Test control methods, devices and systems for propellant supply systems
By automating the propellant supply system test process, valve testing, airtightness testing, and pressure regulation are performed using initial operating condition data and image data. This solves the problem of low efficiency in manual verification in existing technologies and improves the efficiency of test preparation and test bench turnover.
Patent Information
- Application Number
- CN202611114261.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-24
- Publication Date
- 2026-11-17
AI Technical Summary
The existing propellant supply system requires the participation of multiple personnel during testing. Manual inspection and process confirmation result in low efficiency, high labor costs, long information transmission chains, and long test preparation time.
By receiving test task information, generating control fields, acquiring initial operating condition data and image data, automatically performing valve testing, airtightness testing and pressure regulation, and combining real-time detection data and image data to determine the start-up conditions, the system achieves automated control.
It reduces manual verification and waiting time across different positions, improves test preparation efficiency and test bench turnover efficiency, and reduces labor costs.
Smart Images

Figure CN123111701A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of test control, specifically to a test control method, apparatus, and system for a propellant supply system. Background Technology
[0002] A HAN (a type of green propellant) supply system test bench typically includes a nitrogen cylinder group, HAN storage tank, supply pipeline, valves, flow meter, pressure sensor, temperature sensor, downstream test object, data acquisition card, and host computer. The basic working method of the test is usually as follows: the host computer or control system sends control commands to the valves, the data acquisition card collects signals such as pressure, temperature, and flow, the host computer displays, stores, and provides simple alarms for the signals, an industrial camera is used for on-site observation, and the test personnel decide whether to proceed to the next test operation based on the monitoring screen and the measurement point values.
[0003] In existing testing procedures, test personnel typically begin by manually compiling test parameters and procedures based on the test task, followed by checking the initial on-site conditions. Valve operation tests and airtightness checks are then performed manually or semi-automatically. After depressurization, injection, and pressurization, test personnel, based on experience and current measurement values, determine whether the conditions for starting the test are met. After the test, the test data is exported to other software for processing. This approach usually requires multiple personnel to collaboratively complete tasks such as task understanding, process confirmation, on-site verification, pre-test checks, and post-test processing. While some steps can be automated using a host computer or scripts, the overall process still requires manual checks and relies heavily on manual workflow connections, resulting in high labor costs and inefficient test preparation due to long information transmission chains and extended preparation times. Summary of the Invention
[0004] This application provides a test control method, apparatus and system for a propellant supply system to solve the above-mentioned technical problems in the prior art.
[0005] According to a first aspect of this application, a test control method for a propellant supply system is provided, the method comprising performing the following main task operations: Receive test task information and extract key information from the test task information to generate control fields; Acquire the initial operating condition data of the propellant supply system collected by the data acquisition device before the test and the real-time image data captured by the on-site camera, and determine whether the initial conditions are met based on the initial operating condition data and the current image data; When the initial conditions are met, the system controls the valves of the propellant supply system to be tested one by one, and acquires the action signals of the corresponding valves collected by the data acquisition unit. The system then determines whether the valves have passed the test based on the action signals. After all valves pass the test, the system controls the pressurization circuit of the propellant supply system to perform an airtightness test, and obtains the test data. Based on the test data, it is determined whether the airtightness test has been passed. After the airtightness test is passed, the pressure regulation operation is started and the real-time detection data collected by the acquisition device is obtained. Based on the real-time detection data and the currently updated image data, the start-up conditions are determined and the determination result is obtained. When the determination result indicates that the test should be initiated, the test of the propellant supply system is initiated based on the control field.
[0006] In some implementations, the test data includes leakage rate, and the method further includes: The system monitors in real time for any security anomalies. If a security anomaly is detected, the main task operation is paused. The security anomaly includes at least one of the following: Based on real-time captured image data, it was detected that the test area captured by the on-site camera was occupied; Based on the leakage rate described during the airtightness test, it was determined to be an abnormal leak; The valve failed the test. The data / signal acquisition device has lost connection.
[0007] In some implementations, determining whether the initial conditions are met based on the initial operating condition data and the current image data further includes: Based on the current image data analysis, determine whether the test area captured by the on-site camera is unmanned; The initial operating condition data is checked and it is determined whether the check passes. If the test area is unmanned and the initial operating data passes verification, then the initial conditions are met.
