information of the lighting device, construct the lighting operation pattern of the lighting device and determine several normal working time periods of the lighting device;

[0007] Step 2: Use an autoregressive model to predict the historical working data corresponding to each of the normal working time periods to obtain the remaining normal working times of the lighting device;

[0008] Step 3: Derive the predicted remaining lifespan of the lighting device, construct the real-time operational damage of the lighting device using the real-time parameter information, and determine the cumulative damage characteristics corresponding to each lighting component in the lighting device;

[0009] Step 4: Based on the cumulative damage characteristics, mark the device total loss time corresponding to each lighting device in the predicted remaining life, and determine the device maintenance time corresponding to each lighting device.

[0010] In one feasible approach

[0011] Step 1 includes:

[0012] Step 11: Transmit the real-time parameter information of the lighting device through the communication network, encode the real-time parameter information in the application layer of the communication network to obtain the real-time application data of the lighting device, identify the first byte of the real-time application data, and construct the real-time data features of the lighting device based on the data content contained in the first byte of data.

[0013] Step 12: Identify the second byte of the real-time application data, construct the key byte value of the real-time application data based on the first byte and the second byte, use AI technology to perform type matching on the key byte value to determine the device attribute of the lighting device, and perform data calibration on the real-time application data based on the legal data packet type of the device attribute to obtain the real-time valid data of the lighting device;

[0014] Step 13: Normalize the real-time valid data corresponding to different times, sort the normalized data according to the time order, perform linear analysis on the sorting results to obtain the data linear relationship of the lighting device, identify several lighting segments of the lighting device in the data linear relationship, and construct the lighting working law of the lighting device.

[0015] Step 14: Map the lighting operation pattern to time space to obtain several historical lighting time periods of the lighting device. Perform fuzzing processing on the lighting start time corresponding to each historical lighting time period to obtain the fuzzy lighting start point corresponding to each historical lighting time period, and determine several normal operating time periods of the lighting device.

[0016] In one feasible approach

[0017] Also includes:

[0018] The lighting duration of the corresponding historical lighting time period is determined based on each lighting start time, and the historical average lighting duration of the lighting device is determined.

[0019] The adjustable duration corresponding to each of the historical lighting time periods is determined based on the historical average lighting duration.

[0020] Within the adjustable duration range, the corresponding lighting start point is blurred to obtain the blurred lighting start point corresponding to the historical lighting time period.

[0021] In one feasible approach

[0022] Step 2 includes:

[0023] Step 21: Use the autoregressive model to perform autocorrelation calculations on each of the historical working data, determine the current order threshold of the autoregressive model, and adjust the initial window length according to the current order threshold to obtain the effective window function of the lighting device;

[0024] Step 22: Apply the window function to each of the historical working data to obtain several optimized lighting time periods of the lighting device. Feed the optimized lighting time periods back into the autoregressive model for model fitting to obtain the autoregressive coefficients of the lighting device.

[0025] Step 23: Perform regression prediction on historical working data based on the autoregressive coefficients to obtain several predicted lighting times of the lighting device. Determine the failure lighting time period of the lighting device based on the predicted lighting effect characteristics corresponding to each predicted lighting time, and determine the remaining number of normal working times of the lighting device.

[0026] In one feasible approach

[0027] Also includes:

[0028] After obtaining the autoregressive coefficients, residual identification is performed on the autoregressive model to obtain the residual value of the autoregressive model;

[0029] When there is an autocorrelation relationship between the residual value and the historical working data, the current order of the autoregressive model is corrected using the residual value to obtain an updated autoregressive model;

[0030] The updated autoregressive model is used to fit the optimized lighting time period, and the autoregressive coefficients are updated based on the fitting results.

[0031] In one feasible approach

[0032] Step 3 includes:

[0033] Step 31: Map the remaining constant operating times to the lighting operating rules, expand the lighting operating rules according to the mapping position corresponding to each remaining constant operating time, and determine the predicted remaining lifespan of the lighting device according to the expansion length;

[0034] Step 32: Reconstruct the real-time lighting state of the lighting device based on the real-time parameter information, construct the cumulative lighting state of the lighting device, deduce the historical cumulative damage of the lighting device based on the cumulative lighting state, and determine the increased damage of the historical cumulative damage based on the real-time lighting state;

[0035] Step 33: Based on the damage attributes of the increased damage, identify and count the number of damages with the same attributes contained in the historical cumulative damage, and use the number of damages with the same attributes to enhance the damage attributes to determine the real-time operational damage of the increased damage to the lighting device.

[0036] Step 34: Use the real-time working damage to simulate the damage of the lighting device, determine the damage location corresponding to each lighting moment and the damage value corresponding to each damage location, and determine the cumulative damage characteristics of each lighting device in the lighting device.

