Integrated roadway rescue equipment

Abstract

The invention provides integrated roadway rescue equipment which comprises an equipment training system, a manual operation system, a data exchange center, a network node library, an observation equipment library, a support equipment library, a rescue equipment library, a transportation equipment library and auxiliary equipment thereof. The functional modules are coordinated to form the functional modules of the integrated roadway rescue equipment, and are matched with one another; node type ad hoc network communication in the roadway rescue process, semi-automatic operation of rescue equipment in the rescue process, efficient transmission of rescue data and cooperation of a flexible rescue system composed of rescue tools needed for single rescue in a rescue equipment library are achieved, and integration and intellectualization of roadway rescue are further achieved; the systematic rescue efficiency and the safety of rescue workers are greatly improved, and the intelligent degree, the usability and the reliability of the system are improved to a great extent.

Description

Technical Field

[0001] The present invention relates to the fields of coal mine intelligence and technical equipment thereof as well as emergency rescue equipment, and in particular to an integrated tunnel rescue equipment. Background Art

[0002] Intelligent coal mines are the guarantee for high-quality development of the coal industry. They are currently in the early stages of intelligent coal mine development. They are an organic combination of new-generation information technology and coal mining. Many new requirements and problems are difficult to solve under traditional 4G and WiFi conditions. For example, more and more sensors are used underground, and a large amount of image and video data is collected and transmitted. 5G has the characteristics of high speed, low latency, and large connection. It is an important supporting technology for the intelligent construction of coal mines. Its wide application and deep integration in the coal field will also effectively promote the formation of a high-quality and efficient tunnel rescue flow system and promote the development of intelligent and integrated rescue equipment.

[0003] In recent years, my country's coal mining technology has developed rapidly, and its mining scale and depth have continued to increase. Due to the long-term influence of mine pressure, coal mine rock conditions, and the stability of long-term support equipment and devices during tunnel excavation, tunnel collapse at the excavation end often occurs, which has a significant impact on production safety. Tunnel collapse is often accompanied by gas leakage, greatly reduced stability and reliability of support at the collapsed end of the tunnel, and paralysis of local tunnel communication networks at the collapse point. This is very unfavorable to the personal safety of rescue workers and the rapid and efficient rescue work of rescue workers in the tunnel.

[0004] my country's mine emergency rescue started late, and its overall research and development capabilities are weak. The rescue equipment has low integration, single functions, and high energy consumption. In addition, my country's mine emergency rescue lacks advanced, intelligent, and integrated special rescue equipment. It often uses a large amount of manual rescue and ordinary production equipment as a substitute, and has not formed a relatively complete standard rescue system. In addition, during the rescue process, there is still room for improvement in rescue personnel communication, rescue site data transmission, and rescue efficiency.

[0005] Therefore, the prior art needs to be further developed. Summary of the invention

[0006] The purpose of the present invention is to overcome the above technical deficiencies and provide an integrated tunnel rescue equipment to solve the problems existing in the prior art.

[0007] In order to achieve the above technical objectives, the present invention provides an integrated tunnel rescue equipment, the integrated tunnel rescue equipment comprising: An equipment training system, used for training the integrated tunnel rescue equipment using a neural network algorithm model; The network node library is used to form node-based self-organizing network communication, transmit data to terminal devices, and monitor the operating status of terminal devices; Data exchange center, used to connect to the network node library for data exchange, data communication and command data communication; The transport equipment warehouse is used to transport the collapsed objects and injured persons out with the equipment in the rescue equipment warehouse; Auxiliary equipment, including power supply system and electromechanical and hydraulic system; A rescue equipment library, including equipment that performs rescue operations during the rescue process, which is the terminal equipment of the node-based ad hoc network communication; A library of observation equipment for monitoring roadway environmental parameters; A library of support equipment, including flexible support equipment, for supporting the roadways; The artificial operating system, including the equipment operating system and the medical system for assisting the wounded, is used for AI interaction during the rescue process. The medical system for assisting the wounded includes the medical equipment and medical supplies required for the first aid of the wounded.

[0008] Specifically, the equipment training system includes: a training model, a model optimization system, a training site data acquisition system, a training result data conversion system, a training site data conversion system, an equipment training system database, and a model evaluation system.

[0009] Specifically, the training site data collection system includes a first preset sensor for collecting real-time rescue data, and the first preset sensor includes a distance sensor, an angle sensor, and a visual sensor.

[0010] The training model includes a multivariate function set that controls the rescue process and the operating rules of each actuator; The model optimization system is used to determine the parameters of the multivariate function set based on the first rescue real-time data collected by the training site data collection system using the parameter optimization algorithm of the neural network algorithm model, and then obtain the training results of the neural network algorithm model.

[0011] Specifically, the training site data conversion system is used to convert the rescue real-time data collected by the training site data collection system into a first preset data structure type, and convert it into a data packet according to a preset hierarchical structure for data transmission between the rescue point and the ground base station, and convert the rescue real-time data into a second preset data structure type, which is then used for the model optimization system to optimize the neural network algorithm model; The first preset data structure type is a structure type, the elements in the structure include the type of sensor that generates the data, the installation location of the device described in the present invention, and the data value, and the first preset data structure type is packaged and transmitted to the ground base station; The preset hierarchical structure is a packaging method of the first preset data. After the first preset data of the first preset sensor is converted into the first preset data structure type, it is packaged according to the preset structure of "device posture status + device environment status"; The second preset data structure type includes all the contents of the first preset data structure type, and the structure member variables of the second preset data structure type include the sensor type, installation location and data value, as well as the data destination; The training result data conversion system is used to update the parameters of the multivariate function set determined by the model optimization system using the parameter optimization algorithm of the neural network algorithm model into the neural network algorithm model to perform model training.

