Bucket wheel machine anti-collision system and anti-collision method

Abstract

The invention discloses a bucket wheel anti-collision system and an anti-collision method, and relates to the technical field of bucket wheel anti-collision. The system comprises a data acquisition module used for acquiring operation data, environment data and historical collision data of the bucket wheel machine, the operation data comprises the position, the speed, the angle and the operation mode of the bucket wheel machine, and the environment data comprises a coal yard three-dimensional map, obstacle coordinates and meteorological data; the historical collision data comprises accident records and false alarm analysis. The state and environment of the bucket wheel machine are mastered in real time through high-precision positioning and multi-mode sensing, collision is effectively prevented in combination with intelligent graded alarm, and safety is remarkably improved. The risk is predicted through big data analysis and machine learning, the operation path is dynamically adjusted, operation is optimized, the maintenance cost is reduced, and the service life of equipment is prolonged. Meanwhile, the cloud monitoring and the mobile terminal APP support remote operation and real-time information pushing, the convenience and applicability of the system are enhanced, and the management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bucket wheel stacker-reclaimer anti-collision, and particularly relates to a bucket wheel stacker-reclaimer anti-collision system and an anti-collision method. Background Art

[0002] A bucket wheel stacker-reclaimer is a large-scale loading and unloading equipment widely used in places such as power plant coal yards and port bulk cargo yards for stacking and reclaiming operations of bulk cargo such as coal and ore. Due to its complex operating environment, the coal yard is filled with various buildings, dust-proof nets and other equipment, and the boom of the bucket wheel stacker-reclaimer is relatively long. During operation, it is easy to collide with surrounding obstacles due to reasons such as limited vision of operators, fatigue driving or equipment failures, resulting in equipment damage, operation interruption and even safety accidents.

[0003] Traditional anti-collision systems for bucket wheel stacker-reclaimers mainly rely on technologies such as track travel limit switches and simple distance sensors, and have the following defects in actual application: 1. Traditional positioning technologies cannot provide high-precision real-time position information, making it difficult to accurately judge the relative position between the bucket wheel stacker-reclaimer and obstacles, and prone to false alarms or missed alarms.

[0004] 2. Relying solely on a single sensor (such as ultrasonic or infrared ranging) cannot comprehensively perceive the complex operating environment, and has poor adaptability to dynamic obstacles (such as moving personnel and vehicles) and complex scenarios (such as dust and strong light).

[0005] 3. Lack of intelligent grading and adaptive adjustment functions, unable to take corresponding measures according to different risk levels, which is likely to cause fatigue and neglect of operators.

[0006] Therefore, a bucket wheel stacker-reclaimer anti-collision system and an anti-collision method are proposed. Summary of the Invention

[0007] The purpose of the present invention is: to solve the problems mentioned in the above background art, the present invention provides a bucket wheel stacker-reclaimer anti-collision system and an anti-collision method.

[0008] The present invention specifically adopts the following technical solutions to achieve the above purpose: a bucket wheel stacker-reclaimer anti-collision system and an anti-collision method, including: A data acquisition module, used to collect the operation data, environmental data and historical collision data of the bucket wheel stacker-reclaimer. The operation data includes the position, speed, angle and operation mode of the bucket wheel stacker-reclaimer, the environmental data includes the three-dimensional map of the coal yard, the coordinates of obstacles and meteorological data, and the historical collision data includes accident records and false alarm analysis; A data processing module for storing and analyzing the collected data. The data processing module includes a time series database and a big data analysis platform. The time series database is used to store real-time data, and the big data analysis platform is used to perform collision risk analysis in combination with historical data; A multi-modal perception module, including a variety of sensors, for real-time sensing of the environmental information around the bucket wheel stacker-reclaimer. The sensors include RTK-GPS / Beidou positioning devices, lidar, ultrasonic / infrared ranging devices, vision cameras, and inertial measurement units; A data fusion module for fusing the data collected by the multi-modal perception module, using Kalman filtering or deep learning algorithms to improve data reliability, and dynamically updating the coal yard environment in combination with SLAM technology; An alarm module for sending alarm signals of different levels according to the output results of the data processing module and the data fusion module, and performing corresponding anti-collision measures; A remote monitoring module for real-time monitoring of the status of the bucket wheel stacker-reclaimer, and providing real-time information and alarm push to the operators through a cloud visualization dashboard and a mobile APP.

