A training and evaluation system for a space launch site

Abstract

The present invention relates to the technical field of electronic digital data processing, and in particular to a training and evaluation system for a space launch site. The system comprises an instructor platform, an integrated platform for simulation training devices, and a video monitoring platform. The instructor platform includes an integrated training scenario setting module, an instruction module, and an evaluation module. In this solution, task parameters and process logic are customized through the instructor platform, the simulation training device provides highly simulated equipment operation feedback, and the video monitoring platform collects behavioral data without blind spots, forming an integrated "training-execution-evaluation" management and control system. Based on a time node partitioning algorithm, an equipment state vector model, and a weighted average evaluation algorithm, the system quantitatively analyzes trainees' operational accuracy (such as mean square error compared to equipment status), timeliness (task node completion time deviation), and collaboration ability (task allocation matrix tracking role performance), thereby addressing the subjectivity and lag issues of traditional evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a training and evaluation system for a space launch site. Background Art

[0002] The space launch site training system is an important tool for simulating space launch processes and improving operator skills. Its core is to create training scenarios close to actual combat and achieve accurate evaluation of training results.

[0003] Traditional training systems lack dynamic simulation of the real-world launch site environment (such as weather conditions and initial equipment status). Task processes are rigid and unable to flexibly reproduce diverse launch scenarios (such as satellite launches and manned space launches), resulting in insufficient trainees' adaptability to complex working conditions. The evaluation system is highly subjective and lacks quantitative evidence: it relies on manual observation of trainee operations, making it difficult to capture subtle movement deviations in real time (such as valve opening errors and instrument adjustment delays). The evaluation indicators are single (focusing only on operational results), making it impossible to comprehensively analyze operational timeliness, collaboration, and other dimensions. This results in delayed feedback on training effects and makes it difficult to improve trainees' skills in a targeted manner. The system also lacks a multi-source data fusion mechanism, with equipment status data and trainee behavior data collected independently, failing to form a closed-loop analysis link. Furthermore, it is impossible to trace the entire training process, restricting the refined management of training quality.

[0004] Therefore, the present invention proposes a training and evaluation system for a space launch site, which achieves breakthroughs through the following innovations: based on the actual launch process, it integrates five major links: training scenario construction, command distribution, simulation operation, real-time monitoring, and intelligent evaluation. The instructor platform customizes task parameters and process logic, the simulation training device provides highly simulated equipment operation feedback, and the video monitoring platform collects behavioral data without blind spots, forming an integrated "training-execution-evaluation" management and control. Based on the time node division algorithm, the equipment state vector model and the weighted average evaluation algorithm, it quantitatively analyzes the trainees' operation accuracy (such as mean square error compared with equipment status), timeliness (task node completion time deviation) and collaboration ability (task allocation matrix tracks role performance), solving the subjectivity and lag problems of traditional evaluation and providing data support for the precise optimization of training plans. Summary of the Invention

[0005] Technical problems to be solved: Relying on manual observation of trainees' operations makes it difficult to capture subtle movement deviations in real time. The evaluation indicators are single and cannot comprehensively analyze dimensions such as operation timeliness and collaboration, resulting in delayed feedback on training effects.

[0006] In view of the deficiencies of the existing technology, the present invention provides a training and evaluation system for a space launch site, thereby solving the technical problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] A training and evaluation system for a space launch site, comprising an instructor platform, a simulation training device integration platform, and a video monitoring platform;

[0009] The instructor platform includes an integrated training scenario setting module, an instruction module, and an evaluation module;

[0010] The evaluation module includes an instruction parsing unit, and time parsing includes the total time required to complete the instruction. Divided into task nodes Time nodes ; Personnel analysis includes the participation of students People, respectively , establish a student task allocation matrix ,in Indicates students At the time node The roles undertaken, including 、 ; Equipment status analysis determines the real-time status of the simulation training device at each time node, and the equipment status parameter set is , each time node The corresponding device state vector is ,in Indicates the device parameters at the time node The state value to be achieved, where ;

[0011] The evaluation module includes a student target matching unit, which uses a template matching algorithm to calculate the similarity between each student's standing position image and a pre-stored student standing position template. The student corresponding to the template with the highest similarity is the student identity of the standing position;