[0012] Specifically, the model evaluation system is used to evaluate the training results of the trained neural network algorithm model in combination with the actual training environment, and use the flexibility and continuity of movement in the lane as the judgment conditions to determine whether the training results have passed the evaluation of the model evaluation system, and select the training results with good flexibility and continuity of movement, that is, the present invention has the least number of collisions in the lane and the shortest obstacle crossing time; The training system database is used to store the parameters of the neural network algorithm model after optimization by the model optimization system and evaluation by the model evaluation system in the training system database according to a preset hierarchical structure.

[0013] Specifically, the network node library includes: communication network nodes, rescue equipment nodes, and monitoring equipment nodes.

[0014] Specifically, the communication network node is used to generate a 5G signal for mining, and can perform node-based communication network self-organization, thereby generating node-based self-organizing network communication, and perform data exchange and communication between the integrated tunnel rescue equipment and the ground base station; The rescue equipment node is the terminal device of the node-type self-organizing network communication, which is used to perform rescue operations during the rescue process and collect real-time data generated during the rescue process, including the position of the injured, ambient temperature, humidity, gas concentration and the posture data of the rescue equipment itself, and adjust the posture of the rescue equipment node during the rescue process according to the above real-time data; The monitoring device node is used to monitor the real-time rescue environment and the operating status of the rescue equipment during the rescue process, and transmits the operating status of the rescue equipment in the form of images to the ground base station through the node-based self-organizing network communication.

[0015] Specifically, the observation equipment library includes rescue site observation equipment and lane node observation equipment. The rescue site observation equipment is used to monitor the real-time rescue environment and the operating status of the rescue equipment during the rescue process. The rescue equipment node is equipped to enable the rescue site observation equipment to access the node-based self-organizing network communication. The lane node observation equipment includes a second preset sensor that can collect lane environment parameters in the node-based self-organizing network communication path. The second preset sensor includes a temperature sensor, a gas concentration sensor, and an infrared temperature sensor. The rescue equipment library includes flexible rescue equipment and a rescue tool library. The flexible rescue equipment can autonomously switch rescue tools. The rescue tool library is used to provide rescue tools for the flexible rescue equipment. The support equipment library includes flexible support equipment, which is used to collect and return tunnel top status data in real time. The data includes the stress condition and displacement of the contact part between the flexible support equipment and the tunnel roof, and adjust the support strategy in real time according to the tunnel top status data.

[0016] Specifically, the transportation equipment library includes: Collapsed material transport equipment, used to transport collapsed materials transported by flexible rescue equipment during the rescue process to non-rescue sites or out of the tunnel; The wounded transport equipment is used to transport the wounded during the rescue process to the ground.

[0017] Specifically, the data exchange center includes: an instruction data exchange module, an operation data exchange module, an image data exchange module, a data classification and packaging module, and a data processing flow control module; The command data exchange module, the operation data exchange module, and the image data exchange module are used to process the real-time command data, equipment operation data, and image data generated during the rescue process, respectively; The data classification and packaging module is used to package various first rescue real-time data according to the first preset data structure type and generate a real-time data packet; The data processing flow control module is used to control the data operation flow, and the data operation flow includes data collection, packaging, transmission, storage and management.

[0018] Beneficial effects: The present invention utilizes artificial intelligence and neural network algorithms to coordinate the functional modules of an integrated tunnel rescue equipment, namely, the mutual cooperation of functional modules such as equipment training system, manual operation system, data exchange center, network node library, observation equipment library, support equipment library, rescue equipment library, transportation equipment library and its auxiliary equipment, realizes node-based self-organizing network communication in the tunnel rescue process, semi-automatic operation of rescue equipment in the rescue process, efficient transmission of rescue data and cooperation of a flexible rescue system composed of rescue tools required for a single rescue in the rescue equipment library, further realizes the integration and intelligence of tunnel rescue, greatly improves the systematic rescue efficiency and the safety of rescue personnel, greatly reduces the labor cost of manual rescue, and greatly improves the intelligence, availability and reliability of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the composition of the integrated tunnel rescue equipment provided in a specific embodiment of the present invention; Figure 2 It is a schematic diagram of node composition of the integrated tunnel rescue equipment provided in a specific embodiment of the present invention; Figure 3 It is a schematic diagram of the process of node-based self-organizing network communication of integrated tunnel rescue equipment provided in a specific embodiment of the present invention; Figure 4 It is a structural schematic diagram of node-type self-organizing network communication of integrated tunnel rescue equipment provided in a specific embodiment of the present invention; Figure 5 It is a schematic diagram of the integrated tunnel rescue equipment training process provided in a specific embodiment of the present invention. DETAILED DESCRIPTION In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings of the present invention. Based on the embodiments in this application, other similar embodiments obtained by ordinary technicians in this field without making creative work should all fall within the scope of protection of this application. In addition, the directional words mentioned in the following embodiments, such as "up", "down", "left", "right", etc., are only reference to the directions of the accompanying drawings. Therefore, the directional words used are used to illustrate rather than limit the invention.