[0037] In one feasible approach

[0038] Step 4 includes:

[0039] Step 41: Construct a damage lighting model of the lighting device based on the initial device parameters corresponding to each lighting device and the cumulative damage characteristics, and run the damage lighting model to determine the device operating parameters corresponding to each lighting device;

[0040] Step 42: Use the device operating parameters to deduce the device total loss time corresponding to the lighting device, mark the device total loss time in the predicted remaining lifetime, and determine the total loss consequence of each lighting device based on the device attributes corresponding to each lighting device;

[0041] Step 43: Assign a first device sorting order to the lighting devices according to the order of total loss consequences from high to low, assign a second device sorting order to the lighting devices according to the order of total loss times from near to far, and reorder the lighting devices according to the first device sorting order and the second device sorting order;

[0042] Step 44: Feed the sorting results back into the predicted remaining lifespan to determine the device maintenance time corresponding to each of the lighting devices, and generate and display the corresponding maintenance list.

[0043] In one feasible approach

[0044] Also includes:

[0045] Obtain the real-time device status corresponding to each of the aforementioned lighting devices;

[0046] Target lighting devices with abnormal real-time device status are selected, and the target lighting devices are ranked first. An emergency maintenance warning is generated and a corresponding alarm is triggered.

[0047] This invention provides a predictive maintenance system for lighting devices, comprising:

[0048] The pattern analysis module is used to construct the lighting operation pattern of the lighting device based on several real-time parameter information of the lighting device, and to determine several normal working time periods of the lighting device.

[0049] The prediction execution module is used to predict the historical working data corresponding to each of the normal working time periods using an autoregressive model, so as to obtain the remaining normal working number of the lighting device.

[0050] The damage derivation module is used to derive the predicted remaining lifespan of the lighting device, construct the real-time operational damage of the lighting device using the real-time parameter information, and determine the cumulative damage characteristics corresponding to each lighting component in the lighting device.

[0051] The maintenance assistance module is used to mark the device total loss time corresponding to each of the lighting devices in the predicted remaining life according to the cumulative damage characteristics, and to determine the device maintenance time corresponding to each lighting device.

[0052] In one feasible approach

[0053] The pattern analysis module includes:

[0054] The first analysis unit is used to transmit real-time parameter information of the lighting device through a communication network, encode the real-time parameter information in the application layer of the communication network to obtain real-time application data of the lighting device, identify the first byte of data of the real-time application data, and construct the real-time data features of the lighting device based on the data content contained in the first byte of data.

[0055] The second analysis unit is used to identify the second byte data of the real-time application data, construct the key byte value of the real-time application data based on the first byte data and the second byte data, use AI technology to perform type matching on the key byte value to determine the device attribute of the lighting device, and perform data calibration on the real-time application data based on the legal data packet type of the device attribute to obtain the real-time valid data of the lighting device.

[0056] The third analysis unit is used to normalize the real-time effective data corresponding to different times, sort the normalized data according to the time order, perform linear analysis on the sorting results to obtain the data linear relationship of the lighting device, identify several lighting segments of the lighting device in the data linear relationship, and construct the lighting working law of the lighting device.

[0057] The fourth analysis unit is used to map the lighting operation pattern into time space to obtain several historical lighting time periods of the lighting device, perform fuzzification processing on the lighting start time corresponding to each historical lighting time period to obtain the fuzzy lighting start point corresponding to each historical lighting time period, and determine several normal operating time periods of the lighting device.

[0058] The beneficial effects of the above technical solution are as follows: In order to improve the efficiency of workers in maintaining lighting devices and enhance the effectiveness of lighting devices in operation, real-time parameter information of the lighting devices is collected daily to deduce the lighting operation patterns and determine the normal operating time periods of the lighting devices. Then, an autoregressive model is used to analyze historical operating data, and the predictive function of the natural regression model is used to determine the remaining normal operating times of the lighting devices. By combining the known lighting operation patterns, the predicted remaining lifespan of the lighting devices can be derived. At the same time, real-time operational damage of the lighting devices is analyzed based on real-time parameter information. By determining the cumulative damage characteristics of each lighting component in the lighting device, the time of total failure of the lighting component is derived. Finally, the maintenance time of each lighting component is determined. In this way, workers can quickly determine the location and type of failure that is about to occur in the lighting device, thereby intervening in maintenance in advance, reducing the cost of large-scale maintenance later, and bringing long-term convenience to residents and pedestrians within the lighting range.