[0012] The evaluation module includes an equipment status matching unit, which collects real-time equipment status data through the equipment data processing module of the simulation training device integrated platform; compares the collected real-time status data with the status data that the equipment should reach at the time node determined by the instruction parsing unit to determine whether the equipment status meets the requirements;

[0013] The evaluation module includes a training comprehensive evaluation unit, which uses a weighted average algorithm to perform comprehensive calculations on various evaluation indicators to obtain a training comprehensive evaluation score; the evaluation indicator set is , the corresponding weight set is (in ), the score of each indicator is , the comprehensive evaluation score ;

[0014] The simulation training device integrated platform includes an instruction analysis module and an equipment data processing module;

[0015] The video monitoring platform includes a monitoring data processing module.

[0016] In a possible implementation, the integrated training scenario setting module includes a scenario parameter configuration unit and a task process design unit;

[0017] The scenario parameter configuration unit allows the instructor to set diversified training scenario parameters, including launch mission type parameters, launch site environment parameters, and interference item parameters;

[0018] The task process design unit provides a visual graphical editing tool, specifically including task node customization, logical relationship configuration, and process reuse management;

[0019] The instruction module is used to issue specific training instructions, including:

[0020] Instruction type: covers equipment operation instructions, task control instructions, and student management instructions;

[0021] Release method: supports manual immediate release and automatic planned release;

[0022] Command verification: Automatically verify the command format and permission level before sending to ensure the legitimacy of the command.

[0023] In a possible implementation, the instruction analysis module includes an instruction receiving and parsing unit and an instruction execution scheduling unit;

[0024] The instruction receiving and parsing unit:

[0025] Receive encrypted instructions transmitted by the instructor platform via TCP / IP protocol in real time, and support concurrent processing of ≥100 instructions per second;

[0026] Decrypt, grammatically check, and semantically analyze the instructions, extract key information about the target device, operation type, and parameter threshold, and convert them into control signals that can be recognized by the simulation training device;

[0027] The instruction execution scheduling unit:

[0028] Based on the priority queue and time window algorithm, device resources are dynamically allocated to avoid conflicts among multiple instructions;

[0029] Supports concurrent execution of ≥5 independent instructions and optimizes the execution order through task scheduling algorithm.

[0030] In a possible implementation, the device data processing module includes a device state resetting unit, a device state data acquisition unit, and a data feedback unit;

[0031] The device status resetting unit:

[0032] Upon receiving a "reset" command or before training begins, the motor / cylinder is driven to reset the valve, initialize instrument parameters, and clear the console operation records to ensure the consistency of the equipment status;

[0033] Supports batch resetting of device parameters according to preset templates, taking ≤ 10 seconds;

[0034] The device status data acquisition unit:

[0035] Adopt multi-channel synchronous acquisition technology to obtain valve opening, instrument readings, and console operation log data in real time;

[0036] Integrated pressure sensor and displacement sensor, convert analog signals into digital signals through signal conditioning circuit, and transmit them to the processing module via USB / Ethernet interface;

[0037] The data feedback unit:

[0038] Encapsulate device status data in OPC protocol format and provide real-time feedback to the instructor platform evaluation module and video monitoring platform;

[0039] Supports data compression and encrypted transmission to reduce network bandwidth usage and ensure data security.

[0040] In a possible implementation, the monitoring data processing module includes a data acquisition unit, a data storage unit, and a data transmission unit;

[0041] The data acquisition unit:

[0042] Receive H.265 encoded video streams transmitted by multiple cameras in real time, and achieve real-time decoding of ≥30 frames per second through hardware decoding chips;

[0043] Adopting IEEE1588 precise time protocol, it ensures the synchronization error of multi-camera video data is ≤1 millisecond, and supports frame-level synchronization through synchronous trigger signals;

[0044] The data storage unit:

[0045] Adopting a distributed storage architecture, it supports real-time writing of training video data and retrieval of historical data;

[0046] Automatically split video clips by time nodes and generate indexes. The default storage period is 30 days, and you can customize the storage period.

[0047] The data transmission unit:

[0048] Push real-time video streams to the instructor platform via the RTMP protocol, with a delay of ≤500 milliseconds, supporting simultaneous online viewing by multiple users;

[0049] Provides screen splitting function, supports 1 / 4 / 9 / 16 screen modes, and can customize camera group display.

