An intelligent joint control method, system and device for a full-movement simulator environment and a storage medium

Abstract

The application relates to the technical field of environment control and multi-system linkage of flight simulation training equipment, and provides a full-motion simulator environment intelligent linkage control method, system, equipment and storage medium, which solves the problems of low intelligent level and poor emergency response efficiency of multi-system cooperative control. The method comprises the following steps: acquiring the operation data and basic environment parameters of each subsystem in the environment linkage control system in real time through a multi-dimensional environment perception network, and performing fusion and state analysis to identify safety abnormalities, smoke simulation triggering or subsystem faults; when the above abnormal signals are identified, corresponding linkage control instructions are generated by using a logic control algorithm, and the instructions are sent to external systems such as power supply, gallery bridge, motion, fire alarm and an IOS instructor station through a cross-system linkage control mechanism; the system receives external feedback signals in real time, dynamically adjusts the cooperative control strategy, and constructs a closed-loop intelligent linkage control system. The application improves the intelligent level and emergency response efficiency of multi-system cooperative control.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of environment control and multi-system cooperative linkage of flight simulation training equipment, and particularly relates to a full-motion simulator environment intelligent linkage control method, system, device and storage medium. BACKGROUND

[0002] With the continuous improvement of the complexity of modern flight training equipment, higher requirements are put forward for the real-time performance, accuracy and multi-system cooperation of environment control. In particular, during the operation of the full-motion simulator, the cabin environment parameters, equipment operating states and external cooperative systems need to be monitored and intelligently linked in an integrated manner to ensure training safety and simulation authenticity. The traditional single environment monitoring method has been difficult to meet the intelligent linkage control needs of multi-dimensional and cross-system.

[0003] At present, the existing scheme adopts a distributed environment monitoring system based on a sensor network, which collects real-time data of key areas in the simulator cabin and equipment cabinets through the deployment of temperature and humidity, pressure and gas flow sensors. The monitoring data is transmitted to the central control unit through the industrial network, and the system performs threshold comparison and abnormal alarm, and provides fault handling suggestions to the maintenance personnel, forming an automatic monitoring system with environment parameter monitoring as the core.

[0004] However, the existing scheme focuses on the independent monitoring of basic environment parameters in terms of function, and the monitoring dimension is limited to physical quantities such as temperature and humidity, gas flow, and the cooperative monitoring capability of the subsystem operating states such as safety state, smoke simulation, oxygen supply and lighting is still insufficient. In addition, the linkage mechanism between the system and the external systems such as the motion platform, the corridor bridge and the power supply is weak, and when an environmental anomaly occurs, it is difficult to achieve cross-system rapid response and cooperative control, which to some extent affects the overall operation efficiency and emergency handling capability. SUMMARY

[0005] The present application provides a full-motion simulator environment intelligent linkage control method, system, device and storage medium to solve the problems of low intelligent level and poor emergency response efficiency of multi-system cooperative control in the prior art.

[0006] To solve the above technical problems, in a first aspect, the present application provides a full-motion simulator environment intelligent linkage control method, comprising:

[0007] obtaining operating data and basic environment parameters from a plurality of subsystems in an environment linkage control system through a multi-dimensional environment perception network, the plurality of subsystems including a safety subsystem, a smoke subsystem, an oxygen supply subsystem, a lighting subsystem and an air conditioning subsystem;

[0008] fusing and analyzing the operation data and the basic environment parameters in real time to identify whether there is an abnormal signal, the abnormal signal including a safety abnormal signal, a smoke simulation training trigger signal or a fault alarm signal issued by any subsystem;

[0009] When any type of abnormal signal is identified, corresponding linkage control instructions are generated according to the type of the abnormal signal by using a logic control algorithm, the linkage control instructions including a multi-system linkage control instruction set, a cooperative response instruction set or a fault isolation instruction set;

[0010] The multi-system linkage control instruction set, the cooperative response instruction set or the fault isolation instruction set is issued to corresponding external systems including a power supply system, a gallery bridge system, a motion system, a fire alarm system and an IOS instructor station through a cross-system linkage control mechanism;

[0011] Feedback signals sent by the corresponding external systems are received, and a cooperative control strategy between the environment linkage control system and each external system is dynamically adjusted according to the feedback signals to realize a closed-loop intelligent linkage control system.

[0012] Optionally, the receiving of the feedback signals sent by the corresponding external systems and the dynamic adjustment of the cooperative control strategy between the environment linkage control system and each external system according to the feedback signals include:

[0013] The power supply state feedback signal from the power supply system, the position state feedback signal from the gallery bridge system, the attitude state feedback signal from the motion system and the alarm state feedback signal from the fire alarm system are received;

[0014] State parameters in each feedback signal are analyzed to obtain a load connection state of the power supply system, lifting height data of the gallery bridge system, displacement data of the motion system and a sensor state of the fire alarm system;

[0015] The load connection state, the lifting height data, the displacement data and the sensor state are compared with a preset power supply cutoff expected state, a gallery bridge lowering expected position, a motion system homing expected attitude and a fire alarm system shielding expected state respectively;

[0016] According to the comparison result, the cooperative control strategy between the environment linkage control system and each external system is dynamically adjusted.

[0017] Optionally, the dynamic adjustment of the cooperative control strategy between the environment linkage control system and each external system according to the comparison result includes:

[0018] According to the difference degree in the comparison result, whether there is an instruction execution deviation or a system response abnormality is identified;

[0019] When the identification result is instruction execution deviation, the duration and deviation value of the instruction execution deviation are analyzed, and corresponding strategy adjustment parameters are generated according to the analysis result;

[0020] When the identification result is system response anomaly, the communication state and device state of the abnormal system are detected through a deep learning fault diagnosis model, and a candidate control path is generated according to the detection result;

[0021] The strategy adjustment parameters or the candidate control path are taken as input parameters, and based on the input parameters, a collaborative control strategy between the environmental joint control system and each external system is updated in combination with a reinforcement learning decision model.

[0022] Optionally, the detection of the communication state and the device state of the abnormal system through the deep learning fault diagnosis model and the generation of the candidate control path according to the detection result comprise:

[0023] The historical running data and the real-time monitoring data of the abnormal system are obtained;

[0024] The historical running data and the real-time monitoring data are taken as input data and input into a deep learning fault diagnosis model, and the deep learning fault diagnosis model comprises a communication state analysis branch and a device state analysis branch;

[0025] Through the communication state analysis branch, feature extraction is performed on a communication message sequence in the input data to obtain communication link feature parameters, and based on the communication link feature parameters, an abnormal communication state is identified;

[0026] Through the device state analysis branch, feature extraction is performed on a device running log in the input data to obtain device running feature parameters, and based on the device running feature parameters, an abnormal device state is identified;

[0027] According to a combination type of the abnormal communication state and the abnormal device state, a corresponding candidate control path is selected from a preset candidate control path set.

[0028] Optionally, the updating of the collaborative control strategy between the environmental joint control system and each external system based on the input parameters in combination with the reinforcement learning decision model comprises:

[0029] The input parameters are mapped into a spatial vector of the reinforcement learning decision model;

[0030] The spatial vector is evaluated to obtain a corresponding system response time score, a resource utilization efficiency score, and a fault recovery success rate score;

[0031] Based on the system response time score, the resource utilization efficiency score, and the fault recovery success rate score, an optimal control strategy is output through a decision network of the reinforcement learning decision model.

[0032] convert the optimal control strategy into update instructions, according to which a collaborative control strategy between the environmental joint control system and each external system is updated.

[0033] Optionally, the real-time fusion and state analysis of the operation data and the basic environment parameters are to identify whether there is an abnormal signal, including:

[0034] The operation data and the basic environment parameters are fused in real time to obtain unified format analysis data;

[0035] The state analysis is performed on the analysis data, and first feature data corresponding to a safe state, second feature data corresponding to smoke simulation, and third feature data corresponding to a device operation state are extracted from the state analysis result;

[0036] When the range corresponding to the first feature data is greater than a preset safe range, it is determined that there is a safety abnormal signal;

[0037] When the range corresponding to the second feature data is greater than a preset training range, it is determined that there is a smoke simulation training trigger signal;

[0038] When the range corresponding to the third feature data is greater than a preset fault range, it is determined that there is a fault alarm signal.

[0039] Optionally, when any type of abnormal signal is identified, a corresponding linkage control instruction is generated according to the type of the abnormal signal by using a logic control algorithm, including:

[0040] According to the type of the abnormal signal, a corresponding linkage control instruction type identifier is determined by using a logic control algorithm;

[0041] According to the linkage control instruction type identifier, a corresponding linkage control instruction is generated, wherein when the linkage control instruction type identifier indicates that a safety abnormal signal is identified, a multi-system linkage control instruction set is generated, the multi-system linkage control instruction set including a motion system back-to-original position instruction, a corridor bridge lowering instruction, a lighting brightness improving instruction, and a power supply cutting off unnecessary load instruction;

[0042] When the linkage control instruction type identifier indicates that a smoke simulation training trigger signal is identified, a collaborative response instruction set is generated, the collaborative response instruction set including a fire alarm system shielding instruction, an oxygen supply subsystem opening instruction, an air conditioning subsystem closing instruction, a lighting subsystem maximum brightness opening instruction, and an exhaust fan starting instruction;

[0043] When the linkage control instruction type identifier indicates that a fault alarm signal is identified, a fault isolation instruction set is generated, the fault isolation instruction set including a motion system hold-in-place lock instruction, a gallery bridge descent hold instruction, and a fault subsystem function disable instruction.

[0044] In a second aspect, the present application provides a full-movement simulator environment intelligent linkage control system, comprising:

[0045] An acquisition module is configured to acquire operation data and basic environment parameters from a plurality of subsystems in an environment linkage control system through a multi-dimensional environment perception network, the plurality of subsystems including a safety subsystem, a smoke subsystem, an oxygen supply subsystem, an illumination subsystem, and an air conditioning subsystem.

