A shipping machine safety intelligent auxiliary system and method

Abstract

The application discloses a kind of shipment machinery safety intelligent auxiliary system and method, it is related to intelligent safety system field, including, with the environmental data after pre-processing is fused using deep learning model, and the best path from current location to destination is calculated by search algorithm, based on the best path, the safety hidden danger on the best path is calculated using deep learning technology, the safety hidden danger calculated is prompted to operator, operator checks operating state, and provides response measure, to collect the response data of shipment machinery, the present application is by collecting environmental data and pre-processing, realized the comprehensive capture of environmental information and noise filtering, the output prediction value of safety hidden danger is calculated using decision tree model, realized the prediction of safety hidden danger on path, so that the system can identify potential risk point in advance, the safety hidden danger calculated is prompted to operator, collect the response data of shipment machinery, improve the response capability of operator to safety hidden danger.

Description

Technical Field

[0001] This invention relates to the field of intelligent safety systems, and in particular to an intelligent auxiliary system and method for the safety of transport machinery. Background Technology

[0002] With the continuous improvement of industrial automation, loading and unloading machinery is being used more and more widely in industries such as logistics and construction. Traditional loading and unloading machinery mainly relies on manual operation, which is prone to safety accidents due to human error. Advances in sensor technology have made it more convenient and accurate to collect information about the surrounding environment of the machinery.

[0003] However, existing intelligent safety assistance systems for loading machinery still have shortcomings. First, most systems rely on a single type of sensor for data collection, resulting in insufficient environmental perception. Second, regarding path planning, although existing research has incorporated deep learning models for path optimization, these methods neglect the assessment of safety hazards along the path and cannot fully consider unexpected situations encountered during actual operation. Furthermore, existing systems are relatively weak in terms of operator feedback mechanisms, lacking effective closed-loop control strategies to dynamically adjust the machinery's action strategies, thus limiting the system's adaptability and flexibility. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent auxiliary system and method for the safety of transport machinery, which solves the problems of incomplete environmental perception and neglect of safety hazard assessment for transport machinery.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide a safe intelligent assistance method for loading machinery, which includes using multiple sensors to collect environmental data around the loading machinery after startup and performing preprocessing.

[0008] The preprocessed environmental data is fused using a deep learning model, and the optimal path from the current location to the destination is calculated using a search algorithm.

[0009] Based on the optimal path, deep learning technology is used to calculate the security risks on the optimal path;

[0010] The calculated safety hazards are alerted to the operator, who then checks the operating status and provides countermeasures, thereby collecting response data from the loading machinery.

[0011] Adjust the operating status of the loading machinery based on the response data of the loading machinery.

[0012] As a preferred embodiment of the intelligent auxiliary method for the safety of loading machinery described in this invention, the various sensors include a high-definition camera, radar, and a GPS receiver;

[0013] The environmental data includes distance, speed, and specific geographical location;

[0014] The preprocessed data includes removing noise from the environmental data through filtering techniques, deleting outliers, and converting the environmental data into a uniform format.

[0015] As a preferred embodiment of the intelligent safety assistance method for loading machinery described in this invention, the method includes the following steps: fusing preprocessed environmental data using a deep learning model and calculating the optimal path from the current location to the destination using a search algorithm.

[0016] Choose a convolutional neural network model;

[0017] The location and shape of obstacles, as well as the distance, speed and direction of target objects, are extracted from the preprocessed environmental data, and the extracted environmental features are fused in a weighted manner.

[0018] The greedy best-first search algorithm is used to calculate the comprehensive score of each path from the current location to the destination and assign them numbers. The path with the highest comprehensive score is selected as the best path. The expression is:

[0019]

[0020] F(p i )=C(p i )+α×∑ j≠i C(p j );

[0021]