[0059] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0060] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0061] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0062] Figure 1 This is a schematic diagram of the workflow of a predictive maintenance method for lighting devices according to an embodiment of the present invention;

[0063] Figure 2 This is a schematic diagram of the composition of a predictive maintenance system for lighting devices according to an embodiment of the present invention. Detailed Implementation

[0064] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0065] Example 1

[0066] This embodiment provides a predictive maintenance method for lighting devices, such as... Figure 1 As shown, it includes:

[0067] Step 1: Based on several real-time parameter information of the lighting device, construct the lighting operation pattern of the lighting device and determine several normal working time periods of the lighting device;

[0068] Step 2: Use an autoregressive model to predict the historical working data corresponding to each of the normal working time periods to obtain the remaining normal working times of the lighting device;

[0069] Step 3: Derive the predicted remaining lifespan of the lighting device, construct the real-time operational damage of the lighting device using the real-time parameter information, and determine the cumulative damage characteristics corresponding to each lighting component in the lighting device;

[0070] Step 4: Based on the cumulative damage characteristics, mark the device total loss time corresponding to each lighting device in the predicted remaining life, and determine the device maintenance time corresponding to each lighting device.

[0071] In this example, the real-time parameter information includes: information consisting of the operating current, operating voltage, operating temperature, operating duration, and operating humidity of each lighting device at the current moment;

[0072] In this example, the "regular working period" refers to the period during which the lighting fixture is frequently illuminated, for example: the lighting fixture starts illuminating at 19:00 every day and ends at 06:30 the next day;

[0073] In this example, the lighting operation pattern refers to the lighting operation pattern of the lighting device over a 30*24 hour period;

[0074] In this example, the remaining number of constant operating cycles represents the number of times the lighting device can complete the illumination during the constant operating period;

[0075] In this example, real-time operational damage refers to the damage to the lighting device caused by external environmental influences and its own operation.

[0076] In this example, the moment of total device failure indicates the moment when the lighting device becomes unusable.

[0077] In this example, the device maintenance time refers to a time before the total failure of the lighting device, and not any time within the normal operating period.

[0078] The working principle and beneficial effects of the above technical solution are as follows: To improve the efficiency of workers maintaining lighting devices and enhance the effectiveness of lighting operation, real-time parameter information of the lighting devices is collected daily to deduce their lighting operation patterns and determine their normal operating time periods. Then, an autoregressive model is used to analyze historical operating data, and the predictive function of the natural regression model is used to determine the remaining normal operating times of the lighting devices. This, combined with known lighting operation patterns, allows for the deduction of the predicted remaining lifespan of the lighting devices. Simultaneously, real-time operational damage to the lighting devices is analyzed based on real-time parameter information. By determining the cumulative damage characteristics of each lighting component, the time of total failure of each component is deduced. Finally, the maintenance time for each component is determined. This method helps workers quickly identify the location and type of impending failure in the lighting devices, enabling early intervention and maintenance, reducing the cost of large-scale maintenance later, and providing long-term convenience to residents and pedestrians within the lighting area.

[0079] Example 2

[0080] Based on Embodiment 1, the predictive maintenance method for lighting devices, step 1 includes:

[0081] Step 11: Transmit the real-time parameter information of the lighting device through the communication network, encode the real-time parameter information in the application layer of the communication network to obtain the real-time application data of the lighting device, identify the first byte of the real-time application data, and construct the real-time data features of the lighting device based on the data content contained in the first byte of data.

[0082] Step 12: Identify the second byte of the real-time application data, construct the key byte value of the real-time application data based on the first byte and the second byte, use AI technology to perform type matching on the key byte value to determine the device attribute of the lighting device, and perform data calibration on the real-time application data based on the legal data packet type of the device attribute to obtain the real-time valid data of the lighting device;

[0083] Step 13: Normalize the real-time valid data corresponding to different times, sort the normalized data according to the time order, perform linear analysis on the sorting results to obtain the data linear relationship of the lighting device, identify several lighting segments of the lighting device in the data linear relationship, and construct the lighting working law of the lighting device.

[0084] Step 14: Map the lighting operation pattern to time space to obtain several historical lighting time periods of the lighting device. Perform fuzzing processing on the lighting start time corresponding to each historical lighting time period to obtain the fuzzy lighting start point corresponding to each historical lighting time period, and determine several normal operating time periods of the lighting device.

[0085] In this example, the communication network refers to the network used when transmitting real-time parameter information to a remote terminal;

[0086] In this example, real-time application data represents real-time parameter information processed by the application layer;

[0087] In this example, the first byte of data represents the data contained in the first byte of the real-time application data, and the second byte of data represents the data contained in the second byte of the real-time application data;

[0088] In this example, the real-time data features represent the characteristics of the data content contained in the first byte of data;

[0089] In this example, device attributes represent the properties that the lighting device exhibits when it is performing lighting operations;

[0090] In this example, the valid data packet type indicates the types of data packets that the device attributes can identify and that can be generated;

[0091] In this example, the historical lighting time period refers to the time period during which the lighting device performed its lighting function;

[0092] In this example, the fuzzy lighting start point represents the result of extending the time of the lighting start point within the historical lighting time period.

