Operation safety early warning method and device for rail-mounted container crane

Abstract

The present invention provides an operation safety warning method and device for a rail-mounted container gantry crane, relating to the technical field of crane operation safety, including: integrating an unmanned aerial vehicle and an image monitoring module to obtain multi-perspective images; applying virtual reality technology to expand the visible range with the traction part of the rail-mounted container gantry crane as the center, overlay environmental information, and obtain safety area and obstacle markings; constructing a monitoring sensor network to monitor each component of the crane in real time, obtain synchronous data and predict maintenance requirements; using fuzzy logic to set a dynamic control interval and establishing an operation safety warning model for decision-making. Through the present invention, it is possible to solve the problem in the prior art that due to the inability to comprehensively capture potential safety hazards in the working environment and difficult to immediately identify safety areas and obstacles, the identification of potential safety hazards in the operation environment is inaccurate. It realizes real-time monitoring of each component of the rail-mounted container gantry crane, and predicts maintenance requirements through data analysis, improving the timeliness and accuracy of maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of crane operation safety, and in particular to an operation safety early warning method and device for a rail-mounted container-specific crane. Background Art

[0002] As key equipment for port operations, cranes have many potential safety hazards during operation, such as overloading, collision, and overturning. Once an accident occurs, it will not only cause equipment damage, but may also cause serious consequences such as safety problems and environmental pollution.

[0003] At present, the existing technology is unable to fully capture the safety hazards in the working environment and it is difficult to instantly identify safe areas and obstacles, resulting in inaccurate identification of safety hazards in the working environment, further affecting the operational safety, efficiency and effectiveness of maintenance management of rail-mounted container cranes. Summary of the invention

[0004] The purpose of the present invention is to provide an operation safety warning method and device for a rail-mounted container crane, so as to solve the problem that the prior art cannot fully capture the safety hazards in the working environment, and it is difficult to immediately identify safe areas and obstacles, resulting in inaccurate identification of safety hazards in the working environment.

[0005] In view of the above problems, the present invention provides an operation safety early warning method and device for a rail-mounted container crane.

[0006] In the first aspect, the present invention provides an operation safety warning method for a rail-mounted container crane, which is implemented by an operation safety warning device of the rail-mounted container crane, wherein the operation safety warning method for the rail-mounted container crane comprises: integrating unmanned aerial vehicle equipment, wherein the unmanned aerial vehicle equipment is equipped with an image monitoring module, and performs all-round monitoring of a high-altitude perspective to obtain multi-perspective monitoring images; applying virtual reality technology, based on the multi-perspective monitoring images, expanding the visible range with the traction part of the rail-mounted container crane as the center, and using environmental information superposition to obtain safety area marks and obstacle marks; constructing A monitoring sensor network is used to conduct real-time monitoring of various components of the rail-mounted container crane to obtain synchronous monitoring data, which includes load status, mechanical wear, and structural stress. Maintenance needs are predicted through data analysis of the monitoring sensor network. Based on the safety area mark and obstacle mark, a dynamic adjustment control interval is set using fuzzy logic control logic. The dynamic adjustment control interval includes a speed safety threshold and an acceleration safety threshold. Operation logs and maintenance records of the rail-mounted container crane are collected, and an operation safety early warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and maintenance needs is established to make operation safety decisions.

[0007] In a second aspect, the present invention further provides an operation safety warning device for a rail-mounted container crane, which is used to execute the operation safety warning method for a rail-mounted container crane as described in the first aspect, wherein the operation safety warning device for a rail-mounted container crane comprises: a monitoring image acquisition unit, which is used to integrate an unmanned aerial vehicle device, and the unmanned aerial vehicle device is equipped with an image monitoring module, which performs all-round monitoring of a high-altitude perspective and obtains multi-perspective monitoring images; an environmental information superposition unit, which is used to apply virtual reality technology, based on the multi-perspective monitoring images, expand the visible range with the traction part of the rail-mounted container crane as the center, and use environmental information superposition to obtain safety area marks and obstacle marks; a maintenance demand prediction unit, which is used to construct a monitoring system; A sensor network is used to perform real-time monitoring of various components of the rail-mounted container crane to obtain synchronous monitoring data, wherein the synchronous monitoring data includes load status, mechanical wear, and structural stress, and maintenance requirements are predicted through data analysis of the monitoring sensor network; an adjustment control interval setting unit is used to set a dynamic adjustment control interval based on the safety area mark and the obstacle mark using fuzzy logic control logic, wherein the dynamic adjustment control interval includes a speed safety threshold and an acceleration safety threshold; a data collection unit is used to collect operation logs and maintenance records of the rail-mounted container crane, and establish an operation safety early warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and maintenance requirements to make an operation safety decision.