[0022] Among them, C(p) i ) represents the location point p i Environmental characteristic score, Z represents the normalization constant, d(p i ) indicates position p i The distance to the target object, η represents the velocity attenuation coefficient, v(p i ) indicates position p i The speed of the target object, s(p) i ) indicates position p i The size of the obstacle, θ(p) i ) indicates position p i The direction of the target object, ||p i || indicates position p i The Euclidean norm, F(p) i) represents the location point p i The comprehensive environmental characteristic score, C(p) j ) represents the location point p j Environmental characteristic score, α represents the adjusted location point p j The score for p i The weighting coefficient for the overall score, where j represents the index variable of all positions in the traversal path, and i represents the identifier position p. i index variable, This indicates the number of the best path with the highest overall score. This represents the path number that achieves the maximum value across all paths in the set. Y represents the number of one of the paths from the origin to the destination, and p represents the number of the set of all paths. i Representing a path A location point, g represents the destination, H(p) i (g) represents position p i The estimated distance to destination g, where o represents the total number of obstacles. Indicates position p i The number of surrounding obstacles, d(p) i ,o) represents position p i The distance to obstacle o.

[0023] As a preferred embodiment of the intelligent safety assistance method for loading machinery described in this invention, the method includes the following steps: Based on the optimal path, deep learning technology is used to calculate the output prediction value of safety hazards along the optimal path.

[0024] Based on the best path with the highest comprehensive score, a decision tree model is built using deep learning technology, and an integrated development environment is used to deploy the decision tree model to the actual environment.

[0025] The geographical location is input into the decision tree model to calculate the output prediction value of the safety hazard on the optimal path. The expression is:

[0026]

[0027] Where y represents the output predicted value of the safety hazard, n represents the number of decision tree models, f represents the index of the decision tree, and w i G represents the weight of the f-th decision tree. f (x) represents the prediction function of the f-th decision tree.

[0028] As a preferred embodiment of the intelligent safety assistance method for loading machinery described in this invention, the method involves setting thresholds to classify the degree of safety hazards, including the following steps:

[0029] The mean and standard deviation of the output predicted values ​​of safety hazards are calculated, and low and high thresholds are set based on the mean and standard deviation to classify the degree of safety hazards.

[0030] When the output prediction value of the safety hazard is less than or equal to the low threshold, the degree of safety hazard on the best path is judged to be low risk.

[0031] When the predicted value of the safety hazard output is greater than the high threshold, the safety hazard level on the best path is judged to be high risk.

[0032] When the predicted output value of a safety hazard is greater than the low threshold and less than or equal to the high threshold, the degree of safety hazard on the optimal path is judged to be of medium risk.

[0033] As a preferred embodiment of the intelligent safety assistance method for loading machinery described in this invention, the method includes the following steps: identifying safety hazards and alerting the operator; the operator checks the operating status and provides countermeasures; thereby collecting response data from the loading machinery.

[0034] The display information for low-risk safety hazards is set to green, medium-risk to yellow, and high-risk to red, and the display information is presented to the operator.

[0035] When the level of safety hazard is low, listen to the sounds of the surrounding environment and use high-definition cameras to monitor the environment, while saving the monitoring data in the log.

[0036] When the level of safety hazard is medium risk, the loading machinery shall be switched to manual mode and the operating speed shall be reduced, and the medium risk situation shall be reported to the relevant departments.

[0037] When the level of safety hazard is high, stop the operation of all loading machinery and arrange for all staff to evacuate to a safe area. At the same time, immediately contact team members to plan an alternative route.

[0038] Based on the corresponding countermeasures for the different risks described, response data of the loading machinery is collected.

[0039] As a preferred embodiment of the intelligent safety assistance method for loading machinery described in this invention, adjusting the operating state of the loading machinery based on its response data includes the following steps:

[0040] Collect response data, including the speed and distance of the loading machinery following the implementation of countermeasures;

[0041] If the response data does not deviate from the target speed and distance, the loading machinery will operate normally.

[0042] If the response data deviates from the target speed and distance, immediately stop the operation of the loading machinery, check the working status of the machinery's control unit and sensors, repair the faulty parts, and wait for the machinery to return to normal operation before continuing the operation;

[0043] If only the speed is deviating, remind the operator to pay attention and adjust the speed of the loading machinery to bring it back to the target speed;

[0044] If the only deviation is in distance, replan the route and notify the operator to follow the new route.

[0045] Secondly, the present invention provides a safe intelligent auxiliary system for loading machinery, including an environmental data collection module, which is responsible for collecting environmental data around the loading machinery after startup using multiple sensors and preprocessing it.

[0046] The environmental data fusion and path planning module is responsible for using deep learning models to fuse preprocessed environmental data and using search algorithms to calculate the best path from the current location to the destination.