[0009] Furthermore, the data processing module also includes a data playback and analysis function for replaying and analyzing historical collision events to optimize the anti-collision strategy.

[0010] Furthermore, the sensors in the multi-modal perception module are configured as follows: RTK-GPS / Beidou positioning devices for high-precision global positioning; Lidar for 3D environmental modeling and near-field obstacle detection; Ultrasonic / infrared ranging devices for short-distance anti-collision, especially suitable for the end of the boom; Vision cameras, combined with AI recognition technology, for dynamic obstacle detection, such as personnel and vehicles; Inertial measurement units for monitoring the attitude of the bucket wheel stacker-reclaimer boom to prevent mechanical collisions.

[0011] Furthermore, the alarm module adopts an intelligent hierarchical alarm mechanism, divides the alarm levels according to the distance between the bucket wheel stacker-reclaimer and the obstacle, and takes corresponding response measures, specifically including: Level 1 alarm: When the distance to the obstacle is 5 - 10 meters, give an audible and visual reminder and provide operation suggestions; Level 2 alarm: When the distance to the obstacle is 1 - 5 meters, automatically reduce the speed and give a forced intervention reminder; Level 3 alarm: When the distance to the obstacle is less than 1 meter, stop urgently and give a remote alarm.

[0012] Furthermore, the alarm module also adopts an adaptive alarm strategy, dynamically adjusts the alarm threshold in combination with the historical false alarm rate, and optimizes the alarm decision using fuzzy logic control.

[0013] Furthermore, the remote monitoring module supports user privilege management, allows users at different levels to access different data and functions, and supports a multi-language interface.

[0014] Furthermore, the data processing module uses the Hadoop / Spark framework for big data analysis and combines machine learning algorithms for collision risk prediction.

[0015] Furthermore, a predictive alarm module is also included, which predicts the collision risk of the bucket wheel stacker-reclaimer based on a machine learning model. The model uses an LSTM network for time series prediction and combines a random forest algorithm for risk classification, and outputs the collision probability within the next 5 - 10 seconds.

[0016] The predictive alarm module combines digital twin technology to simulate the movement trajectory of the bucket wheel stacker-reclaimer, dynamically generates a risk map, and adjusts the operation path in advance according to the prediction results to avoid collisions.

[0017] A collision prevention method for a bucket wheel stacker-reclaimer, applying the above system, includes the following steps: Step 1: Collect the operation data, environmental data, and historical collision data of the bucket wheel stacker-reclaimer; Step 2: Store the collected data in a time series database and perform collision risk analysis through a big data analysis platform; [[ID=(21]]Step 3: Real-time sense the environmental information around the bucket wheel stacker-reclaimer through a multi-modal perception module, and use a data fusion module to perform fusion processing on the sensed data; Step 4: According to the data processing and fusion results, send an intelligent hierarchical alarm signal through the alarm module and execute corresponding anti-collision measures; Step 5: Real-time monitor the status of the bucket wheel stacker-reclaimer through the remote monitoring module and provide real-time information and alarm push to the operator; Step 6: Predict the collision risk based on a machine learning model and dynamically adjust the operation path in combination with digital twin technology to avoid collisions.

[0018] The beneficial effects of the present invention are as follows: 1. Through a high-precision RTK-GPS / Beidou positioning device and a multi-modal perception module (including lidar, vision cameras, ultrasonic / infrared ranging devices, etc.), the present invention can perceive the operating state of the bucket wheel stacker-reclaimer and the surrounding environment in real time and comprehensively. Combined with an intelligent grading alarm mechanism, the system issues alarm signals at corresponding levels according to different risk levels and takes corresponding anti-collision measures, such as automatic speed reduction, emergency shutdown, etc., effectively avoiding the occurrence of collision accidents and significantly improving the safety of the bucket wheel stacker-reclaimer in complex operating environments.

