Training method of large sand table model training system

Abstract

The invention discloses a training method of a sand table large model training system, and relates to the technical field of model training, and the training method of the sand table large model training system comprises the steps that a simulation device obtains training content; the simulation device operates according to the training content so as to simulate different emergencies of the entity sand table; the main controller identifies the emergency and makes a response corresponding to the emergency; the technical scheme provided by the invention has the technical effect.

Description

Technical Field

[0001] The present invention relates to the technical field of model training, and in particular to a training method for a sandbox large model training system. Background Art

[0002] A sandbox model generally refers to a physical or digital model used to simulate and display complex systems or scenarios. It can be used for a variety of purposes, including urban planning, military exercises, architectural design, game development, etc. Through the sandbox model, people can more intuitively observe and analyze the various components of the system and their interrelationships, so as to make better decisions and plans.

[0003] In urban planning, sand table models can show the city layout, traffic flow and building distribution, helping planners to make more effective designs and adjustments. The development of modern technology has made digital sand table models more and more popular. Using virtual reality (VR) and augmented reality (AR) technology, more dynamic and interactive display effects can be achieved.

[0004] However, the existing sandbox model only relies on big data knowledge to respond to obstacles or emergencies encountered in the physical sandbox and make corresponding drills. In the actual response process, the sandbox model cannot accurately respond to obstacles or emergencies in certain special scenarios in different types of physical sandboxes, and the drills made are not correct and reasonable, which greatly reduces the accuracy of the sandbox model's decision-making. Summary of the invention

[0005] The main purpose of the invention is to propose a sandbox model training method, which aims to conduct targeted training on the accurate response to obstacles or emergencies encountered by different types of physical sandboxes, and improve the accuracy of decision-making of the sandbox model.

[0006] To achieve the above-mentioned purpose, the present invention proposes a training method for a sandbox large model training system, wherein the sandbox large model training system comprises a physical sandbox, a simulation device and a main controller, wherein the simulation device and the main controller are both installed on the physical sandbox, and the simulation device is electrically connected to the main controller; the steps of the training method for the sandbox large model training system include:

[0007] The simulator obtains the training content;

[0008] The simulation device operates according to the training content to simulate different emergencies of the physical sandbox;

[0009] The main controller identifies the emergency event and responds to the emergency event.

[0010] In one embodiment, the step of the main controller identifying the emergency event and responding to the emergency event includes:

[0011] The main controller receives the operation signal sent by the simulation device, and determines whether the simulation device has the emergency event according to the operation signal;

[0012] After the main controller confirms that the emergency event occurs in the simulation device, responds to the emergency event and outputs an intervention instruction corresponding to the emergency event to the simulation device;

[0013] The simulation device receives the intervention instruction and performs intervention processing under the control of the intervention instruction to adjust its working state.

[0014] In one embodiment, the steps of waiting for the main controller to confirm that the emergency event occurs in the simulation device, responding to the emergency event, and outputting an intervention instruction corresponding to the emergency event to the simulation device include:

[0015] After the main controller confirms that the emergency event occurs in the simulation device, the main controller obtains the operation signal;

[0016] The main controller confirms the intervention degree of the emergency event simulated by the simulation device according to the operation signal, and determines whether to output the intervention instruction according to the intervention degree;

[0017] When the main controller confirms that the intervention degree reaches a first preset threshold, the main controller sends the intervention instruction to the simulation device.

[0018] In one embodiment, when the main controller confirms that the intervention degree reaches a first preset threshold, the step of sending the intervention instruction to the simulation device further includes:

[0019] When the main controller confirms that the intervention degree is between the first preset threshold and the second preset threshold, a warning signal is sent to the simulation device;

[0020] After receiving the warning signal, the simulation device controls itself to adjust the operating parameters until the intervention level is less than the second preset threshold, then stops the operating parameter adjustment process.

[0021] In one embodiment, after receiving the warning signal, the simulation device controls itself to adjust the operating parameters, including:

[0022] The main controller obtains the operation signal and converts the operation signal into actual operation parameters;

[0023] The main controller compares the actual operating parameters with the preset operating parameters to determine whether the actual operating parameters are consistent with the preset operating parameters;

[0024] If the actual operating parameters are inconsistent with the preset operating parameters, the main controller adjusts the actual operating parameters to the preset operating parameters to obtain current operating parameters, and sends the current operating parameters to the simulation device so that the simulation device moves according to the current operating parameters.

[0025] In one embodiment, the main controller adjusts the actual operating parameters to the preset operating parameters to obtain current operating parameters, and sends the current operating parameters to the simulation device, including:

[0026] Comparing the actual operating parameters with the preset operating parameters to obtain difference parameters;

[0027] The main controller gradually adjusts the actual operating parameters according to the difference parameters until the actual operating parameters are consistent with the preset operating parameters, stops adjusting, and outputs the adjusted current operating parameters to the simulation device.