[0047] The safety hazard identification module is responsible for calculating the safety hazards on the optimal path based on the optimal path using deep learning technology;

[0048] The safety alert and response module is responsible for alerting the operator to the calculated safety hazards, allowing the operator to check the operating status and provide response measures.

[0049] The response data collection module is responsible for collecting response data from the loading machinery;

[0050] The dynamic adjustment module is responsible for adjusting the operating status of the loading machinery based on the response data of the loading machinery.

[0051] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the intelligent auxiliary method for safe transport machinery as described in the first aspect of the present invention.

[0052] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the intelligent auxiliary method for safe transport machinery as described in the first aspect of the present invention.

[0053] The beneficial effects of this invention are as follows: By using multiple sensors to collect and preprocess environmental data, comprehensive capture of environmental information and noise filtering are achieved, improving data quality and environmental perception accuracy. A decision tree model is constructed using deep learning technology to calculate predicted output values ​​for safety hazards, enabling the system to predict safety hazards along the path. This allows the system to identify potential risk points in advance, alert operators to the calculated safety hazards, and collect response data from the transport machinery, thereby improving the operator's ability to respond to safety hazards. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a flowchart of the intelligent safety assistance method for loading machinery in Example 1.

[0056] Figure 2 This is a judgment diagram of the intelligent auxiliary method for the safety of loading machinery in Example 1. Detailed Implementation

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0060] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides a method for intelligent assistance in the safety of loading machinery, including the following steps:

[0061] S1. Collect and preprocess environmental data around the loading machinery after startup using multiple sensors, including the following steps:

[0062] Multiple sensors, including high-definition cameras, radar, and GPS receivers;

[0063] Environmental data includes distance, speed, and specific geographical location;

[0064] Preprocessing the data includes removing noise from the environmental data through filtering techniques, deleting outliers, and converting the environmental data into a uniform format.

[0065] S2. The preprocessed environmental data is fused using a deep learning model, and the optimal path from the current location to the destination is calculated using a search algorithm, including the following steps.

[0066] Choose a convolutional neural network model;

[0067] The location and shape of obstacles, as well as the distance, speed and direction of target objects, are extracted from the preprocessed environmental data, and the extracted environmental features are fused in a weighted manner.

[0068] Weighting refers to the processing method of assigning different degrees of importance to different data or variables in data analysis, statistical calculation and modeling. The core idea of ​​weighting is to give different weights to each element according to its importance and credibility. The weight is a numerical value that can reflect the relative importance of a specific data or factor in the final result. In mathematics and statistics, weighting is usually used to calculate weighted average, weighted sum or weighted fusion.

[0069] Greedy best-first search is a heuristic search algorithm. Its basic idea is to choose the seemingly optimal path to move forward at each step, that is, to always choose the node closest to the target node for expansion. If the target node is not reached, all unvisited neighbor nodes of the current node are added to the priority queue and the value of each neighbor node is calculated.

[0070] The greedy best-first search algorithm is used to calculate the comprehensive score of each path from the current location to the destination and assign them numbers. The path with the highest comprehensive score is selected as the best path. The expression is:

[0071]

[0072] F(p i )=C(p i )+α×∑ j≠i C(p j );

[0073]

[0074] Among them, C(p) i ) represents the location point p iThe environmental feature score, Z represents the normalization constant, used to normalize the scores of all location points, d(p i ) indicates position p i The closer the target object, the greater the distance d(p) is. i The smaller, The larger the value, the more important the position. η represents the velocity decay coefficient, used to adjust the degree of influence of velocity on the score. i ) indicates position p i The speed of the target object increases with increasing speed, v(p) i ) 2 The larger the value, the smaller the impact of speed at that position on the score; s(p i ) indicates position p i The size of the obstacle, p i (p i The larger θ(p) is, the less the complexity of that position affects the score. i ) indicates position p i The direction of the target object is represented by a cosine function; the more drastic the change in direction, the higher the cosine function. i The smaller the value of ||p, the less the change in direction at that position affects the score. i || indicates position p i The larger the Euclidean norm, the better. The smaller the value, the less the relative position of that location affects the score; F(p) i ) represents the location point p i The comprehensive environmental characteristic score, C(p) j ) represents the location point p j Environmental characteristic score, α represents the adjusted location point p j The score for p i The weighted coefficient representing the overall score's influence; this coefficient determines the impact of the scores of surrounding points on the current point p. i How much influence does the score have? If α is large, the influence of surrounding points is greater; conversely, if α is small, the influence of surrounding points is smaller. j represents the index variable of all points along the traversal path. i Indicates the location point p. i index variable, This indicates the number of the best path with the highest overall score. This represents the path number that achieves the maximum value across all paths in the set. Y represents the number of one of the paths from the origin to the destination, and p represents the number of the set of all paths. i Representing a path A location point, g represents the destination, H(p) i (g) represents position pi The estimated distance to destination g, where o represents the total number of obstacles. Indicates position p i The number of surrounding obstacles, d(p) i ,o) represents position p i The distance to obstacle o;