[0008] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0009] By integrating drone equipment, the drone equipment is equipped with an image monitoring module to monitor the high-altitude perspective in all directions and obtain multi-perspective monitoring images; applying virtual reality technology, based on the multi-perspective monitoring images, the visual range is expanded with the traction part of the rail-mounted container crane as the center, and environmental information is superimposed to obtain safety area markings and obstacle markings; constructing a monitoring sensor network to conduct real-time monitoring of various components of the rail-mounted container crane to obtain synchronous monitoring data, which includes load status, mechanical wear, and structural stress, and predicting maintenance needs through data analysis of the monitoring sensor network; based on the safety area markings and obstacle markings, using the model Fuzzy logic control logic is used to set a dynamic adjustment control interval, wherein the dynamic adjustment control interval includes a speed safety threshold and an acceleration safety threshold; operation logs and maintenance records of the rail-mounted container crane are collected, and an operation safety early warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and maintenance requirements is established to make operation safety decisions. This effectively solves the problem that the existing technology cannot fully capture safety hazards in the working environment, and it is difficult to instantly identify safety areas and obstacles, resulting in inaccurate identification of safety hazards in the working environment. This realizes real-time monitoring of each component of the rail-mounted container crane, and predicts maintenance needs through data analysis, thereby improving the timeliness and accuracy of maintenance.

[0010] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0012] Figure 1 It is a schematic diagram of the process of the operation safety early warning method of the rail-mounted container crane of the present invention;

[0013] Figure 2 It is a structural schematic diagram of the operation safety early warning device of the rail-mounted container crane of the present invention.

[0014] Description of reference numerals:

[0015] Monitoring image acquisition unit 11, environmental information superposition unit 12, maintenance demand prediction unit 13, adjustment control interval setting unit 14, data collection unit 15. DETAILED DESCRIPTION

[0016] The present invention provides an operation safety warning method and device for a rail-mounted container crane, thereby solving the problem that the prior art is unable to fully capture safety hazards in the working environment and is difficult to instantly identify safe areas and obstacles, resulting in inaccurate identification of safety hazards in the working environment. The present invention realizes real-time monitoring of various components of the rail-mounted container crane, predicts maintenance needs through data analysis, and improves the timeliness and accuracy of maintenance.

[0017] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0018] For example, please refer to the attached Figure 1 The present invention provides an operation safety early warning method for a rail-mounted container crane, wherein the operation safety early warning method for a rail-mounted container crane is applied to an operation safety early warning device for a rail-mounted container crane, and the operation safety early warning method for a rail-mounted container crane specifically comprises the following steps:

[0019] S1: Integrate unmanned aerial vehicle equipment, wherein the unmanned aerial vehicle equipment is equipped with an image monitoring module to perform all-round monitoring from a high altitude perspective and obtain multi-perspective monitoring images.

[0020] Specifically, according to the specific needs of the monitoring task, such as monitoring range, flight altitude, and endurance, select the appropriate type of drone, including multi-rotor drones, fixed-wing drones, and vertical take-off and landing fixed-wing drones. Equipped with a high-resolution camera or camera as the core component of the image monitoring module, it ensures that clear and delicate image information can be captured. Special sensors such as infrared cameras and thermal imagers can be optionally equipped. According to the specific requirements of the monitoring task, plan the flight area and route of the drone to ensure that there are no no-fly zones and dangerous obstacles in the flight area. The flight area can be accurately marked and analyzed with the help of tools such as geographic information system (GIS). According to the monitoring needs, set the parameters of the drone such as flight altitude, speed, and shooting angle to ensure that the drone can fly and shoot according to the predetermined plan. For areas that require continuous monitoring, the drone's cruise mode can be set to achieve long-term and uninterrupted data collection. According to the pre-set flight plan and mission parameters, start the drone to fly, and collect flight status and monitoring data in real time during the flight. According to needs, the drone's flight altitude, angle and other parameters can be adjusted to obtain more comprehensive and detailed monitoring images. The acquired monitoring images are preprocessed, such as denoising, contrast enhancement, etc., to improve the image quality and clarity, and finally a multi-view monitoring image is obtained.

[0021] S2: Applying virtual reality technology, based on the multi-view monitoring images, the visible range is expanded with the traction part of the rail-mounted container crane as the center, and environmental information is superimposed to obtain safety area marks and obstacle marks.

[0022] Specifically, through the image monitoring module carried by the drone, multiple monitoring images are obtained from a high-altitude perspective, and these images cover the operating area of ​​the crane and its surrounding environment. Using image fusion technology, these multi-perspective monitoring images are spliced ​​and fused to form a complete and coherent three-dimensional view. The rail-mounted container crane includes but is not limited to a rail-mounted container gantry crane and a rail-mounted container bridge crane. The core area of ​​visualization is determined with the traction part of the rail-mounted container crane as the center. Through VR technology, the visible range of the core area is expanded, including horizontal and vertical expansion, to ensure that the entire operating area of ​​the crane is included in the visualization range. In addition to image data, weather conditions, terrain information, other obstacle locations, etc. are also included. These environmental data are superimposed on the expanded visible range in the form of layers. In this way, users can not only see the operating area of ​​the crane, but also all environmental information related to it. Based on the environmental information and the operating parameters of the crane, the scope of the safe area is calculated, including comprehensive consideration of factors such as the crane's operating radius, load capacity, and terrain conditions. Using image processing technology, obstacles within the visible range, such as other vehicles, buildings, and personnel, are automatically identified. Corresponding marks are generated on the safe area and obstacles. Safe areas can be indicated by highlight colors such as green or blue, while obstacles can be indicated by warning colors such as red or yellow.

[0023] S3: Construct a monitoring sensor network to perform real-time monitoring of various components of the rail-mounted container crane to obtain synchronous monitoring data, which includes load status, mechanical wear, and structural stress. Through data analysis of the monitoring sensor network, maintenance needs are predicted.