[0020] The present invention will be further described below in conjunction with the accompanying drawings and preferred embodiments.

[0021] Embodiment 1 See also Figure 1 , this embodiment provides an integrated tunnel rescue equipment, including: An equipment training system, used for training the integrated tunnel rescue equipment using a neural network algorithm model; The network node library is used to form node-based self-organizing network communication, transmit data to terminal devices, and monitor the operating status of terminal devices; Data exchange center, used to connect to the network node library for data exchange, data communication and command data communication; The transport equipment warehouse is used to transport the collapsed objects and injured persons out with the equipment in the rescue equipment warehouse; Auxiliary equipment, including power supply system and electromechanical and hydraulic system; A rescue equipment library, including equipment that performs rescue operations during the rescue process, which is the terminal equipment of the node-based ad hoc network communication; A library of observation equipment for monitoring roadway environmental parameters; A library of support equipment, including flexible support equipment, for supporting the roadways; An artificial operating system, including an equipment operating system and a medical system for assisting the wounded, is used for AI interaction during the rescue process. The equipment operating system is a control system assembly for controlling the equipment, libraries, systems, nodes, modules and models included in the present invention. The medical system for assisting the wounded includes medical equipment and medical supplies required for first aid of the wounded.

[0022] It should be noted here that the first preset sensor, the second preset sensor, the first preset data structure type, the preset hierarchical structure, and the second preset data structure type. It is understandable that the present invention does not limit the specific content or specific values ​​of the first preset sensor, the second preset sensor, the first preset data structure type, the preset hierarchical structure, and the second preset data structure type, as long as they can be applied to the integrated tunnel rescue equipment proposed by the present invention. Specifically, the equipment training system includes: a training model, a model optimization system, a training site data acquisition system, a training result data conversion system, a training site data conversion system, an equipment training system database, and a model evaluation system.

[0023] Specifically, the training site data collection system includes a first preset sensor for collecting first rescue real-time data, and the first preset sensor includes a distance sensor, an angle sensor, a visual sensor, and other sensors for sensing the posture of the device of the present invention and the environmental conditions in which it is located; The training model includes a multivariate function set that controls the rescue process and the operating rules of each actuator; The model optimization system is used to determine the parameters of the multivariate function set according to the real-time rescue data collected by the training site data collection system, and then obtain the training results of the neural network algorithm model.

[0024] It can be understood that the training model is composed of a multivariate function set after defining optimization parameters of various types of rescue processes and actuators that control the integrated tunnel rescue equipment described in the present invention according to the rescue process and the operating rules of the actuators. The multivariate function set is trained using the collected data so that it can accurately reflect the rescue process. On the basis of model training, the optimization parameters are adjusted according to the actual rescue situation, the model is tested in a virtual environment, its performance and reliability are evaluated, the verified model is applied to actual rescue tasks, and real-time adjustments are made to cope with changes, thereby further improving the availability and reliability of the present invention.

[0025] Specifically, the training site data conversion system is used to convert the first rescue real-time data collected by the training site data collection system into a first preset data structure type, and convert it into a data packet according to a preset hierarchical structure for data transmission between the rescue point and the ground base station, and convert the first rescue real-time data into a second preset data structure type, which is then used for the model optimization system to optimize the neural network algorithm model; The first preset data structure type is a structure type, the elements in the structure include the type of sensor that generates the data, the installation location of the device described in the present invention, and the data value, and the first preset data structure type is packaged and transmitted to the ground base station; The preset hierarchical structure is a packaging method of the first preset data. After the first preset data of the first preset sensor is converted into the first preset data structure type, it is packaged according to the preset structure of "device posture status + device environment status"; The second preset data structure type includes all the contents of the first preset data structure type. Since the second preset data structure type needs to be imported into the model optimization system for optimization, the structure member variables of the second preset data structure type include the data destination in addition to the sensor type, installation location and data value; The training result data conversion system is used to update the parameters of the multivariate function set determined by the model optimization system using the parameter optimization algorithm of the neural network algorithm model into the neural network algorithm model to perform model training.

[0026] It should be further explained that the training site data acquisition system uses a data acquisition algorithm to control a sensor set with a complex hierarchical structure that can obtain multi-source real-time data at the rescue site. The data acquisition algorithm is the order and method of collecting sensor data in a sensor set with a complex hierarchical structure. It can be applied to the device described in the present invention, and does not specifically refer to a specific algorithm. The training site data conversion system converts the multi-source data of the rescue site collected by the training site data acquisition system into one of the data structure types defined specifically for the integrated tunnel rescue equipment described in the present invention, and converts it into a data packet according to the defined hierarchical structure for data transmission between the rescue point and the ground base station, and converts the multi-source data of the rescue site into the data structure type used by the model optimization system, and then used to optimize the training model. The training result data conversion system updates the multivariate function parameters determined by the model optimization system into the training model, so that the integrated tunnel rescue equipment described in the present invention executes the corresponding multivariate function in the training model according to the training environment, and combines with the model evaluation system to complete a stage training in the overall training process. The model optimization system uses the multi-source rescue site data collected by the training site data acquisition system to determine the multivariate function parameters through the model parameter optimization algorithm. The optimized parameters are the model training results.