[0028] In one embodiment, the simulation device receives the intervention instruction and performs intervention processing under the control of the intervention instruction to adjust its working state, the step includes:

[0029] The simulation device controls itself to stop running or reset to the original position under the instruction of the intervention instruction;

[0030] After the simulation device completes the intervention process, it sends an executed electrical signal to the main controller to wait for subsequent instructions from the main controller.

[0031] In one embodiment, after the step of the simulation device receiving the intervention instruction and performing intervention processing under the control of the intervention instruction to adjust its working state, the step further includes:

[0032] The manual intervention device sends a correction control signal to the simulation device;

[0033] The simulation device performs correction processing according to the correction control signal.

[0034] In one embodiment, after the step of performing correction processing according to the correction control signal, the simulation device further comprises:

[0035] The manual intervention device sends a correction control signal to the main controller;

[0036] The main controller analyzes the modified control signal and confirms the emergency event corresponding to the modified control signal;

[0037] The main controller maps the emergency event with the modified control signal, and stores the mapping relationship between the emergency event and the modified control signal.

[0038] In one embodiment, the simulation device operates according to the training content to simulate different emergencies in the physical sandbox, including:

[0039] The simulation controller of the simulation device analyzes the training content and outputs a training plan;

[0040] The simulation controller controls the roadblocks of the simulation device and the simulation vehicle of the simulation device to move on the physical sandbox according to the training plan.

[0041] The sandbox model training system of the technical solution of the present invention includes a physical sandbox, a simulation device and a main controller, the simulation device and the main controller are both installed on the physical sandbox, and the simulation device is electrically connected to the main controller; the steps of the training method of the sandbox model training system include: the simulation device obtains training content; the simulation device operates according to the training content to simulate different emergencies of the physical sandbox; the main controller identifies the emergencies and responds to the emergencies; in this way, different emergencies are simulated according to the received training content by the simulation device to form a more realistic training environment for the main controller in a closer to actual operating environment; then the main controller can identify and respond to emergencies in real time according to the real training environment formed by the simulation device, so that the main controller can conduct targeted training on accurate responses to obstacles or emergencies encountered by different types of physical sandboxes, thereby improving the accuracy of decision-making of the sandbox model. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0043] Figure 1 A schematic diagram of the steps of the training method of the sandbox large model training system provided by the present invention;

[0044] Figure 2 A detailed flow chart of step S3 of the training method of the sandbox large model training system provided by the present invention;

[0045] Figure 3A detailed flow chart of step S32 of the training method of the sandbox large model training system provided by the present invention;

[0046] Figure 4 A detailed flow chart of step S325 of the training method of the sandbox large model training system provided by the present invention;

[0047] Figure 5 A detailed flow chart of step S33 of the training method of the sandbox large model training system provided by the present invention;

[0048] Figure 6 A detailed flow chart of step S33 of the training method of the sandbox large model training system provided by the present invention;

[0049] Figure 7 A detailed flowchart of step S2 of the training method of the sandbox large model training system provided by the present invention.

[0050] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0053] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features limited to "first" and "second" may explicitly or implicitly include at least one of the features. In addition, if "and / or" or "and / or" appears in the full text, its meaning includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0054] The invention provides a training method for a sandbox large model training system.

[0055] See also Figure 1 In one embodiment of the present invention, the sandbox large model training system includes a physical sandbox, a simulation device and a main controller, the simulation device and the main controller are both installed on the physical sandbox, and the simulation device is electrically connected to the main controller; the physical sandbox is used to simulate the terrain, landform and other features in the real environment, and the size of the physical sandbox can be customized according to actual needs. The simulation device is installed on the physical sandbox, and is used to obtain training content and run simulations. The simulation device includes a simulation controller and a simulation operation module, and the simulation controller is used to receive external input training content, such as terrain data, climate data, etc. The simulation operation module simulates different emergencies that may occur on the physical sandbox according to the training content, such as natural disasters, man-made accidents, etc. The main controller is installed on the physical sandbox and is electrically connected to the simulation controller and the simulation operation module of the simulation device. The simulation operation module includes multiple simulation vehicles, multiple roadblocks, multiple meteorological sensors, and multiple fault sensors, wherein the simulation vehicles are used to simulate the movement of cars in the physical sandbox, the roadblocks are used to simulate different obstacles in the physical sandbox, the meteorological sensors are used to simulate emergencies of bad weather in the physical sandbox, and the fault sensors are used to simulate emergencies of large equipment in the physical sandbox encountering faults, etc. The simulation operation module includes but is not limited to the above-mentioned simulation components, and other types of simulation components can also be set according to needs.