[0050] Beneficial effects compared with existing technologies:

[0051] 1. In this solution, integrated and precise management and control of training and evaluation is achieved through the design of a full-process closed-loop system. The system is based on the real operating procedures of the space launch site, and constructs a closed loop of "training scene construction-instruction distribution-simulated operation-real-time monitoring-intelligent evaluation". The instructor platform can customize the task process, environmental parameters and instruction plans. The simulation training device restores the operation scene through high-simulation equipment (such as replica consoles and high-precision instruments), and the video monitoring platform collects student behavior data without blind spots. The synergy of the three makes the training process highly close to actual combat. At the same time, through the instruction parsing algorithm (such as time node division, equipment state vector comparison) and the intelligent evaluation model (weighted average algorithm), a quantitative evaluation of the student's operation accuracy, timeliness and collaboration ability is achieved, avoiding the blindness of "focusing on operation and neglecting evaluation" in traditional training;

[0052] 2. This solution uses high-definition cameras and multiple sensors (such as pressure and displacement sensors) on a video surveillance platform to collect real-time data on trainee operational behavior and equipment status. This approach, combined with a trainee target matching algorithm (template matching + Kalman tracking) and an equipment status matching algorithm (mean square error (MSE)), accurately analyzes trainee action standardization and equipment operation deviations. For example, the trainee task assignment matrix tracks role performance, and a comprehensive training evaluation unit constructs a multi-level indicator system (such as operational accuracy, time deviation, and collaborative ability) to ultimately generate a quantitative evaluation report. This mechanism overcomes the subjectivity and lag inherent in traditional manual evaluations, providing data support for targeted optimization of training programs and significantly improving the training quality and emergency response capabilities of space launch site personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention with reference to the accompanying drawings.

[0054] Figure 1 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0055] Preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention can be implemented in various forms, so the present invention is not limited to the embodiments described below.

[0056] The technical solution in the embodiments of the present application is to solve the problems of the above-mentioned background technology, and the overall idea is as follows:

[0057] Example:

[0058] Please refer to Figure 1 As shown, this embodiment introduces a training and evaluation system for a space launch site. This system is based on the actual operation process of a space launch site and builds a full-process closed-loop system that integrates training scene construction - instruction distribution - simulated operation - real-time monitoring - intelligent evaluation. The core consists of three platforms: the instructor platform, which serves as the system control center and is responsible for training scene definition, instruction generation, process monitoring and result evaluation; the simulation training device integration platform, which is used to provide high-simulation operation equipment to achieve simulation of physical phenomena in the launch process and equipment status feedback; the video monitoring platform, which provides trainee operation behavior data for training evaluation through all-angle video acquisition;

[0059] The details are as follows:

[0060] 1. Teacher Platform

[0061] 1.1、Lower computer

[0062] High-performance industrial control computers are used, equipped with redundant power supplies, high-speed data interfaces (such as USB3.0, PCI-E) and reliable network connection devices to ensure system stability and real-time performance; they are equipped with a variety of I / O interfaces for connecting external devices (such as monitors, keyboards, mice, printers, etc.) and for data communication with other platforms;

[0063] 1.2 Host computer

[0064] 1.2.1 Training scene setting module

[0065] (1) Scenario parameter configuration unit: allows the instructor to set various training scenario parameters, including launch mission type (such as satellite launch, manned space launch, etc.), launch site environmental conditions (such as weather conditions, temperature, humidity, wind speed, etc.), and initial equipment status values ​​(such as console parameters, instrument initial readings, valve switch status, etc.);

[0066] (2) Mission process design unit: provides a visual mission process editing tool. Instructors can customize the various links and sequences of training missions according to the actual launch process, set mission nodes, mission execution time limits, and logical relationships between tasks; supports the import, export, and reuse of mission processes, making it convenient for instructors to quickly create different types of training scenarios;

[0067] 1.2.2, Instruction Module

[0068] Instruction types: including equipment operation instructions (such as opening valves, adjusting instrument parameters, starting console programs, etc.), task process control instructions (such as pausing training, continuing training, resetting training scenarios, etc.), and student management instructions (such as assigning student roles, viewing student information, etc.);

[0069] Command issuance methods: Both manual and automatic command issuance are supported. When issuing commands manually, the instructor directly selects the command type and target device or student through the operation interface and clicks the "Issue" button to issue the command. When issuing commands automatically, the instructor can pre-configure the order and time of command issuance based on the task flow and time nodes set in the training scenario. The system will automatically issue the commands according to the preset plan.