[0046] A fusion module is configured to perform real-time fusion and state analysis on the operation data and the basic environment parameters to identify whether an abnormal signal exists, the abnormal signal including a safety abnormal signal, a smoke simulation training trigger signal, or a fault alarm signal from any subsystem.

[0047] An identification module is configured to, when any type of abnormal signal is identified, generate a corresponding linkage control instruction according to the type of the abnormal signal using a logic control algorithm, the linkage control instruction including a multi-system linkage control instruction set, a cooperative response instruction set, or a fault isolation instruction set.

[0048] A delivery module is configured to deliver the multi-system linkage control instruction set, the cooperative response instruction set, or the fault isolation instruction set to corresponding external systems through a cross-system linkage control mechanism, the external systems including a power supply system, a gallery bridge system, a motion system, a fire alarm system, and an IOS instructor station.

[0049] A receiving module is configured to receive feedback signals sent by the corresponding external systems and dynamically adjust a cooperative control strategy between the environment linkage control system and each external system according to the feedback signals to realize a closed-loop intelligent linkage control system.

[0050] In a third aspect, the present application provides an electronic device, comprising:

[0051] A memory is configured to store a computer program.

[0052] A processor is configured to execute the computer program to implement the steps of the full-movement simulator environment intelligent linkage control method of the first aspect.

[0053] In a fourth aspect, the present application provides a computer readable storage medium, the computer readable storage medium storing a computer program, the computer program being executable by a processor to implement the steps of the full-movement simulator environment intelligent linkage control method of the first aspect.

[0054] The technical scheme provided by the application has the following beneficial effects:

[0055] The application constructs a comprehensive environmental monitoring system, realizes efficient collection of various environmental parameters and device operating states, and provides a complete data foundation for subsequent intelligent analysis. Deep fusion and rapid analysis of multi-source data are realized, the accuracy and real-time performance of abnormal identification are improved, and the system can respond to various abnormal situations in a timely manner. Through intelligent algorithms, targeted control instructions are automatically generated, rapid decision-making and accurate response in abnormal situations are realized, and the need for manual intervention is reduced. An efficient communication and collaboration mechanism between multiple systems is established to ensure the rapid transmission and execution of control instructions and improve the overall linkage capability of the system. Through the feedback mechanism, closed-loop control of the system is realized, and the control strategy can be dynamically optimized according to the actual execution situation, improving the adaptive ability and operation reliability of the system.

[0056] Further, the application also receives feedback signals of the power supply system, the corridor bridge system, the motion system and the fire alarm system, analyzes the state parameters and compares them with the expected state, and dynamically adjusts the collaborative control strategy between the environmental joint control system and each external system according to the comparison result.

[0057] Moreover, through real-time feedback and state comparison, dynamic optimization of the multi-system collaborative control strategy is realized, the adaptive ability and overall control precision of the system are improved, and the rapid response and efficient collaboration of each system in abnormal situations are ensured.

[0058] These aspects or other aspects of the application will be more apparent in the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0060] Figure 1 A flowchart of an intelligent joint control method for a full-motion simulator environment provided by an embodiment of the application;

[0061] Figure 2 An environmental joint control multi-dimensional system interaction block diagram of an intelligent joint control method for a full-motion simulator environment provided by an embodiment of the application;

[0062] Figure 3 An environmental joint control multi-dimensional system monitoring schematic diagram of an intelligent joint control method for a full-motion simulator environment provided by an embodiment of the application;

[0063] Figure 4 A safety signal triggering multi-system inter-control cross-linking diagram of the intelligent inter-control method of the full-motion simulator environment provided by the embodiment of the present application;

[0064] Figure 5 A smoke simulation signal multi-system inter-control cross-linking diagram of the intelligent inter-control method of the full-motion simulator environment provided by the embodiment of the present application;

[0065] Figure 6 A subsystem fault signal multi-system inter-control cross-linking diagram of the intelligent inter-control method of the full-motion simulator environment provided by the embodiment of the present application;

[0066] Figure 7 A structural schematic diagram of the intelligent inter-control system of the full-motion simulator environment provided by the embodiment of the present application. DETAILED DESCRIPTION

[0067] The current full-motion simulator environment monitoring system mainly relies on independent monitoring of basic environmental parameters, although it can realize threshold alarm of single parameters such as temperature and humidity, but its monitoring dimension is limited, and it cannot cover key operation indicators such as safety state and smoke simulation. More importantly, the existing scheme lacks an efficient linkage mechanism with external collaborative systems, and when an environmental anomaly occurs, it is difficult to quickly mobilize power supply, motion platform and other systems for collaborative response, resulting in a bottleneck in the overall emergency handling capability.

[0068] In view of the above limitations, the present application provides an intelligent inter-control method of a full-motion simulator environment, which breaks through the limitations of traditional single environmental parameter monitoring, realizes multi-system collaborative response and closed-loop regulation, improves the timeliness of environmental anomaly handling and the collaborative efficiency between systems, and fundamentally solves the problem of insufficient cross-system linkage in the prior art.

[0069] In order for those skilled in the art to better understand the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0070] The core of the present application is to provide an intelligent inter-control method of a full-motion simulator environment, and a flowchart of one specific embodiment thereof is shown in Figure 1 The method comprises:

[0071] Step 101: Obtain running data and basic environmental parameters from multiple subsystems in the environmental inter-control system through a multi-dimensional environmental perception network, wherein the multiple subsystems include a safety subsystem, a smoke subsystem, an oxygen supply subsystem, an illumination subsystem and an air conditioning subsystem.

[0072] In step 101, the multi-dimensional environment perception network refers to a monitoring system composed of multiple types of sensors, including temperature sensors, humidity sensors, pressure sensors, gas flow sensors, safety state detectors, smoke concentration sensors, oxygen concentration sensors, lighting state detectors, and air conditioning operating state detectors. The environment joint control system refers to a central control platform integrating the above-mentioned subsystems. The operating data includes the access state of the safety subsystem, the smoke concentration value of the smoke subsystem, the oxygen output of the oxygen supply subsystem, the brightness level of the lighting subsystem, and the operating mode of the air conditioning subsystem. The basic environmental parameters include temperature, humidity, pressure, and gas flow values.

[0073] In the embodiments of the present application, the system continuously collects environmental data through sensors deployed at various positions in the simulator cabin. Temperature sensors monitor temperature changes in the cabin, humidity sensors detect air humidity levels, pressure sensors obtain air pressure data, gas flow sensors record ventilation status, the safety subsystem monitors access and emergency button status, the smoke subsystem detects smoke concentration, the oxygen supply subsystem measures oxygen content, the lighting subsystem collects brightness information, and the air conditioning subsystem reports operating mode. All data is transmitted to the central processing unit of the environment joint control system through industrial Ethernet, forming a complete multi-source data set.

[0074] For example, in the No. 1 simulator cabin of Flight Simulation Training Center A, the temperature sensor detects that the current temperature is 25 degrees Celsius, the humidity sensor shows that the humidity is 60%, the pressure sensor measures the air pressure value as 101 kilopascals, the gas flow sensor indicates that the ventilation volume is 0.5 cubic meters per second, the safety subsystem reports that all access is in the closed state, the smoke sensor detects the smoke concentration value as 0.1 milligrams per cubic meter, the oxygen supply system shows that the oxygen concentration is 21%, the lighting system brightness is set to 300 lux, and the air conditioning system is in cooling mode. All data is transmitted to the central control console through Ethernet.

[0075] Step 102: Real-time fusion and state analysis of the operating data and the basic environmental parameters to identify whether there are abnormal signals, including safety abnormal signals, smoke simulation training trigger signals, or any subsystem issued fault alarm signals.

[0076] In step 102, real-time fusion refers to the integration of multi-source data in time series. State analysis refers to feature extraction and pattern recognition of the integrated data. Safety abnormal signals include abnormal opening of access or triggering of emergency buttons. Smoke simulation training trigger signals refer to smoke concentration exceeding a preset threshold. Fault alarm signals include abnormal oxygen supply, lighting failure, or air conditioning shutdown.

[0077] In the embodiment of the present application, the multi-source data received by the central processing unit is first subjected to timestamp alignment processing, then a unified format data frame is generated through a data fusion algorithm, then a state analysis algorithm is used to extract data features, including calculating temperature change rate, humidity gradient, pressure fluctuation frequency, gas flow stability, safety state continuity, smoke concentration trend, oxygen supply deviation, lighting brightness fluctuation and air conditioning running state, and finally the extracted features are compared with the preset threshold value, and when any feature value exceeds the threshold value range, the corresponding abnormal signal is generated.

[0078] For example, the central processing unit aligns the received temperature 25 degrees Celsius, humidity 60 percent, etc. with millisecond-level timestamps, forms a data frame after fusion, and analyzes to find that the smoke concentration rises from 0.1 mg per cubic meter to 15 mg per cubic meter in 2 seconds, exceeding the preset threshold value of 10 mg per cubic meter. At the same time, it is detected that the output of the oxygen supply system decreases from 20 liters per minute to 5 liters per minute, which is lower than the minimum threshold value of 15 liters per minute. The system determines to generate a smoke simulation training trigger signal and an oxygen subsystem failure alarm signal.

[0079] Step 103: When any type of abnormal signal is identified, according to the type of the abnormal signal, a corresponding linkage control instruction is generated using a logic control algorithm, the linkage control instruction including a multi-system linkage control instruction set, a cooperative response instruction set or a fault isolation instruction set.

[0080] In step 103, the logic control algorithm is a rule-based decision algorithm. The multi-system linkage control instruction set includes a motion system return instruction, a gallery bridge lowering instruction, a lighting brightening instruction and a power-off instruction. The cooperative response instruction set includes a fire alarm shielding instruction, an oxygen supply opening instruction, an air conditioning closing instruction, a lighting maximum brightness instruction and a smoke exhaust starting instruction. The fault isolation instruction set includes a motion locking instruction, a gallery bridge holding instruction and a fault system disabling instruction.