[0075] The derivation of the expression for calculating the optimal path is as follows:

[0076] First, initialize an empty priority queue and add the starting point to the queue, while also setting a priority queue for each position p. i Initialize an infinitely large overall score and set the starting overall score to zero;

[0077] For each location point p i Calculate its overall score:

[0078] F(p i )=C(p i )+α×∑ j≠i C(p j );

[0079] Here C(p) i ) is the location point p i The environmental characteristic score has been calculated using the previous formula, and the comprehensive score F(p) i It includes the environmental feature score of the location itself and the influence of surrounding locations;

[0080] For each path, calculate its overall score:

[0081]

[0082] Retrieve the position p with the highest current score from the priority queue. i Mark it as visited and update the overall score of its neighboring locations. If the overall score of a neighboring location is smaller than before, update its overall score and add it to the queue.

[0083] If the current expanded position is the endpoint, stop the search and return the current path with the maximum value as the optimal path, expressed as:

[0084]

[0085] If the currently extended location is not the endpoint, the path is extended again until an empty endpoint is found.

[0086] S3. Based on the optimal path, use deep learning technology to calculate the output prediction value of safety hazards on the optimal path, including the following steps.

[0087] Based on the best path with the highest comprehensive score, a decision tree model is built using deep learning technology, and an integrated development environment is used to deploy the decision tree model to the actual environment.

[0088] An integrated development environment (IDE) is a software application used for software development that integrates various development tools and functions into a single graphical user interface, enabling developers to efficiently write, debug, run, and manage software code.

[0089] The geographical location is input into the decision tree model to calculate the output prediction value of the safety hazard on the optimal path. The expression is:

[0090]

[0091] Where y represents the predicted output value of the safety hazard, n represents the number of decision tree models, which is determined based on experiments, f represents the index of the decision tree, used to distinguish different decision trees, and is assigned sequentially according to the order of decision tree training, w i G represents the weight of the f-th decision tree, which reflects its contribution to the overall model prediction. f (x) represents the prediction function of the f-th decision tree, which takes geographical location as input and outputs a predicted value of safety hazards. It is obtained by training the decision tree model. For each decision tree, the model is fitted using the training data to obtain a function that takes geographical location as input and outputs a predicted value.

[0092] For each decision tree index, the input geographic location information is used and the predicted value of each decision tree is multiplied by its corresponding weight. The weighted predicted values ​​of all decision trees are summed, and the final y is the output predicted value of the security risk after combining the prediction results of all decision trees.

[0093] The mean and standard deviation of the output predicted values ​​of safety hazards are calculated, and low and high thresholds are set based on the mean and standard deviation to classify the degree of safety hazards.

[0094] When the output prediction value of the safety hazard is less than or equal to the low threshold, the degree of safety hazard on the best path is judged to be low risk.

[0095] When the predicted value of the safety hazard output is greater than the high threshold, the safety hazard level on the best path is judged to be high risk.

[0096] When the predicted output value of a safety hazard is greater than the low threshold and less than or equal to the high threshold, the degree of safety hazard on the optimal path is judged to be of medium risk.

[0097] S4. The identified safety hazards are alerted to the operator, who then checks the operating status and provides countermeasures, thereby collecting response data from the loading machinery. This includes the following steps:

[0098] The display information for low-risk safety hazards is set to green, medium-risk to yellow, and high-risk to red. At the same time, three types of speaker voice prompts are set: "Current path is in a low-risk state," "Please note, current path has a medium risk, please operate with caution," and "Warning, current path has a high risk, please take immediate action." All display information is displayed to the operator.