[0024] Specifically, the sensor network can be divided into the edge layer and the platform layer. The edge layer collects the operating data of each component of the crane, including load status, mechanical wear (such as vibration, temperature), structural stress, etc. The platform layer uses intelligent technologies such as machine learning and deep learning to analyze the collected data in an integrated manner to achieve real-time monitoring and predictive maintenance of the equipment status. According to the monitoring needs, appropriate sensors such as gravity sensors, vibration sensors, temperature sensors, stress sensors, etc. are selected and installed in key positions such as the crane's load system, transmission components (such as motors, pulleys, wheels), and structural parts. The sensor network is constructed using wireless communication technologies such as ZigBee, LoRa, and NB-IoT to achieve real-time data transmission. Network nodes include field monitoring nodes (terminal nodes), routing nodes, coordinator nodes, etc. to ensure that data covers the entire crane. Sensors are installed on key components of the crane to collect data such as load status, vibration, temperature, and stress in real time. Data preprocessing is performed on the platform layer, including filtering, demodulation, FFT processing, calculation of kurtosis, etc., to remove noise, and machine learning and deep learning algorithms are used to perform pattern recognition on the preprocessed data to identify patterns, trends, and anomalies in the data. Based on the data analysis results, the maintenance needs of the crane are predicted.

[0025] S4: Based on the safety area mark and the obstacle mark, a dynamic adjustment control interval is set using fuzzy logic control logic, and the dynamic adjustment control interval includes a speed safety threshold and an acceleration safety threshold.

[0026] Specifically, fuzzy logic control logic is used to process this information. Fuzzy logic is a method for dealing with uncertainty and ambiguity, allowing decisions to be made based on imprecise or fuzzy inputs. The safety zone markers and obstacle markers are converted into input variables that can be understood by the fuzzy logic system. For example, the distance of the safety zone is converted into fuzzy sets such as near, medium, and far, and the location, size, speed, and other information of the obstacle are also converted into corresponding fuzzy sets. According to the operation requirements and safety standards of the crane, a series of fuzzy rules are formulated by technical personnel to describe how the crane should adjust its speed and acceleration in different situations. For example, if the obstacle is within the safety zone and the distance is close, the crane should slow down or stop; if the obstacle is outside the safety zone and the distance is far, the crane can maintain the current speed or accelerate. The fuzzy logic system is used for reasoning to derive the control strategy that the crane should adopt. Finally, according to the output of the fuzzy logic control logic, a dynamically adjusted control interval is set, including the speed safety threshold and the acceleration safety threshold. According to the operating environment and safety requirements of the crane, a reasonable speed range is set as the speed safety threshold, which is set according to factors such as the load state, mechanical wear, and structural stress of the crane. Similarly, a reasonable acceleration range is set as the acceleration safety threshold, which is set according to the dynamic performance and operation requirements of the crane.

[0027] S5: collecting the operation log and maintenance record of the rail-mounted container crane, and establishing an operation safety early warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and the maintenance demand to make an operation safety decision.

[0028] Specifically, the operation log contains detailed information such as the time, location, operator, load condition, speed, acceleration, fault record, safety incident, etc. of each operation. The operation log is exported from the control system of the crane regularly, or recorded in real time using a dedicated data acquisition tool. The maintenance record contains the time, maintenance personnel, maintenance content (such as replacement of parts, adjustment of parameters, lubrication, etc.), problems found, measures taken and results, etc. of each maintenance. A maintenance record management system can be established to require maintenance personnel to fill in and submit maintenance records after each maintenance. The collected operation logs and maintenance records are sorted to ensure the integrity and accuracy of the data. The data in the operation log is analyzed to identify abnormal conditions and potential risks during the operation of the crane. Combined with the maintenance records, the wear condition, failure frequency and cause of each component of the crane are analyzed. Statistical analysis and data mining techniques are used to extract key features and indicators and establish an early warning model. Based on the collected and analyzed data, advanced algorithms such as machine learning and fuzzy logic control are used to build an operation safety early warning model, which can comprehensively consider multiple aspects such as the operating status, maintenance status and environmental factors of the crane. The model is trained using historical data, the model parameters are adjusted to optimize the performance, and the accuracy and generalization ability of the model are evaluated through methods such as cross-validation. Receive the operation log and maintenance record data of the crane in real time, and use the model for safety warning and decision support. According to the analysis results of the early warning model, dynamically adjust the control ranges such as the speed safety threshold and acceleration safety threshold of the crane. When the model predicts potential risks, it automatically triggers safety measures such as deceleration and parking. When the model identifies that key components are about to reach their life limit or there is a potential failure, it will issue maintenance warnings in time and take corresponding countermeasures.

[0029] Further, step S4 of the present invention also includes:

[0030] Based on the safety area mark and the obstacle mark, the climatic conditions of the on-site operation of the rail-mounted container crane are identified, and the climatic conditions include wind speed, temperature, and humidity; based on historical operation examples, in combination with the climatic conditions of the on-site operation of the rail-mounted container crane, an environmental adaptability channel is set; based on the environmental adaptability channel, with the operation safety requirements under different climatic conditions as constraints, a dynamic adjustment control interval is set, and synchronized to the control terminal of the interactively connected rail-mounted container crane according to the short message service protocol.

