A method and device for collaborative operation and maintenance of a port facility

Abstract

The application relates to a collaborative operation and maintenance method and device of a port equipment, and relates to the technical field of computer technology.The method comprises the following steps: comprehensively acquiring operation parameters of lighting equipment, environment information of a yard area, and operation area division related data, evaluating operation risks of the lighting equipment in a future time period, and comprehensively judging maintenance emergency degrees of each lighting equipment on the basis of possible associated abnormal conditions between the equipment and operation arrangement of an area where the equipment is located, so that equipment maintenance tasks with response priority differentiation are formed and are sequentially distributed.The method can help improve the matching degree between maintenance response and actual operation arrangement, reduce the influence of lighting failure on yard operation, and improve the overall reliability and operation and maintenance efficiency of the port lighting system under a complex operation environment.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a collaborative operation and maintenance method and apparatus for port equipment. Background Technology

[0002] Port yards are typically equipped with numerous lighting fixtures to ensure loading and unloading operations, safety inspections, and personnel passage at night and in low visibility conditions. Due to the large area of ​​the yard, the dispersed distribution of equipment, and the long-term exposure to high humidity, high salt spray, and complex climatic environments, the lighting equipment is prone to performance degradation or failure during operation, making operation and maintenance management quite challenging.

[0003] Current port lighting equipment maintenance methods largely rely on manual inspections or only arrange repairs after obvious equipment failures occur. Maintenance decisions are mainly based on the operating status of individual devices or past maintenance records, lacking a systematic assessment of future operational risks and related failures. In practical applications, this approach makes it difficult to detect potential faults in a timely manner, easily causing lighting equipment to malfunction during critical operating periods, thus affecting the continuity of yard operations.

[0004] On the other hand, lighting equipment in port yards is usually installed in batches, spatially adjacent to each other, and some equipment shares power lines, so there may be some correlation between their operating status. However, existing operation and maintenance management methods often fail to fully consider the above-mentioned correlations when formulating maintenance plans, and only deal with individual equipment, which easily overlooks the mutual influence between equipment and increases the risk of concentrated failures.

[0005] In addition, different areas of the yard undertake different tasks at different times. However, existing technologies often lack comprehensive consideration of the regional work arrangements when arranging the maintenance sequence of lighting equipment, resulting in a mismatch between maintenance response and actual work needs, which affects the rational use of operation and maintenance resources.

[0006] Although there are some technologies that use sensor data to predict equipment health, existing solutions often fail to effectively integrate equipment-related risks and dynamic operational needs when applied to scenarios such as port lighting, which have strong spatial correlation, operational sequence, and environmental complexity. This results in a disconnect between prediction results and operation and maintenance decisions, leading to low resource allocation efficiency.

[0007] Therefore, the existing port lighting equipment operation and maintenance management methods still need further improvement in terms of the foresight of fault identification, the rationality of maintenance decisions, and the coordination with yard operation arrangements. Summary of the Invention

[0008] Therefore, it is necessary to provide a collaborative operation and maintenance method and device for port equipment to address the aforementioned technical problems.

[0009] Firstly, this application provides a collaborative operation and maintenance method for port equipment, including:

[0010] Obtain the operating parameters of multiple lighting devices in the port, environmental data of the storage yard area, and the area operation plan corresponding to the lighting devices;

[0011] The operating parameters and environmental data are input into a pre-trained fault prediction model to generate the fault probability of each lighting device in a future preset time period.

[0012] The risk coefficient of cascading failures for each lighting device is obtained by weighting the historical common failure rate of devices in the same batch based on batch association, the recent failure rate of adjacent devices based on spatial association, and the abnormality rate of devices in the same circuit based on circuit association.

[0013] The failure probability, the cascading failure risk coefficient, and the urgency of the operation indicated by the regional operation plan are weighted and calculated to obtain the failure impact of each lighting device.

[0014] Based on the impact of the fault, equipment maintenance tasks with different response priorities are established, and the equipment maintenance tasks are sequentially assigned to preset maintenance terminals according to the response priorities.

[0015] Optionally, the historical common failure rate of the same batch of lighting equipment is: the ratio of the number of times multiple equipment in the same batch of equipment experienced consecutive failures within a preset historical period to the total number of failures of all equipment in the same batch.

[0016] The recent failure rate of the adjacent equipment is: the percentage of other lighting equipment within a preset range centered on the lighting equipment that fails within a preset adjacent time period;

[0017] The equipment failure rate in the same circuit is the percentage of other lighting equipment that experience failures in the same power circuit as the lighting equipment.

[0018] Optionally, acquiring the operating parameters of multiple lighting devices in the port, environmental data of the storage yard area, and preset work area division information includes:

[0019] By using sensors deployed on the power module, heat sink, and light source assembly of each lighting device, at least one of the following data is collected: voltage, current, temperature, and luminous flux of the lighting device.

[0020] By using environmental monitoring nodes distributed across various storage yard areas, at least one of the following data is collected: light intensity, temperature and humidity, wind speed, and salt spray concentration in the storage yard area.

[0021] The port operations management system periodically obtains information on the division of work areas.

[0022] Optionally, the equipment maintenance tasks are sequentially assigned to preset maintenance terminals according to the response priority, including:

[0023] Acquire real-time location information reported by multiple preset maintenance terminals, mobile operation planning of large mobile machinery in the port, and storage location information of fault repair parts;

[0024] By combining the real-time location information, the mobile operation plan, and the warehouse location information, a preset path planning algorithm is used to determine the response time of each maintenance terminal for the equipment maintenance task;

[0025] The target maintenance terminal is selected based on the response time, and a maintenance task allocation sequence is dynamically generated based on the response priority and the response time. The equipment maintenance task is then allocated to the corresponding target maintenance terminal according to the task allocation sequence.

[0026] Optionally, selecting the target maintenance terminal based on the response time includes:

[0027] By combining the real-time location information, the mobile operation plan, and the warehouse location information, a preset path planning algorithm is used to calculate the execution path of each maintenance terminal for the equipment maintenance task;

[0028] Based on the status of the emergency lighting equipment bound to the maintenance terminal and the lighting status along the execution path, the execution risk of each maintenance terminal for the equipment maintenance task is determined;

[0029] With the objectives of minimizing the execution path, minimizing the execution risk, and minimizing the response time, a multi-objective optimization algorithm is used to select the target maintenance terminal.

[0030] Optionally, the method further includes:

[0031] If the execution risk of the equipment maintenance task by each maintenance terminal is greater than the preset risk threshold, then two maintenance terminals are selected simultaneously by the multi-objective optimization algorithm with the goal of minimizing the execution path and minimizing the response time.

[0032] Optionally, the failure probability, the area operation plan corresponding to the lighting equipment, and the cascading failure risk coefficient are weighted and calculated to obtain the failure impact degree of each lighting equipment, including:

[0033] The failure probability is weighted and corrected based on the reliability of the failure prediction model.