[0008] In some embodiments, determining whether the valve passes the test based on the action signal further includes: Extract the action features and timing features from the action signal; Based on the motion characteristics, a single-modal result is obtained to determine whether the valve's action is normal. Based on the timing characteristics and the timing of the action command issued during the valve test, a timing consistency check is performed. Based on the timing consistency check result and the single-modal result, a final result is generated to determine whether the valve has passed the test.
[0009] In some implementations, before determining whether the initial conditions are met based on the initial operating condition data and the current image data, before determining whether the valve passes the test based on the action signal, before determining whether the airtightness test is passed based on the test data, and before determining the opening conditions based on the real-time detection data and the currently updated image data to obtain the determination result, the following further methods are included: Standardize the data / signals.
[0010] In some implementations, the test data includes the leakage rate; determining whether the airtightness test is passed based on the test data includes: The leakage rate is compared with a preset threshold. If the leakage rate is lower than the preset threshold, the airtightness test is deemed to have passed.
[0011] In some embodiments, the pressure regulation operation includes depressurization, injection, and pressurization operations, and the real-time detection data includes: real-time data of key measuring points collected by the data acquisition device during the depressurization, injection, and pressurization processes; The step of determining the start-up conditions based on the real-time detection data and the currently updated image data to obtain the determination result further includes: Historical data of the key measurement points are retrieved from the historical test database, and the allowable range of the key measurement points for the current test is generated based on the historical data. The parameter results are obtained by comparing the real-time data of the key measuring points with the corresponding allowable intervals. Based on the currently updated image data captured by the on-site camera, the test area captured by the on-site camera is checked to determine whether it is unmanned, and the on-site verification result is obtained; Based at least on the parameter results and the on-site verification results, determine whether the conditions for starting the test are met, and output the determination result.
[0012] In some embodiments, the test of initiating the propellant supply system based on the control field further includes: When the determination result indicates that the test should be started, the user authorization selection information is output. If an authorization instruction is received in response to the user authorization selection information, the test of the propellant supply system is initiated based on the control field.
[0013] In some embodiments, after initiating the test of the propellant supply system based on the control field, the method further includes: Collect experimental data during the experiment, and generate visualization results based on the experimental data. The visualization results include the experimental data, the analysis results after analyzing the experimental data, and / or the experimental report generated based on the experimental data.
[0014] According to a second aspect of this application, a test control device for a propellant supply system is provided, comprising: The task parsing module is used to receive test task information and extract key information from the test task information to generate control fields. The initial operating condition analysis module is used to acquire the initial operating condition data of the propellant supply system collected by the data acquisition device before the test and the image data captured in real time by the on-site camera, and to determine whether the initial conditions are met based on the initial operating condition data and the current image data. The valve testing module is used to control the propellant supply system to perform valve-by-valve testing when the initial conditions are met, and to acquire the corresponding valve action signals collected by the data acquisition unit, and to determine whether the valve passes the test based on the action signals. The airtightness testing module is used to control the airtightness test of the pressurization circuit of the propellant supply system after each valve has passed the test, and to acquire the test data and determine whether the airtightness test has been passed based on the test data. The test start determination module is used to initiate a pressure adjustment operation and acquire real-time detection data collected by the data acquisition device after the air tightness test is passed, and to determine the test start conditions based on the real-time detection data and the currently updated image data to obtain a determination result. The test execution module is used to initiate the test of the propellant supply system based on the control field when the determination result is to initiate the test.
[0015] According to a third aspect of this application, a test system for a propellant supply system is provided, including a data logger, a field camera, and a server; The data acquisition device is used to collect initial operating condition data, valve action signals, and real-time detection data and send them to the server. The field camera is used to photograph the test area of the propellant supply system and send the image data to the server; The server is used to implement the steps of the above-described test control method for the propellant supply system.
[0016] In some embodiments, the above-described experimental system further includes a data acquisition card, which is used to acquire data / signals acquired by the acquisition device and the field camera and send them to the server.