[0031] Specifically, the climatic conditions of the crane's on-site operation, including wind speed, temperature, humidity, etc., are collected in real time using sensor networks or weather station data. The collected climatic condition data is combined with safety zone markers and obstacle markers. Historical operation examples are analyzed to find out the crane's operating performance and safety record under different climatic conditions. Based on the historical data analysis results, an environmental adaptability channel is defined, that is, the parameter range within which the crane can operate safely under different climatic conditions. The environmental adaptability channel is optimized in combination with the crane's technical specifications and operating requirements. According to the operating safety requirements under different climatic conditions, the constraints of the dynamic adjustment control interval are determined. Based on the environmental adaptability channel, a dynamic adjustment control interval is set, including speed safety threshold, acceleration safety threshold, etc. When the climatic conditions change, the control interval is automatically adjusted according to the environmental adaptability channel to ensure that the crane always operates within the safe range. A short message service protocol is formulated to synchronize the dynamic adjustment control interval to the control terminal of the interactively connected rail-mounted container crane. When the dynamic adjustment control interval changes, the relevant information is synchronized to the control terminal according to the short message service protocol. After receiving the synchronization information, the control terminal automatically adjusts the control parameters of the crane to ensure that it operates safely within the new control interval. Through environmental adaptability adjustment and safety threshold self-adaptation, the accuracy and reliability of operational safety warnings can be improved and safety accidents caused by severe weather can be reduced.

[0032] Further, step S2 of the present invention also includes:

[0033] The drone device is connected to an image monitoring module, which integrates an infrared imaging function to obtain a multi-perspective primary processed image; based on the multi-perspective primary processed image, an image enhancement algorithm is used to obtain a multi-perspective processed image and replace the multi-perspective monitoring image; after completing the image replacement operation, a deep learning algorithm is introduced to automatically detect obstacles, and environmental information is superimposed to obtain safe area marks and obstacle marks.

[0034] Specifically, the image monitoring module carried by the UAV equipment is connected to the crane control system to ensure the transmission of real-time image data. The infrared imaging function is integrated in the image monitoring module to facilitate the acquisition of clear images at night or in low light conditions. The mobility of the UAV equipment is used to obtain primary processed images of the working environment from multiple perspectives. Image enhancement algorithms, such as contrast enhancement and sharpening, are applied to the multi-perspective primary processed images to improve the image quality. After being processed by the image enhancement algorithm, a higher-quality multi-perspective processed image is obtained. The original multi-perspective monitoring image is replaced with the enhanced multi-perspective processed image. Deep learning algorithms, such as convolutional neural networks (CNNs), are introduced to automatically detect obstacles in the multi-perspective processed images. The deep learning algorithm will automatically identify obstacles in the image and mark their location and type. The detected obstacle information is superimposed with other information of the working environment (such as safety areas, working boundaries, etc.) to generate a comprehensive environmental information map. In the environmental information map, the location of safety areas and obstacles is clearly marked to provide intuitive guidance for the safe operation of the crane. The safety of night operations is improved by integrating image enhancement and night vision functions.

[0035] Further, step S5 of the present invention also includes:

[0036] A spatial analysis algorithm is used to identify high-density operation areas, where the high-density operation areas are used to identify overlapping areas where multiple rail-mounted container cranes operate simultaneously. A path planning algorithm is used to perform dynamic obstacle avoidance planning in the high-density operation areas, and determine a first safety distance between the multiple rail-mounted container cranes. A collision detection algorithm is used to predict potential collision risks in real time in the high-density operation areas, and determine a second safety distance between multiple containers, where the multiple rail-mounted container cranes are matched with the multiple containers. Operation scheduling optimization is performed based on the first safety distance between the multiple rail-mounted container cranes and the second safety distance between the multiple containers.

[0037] Specifically, collect the operation data of multiple rail-mounted container cranes, including the operation location, operation time, operation frequency, etc. Apply spatial analysis algorithms to process the collected data, identify the overlapping areas where multiple cranes operate simultaneously, i.e., the high-density operation areas, and mark the identified high-density operation areas. Within the high-density operation areas, use path planning algorithms to plan the optimal travel paths for each crane to ensure that they can operate efficiently and safely. According to the path planning results, determine the first safety distance between multiple cranes to prevent collisions between them. Use collision detection algorithms to predict potential collision risks in real time within the high-density operation areas, including the collision risks between cranes and between cranes and containers. According to the collision detection results, determine the second safety distance between multiple containers to ensure that the cranes will not collide with the containers during operation. Based on the first safety distance and the second safety distance, formulate a refined operation scheduling strategy to ensure that multiple cranes can operate efficiently and orderly. During operation, dynamically adjust the scheduling strategy according to the real-time operation data and collision prediction results to adapt to the changing operation environment. Set the goals of operation scheduling optimization, such as improving operation efficiency, reducing collision risks, and reducing waiting time, and evaluate and adjust the scheduling strategy according to these goals. Improve the safety of the high-density operation areas.

[0038] Furthermore, the present invention further includes:

[0039] Connect to a database, where the database is used to accumulate the operation data of the rail-mounted container cranes in the long term; based on the database, use long short-term memory networks to predict the maintenance requirements; through the maintenance requirements, with the goal of reducing the unplanned downtime duration, optimize the maintenance plan within a safe and controllable range.