[0034] The area affected by the malfunction is determined by the area operation plan corresponding to the lighting equipment;

[0035] The risk coefficient of the cascading failure is weighted and corrected based on the current operation and maintenance strategy mode, workload level and / or preset risk control level;

[0036] The impact of each lighting device failure is calculated using the weighted and corrected failure probability and cascading failure risk coefficient, as well as the working area affected by the failure.

[0037] Secondly, this application also provides a collaborative operation and maintenance device for port equipment, comprising:

[0038] The data acquisition module is used to acquire the operating parameters of multiple lighting devices in the port, environmental data of the storage yard area, and the area operation plan corresponding to the lighting devices;

[0039] The failure probability prediction module is used to input the operating parameters and environmental data into a pre-trained failure prediction model to generate the failure probability of each lighting device in a future preset time period.

[0040] The cascading risk assessment module is used to calculate the cascading failure risk coefficient of each lighting device by weighting the historical common failure rate of the same batch of equipment, the recent failure rate of adjacent equipment, and the abnormality rate of equipment in the same circuit, based on batch, spatial and circuit correlation.

[0041] The fault impact assessment module is used to perform a weighted calculation based on the fault probability, the cascading fault risk coefficient, and the urgency of the operation indicated by the regional operation plan to obtain the fault impact degree of each lighting device.

[0042] The maintenance task allocation module is used to establish equipment maintenance tasks with different response priorities based on the fault impact, and to allocate the equipment maintenance tasks to preset maintenance terminals in sequence according to the response priority.

[0043] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in the first aspect.

[0044] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0045] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0046] This application proposes a fault impact assessment model that integrates equipment status, batch / space / circuit multi-related risks, and dynamic operation planning, enabling precise quantification of the consequences of port lighting equipment failures. Simultaneously, it designs a collaborative allocation mechanism for maintenance tasks based on multi-objective optimization and real-time dynamic information (personnel location, machinery planning, and spare parts inventory), achieving efficient and safe scheduling of maintenance resources. Furthermore, it constructs a closed-loop operation and maintenance system encompassing prediction, assessment, decision-making, execution, and feedback, enhancing the adaptability and continuous optimization capabilities of operation and maintenance management. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the architecture of the port equipment operation and maintenance management system in one embodiment;

[0048] Figure 2 This is a flowchart illustrating a collaborative operation and maintenance method for port equipment in one embodiment;

[0049] Figure 3 This is a schematic diagram of the structure of a port equipment operation and maintenance device in one embodiment;

[0050] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] This application provides a collaborative operation and maintenance method for port equipment. This method can be applied to a port lighting equipment operation and maintenance management system, which is suitable for operation and maintenance scenarios of lighting equipment in container yards, bulk cargo yards, or other port operation areas. Port lighting equipment is typically numerous and widely distributed, and its operating status is closely related to the operational needs of port nighttime operations, security inspections, and personnel passage. Figure 1 As shown, the operation and maintenance management system may include a server and at least one terminal device. The server may be a backend server deployed on the port operation and maintenance management platform, used for centralized processing of the operating data of port lighting equipment and operation and maintenance decisions. The terminal device may be a mobile terminal, tablet device or other smart terminal held by operation and maintenance personnel and equipped with an operation and maintenance management application, used to receive operation and maintenance tasks and perform on-site maintenance operations.

[0053] In actual operation, the server can obtain operating parameters of multiple lighting devices in the port, environmental data of the yard area where the lighting devices are located, and preset work area division information. Based on the above data, it analyzes the operating status of the lighting devices and generates corresponding equipment maintenance tasks. The server can also determine different response priorities based on the generated maintenance tasks and allocate the maintenance tasks to the corresponding terminal devices according to the response priority. The terminal devices, as the execution end of the maintenance tasks, are used to receive the equipment maintenance tasks issued by the server and display the lighting equipment information that needs to be handled to the maintenance personnel. The maintenance personnel can go to the corresponding lighting equipment site to complete the inspection, repair, or replacement operations according to the maintenance tasks displayed on the terminal devices, thereby realizing the daily operation and maintenance management of port lighting equipment.

[0054] The following will be about Figure 2 The following is a detailed explanation of a collaborative operation and maintenance method for port equipment, which may include the following steps:

[0055] Step 201: Obtain the operating parameters of multiple lighting devices in the port, environmental data of the storage yard area, and the area operation plan corresponding to the lighting devices.

[0056] In implementation, the server acts as the data aggregation and processing node of the aforementioned operation and maintenance management system. It can uniformly acquire the operating parameters of multiple lighting devices in the port, environmental data of the storage yard area, and the regional operation plans corresponding to each lighting device. This provides basic data support for subsequent equipment status analysis and operation and maintenance decisions. The operating parameters reflect the real-time operating status of each lighting device, the environmental data characterizes the environmental conditions of the lighting devices, and the regional operation plans display the port areas where each lighting device is in operation at different times.

[0057] Firstly, the server can monitor the key operating status of each lighting device in real time using multiple sensors deployed on each device. Specifically, electrical parameter sensors can be installed on the power module of each lighting device to collect input voltage and operating current, reflecting the power supply status and load changes of the lighting device. Temperature sensors can also be installed near the heat sink or light source assembly to collect junction temperature or operating temperature, reflecting the thermal characteristics of the lighting device during continuous operation. Simultaneously, optical sensors can be installed at the light-emitting end of the light source assembly or at corresponding locations to collect luminous flux data, characterizing changes in the luminous performance of the lighting device. Furthermore, the above operating parameters can be collected at a preset sampling frequency, for example, sampling at least one of voltage, current, temperature, and luminous flux data every 5 minutes.

[0058] Secondly, the server can deploy multiple environmental monitoring nodes in various storage yard areas of the port to collect environmental factors affecting the aging and operational reliability of lighting equipment. In this embodiment, the storage yard area can be divided according to a preset spatial grid, for example, a 60m × 60m grid unit, with a total of 28 environmental monitoring nodes deployed at corresponding locations to cover the entire storage yard area. Each environmental monitoring node can be used to collect at least one environmental parameter among ambient light intensity, ambient temperature and humidity, wind speed, and salt spray concentration in its area. Among these, salt spray concentration can be detected by an electrochemical sensor to assess the potential corrosion and aging risks faced by lighting equipment in the coastal port environment.

[0059] Third, the server can interface with the port operations management system to synchronize operational planning information for the yard area on a regular basis. Specifically, the server can establish a connection with the database of the port operations management system and synchronize operational planning information at preset time intervals (e.g., every 15 minutes). This operational planning information can include the current operational status and estimated operational duration of each bay or yard area. For example, it can be used to identify whether certain areas are in an idle state, a planned operational state, or an operational state during a certain period of time, which can be represented as the operational planning for each lighting device.