[0081] In the embodiment of the present application, the logic control algorithm receives the type of abnormal signal as input, queries a predefined rule base, outputs a first type of instruction identifier when the input is a safety abnormal signal, outputs a second type of instruction identifier when the input is a smoke simulation training trigger signal, and outputs a third type of instruction identifier when the input is a fault alarm signal. Then, according to the instruction identifier, the corresponding instruction template is called from the instruction template library, and after filling in the specific parameters, an executable instruction set is generated.

[0082] For example, the system identifies the smoke simulation training trigger signal and the oxygen supply subsystem failure alarm signal, the logic control algorithm first processes the smoke signal, outputs the second type of instruction identifier, generates the instruction set containing the fire alarm shielding command, the oxygen supply opening command (but automatically modified to enable the standby oxygen supply due to oxygen supply failure), the air conditioning closing command, the lighting brightness increasing to the maximum 1000 lux command and the exhaust fan starting command; At the same time, process the failure signal, output the third type of instruction identifier, generate the oxygen supply subsystem disable command and enable the standby oxygen supply system.

[0083] Step 104: The multi-system linkage control instruction set, the cooperative response instruction set or the fault isolation instruction set is issued to the corresponding external system through the cross-system linkage control mechanism, and the external system includes a power supply system, a corridor bridge system, a motion system, a fire alarm system and an IOS instructor station.

[0084] In step 104, the cross-system linkage control mechanism refers to a network protocol-based inter-system communication interface. The external system includes a power supply system that provides power management, a corridor bridge system that controls the boarding channel, a motion system that manages platform motion, a fire alarm system that processes fire alarms, and an IOS instructor station for manual intervention.

[0085] In the embodiments of the present application, the environment linkage control system encapsulates the generated instruction set into a data packet according to a predefined communication protocol, and sends it to the control interface of each external system through an Ethernet switch. The power supply system receives power control instructions, the corridor bridge system receives position control instructions, the motion system receives motion control instructions, the fire alarm system receives alarm management instructions, and the instructor station (Instructor Operating Station, IOS) receives state monitoring instructions.

[0086] For example, the system sends the generated lighting brightness increase instruction to the lighting subsystem control interface, sends the exhaust fan start instruction to the exhaust system control interface, sends the air conditioning closing instruction to the air conditioning subsystem control interface, sends the fire alarm shielding instruction to the fire alarm system control interface, and sends the standby oxygen supply enable instruction to the oxygen supply system control interface. All instructions are transmitted through Gigabit Ethernet within 50 milliseconds.

[0087] Step 105: Receive the feedback signal sent by the corresponding external system, and dynamically adjust the cooperative control strategy between the environment linkage control system and each external system according to the feedback signal to realize a closed-loop intelligent linkage control system.

[0088] In step 105, the feedback signal includes the power supply state confirmation of the power supply system, the position to position signal of the corridor bridge system, the attitude stability signal of the motion system and the alarm shielding confirmation of the fire alarm system. Dynamic adjustment refers to real-time modification of control parameters according to feedback information. The cooperative control strategy includes instruction retransmission mechanism, timeout waiting time and fault switching scheme.

[0089] In the embodiments of the present application, the system continuously receives the instruction execution status returned by each external system, and records the completion status of the instruction when receiving the feedback that the power supply system successfully cuts off the unnecessary load; triggers the instruction retransmission mechanism when detecting that the gallery bridge system does not drop to the position within the predetermined time; starts the backup control scheme when finding that the posture of the motion system is abnormal; comprehensively evaluates the execution effect according to all feedback information, and adjusts the sending time sequence and parameter setting of the subsequent instruction.

[0090] For example, the system receives feedback that the brightness of the lighting subsystem has been increased to 1000 lux, but does not receive feedback that the smoke exhaust system has started successfully, waits for 2000 milliseconds, and then re-sends the smoke exhaust start instruction. After the second sending, the confirmation signal that the smoke exhaust machine has started is received, and it is detected that the air conditioning system has been successfully turned off, the fire alarm system has been shielded, and the backup oxygen supply system is normally supplying oxygen. The system adjusts the retransmission timeout time of the smoke exhaust instruction from 2000 milliseconds to 3000 milliseconds according to these feedbacks.

[0091] The method realizes comprehensive data collection through a multi-dimensional environment perception network, quickly identifies the type of abnormality through real-time fusion and intelligent analysis, generates precise control instructions using a logic control algorithm, ensures efficient execution of the instructions with the help of a cross-system joint control mechanism, and dynamically optimizes the control strategy through feedback signals. Ultimately, a complete closed-loop intelligent joint control system is built, the timeliness and multi-system collaboration efficiency of environmental abnormality processing are improved, and the reliability and adaptability of the overall system are enhanced.

[0092] In order to solve the real-time adaptability problem of the environmental joint control system and the external system in collaborative control, in some embodiments, step 105: the feedback signal sent by the corresponding external system is received, and the collaborative control strategy between the environmental joint control system and each external system is dynamically adjusted according to the feedback signal, including:

[0093] Step 201: receiving power supply state feedback signals from the power supply system, position state feedback signals from the gallery bridge system, posture state feedback signals from the motion system, and alarm state feedback signals from the fire alarm system.

[0094] The power supply state feedback signal refers to the confirmation information returned by the power supply system about the power supply condition, including voltage stability and load on-off state. The position state feedback signal refers to the real-time position information of the lifting mechanism returned by the gallery bridge system. The attitude state feedback signal refers to the platform spatial coordinates and angle data returned by the motion system. The alarm state feedback signal refers to the sensor working state and alarm triggering condition returned by the fire alarm system. Because the IOS instructor station has been listed as an external system receiving instructions, but in the feedback link, the IOS instructor station mainly acts as an instruction transfer or monitoring interface, the feedback signal thereof does not include the device-level execution state data, and the feedback of the power supply system, the gallery bridge system, the motion system and the fire alarm system directly reflects the actual execution state of the physical device, which is a key data source for dynamic adjustment of the cooperative control strategy.

[0095] In the embodiment of the present application, the environment joint control system continuously monitors the data packets sent by each external system through the communication interface, extracts the power supply state of the power supply system, the lifting height value of the gallery bridge system, the three-dimensional coordinates and inclination angle of the motion system, the sensor detection value and alarm state of the fire alarm system after analyzing the data packet format, and converts these data into a unified processing format inside the system.

[0096] Step 202: Analyze the state parameters in each feedback signal to obtain the load connection state of the power supply system, the lifting height data of the gallery bridge system, the displacement data of the motion system and the sensor state of the fire alarm system.

[0097] In step 202, the load connection state refers to the power-on and power-off condition of each electrical device in the power supply system. The lifting height data refers to the vertical distance of the gallery bridge platform relative to the reference position. The displacement data refers to the movement amount of the motion platform in the horizontal direction and the vertical direction. The sensor state refers to the normal working or fault state of the smoke detector and temperature detector in the fire alarm system.

[0098] In the embodiment of the present application, the system separates the received formatted data into parameters, analyzes the on-off state of the key load from the power supply system data, calculates the difference between the current height and the reference position from the gallery bridge system data, extracts the displacement amount of the platform in the X axis, Y axis and Z axis from the motion system data, and judges whether the sensor is in a normal monitoring state from the fire alarm system data.

[0099] Step 203: Based on the load connection state, the lifting height data, the displacement data and the sensor state, respectively, compare with the preset power-off expected state, the gallery descent expected position, the motion system return expected attitude and the fire alarm system shielding expected state one by one.

[0100] In step 203, the power-off expected state refers to the ideal situation in which non-critical loads should be in a power-off state. The gallery bridge descending expected position refers to the safe parking height that the gallery bridge platform should reach. The motion system return expected posture refers to the initial coordinates and horizontal state to which the motion platform should return. The fire alarm system shielding expected state refers to the manual shielding mode in which the alarm system should be in.

[0101] In the embodiments of the present application, the system compares the parsed load connection state with the expected power-off device list, checks the number of devices that have not been powered off, compares the actual height of the gallery bridge with the expected safe height, calculates the height deviation value, analyzes the difference between the current position of the motion platform and the initial coordinates to obtain the position offset, and matches the state of the fire alarm sensor with the expected shielding state to confirm whether the alarm function is closed as required.

[0102] Step 204: According to the comparison result, dynamically adjust the cooperative control strategy between the environmental joint control system and each external system.

[0103] In step 204, dynamic adjustment refers to the process of modifying control parameters according to real-time comparison results.

[0104] In the embodiments of the present application, the system reissues the number of instructions found in the comparison results according to the increase in the number of devices that have not been powered off, adjusts the sending frequency of the descending instructions according to the gallery bridge height deviation value, starts a backup calibration program according to the position offset of the motion platform, triggers a manual intervention request according to the abnormal state of the fire alarm sensor, and updates the cooperative control parameter table of all external systems.