[0056] The training method of the sandbox large model training system includes the following steps:

[0057] S1: The simulation device obtains the training content;

[0058] The simulation device obtains training content, such as terrain, climate and other data. The simulation device can obtain training content by setting a signal input device connected to the simulation device, so that the trainee can input the training content for selection or directly randomly select from multiple training contents saved in the signal input device.

[0059] The present invention obtains training content through a simulation device, and can achieve a comprehensive simulation of a physical sandbox training environment. This technical feature directly brings about the beneficial effect of improving training efficiency. Compared with the traditional manual setting of training scenes, the present invention can automatically complete the setting of training content, greatly reducing the time for training preparation and improving the efficiency of training.

[0060] S2: the simulation device operates according to the training content to simulate different emergencies of the physical sandbox;

[0061] The simulator simulates different emergencies that may occur on the physical sandbox through the simulation operation module based on the acquired training content. For example, the simulator can simulate natural disasters such as floods and fires, as well as man-made accidents such as building collapses and traffic accidents.

[0062] The simulation device runs according to the training content and can simulate different emergencies in the physical sandbox. This technical feature makes the training closer to the actual operating environment and improves the practicality and pertinence of the training. In the prior art, due to the lack of effective simulation means, the training scenes are often too idealized and it is difficult to simulate various complex situations that may occur in actual operations. The simulation device of the present invention can generate a variety of emergencies, so that the main controller can perform decision-making training in a more realistic environment, improving the ability to deal with practical problems.

[0063] S3: The main controller identifies the emergency event and responds to the emergency event.

[0064] The main controller identifies the emergency events simulated by the simulation device through the identification module, and responds through the response module according to the identification results. The response measures include but are not limited to launching emergency plans, adjusting training strategies, and recording training data.

[0065] In the prior art, the main controller can only respond to preset scenarios and cannot effectively respond to unpreset emergencies. However, the main controller in this case can identify these emergencies and respond accordingly. This technical feature improves the intelligence level of the system, enables the main controller to make corresponding adjustments according to different emergencies, and enhances the flexibility and adaptability of the training of the main controller.

[0066] The present invention simulates different emergencies according to the received training content through a simulation device, so as to be closer to the actual operating environment and form a more realistic training environment for the main controller; then the main controller can identify and respond to emergencies in real time according to the real training environment formed by the simulation device, so that the main controller can conduct targeted training on accurate response to obstacles or emergencies encountered by different types of physical sand tables, thereby improving the accuracy of decision-making of the large sand table model.

[0067] In one embodiment, see Figure 1 and Figure 2 , S3: The step of the main controller identifying the emergency event and responding to the emergency event includes:

[0068] S31: the main controller receives the operation signal sent by the simulation device, and determines whether the simulation device has the emergency event according to the operation signal;

[0069] The main controller receives the operation signal sent by the simulation device through its built-in communication interface. The operation signal contains information such as the current working status and operation parameters of the simulation device. For example, assuming that the simulation device is a flight simulator used for flight training, the main controller will receive the current flight speed, altitude, heading and other parameters of the simulator.

[0070] The main controller analyzes the received operation signals to determine whether the simulation device has any unexpected events. For example, the flight simulator may encounter unexpected events such as airborne system failures and changes in the external environment. The main controller has a built-in event recognition algorithm, which can accurately identify whether the simulation device has any abnormal conditions through real-time analysis of the operation signals.

[0071] S32: Wait for the main controller to confirm that the emergency event occurs in the simulation device, respond to the emergency event, and output an intervention instruction corresponding to the emergency event to the simulation device;

[0072] Once the main controller confirms that an emergency has occurred in the simulation device, it will immediately initiate a response mechanism. The main controller generates corresponding intervention instructions by analyzing the nature and severity of the event. For example, if the simulation device is a flight simulator, and the flight simulator detects an engine failure, the main controller will generate an intervention instruction to reduce the flight speed and adjust the flight path.

[0073] S33: The simulation device receives the intervention instruction and performs intervention processing under the control of the intervention instruction to adjust its working state.

[0074] The main controller sends the generated intervention instruction to the simulation device through the communication interface. The intervention instruction includes the adjustment instruction of the working state of the simulation device to ensure that the simulation device can respond to emergencies safely and effectively. For example, the intervention instruction may include "lower the flight altitude to 3000 meters", "turn off the faulty engine", etc. After the simulation device receives the intervention instruction sent by the main controller, it immediately performs intervention processing according to the content of the instruction. The simulation device has a built-in execution module that can quickly adjust the working state according to the instruction. For example, after receiving the instruction of "lowering the flight altitude to 3000 meters", the flight simulator will automatically adjust the flight parameters so that the flight altitude displayed by the simulator drops to 3000 meters.