[0040] Specifically, select a database system, such as MySQL, PostgreSQL, or MongoDB, to store the operation data of the rail-mounted container crane. Design the data table structure, including the basic information of the crane, operation records, maintenance records, fault records, etc. Use appropriate database connection tools or programming languages ​​(such as Python's pymysql library) to connect to the database to ensure that the data can be accessed and updated in real time. Extract the operation data of the crane from the database and perform preprocessing, such as data cleaning, feature selection, normalization, etc. Build an LSTM neural network model and use the preprocessed data as input to learn the operation mode and failure mode of the crane. Train the LSTM model using historical operation data and adjust the model parameters to optimize the prediction performance. Use the trained LSTM model to predict the maintenance needs of the crane based on the real-time operation data, including maintenance time, maintenance type, etc. Based on the predicted maintenance needs, formulate maintenance strategies, including scheduled maintenance, preventive maintenance, and condition-based maintenance. Analyze historical unplanned downtime data, identify the main reasons for downtime, and evaluate the impact of different maintenance strategies on the duration of unplanned downtime. With the goal of reducing unplanned downtime, optimize the maintenance plan within a safe and controllable range, taking into account factors such as availability, maintenance cost, and maintenance effect. Execute the optimized maintenance plan and monitor the operating status and maintenance effect of the crane in real time. Make necessary adjustments based on feedback.

[0041] Furthermore, the present invention also includes:

[0042] In the high-density operation area, collaborative operation scheduling is performed based on the multiple rail-mounted container cranes to obtain first collaborative scheduling information; in the high-density operation area, collaborative obstacle avoidance scheduling is performed based on the multiple rail-mounted container cranes to obtain second collaborative scheduling information; a local real-time communication network corresponding to the multiple rail-mounted container cranes in the high-density operation area is established, and collaborative management is performed in combination with the first collaborative scheduling information and the second collaborative scheduling information.

[0043] Specifically, collect real-time operation data of multiple rail-mounted container cranes, including operation location, operation status, operation tasks, etc. Analyze the data to determine the operation capacity and operation requirements of each crane. According to the operation requirements and crane capacity, formulate a collaborative operation plan to clarify the operation tasks and operation sequence of each crane. Execute the collaborative operation plan, monitor the operation status of each crane in real time, and obtain the first collaborative scheduling information, including operation progress, operation efficiency, etc. In the high-density operation area, monitor the position and movement trajectory of each crane, as well as the position and status of the container in real time. According to the real-time monitoring data, formulate a collaborative obstacle avoidance strategy to ensure that each crane will not collide with each other or with the container during the operation. Execute the collaborative obstacle avoidance strategy, monitor the obstacle avoidance effect in real time, and obtain the second collaborative scheduling information, including obstacle avoidance success rate, obstacle avoidance time, etc. Design the architecture of the local real-time communication network, including network topology, communication protocol, data transmission rate, etc. Deploy necessary network equipment, such as wireless routers and switches, in the high-density operation area to ensure real-time communication between cranes. Test the local real-time communication network to ensure the stability and reliability of the network. Optimize the network based on the test results to improve communication efficiency. Integrate the first collaborative scheduling information and the second collaborative scheduling information, and display the operation status and obstacle avoidance status of each crane in real time through a visual interface. Monitor the scheduling effect in real time and make necessary adjustments based on feedback to ensure the smooth progress of collaborative operations and obstacle avoidance. Improve the safety of multi-crane collaborative operations through collaborative operation scheduling and collaborative obstacle avoidance planning.

[0044] Furthermore, the present invention also includes:

[0045] Based on the operation log and the dynamically adjusted control interval, automatic risk avoidance control is performed in response to safety events to generate a risk avoidance control channel; based on the maintenance record and maintenance requirements, self-learning optimization is performed in response to safety events to generate a self-learning optimization channel; the risk avoidance control channel is connected to the self-learning optimization channel, and an operation safety early warning model corresponding to the operation log and the dynamically adjusted control interval, and the maintenance record and maintenance requirements is established.

[0046] Specifically, operation logs are collected from the crane control system, including information such as operation instructions, operation time, and operators. According to the operation characteristics and safety requirements of the crane, a dynamic adjustment control interval is defined, that is, the operation range that the crane can safely adjust during operation. When a safety event occurs, such as a sudden change in wind force, uneven ground, etc., automatic risk avoidance control is performed based on the operation log and the dynamic adjustment control interval to adjust the operation of the crane to avoid potential safety risks. The logic of automatic risk avoidance control is encapsulated into a risk avoidance control channel for real-time response to safety events and risk avoidance operations. Maintenance records are collected from the crane maintenance system, including maintenance time, maintenance content, maintenance personnel, etc. Based on the maintenance records, the maintenance needs of the crane are analyzed to identify common failure modes and maintenance cycles. When a safety event occurs, such as a crane failure, operating error, etc., self-learning optimization is performed based on the maintenance records and maintenance needs to adjust the control strategy and maintenance plan of the crane to improve the safety of the operation. The logic and algorithm of self-learning optimization are encapsulated into a self-learning optimization channel for real-time response to safety events and optimization operations. The risk avoidance control channel and the self-learning optimization channel are connected to achieve real-time response and processing of safety events and safety incidents. Integrate operation logs, dynamically adjust control intervals, maintenance records and maintenance requirements to provide comprehensive data support for model warning and decision-making. Based on the integrated data and information, establish a warning mechanism to monitor and warn potential operational safety risks in real time. According to the actual operation situation and warning effect, optimize and iterate the operational safety warning model to improve its accuracy and reliability.