[0027] Specifically, the model evaluation system is used to evaluate the training results of the trained neural network algorithm model in combination with the actual training environment, and to use the motion flexibility and continuity of the present invention in the lane as the judgment conditions to determine whether the training results have passed the evaluation of the model evaluation system, and to select the training results with the best motion flexibility and continuity, that is, the present invention has the least number of collisions in the lane and the shortest obstacle crossing time; The training system database is used to store the parameters of the neural network algorithm model after optimization by the model optimization system and evaluation by the model evaluation system in the training system database according to a preset hierarchical structure.

[0028] It can be understood that the model evaluation system evaluates the trained model in combination with the actual training environment to determine whether the training results meet the specified requirements, thereby further improving the accuracy and reliability of the model. The training system database optimizes the model optimization system and determines the training model parameters that meet the specified requirements after evaluation by the model evaluation system. The database hierarchical structure of the integrated tunnel rescue equipment described in the present invention is stored in the database, providing the necessary input data for the neural network algorithm model so that the model can learn the relevant characteristics of the rescue equipment, and the stored model parameters can be directly used for predictive analysis of new data, greatly expanding the application scenarios of the present invention.

[0029] Specifically, the network node library includes: communication network nodes, rescue equipment nodes, and monitoring equipment nodes.

[0030] Specifically, the communication network node is used to generate a 5G signal for mining, and can perform node-based communication network self-organization, thereby generating node-based self-organizing network communication, and perform data exchange and communication between the integrated tunnel rescue equipment and the ground base station; The rescue equipment node is the terminal device of the node-type self-organizing network communication, which is used to perform rescue operations during the rescue process and collect real-time data generated during the rescue process, including the position of the injured, ambient temperature, humidity, gas concentration and the posture data of the rescue equipment itself, and adjust the posture of the rescue equipment node during the rescue process according to the above real-time data; The monitoring device node is used to monitor the real-time rescue environment and the operating status of the rescue equipment during the rescue process, and transmits the operating status of the rescue equipment in the form of images to the ground base station through the node-based self-organizing network communication.

[0031] It should be noted here that the present invention realizes various data exchanges and communications between the integrated tunnel rescue equipment and the ground base station during the rescue process by forming node-type self-organizing network communications through communication network nodes, so that after receiving the information from the communication network nodes, the rescue equipment nodes can realize semi-autonomous rescue in combination with the auxiliary operation of the rescue equipment administrator, and at the same time collect the posture data of the rescue equipment itself for real-time adjustment of the real-time posture of the rescue equipment nodes during the rescue process. The monitoring equipment nodes monitor the rescue environment and the operating status of the rescue equipment in real time and transmit the images to the ground base station through node-type self-organizing network communications, so that the rescue staff of the ground base station can know the rescue situation in the tunnel in real time, which greatly improves the intelligence, usability and reliability of the present invention.

[0032] Specifically, the observation equipment library includes rescue site observation equipment and lane node observation equipment. The rescue site observation equipment is used to monitor the real-time rescue environment and the operating status of the rescue equipment during the rescue process. The rescue equipment node is equipped to enable the rescue site observation equipment to access the node-based self-organizing network communication. The lane node observation equipment includes a second preset sensor capable of collecting lane environment parameters in the node-based self-organizing network communication path. The second preset sensor includes a temperature sensor, a gas concentration sensor, and an infrared temperature sensor. The rescue equipment library includes flexible rescue equipment and a rescue tool library. The flexible rescue equipment can autonomously switch rescue tools. The rescue tool library is used to provide rescue tools for the flexible rescue equipment. The support equipment library includes flexible support equipment, which is used to collect and return tunnel top status data in real time. The data includes the stress condition and displacement of the contact part between the flexible support equipment and the tunnel roof, and adjust the support strategy in real time according to the tunnel top status data.

[0033] It can be understood that the tunnel node observation equipment is equipped with a set of sensors that can collect tunnel environment data in the node-type self-organizing network communication path, which is used to monitor the gas concentration, temperature, etc. in the tunnel environment. The flexible rescue equipment can autonomously switch the required rescue tools according to the rescue site conditions. Compared with traditional production tools for rescue in the tunnel, the flexible rescue equipment greatly reduces the use of rescue equipment, greatly saves the space occupied by the rescue equipment in the tunnel, and greatly improves the flexibility of the rescue equipment and the efficiency of tunnel rescue. The flexible support equipment, whose support surface can adapt to the structural conditions of different tunnel tops and collect and return the support conditions to the support equipment in real time during the rescue process, and adjust the support strategy in real time, greatly improving the safety and reliability of the present invention.

[0034] Specifically, the transportation equipment library includes: Collapsed material transport equipment, used to transport collapsed materials transported by flexible rescue equipment during the rescue process to non-rescue sites or out of the tunnel; The wounded transport equipment is used to transport the wounded during the rescue process to the ground.

[0035] It can be understood that the wounded transport equipment is used to transport the wounded who are found during the rescue process and receive initial medical rescue to the ground, and then further rescue the wounded, which further improves the intelligence level of the present invention.