[0075] By real-time monitoring and judging the received operation signals by the main controller, emergencies in the simulation device can be discovered in time. This process improves the intelligence level of the system, allowing the simulation device to respond in time when encountering problems, thereby effectively avoiding potential risks and losses caused by failure to discover and respond to emergencies in time. Secondly, after confirming the emergency, the main controller can quickly output intervention instructions corresponding to the event. The design of this response mechanism greatly shortens the time from the occurrence of the event to the output of the intervention instruction, improves the emergency response speed of the system, and ensures the safe and stable operation of the simulation device under various working conditions. Furthermore, after receiving the intervention instruction, the simulation device can perform corresponding intervention processing and adjust the working state according to the instruction requirements. This process not only enhances the adaptive ability of the system, but also enables the simulation device to make rapid adjustments according to changes in actual working conditions.

[0076] In one embodiment, see Figure 1 and Figure 3 S32: The step of waiting for the main controller to confirm that the emergency event occurs in the simulation device, responding to the emergency event, and outputting an intervention instruction corresponding to the emergency event to the simulation device includes:

[0077] S321: After the main controller confirms that the emergency event occurs in the simulation device, the main controller obtains the operation signal;

[0078] The main controller first needs to monitor the operating status of the simulation device in real time. To this end, the main controller collects data through multiple sensors connected to the simulation device. These sensors may include but are not limited to position sensors, speed sensors, pressure sensors, and temperature sensors. These sensors can provide key operating parameters such as the real-time position, speed, pressure, and temperature of the simulation device.

[0079] The main controller receives data streams in real time through multiple sensors connected to the simulation device. The data acquisition system has high precision and high stability, which can ensure the accuracy and real-time nature of the data. The data processing unit inside the main controller processes the data quickly and extracts key operating signals.

[0080] The main controller can detect abnormal conditions of the simulation device in time through real-time monitoring, such as abnormal speed, excessive pressure or temperature outside the normal range. This helps prevent potential failures and accidents and improves the safety and reliability of the simulation device.

[0081] S322: the main controller confirms the intervention degree of the emergency event simulated by the simulation device according to the operation signal, and determines whether to output the intervention instruction according to the intervention degree;

[0082] The main controller analyzes the current operating status of the simulation device based on the acquired operating signals and evaluates the degree of intervention for possible emergencies. This process involves complex algorithms and logical judgments. The central processing unit inside the main controller runs a pre-set algorithm to analyze the collected operating signals. The algorithm calculates an intervention degree value based on the degree of abnormality of the operating signal. This value reflects the degree of deviation between the current state of the simulation device and the normal operating state. The main controller compares the intervention degree value with the preset threshold to determine whether an intervention instruction needs to be output.

[0083] By accurately assessing the degree of intervention, the main controller can make more reasonable decisions, avoid unnecessary intervention, and ensure timely response when it is really needed. This not only improves the operating efficiency of the simulation device, but also reduces the waste of resources caused by misjudgment.

[0084] S323: When the main controller confirms that the intervention degree reaches a first preset threshold, the intervention instruction is sent to the simulation device.

[0085] When the main controller confirms that the intervention level reaches the first preset threshold, it will send an intervention instruction to the simulation device to respond to the emergency. Once the main controller determines that intervention is needed, it will immediately generate an intervention instruction and send it to the simulation device through the communication interface. The instruction contains specific operation steps, such as deceleration, stopping, adjusting pressure or temperature, etc. After receiving the instruction, the simulation device will immediately perform the corresponding operation to alleviate or eliminate the impact of the emergency. Through timely intervention, the simulation device can quickly resume normal operation, and at the same time allow the main controller to gain experience in solving emergencies.

[0086] In one embodiment, see Figure 1 and Figure 3S323: When the main controller confirms that the intervention degree reaches the first preset threshold, the step of sending the intervention instruction to the simulation device further includes:

[0087] S324: When the main controller confirms that the intervention degree is between the first preset threshold and the second preset threshold, sending a warning signal to the simulation device;

[0088] When the master controller confirms that the intervention level of the simulation device is between the first preset threshold and the second preset threshold, it will send an early warning signal to the simulation device. This step is part of the system safety strategy and is intended to provide early warning to avoid potential risks.

[0089] The main controller continuously monitors the operating data of the simulation device and analyzes this data through the built-in algorithm. When the monitored intervention level is between the first preset threshold and the second preset threshold, the main controller will identify the potential risk. The main controller will then generate an early warning signal based on the analysis results. The signal contains the current operating status information of the simulation device, the intervention level, and possible risk warnings. The early warning signal is then sent to the simulation device through a wireless or wired communication module. The communication module ensures stable transmission of the signal to prevent early warning delays caused by communication failures. After the simulation device receives the early warning signal, it will send a confirmation message to the main controller to ensure that the early warning signal has been correctly received.