[0060] In a further embodiment, after receiving the operating parameters of the lighting equipment, environmental data, and work area division information, the server can preprocess and manage the aforementioned multi-source data in a unified manner. Specifically, the server can use the 3σ criterion to remove instantaneous spikes and outliers in the collected voltage and current data to reduce the impact of occasional interference on subsequent analysis. For missing environmental data due to communication interruptions, linear interpolation between adjacent time points can be used to fill in the gaps, ensuring the continuity of the data sequence. Simultaneously, the server can store the cleaned data according to a preset data structure. For example, the data can be structured and stored in a distributed database, with "equipment number + timestamp" as the row key to establish data partitions, thereby improving the efficiency of subsequent queries and analyses by device or by time dimension.

[0061] In addition, the server can generate a dynamic operation area mapping table that is precisely aligned with the timestamp based on the operation area division information synchronized from the port operation management system. This table is used to indicate the operation plan of each lighting device, that is, whether it is located in the operation area within the current time or a future preset time window.

[0062] Step 202: Input the operating parameters and environmental data into the pre-trained fault prediction model to generate the fault probability of each lighting device in the future preset time period.

[0063] In implementation, the server can predict the probability of lighting equipment failure within a preset future time period based on the historical operating characteristics and current status of the equipment. Specifically, this can be achieved by inputting the operating parameters of the lighting equipment and environmental data of the surrounding storage area into a pre-trained failure prediction model. This model then generates the failure probability of each piece of lighting equipment within the preset future time period. The preset future time period can be set according to operational and maintenance management needs, such as 1 hour, 4 hours, or 24 hours in advance.

[0064] The fault prediction model can be trained on a historical dataset, which may contain operational data of multiple lighting devices that have failed, covering a period of time prior to the failure, to indicate the evolution of the devices' state before the failure. Specifically, the historical dataset may include a sequence of operating parameters of the lighting devices within a preset time window before the failure, a sequence of environmental data for the corresponding time period, and information on the service life and batch of the lighting devices. For example, the sequence of operating parameters may include data on the changes in voltage, current, junction temperature, and luminous flux over time, while the sequence of environmental data may include data on the changes in environmental factors such as illuminance, temperature, humidity, wind speed, and salt spray concentration over time.

[0065] Furthermore, the historical dataset can be divided into a training set and a validation set according to a preset ratio, such as a 7:3 ratio. The training set is used for learning model parameters, while the validation set is used to evaluate the model's predictive performance. During model training, the gradient boosting tree algorithm can be used to train the training set. The gradient boosting tree algorithm is mainly used to model the nonlinear relationships between multi-dimensional features and is applicable to processing multi-source feature data such as lighting equipment operating parameters, environmental factors, and equipment service information. Specific modeling can refer to existing technologies, and this embodiment is not limited to any particular approach. After training, the server can evaluate the model's prediction accuracy on the validation set. When the model's prediction accuracy on the validation set reaches a preset threshold, the current model parameters are saved to generate the pre-trained fault prediction model required in step 202.

[0066] Step 203: The risk coefficient of cascading failures of each lighting device is obtained by weighting the historical common failure rate of devices in the same batch based on batch association, the recent failure rate of neighboring devices based on spatial association, and the abnormality rate of devices in the same circuit based on circuit association.

[0067] Among them, the historical common failure rate of equipment in the same batch based on batch association is the ratio of the number of times multiple equipment in the same batch experienced consecutive failures within a preset historical period to the total number of failures of all equipment in the same batch; the recent failure rate of neighboring equipment based on spatial association is the proportion of the number of other lighting equipment within a preset range centered on the lighting equipment that experienced failures within a preset adjacent period; and the abnormality rate of equipment in the same circuit based on circuit association is the proportion of the number of other lighting equipment in the same power circuit as the lighting equipment that experienced abnormalities.

[0068] In practice, due to the correlation between lighting equipment in port yards in terms of installation batches, spatial distribution, and power supply structure, the abnormal state of a single lighting device is often not an isolated event, but may be related to other equipment in the same batch, adjacent equipment, or other equipment within the same power circuit. Therefore, a cascading failure risk coefficient can be introduced to assess the potential risk of a single lighting device triggering a group failure while evaluating its operational risk. Specifically, the cascading failure risk coefficient can be calculated by weighting indicators of the associated risks of multiple devices. These indicators can include at least the historical common failure rate of equipment in the same batch, the recent failure rate of adjacent equipment, and the abnormality rate of equipment in the same circuit.

[0069] Firstly, the server can group and statistically analyze lighting equipment belonging to the same batch based on installation batch information. Specifically, within a preset historical time period, it counts the number of consecutive failures of multiple devices within the same batch and the total number of failures occurring within that historical period. Then, it calculates the ratio of the number of consecutive failures to the total number of failures in the same batch, thus obtaining the historical shared failure rate for the corresponding lighting equipment within the same batch. This indicator reflects whether there are concentrated or batch-wide failures in the historical operation of the same batch of equipment, and can, to some extent, reflect the associated risks caused by manufacturing processes, material aging, or shared batch defects.

[0070] Secondly, the server can define a preset spatial range centered on the installation location of the target lighting equipment, such as a preset distance or a grid within the same cluster, and identify other lighting equipment within this range. Furthermore, the server can count the number of faulty devices among neighboring equipment within preset adjacent time periods and calculate the ratio of this number to the total number of neighboring devices within the range, thus obtaining the recent failure rate of neighboring devices. This indicator reflects the recent operational stability of the area surrounding the target lighting equipment and helps identify spatially correlated failure risks caused by regional factors such as regional environmental conditions.

[0071] Simultaneously, the server can also identify other lighting devices in the same power circuit as the target lighting device based on the power supply topology information. Specifically, within a preset statistical period, the server can count the number of devices experiencing abnormal states within the same power circuit and calculate the ratio of this number to the total number of lighting devices in the power circuit, thus obtaining the device failure rate within the same circuit. Abnormal states can include operating parameters deviating from normal ranges, communication anomalies, or short-term failures. This indicator allows for the assessment of the impact of abnormal events on the operating status of lighting equipment at the power supply circuit level.

[0072] Furthermore, the server can analyze the correlation between the aforementioned related risk indicators and actual mass failure events based on fault records within a preset historical period, and configure the weights of each indicator according to the correlation. For example, when historical statistical results show a high correlation between the historical common failure rate of the same batch of equipment and concentrated failure events of multiple devices, the weighting coefficient of that indicator can be increased accordingly; when the recent failure rate of adjacent equipment or the abnormality rate of equipment on the same circuit has a relatively low impact on mass failures, the corresponding weighting coefficient can be appropriately decreased.

[0073] In another embodiment, the weighting coefficient can also be preset and configured according to the deployment characteristics and operating environment of the port lighting equipment. For example, in scenarios where equipment in the same batch is deployed in a concentrated manner and has a similar service life, the weighting coefficient corresponding to the historical common failure rate of the same batch of equipment can be increased; in areas where lighting equipment is densely distributed in space or where local environmental conditions change frequently, the weighting coefficient corresponding to the recent failure rate of adjacent equipment can be increased; and when the power supply circuit spans a large distance or the circuit load changes significantly, the weighting coefficient corresponding to the abnormality rate of equipment in the same circuit can be increased.