[0093] The working principle and beneficial effects of the above technical solution are as follows: In order to better maintain the lighting device, it is necessary to first determine the working pattern of the lighting device and analyze whether it will malfunction based on the working pattern. First, the real-time parameter information is encoded using the application layer of the communication network to obtain the real-time application data of the lighting device. Then, the first and second bytes of data in the real-time application data are analyzed and calibrated multiple times to derive the real-time effective data of the lighting device. Furthermore, the real-time effective data corresponding to different times are standardized and sorted. Based on the linear relationship of the data shown by the sorting results, several lighting segments of the lighting device are determined, generating the lighting working pattern of the lighting device. Since the lighting time period of the lighting device may change, the lighting start time of the lighting device is fuzzyened. Finally, several normal working time periods of the lighting device are determined. In this way, the data generated by the lighting device can be processed reasonably, and the normal working time periods of the lighting device can be determined, improving the efficiency and quality of subsequent prediction and maintenance.

[0094] Example 3

[0095] Based on Embodiment 2, the predictive maintenance method for lighting devices further includes:

[0096] The lighting duration of the corresponding historical lighting time period is determined based on each lighting start time, and the historical average lighting duration of the lighting device is determined.

[0097] The adjustable duration corresponding to each of the historical lighting time periods is determined based on the historical average lighting duration.

[0098] Within the adjustable duration range, the corresponding lighting start point is blurred to obtain the blurred lighting start point corresponding to the historical lighting time period.

[0099] The working principle and beneficial effects of the above technical solution are as follows: In order to avoid the fuzzy lighting starting point deviating too much from the original lighting starting point, the adjustable duration of each historical lighting time period is determined by using the historical average lighting duration, thereby performing fuzzy processing and ensuring the effectiveness of the simulated lighting starting point.

[0100] Example 4

[0101] Based on Example 1, the predictive maintenance method for lighting devices, step 2 includes:

[0102] Step 21: Use the autoregressive model to perform autocorrelation calculations on each of the historical working data, determine the current order threshold of the autoregressive model, and adjust the initial window length according to the current order threshold to obtain the effective window function of the lighting device;

[0103] Step 22: Apply the window function to each of the historical working data to obtain several optimized lighting time periods of the lighting device. Feed the optimized lighting time periods back into the autoregressive model for model fitting to obtain the autoregressive coefficients of the lighting device.

[0104] Step 23: Perform regression prediction on historical working data based on the autoregressive coefficients to obtain several predicted lighting times of the lighting device. Determine the failure lighting time period of the lighting device based on the predicted lighting effect characteristics corresponding to each predicted lighting time, and determine the remaining number of normal working times of the lighting device.

[0105] In this example, autocorrelation calculation represents the process of analyzing the logical relationships between time series.

[0106] In this example, the current order threshold represents the value of the current order of the autoregressive model;

[0107] In this example, the initial window length represents the window length of the initial window function.

[0108] The working principle and beneficial effects of the above technical solution are as follows: By using an autoregressive model to perform autocorrelation calculations on historical working data, the current order threshold of the autoregressive model is determined. The window length of the initial window function is then adjusted using this current order threshold to determine the effective window function of the lighting device. Furthermore, the effective window function is used to window the historical working data to obtain the optimized lighting time period of the lighting device. This optimized time period is then fed back into the autoregressive model for model fitting to obtain the autoregressive coefficients of the lighting device. The autoregressive coefficients are then used to perform regression prediction on the historical working data, determining several predicted lighting times and corresponding predicted lighting effect characteristics of the lighting device. This allows for easy determination of the lighting device's ineffective lighting time period and derivation of the remaining normal operating frequency of the lighting device. In this way, effective information in the historical working data can be separated, and the predictive function of the autoregressive model and the function of the window function to improve data resolution are utilized to predict the lighting device. Finally, the remaining normal operating frequency of the lighting device is derived, achieving the purpose of preliminary prediction.

[0109] Example 5

[0110] Based on Example 4, the predictive maintenance method for lighting devices further includes:

[0111] After obtaining the autoregressive coefficients, residual identification is performed on the autoregressive model to obtain the residual value of the autoregressive model;

[0112] When there is an autocorrelation relationship between the residual value and the historical working data, the current order of the autoregressive model is corrected using the residual value to obtain an updated autoregressive model;

[0113] The updated autoregressive model is used to fit the optimized lighting time period, and the autoregressive coefficients are updated based on the fitting results.

[0114] In this example, the residual represents the difference between the predicted value and the actual value of the autoregressive model.