[0090] By sending early warning signals, operators or automatic control systems can be reminded to take preventive measures before potential risks occur, thereby improving the safety of the system. Early warning signals help to detect and deal with small problems in a timely manner to prevent them from becoming big problems, thereby reducing the possibility of accidents. The early warning mechanism allows the simulator to make adjustments before the problem becomes serious, which helps to maintain the efficient operation of the simulator and also helps the main controller obtain early warning capabilities to reduce the risks brought by emergencies in advance.

[0091] S325: After receiving the warning signal, the simulation device controls itself to adjust the operating parameters until the intervention level is less than the second preset threshold, and then stops the operating parameter adjustment process.

[0092] The simulation controller of the simulation device receives the warning signal from the main controller through the built-in communication module, analyzes the content of the warning signal, and determines the operating parameters that need to be adjusted. Then, according to the instructions of the warning signal, the simulation device automatically adjusts its operating parameters, such as speed, temperature, pressure, etc., to reduce the degree of intervention. During the adjustment process, the simulation device continues to monitor its own operating status to ensure the effect of the adjustment. When the monitored degree of intervention is lower than the second preset threshold, the simulation device stops adjusting the operating parameters.

[0093] The simulator can automatically respond to warning signals, reducing reliance on manual intervention; and the automatic adjustment mechanism enables the simulator to quickly respond to warnings, improving the system's response speed. By timely adjusting operating parameters, the simulator can maintain stable operation, avoiding shutdowns or damage caused by abnormal parameters, while allowing the main controller and trainers to directly observe the response actions made by the simulator to the main controller's decisions, so that the main controller and trainers can make better decisions to resolve emergencies.

[0094] In one embodiment, see Figure 1 , Figure 3 and Figure 4 S325: After receiving the warning signal, the simulation device controls itself to adjust the operating parameters, including:

[0095] S3251: The main controller obtains the operation signal and converts the operation signal into actual operation parameters;

[0096] The main controller collects operating signals in real time through a sensor array connected to the simulation device. These signals may include data such as position, speed, pressure, temperature, etc. The data processing unit (such as a digital signal processor DSP) inside the main controller processes the collected raw signals, including filtering, amplification, analog-to-digital conversion, etc., to ensure the accuracy and availability of the signals. The processed signals are converted into actual operating parameters, such as current speed, current pressure, etc. This conversion process involves complex mathematical models and algorithms to ensure the accuracy of the conversion. The converted operating parameters are stored in the memory of the main controller for subsequent comparison and adjustment.

[0097] By acquiring and converting operating signals in real time, the main controller can accurately monitor the operating status of the simulation device and detect abnormalities in a timely manner. The converted operating parameters provide a reliable data basis for subsequent comparison and adjustment, improving the system's response speed and adjustment accuracy.

[0098] S3252: The main controller compares the actual operating parameters with the preset operating parameters to determine whether the actual operating parameters are consistent with the preset operating parameters;

[0099] The main controller reads the actual operating parameters from the memory and compares them with the preset operating parameters. The preset operating parameters are the parameters that the simulation device should reach in an ideal or safe state. Through comparison, the main controller determines whether the actual operating parameters are consistent with the preset operating parameters. This judgment involves precise numerical comparison and logical judgment. If the actual operating parameters are inconsistent with the preset operating parameters, the main controller will identify the abnormality and prepare to make adjustments.

[0100] Through timely comparison and judgment, the main controller can promptly detect the operation deviation of the simulation device and prepare to make adjustments. The main controller helps prevent potential failures and accidents through comparison, improving the safety and reliability of the simulation device.

[0101] S3253: If the actual operating parameters are inconsistent with the preset operating parameters, the main controller adjusts the actual operating parameters to the preset operating parameters to obtain current operating parameters, and sends the current operating parameters to the simulation device so that the simulation device moves according to the current operating parameters.

[0102] The main controller adjusts the actual operating parameters based on the comparison results through the built-in adjustment algorithm. The adjustment algorithm may include PID control, fuzzy control, etc. to ensure the accuracy and effectiveness of the adjustment. The adjusted operating parameters are called current operating parameters, which are the new target state that the simulation device needs to achieve. The main controller sends the current operating parameters to the simulation device through the communication module. The communication module ensures the accurate transmission of the parameters. After receiving the current operating parameters, the simulation device adjusts its own operating state according to these parameters, such as adjusting the speed, pressure, etc.

[0103] By quickly adjusting and sending the current operating parameters, the main controller can enable the simulation device to respond quickly to abnormal situations, improving the stability of the system. The adjusted operating parameters ensure that the simulation device can operate as expected, improving the accuracy and efficiency of the operation.

[0104] In one embodiment, see Figure 1 , Figure 3 and Figure 4 , S3253: The main controller adjusts the actual operating parameters to the preset operating parameters to obtain current operating parameters, and sends the current operating parameters to the simulation device, including:

[0105] Comparing the actual operating parameters with the preset operating parameters to obtain difference parameters;

[0106] The main controller gradually adjusts the actual operating parameters according to the difference parameters until the actual operating parameters are consistent with the preset operating parameters, stops adjusting, and outputs the adjusted current operating parameters to the simulation device.

