Search

CN-120196864-B - Intelligent auxiliary system and method for safety of shipping machinery

CN120196864BCN 120196864 BCN120196864 BCN 120196864BCN-120196864-B

Abstract

The invention discloses a shipping machinery safety intelligent auxiliary system and a method, which relate to the field of intelligent safety systems and comprise the steps of utilizing a deep learning model to fuse preprocessed environment data, calculating an optimal path from a current position to a destination through a search algorithm, calculating potential safety hazards on the optimal path based on the optimal path through a deep learning technology, prompting the calculated potential safety hazards to an operator, checking an operating state by the operator and providing countermeasures so as to collect response data of the shipping machinery.

Inventors

  • WU YONGPENG
  • CHEN CHENG

Assignees

  • 北京爱学思技术有限公司

Dates

Publication Date
20260508
Application Date
20250307

Claims (6)

  1. 1. A shipping machinery safety intelligent auxiliary method is characterized by comprising the steps of, Collecting and preprocessing the environmental data of the started shipping machinery by using various sensors; the preprocessed environmental data are fused by using a deep learning model, and an optimal path from the current position to the destination is calculated by a search algorithm, and the method comprises the following specific steps: Selecting a convolutional neural network model; extracting the position and shape of the obstacle and the environmental characteristics of the distance, speed and direction of the target object from the preprocessed environmental data, and fusing the extracted environmental characteristics in a weighted mode; Calculating the comprehensive score of each path from the current position to the destination by using a greedy optimal priority search algorithm, numbering the comprehensive scores, and selecting the path with the highest comprehensive score from the comprehensive scores as the optimal path; Based on the optimal path, the potential safety hazard on the optimal path is calculated by utilizing a deep learning technology, and the method comprises the following specific steps: Based on the best path with highest comprehensive score, constructing a decision tree model by using a deep learning technology, and deploying the decision tree model into an actual environment by using an integrated development environment; Inputting the geographic position into a decision tree model, and calculating an output predicted value of potential safety hazards on the optimal path; Calculating the average value and standard deviation of the output predicted value of the potential safety hazard, and setting a low threshold value and a high threshold value according to the average value and the standard deviation to divide the degree of the potential safety hazard; when the output predicted value of the potential safety hazard is smaller than or equal to the low threshold value, judging that the potential safety hazard degree on the optimal path is low risk; When the output predicted value of the potential safety hazard is larger than a high threshold value, judging that the potential safety hazard degree on the optimal path is high risk; When the output predicted value of the potential safety hazard is larger than the low threshold value and smaller than or equal to the high threshold value, judging that the degree of the potential safety hazard on the optimal path is a medium risk; prompting the calculated potential safety hazard to an operator, checking the running state of the operator, and providing countermeasures so as to collect response data of the shipping machinery, wherein the specific steps are as follows: setting the display information of the potential safety hazard degree of low risk to be green, the medium risk to be yellow and the high risk to be red, simultaneously setting voice prompts of three speakers to respectively show that the current path is in a low risk state, please pay attention to the fact that the current path has medium risk, please pay attention to the fact that the current path has cautious operation and warning, please take measures immediately, and prompting all the display information to an operator; When the potential safety hazard degree is low risk, monitoring the sound of the surrounding environment, using a high-definition camera to set a period to scan the environmental change around the shipping machinery, using an instrument panel to monitor the environment, and simultaneously storing monitoring data in a log; When the potential safety hazard degree is medium risk, the shipment machinery is switched to a manual mode and the operation speed is reduced, auxiliary monitoring is carried out by using a magnetometer and a vibration sensor, the reading of the sensor and the monitoring data of the image data are recorded, and the medium risk condition is reported to related departments; When the potential safety hazard degree is high risk, stopping the operation of all the shipping machines, arranging all the staff to withdraw to a safety area, and simultaneously contacting team members to plan an alternative action path; collecting response data of the shipping machine according to countermeasures under different risks; the operational status of the shipping machine is adjusted based on the response data of the shipping machine.
  2. 2. The intelligent auxiliary method for the safety of the shipping machinery according to claim 1, wherein the plurality of sensors comprise a high-definition camera, a radar and a GPS receiver; The environmental data includes distance, speed and specific geographic location; The preprocessing data comprises removing noise in the environment data through a filtering technology, and converting the environment data into a uniform format after deleting abnormal values.
  3. 3. The intelligent security assistance method of a shipping machine according to claim 2, wherein adjusting the operational status of the shipping machine based on the response data of the shipping machine comprises the steps of, Collecting response data including speed and distance of the shipment machine after the countermeasure; if the response data has no deviation from the target speed and distance, the shipment machinery is normally operated; If the response data deviate from the target speed and distance, immediately stopping the operation of the shipment machine, checking the working states of a control unit and a sensor of the machine, repairing a fault part, and waiting for the machine to resume normal operation and then continuing the operation; if only the speed deviates, reminding an operator to pay attention to and adjust the speed of the shipment machinery to return to the target speed; if only the distance deviates, the route is re-planned and the operator is informed to drive according to the new route.
  4. 4. A shipping machinery safety intelligent auxiliary system based on the method of the claim 1-3, which is characterized in that the system comprises, The environment data collection module is responsible for collecting and preprocessing the environmental data around the started shipping machinery by using various sensors; The environment data fusion and path planning module is responsible for fusing the preprocessed environment data by using a deep learning model and calculating an optimal path from the current position to the destination by a search algorithm; the potential safety hazard identification module is responsible for calculating potential safety hazards on the optimal path by utilizing a deep learning technology based on the optimal path; The safety prompt and countermeasure module is responsible for prompting the calculated potential safety hazard to an operator, checking the running state of the operator and providing countermeasures; the response data collection module is responsible for collecting response data of the shipping machinery; And the dynamic adjustment module is responsible for adjusting the operation state of the shipment machine according to the response data of the shipment machine.
  5. 5. A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the computer program is characterized in that the processor realizes the steps of the shipping mechanical safety intelligent auxiliary method of any one of claims 1-3 when executing the computer program.
  6. 6. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the shipping machine safety intelligent assistance method of any one of claims 1-3.