[0074] This embodiment is the first to integrate three indicators—batch-wide shared failure, spatial proximity failure, and circuit anomaly—which respectively reflect manufacturing quality consistency, local environmental pressure, and power supply and distribution system stability, to construct a multi-dimensional cascading failure risk quantification model. This integrated approach can more comprehensively capture the group failure risks caused by the inherent correlation of a large number of port lighting equipment, which is not available in traditional single-equipment assessment methods.

[0075] Step 204: Based on the failure probability, cascading failure risk coefficient and the urgency of the operation indicated by the regional operation plan, a weighted calculation is performed to obtain the failure impact of each lighting device.

[0076] Among them, the failure impact can be used to comprehensively assess the overall impact of a single lighting device failing within a preset time period on the continuity of port yard operations and maintenance decisions. It is not only related to the failure probability of the device itself, but also considers the importance of the operating area where the device is located and the potential risk of cascading failures.

[0077] In one embodiment, the process of calculating the impact of a fault can be as follows: the fault probability is weighted and corrected based on the reliability of the fault prediction model; the area affected by the fault is determined by the regional operation plan corresponding to the lighting equipment; the cascading fault risk coefficient is weighted and corrected based on the current operation and maintenance strategy mode, the workload level and / or the preset risk control level; and the impact of each lighting equipment fault is calculated using the weighted and corrected fault probability and cascading fault risk coefficient, as well as the area affected by the fault.

[0078] First, the server can combine the overall prediction accuracy, recall, or other model evaluation metrics of the fault prediction model on the validation set to generate a corresponding model confidence parameter w1. This confidence parameter w1 is then used to weight and correct the fault probability Pf, reducing the impact of model uncertainty on subsequent decision-making. For example, when the model's prediction performance is stable over a certain period, the original output of the fault probability Pf can be maintained, meaning a relatively high confidence parameter w1 can be set. Conversely, when the model's prediction accuracy is below a preset threshold, the fault probability Pf can be attenuated, meaning a relatively low confidence parameter w1 can be set.

[0079] Secondly, the server can use the dynamic work area mapping table generated in step 201 to identify whether the yard area where the lighting equipment is located is in a current or future preset time period of operation, and further determine the number of bays, grid area, or actual work coverage of the area, thereby calculating the work area Ar affected by the lighting equipment failure to reflect the corresponding work urgency. When the lighting equipment is located in a non-work area or a low-frequency work area, the corresponding affected work area Ar value can be reduced accordingly.

[0080] Furthermore, the server can apply an adjustment factor w3 to the cascading failure risk coefficient Tc based on whether a preventative or fault-response maintenance mode is currently in use, as well as the overall operational load of the yard. For example, under high load or continuous nighttime operation scenarios, the adjustment factor w3 can be increased to enhance sensitivity to potential group failures; under low load or during maintenance windows, the adjustment factor w3 of the cascading failure risk coefficient Tc can be appropriately decreased; for another example, when implementing preventative maintenance strategies or centralized equipment maintenance plans, the overall adjustment factor w3 of the failure risk coefficient Tc can be increased; under maintenance modes where the primary goal is rapid repair of individual equipment, the adjustment factor w3 of the failure risk coefficient Tc can be appropriately decreased.

[0081] After completing the above weighted adjustments, the server can calculate the failure impact index of each lighting device based on the following formula. : The weighting coefficients w1, w2, and w3 are not fixed values ​​but can be dynamically adjusted based on port operation patterns (e.g., day / night shifts), special weather warnings (e.g., typhoons, heavy fog), or specific period (e.g., Spring Festival travel rush, peak season). For example, w2 can be increased during continuous nighttime operations; w3 can be increased during salt spray concentration warnings to strengthen the prevention of related faults. Specifically, when the dynamic operation area mapping table shows that the area where the lighting equipment is located is in a high-priority operation period, the weight of the affected operation area Ar in the fault impact calculation can be increased, making the value of w2 greater than 1.0 to highlight the impact of lighting faults on critical operation areas; when the lighting equipment is located in a non-critical operation area or during idle periods, w2 can be restored to the default weight or less than the value corresponding to the high-priority period.

[0082] Furthermore, when calculating the fault impact index for each lighting device, the server can also combine the functional type of the lighting device and the external dynamic supplementary lighting conditions to refine the fault impact index, so as to more realistically reflect the impact of lighting device failures on the actual operations of the port yard.

[0083] The functional types of lighting equipment can be pre-configured by the operation and maintenance management system during the equipment documentation or system initialization phases, and are used to identify the main lighting uses of the equipment in the yard. Functional types should include at least the following categories: work lighting, inspection lighting, and supplementary lighting for security monitoring. When calculating the fault impact index, the server can apply differentiated weighting strategies for different types of lighting equipment based on their functional types.

[0084] For example, when the function type of the lighting equipment is operational lighting, and the dynamic operational area mapping table shows that the area where the lighting equipment is located is in the current operational period or will enter the operational state within a preset future time period, the server can increase the weight coefficient w2 corresponding to the affected operational area Ar, so that it has a higher impact weight in the fault impact calculation compared to other types of lighting equipment. The specific increase can be 1.5 to 2.0 times the original weight. When the function type of the lighting equipment is security monitoring supplementary lighting, and the time period is at night, in severe weather, or during high-risk monitoring periods with high security risk levels, the server can also increase its corresponding weight coefficient w2 to enhance the risk perception capability of security supplementary lighting equipment faults.

[0085] In addition, the operation and maintenance management system can be configured with a mobile light source database to store the built-in lighting capability parameters of large mobile machinery in the yard. The mobile light source database can include information such as lighting power, illumination angle, and effective illumination distance for large mobile machinery such as tire-mounted cranes and straddle carriers. The server can synchronize the location information of large mobile machinery in real time through the terminal operation management system or vehicle positioning system. Thus, when calculating the fault impact index, the server can assess the dynamic compensation effect of large mobile machinery on areas lacking lighting based on the mobile light source database. Specifically, when the server determines that within a preset time period (e.g., the next hour), at least one large mobile machine with effective lighting capability will be able to move to the area where the lighting equipment is located and provide effective supplementary lighting to that area both spatially and temporally, the affected operating area Ar can be reduced accordingly.

[0086] In addition, considering that port yards typically have lighting equipment with remote angle adjustment or relocation capabilities, their actual illumination coverage may vary depending on the luminaire's attitude, output parameters, and the status of surrounding temporary light sources. Assessing the impact of a failure solely based on the nominal illumination range or designed coverage area of ​​the lighting equipment can easily lead to overestimation or underestimation of the affected work area in specific operational scenarios. Therefore, the server can introduce a dynamic illumination simulation model to calculate the actual service area of ​​such lighting equipment and correct the affected work area Ar in the failure impact assessment accordingly. Specifically, when lighting equipment is identified as having remote pitch angle adjustment, rotation angle adjustment, or relocation capabilities, the server can call the dynamic illumination simulation model to simulate and analyze the real-time illumination coverage of the lighting equipment. The dynamic illumination simulation model can use the current attitude parameters and output parameters of the lighting equipment as input, where the input parameters include at least the luminaire's pitch angle, rotation angle, and output luminous flux.