[0047] Based on the above schemes, it is known that there is a certain amount of shaking during container transportation. In order to avoid safety problems caused by shaking during transportation, further, a detailed description of the training process of the operation safety warning model is given: collect the operation log of the rail-mounted container crane, including date and time stamp, operator ID, crane ID, load weight (tons), lifting height (meters), operation duration (minutes), operation type (loading and unloading, moving, etc.); collect maintenance records, including maintenance date, crane ID, maintenance type (routine inspection, emergency repair, etc.), replacement parts (motor, wire rope, brake, etc.), component life (hours or times); connect to the database to accumulate crane operation data, including real-time load (kilograms), mechanical wear indicators (vibration frequency, temperature rise, etc.), structural stress (sensor readings), and number of operation cycles; record the environmental conditions of the operation site, including wind speed (meters / second), temperature (degrees Celsius), humidity (percentage), and precipitation (mm / hour); then, clean, standardize and feature the collected operation logs, maintenance records, operation data, and environmental data The process is processed to eliminate the influence of different dimensions; through correlation analysis and importance evaluation, the most influential features for the operation safety warning model are selected, such as operation frequency, load change rate, etc.; then, according to the nature of the problem, a suitable algorithm is selected, such as long short-term memory network (LSTM); the processed data is divided into training set (75%), validation set (15%) and test set (10%); the model is trained with the training set data, the model parameters are adjusted, and the validation set is used for hyperparameter optimization; the stability and generalization ability of the model are evaluated by cross-validation method; the final performance of the model is evaluated using the test set, corresponding to indicators such as accuracy and recall rate; further, the operation safety warning model is integrated, including, combining automatic risk avoidance control logic to generate risk avoidance control channels; combining maintenance records and requirements to generate self-learning optimization channels; combining risk avoidance control and self-learning optimization channels with operation logs and maintenance records to form a complete operation safety warning model; further, collaborative operation and real-time communication are used to obtain collaborative operation and obstacle avoidance scheduling information in high-density operation areas; a real-time communication network is established to realize information sharing among multiple cranes.

[0048] In the actual application process, it also includes continuously monitoring the performance of the model in actual operations; regularly updating operation logs, maintenance records and operation data; and continuously iterating and optimizing the model based on new data and feedback. This ensures that the operation safety warning model can accurately predict and respond to potential safety risks, and improve the operation safety and efficiency of rail-mounted container cranes.

[0049] In summary, the operation safety early warning method of the rail-mounted container crane provided by the present invention has the following technical effects:

[0050] By integrating drone equipment, the drone equipment is equipped with an image monitoring module to monitor the high-altitude perspective in all directions and obtain multi-perspective monitoring images; applying virtual reality technology, based on the multi-perspective monitoring images, the visual range is expanded with the traction part of the rail-mounted container crane as the center, and environmental information is superimposed to obtain safety area markings and obstacle markings; constructing a monitoring sensor network to conduct real-time monitoring of various components of the rail-mounted container crane to obtain synchronous monitoring data, which includes load status, mechanical wear, and structural stress, and predicting maintenance needs through data analysis of the monitoring sensor network; based on the safety area markings and obstacle markings, using the model Fuzzy logic control logic is used to set a dynamic adjustment control interval, wherein the dynamic adjustment control interval includes a speed safety threshold and an acceleration safety threshold; operation logs and maintenance records of the rail-mounted container crane are collected, and an operation safety early warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and maintenance requirements is established to make operation safety decisions. This effectively solves the problem that the existing technology cannot fully capture safety hazards in the working environment, and it is difficult to instantly identify safety areas and obstacles, resulting in inaccurate identification of safety hazards in the working environment. This realizes real-time monitoring of each component of the rail-mounted container crane, and predicts maintenance needs through data analysis, thereby improving the timeliness and accuracy of maintenance.

[0051] Embodiment 2: Based on the operation safety warning method of the rail-mounted container crane in the above embodiment, the present invention also provides an operation safety warning device for the rail-mounted container crane, as shown in the attached figure. Figure 2 The operation safety warning device of the rail-mounted container crane includes:

[0052] The monitoring image acquisition unit 11 is used to integrate unmanned aerial vehicle equipment. The unmanned aerial vehicle equipment is equipped with an image monitoring module to perform all-round monitoring of high-altitude viewing angles and acquire multi-viewing angle monitoring images.

[0053] The environmental information superposition unit 12 is used to apply virtual reality technology, based on the multi-view monitoring images, expand the visible range with the traction part of the rail-mounted container crane as the center, and use environmental information superposition to obtain safety area marks and obstacle marks.

[0054] The maintenance demand prediction unit 13 is used to construct a monitoring sensor network to perform real-time monitoring of various components of the rail-mounted container crane to obtain synchronous monitoring data, which includes load status, mechanical wear, and structural stress, and predict maintenance needs through data analysis of the monitoring sensor network.

[0055] The adjustment control interval setting unit 14 is used to set a dynamic adjustment control interval based on the safety area mark and the obstacle mark using fuzzy logic control logic, and the dynamic adjustment control interval includes a speed safety threshold and an acceleration safety threshold.

[0056] The data collection unit 15 is used to collect the operation log and maintenance record of the rail-mounted container crane, and establish an operation safety warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and the maintenance demand to make an operation safety decision.