[0099] When the safety hazard level is low, listen to the sounds of the surrounding environment, use a high-definition camera to scan the environmental changes around the loading machinery at set intervals, use the dashboard to monitor the environment, and save the monitoring data in the log.

[0100] When the level of safety hazard is medium risk, the loading machinery is switched to manual mode and the operating speed is reduced. Magnetometers and vibration sensors are used for auxiliary monitoring. The sensor readings and monitoring data of image data are recorded and the medium risk situation is reported to the relevant departments.

[0101] When the level of safety hazard is high, stop the operation of all loading machinery and arrange for all staff to evacuate to a safe area. At the same time, immediately contact team members to plan an alternative route.

[0102] Based on the response measures under different risks, collect response data of the loading machinery.

[0103] S5. Adjust the operating status of the loading machinery based on the response data of the loading machinery, including the following steps:

[0104] Collect response data, including the speed and distance of the loading machinery following the implementation of countermeasures;

[0105] If the response data does not deviate from the target speed and distance, the loading machinery should be operated normally and the system status should be monitored regularly.

[0106] If the response data deviates from the target speed and distance, immediately stop the operation of the loading machinery, find out the cause of the deviation, check the working status of the machinery's control unit and sensors and repair the faulty parts. If there is electromagnetic interference, use shielded cables to isolate sensitive equipment to prevent electromagnetic interference from entering the control system. Wait for the machinery to return to normal operation before continuing the operation.

[0107] If only the speed is deviating, check the motor system for faults such as overload, wear, or electrical faults. Clean the motor surface with compressed air and a special cleaning agent and add lubricating oil to the bearings. At the same time, remind the operator to pay attention and adjust the speed of the loading machinery to bring it back to the target speed.

[0108] If the only deviation is in distance, check the main structure of the loading machinery for wear, looseness or other physical problems. Tighten loose screws, nuts and other fasteners, and adjust the belt tension and gear meshing clearance of the mechanical parts. After the problem is resolved, replan the route and notify the operator to drive according to the new route.

[0109] This embodiment also provides a safe intelligent auxiliary system for loading machinery, including: an environmental data collection module, which is responsible for collecting environmental data around the loading machinery after startup using multiple sensors and performing preprocessing;

[0110] The environmental data fusion and path planning module is responsible for using deep learning models to fuse preprocessed environmental data and using search algorithms to calculate the best path from the current location to the destination.

[0111] The safety hazard identification module is responsible for calculating the safety hazards on the optimal path based on the optimal path using deep learning technology;

[0112] The safety alert and response module is responsible for alerting the operator to the calculated safety hazards, allowing the operator to check the operating status and provide response measures.

[0113] The response data collection module is responsible for collecting response data from the loading machinery;

[0114] The dynamic adjustment module is responsible for adjusting the operating status of the loading machinery based on the response data of the loading machinery.

[0115] This embodiment also provides a computer device applicable to the intelligent auxiliary method for the safety of transport machinery, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the intelligent auxiliary method for the safety of transport machinery as proposed in the above embodiment.

[0116] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0117] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the intelligent auxiliary method for safe transport machinery as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0118] In summary, this invention achieves comprehensive environmental information capture and noise filtering by using multiple sensors to collect and preprocess environmental data, thereby improving data quality and environmental perception accuracy. By utilizing deep learning technology to construct a decision tree model and calculate predicted output values ​​for safety hazards, the system can predict safety hazards along the path, enabling it to identify potential risk points in advance, alert operators to the calculated safety hazards, and collect response data from the transport machinery, thus improving the operator's ability to respond to safety hazards.