[0087] For example, for a high-mast lighting fixture located in area G5 of the port yard, the designed illumination coverage area is 400 square meters. When assessing the impact of a fault, the server can call a dynamic illumination simulation model and input parameters such as the current pitch angle of the high-mast light (30°), rotation angle (45°), and output luminous flux (15000 lm). The calculation shows that the actual illumination coverage area of ​​the high-mast light under the current posture and environmental conditions is 380 square meters. After obtaining the simulation results, the server can correct the affected work area (Ar) in the fault impact assessment based on the actual coverage service area, thereby avoiding incorrect judgments about the scope of work affected by the lighting equipment fault when calculating the fault impact index.

[0088] Step 205: Establish equipment maintenance tasks with different response priorities based on the degree of fault impact, and assign the equipment maintenance tasks to the preset maintenance terminals in order of response priority.

[0089] In implementation, after obtaining the failure impact of each lighting device, the server can transform the assessment results into executable maintenance tasks and, in conjunction with the actual distribution of maintenance resources within the port yard, orderly dispatch these tasks. Specifically, the server sorts the lighting devices to be repaired based on their failure impact and, according to preset threshold ranges or grading rules, classifies the corresponding equipment maintenance tasks into different response priorities, such as urgent, high priority, and normal priority. This response priority characterizes the processing order of the maintenance tasks within the overall dispatch process.

[0090] After generating an equipment maintenance task, the server can further obtain real-time location information reported by multiple preset maintenance terminals. These terminals can be mobile or vehicle-mounted terminals carried by maintenance personnel, and their reported real-time location information reflects the current spatial location of the maintenance personnel within the yard. Simultaneously, the server can also obtain the movement operation planning information of large mobile machinery within the port. This information reflects the movement path and occupied area of ​​each machine in the current or future time period, used to identify impassable or high-risk passages that maintenance personnel may encounter during their movement. Furthermore, the server can obtain the storage location information of faulty repair parts, used to determine the retrieval route required by maintenance personnel before performing equipment maintenance tasks. This storage location information may include the spatial coordinates of the parts warehouse and the location of available inventory.

[0091] After obtaining the aforementioned real-time location information, mobile operation planning information, and warehouse location information, the server can integrate this information and use a preset path planning algorithm to calculate the response time of each maintenance terminal for each equipment maintenance task. Specifically, this includes the estimated time from the current location of the maintenance terminal, through the parts storage location to retrieve parts, avoiding the operation area of ​​large mobile machinery, and finally reaching the location of the target lighting equipment. Then, for the currently assigned equipment maintenance task, the server can select the target maintenance terminal with the shortest response time or that meets the preset response conditions from multiple maintenance terminals. Based on the response priority and response time, it dynamically generates a maintenance task allocation sequence and assigns the equipment maintenance task to the corresponding target maintenance terminal according to the task allocation sequence. It can be understood that equipment maintenance tasks can be allocated sequentially according to response priority from high to low to ensure that high-priority maintenance tasks receive maintenance resources first. In this way, the server can consider the urgency of the maintenance task while combining the real-time location of maintenance personnel, the dynamic operating environment of the yard, and the parts acquisition path to rationally dispatch equipment maintenance tasks, thereby improving the overall response efficiency and execution feasibility of port lighting equipment operation and maintenance.

[0092] It should be noted that when assigning equipment maintenance tasks, the selection of maintenance terminals can be further refined by considering the skill matching of maintenance personnel. This avoids selecting personnel without the corresponding maintenance capabilities based solely on response time or path factors. Specifically, the server can pre-configure skill tag information for each maintenance personnel. Skill tags should include at least the electrician's qualification level, high-voltage operation qualification, maintenance experience with specific models of lighting equipment, and whether they have the ability to work at night or at heights. Correspondingly, the server can also configure skill requirement tags for different types of equipment maintenance tasks to indicate the minimum skill requirements for completing the task. Taking the maintenance task of high-mast LED lighting as an example, this task is marked as "high-mast operation + driver power supply replacement," and the corresponding skill requirements include high-voltage operation qualification and high-mast lighting maintenance experience. When evaluating multiple maintenance terminals, the server found that maintenance personnel A possesses the above skill tags, maintenance personnel B, although arriving sooner, lacks high-mast operation experience, and maintenance personnel C possesses some skills but is currently occupied by a task. In this scenario, after considering response time, execution path, and skill matching, the server can apply a penalty factor to maintenance terminals with insufficient skill matching, lowering their priority in the overall evaluation. Ultimately, the maintenance personnel A who meets the skill matching requirements and has the best overall evaluation result is selected as the target maintenance terminal to perform the equipment maintenance task. By introducing the personnel skill matching dimension into the task assignment phase, duplicate assignments, maintenance failures, or safety risks caused by skill mismatches can be avoided, improving the reliability of equipment maintenance task allocation and the one-time completion rate.

[0093] In one embodiment, the process of selecting a target maintenance terminal based on response time may include the following steps: integrating real-time location information, mobile operation planning, and warehouse location information, and using a preset path planning algorithm to calculate the execution path of each maintenance terminal for the equipment maintenance task; determining the execution risk of each maintenance terminal for the equipment maintenance task based on the status of the emergency lighting equipment bound to the maintenance terminal and the lighting status on the execution path; and selecting a target maintenance terminal using a multi-objective optimization algorithm with the objectives of minimizing the execution path, minimizing the execution risk, and minimizing the response time.

[0094] In implementation, when selecting target maintenance terminals based on response time, it is necessary to consider not only the time cost for the maintenance terminal to reach the target lighting equipment, but also the safety and feasibility of passage for maintenance personnel during the performance of maintenance tasks, especially in complex environments such as port yards with insufficient lighting and frequent operations of large mobile machinery. Correspondingly, the server can integrate real-time location information, mobile operation planning, and warehouse location information, and use a pre-defined path planning algorithm to calculate the execution path for each maintenance terminal for equipment maintenance tasks.

[0095] First, the server can use the current location reported by the maintenance terminal as the starting point of the path, the location of the target lighting equipment as the ending point, and combine this with the storage location information of maintenance parts to incorporate the retrieval path into the overall path planning. Simultaneously, the server can also use the movement and operation plans of large mobile machinery such as rubber-tired gantry cranes and straddle carriers within the port as dynamic constraints, avoiding occupied or hazardous passageways during the path planning process, thereby generating candidate execution paths for each maintenance terminal.