[0057] Furthermore, the control interval setting unit 14 in the operation safety warning device for the rail-mounted container crane is also used for:

[0058] Based on the safety area mark and the obstacle mark, the climatic conditions of the on-site operation of the rail-mounted container crane are identified, and the climatic conditions include wind speed, temperature, and humidity; based on historical operation examples, in combination with the climatic conditions of the on-site operation of the rail-mounted container crane, an environmental adaptability channel is set; based on the environmental adaptability channel, with the operation safety requirements under different climatic conditions as constraints, a dynamic adjustment control interval is set, and synchronized to the control terminal of the interactively connected rail-mounted container crane according to the short message service protocol.

[0059] Furthermore, the environmental information superposition unit 12 in the operation safety warning device of the rail-mounted container crane is also used for:

[0060] The drone device is connected to an image monitoring module, which integrates an infrared imaging function to obtain a multi-perspective primary processed image; based on the multi-perspective primary processed image, an image enhancement algorithm is used to obtain a multi-perspective processed image and replace the multi-perspective monitoring image; after completing the image replacement operation, a deep learning algorithm is introduced to automatically detect obstacles, and environmental information is superimposed to obtain safe area marks and obstacle marks.

[0061] Furthermore, the data collection unit 15 in the operation safety warning device of the rail-mounted container crane is also used for:

[0062] A spatial analysis algorithm is used to identify high-density operation areas, where the high-density operation areas are used to identify overlapping areas where multiple rail-mounted container cranes operate simultaneously. A path planning algorithm is used to perform dynamic obstacle avoidance planning in the high-density operation areas, and determine a first safety distance between the multiple rail-mounted container cranes. A collision detection algorithm is used to predict potential collision risks in real time in the high-density operation areas, and determine a second safety distance between multiple containers, where the multiple rail-mounted container cranes are matched with the multiple containers. Operation scheduling optimization is performed based on the first safety distance between the multiple rail-mounted container cranes and the second safety distance between the multiple containers.

[0063] Furthermore, the operation safety warning device of the rail-mounted container crane also includes a maintenance plan optimization unit, which is used to:

[0064] A database is connected, and the database is used to accumulate the operation data of the rail-mounted container crane over a long period of time; based on the database, the maintenance demand is predicted using a long short-term memory network; through the maintenance demand, the maintenance plan is optimized within a safe and controllable range with the goal of reducing the unplanned downtime.

[0065] Furthermore, the operation safety warning device of the rail-mounted container crane also includes a collaborative management unit, which is used to:

[0066] In the high-density operation area, collaborative operation scheduling is performed based on the multiple rail-mounted container cranes to obtain first collaborative scheduling information; in the high-density operation area, collaborative obstacle avoidance scheduling is performed based on the multiple rail-mounted container cranes to obtain second collaborative scheduling information; a local real-time communication network corresponding to the multiple rail-mounted container cranes in the high-density operation area is established, and collaborative management is performed in combination with the first collaborative scheduling information and the second collaborative scheduling information.

[0067] Furthermore, the operation safety warning device of the rail-mounted container crane also includes a self-learning optimization channel unit, which is used to:

[0068] Based on the operation log and the dynamically adjusted control interval, automatic risk avoidance control is performed in response to safety events to generate a risk avoidance control channel; based on the maintenance record and maintenance requirements, self-learning optimization is performed in response to safety events to generate a self-learning optimization channel; the risk avoidance control channel is connected to the self-learning optimization channel, and an operation safety early warning model corresponding to the operation log and the dynamically adjusted control interval, and the maintenance record and maintenance requirements is established.

[0069] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1The operation safety warning method and specific examples of the rail-mounted container crane in the first embodiment are also applicable to the operation safety warning device of the rail-mounted container crane in this embodiment. Through the detailed description of the operation safety warning method of the rail-mounted container crane, those skilled in the art can clearly know the operation safety warning device of the rail-mounted container crane in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0070] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0071] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. An operation safety early warning method for a rail-mounted container crane, characterized in that: include: Integrate unmanned aerial vehicle equipment, which is equipped with an image monitoring module to monitor the high-altitude viewing angle in all directions and obtain multi-view monitoring images; Applying virtual reality technology, based on the multi-view monitoring images, the visual range is expanded with the traction part of the rail-mounted container crane as the center, and environmental information is superimposed to obtain safety area marks and obstacle marks; Constructing a monitoring sensor network to conduct real-time monitoring of various components of the rail-mounted container crane to obtain synchronous monitoring data, which includes load status, mechanical wear, and structural stress, and predicting maintenance needs through data analysis of the monitoring sensor network; Based on the safety area mark and the obstacle mark, a dynamic adjustment control interval is set by using fuzzy logic control logic, and the dynamic adjustment control interval includes a speed safety threshold and an acceleration safety threshold; Collecting the operation log and maintenance record of the rail-mounted container crane, establishing an operation safety early warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and the maintenance demand to make an operation safety decision; Wherein, establishing the operation log and the dynamically adjusted control interval, the operation safety early warning model corresponding to the maintenance record and the maintenance demand to make an operation safety decision also includes: Using a spatial analysis algorithm to identify high-density operating areas, the high-density operating areas are used to identify overlapping areas where multiple rail-mounted container cranes are operating simultaneously; Using a path planning algorithm, dynamic obstacle avoidance planning is performed in the high-density operation area to determine a first safe distance between the plurality of rail-mounted container cranes; Using a collision detection algorithm, predicting potential collision risks in real time in the high-density operation area, determining a second safe distance between a plurality of containers, and matching the plurality of rail-mounted container-specific cranes with the plurality of containers; Based on the first safety distance between the multiple rail-mounted container-specific cranes and the second safety distance between the multiple containers, operation scheduling optimization is performed.