[0019] 2. The present invention uses big data analysis and machine learning models (such as LSTM networks) to deeply analyze the collected data, can predict collision risks in advance, and dynamically generates risk maps in combination with digital twin technology. Based on the prediction results, the system automatically adjusts the operating path of the bucket wheel stacker-reclaimer and optimizes the operating parameters, thereby realizing intelligent anti-collision control. This intelligent anti-collision mechanism not only improves the operating efficiency but also reduces the equipment maintenance cost and extends the service life of the equipment.

[0020] 3. Through a cloud visualization dashboard and a mobile APP, operators can monitor the operating state, alarm information, and environmental data of the bucket wheel stacker-reclaimer in real time. The system supports remote operation, allowing operators to intervene and control at locations far from the equipment. In addition, the system also has a user permission management function to ensure that users at different levels can access corresponding data and functions, enhancing the security and applicability of the system. This remote monitoring and management mechanism improves the convenience of the system, enabling operators to manage and maintain the bucket wheel stacker-reclaimer more efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a schematic diagram of the system structure of the present invention; Figure 2 is a schematic diagram of the method flow of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Generally, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0023] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0024] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, terms such as "first", "second", etc. are only used for descriptive distinction and cannot be construed as indicating or implying relative importance.

[0025] All electrical components appearing in this article are electrically connected to an external main controller and the 220V mains power supply, and the main controller can be a conventional known device such as a computer for control.

[0026] In the description of the embodiments of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "inner", "outer", "upper", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present invention is usually placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation of the present invention.

[0027] As Figure 1 , Figure 2 shown, a bucket wheel stacker-reclaimer anti-collision system includes: A data acquisition module, which is the basis of the system and is responsible for collecting various data related to the operation of the bucket wheel stacker-reclaimer. These data include: Operation data: including the position, speed, angle, and operation mode of the bucket wheel stacker-reclaimer, etc., which are collected in real time by sensors (such as encoders, speed sensors, angle sensors) installed on the bucket wheel stacker-reclaimer.

[0028] Environmental data: including the three-dimensional map of the coal yard, obstacle coordinates, and meteorological data, etc., which are collected by sensors such as lidar and vision cameras.

[0029] Historical data: including accident records and false alarm analysis, etc., which are obtained from the equipment management system and the accident record system.

[0030] These data provide comprehensive information support for the subsequent processing and analysis of the system, ensuring that the system can accurately perceive the operation status of the bucket wheel stacker-reclaimer and the surrounding environment.

[0031] The data processing module is the central hub of the system, responsible for efficiently storing and deeply analyzing the collected data. The module uses a time-series database (such as InfluxDB) to store real-time data, ensuring efficient reading / writing and fast querying of the data. At the same time, in combination with big data analysis platforms such as Hadoop / Spark, it conducts collision risk analysis on the collected historical data and real-time data. Through big data analysis, the system can mine potential patterns in the data, identify potential collision risks in advance, and provide a scientific basis for anti-collision measures. In addition, the data processing module also includes a data playback and analysis function, which can conduct a review analysis of historical collision events and optimize the anti-collision strategy.

[0032] The core of the data processing module lies in transforming the large amount of collected data into useful information through efficient data storage and analysis technologies. The time-series database can handle high-frequency real-time data, while the Hadoop / Spark framework can handle large-scale historical data and mine the patterns therein. This combination ensures that the system can respond quickly and accurately predict collision risks.

[0033] The multi-modal perception module real-time perceives the environmental information around the bucket wheel stacker-reclaimer through multiple sensors. These sensors include: High-precision positioning device: Adopting RTK-GPS / Beidou technology, it provides centimeter-level global positioning accuracy.

[0034] LiDAR: Used for 3D environmental modeling and can detect near-field obstacles.

[0035] Ultrasonic / infrared ranging device: Used for short-distance anti-collision, especially suitable for the end of the boom.

[0036] Vision camera: Combined with AI recognition technology, it is used to detect dynamic obstacles such as people and vehicles.