[0096] Secondly, the server can determine the execution risk of each maintenance terminal for equipment maintenance tasks based on the status of the emergency lighting equipment bound to the maintenance terminal and the lighting status along the execution path. Specifically, each maintenance terminal can be pre-bound to the emergency lighting equipment carried by the corresponding maintenance personnel. Its status information can include whether the emergency lighting equipment is available, its power level, and the duration of continuous lighting. When assessing execution risk, the server can combine the working status of the fixed lighting equipment along the execution path to determine whether there are long sections of insufficient or completely unlit road. When the status of the emergency lighting equipment bound to the maintenance terminal is insufficient to cover such sections, the execution risk of the corresponding execution path can be determined to be high.

[0097] Furthermore, after obtaining the execution path length, execution risk, and response time corresponding to each maintenance terminal, the server can select the target maintenance terminal from multiple maintenance terminals using a multi-objective optimization algorithm, with the objectives of minimizing the execution path, minimizing the execution risk, and minimizing the response time. The multi-objective optimization algorithm can employ existing algorithm frameworks, and this embodiment does not limit it.

[0098] By using the above methods, the selection of target maintenance terminals can not only shorten maintenance response time, but also effectively reduce the passage risks faced by maintenance personnel when performing tasks in complex yard environments, and improve the rationality and reliability of equipment maintenance task allocation results.

[0099] In one embodiment, when it is determined that the execution risk of the equipment maintenance task at each maintenance terminal is greater than a preset risk threshold, it indicates that there is a high safety risk for a single maintenance personnel to independently perform the maintenance task under the current environmental conditions. To ensure the personal safety of maintenance personnel and improve the reliability of task execution, the server can adopt a two-person collaborative approach to perform equipment maintenance tasks, that is, simultaneously selecting maintenance personnel corresponding to two maintenance terminals to go to the target lighting equipment site to collaboratively complete the maintenance operation.

[0100] Subsequently, after the condition of two people traveling together is triggered, the server can reconstruct the optimization objective function selected by the maintenance terminal, without prioritizing minimizing execution risk. The primary optimization objectives are minimizing the execution path and minimizing response time. Specifically, the server can construct maintenance terminal combinations for any two different maintenance terminals based on the candidate execution paths from each maintenance terminal to the target lighting device and their corresponding response times. The combined execution path can consist of the execution paths from the two maintenance terminals to the target lighting device, and its path cost can be the weighted sum or total of the lengths of the two execution paths. The combined response time can be defined as the maximum time required for the two maintenance terminals to reach the target lighting device, representing the earliest time point required to begin the maintenance operation in the two-person-traveling scenario.

[0101] After obtaining the combined execution paths and combined response times corresponding to multiple maintenance terminal combinations, the server can select the target maintenance terminal combination from the multiple maintenance terminal combinations with the goal of minimizing the combined execution path and minimizing the combined response time, and simultaneously allocate the equipment maintenance task to the two maintenance terminals corresponding to the target maintenance terminal combination.

[0102] In this way, under high-risk scenarios, the safety of maintenance personnel can be ensured while taking into account the overall response efficiency of maintenance tasks. This avoids path redundancy or response delays caused by simply adding personnel, thereby improving the rationality and feasibility of scheduling port lighting equipment operation and maintenance tasks.

[0103] It's worth noting that after determining that a two-person team is needed to perform equipment maintenance tasks, the server can further assess the location of execution risks to determine the specific timing and location for the two maintenance personnel to meet. This ensures safety while avoiding unnecessary path redundancy. For example, when assessing the execution risks of equipment maintenance tasks at each maintenance terminal, the server can divide the execution path into multiple continuous segments and, combined with the lighting conditions, environmental conditions, and the operation of large mobile machinery along the execution path, identify the risk points corresponding to the execution risks. These risk points are locations with high safety risks within the execution path or the target equipment area.

[0104] In one scenario, when the primary risk stems from consecutive unlit or poorly lit sections along the path of the maintenance terminal, the server can designate the starting point of the unlit section as a high-risk point. In this case, the server can set constraints during the path planning phase, requiring the two selected maintenance terminals to meet before entering the unlit section and then jointly traverse the high-risk section to reach the target lighting equipment.

[0105] In another scenario, when the execution risk is determined to be primarily concentrated in the area where the target lighting equipment is located—for example, if the equipment is located in an area with extremely low illumination, large mobile machinery frequently passes through the vicinity of the equipment, or maintenance operations need to be performed at height or in confined spaces—the entrance location of the area where the target lighting equipment is located can be designated as a high-risk point. In this case, the server can allow two maintenance terminals to independently travel along their respective planned paths to the vicinity of the target area and meet before entering the area where the equipment is located, so that they can jointly enter the high-risk work area to perform the maintenance task.

[0106] It is understandable that the aforementioned meeting point can be dynamically determined by the server based on the real-time location information of the two maintenance terminals, the execution path, and the location of the risk occurrence point. This allows the two maintenance personnel to shorten the overall execution path and reduce response time as much as possible while meeting safety and collaboration requirements. This mechanism not only considers risk avoidance but also strives to minimize efficiency loss while ensuring safety by optimizing the meeting point and path. This method of transforming safety rules into quantifiable and optimizable scheduling constraints achieves a synergy between safety and efficiency, which cannot be achieved by simply relying on safety procedures in traditional operation and maintenance management. Therefore, by dynamically determining the two-person meeting strategy based on the risk occurrence point, the two-person travel mechanism can be made more flexible and refined, avoiding premature meeting in low-risk sections and increasing ineffective travel, while ensuring necessary collaborative support at critical high-risk locations, thereby further improving the safety and efficiency of port lighting equipment maintenance tasks.

[0107] For example, this application specifically relates to a predictive operation and maintenance management platform for yard lighting in a coastal automated container terminal. The terminal yard has a total area of ​​approximately 180,000 square meters and is equipped with 1,120 high-mast LED lights, handling container loading and unloading operations 24 hours a day. Nighttime operations are highly dependent on the lighting system, and large mobile machinery such as rubber-tired gantry cranes and straddle carriers frequently move through the yard, making the operation and maintenance environment highly dynamic.

[0108] The server collects data on the voltage, current, junction temperature, and luminous flux of the lighting fixtures every 5 minutes. It also deploys 28 environmental monitoring nodes within the yard in a 60m x 60m grid to collect environmental data such as light intensity, temperature, humidity, wind speed, and salt spray concentration. Simultaneously, the server interfaces with the terminal operations management system to synchronize operational area division information every 15 minutes, identifying key lighting areas for future operational periods.

[0109] In a predictive assessment, the server output the probability (Pf) of a failure occurring within the next 24 hours for high-mast light No. 7 in Zone B3. This light is designed to cover an area of ​​400 square meters. The area where this light is located will enter the night shift for tire crane operations in 3 hours, and is therefore marked as a high-priority work area with a corresponding work area weight (Ar) of 1.0. Historical data indicates that the batch of this light fixture experienced cascading failures in high-salt-spray environments, with a cascading failure risk coefficient (Tc) of 0.75.