[0070] Instruction format specification: defines a unified instruction format, including fields such as instruction identifier, target address, instruction content, and instruction execution time, to ensure the accuracy and reliability of instructions; instructions are transmitted in an encrypted manner to prevent them from being tampered with or stolen during transmission;

[0071] 1.2.3 Evaluation Module

[0072] (1) Instruction parsing unit

[0073] (1.1) Time resolution algorithm

[0074] Algorithm formula: the total time to complete the instruction Divided into task nodes Time nodes ,in , , the division of intermediate time nodes is based on the specific task rule logic, such as the division based on the key operation steps of the task or the equipment status change point; assuming that the task rule logic is determined in the first Set a time node at each key operation step, then the time node It can be expressed as the time from the start to the estimated completion of the key operation step;

[0075] Example: Assume that the total duration of a training task is 120 seconds. According to the task rule logic, it is necessary to start at ( ), complete the initial equipment check (estimated 30 seconds), complete the launch program start (estimated 60 seconds), complete the countdown start (estimated 90 seconds) and the end of the mission ( Seconds) These key steps set time nodes, and the time nodes are divided into , , , , ;

[0076] (1.2) Personnel resolution algorithm

[0077] Algorithm formula: Assuming that the total number of participating students is People, respectively , according to the instruction requirements, match each student to the corresponding time node and task role; a student task allocation matrix can be established ,in Indicates students At the time node The role of the task undertaken (if the student At the time node No task, then )(in ; );

[0078] Example: Suppose there are 3 students 、 、 , the time node of a training task is 、 、 , the task requires students exist Always in charge of operating the console , students exist and Responsible for monitoring instrument B at all times, students exist Responsible for checking valve C at all times, the student task allocation matrix for:

[0079] ;

[0080] (1.3) Device status analysis algorithm

[0081] Algorithm formula: According to the instruction requirements, determine the real-time status of the simulation training device at each time node; let the device status parameter set be , each time node The corresponding device state vector is ,in Indicates the device parameters at the time node The state value to be achieved, ;

[0082] Example: Assume that the equipment status parameters of a simulation training device include valve opening (Value range 0-100%), instrument reading (Unit: MPa) and console switch status (0 means off, 1 means on); at the time node At 1 second, the instruction requires the valve to open 50%, the instrument reading is 2.5MPa, and the console switch state is open, then the device state vector ;

[0083] (2) Student goal matching unit

[0084] Video data processing process: First, the collected video data is segmented according to time nodes, dividing the video into multiple time segments, each of which corresponds to a time node. Then, image recognition and target tracking algorithms are used to detect, identify, and track the students in each time segment, obtaining data such as the students' position coordinates, posture information, and movement characteristics.

[0085] Student identity recognition algorithm: At a certain time point, the student's position is matched with the preset student position template to realize the identification of the student's identity. A template matching algorithm can be used to calculate the similarity between each student's position image and the pre-stored student position template. The student corresponding to the template with the highest similarity is the student identity of the position.

[0086] Algorithm formula: Assume that the student position template set is , current time node The image of the student standing at a certain position is , then the similarity calculation function of student identity recognition is ,in Represents image pixel coordinates, similarity The largest Corresponding students That is, the student status of the position, where ;

[0087] Example: Assume that a student Site template The pixel values ​​in the image are distributed in a certain pattern. Image of students standing at a certain position at a certain time point and The similarity calculation result is 0.95, which is higher than the similarity of other student templates. Therefore, the student at this position is judged to be At subsequent time points, the trainees are continuously tracked through target tracking algorithms (such as Kalman filter tracking algorithms) to determine whether trainees of different roles are in the corresponding work positions at each time point;

[0088] (3) Device status matching unit

[0089] Equipment status data collection and comparison process: At a certain time point, the device is in a reset state, at which point the initial state data of the device is collected and recorded. At each subsequent time point, according to the time node analyzed by the instruction parsing unit, the device data processing module of the simulation training device integrated platform collects the real-time state data of the device. The collected real-time state data is compared with the state data that the device should reach at that time node, as determined by the instruction parsing unit, to determine whether the device state meets the requirements.