[0115] The working principle and beneficial effects of the above technical solution are as follows: Since the daily operation of the lighting device may be different, the prediction work may be biased. When there is an autocorrelation relationship between the residuals in the autoregressive model and the historical working data, the current order of the autoregressive model is corrected, and then the autoregressive coefficients of the lighting device are updated. Through continuous optimization and training, the accuracy of the prediction is improved.

[0116] Example 6

[0117] Based on Example 1, the predictive maintenance method for lighting devices, step 3 includes:

[0118] Step 31: Map the remaining constant operating times to the lighting operating rules, expand the lighting operating rules according to the mapping position corresponding to each remaining constant operating time, and determine the predicted remaining lifespan of the lighting device according to the expansion length;

[0119] Step 32: Reconstruct the real-time lighting state of the lighting device based on the real-time parameter information, construct the cumulative lighting state of the lighting device, deduce the historical cumulative damage of the lighting device based on the cumulative lighting state, and determine the increased damage of the historical cumulative damage based on the real-time lighting state;

[0120] Step 33: Based on the damage attributes of the increased damage, identify and count the number of damages with the same attributes contained in the historical cumulative damage, and use the number of damages with the same attributes to enhance the damage attributes to determine the real-time operational damage of the increased damage to the lighting device.

[0121] Step 34: Use the real-time working damage to simulate the damage of the lighting device, determine the damage location corresponding to each lighting moment and the damage value corresponding to each damage location, and determine the cumulative damage characteristics of each lighting device in the lighting device.

[0122] In this example, the real-time lighting state represents the current state of the lighting device, while the cumulative lighting state represents the state presented after multiple real-time lighting states are superimposed.

[0123] In this example, the added damage represents the effect of real-time lighting status on historical cumulative damage;

[0124] In this example, damage with the same attribute refers to damage with the same attribute as the damage added in the historical cumulative damage.

[0125] In this example, the cumulative damage feature represents the characteristics of a lighting device after long-term damage.

[0126] The working principle and beneficial effects of the above technical solution are as follows: By mapping the remaining number of normal working cycles to the lighting working pattern, the predicted remaining lifespan of the lighting device is analyzed. Then, real-time parameter information is used to reconstruct the real-time lighting state and cumulative lighting state of the lighting device to deduce the historical cumulative damage of the lighting device and determine the increase in historical cumulative damage. By identifying the number of damages of the same attribute contained in the historical cumulative damage, the real-time working damage of the lighting device is analyzed. In order to ensure the effectiveness of the derivation process, the damage location and damage value at each lighting moment are analyzed by modeling. Finally, the cumulative damage characteristics of each lighting device are obtained. In this way, the lighting device can be monitored for a long time, and the damage characteristics of each lighting device can be determined, which improves the efficiency of later maintenance.

[0127] Example 7

[0128] Based on Example 1, the predictive maintenance method for lighting devices, step 4 includes:

[0129] Step 41: Construct a damage lighting model of the lighting device based on the initial device parameters corresponding to each lighting device and the cumulative damage characteristics, and run the damage lighting model to determine the device operating parameters corresponding to each lighting device;

[0130] Step 42: Use the device operating parameters to deduce the device total loss time corresponding to the lighting device, mark the device total loss time in the predicted remaining lifetime, and determine the total loss consequence of each lighting device based on the device attributes corresponding to each lighting device;

[0131] Step 43: Assign a first device sorting order to the lighting devices according to the order of total loss consequences from high to low, assign a second device sorting order to the lighting devices according to the order of total loss times from near to far, and reorder the lighting devices according to the first device sorting order and the second device sorting order;

[0132] Step 44: Feed the sorting results back into the predicted remaining lifespan to determine the device maintenance time corresponding to each of the lighting devices, and generate and display the corresponding maintenance list.

[0133] In this example, the first device sorting represents the result of sorting the lighting devices from high to low according to the severity of the consequences of total loss, while the second device sorting represents the result of sorting them from near to far according to the time of total loss.

[0134] The working principle and beneficial effects of the above technical solution are as follows: By using model technology to analyze the operating parameters of each lighting device, and sorting the lighting devices from multiple perspectives, the maintenance time of each lighting device is determined, and finally a corresponding maintenance list is generated. In this way, technical references can be provided to workers to assist them in maintaining the lighting devices.

[0135] Example 8

[0136] Based on Example 7, the predictive maintenance method for lighting devices further includes:

[0137] Obtain the real-time device status corresponding to each of the aforementioned lighting devices;

[0138] Target lighting devices with abnormal real-time device status are selected, and the target lighting devices are ranked first. An emergency maintenance warning is generated and a corresponding alarm is triggered.

[0139] The working principle and beneficial effects of the above technical solution are as follows: When a lighting device suddenly fails, it is prioritized and an alarm is triggered to remind workers to prioritize the maintenance of that lighting device.