[0037] Inertial measurement unit (IMU): Used to monitor the attitude of the bucket wheel stacker-reclaimer boom to prevent mechanical collisions.

[0038] Through the collaborative work of multiple sensors, the system can comprehensively perceive the environment around the bucket wheel stacker-reclaimer, improving the reliability and adaptability of the system.

[0039] The design concept of the multi-modal perception module is to achieve a comprehensive perception of complex environments through the complementary advantages of multiple sensors. For example, LiDAR can provide high-precision 3D environmental information, while the vision camera can identify dynamic obstacles. This multi-modal perception method can significantly enhance the perception ability and adaptability of the system.

[0040] The data fusion module is the core of the system's data processing, responsible for fusing the data collected by the multi-modal perception module. The module uses Kalman filtering or deep learning algorithms to fuse the data, improving the reliability and accuracy of the data. At the same time, combined with SLAM (Simultaneous Localization and Mapping) technology, it dynamically updates the coal yard environment to ensure the system's real-time response to environmental changes. Through data fusion, the system can more accurately judge the relative position and collision risk between the bucket wheel stacker-reclaimer and obstacles, reducing false alarms and missed alarms.

[0041] The key to the data fusion module lies in integrating data from different sensors through advanced algorithms, thereby improving the system's perception accuracy and reliability. Kalman filtering and deep learning algorithms can effectively handle the noise and uncertainty in sensor data, while SLAM technology can update the environmental model in real time to ensure the system's adaptability.

[0042] The alarm module is the core of the system's safety warning, responsible for issuing alarm signals of different levels according to the output results of the data processing module and the data fusion module, and executing corresponding anti-collision measures. The module adopts an intelligent hierarchical alarm mechanism, divides the alarm level according to the distance between the bucket wheel stacker-reclaimer and the obstacle, and takes corresponding response measures. For example: When the distance to the obstacle is 5 - 10 meters, it issues an audible and visual reminder and provides operation suggestions.

[0043] When the distance to the obstacle is 1 - 5 meters, it automatically reduces the speed and gives a forced intervention reminder.

[0044] When the distance to the obstacle is less than 1 meter, it immediately stops the machine and issues a remote alarm.

[0045] In addition, the alarm module also adopts an adaptive alarm strategy, dynamically adjusts the alarm threshold in combination with the historical false alarm rate, and uses fuzzy logic control to optimize the alarm decision. Through the intelligent hierarchical alarm and the adaptive alarm strategy, the system can take corresponding measures according to different risk levels, avoid false alarms and missed alarms, and improve the operator's vigilance.

[0046] The alarm module ensures the accuracy and timeliness of the alarm signal through the intelligent hierarchical alarm mechanism and the adaptive alarm strategy. The intelligent hierarchical alarm mechanism can take corresponding measures according to different risk levels, while the adaptive alarm strategy can dynamically adjust the alarm threshold according to the historical false alarm rate, thereby improving the intelligence level of the system.

[0047] The remote monitoring module is the core of the system's remote management, responsible for real-time monitoring of the bucket wheel stacker-reclaimer's status, and providing real-time information and alarm push to operators through the cloud visualization dashboard and the mobile APP. The module supports user permission management, allowing users at different levels to access different data and functions, and supports a multi-language interface. Through the remote monitoring module, operators can understand the operating status of the bucket wheel stacker-reclaimer anytime and anywhere, receive alarm information in a timely manner and perform remote operations, improving the convenience and operation efficiency of the system.

[0048] The remote monitoring module realizes real-time monitoring and remote management of the bucket wheel stacker-reclaimer through cloud technology and mobile devices. The cloud visualization dashboard can display the status and alarm information of the bucket wheel stacker-reclaimer in real time, while the mobile APP can provide real-time alarm push and remote operation functions. This design not only improves the convenience of the system, but also enhances the operation efficiency and security of the system.

[0049] The remote monitoring module in this embodiment has multiple functions, aiming to improve the convenience and operation efficiency of the system. The specific functions are as follows: Real-time monitoring: Through the cloud visualization dashboard, the remote monitoring module can display the operating status, alarm information and environmental data of the bucket wheel stacker-reclaimer in real time. Operators can understand the operating conditions of the bucket wheel stacker-reclaimer anytime and anywhere through devices such as computers, tablets or mobile phones.