[0090] State comparison algorithm: The mean square error (MSE) algorithm is used to calculate the difference between the real-time state data of the device and the target state data; the real-time state vector of the device is , the target state vector is , then the mean square error is ,in ;when Less than the preset threshold If the device status is correct, it is considered that the operation is correct; otherwise, it is considered that the operation is wrong;

[0091] Example: Assume that at time , the device target state vector , the state vector collected in real time , number of device status parameters , then the mean square error ; If the preset threshold ,but , it is believed that the equipment status operation is accurate;

[0092] (4) Training Comprehensive Evaluation Unit

[0093] Construction of an evaluation indicator system: A multi-level evaluation indicator system will be established, including indicators for student goal matching (such as the accuracy of student positioning at corresponding time points), student operation accuracy indicators (such as the accuracy of equipment status matching), and instructor evaluation indicators (such as evaluation of student attitudes during training and the degree of task coordination and cooperation between students). Each indicator will be weighted differently based on its priority.

[0094] Comprehensive evaluation algorithm: Use weighted average algorithm to calculate the comprehensive evaluation indexes and get the comprehensive evaluation score of training; suppose the evaluation index set is , the corresponding weight set is (in ), the score of each indicator is , the comprehensive evaluation score ;

[0095] Example: Assume that the evaluation metric includes device state matching accuracy (Weight ), the accuracy of students’ positions at corresponding time nodes (Weight ) and student collaboration skills (Weight ); A student's device status matching accuracy score is 85 points, the student's corresponding time node position score is 90 points, and the student's collaboration ability score is 80 points. The comprehensive evaluation score is point;

[0096] 2. Simulation training device integration platform

[0097] 2.1、Lower computer

[0098] The console adopts the same appearance design and operation layout as the actual console at the space launch site, equipped with various buttons, switches, knobs, display screens and other operating components to realize the control operation of the simulation training device. The console integrates a high-performance microprocessor and data acquisition module to receive and process instructions, collect equipment status data and trainee operation data;

[0099] Instruments: These include various analog and digital instruments, such as pressure gauges, thermometers, tachometers, and liquid level gauges, which are used to display equipment status parameters and launch site environmental parameters in real time during simulated training. The instruments utilize high-precision sensors and simulation drive technology to ensure the accuracy and real-time nature of displayed data.

[0100] Valves: Electric or pneumatic valves are used, with similar operating feel and control characteristics to valves at actual launch sites. The valves are driven by motors or cylinders and can be opened, closed, and adjusted in degree according to instructions. Position sensors provide real-time feedback on the valve's status.

[0101] Other equipment: Based on the needs of the simulated training scenario, other simulation equipment such as engine models, rocket body structure models, and refueling system models can also be equipped to enhance the realism and comprehensiveness of the training;

[0102] 2.2 Host Computer

[0103] 2.2.1、Instruction Analysis Module

[0104] (1) Command receiving and parsing unit: Receives training commands issued by the instructor platform in real time, parses and verifies the commands to ensure their legality and validity; converts the commands into control signals that can be recognized and executed by the simulation training device based on the command type and target device;

[0105] (2) Instruction execution scheduling unit: According to the priority and execution time requirements of the instructions, the execution order of the simulation training device is reasonably scheduled to ensure that the instructions can be executed in a timely and accurate manner; it supports the concurrent execution of multiple instructions and realizes the reasonable allocation and management of the simulation training device resources through the task scheduling algorithm;

[0106] 2.2.2 Equipment data processing module

[0107] (1) Device status reset unit

[0108] Before training begins or when a reset command is received, the device status of the simulation training device is restored to the initial setting state; by controlling the device's drive mechanism and data initialization operations, the consistency and accuracy of the device status are ensured;

[0109] (2) Equipment status data acquisition unit

[0110] Data collection plan: According to the time nodes analyzed by the instruction parsing unit, the device status data of each time node is collected regularly. Multi-channel data collection technology is used to collect multiple device status parameters simultaneously to ensure the real-time and synchronization of data collection. The data collection frequency is set according to the speed of device status changes and the training accuracy requirements, generally not less than 10Hz.