[0140] Example 9

[0141] This embodiment provides a predictive maintenance system for lighting devices, such as Figure 2 As shown, it includes:

[0142] The pattern analysis module is used to construct the lighting operation pattern of the lighting device based on several real-time parameter information of the lighting device, and to determine several normal working time periods of the lighting device.

[0143] The prediction execution module is used to predict the historical working data corresponding to each of the normal working time periods using an autoregressive model, so as to obtain the remaining normal working number of the lighting device.

[0144] The damage derivation module is used to derive the predicted remaining lifespan of the lighting device, construct the real-time operational damage of the lighting device using the real-time parameter information, and determine the cumulative damage characteristics corresponding to each lighting component in the lighting device.

[0145] The maintenance assistance module is used to mark the device total loss time corresponding to each of the lighting devices in the predicted remaining life according to the cumulative damage characteristics, and to determine the device maintenance time corresponding to each lighting device.

[0146] In this example, the real-time parameter information includes: information consisting of the operating current, operating voltage, operating temperature, operating duration, and operating humidity of each lighting device at the current moment;

[0147] In this example, the "regular working period" refers to the period during which the lighting fixture is frequently illuminated, for example: the lighting fixture starts illuminating at 19:00 every day and ends at 06:30 the next day;

[0148] In this example, the lighting operation pattern refers to the lighting operation pattern of the lighting device over a 30*24 hour period;

[0149] In this example, the remaining number of constant operating cycles represents the number of times the lighting device can complete the illumination during the constant operating period;

[0150] In this example, real-time operational damage refers to the damage to the lighting device caused by external environmental influences and its own operation.

[0151] In this example, the moment of total device failure indicates the moment when the lighting device becomes unusable.

[0152] In this example, the device maintenance time refers to a time before the total failure of the lighting device, and not any time within the normal operating period.

[0153] The working principle and beneficial effects of the above technical solution are as follows: To improve the efficiency of workers maintaining lighting devices and enhance the effectiveness of lighting operation, real-time parameter information of the lighting devices is collected daily to deduce the lighting operation patterns and determine the normal operating time periods. Then, an autoregressive model is used to analyze historical operating data, and the predictive function of the natural regression model is used to determine the remaining normal operating times of the lighting devices. This, combined with the known lighting operation patterns, allows for the deduction of the predicted remaining lifespan of the lighting devices. Simultaneously, real-time operational damage to the lighting devices is analyzed based on real-time parameter information. By determining the cumulative damage characteristics of each lighting component, the time of total failure of the lighting components is deduced. Finally, the maintenance time for each lighting component is determined. This method helps workers quickly identify the location and type of impending failure in the lighting devices, enabling early intervention and maintenance, reducing the cost of large-scale maintenance later, and providing long-term convenience to residents and pedestrians within the lighting area.

[0154] Example 10

[0155] Based on Example 9, the predictive maintenance system for lighting devices, wherein the pattern analysis module includes:

[0156] The first analysis unit is used to transmit real-time parameter information of the lighting device through a communication network, encode the real-time parameter information in the application layer of the communication network to obtain real-time application data of the lighting device, identify the first byte of data of the real-time application data, and construct the real-time data features of the lighting device based on the data content contained in the first byte of data.

[0157] The second analysis unit is used to identify the second byte data of the real-time application data, construct the key byte value of the real-time application data based on the first byte data and the second byte data, use AI technology to perform type matching on the key byte value to determine the device attribute of the lighting device, and perform data calibration on the real-time application data based on the legal data packet type of the device attribute to obtain the real-time valid data of the lighting device.

[0158] The third analysis unit is used to normalize the real-time effective data corresponding to different times, sort the normalized data according to the time order, perform linear analysis on the sorting results to obtain the data linear relationship of the lighting device, identify several lighting segments of the lighting device in the data linear relationship, and construct the lighting working law of the lighting device.

[0159] The fourth analysis unit is used to map the lighting operation pattern into time space to obtain several historical lighting time periods of the lighting device, perform fuzzification processing on the lighting start time corresponding to each historical lighting time period to obtain the fuzzy lighting start point corresponding to each historical lighting time period, and determine several normal operating time periods of the lighting device.

[0160] In this example, the communication network refers to the network used when transmitting real-time parameter information to a remote terminal;

[0161] In this example, real-time application data represents real-time parameter information processed by the application layer;

[0162] In this example, the first byte of data represents the data contained in the first byte of the real-time application data, and the second byte of data represents the data contained in the second byte of the real-time application data;

[0163] In this example, the real-time data features represent the characteristics of the data content contained in the first byte of data;

[0164] In this example, device attributes represent the properties that the lighting device exhibits when it is performing lighting operations;

[0165] In this example, the valid data packet type indicates the types of data packets that the device attributes can identify and that can be generated;

[0166] In this example, the historical lighting time period refers to the time period during which the lighting device performed its lighting function;

[0167] In this example, the fuzzy lighting start point represents the result of extending the time of the lighting start point within the historical lighting time period.