[0036] Specifically, the data exchange center includes: an instruction data exchange module, an operation data exchange module, an image data exchange module, a data classification and packaging module, and a data processing flow control module; The command data exchange module, the operation data exchange module, and the image data exchange module are used to process the real-time command data, equipment operation data, and image data generated during the rescue process, respectively; The data classification and packaging module is used to package various first rescue real-time data according to the first preset data structure type and generate a real-time data packet; The data processing flow control module is used to control the data operation flow, and the data operation flow includes data collection, packaging, transmission, storage and management.

[0037] It should be further explained that the data processing process control module strictly controls a series of data operation processes such as data collection, packaging, transmission, storage, and management to ensure the normal operation of the integrated tunnel rescue equipment described in the present invention during the data operation process, thereby greatly improving the reliability and usability of the present invention.

[0038] It should be noted here that the present invention utilizes artificial intelligence and neural network algorithms to coordinate the functional modules of an integrated tunnel rescue equipment, namely, the mutual cooperation of functional modules such as equipment training system, manual operation system, data exchange center, network node library, observation equipment library, support equipment library, rescue equipment library, transportation equipment library and its auxiliary equipment, realizes node-based self-organizing network communication in the tunnel rescue process, semi-automatic operation of rescue equipment during the rescue process, efficient transmission of rescue data, and collaborative cooperation of a flexible rescue system composed of rescue tools required for a single rescue in the rescue equipment library, further realizes the integration and intelligence of tunnel rescue, greatly improves the systematic rescue efficiency and the safety of rescue personnel, greatly reduces the labor cost of manual rescue, and greatly improves the intelligence, usability and reliability of the present invention.

[0039] Embodiment 2 See also Figure 5 This embodiment provides a training process for a neural network algorithm of an integrated tunnel rescue equipment, and the specific implementation process is as follows: The integrated tunnel rescue equipment of the present invention is placed in various simulated tunnel environments and simulated rescue operations to provide a large amount of rich original environmental data and original rescue scenes, that is, Figure 5 The device training environment shown.

[0040] Step 1: After the integrated tunnel rescue equipment of the present invention is placed in a simulated rescue environment, the training site data acquisition system acquires multi-source real-time data in the simulated rescue environment according to set rules; Step 2: The training site data acquisition system performs preliminary data processing on the preliminarily collected multi-source real-time data, such as data collection, data cleaning and other operations, and transmits the preliminarily processed multi-source real-time data to the training site data conversion system, and converts the preliminarily processed multi-source real-time data into data with a specified data structure type according to the data structure type and its conversion rules defined by the integrated tunnel rescue equipment described in the present invention, which is data conversion in the training site data conversion system; Step 3: After the data conversion is completed, the training site data conversion system encapsulates and packages the multi-source real-time data with a specified data structure, and transmits the encapsulated and packaged multi-source real-time data with a specified data structure to the model training system for training the training model and generating corresponding model training results; Step 4: The training model is composed of a multivariate function set after the rescue process of various types of integrated tunnel rescue equipment and the optimization parameters of each actuator are defined according to the rescue process and the operating rules of the actuator, and the training results are various parameters to be optimized of the multivariate function set in the training model, etc.; Step 5: The training results after model training are transmitted to the training result data conversion system for parsing the training results. The parsed content includes three outputs: model correction data, operation instruction set and training results; Step 6: Model correction data includes various optimized parameters of multivariate functions in the training model, model hyperparameters (learning rate α, number of neural network layers, number of neurons in each layer, etc.), and related parameter data used to optimize the training model and neural network; Step 7: Figure 5 The operation instruction set in the training model refers to the calling rules of the multivariate function set after the optimization parameters are defined according to the rescue process and the operating rules of the actuator, such as the node operation instruction set, the monitoring equipment operation instruction set and the rescue equipment operation instruction set, etc. The calling rules of the multivariate function set are the calling rules followed when dealing with the problems of how to avoid obstacles, plan network nodes, rescue equipment nodes and observation nodes in the simulated training environment, and how to perform rescue after arriving at the rescue point, that is, how to call the multivariate function and what kind of multivariate function to call; Step 8: Figure 5 The training results in the training include post-training judgment logic, post-training route correction rules, post-training equipment deployment rules, and post-training group control rules, etc. These rules will be used to update the training model set Figure 5 Model initial conditions shown; Step 9: The model initial conditions make a preliminary judgment on the calling rules of the multivariate function set, that is, the calling rules of the multivariate function set are matched; Step 10: The above three outputs, model correction data, operation instruction set and training results will be passed Figure 5 The model optimization system shown performs training model updates; Step 11: After the training model is updated, it enters the model evaluation stage, that is, the model evaluation system is used to test whether the optimized model can correctly make decisions on situations occurring in the simulated rescue environment and take corresponding countermeasures.

[0041] Step 12: After passing the inspection of the model evaluation system, the integrated tunnel rescue equipment will output the model correction data, operation instruction set and training results, and store them in the database according to a certain data structure level; Step 13: After the above training process is completed, the integrated tunnel rescue equipment is placed in a new simulated rescue environment to repeat the above training process until the optimal training model is obtained and the simulated training environment data is used up.

[0042] It should be further explained that the present invention utilizes artificial intelligence and neural network algorithms to coordinate the functional modules of an integrated tunnel rescue equipment, namely, the equipment training system, artificial operating system, data exchange center, network node library, observation equipment library, support equipment library, rescue equipment library, transportation equipment library and its auxiliary equipment and other functional modules. The mutual cooperation of these modules further realizes the integration and intelligence of tunnel rescue, greatly improves the systematic rescue efficiency and the safety of rescue personnel, and greatly improves the intelligence and reliability of the present invention.