[0111] Sensor selection and placement: Based on the type of equipment status parameters and measurement requirements, select appropriate sensors (such as pressure sensors, temperature sensors, displacement sensors, angle sensors, etc.) and arrange the sensors in a reasonable position to ensure accurate measurement of equipment status information. The sensors convert analog signals into digital signals through signal conditioning circuits and transmit them to the equipment data processing module through the communication interface.

[0112] (3) Data feedback unit

[0113] The collected equipment status data and trainee operation data are fed back to the instructor platform and video monitoring platform in real time, providing data support for training monitoring and evaluation. Data feedback uses reliable communication protocols (such as TCP / IP and OPC) to ensure the accuracy and real-time nature of data transmission. Data compression and encrypted transmission are supported to reduce network bandwidth usage and ensure data security.

[0114] 3. Video surveillance platform

[0115] 3.1、Lower computer

[0116] High-definition camera: A high-definition network camera with a resolution of no less than 1080P, wide-angle shooting function (viewing angle no less than 90 degrees) and night vision function (minimum illumination no more than 0.1 Lux), capable of clearly capturing video images of the trainees' training process under different lighting conditions; the camera supports autofocus, autoiris, and auto white balance functions to ensure the stability and clarity of the captured images;

[0117] Camera deployment: Cameras are deployed throughout the simulation training area to ensure comprehensive coverage and clear images. A multi-camera distributed deployment solution is used to capture all trainees' movements and postures from different angles. The camera locations and angles are designed through on-site surveys and simulations. Using 3D modeling and ray tracing technology, the camera installation positions and shooting angles are optimized to avoid blind spots and reflections.

[0118] 3.2 Host Computer

[0119] 3.2.1 Monitoring data processing module

[0120] (1) Data acquisition unit

[0121] Video stream reception and decoding: Receive video stream data transmitted by high-definition cameras in real time, support mainstream video encoding formats such as H.264 and H.265, and decode the video stream in real time through hardware decoding chips or software decoding algorithms, and convert it into processable digital image data;

[0122] Multi-camera synchronous acquisition: For multi-camera deployment scenarios, time synchronization technology (such as the IEEE1588 Precision Time Protocol) is used to ensure that the video data collected by each camera is strictly synchronized in time, with an error of no more than 1 millisecond. Through a synchronized trigger mechanism, multiple cameras can start collecting video data at the same time node, providing an accurate time reference for subsequent student target matching and behavior analysis.

[0123] (2) Data storage unit

[0124] Adopting a distributed storage architecture, the decoded video data is stored in a high-performance storage server or cloud storage platform. It supports real-time storage and historical data retrieval, and the storage time can be configured according to training requirements (e.g., 30 days of training video data is stored by default). It also uses data compression technology (e.g., dynamic bitrate compression) to reduce storage space usage while ensuring video quality.

[0125] (3) Data transmission unit

[0126] Real-time video streams are transmitted to the instructor platform and monitoring terminals via the network, supporting simultaneous online viewing and monitoring by multiple users. Streaming media transmission protocols (such as RTMP and RTSP) are used to ensure smooth video streaming and low latency (delay does not exceed 500 milliseconds). A video screen splitting function is provided, which can simultaneously display real-time images of multiple cameras on the same monitoring interface, supporting multiple screen split modes such as 1, 4, 9, and 16.

[0127] Finally, it should be noted that the above embodiments are merely examples for the purpose of illustrating the present invention and are not intended to limit the embodiments. Those skilled in the art will readily appreciate that other variations or modifications based on the above description are possible. It is not necessary and impossible to provide an exhaustive list of all embodiments. However, obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A training and evaluation system for a space launch site, characterized in that: The system includes an instructor platform, a simulation training device integration platform, and a video monitoring platform; The instructor platform includes an integrated training scenario setting module, an instruction module, and an evaluation module; The evaluation module includes an instruction parsing unit, and time parsing includes the total time required to complete the instruction. Divided into task nodes Time nodes ; Personnel analysis includes the participation of trainees People, respectively , establish a student task allocation matrix ,in Indicates students At the time node The roles undertaken, including 、 ; Equipment status analysis determines the real-time status of the simulation training device at each time node, and the equipment status parameter set is , each time node The corresponding device state vector is ,in Indicates the device parameters at the time node The state value to be achieved, where ; The evaluation module includes a student target matching unit, which uses a template matching algorithm to calculate the similarity between each student's standing position image and a pre-stored student standing position template. The student corresponding to the template with the highest similarity is the student identity of the standing position; The evaluation module includes an equipment status matching unit, which collects real-time equipment status data through the equipment data processing module of the simulation training device integrated platform; compares the collected real-time status data with the status data that the equipment should reach at the time node determined by the instruction parsing unit to determine whether the equipment status meets the requirements; The evaluation module includes a training comprehensive evaluation unit, which uses a weighted average algorithm to perform comprehensive calculations on various evaluation indicators to obtain a training comprehensive evaluation score; the evaluation indicator set is , the corresponding weight set is ,in The scores of each indicator are , the comprehensive evaluation score ; The simulation training device integrated platform includes an instruction analysis module and an equipment data processing module; The video monitoring platform includes a monitoring data processing module.