[0107] The main controller first compares the actual operating parameters obtained from the sensor with the preset operating parameters. This process involves precise numerical calculations and comparisons to determine the difference between the two. After the comparison, the main controller calculates the difference between the actual operating parameters and the preset operating parameters, namely the difference parameter. The difference parameter is the key to the adjustment process, which guides the main controller on how to adjust the actual operating parameters. The main controller gradually adjusts the actual operating parameters based on the difference parameter through the built-in adjustment algorithm. The adjustment process is dynamic, and the main controller monitors the adjustment effect in real time and makes fine adjustments as needed. During the adjustment process, the main controller continuously compares the adjusted actual operating parameters with the preset operating parameters. When the two are consistent, the main controller stops the adjustment process. After the adjustment is completed, the main controller sends the adjusted current operating parameters to the simulation device through the communication module. After receiving these parameters, the simulation device will operate according to the new operating parameters.

[0108] Through gradual adjustments, the main controller can accurately adjust the actual operating parameters to the preset operating parameters to ensure that the performance of the simulation device meets the expected standards. During the adjustment process, the main controller can monitor the operating status of the simulation device in real time, detect and resolve deviations in a timely manner, and improve the stability and reliability of the system.

[0109] In one embodiment, see Figure 1 , Figure 2 and Figure 5 , S33: The simulation device receives the intervention instruction and performs intervention processing under the control of the intervention instruction to adjust its working state, the step includes:

[0110] S331: the simulation device controls itself to stop running or reset to the original position under the instruction of the intervention instruction;

[0111] S332: After the simulation device completes the intervention process, it sends an executed electrical signal to the main controller to wait for subsequent instructions from the main controller.

[0112] The simulator receives intervention instructions from the main controller through the built-in communication module. These instructions may instruct the simulator to stop running or reset to the original position. The microcontroller of the simulator parses the received intervention instructions to determine the specific operations that need to be performed. The parsing process involves decoding and understanding the instruction data. If the instruction requires stopping, the actuator of the simulator (such as a motor) will be immediately cut off from power to achieve a quick stop. If the instruction requires a reset, the simulator will start the built-in positioning system and return to the original position according to the preset coordinates or path. Once the intervention operation is completed, the simulator will send an executed electrical signal to the main controller, indicating that the intervention process has been completed and wait for subsequent instructions from the main controller.

[0113] The simulation device can quickly respond to the intervention command of the main controller, stop or reset in time, and improve the safety of the system. Through precise instruction parsing and execution, the simulation device can accurately perform stop or reset operations, reducing operational errors. By sending execution signals to the main controller, the simulation device provides real-time feedback on the operating status, allowing the main controller to understand the on-site situation in a timely manner and make further decisions.

[0114] In one embodiment, see Figure 1 , Figure 2 and Figure 6 S33: the simulation device receives the intervention instruction and performs intervention processing under the control of the intervention instruction to adjust its working state, and further includes:

[0115] S34: The manual intervention device sends a correction control signal to the simulation device;

[0116] The operator performs manual intervention at the control console or through the remote control device. This may include adjusting the operating parameters of the simulator, such as speed, direction, pressure, etc. The manual intervention device generates correction control signals based on the operator's input. These signals contain the specific adjusted parameters and are used to guide the main controller to perform correction processing on the simulator. The manual intervention device sends the correction control signals to the simulator through the communication module. The communication module ensures stable transmission of the signal to prevent signal loss or errors caused by communication failures. After the simulator receives the correction control signal, it will send a confirmation message to the manual intervention device to ensure that the signal has been correctly received.

[0117] Through manual intervention, trainers can make detailed adjustments to the working state of the simulator according to actual conditions, which improves the flexibility of the system. Manual intervention provides more precise control means, which helps to optimize the internal algorithm of the main controller, so that the main controller can output more accurate decisions after manual intervention.

[0118] S35: The simulation device performs correction processing according to the correction control signal.

[0119] The simulation device receives the correction control signal from the manual intervention device through the communication module. The microcontroller of the simulation device analyzes the correction control signal and determines the correction operation to be performed. According to the analysis results, the actuator of the simulation device (such as a motor, a hydraulic system) performs the correction operation, such as adjusting the speed, changing the direction, adjusting the pressure, etc. During the correction operation, the sensor array of the simulation device continuously monitors its status and provides real-time feedback to the operator to ensure the accuracy and safety of the correction operation. After the correction operation is completed, the simulation device sends a confirmation signal of the completion of the correction to the manual intervention device.