[0105] The following is a specific example:

[0106] In the No. 1 simulation cabin of the flight simulation training center A, after the system completes the instruction issuing, the environment joint control system starts to receive the external system feedback signals. The power supply system returns the power supply state feedback signal showing that the No. 3 and No. 5 non-critical equipment cabinets are still in the power-on state. The position state feedback signal returned by the corridor bridge system indicates that the current height is 1.2 meters. The attitude state feedback signal returned by the motion system contains the current position coordinates [1050, 980, 200] millimeters of the platform (the initial reference coordinates are [1000, 1000, 200] millimeters). The alarm state feedback signal returned by the fire alarm system confirms that the smoke alarm has been shielded, but the temperature sensor reports an abnormal code E02. After the system analyzes these feedback signals, it obtains the load connection state of the power supply system as the No. 3 and No. 5 equipment cabinets are not disconnected, the lifting height data of the corridor bridge system as 1.2 meters, the displacement data of the motion system as 50 millimeters in the positive direction of the X axis, 20 millimeters in the negative direction of the Y axis, and no offset in the Z axis, and the sensor state of the fire alarm system as the temperature sensor failure. The system compares the load connection state with the power-off expected state (requiring all non-critical equipment to be powered off) and finds that 2 devices are not up to standard. The comparison of the lifting height data 1.2 meters with the expected position 1.0 meters of the corridor bridge descending obtains a height difference of 0.2 meters. The comparison of the displacement data [50, -20, 0] millimeters with the expected attitude [0, 0, 0] millimeters of the motion system returning obtains a total offset of 53.85 millimeters (calculated by the formula , wherein represents the total offset of the motion system, represents the displacement deviation in the direction of the X axis, , represents the displacement deviation in the direction of the Y axis, represents the displacement deviation in the direction of the Z axis, , represents the displacement deviation in the direction of the X axis, represents the displacement deviation in the direction of the Y axis, represents the displacement deviation in the direction of the Z axis, ), and the comparison of the sensor state with the shielding expected state of the fire alarm system (requiring all sensors to be normal) finds that the temperature sensor is abnormal. According to the comparison results, the system dynamically adjusts the cooperative control strategy: for the power supply system not being disconnected, the number of instruction reissuing is increased from 3 times to 5 times; for the corridor bridge height deviation, the frequency of height control instruction sending is increased from 2 times per second to 3 times per second; for the motion platform offset, the platform automatic calibration program is triggered (the calibration force F is calculated by the formula , wherein F represents the calibration force of the motion platform, k is the elastic coefficient and is taken as 0.5 N / mm, and the calculation obtains ); for the fire sensor failure, send a priority repair request to the IOS instructor station. After adjustment, the power supply system successfully cuts off the power supply of device cabinets 3 and 5 by reissuing instructions, the corridor bridge drops to 1.0 meters within 10 seconds after frequency adjustment, the motion platform returns to the initial position [1000, 1000, 200] millimeters within 20 seconds under the action of the calibration program, and the fire sensor returns to normal after being repaired by the technician.

[0107] In the embodiments of the present application, through real-time feedback signal analysis and multi-dimensional state comparison, the execution effect of the external system is accurately evaluated, and the control strategy is dynamically optimized based on the evaluation result, thereby improving the accuracy of multi-system collaborative execution and the self-adaptation ability of the environmental joint control system.

[0108] In order to solve the dynamic optimization problem of the collaborative control strategy of the environmental joint control system in a complex scene, in some embodiments, step 204: dynamically adjusting the collaborative control strategy between the environmental joint control system and each external system according to the comparison result, comprises:

[0109] Step 301: According to the difference degree in the comparison result, it is identified whether there is an instruction execution deviation or a system response anomaly.

[0110] In step 301, the difference degree is obtained by quantitatively comparing the real-time acquired external system state parameters (such as the load connection state of the power supply system, the lifting height data of the corridor bridge system, etc.) with the pre-set expected execution state of each system (such as the expected state of power cut-off, the expected position of the corridor bridge lowering, etc.) item by item. The meaning reflects the deviation size and nature between the actual execution state and the ideal expected state, and is a direct basis for judging whether the system is running normally or abnormally. The instruction execution deviation refers to that the external system does not completely execute the operation according to the control instruction, but the system itself is normal. The system response anomaly refers to that the external system cannot respond to the instruction due to communication interruption or device failure.

[0111] In the embodiments of the present application, the system calculates the deviation absolute value of each parameter in the comparison result, including the number difference of devices not powered off by the power supply, the corridor bridge height deviation value, the motion platform displacement deviation amount and the number of abnormal fire sensors. When any deviation value exceeds the pre-set threshold value, it is marked as abnormal. Then, according to the type of the anomaly, it is judged whether the instruction execution is incomplete or the system does not respond.

[0112] Step 302: When the identification result is an instruction execution deviation, analyze the duration and deviation value of the instruction execution deviation, and generate corresponding strategy adjustment parameters according to the analysis result.

[0113] In step 302, the duration of the instruction execution deviation refers to the time from when the instruction is issued to when the first abnormal feedback is received. The deviation value refers to the difference in parameter values ​​that do not meet the expected state. The strategy adjustment parameters include the instruction retransmission interval, the upper limit of the number of instruction retransmissions, and the instruction priority weight.

[0114] In this embodiment, the system records the instruction issuance time and the first feedback time, calculates the duration, and extracts the difference between the actual value and the expected value of the deviation parameter as the deviation value. Based on the duration and the magnitude of the deviation value, a linear adjustment algorithm is used to generate a new instruction retransmission interval, increase the upper limit of the number of retransmissions, or increase the priority of the instruction in the transmission queue.

[0115] Step 303: When the identification result is that the system response is abnormal, the communication status and equipment status of the abnormal system are detected by the deep learning fault diagnosis model, and alternative control paths are generated based on the detection results.

[0116] In step 303, the term "abnormal system" refers to an external system identified in the preceding steps as having an abnormal system response. This abnormality arises from comparing the system's feedback state with its expected state, thus determining the system to have an abnormal response. The deep learning fault diagnosis model refers to a neural network model trained on historical data, used to identify communication interruptions and device hardware failures. Communication status refers to network connection quality and data transmission rate. Device status refers to the operational health of hardware components. Alternative control paths include direct control paths, relay control paths, and hierarchical collaborative control paths.

[0117] In this embodiment, the system inputs the historical operating data of the abnormal system into a pre-trained deep learning model. The model outputs the communication interruption probability and the equipment failure probability. When the communication interruption probability is high, a control path via a relay is generated. When the equipment failure probability is high, a direct control path or a hierarchical collaborative control path is generated.

[0118] Step 304: Using the strategy adjustment parameters or the alternative control paths as input parameters, and based on the input parameters, combined with the reinforcement learning decision model, update the collaborative control strategy between the environmental control system and each external system.

[0119] In step 304, the input parameters refer to policy adjustment parameters or alternative control paths. A reinforcement learning decision model refers to an algorithmic model that learns the optimal decision policy through a reward mechanism.

[0120] In this embodiment, the system converts the strategy adjustment parameters or alternative control paths into state vectors and inputs them into the reinforcement learning model. The model outputs an optimized control strategy based on the current environmental state and historical decision-making results, including adjusting the command sending frequency, modifying the anomaly judgment threshold, and updating the inter-system cooperation rules.

[0121] The following is a specific example:

[0122] In the No. 1 simulation cabin of the flight simulation training center A, after the system completes the adjustment of the cooperative control strategy, the environment joint control system performs in-depth analysis according to the difference in the comparison result, wherein the number of non-power-off equipment of the power supply system is 2 for 25 seconds, the corridor bridge height deviation is 0.2 meters for 30 seconds, the total offset of the motion platform is 53.85 millimeters for 15 seconds, and the temperature sensor of the fire alarm system is abnormal for 40 seconds. The system identifies that the power supply and corridor bridge problems belong to instruction execution deviation because the equipment can still respond but not completely execute, and the fire alarm system problem belongs to system response abnormality because the sensor has no data feedback at all. For the instruction execution deviation, the system analyzes the power supply deviation duration of 25 seconds and the deviation value of 2 equipment, and the corridor bridge deviation duration of 30 seconds and the deviation value of 0.2 meters, and generates strategy adjustment parameters including increasing the power supply instruction retransmission times from 5 to 7, shortening the retransmission interval from 3 seconds to 2 seconds, and increasing the corridor bridge instruction sending frequency from 3 times per second to 4 times per second. For the system response abnormality, the historical data of the fire alarm system is analyzed through the deep learning fault diagnosis model, the model outputs the communication state normal probability of 0.2 and the equipment state fault probability of 0.8, and the alternative control path is to enable the standby temperature sensor and bypass the faulty equipment. The strategy adjustment parameters and the alternative control path are input into the reinforcement learning decision model as input parameters, the model outputs the updated cooperative control strategy based on the current system state and the historical decision effect, including the power supply instruction using the highest priority transmission, the corridor bridge instruction using the redundant channel transmission, and the fire alarm system switching to the standby sensor monitoring. After executing the new strategy, the power supply system successfully cuts off the power supply of all non-critical equipment within 10 seconds, the corridor bridge drops to the expected height of 1.0 meters within 8 seconds, the motion platform returns to the initial position within 12 seconds through continuous calibration, and the fire alarm system restores normal monitoring function through the standby sensor. Among them, the power supply instruction retransmission times of 7 times are obtained by adding the reference number of 5 times to the duration of 25 seconds divided by 12.5 seconds, and the corridor bridge instruction frequency of 4 times per second is obtained by adding the deviation amount of 0.2 meters to the reference frequency of 3 times per meter multiplied by 5 times per meter, and the calculation formula is wherein represents the adjusted corridor bridge instruction sending frequency, represents the reference instruction sending frequency, k represents the frequency adjustment coefficient, d represents the corridor bridge height deviation amount, . Substituting the above formula, we get .

[0123] In the embodiments of the present application, by intelligently identifying the abnormal type and generating optimization parameters, the dynamic update of the control strategy is realized by combining the reinforcement learning model, the adaptability of the system to external abnormal conditions and the cooperative control efficiency are improved, and the stable operation of the joint control system in complex environments is ensured.

[0124] To improve the accuracy of system fault diagnosis and the intelligent level of control path generation, in some embodiments, step 303: the communication state and device state of the abnormal system are detected by the deep learning fault diagnosis model, and a candidate control path is generated according to the detection result, comprising:

[0125] Step 401: Obtain the historical running data and real-time monitoring data of the abnormal system.

[0126] In step 401, the historical running data refers to a set of running state information recorded by the abnormal system in the past period of time, including communication connection records and device performance logs. The real-time monitoring data refers to the current collected system running state information, including communication message content and device real-time parameters.

[0127] In the embodiments of the present application, the system extracts the running records of the abnormal system in the last thirty days from the database, including the number of daily communication connection successes, data transmission delay values, device running temperature curves and power consumption data, and simultaneously collects the communication message transmission state, device working temperature, voltage value and current value at the current time, forming a complete data input set.