2. A space launch site training and evaluation system as claimed in claim 1, characterized in that: The integrated training scenario setting module includes a scenario parameter configuration unit and a task process design unit; The scenario parameter configuration unit allows the instructor to set diversified training scenario parameters, including launch mission type parameters, launch site environment parameters, and interference item parameters; The task process design unit provides a visual graphical editing tool, specifically including task node customization, logical relationship configuration, and process reuse management; The instruction module is used to issue specific training instructions, including: Instruction type: covers equipment operation instructions, task control instructions, and student management instructions; Release method: supports manual immediate release and automatic planned release; Command verification: Automatically verify the command format and permission level before sending to ensure the legitimacy of the command.

3. The space launch site training and evaluation system according to claim 1, wherein: The instruction analysis module includes an instruction receiving and parsing unit and an instruction execution scheduling unit; The instruction receiving and parsing unit: Receive encrypted instructions transmitted by the instructor platform via TCP / IP protocol in real time, and support concurrent processing of ≥100 instructions per second; Decrypt, grammatically check, and semantically analyze the instructions, extract key information about the target device, operation type, and parameter threshold, and convert them into control signals that can be recognized by the simulation training device; The instruction execution scheduling unit: Based on the priority queue and time window algorithm, device resources are dynamically allocated to avoid conflicts among multiple instructions; Supports concurrent execution of ≥5 independent instructions and optimizes the execution order through task scheduling algorithm.

4. The space launch site training and evaluation system according to claim 1, wherein: The device data processing module includes a device status resetting unit, a device status data acquisition unit, and a data feedback unit; The device status resetting unit: Upon receiving the "reset" command or before training begins, the motor / cylinder is driven to reset the valve, initialize instrument parameters, and clear the console operation records to ensure the consistency of the equipment status; Supports batch resetting of device parameters according to preset templates, taking ≤ 10 seconds; The device status data acquisition unit: Adopt multi-channel synchronous acquisition technology to obtain valve opening, instrument readings, and console operation log data in real time; Integrated pressure sensor and displacement sensor, convert analog signals into digital signals through signal conditioning circuit, and transmit them to the processing module via USB / Ethernet interface; The data feedback unit: Encapsulate device status data in OPC protocol format and provide real-time feedback to the instructor platform evaluation module and video monitoring platform; Supports data compression and encrypted transmission to reduce network bandwidth usage and ensure data security.

5. The space launch site training and evaluation system according to claim 1, wherein: The monitoring data processing module includes a data acquisition unit, a data storage unit, and a data transmission unit; The data acquisition unit: Receive H.265 encoded video streams transmitted by multiple cameras in real time, and achieve real-time decoding of ≥30 frames per second through hardware decoding chips; Adopting IEEE1588 precise time protocol, it ensures the synchronization error of multi-camera video data is ≤1 millisecond, and supports frame-level synchronization through synchronous trigger signals; The data storage unit: Adopting a distributed storage architecture, it supports real-time writing of training video data and retrieval of historical data; Automatically split video clips by time nodes and generate indexes. The default storage period is 30 days, and you can customize the storage period. The data transmission unit: Push real-time video streams to the instructor platform via the RTMP protocol, with a delay of ≤500 milliseconds, supporting simultaneous online viewing by multiple users; Provides screen splitting function, supports 1 / 4 / 9 / 16 screen modes, and can customize camera group display.

Images