[0120] Through correction processing, the simulator can accurately adjust the working state according to the operator's requirements, improving the accuracy of operation. Correction processing helps to ensure the stable operation of the simulator and reduce the risk of failure caused by parameter deviation. The trainee can directly participate in the control of the simulator, improving the decision-making ability of the main controller.

[0121] In one embodiment, see Figure 1 , Figure 2 and Figure 6 S35: After the step of the simulation device performing correction processing according to the correction control signal, the step further includes:

[0122] S36: The manual intervention device sends a correction control signal to the main controller;

[0123] The operator performs manual intervention at the control console or through a remote control device. The manual intervention device generates correction control signals based on the operator's input. These signals contain specific parameters after adjustment and are used to guide the main controller for further analysis and processing. The manual intervention device sends the correction control signal to the main controller through the communication module. After receiving the correction control signal, the main controller sends a confirmation message to the manual intervention device to ensure that the signal has been correctly received.

[0124] S37: the main controller analyzes the modified control signal and confirms the emergency event corresponding to the modified control signal;

[0125] The main controller receives the correction control signal from the manual intervention device through the communication module. The microcontroller of the main controller analyzes the correction control signal and extracts key information from the signal, such as the parameters and range of adjustment. According to the analysis results, combined with the operating status and historical data of the simulation device, the emergency event corresponding to the correction control signal is confirmed. The main controller records the confirmed emergency event in the event log for subsequent analysis and processing.

[0126] By accurately identifying emergencies, the main controller can take appropriate measures to ensure the safe operation of the system. The main controller can optimize the working performance of the simulation device according to the nature and impact of the emergencies.

[0127] S38: The main controller maps the emergency event with the modified control signal, and stores the mapping relationship between the emergency event and the modified control signal.

[0128] The master controller generates a mapping relationship based on the confirmed emergency events and the correction control signals. This mapping relationship clarifies the correspondence between specific events and specific control signals. The master controller stores the generated mapping relationship in the mapping database. The database design allows for fast retrieval and update of mapping relationships. If the same emergency event is encountered in the future, the master controller can directly retrieve the corresponding correction control signal from the mapping database and respond to the event quickly. The master controller can also continuously optimize the mapping relationship based on the results and feedback of event processing to improve the system's adaptive ability.

[0129] By storing and optimizing mapping relationships, the system can better adapt to different operating environments and conditions. The existence of mapping relationships enables the system to quickly respond to similar emergencies and reduce the time for event processing. The storage and optimization of mapping relationships improves the data processing capabilities of the main controller and makes the system more intelligent.

[0130] In one embodiment, see Figure 1 and Figure 7 S2: The simulation device operates according to the training content to simulate different emergencies in the physical sandbox, including:

[0131] S21: The simulation controller of the simulation device analyzes the training content and outputs a training plan;

[0132] The simulation controller receives training content containing descriptions of various emergencies that may occur on the physical sandbox. This content may be provided in a data file, database query results, or other electronic format. The analysis module inside the simulation controller performs a detailed analysis of the training content to identify key simulation parameters and event characteristics. The analysis process may involve natural language processing, pattern recognition, or machine learning algorithms. Based on the analysis results, the simulation controller generates a training plan. The plan describes in detail how the simulation device should act to simulate various emergencies, including the arrangement of roadblocks and the movement path of the simulated vehicle. The generated training plan is output to a format that is easy for the simulation controller to understand and execute. This may involve converting the plan into a series of control instructions or action sequences.

[0133] By analyzing the training content in detail, the simulation controller can ensure that the simulation device accurately simulates the emergencies in the physical sandbox. The generation of training plans makes the simulation training process more efficient and organized, reducing uncertainty and confusion during the training process. The simulation controller can flexibly adjust the training plan according to different training contents, improving the adaptability of the system.

[0134] S22: The simulation controller controls the roadblocks of the simulation device and the simulation vehicle of the simulation device to move on the physical sandbox according to the training plan.

[0135] The simulation controller converts the action items in the training plan into specific control instructions, which specify in detail the placement of the roadblocks and the movement path of the simulation vehicle. The simulation controller controls the movement and placement of the roadblocks through motors, servo mechanisms or other mechanical devices to ensure that they are correctly placed on the physical sandbox according to the training plan. The simulation controller sends control instructions to the simulation vehicle through wireless or wired communication to guide its movement on the sandbox to simulate specific traffic flows or event scenarios. During execution, the simulation controller continuously monitors the movement status of the roadblocks and the simulation vehicle to ensure that they are executed according to the training plan. If there are any deviations, the simulation controller will make real-time adjustments.

[0136] By precisely controlling the movement of the roadblocks and the simulation vehicle, the simulation device can realistically simulate emergencies in the physical sandbox, providing a realistic scenario for training. The simulation controller can flexibly control the simulation device according to the training plan, making the training process richer and more effective. By simulating different emergencies, the main controller can gain valuable response experience in a safe environment, improving the effectiveness of training.