[0043] Embodiment 3 See also Figure 2-Figure 4 This embodiment provides a specific implementation process for integrated tunnel rescue equipment to realize node-based self-organizing network communication: In the event of tunnel collapse and communication interruption, the integrated tunnel rescue equipment of the present invention can plan an optimal node-based communication network based on the data collected by the first preset sensor.

[0044] The self-organizing process of node-based self-organizing network communication is as follows: Figure 2 As shown, taking three communication network nodes as an example, the specific implementation steps are as follows: Step 1: Import the digital model of the tunnel structure into the integrated tunnel rescue equipment and mark the determined tunnel collapse location for planning the preliminary optimal arrival path. The reason why it is a preliminary path is that only the basic structure of the tunnel can be collected from the digital model of the tunnel structure, while the specific details inside, such as obstacles caused by tunnel collapse and the location of the original production equipment inside the tunnel, cannot be obtained; Step 2: After obtaining the above information, the integrated tunnel rescue equipment of the present invention plans the node-based communication self-organizing network path through an algorithm; Step 3: The integrated tunnel rescue equipment follows the planned initial optimal path. Figure 2 and Figure 3 The communication module shown is connected to the integrated tunnel rescue equipment, enters the tunnel, and according to the relevant obstacle information collected by the training site data collection system, on the basis of the initial planned path remaining unchanged, avoids obstacles on the initial optimal path according to the training model and reaches the first node layout position; Step 4: After arriving at the first deployment location, the integrated tunnel rescue equipment releases the first communication node, such as Figure 3 Node 1 shown, at this time, the communication node 1 is connected to the mirror communication module of the integrated tunnel rescue equipment, and at the same time, the node 1 is connected to the ground base station and the mirror communication module in AP-STA mode; Step 5: After the communication device detects that the node 1 is successfully connected to the ground base station, the connection between the communication module and the integrated tunnel rescue equipment is disconnected, the connection of the first node-type communication ad hoc network node is completed, and then the preliminary optimal path is continued; Step 6: After reaching the second node placement position, the integrated tunnel rescue equipment is released as follows: Figure 2 Node 2 shown, then node 2 is connected to node 2 in AP-STA mode, and is connected to node 1 in AP-STA mode at the same time, after detecting that the connection is successful, the mirror communication module disconnects the connection between the rescue device and node 1; Step 6: With the same arrangement mode of nodes 1 and 2, the arrangement of node 3 is completed under the switching connection between the communication module and the mirror communication module, and then the integrated tunnel rescue equipment continues to drive to the tunnel collapse point according to the preliminary optimal path, completing the arrangement of the three-node node communication ad hoc network; Step 7: When the number of communication nodes is greater than 3, the node-based communication ad hoc network is arranged by itself under the control of the algorithm according to the above process to form Figure 4 The structure of the integrated tunnel rescue equipment self-organizing network shown in the figure can realize the real-time transmission of data between the tunnel collapse point and the ground base station; Step 8: After the node-based communication ad hoc network is built, the integrated tunnel rescue equipment also arrives at the tunnel collapse point, releases the rescue site observation equipment, and communicates with the rescue team in STA mode. Figure 4 The data exchange center of the integrated tunnel rescue equipment shown is connected to form Figure 4 The observation equipment set shown, thereby establishing real-time data communication between the rescue site and the integrated tunnel rescue equipment and the ground base station, so as to return the tunnel collapse point situation to the integrated tunnel rescue equipment and the ground base station; Step 9: The equipment administrator on the integrated tunnel rescue equipment checks the status of the rescue equipment library and the support equipment library, and after setting the relevant equipment information, the integrated tunnel rescue equipment releases the flexible support equipment to support the vicinity of the tunnel collapse point, and then releases the flexible rescue equipment, and carries out the rescue operation under the monitoring of the monitoring equipment set under the autonomous algorithm of the flexible rescue equipment and the group control algorithm of the integrated tunnel rescue equipment; Step 10: During the rescue operation, the collapsed objects removed by the flexible rescue equipment are transported to the ground by the collapsed object transporting equipment, or transported to an open non-rescue area in the tunnel; Step 11: After the infrared detection device of the flexible rescue equipment participating in the rescue detects the injured person in combination with the life detection algorithm of the flexible rescue equipment, the location information of the injured person is sent to other flexible rescue equipment participating in the rescue to prevent other flexible rescue equipment from causing secondary injuries to the injured person in the process of carrying the collapsed objects. At the same time, the location information of the injured person is sent to the equipment manager of the integrated tunnel rescue equipment; Step 12: After obtaining the location data of the injured person and combining it with the rescue environment conditions (such as temperature, gas concentration, etc.) sent by the monitoring equipment set, the equipment manager feeds back the above information to the rescue personnel on the integrated tunnel rescue equipment. After taking protective measures, the rescue personnel arrive at the location of the injured person, provide basic medical treatment to the injured person, and then transport him to the rescue equipment. Step 13: After the injured are transported to the integrated tunnel rescue equipment, the rescuers will provide further medical treatment to the injured. After the treatment is completed, the rescuers and the injured are transported to the ground base station for further rescue under the transportation of the injured. The integrated tunnel rescue equipment is equipped with sufficient injured transportation equipment, and the injured transportation equipment can work simultaneously to transport the injured, thereby improving the rescue efficiency; Step 14: During the tunnel rescue process, the monitoring equipment set sends the on-site rescue data to the integrated tunnel rescue equipment and the ground base station, so that the equipment administrator and the ground base station rescue staff can know the on-site rescue status; Step 15: During the tunnel rescue process, the operating status information (such as posture, motion data, etc.) of the flexible rescue equipment and the observation equipment set are transmitted to the integrated tunnel rescue equipment in a data packet with a specified data structure and a specified level, and further corresponding digital twins are performed. The relevant parts of the digital twins are not described in detail in the present invention; Step 16: During the tunnel rescue process, each communication node in the node-based communication ad hoc network will send the tunnel environment data of the tunnel where it is located to the ground base station according to the prescribed communication protocol. The communication protocol part here is not described in detail in the present invention; Step 17: During the tunnel rescue process, the flexible support equipment can monitor the support conditions (such as support force, flexible support equipment posture status, etc.) in real time. The above data are transmitted to the integrated tunnel rescue equipment in a data packet with a specified data structure and a specified level, and further corresponding digital twins are performed; Step 18: According to the above implementation method, a systematic rescue process can be formed to realize the intelligence and semi-automation of the tunnel rescue process, which greatly improves the rescue efficiency and ensures the personal safety of the rescuers.