[0017] In some embodiments, the data acquisition device includes one or more of a pressure sensor, a flow meter, a temperature sensor, a sound pressure sensor, and a contact sensor. The pressure sensor is used to acquire the pressure at different measuring points of the propellant supply system, the temperature sensor is used to acquire the temperature at different measuring points of the propellant supply system, and the sound pressure sensor and the contact sensor are used to acquire the actuation signals of the valves of the propellant supply system.
[0018] According to a fourth aspect of this application, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the steps of the test control method for the propellant supply system described above.
[0019] In summary, the test control method, apparatus, test system, and computer-readable storage medium for the propellant supply system provided in this application have at least the following beneficial effects: After extracting key information from the test task to generate control fields, the system sequentially controls valve testing, airtightness testing, and pressure regulation to determine the start-up conditions based on the initial conditions. Finally, upon obtaining the start-up test result, the system starts the test based on the control fields to enter the formal test phase. In this way, the main process of the propellant supply system test can be completed automatically, reducing the time and labor costs caused by manual confirmation, verbal handover, waiting across positions, and switching between multiple software programs. This shortens the test preparation cycle and improves the efficiency of test preparation and the turnaround efficiency of the test bench. Attached Figure Description
[0020] To more clearly illustrate the technical solutions of the specific embodiments of this application, the accompanying drawings used in the specific embodiments will be briefly introduced below in conjunction with the accompanying drawings. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings or solutions can be obtained based on these drawings without creative effort.
[0021] Figure 1 This is a flowchart of a test control method for a propellant supply system in one embodiment of this application; Figure 2 This is a flowchart of a test control method for a propellant supply system in another embodiment of this application; Figure 3 This is a structural diagram of the test control device for the propellant supply system in one embodiment of this application; Figure 4 This is a structural diagram of a test system for a propellant supply system in one embodiment of this application. Detailed Implementation
[0022] To make the above and other features and advantages of this application clearer, the application is further described below with reference to the accompanying drawings. It should be understood that the specific embodiments given herein are for the purpose of explanation to those skilled in the art, and are exemplary only, not restrictive.
[0023] In the following description, numerous specific details are set forth to provide a thorough understanding of this application. However, it will be apparent to those skilled in the art that the specific details are not required to practice this application. In other instances, well-known steps or operations have not been described in detail to avoid obscuring this application.
[0024] The test control method for the propellant supply system provided in this application embodiment can be executed by the test control device for the propellant supply system provided in this application embodiment, which can be configured in a server that deploys intelligent agents.
[0025] refer to Figure 1 The test control method for the propellant supply system provided in this application includes steps S110 to S160 of performing the following main task operations.
[0026] S110: Receive test task information and extract key information from the test task information to generate control fields.
[0027] Test task information can be obtained by receiving user input or information sent from a host computer. For example, test task information may include: test purpose, test object, target pressure / flow rate, action sequence, safety thresholds, test phase divisions, historical reference tasks, and report output requirements. After receiving the test task information, the agent calls the interface service to extract key test-related information and converts natural language into structured control fields. For example, control fields include: valve identifier, action type, action start time, action duration, interlock conditions, backoff actions, record items, and alarm thresholds.
[0028] S120: Acquire the initial operating condition data of the propellant supply system collected by the data acquisition device before the test and the real-time image data captured by the on-site camera, and determine whether the initial conditions are met based on the initial operating condition data and the current image data.
[0029] A field camera is used to photograph the test area of the propellant supply system; for example, an industrial camera can be used. The type of initial operating condition data can be specifically set according to the test requirements. For example, the initial operating condition data can include the pressure status of the propellant supply system, the storage status of the propellant supply system tanks, and the data to be measured at key measuring points, such as temperature. Correspondingly, the data acquisition device includes pressure sensors for detecting pressure and temperature sensors for detecting temperature. Among these, key measuring points are important test points of the propellant supply system, and their locations can be set as needed. Specifically, the presence of people in the test area can be analyzed based on the image data to verify the initial operating condition data. The combined analysis results and verification results are then used to comprehensively determine whether the initial conditions are met.
[0030] S130: When the initial conditions are met, the control performs valve testing on the propellant supply system one by one, and acquires the corresponding valve action signals collected by the data acquisition unit. Based on the action signals, it is determined whether the valve has passed the test.