[0128] Step 402: input the historical running data and the real-time monitoring data as input data into the deep learning fault diagnosis model, and the deep learning fault diagnosis model includes a communication state analysis branch and a device state analysis branch.

[0129] In step 402, the deep learning fault diagnosis model refers to a double-branch analysis model constructed by a neural network. The communication state analysis branch is specially designed to process communication-related data features. The device state analysis branch is specially designed to process device running-related data features.

[0130] In the embodiments of the present application, after aligning the historical running data and real-time monitoring data according to the time sequence, the system inputs them into the communication state analysis branch and the device state analysis branch of the model respectively. The communication branch receives the communication connection times and transmission delay data, and the device branch receives the temperature curve and power consumption data.

[0131] Step 403: feature extraction is performed on the communication message sequence in the input data by the communication state analysis branch to obtain communication link feature parameters, and based on the communication link feature parameters, an abnormal communication state is identified.

[0132] In step 403, the communication message sequence refers to a set of data packets captured from the network interface of the abnormal system or recorded by the communication module in chronological order, which means that the communication process between systems is recorded, and time series data for analyzing the communication state is recorded. The communication link characteristic parameters include the message transmission success rate, the average transmission delay, and the connection stability index. The abnormal communication state refers to communication interruption, data packet loss, or excessively high delay.

[0133] In the embodiment of the present application, the communication state analysis branch extracts features from the input communication message sequence, calculates the transmission success rate of the last 100 messages, counts the average transmission delay time, and analyzes the number of connection interruptions. When the transmission success rate is lower than the threshold or the delay time exceeds the limit, it is identified that there is an abnormal communication state.

[0134] Step 404: Through the device state analysis branch, the device operation log in the input data is extracted to obtain the device operation characteristic parameters, and based on the device operation characteristic parameters, the abnormal device state is identified.

[0135] In step 404, the device operation log refers to a historical data file obtained from the controller or monitoring module of the abnormal system, which records the internal operation state and events of the device, and its meaning is a record set reflecting the device hardware working state, operation parameters, and abnormal events. The abnormal device state refers to device overheating, abnormal power consumption, or hardware failure.

[0136] In the embodiment of the present application, the device state analysis branch extracts features from the input device operation log, calculates the hourly change amplitude of the device temperature, analyzes the power consumption fluctuation range, and counts the continuous operation time. When the temperature change is too fast, the power consumption fluctuation is too large, or the operation time exceeds the limit, it is identified that there is an abnormal device state.

[0137] Step 405: According to the combination type of the abnormal communication state and the abnormal device state, a corresponding alternative control path is selected from a preset alternative control path set.

[0138] In step 405, the combination type refers to different abnormal mode combinations formed when the communication state abnormality (such as packet loss, delay) and the device state abnormality (such as failure, performance degradation) occur at the same time, which is obtained by correlating and matching the detection results of the two types of abnormalities after performing communication state analysis and device state analysis in parallel. The alternative control path set includes a direct control path, a transfer control path, a backup device switching path, and a hierarchical control path.

[0139] In the embodiments of the present application, the system selects a corresponding scheme from a set of predefined paths according to the combination of the identified abnormal communication state and abnormal device state, selects a transit control path when only the communication is abnormal, selects a backup device switching path when only the device is abnormal, and selects a hierarchical control path when both are abnormal. Wherein, when the communication state is identified as abnormal, the selected alternative control path includes a communication rerouting path or an IOS instructor station transit control path; when the device state is identified as abnormal, the selected alternative control path includes a backup device enabling path or a hierarchical cooperative control path of each subsystem; when both the communication state and the device state are identified as abnormal, a combination control scheme of the direct device control path and the hierarchical cooperative control path of each subsystem is selected.

[0140] The following is a specific example:

[0141] In the No. 1 simulator cabin of the flight simulation training center A, for the system response abnormality condition that the temperature sensor of the fire alarm system is abnormal for 40 seconds and has no data feedback at all, the environmental joint control system executes the deep learning fault diagnosis process. First, the historical operation data of the fire alarm system in the last 30 days is obtained, including 200 daily communication connection records, of which 196 are successful, the device operating temperature record is kept in the range of 40 to 50 degrees Celsius, and the power consumption data is stable in the range of 100 to 120 watts. At the same time, real-time monitoring data is collected, including the current communication message transmission success rate of 70%, the average transmission delay of 200 milliseconds, the device temperature of 65 degrees Celsius, and the power consumption fluctuation range of 80 to 150 watts. The historical operation data and real-time monitoring data are input into the deep learning fault diagnosis model, which includes a communication state analysis branch that extracts features from the communication message sequence in the input data. The communication link feature parameters calculated include a transmission success rate of 70%, an average delay of 200 milliseconds, and a connection interruption number of 5. Based on these parameters, it is identified that the abnormal communication state is because the transmission success rate is lower than the threshold of 85% and the delay exceeds the limit of 100 milliseconds. The device state analysis branch extracts features from the device operation log in the input data, and calculates the device operation feature parameters including temperature change rate of 15 degrees Celsius per hour, power consumption fluctuation range of 70 watts, and continuous running time of 1000 hours. Based on these parameters, it is identified that the abnormal device state is because the temperature change rate exceeds the limit of 10 degrees Celsius per hour and the power consumption fluctuation exceeds the limit of 50 watts. According to the combination type of the abnormal communication state and the abnormal device state, the system selects the corresponding hierarchical control path from the set of pre-set alternative control paths, which includes enabling a backup communication channel, switching to a backup temperature sensor, and reducing the data acquisition frequency to 1 per second. Wherein the temperature change rate is calculated by the formula wherein r represents the device temperature change rate, represents the temperature change value of 15 degrees Celsius, represents the time interval of 1 hour, and The power fluctuation range is 70 watts, calculated as the difference between the maximum value of 150 watts and the minimum value of 80 watts. After executing the alternative control path, the fire alarm system communication success rate is restored to 90%, the device temperature is reduced to 55 degrees Celsius, and the system resumes normal monitoring functions.

[0142] In the embodiments of the present application, the communication and device state are accurately diagnosed through a deep learning model, and the control path is intelligently selected according to the abnormal combination type, thereby improving the accuracy and efficiency of system fault handling and ensuring the reliability and adaptability of the control strategy under abnormal conditions.

[0143] To further improve the intelligent level of the collaborative control strategy, in some embodiments, step 304: updating the collaborative control strategy between the environmental joint control system and each external system based on the input parameters and combining a reinforcement learning decision model, comprises:

[0144] Step 501: mapping the input parameters into a spatial vector of the reinforcement learning decision model.

[0145] In step 501, the spatial vector refers to converting the input parameters into a mathematical vector form that the reinforcement learning model can process, including the number of instruction retransmissions dimension, the instruction interval time dimension, the control path type dimension, and the priority weight dimension.

[0146] In the embodiments of the present application, the system converts numerical parameters such as the number of instruction retransmissions and the instruction interval time in the strategy adjustment parameters, as well as category parameters such as the type code of the alternative control path, into values of a unified dimension through standardization processing, and combines them into a multi-dimensional vector according to a pre-set dimension order.

[0147] Step 502: evaluating the spatial vector to obtain corresponding system response time scores, resource utilization efficiency scores, and fault recovery success rate scores.

[0148] In step 502, the system response time score refers to the efficiency score of the time required for the instruction to be issued and executed. The resource utilization efficiency score refers to the utilization rate score of the computing resources and communication resources in the system during execution. The fault recovery success rate score refers to the probability score of the system recovering from a fault state to a normal state.

[0149] In the embodiments of the present application, the reinforcement learning model uses a pre-defined scoring function to evaluate the input spatial vector. The scoring function considers the actual response time, resource occupation size, and fault recovery situation corresponding to similar vectors in historical execution data to calculate the expected performance scores of the current vector in the three dimensions.

[0150] Step 503: Based on the system response time score, the resource utilization efficiency score, and the fault recovery success rate score, output an optimal control strategy through the decision network of the reinforcement learning decision model.

[0151] In step 503, the decision network refers to the neural network structure in the reinforcement learning model responsible for outputting the decision strategy. The optimal control strategy refers to the control scheme that can achieve the highest comprehensive score under the current system state.

[0152] In the embodiments of the present application, the reinforcement learning decision model inputs three scores into the decision network. The network analyzes the importance weight of different score dimensions through multi-layer calculation, and outputs a control strategy with the highest comprehensive score after comprehensive evaluation. The strategy includes specific instruction sending rules, system cooperation schemes, and fault handling processes.

[0153] Step 504: Convert the optimal control strategy into update instructions, and update the collaborative control strategy between the environmental joint control system and each external system according to the update instructions.

[0154] In step 504, the update instruction refers to the conversion of the optimal control strategy into system executable operation commands.

[0155] In the embodiments of the present application, the system parses the optimal control strategy into specific configuration parameters and operation instructions, including modification instructions, retransmission frequency upper limit adjustment instructions, sending interval update instructions, control path selection rules, etc., and deploys these update contents to the control module of the environmental joint control system.