[0045] It should be noted here that the present invention coordinates the functional modules of an integrated tunnel rescue equipment, namely, the mutual cooperation of functional modules such as equipment training system, manual operation system, data exchange center, network node library, observation equipment library, support equipment library, rescue equipment library, transportation equipment library and its auxiliary equipment, realizes the node-based self-organizing network communication in the tunnel rescue process, the semi-automatic operation of the rescue equipment during the rescue process, the efficient transmission of rescue data and the collaborative cooperation of the flexible rescue system composed of rescue tools required for a single rescue in the rescue equipment library, further realizes the integration and intelligence of tunnel rescue, greatly improves the systematic rescue efficiency and the safety of rescue personnel, greatly reduces the labor cost of manual rescue, and greatly improves the intelligence, usability and reliability of the present invention.

[0046] Embodiment 4 In a preferred embodiment, the present application further provides an electronic device, the electronic device comprising: A memory; and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the integrated tunnel rescue equipment is implemented. The computer device can be broadly a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, a memory, a network interface, a communication interface, etc. connected via a system bus. The processor of the computer device can be used to provide necessary computing, processing and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices via a network. When the computer program is executed by the processor, the steps of the method of the present invention are performed.

[0047] The present invention may be implemented as a computer-readable storage medium having a computer program stored thereon, which causes the steps of the method of an embodiment of the present invention to be executed when executed by a processor. In one embodiment, the computer program is distributed on a plurality of computer devices or processors coupled to a network so that the computer program is stored, accessed and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be performed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be performed by one or more computer devices or processors, and one or more other method steps / operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step / operation, or perform two or more method steps / operations.

[0048] It will be appreciated by a person skilled in the art that the method steps of the present invention may be performed by instructing related hardware such as a computer device or a processor through a computer program, and the computer program may be stored in a non-temporary computer-readable storage medium, which causes the steps of the present invention to be performed when the computer program is executed. Depending on the circumstances, any reference to memory, storage, database, or other media herein may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0049] The present invention utilizes artificial intelligence and neural network algorithms to coordinate the functional modules of an integrated tunnel rescue equipment, namely, the mutual cooperation of functional modules such as equipment training system, manual operation system, data exchange center, network node library, observation equipment library, support equipment library, rescue equipment library, transportation equipment library and its auxiliary equipment, realizes node-based self-organizing network communication in the tunnel rescue process, semi-automatic operation of rescue equipment in the rescue process, efficient transmission of rescue data and cooperation of a flexible rescue system composed of rescue tools required for a single rescue in the rescue equipment library, further realizes the integration and intelligence of tunnel rescue, greatly improves the systematic rescue efficiency and the safety of rescue personnel, greatly reduces the labor cost of manual rescue, and greatly improves the intelligence, availability and reliability of the present invention.

[0050] The various technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by this specification as long as there is no contradiction in such combination.

[0051] The specific implementation of the present invention described above does not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. An integrated tunnel rescue equipment, characterized in that: include: An equipment training system, used for training the integrated tunnel rescue equipment using a neural network algorithm model; The network node library is used to form node-based self-organizing network communication, transmit data to terminal devices, and monitor the operating status of terminal devices; Data exchange center, used to connect to the network node library for data exchange, data communication and command data communication; The transport equipment warehouse is used to transport the collapsed objects and injured persons out with the equipment in the rescue equipment warehouse; Auxiliary equipment, including power supply system and electromechanical and hydraulic system; A rescue equipment library, including equipment that performs rescue operations during the rescue process, which is the terminal equipment of the node-based ad hoc network communication; A library of observation equipment for monitoring roadway environmental parameters; A library of support equipment, including flexible support equipment, for supporting the roadways; The artificial operating system, including the equipment operating system and the medical system for assisting the wounded, is used for AI interaction during the rescue process. The medical system for assisting the wounded includes the medical equipment and medical supplies required for the first aid of the wounded.