[0168] The working principle and beneficial effects of the above technical solution are as follows: In order to better maintain the lighting device, it is necessary to first determine the working pattern of the lighting device and analyze whether it will malfunction based on the working pattern. First, the real-time parameter information is encoded using the application layer of the communication network to obtain the real-time application data of the lighting device. Then, the first and second bytes of data in the real-time application data are analyzed and calibrated multiple times to derive the real-time effective data of the lighting device. Furthermore, the real-time effective data corresponding to different times are standardized and sorted. Based on the linear relationship of the data shown by the sorting results, several lighting segments of the lighting device are determined, generating the lighting working pattern of the lighting device. Since the lighting time period of the lighting device may change, the lighting start time of the lighting device is fuzzyened. Finally, several normal working time periods of the lighting device are determined. In this way, the data generated by the lighting device can be processed reasonably, and the normal working time periods of the lighting device can be determined, improving the efficiency and quality of subsequent prediction and maintenance.

[0169] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for predictive maintenance of a lighting device, characterized in that, The application relates to a lighting device life prediction method, comprising the following steps: Step 1: constructing a lighting work rule of the lighting device according to a plurality of real-time parameter information of the lighting device, determining a plurality of normal working time periods of the lighting device; Step 2: predicting historical working data corresponding to each normal working time period by using an autoregressive model to obtain a remaining normal working time of the lighting device; Step 3: deriving a predicted remaining life of the lighting device, constructing a real-time working damage of the lighting device by using the real-time parameter information, and determining a cumulative damage feature corresponding to each lighting device in the lighting device; Step 4: marking a device total damage time of each lighting device corresponding to the predicted remaining life according to the cumulative damage feature, and determining a device maintenance time corresponding to each lighting device; The step 1 comprises the following steps: Step 11: transmitting the real-time parameter information of the lighting device through a communication network, data encoding the real-time parameter information in an application layer of the communication network to obtain real-time application data of the lighting device, identifying first byte data of the real-time application data, and constructing a real-time data feature of the lighting device according to data content contained in the first byte data; Step 12: identifying second byte data of the real-time application data, constructing a key byte value of the real-time application data according to the first byte data and the second byte data, determining a device attribute of the lighting device by using AI technology to perform type matching on the key byte value, performing data calibration on the real-time application data based on a legal data packet type of the device attribute to obtain real-time effective data of the lighting device; Step 13: normalizing the real-time effective data corresponding to different time points, sorting the normalized data according to time sequence, performing linear analysis on the sorting result to obtain a data linear relationship of the lighting device, identifying a plurality of lighting segments of the lighting device in the data linear relationship, and constructing a lighting work rule of the lighting device; Step 14: mapping the lighting work rule to a time space to obtain a plurality of historical lighting time periods of the lighting device, performing fuzzy processing on a lighting starting time corresponding to each historical lighting time period to obtain a fuzzy lighting starting point corresponding to each historical lighting time period, and determining a plurality of normal working time periods of the lighting device.

2. A method for predictive maintenance of a lighting device as claimed in claim 1, characterized in that, Further comprising: determining a lighting duration of the corresponding historical lighting time period according to each lighting starting time, and determining a historical average lighting duration of the lighting device; determining an adjustable duration corresponding to each historical lighting time period based on the historical average lighting duration; performing fuzzy processing on the corresponding lighting starting point in the adjustable duration to obtain a fuzzy lighting starting point corresponding to the corresponding historical lighting time period.

3. A method for predictive maintenance of a lighting device as claimed in claim 1, characterized in that, The step 2 comprises the following steps: Step 21: performing autocorrelation calculation on each historical working data by using the autoregressive model to determine a current order threshold of the autoregressive model, adjusting an initial window length to obtain an effective window function of the lighting device according to the current order threshold. Step 22: windowing each of the historical working data by using the window function to obtain a plurality of optimized lighting time periods of the lighting device, feeding back the optimized lighting time periods to the autoregressive model for model fitting to obtain autoregressive coefficients of the lighting device; Step 23: according to the autoregressive coefficients, performing regression prediction on the historical working data to obtain a plurality of predicted lighting time instants of the lighting device, determining a failure lighting time period of the lighting device according to a predicted lighting effect feature corresponding to each of the predicted lighting time instants, and determining a remaining normal working frequency of the lighting device.