[0156] The following is a specific example:

[0157] In the 1st simulation cabin of flight simulation training center A, the environmental joint control system adjusts the strategy parameters including power instruction retransmission frequency 7 times, retransmission interval 2 seconds, corridor bridge instruction frequency 4 times per second, and alternative control path enabling a backup temperature sensor and bypassing the faulty device as input parameters. First, these parameters are mapped into a spatial vector of the reinforcement learning decision model, where the power retransmission frequency of 7 times is mapped into the first dimension value 7 of the vector, the retransmission interval of 2 seconds is mapped into the second dimension value 0.5 because the inverse relationship is adopted 1 / 2=0.5, the corridor bridge frequency of 4 times per second is mapped into the third dimension value 4, and the alternative control path type is mapped into the fourth dimension value 3 representing hierarchical control, forming the spatial vector [7, 0.5, 4, 3]. The spatial vector is evaluated, and based on the performance of similar vectors in historical execution data, the system response time score is 82 points, the resource utilization efficiency score is 75 points, and the fault recovery success rate score is 90 points. Based on these three scores, the decision network of the reinforcement learning decision model calculates the comprehensive score by using the weighted sum formula where S represents the comprehensive score of the reinforcement learning decision model, the response time weight is 0.4, a system response time score, 0.2 for resource efficiency weight, a resource utilization efficiency score, 0.4 for fault recovery weight, a fault recovery success rate score. , , , substituting , the decision network outputs the optimal control strategy as the power instruction adopts the highest priority and the retransmission frequency remains 7 times, the gallery bridge instruction adopts the redundant channel and the frequency is raised to 5 times per second, and the fire alarm system is completely switched to the backup sensor and sets up a data verification mechanism. After converting the optimal control strategy into an update instruction, the system updates the cooperative control strategy, sets the power instruction priority to the highest, increases the redundant transmission channel for the gallery bridge instruction and raises the sending frequency from 4 times per second to 5 times per second, disables the faulty sensor and enables the backup sensor for the fire alarm system, and increases the data verification frequency to 2 times per second. After the update is executed, the power system completes power-off of all non-critical equipment within 7 seconds, the gallery bridge accurately drops to 1.0 meters in height within 5 seconds, and the fire alarm system resumes normal monitoring through the backup sensor within 3 seconds and the data accuracy reaches 99%.

[0158] In the embodiments of the present application, by intelligently mapping the input parameters into a spatial vector and outputting the optimal strategy based on multi-dimensional scores, dynamic optimization and accurate updating of the cooperative control strategy are realized, the system response speed and resource utilization efficiency are improved, and the fault recovery capability is enhanced.

[0159] In order to improve the processing efficiency of environmental monitoring data and the accuracy of abnormal identification, in some embodiments, step 102: the real-time fusion and state analysis of the running data and the basic environmental parameters are performed to identify whether there is an abnormal signal, including:

[0160] Step 601: real-time fusion processing of the running data and the basic environmental parameters to obtain unified format analysis data.

[0161] In step 601, real-time fusion processing refers to the process of time alignment and format unification of data from different sources and formats. The unified format analysis data refers to a standardized data set in which all data are converted to the same time granularity and numerical range.

[0162] In the embodiments of the present application, the system receives running data and basic environmental parameters from each subsystem, adds a unified time stamp to these data, converts all numerical values to the same unit of measurement, and samples data at fixed time intervals to form a regular data sequence.

[0163] Step 602: performing state analysis on the data to be analyzed, extracting first feature data corresponding to a safety state, second feature data corresponding to smoke simulation, and third feature data corresponding to a device running state from the state analysis result.

[0164] In step 602, the state analysis refers to analyzing and processing the standardized data to extract feature information. The first feature data refers to feature values related to the safety state, including the access control state change frequency and the emergency button trigger times. The second feature data refers to feature values related to the smoke simulation, including the smoke concentration rising rate and the duration. The third feature data refers to feature values related to the device running state, including the device temperature change rate and the power consumption fluctuation amplitude.

[0165] In the embodiments of the present application, the system performs feature extraction calculation on the data to be analyzed, calculates the frequency of access control state change and the number of times of pressing the emergency button for the safety state, calculates the value of smoke concentration rising per minute and the length of time of maintaining high concentration for the smoke simulation, and calculates the value of device temperature changing per minute and the size range of power consumption fluctuation for the device running state.

[0166] Step 603: determining that there is a safety abnormal signal when the range corresponding to the first feature data is greater than a preset safety range.

[0167] In step 603, the preset safety range refers to the normal change frequency range of the access control state and the normal trigger times range of the emergency button.

[0168] In the embodiments of the present application, the system compares the calculated first feature data with the preset safety range, and determines that there is a safety abnormal signal when the access control state change frequency exceeds the normal range or the number of times of pressing the emergency button abnormally increases.

[0169] Step 604: determining that there is a smoke simulation training trigger signal when the range corresponding to the second feature data is greater than a preset training range.

[0170] In step 604, the preset training range refers to the allowed smoke concentration change range and the duration range during the smoke simulation training.

[0171] In the embodiments of the present application, the system compares the calculated second feature data with the preset training range, and determines that there is a smoke simulation training trigger signal when the smoke concentration rising rate reaches the training requirement and the high concentration duration exceeds the minimum training time.

[0172] Step 605: determining that there is a fault alarm signal when the range corresponding to the third feature data is greater than a preset fault range.

[0173] In step 605, the preset fault range refers to the allowed range of temperature change and the allowed range of power consumption fluctuation when the device is in normal operation.

[0174] In the embodiments of the present application, the system compares the calculated third feature data with the preset fault range. When the device temperature changes too fast to exceed the allowed range or the power consumption fluctuation is too large to exceed the normal threshold, it is determined that there is a fault alarm signal.

[0175] The following is a specific example:

[0176] In the No. 1 simulation cabin of the flight simulation training center A, the system performs real-time fusion processing on the operation data and the basic environment parameters, wherein the operation data includes that the security subsystem reports the access control state as closed, the smoke sensor detects the smoke concentration value as 0.1 mg per cubic meter, the oxygen supply system displays the oxygen concentration as 21%, the lighting system brightness is 300 lux, the air conditioning system is in cooling mode, the basic environment parameters include temperature 25 degrees Celsius, humidity 60%, air pressure 101 kPa, and ventilation volume 0.5 cubic meters per second. After all the data are aligned by millisecond level time stamp and converted into unified format of the data to be analyzed, a data frame containing time sequence is formed. The state analysis is performed on the data to be analyzed, and the first feature data safety state feature value is extracted as the access control state change frequency 0 times, the second feature data smoke simulation feature value is the smoke concentration rising rate, which is calculated by rising from 0.1 mg per cubic meter to 15 mg per cubic meter within 2 seconds to obtain the rate value of 7.45 mg per cubic meter per second, and the calculation formula is wherein v represents the smoke concentration rising rate, 14.9 mg per cubic meter represents the concentration change value, 2 seconds represents the time interval, and the third feature data device operation state feature value is the oxygen supply system output change rate, which is calculated by falling from 20 liters per minute to 5 liters per minute within 1 minute to obtain the change rate of -15 liters per minute. When the first feature data access control state change frequency 0 times is within the preset safety range of 0 to 1 times, it is determined that there is no safety abnormal signal. When the second feature data smoke concentration rising rate 7.45 mg per cubic meter per second is greater than the preset training range 5 mg per cubic meter per second, it is determined that there is a smoke simulation training trigger signal. When the third feature data oxygen supply output change rate -15 liters per minute exceeds the preset fault range of +5 liters per minute, it is determined that there is a fault alarm signal. The system generates the smoke simulation training trigger signal and the oxygen supply subsystem fault alarm signal according to these determination results, thereby providing a basis for subsequent control instruction generation.

[0177] In the embodiments of the present application, through real-time data fusion and multi-dimensional feature analysis, rapid and accurate identification of various types of abnormal signals is realized, the intelligent level of environmental monitoring and the timeliness of abnormal response are improved, and reliable data support is provided for subsequent control decision-making.

[0178] In order to improve the accuracy and efficiency of the control instruction generation in the abnormal response process, in some embodiments, step 103: when any type of abnormal signal is identified, a corresponding linkage control instruction is generated according to the type of the abnormal signal by using a logic control algorithm, including:

[0179] Step 701: based on the type of the abnormal signal, a corresponding linkage control instruction type identifier is determined by using a logic control algorithm.

[0180] In step 701, the type of the abnormal signal refers to three categories of safety abnormal signal, smoke simulation training trigger signal or fault alarm signal. The linkage control instruction type identifier refers to a digital code used to distinguish different control instruction sets, wherein 1 represents a multi-system linkage control instruction set, 2 represents a cooperative response instruction set, and 3 represents a fault isolation instruction set.

[0181] In the embodiments of the present application, the logic control algorithm receives the type of the abnormal signal as input, determines the corresponding instruction type identifier digital code by querying the pre-defined mapping relationship table, and ensures that each type of abnormal signal can be mapped to the correct instruction set category.

[0182] Step 702: according to the linkage control instruction type identifier, a corresponding linkage control instruction is generated, wherein when the linkage control instruction type identifier indicates that a safety abnormal signal is identified, a multi-system linkage control instruction set is generated, the multi-system linkage control instruction set includes a motion system back-to-origin instruction, a corridor bridge lowering instruction, a lighting brightness improving instruction and a power supply cutting off non-essential load instruction.

[0183] In step 702, the multi-system linkage control instruction set refers to an instruction set that requires multiple systems to respond cooperatively to a safety abnormality. The motion system back-to-origin instruction refers to a command to control the motion platform to return to the initial position. The corridor bridge lowering instruction refers to a command to control the boarding bridge to descend to a safe height. The lighting brightness improving instruction refers to a command to increase the lighting system brightness to the highest level. The power supply cutting off non-essential load instruction refers to a command to cut off the power supply of non-essential equipment.

[0184] In the embodiments of the present application, when the instruction type identifier is 1, the system calls the multi-system linkage control instruction template from the instruction template library, fills in the specific device number and parameter value, and generates a complete instruction set including the motion system back-to-origin, the corridor bridge lowering, the lighting brightness improving and the power supply cutting off non-essential load.

[0185] Step 703: When the linkage control instruction type identifier indicates that a smoke simulation training trigger signal is identified, a coordinated response instruction set is generated, and the coordinated response instruction set includes a fire alarm system shielding instruction, an oxygen supply subsystem opening instruction, an air conditioning subsystem closing instruction, a lighting subsystem maximum brightness opening instruction, and an exhaust fan starting instruction.

[0186] In step 703, the coordinated response instruction set refers to a set of instructions that multiple subsystems need to cooperate for smoke simulation training. The fire alarm system shielding instruction refers to a command to temporarily disable the fire alarm function. The oxygen supply subsystem opening instruction refers to a command to start the oxygen supply system. The air conditioning subsystem closing instruction refers to a command to turn off the air conditioning system. The lighting subsystem maximum brightness opening instruction refers to a command to set the lighting brightness to the maximum value. The exhaust fan starting instruction refers to a command to start the exhaust equipment.