2. The integrated tunnel rescue equipment according to claim 1, characterized in that: The equipment training system includes: a training model, a model optimization system, a training site data acquisition system, a training result data conversion system, a training site data conversion system, an equipment training system database, and a model evaluation system.

3. The integrated tunnel rescue equipment according to claim 2 is characterized in that: The training site data acquisition system includes a first preset sensor for collecting first rescue real-time data, wherein the first preset sensor includes a distance sensor, an angle sensor, and a visual sensor; The training model includes a multivariate function set that controls the rescue process and the operating rules of each actuator; The model optimization system is used to determine the parameters of the multivariate function set based on the first rescue real-time data collected by the training site data collection system using the parameter optimization algorithm of the neural network algorithm model, and then obtain the training results of the neural network algorithm model.

4. The integrated tunnel rescue equipment according to claim 3 is characterized in that: The training site data conversion system is used to convert the first rescue real-time data collected by the training site data collection system into a first preset data structure type, and convert it into a data packet according to a preset hierarchical structure for data transmission between the rescue point and the ground base station, and convert the first rescue real-time data into a second preset data structure type, which is then used by the model optimization system to optimize the neural network algorithm model; The first preset data structure type is a structure type, the elements in the structure include the type of sensor that generates the data, the installation location of the device described in the present invention, and the data value, and the first preset data structure type is packaged and transmitted to the ground base station; The preset hierarchical structure is a packaging method of the first preset data. After the first preset data of the first preset sensor is converted into the first preset data structure type, it is packaged according to the preset structure of "device posture status + device environment status"; The second preset data structure type includes all the contents of the first preset data structure type, and the structure member variables of the second preset data structure type include the sensor type, installation location and data value, as well as the data destination; The training result data conversion system is used to update the parameters of the multivariate function set determined by the model optimization system using the parameter optimization algorithm of the neural network algorithm model into the neural network algorithm model to perform model training.

5. The integrated tunnel rescue equipment according to claim 2, characterized in that: The model evaluation system is used to evaluate the training results of the trained neural network algorithm model in combination with the actual training environment, and use the flexibility and continuity of movement in the lane as the judgment conditions to determine whether the training results have passed the evaluation of the model evaluation system, and select the training results with good flexibility and continuity of movement, that is, the present invention has the least number of collisions in the lane and the shortest obstacle crossing time; The training system database is used to store the parameters of the neural network algorithm model after optimization by the model optimization system and evaluation by the model evaluation system in the training system database according to a preset hierarchical structure.

6. The integrated tunnel rescue equipment according to claim 1, characterized in that: The network node library includes: communication network nodes, rescue equipment nodes, and monitoring equipment nodes.

7. The integrated tunnel rescue equipment according to claim 6, characterized in that: The communication network node is used to generate a 5G signal for mining, and can perform node-based communication network self-organization, thereby generating node-based self-organizing network communication, and perform data exchange and communication between the integrated tunnel rescue equipment and the ground base station; The rescue equipment node is the terminal device of the node-type self-organizing network communication, which is used to perform rescue operations during the rescue process and collect real-time data generated during the rescue process, which includes the location of the injured, ambient temperature, humidity, gas concentration and the posture data of the rescue equipment itself; The monitoring device node is used to monitor the real-time rescue environment and the operating status of the rescue equipment during the rescue process, and transmits the operating status of the rescue equipment in the form of images to the ground base station through the node-based self-organizing network communication.

8. The integrated tunnel rescue equipment according to claim 1, characterized in that: The observation equipment library includes rescue scene observation equipment and lane node observation equipment. The rescue scene observation equipment is used to monitor the real-time rescue environment and the operating status of the rescue equipment during the rescue process, and is equipped with rescue equipment nodes so that the rescue scene observation equipment is connected to the node-based self-organizing network communication; The lane node observation device includes a second preset sensor capable of collecting lane environmental parameters in the node-type ad hoc network communication path, and the second preset sensor includes a temperature sensor, a gas concentration sensor, and an infrared temperature sensor; The rescue equipment library includes flexible rescue equipment and a rescue tool library. The flexible rescue equipment can autonomously switch rescue tools. The rescue tool library is used to provide rescue tools for the flexible rescue equipment. The support equipment library includes flexible support equipment, and the flexible support equipment is used to collect and return the tunnel top status data in real time. The data includes the stress condition and displacement of the contact part between the flexible support equipment and the tunnel roof.

9. The integrated tunnel rescue equipment according to claim 1, characterized in that: The transport equipment library includes: Collapsed material transport equipment, used to transport collapsed materials transported by flexible rescue equipment during the rescue process to non-rescue sites or out of the tunnel; The wounded transport equipment is used to transport the wounded during the rescue process to the ground.

10. The integrated tunnel rescue equipment according to claim 4, characterized in that: The data exchange center includes: an instruction data exchange module, an operation data exchange module, an image data exchange module, a data classification and packaging module, and a data processing flow control module; The command data exchange module, the operation data exchange module, and the image data exchange module are used to process the real-time command data, equipment operation data, and image data generated during the rescue process, respectively; The data classification and encapsulation module is used to encapsulate various first rescue real-time data according to a first preset data structure type and generate a real-time data packet; The data processing flow control module is used to control the data operation flow, and the data operation flow includes data collection, packaging, transmission, storage and management.

Images