[0031] The intelligent agent can control the valve to enter the valve testing phase by sending control commands to the valve and other related actuators. During the valve testing process, the valve's action signals are collected by a data acquisition device, and the action signals are analyzed to determine whether the corresponding valve has passed the test. For example, for pneumatic valves, the action audio signal can be collected by a sound pressure sensor or a sound acquisition device; for electromagnetic valves, the action response signal can be collected by a contact sensor or an industrial camera.
[0032] S140: After all valves have passed the test, control the pressurization circuit of the propellant supply system to perform an airtightness test, obtain the test data, and determine whether the airtightness test has been passed based on the test data.
[0033] Specifically, all valves in the propellant supply system undergo testing before a leak-proof test is performed. The intelligent agent can initiate the leak-proof test by sending control commands to the actuators in the pressurization loop. The test data can be collected by a data acquisition unit or calculated using a leakage rate testing method based on the data collected by the acquisition unit. For example, if the test data is the leakage rate, the leakage rate can be calculated by collecting the flow rate through the acquisition unit.
[0034] S150: After the airtightness test is passed, the pressure regulation operation is started and the real-time detection data collected by the data acquisition unit is obtained. The test conditions are determined based on the real-time detection data and the currently updated image data to obtain the judgment result.
[0035] Pressure regulation operation refers to the operation of adjusting the pressure of the propellant supply system, such as depressurization, filling, and increasing. Real-time monitoring data refers to real-time data collected from key measuring points during the pressure regulation operation, including parameters such as pressure and temperature. Specifically, the currently updated image data can be image data collected and updated in real time during the pressure regulation operation. The presence of people in the test area can be analyzed based on the image data, and the real-time monitoring data can be analyzed in conjunction with the analysis results of the image data to make a comprehensive judgment.
[0036] S160: When the determination result is to initiate a test, initiate a test of the propellant supply system based on the control field.
[0037] For example, the judgment results include three types: start test, prohibit test, and recommend review. If the judgment result is start test, the propellant supply system test can be started based on the control fields, and the test can be initiated.
[0038] The aforementioned test control method for the propellant supply system, after extracting key information from the test task to generate control fields, sequentially controls valve testing, airtightness testing, and pressure regulation to determine the start-up conditions through initial condition determination. Finally, upon obtaining the start-up test determination result, the test is initiated based on the control fields to enter the formal test phase. In this way, the main process of the propellant supply system test can be completed automatically, reducing the time and labor costs caused by manual item confirmation, verbal handover, cross-post waiting, and switching between multiple software programs, shortening the test preparation cycle, and thus improving the test preparation efficiency and the turnaround efficiency of the test bench.
[0039] In one embodiment, the test data includes the leakage rate, and the test control method for the propellant supply system further includes: real-time monitoring for any safety anomalies; if a safety anomaly is detected, the main task operation is suspended. That is, during the execution of the main task operation, safety monitoring is also performed; if a safety anomaly is detected, the main task operation is interrupted, thereby improving the safety of the test. The safety anomaly includes at least one of the following (1) to (4).
[0040] (1): Based on the real-time captured image data, the test area captured by the on-site camera is detected to be occupied. Specifically, image analysis can be performed on the image data to determine whether personnel are identified in the image, thereby monitoring whether there are people in the test area. If personnel are identified, it indicates that personnel have mistakenly entered the test area, which is determined to be a safety anomaly, and the main task operation process is interrupted.
[0041] (2) The leakage rate during the airtightness test is used to determine if it is an abnormal leak. Specifically, the leakage rate can be compared with a preset threshold. If the leakage rate is higher than the set threshold, it is an abnormal leak, which is determined to be a safety anomaly event, and the main task operation process is interrupted.
[0042] (3) Valve test fails. Specifically, there are multiple valves. If any valve fails the test, it is determined to be a safety anomaly.
[0043] (4) Data / signal acquisition device loses connection. There may be multiple acquisition devices. If any acquisition device is found to be out of contact, it is determined to be a safety anomaly. For example, initial operating condition data includes data such as pressure and temperature. Correspondingly, the acquisition devices for acquiring initial operating condition data include pressure sensors, temperature sensors, etc.; the acquisition devices for acquiring valve action signals include one or more of sound pressure sensors and contact sensors.