[0050] Alarm push: The remote monitoring module supports the mobile APP and can push alarm information to operators in real time. Even if the operator is not on site, they can receive alarm notifications in a timely manner and perform remote operations through the APP.

[0051] User permission management: The remote monitoring module supports user permission management, allowing users at different levels to access different data and functions. This permission management mechanism ensures the security of the system and prevents unauthorized access and operations.

[0052] Multi-language support: The remote monitoring module supports a multi-language interface, which is convenient for operators with different language backgrounds to use. This function enables the system to better adapt to the international operation environment and improves the universality of the system.

[0053] Through these functions, the remote monitoring module not only improves the operator's monitoring ability of the bucket wheel stacker-reclaimer, but also enhances the operation convenience and applicability of the system.

[0054] The data processing module in this embodiment uses the Hadoop / Spark framework for big data analysis and combines machine learning algorithms for collision risk prediction. Specifically as follows: Big Data Analysis: Through the Hadoop / Spark framework, the data processing module can efficiently process large-scale historical data and real-time data. This data includes the operating data of the bucket wheel stacker / reclaimer, environmental data, and historical collision data, etc. Through in-depth analysis of this data, the system can identify potential collision risk patterns and provide a scientific basis for anti-collision measures.

[0055] Machine Learning Algorithms: The data processing module combines machine learning algorithms such as LSTM networks and random forest algorithms to predict collision risks. These algorithms can predict the collision probability of the bucket wheel stacker / reclaimer in the next period of time based on historical data and real-time data, so as to take preventive measures in advance.

[0056] The anti-collision system of the bucket wheel stacker / reclaimer of the present invention realizes comprehensive perception, real-time analysis, and intelligent alarm of the operating state of the bucket wheel stacker / reclaimer and the surrounding environment through the comprehensive application of a variety of advanced technologies.

[0057] Through the RTK-GPS / Beidou positioning device and multi-modal sensors, the system can provide high-precision positioning information and comprehensive environmental perception, and effectively identify potential collision risks.

[0058] The intelligent grading alarm mechanism and adaptive alarm strategy can take corresponding measures according to different risk levels, avoid false alarms and missed alarms, and improve the alertness of operators.

[0059] The remote monitoring module supports real-time monitoring and remote operation. Operators can understand the operating state of the bucket wheel stacker / reclaimer at any time through the cloud visualization dashboard and the mobile APP, receive alarm information in a timely manner, and perform remote operations.

[0060] The data playback and analysis function can help operators and managers deeply analyze the causes of collision events, optimize the anti-collision strategy, and improve the safety and reliability of the system.

[0061] The predictive alarm module combines digital twin technology to simulate the movement trajectory of the bucket wheel stacker / reclaimer, dynamically generate a risk map, and adjust the operation path in advance according to the prediction results to avoid the occurrence of collision accidents and improve operation efficiency and safety.

[0062] The present invention also provides a method for preventing collisions of a bucket wheel stacker / reclaimer, and the specific steps are as follows: Step 1, Data Acquisition: Collect the operating data, environmental data, and historical collision data of the bucket wheel stacker / reclaimer. This enables the system to obtain detailed information on the operating state of the bucket wheel stacker / reclaimer and the surrounding environment, providing a solid foundation for subsequent collision risk assessment. Step 2: Data Storage and Analysis: Store the collected data in a time-series database and conduct collision risk analysis through a big data analysis platform. Through efficient data storage and in-depth analysis, the system can quickly respond and accurately predict collision risks, providing a scientific basis for anti-collision measures.

[0063] Step 3: Multimodal Sensing and Data Fusion: Use the multimodal sensing module to continuously sense the environmental information around the bucket wheel stacker-reclaimer, and use the data fusion module to fuse the sensed data. Through multimodal sensing and data fusion, the system can comprehensively perceive the environment around the bucket wheel stacker-reclaimer, improve the reliability and adaptability of the system, and reduce false alarms and missed alarms.