[0110] In this work scenario, the weight parameters w1=1.0 and w2=1.5 can be dynamically set. Since the lighting function is for work lighting and it is during a work period, w2 is further increased to 1.8. It is determined that no large mobile machinery can move to this area and provide effective supplementary lighting within the next hour; therefore, the work area is not reduced. Based on the above parameters, the failure impact index of this lighting is calculated. It was identified as a high-priority repair task.

[0111] The server receives real-time locations and skill levels (e.g., electrician's license level, high-voltage operation qualification) reported by six maintenance personnel via handheld terminals. For the task involving light #7 in Zone B3, the server assesses the current location of the maintenance personnel, the coordinates of light #7 in Zone B3, and the predicted movement path of large machinery (e.g., tire crane) within the next 5 minutes. Areas occupied by the predicted machinery are marked as dynamic obstacles, and relevant passageways are excluded. Afterward, the server can output the arrival time for maintenance personnel A (skilled and available) as 15 minutes; the arrival time for maintenance personnel B (insufficient skills) as 12 minutes but with a low repair success rate; and the estimated arrival time for maintenance personnel C (performing other tasks) as 18 minutes later.

[0112] The server employs a multi-objective optimization algorithm to comprehensively consider minimizing the overall impact loss, minimizing the total travel distance of maintenance resources, and minimizing the safety risk value of maintenance personnel. Through iterative calculations, maintenance personnel A is determined to be the optimal candidate. Furthermore, the server can automatically query spare parts inventory, locate the same model drive module in the M2 tool room closest to area B3, and push the "maintenance task + navigation path + parts retrieval instruction" to maintenance personnel A's maintenance terminal.

[0113] Maintenance personnel A can navigate to the M2 tool room via the maintenance terminal to retrieve the part, and then proceed to lamp number 7 in area B3 to complete the repair. Simultaneously, the maintenance terminal can automatically record the voltage, current, and luminous flux data of the equipment before and after replacement during the repair process, and upload this data to the server. This repair record, along with environmental data and maintenance personnel information, can be used as a new sample to feed back into the fault prediction model for subsequent model iteration and optimization, forming a closed loop of "prediction-execution-learning".

[0114] After six months of continuous application of the above method at the wharf, significant technical results were achieved: Before the application of this method, lighting failures at the wharf mainly relied on manual reporting and regular inspections, with an average fault response time of 45 minutes. The average number of nighttime operation efficiency reduction events due to insufficient lighting was 3.2 per month. After the application of this method, the proactive intervention rate for high-priority tasks based on fault impact prediction reached over 85%, the average maintenance response time was shortened to 18 minutes, lighting-related operation interruption events decreased to less than 0.5 per month, and spare parts turnover efficiency was also improved.

[0115] In one example, the server has a built-in mobile light source database to record the built-in lighting capability parameters of large mobile machinery in the port. The lighting power, illumination angle, effective supplementary lighting distance, and minimum achievable illuminance for different types of machinery are shown in Table 1.

[0116] Table 1

[0117]

[0118] When it is predicted that light No. 3 in zone F7 (function type: "security monitoring supplementary lighting") has a drive fault ( When this area is confirmed to be a video surveillance blind spot, initially... The scheduling plan is as follows: a straddle carrier will be able to move to the area within the next 45 minutes, and its lighting will cover the camera's field of view. The server can determine that there is effective dynamic supplementary lighting and will... The failure impact index is reduced to 0.4, from the original... Down to The task priority has been reduced from high to medium.

[0119] In another example, maintenance personnel D needs to travel to area G8 to replace a faulty light located in an inspection passage that has long lacked fixed lighting. The server performs a safety risk assessment: the path is 320 meters long, with 200 meters being a "light blind spot"; ambient light is <5 lx (belonging to nighttime background light); the maintenance terminal reported that emergency lighting equipment was not registered, and the battery level is 25%. The server comprehensively determines this as a "high safety risk" and ultimately decides not to dispatch personnel D.

[0120] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0121] Based on the same inventive concept, such as Figure 3 As shown in the figure, this application embodiment also provides a collaborative operation and maintenance device 300 for port equipment, the device 300 comprising:

[0122] The data acquisition module 301 is used to acquire the operating parameters of multiple lighting devices in the port, the environmental data of the storage yard area, and the area operation plan corresponding to the lighting devices;

[0123] The fault probability prediction module 302 is used to input the operating parameters and environmental data into a pre-trained fault prediction model to generate the fault probability of each lighting device in a future preset time period.

[0124] The cascading risk assessment module 303 is used to calculate the cascading failure risk coefficient of each lighting device by weighting the historical common failure rate of the same batch of equipment, the recent failure rate of adjacent equipment, and the abnormality rate of equipment in the same circuit, based on batch, spatial and circuit correlation.

[0125] The fault impact assessment module 304 is used to perform a weighted calculation of the fault probability, the regional operation plan and the cascading fault risk coefficient based on the fault probability, the cascading fault risk coefficient and the urgency of the operation indicated by the regional operation plan, so as to obtain the fault impact degree of each lighting device.

[0126] The maintenance task allocation module 305 is used to establish equipment maintenance tasks with different response priorities based on the fault impact, and to allocate the equipment maintenance tasks to preset maintenance terminals in sequence according to the response priorities.

[0127] Optionally, the historical common failure rate of the same batch of lighting equipment is: the ratio of the number of times multiple equipment in the same batch of equipment experienced consecutive failures within a preset historical period to the total number of failures of all equipment in the same batch.

[0128] The recent failure rate of the adjacent equipment is: the percentage of other lighting equipment within a preset range centered on the lighting equipment that fails within a preset adjacent time period;

[0129] The equipment failure rate in the same circuit is the percentage of other lighting equipment that experience failures in the same power circuit as the lighting equipment.

[0130] Optionally, the data acquisition module 301 is specifically used for:

[0131] By using sensors deployed on the power module, heat sink, and light source assembly of each lighting device, at least one of the following data is collected: voltage, current, temperature, and luminous flux of the lighting device.

[0132] By using environmental monitoring nodes distributed across various storage yard areas, at least one of the following data is collected: light intensity, temperature and humidity, wind speed, and salt spray concentration in the storage yard area.

[0133] The port operations management system periodically obtains information on the division of work areas.

[0134] Optionally, the maintenance task allocation module 305 is specifically used for:

[0135] Acquire real-time location information reported by multiple preset maintenance terminals, mobile operation planning of large mobile machinery in the port, and storage location information of fault repair parts;

[0136] By combining the real-time location information, the mobile operation plan, and the warehouse location information, a preset path planning algorithm is used to determine the response time of each maintenance terminal for the equipment maintenance task;

[0137] The target maintenance terminal is selected based on the response time, and a maintenance task allocation sequence is dynamically generated based on the response priority and the response time. The equipment maintenance task is then allocated to the corresponding target maintenance terminal according to the task allocation sequence.