[0137] The above description is only an exemplary embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the technical concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A training method for a sandbox large model training system, characterized in that: The sandbox large model training system comprises a physical sandbox, a simulation device and a main controller, the simulation device and the main controller are both installed on the physical sandbox, and the simulation device is electrically connected to the main controller; The training method of the sandbox large model training system includes the following steps: The simulator obtains the training content; The simulation device operates according to the training content to simulate different emergencies of the physical sandbox; The main controller identifies the emergency event and responds to the emergency event.

2. The training method of the sandbox large model training system as claimed in claim 1, characterized in that: The step of the main controller identifying the emergency event and responding to the emergency event includes: The main controller receives the operation signal sent by the simulation device, and determines whether the simulation device has the emergency event according to the operation signal; After the main controller confirms that the emergency event occurs in the simulation device, responds to the emergency event and outputs an intervention instruction corresponding to the emergency event to the simulation device; The simulation device receives the intervention instruction and performs intervention processing under the control of the intervention instruction to adjust its working state.

3. The training method of the sandbox large model training system as claimed in claim 2, characterized in that: The steps of waiting for the main controller to confirm that the emergency event occurs in the simulation device, responding to the emergency event, and outputting an intervention instruction corresponding to the emergency event to the simulation device include: After the main controller confirms that the emergency event occurs in the simulation device, the main controller obtains the operation signal; The main controller confirms the intervention degree of the emergency event simulated by the simulation device according to the operation signal, and determines whether to output the intervention instruction according to the intervention degree; When the main controller confirms that the intervention degree reaches a first preset threshold, the main controller sends the intervention instruction to the simulation device.

4. The training method of the sandbox large model training system as claimed in claim 3, characterized in that: When the main controller confirms that the intervention degree reaches a first preset threshold, the step of sending the intervention instruction to the simulation device further includes: When the main controller confirms that the intervention degree is between the first preset threshold and the second preset threshold, a warning signal is sent to the simulation device; After receiving the warning signal, the simulation device controls itself to adjust the operating parameters until the intervention level is less than the second preset threshold, then stops the operating parameter adjustment process.

5. The training method of the sandbox large model training system as claimed in claim 4, characterized in that: After receiving the warning signal, the simulation device controls itself to adjust the operating parameters, including: The main controller obtains the operation signal and converts the operation signal into actual operation parameters; The main controller compares the actual operating parameters with the preset operating parameters to determine whether the actual operating parameters are consistent with the preset operating parameters; If the actual operating parameters are inconsistent with the preset operating parameters, the main controller adjusts the actual operating parameters to the preset operating parameters to obtain current operating parameters, and sends the current operating parameters to the simulation device so that the simulation device moves according to the current operating parameters.

6. The training method of the sandbox large model training system as claimed in claim 5, characterized in that: The step of the main controller adjusting the actual operating parameters to the preset operating parameters to obtain current operating parameters, and sending the current operating parameters to the simulation device includes: Comparing the actual operating parameters with the preset operating parameters to obtain difference parameters; The main controller gradually adjusts the actual operating parameters according to the difference parameters, stops adjusting when the actual operating parameters are consistent with the preset operating parameters, and outputs the adjusted current operating parameters to the simulation device.

7. The training method of the sandbox large model training system as claimed in claim 2, characterized in that: The step of the simulation device receiving the intervention instruction and performing intervention processing under the control of the intervention instruction to adjust its working state includes: The simulation device controls itself to stop running or reset to the original position under the instruction of the intervention instruction; After the simulation device completes the intervention process, it sends an executed electrical signal to the main controller to wait for subsequent instructions from the main controller.

8. The training method of the sandbox large model training system as claimed in claim 2, characterized in that: After the step of the simulation device receiving the intervention instruction and performing intervention processing under the control of the intervention instruction to adjust its working state, the method further includes: The manual intervention device sends a correction control signal to the simulation device; The simulation device performs correction processing according to the correction control signal.

9. The training method of the sandbox large model training system as claimed in claim 8, characterized in that: After the step of the simulation device performing correction processing according to the correction control signal, the simulation device further comprises: The manual intervention device sends a correction control signal to the main controller; The main controller analyzes the modified control signal and confirms the emergency event corresponding to the modified control signal; The main controller maps the emergency event with the modified control signal, and stores the mapping relationship between the emergency event and the modified control signal.

10. The training method of the sandbox large model training system according to claim 1, characterized in that: The simulation device operates according to the training content to simulate different emergencies in the physical sandbox, including: The simulation controller of the simulation device analyzes the training content and outputs a training plan; The simulation controller controls the roadblocks of the simulation device and the simulation vehicle of the simulation device to move on the physical sandbox according to the training plan.

Images