[0064] Step 4: Intelligent Hierarchical Alarm: Based on the data processing and fusion results, send intelligent hierarchical alarm signals through the alarm module and execute corresponding anti-collision measures. The intelligent hierarchical alarm mechanism and adaptive alarm strategy can take corresponding measures according to different risk levels, avoid false alarms and missed alarms, and improve the alertness of operators and the intelligence level of the system.

[0065] Step 5: Remote Monitoring and Real-time Feedback: Use the remote monitoring module to continuously monitor the status of the bucket wheel stacker-reclaimer and provide real-time information and alarm push to the operator. Through remote monitoring and real-time feedback, the operator can understand the operating status of the bucket wheel stacker-reclaimer anytime and anywhere, receive alarm information in a timely manner and perform remote operations, improving the convenience and operation efficiency of the system.

[0066] Step 6: Predictive Alarm and Dynamic Adjustment: Predict the collision risk based on a machine learning model and dynamically adjust the operation path in combination with digital twin technology to avoid collisions. Through predictive alarm and dynamic adjustment, the system can predict collision risks in advance and take preventive measures to avoid the occurrence of collision accidents, improving operation efficiency and the service life of equipment.

[0067] In summary, the present invention can comprehensively and real-time perceive the operating status of the bucket wheel stacker reclaimer and the surrounding environment through a high-precision RTK-GPS / Beidou positioning device and a multi-modal sensing module (including lidar, vision cameras, ultrasonic / infrared ranging devices, etc.). Combining with an intelligent hierarchical alarm mechanism, the system issues alarm signals at corresponding levels according to different risk levels and takes corresponding anti-collision measures, such as automatic speed reduction, emergency shutdown, etc., effectively avoiding the occurrence of collision accidents and significantly improving the safety of the bucket wheel stacker reclaimer in complex operating environments. The present invention uses big data analysis and machine learning models (such as LSTM networks) to deeply analyze the collected data, can predict collision risks in advance, and dynamically generates risk maps in combination with digital twin technology. Based on the prediction results, the system automatically adjusts the operating path of the bucket wheel stacker reclaimer and optimizes the operating parameters, thereby realizing intelligent anti-collision control. This intelligent anti-collision mechanism not only improves the operating efficiency but also reduces the equipment maintenance cost and extends the service life of the equipment. Through the cloud visualization dashboard and the mobile APP, the operator can monitor the operating status, alarm information, and environmental data of the bucket wheel stacker reclaimer in real time. The system supports remote operation, allowing the operator to intervene and control at a location far from the equipment. In addition, the system also has a user permission management function to ensure that users at different levels can access the corresponding data and functions, enhancing the security and applicability of the system. This remote monitoring and management mechanism improves the convenience of the system, enabling the operator to manage and maintain the bucket wheel stacker reclaimer more efficiently.

[0068] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, various changes and improvements will occur to the present invention, and all these changes and improvements fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A bucket wheel stacker-reclaimer anti-collision system, characterized in that, Including: A data acquisition module, which is used to collect the operation data, environmental data and historical collision data of the bucket wheel stacker-reclaimer. The operation data includes the position, speed, angle and operation mode of the bucket wheel stacker-reclaimer. The environmental data includes the 3D map of the coal yard, the coordinates of obstacles and meteorological data. The historical collision data includes accident records and false alarm analysis; A data processing module, which is used to store and analyze the collected data. The data processing module includes a time series database and a big data analysis platform. The time series database is used to store real-time data. The big data analysis platform is used to conduct collision risk analysis in combination with historical data; A multi-modal perception module, which includes a variety of sensors and is used to perceive the environmental information around the bucket wheel stacker-reclaimer in real time. The sensors include an RTK-GPS / Beidou positioning device, a lidar, an ultrasonic / infrared ranging device, a vision camera and an inertial measurement unit; A data fusion module, which is used to perform fusion processing on the data collected by the multi-modal perception module, adopts the Kalman filter or deep learning algorithm to improve the data reliability, and dynamically updates the coal yard environment in combination with the SLAM technology; An alarm module, which is used to issue alarm signals of different levels according to the output results of the data processing module and the data fusion module, and execute corresponding anti-collision measures; A remote monitoring module, which is used to monitor the status of the bucket wheel stacker-reclaimer in real time, and provide real-time information and alarm push to the operator through the cloud visualization dashboard and the mobile APP.