Description

Intelligent auxiliary system and method for safety of shipping machinery Technical Field The invention relates to the field of intelligent safety systems, in particular to an intelligent auxiliary system and method for safety of shipping machinery. Background Along with the continuous improvement of the industrial automation level, the application of the shipment machinery in the industries of logistics, construction and the like is more and more extensive, and the traditional shipment machinery mainly depends on manual operation and is easy to cause safety accidents due to human errors. Advances in sensor technology have made it more convenient and accurate to collect information about the environment of the machine. However, existing shipping machinery safety intelligent auxiliary systems still have shortcomings. First, most systems rely on a single type of sensor for data acquisition, resulting in less comprehensive environmental awareness. Secondly, in the aspect of path planning, although the existing research is combined with a deep learning model to perform path optimization, the methods ignore potential safety hazard assessment on the path and cannot fully consider accidents encountered in the actual operation process. In addition, the existing system is weak in terms of an operator feedback mechanism, and lacks an effective closed-loop control strategy to dynamically adjust the action strategy of the machine, so that the adaptability and flexibility of the system are limited. Disclosure of Invention The present invention has been made in view of the above-described problems occurring in the prior art. Therefore, the invention provides the intelligent auxiliary system and the intelligent auxiliary method for the safety of the shipping machinery, which solve the problems that the environmental perception of the shipping machinery is incomplete and the potential safety hazard assessment is ignored. In order to solve the technical problems, the invention provides the following technical scheme: in a first aspect, embodiments of the present invention provide a shipping machine safety intelligent assistance method, comprising collecting and preprocessing environmental data around a shipping machine after start-up using a plurality of sensors; fusing the preprocessed environmental data by using a deep learning model, and calculating an optimal path from the current position to the destination by using a search algorithm; Based on the optimal path, calculating potential safety hazards on the optimal path by using a deep learning technology; prompting the calculated potential safety hazard to an operator, checking the running state by the operator, and providing countermeasures so as to collect response data of the shipping machinery; the operational status of the shipping machine is adjusted based on the response data of the shipping machine. As a preferable scheme of the intelligent auxiliary method for the safety of the shipping machinery, the invention comprises the steps that the plurality of sensors comprise a high-definition camera, a radar and a GPS receiver; The environmental data includes distance, speed and specific geographic location; The preprocessing data comprises removing noise in the environment data through a filtering technology, and converting the environment data into a uniform format after deleting abnormal values. As a preferable scheme of the intelligent auxiliary method for the safety of the shipping machinery, the method comprises the steps of fusing the preprocessed environment data by using a deep learning model, calculating an optimal path from a current position to a destination by a search algorithm, Selecting a convolutional neural network model; extracting the position and shape of the obstacle and the environmental characteristics of the distance, speed and direction of the target object from the preprocessed environmental data, and fusing the extracted environmental characteristics in a weighted mode; Calculating the comprehensive score of each path from the current position to the destination by using a greedy optimal priority search algorithm, numbering, and selecting the path with the highest comprehensive score from the comprehensive scores as the optimal path, wherein the expression is as follows: F(pi)＝C(pi)+α×∑j≠iC(pj); wherein C (p i) represents the environmental characteristic score of position point p i, Z represents the normalization constant, d (p i) represents the distance of the target object at position p i, eta represents the decay factor of velocity, v (p i) represents the velocity of the target object at position p i, s (p i) represents the size of the obstacle at position p i, θ (p i) represents the direction of the target object at position p i, |p i |represents the Euclidean norm of position p i, F (p i) represents the integrated environmental characteristic score of position point p i, C (p j) represents the environmental characteristic score of posi