[0138] Optionally, the maintenance task allocation module 305 is specifically used for:

[0139] By combining the real-time location information, the mobile operation plan, and the warehouse location information, a preset path planning algorithm is used to calculate the execution path of each maintenance terminal for the equipment maintenance task;

[0140] Based on the status of the emergency lighting equipment bound to the maintenance terminal and the lighting status along the execution path, the execution risk of each maintenance terminal for the equipment maintenance task is determined;

[0141] With the objectives of minimizing the execution path, minimizing the execution risk, and minimizing the response time, a multi-objective optimization algorithm is used to select the target maintenance terminal.

[0142] Optionally, the maintenance task allocation module 305 is further configured to:

[0143] If the execution risk of the equipment maintenance task by each maintenance terminal is greater than the preset risk threshold, then two maintenance terminals are selected simultaneously by the multi-objective optimization algorithm with the goal of minimizing the execution path and minimizing the response time.

[0144] Optionally, the fault impact assessment module 304 is specifically used for:

[0145] The failure probability is weighted and corrected based on the reliability of the failure prediction model.

[0146] The area affected by the malfunction is determined by the area operation plan corresponding to the lighting equipment;

[0147] The risk coefficient of the cascading failure is weighted and corrected based on the current operation and maintenance strategy mode, workload level and / or preset risk control level;

[0148] The impact of each lighting device failure is calculated using the weighted and corrected failure probability and cascading failure risk coefficient, as well as the working area affected by the failure.

[0149] In one embodiment, a computer device is provided, the internal structure of which can be shown as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for data exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a collaborative operation and maintenance method for port equipment.

[0150] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0151] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0152] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0154] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited thereto.

[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A collaborative operation and maintenance method for port equipment, characterized in that, The method includes: Obtain the operating parameters of multiple lighting devices in the port, environmental data of the storage yard area, and the area operation plan corresponding to the lighting devices; The operating parameters and environmental data are input into a pre-trained fault prediction model to generate the fault probability of each lighting device in a future preset time period. The risk coefficient of cascading failures for each lighting device is obtained by weighting the historical common failure rate of devices in the same batch based on batch association, the recent failure rate of adjacent devices based on spatial association, and the abnormality rate of devices in the same circuit based on circuit association. The failure probability, the cascading failure risk coefficient, and the affected work area determined based on the regional work plan are weighted by a preset weighting coefficient to obtain the failure impact degree of each lighting device. Based on the impact of the fault, equipment maintenance tasks with different response priorities are established, and the equipment maintenance tasks are sequentially assigned to preset maintenance terminals according to the response priorities.

2. The method according to claim 1, characterized in that, The historical common failure rate of each lighting device in the same batch is the ratio of the number of times multiple devices in the same batch experience continuous failures within a preset historical period to the total number of failures of all devices in the same batch. The recent failure rate of the adjacent equipment is: the percentage of other lighting equipment within a preset range centered on the lighting equipment that fails within a preset adjacent time period; The equipment failure rate in the same circuit is the percentage of other lighting equipment that experience failures in the same power circuit as the lighting equipment.

3. The method according to claim 1, characterized in that, The acquisition of operating parameters of multiple lighting devices in the port, environmental data of the storage yard area, and preset work area division information includes: By using sensors deployed on the power module, heat sink, and light source assembly of each lighting device, at least one of the following data is collected: voltage, current, temperature, and luminous flux of the lighting device. By using environmental monitoring nodes distributed across various storage yard areas, at least one of the following data is collected: light intensity, temperature and humidity, wind speed, and salt spray concentration in the storage yard area. The port operations management system periodically obtains information on the division of work areas.

4. The method according to claim 1, characterized in that, The step of allocating the equipment maintenance tasks to preset maintenance terminals according to the response priority includes: Acquire real-time location information reported by multiple preset maintenance terminals, mobile operation planning of large mobile machinery in the port, and storage location information of fault repair parts; By combining the real-time location information, the mobile operation plan, and the warehouse location information, a preset path planning algorithm is used to determine the response time of each maintenance terminal for the equipment maintenance task; The target maintenance terminal is selected based on the response time, and a maintenance task allocation sequence is dynamically generated based on the response priority and the response time. The equipment maintenance task is then allocated to the corresponding target maintenance terminal according to the task allocation sequence.

5. The method according to claim 4, characterized in that, Selecting a target repair terminal based on the response time includes: By combining the real-time location information, the mobile operation plan, and the warehouse location information, a preset path planning algorithm is used to calculate the execution path of each maintenance terminal for the equipment maintenance task; Based on the status of the emergency lighting equipment bound to the maintenance terminal and the lighting status along the execution path, the execution risk of each maintenance terminal for the equipment maintenance task is determined; With the objectives of minimizing the execution path, minimizing the execution risk, and minimizing the response time, a multi-objective optimization algorithm is used to select the target maintenance terminal.

6. The method according to claim 5, characterized in that, The method further includes: If the execution risk of the equipment maintenance task by each maintenance terminal is greater than the preset risk threshold, then two maintenance terminals are selected simultaneously by the multi-objective optimization algorithm with the goal of minimizing the execution path and minimizing the response time.

7. The method according to claim 1, characterized in that, The failure probability, the cascading failure risk coefficient, and the affected work area determined based on the regional operation plan are weighted using preset weighting coefficients to obtain the failure impact degree of each lighting device, including: The failure probability is weighted and corrected based on the reliability of the failure prediction model. The area affected by the malfunction is determined by the area operation plan corresponding to the lighting equipment; The risk coefficient of the cascading failure is weighted and corrected based on the current operation and maintenance strategy mode, workload level and / or preset risk control level; The impact of each lighting device failure is calculated using the weighted and corrected failure probability and cascading failure risk coefficient, as well as the working area affected by the failure.

8. A collaborative operation and maintenance device for port equipment, characterized in that, The device includes: The data acquisition module is used to acquire the operating parameters of multiple lighting devices in the port, environmental data of the storage yard area, and the area operation plan corresponding to the lighting devices; The failure probability prediction module is used to input the operating parameters and environmental data into a pre-trained failure prediction model to generate the failure probability of each lighting device in a future preset time period. The cascading risk assessment module is used to calculate the cascading failure risk coefficient of each lighting device by weighting the historical common failure rate of the same batch of equipment, the recent failure rate of adjacent equipment, and the abnormality rate of equipment in the same circuit, based on batch, spatial and circuit correlation. The fault impact assessment module is used to calculate the fault probability, the cascading fault risk coefficient, and the affected work area determined based on the regional work plan using preset weighting coefficients to obtain the fault impact degree of each lighting device. The maintenance task allocation module is used to establish equipment maintenance tasks with different response priorities based on the fault impact, and to allocate the equipment maintenance tasks to preset maintenance terminals in sequence according to the response priority.

9. A computer device, the computer device comprising a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the collaborative operation and maintenance method for port equipment according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the collaborative operation and maintenance method for port equipment according to any one of claims 1-7.

Images