2. The anti-collision system of a bucket wheel stacker-reclaimer according to claim 1, wherein, The data processing module also includes a data playback and analysis function, which is used to conduct a review analysis of historical collision events and optimize the anti-collision strategy.

3. The anti-collision system for a bucket wheel stacker according to claim 1, wherein, The sensors in the multi-modal perception module are configured as follows: An RTK-GPS / Beidou positioning device, which is used for high-precision global positioning; A lidar, which is used for 3D environment modeling and near-field obstacle detection; An ultrasonic / infrared ranging device, which is used for short-distance anti-collision, especially suitable for the end of the boom; A vision camera, which is used for dynamic obstacle detection, such as personnel and vehicles, in combination with AI recognition technology; An inertial measurement unit, which is used to monitor the attitude of the boom of the bucket wheel stacker-reclaimer to prevent mechanical collision.

4. The anti-collision system of a bucket wheel stacker-reclaimer according to claim 1, wherein The alarm module adopts an intelligent grading alarm mechanism, divides the alarm level according to the distance between the bucket wheel stacker-reclaimer and the obstacle, and takes corresponding response measures, specifically including: Level 1 alarm: When the distance from the obstacle is 5-10 meters, give an audible and visual reminder and provide operation suggestions; Level 2 alarm: When the distance from the obstacle is 1-5 meters, automatically reduce the speed and give a forced intervention reminder; Level 3 alarm: When the distance from the obstacle is less than 1 meter, stop urgently and give a remote alarm.

5. The anti-collision system of a bucket wheel stacker-reclaimer according to claim 4, characterized in that, The alarm module also adopts an adaptive alarm strategy, dynamically adjusts the alarm threshold in combination with the historical false alarm rate, and optimizes the alarm decision by using fuzzy logic control.

6. The anti-collision system of a bucket wheel stacker-reclaimer according to claim 1, characterized in that, The remote monitoring module supports user permission management, allows users at different levels to access different data and functions, and supports multi-language interfaces.

7. The anti-collision system of a bucket wheel stacker-reclaimer according to claim 1, wherein, The data processing module uses the Hadoop / Spark framework for big data analysis and combines machine learning algorithms for collision risk prediction.

8. The anti-collision system of a bucket wheel stacker-reclaimer according to claim 7, characterized in that, It further includes a predictive alarm module that predicts the collision risk of the bucket wheel stacker-reclaimer based on a machine learning model. The model uses an LSTM network for time series prediction and combines the random forest algorithm for risk classification, and outputs the collision probability within the next 5-10 seconds.

9. The anti-collision system of a bucket wheel stacker-reclaimer according to claim 1, characterized in that, The predictive alarm module combines digital twin technology to simulate the movement trajectory of the bucket wheel stacker-reclaimer, dynamically generates a risk map, and adjusts the operation path in advance according to the prediction results to avoid collisions.

10. A collision prevention method for a bucket wheel stacker-reclaimer, applying the system according to any one of claims 1 to 9, characterized in that, It includes the following steps: Step 1: Collect the operation data, environmental data, and historical collision data of the bucket wheel stacker-reclaimer; Step 2: Store the collected data in a time series database and perform collision risk analysis through a big data analysis platform; Step 3: Use the multi-modal perception module to continuously perceive the environmental information around the bucket wheel stacker-reclaimer, and use the data fusion module to fuse and process the perceived data; Step 4: According to the data processing and fusion results, send an intelligent hierarchical alarm signal through the alarm module and execute corresponding anti-collision measures; Step 5: Use the remote monitoring module to continuously monitor the status of the bucket wheel stacker-reclaimer and provide real-time information and alarm push to the operator; Step 6: Predict the collision risk based on a machine learning model and dynamically adjust the operation path in combination with digital twin technology to avoid collisions.

Images