2. The operation safety early warning method of the rail-mounted container crane according to claim 1, characterized in that: Based on the safety area mark and the obstacle mark, a dynamic adjustment control interval is set using fuzzy logic control logic, including: Based on the safety area mark and the obstacle mark, identifying the climatic conditions for on-site operation of the rail-mounted container crane, the climatic conditions including wind speed, temperature, and humidity; Based on historical operation examples and combined with the climatic conditions of on-site operation of rail-mounted container cranes, an environmental adaptability channel is set up; Based on the environmental adaptability channel, a dynamically adjusted control interval is set with the operational safety requirements under different climatic conditions as constraints, and synchronized to the control terminal of the interactively connected rail-mounted container crane according to the short message service protocol.

3. The operation safety early warning method of the rail-mounted container crane according to claim 2, characterized in that: Environmental information is superimposed to obtain safe area markings and obstacle markings, and also includes: Connect the drone device to carry an image monitoring module, integrate infrared imaging function, and obtain multi-view primary processed images; Based on the multi-view primary processed image, an image enhancement algorithm is used to obtain a multi-view processed image and replace the multi-view monitoring image; After completing the image replacement operation, a deep learning algorithm is introduced to automatically detect obstacles, and environmental information is superimposed to obtain safe area marks and obstacle marks.

4. The operation safety early warning method of the rail-mounted container crane according to claim 1, characterized in that: include: Connecting to a database, the database is used to accumulate the operation data of the rail-mounted container crane over a long period of time; Based on the database, using a long short-term memory network, predicting the maintenance demand; Through the maintenance requirements, the maintenance plan is optimized within a safe and controllable range with the goal of reducing unplanned downtime.

5. The operation safety early warning method of the rail-mounted container crane according to claim 4, characterized in that: Use spatial analysis algorithms to identify high-density work areas, including: In the high-density operation area, performing collaborative operation scheduling based on the plurality of rail-mounted container-specific cranes to obtain first collaborative scheduling information; In the high-density operation area, performing coordinated obstacle avoidance scheduling based on the plurality of rail-mounted container cranes to obtain second coordinated scheduling information; A local real-time communication network corresponding to the multiple rail-mounted container cranes in the high-density operation area is established, and collaborative management is performed in combination with the first collaborative scheduling information and the second collaborative scheduling information.

6. The operation safety early warning method of the rail-mounted container crane according to claim 5, characterized in that: include: Based on the operation log and the dynamically adjusted control interval, automatic risk avoidance control is performed in response to emergencies to generate a risk avoidance control channel; Based on the maintenance records and maintenance requirements, self-learning optimization is performed in response to security events to generate a self-learning optimization channel; The risk avoidance control channel is connected to the self-learning optimization channel, and an operation safety early warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and maintenance requirements is established.

7. An operation safety warning device for a rail-mounted container crane, characterized in that: The steps for implementing the operation safety warning method of the rail-mounted container crane according to any one of claims 1 to 6, wherein the operation safety warning device of the rail-mounted container crane comprises: A monitoring image acquisition unit is used to integrate unmanned aerial vehicle equipment, wherein the unmanned aerial vehicle equipment is equipped with an image monitoring module to perform all-round monitoring of high-altitude viewing angles and acquire multi-viewing angle monitoring images; An environmental information superposition unit is used to apply virtual reality technology, based on the multi-view monitoring images, expand the visual range with the traction part of the rail-mounted container crane as the center, and use environmental information superposition to obtain safety area marks and obstacle marks; A maintenance demand prediction unit is used to construct a monitoring sensor network to perform real-time monitoring of various components of the rail-mounted container crane to obtain synchronous monitoring data, wherein the synchronous monitoring data includes load status, mechanical wear, and structural stress, and to predict maintenance demand through data analysis of the monitoring sensor network; An adjustment control interval setting unit, configured to set a dynamic adjustment control interval based on the safety area mark and the obstacle mark using fuzzy logic control logic, wherein the dynamic adjustment control interval includes a speed safety threshold and an acceleration safety threshold; A data collection unit, used to collect the operation log and maintenance record of the rail-mounted container crane, establish an operation safety early warning model corresponding to the operation log and the dynamic adjustment control interval, and the maintenance record and the maintenance demand to make an operation safety decision; Among them, the operation log and the dynamic adjustment control interval, the maintenance record and the operation safety warning model corresponding to the maintenance demand are established to make operation safety decisions, and the device is also used to execute the following method: Using a spatial analysis algorithm to identify high-density operating areas, the high-density operating areas are used to identify overlapping areas where multiple rail-mounted container cranes are operating simultaneously; Using a path planning algorithm, dynamic obstacle avoidance planning is performed in the high-density operation area to determine a first safe distance between the plurality of rail-mounted container cranes; Using a collision detection algorithm, predicting potential collision risks in real time in the high-density operation area, determining a second safe distance between a plurality of containers, and matching the plurality of rail-mounted container-specific cranes with the plurality of containers; Based on the first safety distance between the multiple rail-mounted container-specific cranes and the second safety distance between the multiple containers, operation scheduling optimization is performed.

Images