4. A method for predictive maintenance of a lighting device according to claim 3, characterized in that, Further comprising: After obtaining the autoregressive coefficients, performing residual error identification on the autoregressive model to obtain residual error values of the autoregressive model; When there is an autocorrelation relationship between the residual error values and the historical working data, correcting a current order of the autoregressive model by using the residual error values to obtain an updated autoregressive model; Using the updated autoregressive model to perform model fitting on the optimized lighting time period, and updating the autoregressive coefficients according to the fitting result.

5. A method for predictive maintenance of a lighting device as claimed in claim 1, characterized in that, The step 3 comprises: Step 31: mapping the remaining normal working frequency to the lighting working law, extending the lighting working law according to a mapping position corresponding to each of the remaining normal working frequencies, and determining a predicted remaining life of the lighting device according to an extension length; Step 32: restoring a real-time lighting state of the lighting device according to the real-time parameter information, constructing a cumulative lighting state of the lighting device, deriving a historical cumulative damage of the lighting device according to the cumulative lighting state, and determining an increased damage of the historical cumulative damage according to the real-time lighting state; Step 33: according to a damage attribute of the increased damage, identifying and counting a same-attribute damage quantity contained in the historical cumulative damage, and determining a real-time working damage of the lighting device by using the same-attribute damage quantity to enhance the damage attribute of the increased damage; Step 34: using the real-time working damage to simulate damage of the lighting device, determining a damage position corresponding to each lighting instant and a damage value corresponding to each of the damage positions, and determining a cumulative damage feature corresponding to each lighting device in the lighting device.

6. A method for predictive maintenance of a lighting device as claimed in claim 1, characterized in that, The step 4 comprises: Step 41: constructing a damage lighting model of the lighting device according to an initial device parameter corresponding to each of the lighting devices and the cumulative damage feature, and determining a device running parameter corresponding to each of the lighting devices by running the damage lighting model; Step 42: deriving a device total damage time instant corresponding to the lighting device by using the device running parameter, marking the device total damage time instant in the predicted remaining life, and determining a total damage consequence corresponding to each of the lighting devices based on a device attribute corresponding to each of the lighting devices; Step 43: setting a first device order for the lighting devices according to a descending order of the total damage consequence, setting a second device order for the lighting devices according to a descending order of the total damage time instant, and reordering the lighting devices according to the first device order and the second device order. Step 44: feedback the ranking result to determine the device maintenance time corresponding to each of the lighting devices in the predicted residual life, and generate and display a corresponding maintenance list.

7. A method for predictive maintenance of a lighting device as claimed in claim 6, characterized in that, Also comprising: respectively acquiring the real-time device state corresponding to each of the lighting devices; screening the target lighting device with abnormal real-time device state, defining the ranking of the target lighting device as first, generating an emergency maintenance warning and corresponding alarm.

8. A predictive maintenance system for a lighting arrangement, characterized by Comprising: a regularity analysis module for constructing the lighting work regularity of the lighting device according to a plurality of real-time parameter information of the lighting device, and determining a plurality of common working time periods of the lighting device; a prediction execution module for predicting the residual working time of the lighting device by using an autoregressive model on the historical working data corresponding to each of the common working time periods; a damage derivation module for deriving the predicted residual life of the lighting device, constructing the real-time working damage of the lighting device by using the real-time parameter information, and determining the cumulative damage characteristics corresponding to each lighting device in the lighting device; a maintenance assistance module for marking the device total damage time corresponding to each of the lighting devices in the predicted residual life according to the cumulative damage characteristics, and determining the device maintenance time corresponding to each of the lighting devices; The regularity analysis module comprises: a first analysis unit for transmitting the real-time parameter information of the lighting device through a communication network, data encoding the real-time parameter information in the application layer of the communication network to obtain real-time application data of the lighting device, identifying the first byte data of the real-time application data, and constructing the real-time data characteristics of the lighting device according to the data content contained in the first byte data; a second analysis unit for identifying the second byte data of the real-time application data, constructing the key byte value of the real-time application data according to the first byte data and the second byte data, determining the device attribute of the lighting device by using AI technology to type match the key byte value, and data calibrating the real-time application data based on the legal data packet type of the device attribute to obtain the real-time effective data of the lighting device; a third analysis unit for normalizing the real-time effective data corresponding to different time points, sorting the normalized data according to time sequence, obtaining the data linear relationship of the lighting device by linear analysis on the sorting result, identifying a plurality of lighting segments of the lighting device in the data linear relationship, and constructing the lighting work regularity of the lighting device; a fourth analysis unit for mapping the lighting work regularity to time space to obtain a plurality of historical lighting time periods of the lighting device, fuzzy processing the lighting start time corresponding to each of the historical lighting time periods to obtain the fuzzy lighting start point corresponding to each of the historical lighting time periods, and determining a plurality of common working time periods of the lighting device.

Images