[0044] In one embodiment, before determining whether the initial conditions are met based on the initial operating condition data and the current image data, before determining whether the valve passes the test based on the action signal, before determining whether the airtightness test is passed based on the test data, and before obtaining a judgment result by determining the opening conditions based on the real-time detection data and the currently updated image data, the process further includes: standardizing the data / signals. Specifically, before determining whether the initial conditions are met based on the initial operating condition data and the current image data, the collected initial operating condition data and image data are standardized. Before determining whether the airtightness test is passed based on the test data, the test data is standardized. Before obtaining a judgment result by determining the opening conditions based on the real-time detection data and the currently updated image data, the real-time detection data and the currently updated image data are standardized.
[0045] Standardization processing includes format unification, timestamp alignment, and other procedures. Different standardization operations can be applied to different types of data. For example, the types of data collected include pressure, temperature, flow rate, six-component force data from a six-component force sensor, images, audio, and contact response signals from a contact sensor. For pressure, temperature, flow rate, and six-component force data, standardization processing such as noise reduction filtering, outlier removal, unit unification, and timestamp alignment can be performed. For audio data, frame segmentation, noise reduction, envelope extraction, or spectral feature extraction can be performed. For image data, key region cropping, target detection, personnel identification, and keyframe filtering can be performed. For contact response signals, edge extraction, action timing recognition, and event-based encoding can be performed.
[0046] While existing propellant supply systems can collect pressure, temperature, flow rate, images, and some actuator status information, these data are typically collected independently by different devices, resulting in issues such as varying sampling frequencies, inconsistent timestamps, inconsistent data formats, and inconsistent data quality. This makes direct horizontal comparison and fusion analysis difficult. This application addresses this by standardizing the data / signals before processing them, achieving data regularization, time sequence alignment, feature extraction, and standardization. This enables support for multimodal joint judgment and online safety interlocking.
[0047] In one embodiment, step S120, which determines whether the initial conditions are met based on the initial operating condition data and the current image data, further includes: analyzing whether the test area captured by the on-site camera is unmanned based on the current image data; verifying the initial operating condition data and determining whether it passes the verification; if the test area is unmanned and the initial operating condition data passes the verification, then the initial conditions are met. Furthermore, the image data and the initial operating condition data can be standardized data.
[0048] Initial operating condition data includes the pressure status of the propellant supply system, the storage status of the propellant supply system's tanks, and the data to be measured at key measuring points. The pressure status of the propellant supply system is divided into unpressurized and pressurized states, which can be analyzed by collecting pressure data at designated locations. The storage status includes empty and non-empty tank states, which can be analyzed by detecting the presence of gas in the tanks. The data to be measured at key measuring points is compared with a set reasonable handling range. Specifically, the initial operating condition data verification conditions include: the propellant supply system is unpressurized, the tanks are empty, and the signals at key measuring points are online, with the corresponding data within a reasonable initial value range. For example, the agent calls the on-site visual interface to identify image data to determine if there are personnel in the test area; after confirming that the personnel status meets safety requirements (no one in the test area), it determines whether the propellant supply system is unpressurized, whether the tanks are empty, whether the signals at key measuring points are online, and whether the corresponding data are within a reasonable initial value range; if all conditions are met, step S130 is executed to proceed to the next stage. In this way, the analysis of initial conditions is completed automatically, reducing the time and labor costs associated with manual processing.
[0049] In one embodiment, step S130, which determines whether the valve passes the test based on the action signal, further includes: extracting action features and timing features from the action signal; determining whether the valve's action is normal based on the action features to obtain a single-modal result; performing a timing consistency check based on the timing features and the timing of the action command issued during the valve test; and generating a final result indicating whether the valve passes the test based on the timing consistency check result and the single-modal result. Furthermore, the action signal is a standardized signal.