[0187] In the embodiments of the present application, when the instruction type identifier is 2, the system calls the coordinated response instruction template from the instruction template library, fills in the specific parameters according to the current environment state, and generates a complete instruction set containing fire alarm shielding, oxygen supply opening, air conditioning closing, lighting maximum brightness opening, and exhaust fan starting.

[0188] Step 704: When the linkage control instruction type identifier indicates that a fault alarm signal is identified, a fault isolation instruction set is generated, and the fault isolation instruction set includes a motion system stay-in-place locking instruction, a gallery bridge lowering holding instruction, and a fault subsystem function disabling instruction.

[0189] In step 704, the fault isolation instruction set refers to a set of instructions that need to be isolated for device failure. The motion system stay-in-place locking instruction refers to a command to prohibit the movement of the motion platform. The gallery bridge lowering holding instruction refers to a command to keep the gallery bridge in the lowered position. The fault subsystem function disabling instruction refers to a command to disable the function of the faulty device.

[0190] In the embodiments of the present application, when the instruction type identifier is 3, the system calls the fault isolation instruction template from the instruction template library, fills in the specific parameters according to the fault device information, and generates a complete instruction set containing motion system stay-in-place locking, gallery bridge lowering holding, and fault subsystem function disabling.

[0191] The following is a specific example:

[0192] In the No. 1 simulation cabin of the flight simulation training center A, after the system identifies the smoke simulation training trigger signal and the oxygen supply subsystem fault alarm signal, based on the type of the abnormal signal, the corresponding linkage control instruction type identifier is determined by using a logic control algorithm, wherein the smoke simulation training trigger signal corresponds to the second type of instruction identifier represented by the number 2, and the oxygen supply subsystem fault alarm signal corresponds to the third type of instruction identifier represented by the number 3. According to the linkage control instruction type identifier, when the identifier is 2, a set of coordinated response instructions is generated, including a fire alarm system shielding instruction, an oxygen supply subsystem opening instruction but automatically modified to an auxiliary oxygen supply instruction due to the detection of an oxygen supply fault, an air conditioning subsystem closing instruction, an illumination subsystem maximum brightness opening instruction set to 1000 lux, and a smoke exhaust machine starting instruction; when the identifier is 3, a set of fault isolation instructions is generated, including a motion system keeping the original position locking instruction, a gallery bridge descending keeping instruction, and an oxygen supply subsystem function disabling instruction. The illumination brightness value of 1000 lux is the maximum brightness value obtained by querying the equipment specification, and the oxygen supply output threshold of 15 liters per minute is calculated according to the human body's safe oxygen requirement, and the calculation formula is , wherein represents the oxygen supply output threshold (minimum oxygen requirement), the maximum number of people in the cabin is 10, the minimum oxygen requirement per person is 1.5 liters per minute, and the substitution gives . The system sends the generated instructions through a gigabit Ethernet, wherein the illumination brightness raising instruction raises the brightness from 300 lux to 1000 lux, with a raising amount of 700 lux; the smoke exhaust machine starting instruction requires immediate starting; the air conditioning closing instruction stops the operation of the refrigeration mode; the fire alarm shielding instruction disables the alarm function; the auxiliary oxygen supply instruction starts the auxiliary system and sets the output to 20 liters per minute; the motion system locking instruction keeps the current position; the gallery bridge descending keeping instruction maintains the descending state; and the oxygen supply disabling instruction closes the fault main oxygen supply system. All instructions are sent within 50 milliseconds, and the system enters the instruction execution monitoring state.

[0193] In the embodiments of the present application, the abnormal signal type is accurately mapped to the corresponding instruction set by the logic control algorithm, and specific executable control instructions are generated, realizing rapid response and precise control in abnormal situations, and improving the efficiency and reliability of multi-system cooperative processing.

[0194] Specific embodiments are:

[0195] By expanding the environmental system coverage dimension, the environmental joint control system integrates the monitoring and control functions of safety, lighting, oxygen supply, smoke, air conditioning and other subsystems, and builds a multi-dimensional environmental perception network. At the same time, the environmental joint control system innovatively develops a cross-system joint control mechanism with power supply, corridor bridge, motion platform, and fire alarm system. When the environmental system captures data anomalies, it can instantly send a linkage signal to the collaborative system after being processed by a logic control algorithm. After the feedback control instructions of each system, the environmental system uniformly dispatches the equipment to execute actions, forming a "perception-computation-communication-control" closed-loop intelligent system, which improves the coordination and emergency response capability of the simulation environment simulation. As shown in Figure 2 .

[0196] The environmental joint control system itself integrates safety, smoke, oxygen supply, lighting, air conditioning and other subsystems, and realizes multi-dimensional monitoring of the environmental system compared with traditional basic environmental parameter monitoring. Through the multi-dimensional collaborative monitoring mechanism, the system can not only capture real-time basic data such as temperature, humidity, and pressure, but also simultaneously warn of safety hazards, regulate oxygen concentration, and intelligently manage lighting and temperature control systems, forming a three-dimensional monitoring network covering environmental safety, comfort, and equipment operating status. Compared with traditional solutions, it realizes the upgrade from single-point data collection to full-scene environmental collaborative control, improving the precision and intelligent level of environmental management. As shown in Figure 3 .

[0197] The environmental joint control system realizes deep collaboration with power supply, corridor bridge, motion, fire alarm and other systems through intelligent integration technology. The system builds a "perception-computation-communication-control" closed-loop control architecture and realizes intelligent linkage response relying on real-time data interaction.

[0198] During operation, the system exhibits multi-level collaborative control capability:

[0199] (1) When the safety signal appears abnormal, the system automatically triggers the linkage control of the motion system, corridor bridge, power supply, lighting and environmental system. The motion system returns to the original position, the corridor bridge automatically descends to the position, the lighting system automatically adjusts the brightness to the highest, and the power supply system immediately cuts off the power supply of unnecessary equipment. As shown in Figure 4 .

[0200] (2) When smoke simulation training is performed, the air conditioning, oxygen supply, lighting, fire alarm and power supply systems will start the collaborative response mechanism. The fire alarm will be immediately cut off, the oxygen supply system will be automatically opened, the air conditioning system will be immediately closed, and the lighting system will be adjusted to the maximum brightness. When the smoke simulation training is completed, the smoke exhaust will be immediately started for smoke exhaust, and the lighting system will return to the controllable brightness state. When the smoke exhaust is completed, the air conditioning and fire alarm systems will be immediately started to resume normal work. When a subsystem fails, the motion system and the corridor bridge system will be immediately controlled. As shown in Figure 5 , Figure 5The hollow air conditioning system corresponds to the air conditioning subsystem in the present application, and the oxygen supply system corresponds to the oxygen supply subsystem in the present application.

[0201] (3) When a subsystem appears a fault signal, the motion system will keep in place, and the starting function fails. The gallery bridge will be lowered or kept in a lowered position, and the lifting function fails, avoiding the expansion of the fault. As shown in Figure 6 .

[0202] The environmental joint control system can achieve the following three core effects through intelligent integration and multi-system cooperation: 1. Improve safety response efficiency: Through the "perception-computation-communication-control" closed-loop architecture and data perception and automatic linkage mechanism, the system can identify abnormalities (such as safety signal abnormalities, smoke alarms, etc.) within milliseconds, realize rapid linkage of each subsystem, and trigger preset emergency strategies. Whether it is a safety signal anomaly, smoke detection or equipment failure, it can quickly trigger the corresponding cooperation mechanism, greatly improving the overall response speed. 2. Optimize resource coordination management: Based on a unified central control platform, the system breaks down the information silos between subsystems, realizes dynamic allocation of cross-system resources (such as air conditioning and oxygen supply cooperation), avoids systemic failure caused by single-point failure, and improves overall operation reliability. 3. Enhance scene adaptability: Modular design and standardized interface support flexible expansion, taking into account independent operation and emergency linkage of subsystems, and can quickly adapt to different scene requirements (such as airport gallery bridges). Modular design can ensure normal operation of each system without interference, and can flexibly respond to continuous optimization of joint control strategies in complex environments, realizing the upgrade from passive response to active prevention.

[0203] Figure 7 The structure diagram of the environmental intelligent joint control system of the full-movement simulator provided in the embodiments of the present application, and the specific implementation part describes:

[0204] The acquisition module 71 is configured to acquire running data and basic environment parameters from a plurality of subsystems in the environmental joint control system through a multi-dimensional environment perception network, wherein the plurality of subsystems include a safety subsystem, a smoke subsystem, an oxygen supply subsystem, an illumination subsystem, and an air conditioning subsystem.

[0205] The fusion module 72 is configured to perform real-time fusion and state analysis on the running data and the basic environment parameters to identify whether there is an abnormal signal, wherein the abnormal signal includes a safety abnormal signal, a smoke simulation training trigger signal, or a fault alarm signal issued by any subsystem.

[0206] The identification module 73 is configured to, when identifying that there is any type of abnormal signal, generate corresponding linkage control instructions according to the type of the abnormal signal by using a logic control algorithm, wherein the linkage control instructions include a multi-system linkage control instruction set, a cooperative response instruction set, or a fault isolation instruction set.

[0207] The issuing module 74 is configured to issue the multi-system linkage control instruction set, the cooperative response instruction set or the fault isolation instruction set to corresponding external systems, including a power system, a gallery bridge system, a motion system, a fire alarm system and an IOS instructor station, through a cross-system linkage control mechanism.

[0208] The receiving module 75 is configured to receive feedback signals sent by the corresponding external systems, and dynamically adjust the cooperative control strategy between the environment linkage control system and each external system according to the feedback signals, so as to realize a closed-loop intelligent linkage control system.