[0119] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent safety assistance in loading machinery, characterized in that: include, Multiple sensors are used to collect and preprocess data on the surrounding environment of the loading machinery after startup. The preprocessed environmental data is fused using a deep learning model, and the optimal path from the current location to the destination is calculated using a search algorithm. The specific steps are as follows: Choose a convolutional neural network model; The location and shape of obstacles, as well as the distance, speed and direction of target objects, are extracted from the preprocessed environmental data, and the extracted environmental features are fused in a weighted manner. The greedy best-first search algorithm is used to calculate the comprehensive score of each path from the current location to the destination and assign them numbers. The path with the highest comprehensive score is selected as the best path. Based on the optimal path, deep learning techniques are used to calculate the security risks along the optimal path. The specific steps are as follows: Based on the best path with the highest comprehensive score, a decision tree model is built using deep learning technology, and an integrated development environment is used to deploy the decision tree model to the actual environment. The geographical location is input into the decision tree model to calculate the output prediction value of the safety hazard on the best path; The mean and standard deviation of the output predicted values ​​of safety hazards are calculated, and low and high thresholds are set based on the mean and standard deviation to classify the degree of safety hazards. When the output prediction value of the safety hazard is less than or equal to the low threshold, the degree of safety hazard on the best path is judged to be low risk. When the predicted value of the safety hazard output is greater than the high threshold, the safety hazard level on the best path is judged to be high risk. When the predicted output value of a safety hazard is greater than the low threshold and less than or equal to the high threshold, the degree of safety hazard on the best path is judged to be of medium risk. The calculated safety hazards are then alerted to the operator, who checks the operating status and provides countermeasures, thereby collecting response data from the loading machinery. The specific steps are as follows: The display information for low-risk safety hazards is set to green, medium-risk to yellow, and high-risk to red. At the same time, three types of speaker voice prompts are set: "Current path is in a low-risk state," "Please note, current path has a medium risk, please operate with caution," and "Warning, current path has a high risk, please take immediate action." All display information is displayed to the operator. When the safety hazard level is low, listen to the sounds of the surrounding environment, use a high-definition camera to scan the environmental changes around the loading machinery at set intervals, use the dashboard to monitor the environment, and save the monitoring data in the log. When the level of safety hazard is medium risk, the loading machinery is switched to manual mode and the operating speed is reduced. Magnetometers and vibration sensors are used for auxiliary monitoring. The sensor readings and monitoring data of image data are recorded and the medium risk situation is reported to the relevant departments. When the level of safety hazard is high, stop the operation of all loading machinery and arrange for all staff to evacuate to a safe area. At the same time, immediately contact team members to plan an alternative route. Based on the response measures under different risks, collect response data of the loading machinery; Adjust the operating status of the loading machinery based on the response data of the loading machinery.

2. The intelligent auxiliary method for safety of loading machinery as described in claim 1, characterized in that: The various sensors include high-definition cameras, radar, and GPS receivers; The environmental data includes distance, speed, and specific geographical location; The preprocessed data includes removing noise from the environmental data through filtering techniques, deleting outliers, and converting the environmental data into a uniform format.

3. The intelligent auxiliary method for safety of loading machinery as described in claim 2, characterized in that: Adjusting the operating status of the loading machinery based on its response data includes the following steps: Collect response data, including the speed and distance of the loading machinery following the implementation of countermeasures; If the response data does not deviate from the target speed and distance, the loading machinery will operate normally. If the response data deviates from the target speed and distance, immediately stop the operation of the loading machinery, check the working status of the machinery's control unit and sensors, repair the faulty parts, and wait for the machinery to return to normal operation before continuing the operation; If only the speed is deviating, remind the operator to pay attention and adjust the speed of the loading machinery to bring it back to the target speed; If the only deviation is in distance, replan the route and notify the operator to follow the new route.

4. A safe intelligent auxiliary system for loading machinery, based on the method for safe intelligent auxiliary system for loading machinery as described in any one of claims 1 to 3, characterized in that: include, The environmental data collection module is responsible for collecting and preprocessing environmental data around the loading machinery after it starts using various sensors. The environmental data fusion and path planning module is responsible for using deep learning models to fuse preprocessed environmental data and using search algorithms to calculate the best path from the current location to the destination. The safety hazard identification module is responsible for calculating the safety hazards on the optimal path based on the optimal path using deep learning technology; The safety alert and response module is responsible for alerting the operator to the calculated safety hazards, allowing the operator to check the operating status and provide response measures. The response data collection module is responsible for collecting response data from the loading machinery; The dynamic adjustment module is responsible for adjusting the operating status of the loading machinery based on the response data of the loading machinery.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent auxiliary method for safety of loading machinery as described in any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the intelligent auxiliary method for the safety of transport machinery as described in any one of claims 1 to 3.

Images