[0209] The full-movement simulator environment intelligent linkage control system of the embodiments of the present application is used to realize the full-movement simulator environment intelligent linkage control method described above, and therefore the specific implementation of the full-movement simulator environment intelligent linkage control system can be seen from the embodiment part of the full-movement simulator environment intelligent linkage control method described above. The specific implementation can be referred to the description of the corresponding embodiment part, and will not be described here.

[0210] The present application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing the computer program to realize the steps of the full-movement simulator environment intelligent linkage control method described above.

[0211] The present application also provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to realize the steps of the full-movement simulator environment intelligent linkage control method described above.

[0212] In an exemplary embodiment, the computer readable storage medium described above can include, but is not limited to, a U disk, a read-only memory, a random access memory, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0213] The embodiments of the present application also provide a computer program product, which comprises a computer program. The computer program is executed by a processor to realize the steps in the full-movement simulator environment intelligent linkage control method embodiments described above.

[0214] The skilled person can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in the above description in general terms. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0215] The above describes in detail the method, system, device and storage medium for intelligent joint control of a full-movement simulator environment provided by the present application. The principles and implementation modes of the present application are described by applying specific examples, and the above description of the examples is only used to help understand the method of the present application and its core idea. It should be pointed out that, for those skilled in the art, without departing from the principles of the present application, the present application can be improved and modified in several ways, and these improvements and modifications also fall within the protection scope of the present application.

Claims

1. An intelligent joint control method for a full-movement simulator environment, characterized in that, The method comprises the following steps: acquiring operation data and basic environment parameters from multiple subsystems in an environmental joint control system through a multi-dimensional environment perception network, the multiple subsystems including a safety subsystem, a smoke subsystem, an oxygen supply subsystem, a lighting subsystem, and an air conditioning subsystem; performing real-time fusion and state analysis on the operation data and the basic environment parameters to identify whether there is an abnormal signal, the abnormal signal including a safety abnormal signal, a smoke simulation training trigger signal, or a fault alarm signal issued by any subsystem; when any type of abnormal signal is identified, generating corresponding joint control instructions according to the type of the abnormal signal using a logic control algorithm, the joint control instructions including a multi-system joint control instruction set, a cooperative response instruction set, or a fault isolation instruction set; downloading the multi-system joint control instruction set, the cooperative response instruction set, or the fault isolation instruction set to corresponding external systems through a cross-system joint control mechanism, the external systems including a power supply system, a corridor bridge system, a motion system, a fire alarm system, and an IOS instructor station; receiving feedback signals sent by the corresponding external systems and dynamically adjusting the cooperative control strategy between the environmental joint control system and each external system according to the feedback signals to realize a closed-loop intelligent joint control system; the receiving feedback signals sent by the corresponding external systems and dynamically adjusting the cooperative control strategy between the environmental joint control system and each external system according to the feedback signals comprises: receiving power supply state feedback signals from the power supply system, position state feedback signals from the corridor bridge system, attitude state feedback signals from the motion system, and alarm state feedback signals from the fire alarm system; analyzing state parameters in each feedback signal to obtain a load connection state of the power supply system, lifting height data of the corridor bridge system, displacement data of the motion system, and sensor states of the fire alarm system; comparing the load connection state, the lifting height data, the displacement data, and the sensor states with preset power cutoff expected states, corridor bridge lowering expected positions, motion system homing expected attitudes, and fire alarm system shielding expected states, respectively; dynamically adjusting the cooperative control strategy between the environmental joint control system and each external system according to the comparison results.

2. The full-movement simulator environment intelligent joint control method according to claim 1, characterized in that, the dynamically adjusting the cooperative control strategy between the environmental joint control system and each external system according to the comparison results comprises: identifying whether there is an instruction execution deviation or a system response abnormality according to the difference degree in the comparison results; when the identification result is an instruction execution deviation, analyzing the duration and the deviation value of the instruction execution deviation and generating corresponding strategy adjustment parameters according to the analysis results; when the identification result is a system response abnormality, detecting the communication state and the device state of the abnormal system through a deep learning fault diagnosis model and generating an alternative control path according to the detection results; using the strategy adjustment parameters or the alternative control path as input parameters, updating the cooperative control strategy between the environmental joint control system and each external system based on the input parameters and in combination with a reinforcement learning decision model.

3. The full-movement simulator environment intelligent joint control method according to claim 2, characterized in that, The communication state and the equipment state of the abnormal system are detected by the deep learning fault diagnosis model, and a candidate control path is generated according to the detection result, comprising: obtain historical operation data and real-time monitoring data of the abnormal system; input the historical operation data and the real-time monitoring data as input data into a deep learning fault diagnosis model, the deep learning fault diagnosis model comprising a communication state analysis branch and an equipment state analysis branch; by the communication state analysis branch, the communication message sequence in the input data is feature extracted to obtain communication link feature parameters, and based on the communication link feature parameters, an abnormal communication state is identified; by the equipment state analysis branch, the equipment operation log in the input data is feature extracted to obtain equipment operation feature parameters, and based on the equipment operation feature parameters, an abnormal equipment state is identified; according to the combination type of the abnormal communication state and the abnormal equipment state, a corresponding candidate control path is selected from a preset candidate control path set.

4. The full-movement simulator environment intelligent joint control method according to claim 2, characterized in that, The input parameters are mapped into a spatial vector of a reinforcement learning decision model, the spatial vector is evaluated to obtain a system response time score, a resource utilization efficiency score and a fault recovery success rate score, and based on the system response time score, the resource utilization efficiency score and the fault recovery success rate score, an optimal control strategy is output through a decision network of the reinforcement learning decision model. The optimal control strategy is converted into an update instruction, and the collaborative control strategy between the environmental joint control system and each external system is updated according to the update instruction. The running data and the basic environment parameters are fused and analyzed in real time to identify whether there is an abnormal signal, comprising: fuse the running data and the basic environment parameters in real time to obtain unified format analysis data; analyze the analysis data, extract first feature data corresponding to the safe state, second feature data corresponding to the smoke simulation and third feature data corresponding to the equipment operation state from the state analysis result; 5. The full-movement simulator environment intelligent joint control method according to claim 1, characterized in that, when the range corresponding to the first feature data is greater than the preset safety range, it is determined that there is a safety abnormal signal; when the range corresponding to the second feature data is greater than the preset training range, it is determined that there is a smoke simulation training trigger signal; when the range corresponding to the third feature data is greater than the preset fault range, it is determined that there is a fault alarm signal. When any type of abnormal signal is identified, a corresponding linkage control instruction is generated according to the type of the abnormal signal by using a logic control algorithm, comprising: based on the type of the abnormal signal, the type of the linkage control instruction is determined by using a logic control algorithm. ​ 6. The full-movement simulator environment intelligent joint control method according to claim 1, characterized in that, ​ ​ According to the linkage control instruction type identification, a corresponding linkage control instruction is generated, wherein when the linkage control instruction type identification indicates that a safety abnormal signal is identified, a multi-system linkage control instruction set is generated, the multi-system linkage control instruction set including a motion system back-to-position instruction, a gallery bridge lowering instruction, a lighting brightness increasing instruction, and a power supply cut-off unnecessary load instruction; When the linkage control instruction type identification indicates that a smoke simulation training trigger signal is identified, a cooperative response instruction set is generated, the cooperative response instruction set including a fire alarm system shielding instruction, an oxygen supply subsystem opening instruction, an air conditioning subsystem closing instruction, a lighting subsystem maximum brightness opening instruction, and an exhaust fan starting instruction; When the linkage control instruction type identification indicates that a fault alarm signal is identified, a fault isolation instruction set is generated, the fault isolation instruction set including a motion system hold-to-position locking instruction, a gallery bridge lowering holding instruction, and a fault subsystem function disabling instruction.

7. An intelligent joint control system for a full-mobility simulator environment, characterized in that, Comprise: An acquisition module configured to acquire running data and basic environment parameters from multiple subsystems in an environmental linkage control system through a multi-dimensional environment perception network, the multiple subsystems including a safety subsystem, a smoke subsystem, an oxygen supply subsystem, a lighting subsystem, and an air conditioning subsystem; A fusion module configured to perform real-time fusion and state analysis on the running data and the basic environment parameters to identify whether an abnormal signal exists, the abnormal signal including a safety abnormal signal, a smoke simulation training trigger signal, or a fault alarm signal from any subsystem; An identification module configured to, when any type of abnormal signal is identified, generate a corresponding linkage control instruction according to the type of the abnormal signal using a logic control algorithm, the linkage control instruction including a multi-system linkage control instruction set, a cooperative response instruction set, or a fault isolation instruction set; A delivery module configured to deliver the multi-system linkage control instruction set, the cooperative response instruction set, or the fault isolation instruction set to corresponding external systems through a cross-system linkage control mechanism, the external systems including a power supply system, a gallery bridge system, a motion system, a fire alarm system, and an IOS instructor station; A receiving module configured to receive feedback signals sent by the corresponding external systems and dynamically adjust a cooperative control strategy between the environmental linkage control system and each external system according to the feedback signals to realize a closed-loop intelligent linkage control system; The receiving module is further configured to: Receive power supply state feedback signals from the power supply system, position state feedback signals from the gallery bridge system, attitude state feedback signals from the motion system, and alarm state feedback signals from the fire alarm system; Analyze state parameters in each feedback signal to obtain a load connection state of the power supply system, lifting height data of the gallery bridge system, displacement data of the motion system, and sensor states of the fire alarm system; Based on the load connection state, the lifting height data, the displacement data and the sensor state, respectively, compare with preset power cut expected state, gallery bridge descending expected position, motion system back to position expected posture and fire alarm system shielding expected state one by one; According to the comparison result, dynamically adjust the cooperative control strategy between the environment joint control system and each external system.

8. An electronic device, comprising: Comprise: Memory for storing computer programs; Processor for executing the computer program to realize the steps of the full-movement simulator environment intelligent joint control method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the full-movement simulator environment intelligent joint control method of any one of claims 1 to 6.

Images