[0050] By identifying and extracting features from action signals, action characteristics and temporal characteristics of the executed actions are obtained. Single-action analysis is then performed on the action characteristics. For example, for pneumatic valves, action audio is collected using a sound pressure sensor or sound acquisition device. After timing alignment, noise reduction, and feature extraction, a single-modal sub-model, such as an acoustic recognition sub-model, is used to determine whether the action is in place, and whether there is hysteresis, jamming, or abnormal impact. For solenoid valves, their action response is collected using a contact sensor or industrial camera. After edge extraction or visual keyframe recognition, a single-modal sub-model, such as a contact response recognition sub-model or a visual recognition sub-model, is used to determine the action. Furthermore, the temporal characteristics are checked for consistency based on the corresponding action command time. For example, the time difference between the time corresponding to the temporal characteristics and the action command time is compared to see if it is within a preset deviation range. If it is within the preset deviation range, the timing is consistent; otherwise, it is inconsistent. Multimodal fusion decision is performed by combining the results of multiple single-modal recognition sub-models. For example, if the single-modal recognition sub-model result indicates normal action and the consistency check result indicates that the check is passed, the final result is that the valve passes the test. In this way, the data is first standardized, then the single-modal sub-models perform local identification on different data, and finally, a unified conclusion is output through fusion. This allows for the identification of risks that are difficult to detect with fixed scripts and single threshold monitoring before the experiment, such as valve lag, false action, jamming, and local leakage. Before the experiment officially begins, the occurrence, delay, and integrity of valve actions are automatically verified. This not only reduces the workload of manual timing programming, manual data reading, and manual item-by-item comparison, but also makes safety monitoring more granular and rigorous, and easier to form closed-loop interlocks, because all types of data are aligned and standardized before participating in the judgment. Specifically, each valve is tested in sequence, and if all valves pass the test, step S140 is executed to proceed to the next stage.
[0051] In one embodiment, the test data includes the leakage rate; step S140, which determines whether the airtightness test is passed based on the test data, includes: comparing the leakage rate with a preset threshold; if the leakage rate is lower than the preset threshold, the airtightness test is determined to be passed.
[0052] After all valves pass the test, the intelligent agent activates the pressurization circuit to perform an airtightness test and records the leakage rate in real time. When the leakage rate is lower than the set threshold, the airtightness test is deemed passed, and the subsequent depressurization, filling, and pressurization stages begin; otherwise, it reverts to the safety holding state or re-enters the troubleshooting process.
[0053] In one embodiment, the pressure regulation operation includes depressurization, injection, and pressurization operations. The real-time detection data includes real-time data of key measuring points collected by the data acquisition device during the depressurization, injection, and pressurization processes, such as pressure, temperature, and flow rate. Further, step S150, which determines the start-up conditions based on the real-time detection data and the currently updated image data, further includes steps (a1) to (a4).
[0054] Step (a1): Retrieve historical data of key measurement points from the historical test database, and generate the allowable range of key measurement points for the current test based on the historical data.
[0055] During depressurization, injection, and pressurization, the intelligent agent continuously monitors real-time data from key measurement points such as pressure, temperature, and flow rate. Simultaneously, it retrieves the numerical ranges of historical data from key measurement points in the pre-test phase from the historical test database, forming the allowable range for the initial operating conditions. Preferably, the historical data also undergoes data standardization processing, such as field mapping, anomaly cleaning, and timestamp alignment, to ensure direct comparison with current real-time data. This supports stable fusion judgment, and the historical data is no longer solely for post-test queries but can serve as a direct reference benchmark for current test start-up judgment.
[0056] Step (a2): Compare the real-time data of the key measuring points with the corresponding allowable intervals to obtain the parameter results. Preferably, the standardized real-time data is compared with the allowable intervals to determine whether the real-time data is within the corresponding allowable intervals.
[0057] Step (a3): Based on the updated image data captured by the field camera, check whether the test area captured by the field camera is unmanned, and obtain the field verification results.
[0058] The on-site camera captures real-time image data. When it is necessary to verify whether the test area is unoccupied, the agent again calls the on-site visual interface to recognize the image data to confirm whether the test area is unoccupied.
[0059] Step (a4): Determine whether the conditions for starting the test are met based on the parameter results and the on-site verification results, and output the determination result.
[0060] By comparing the current real-time data with the allowable range determined by historical data, and then combining the results of multimodal perception from visual or other types of data, a decision output is fused to ensure the safety of the trial. For example, the decision output may include three outcomes: initiating the trial, prohibiting the trial, or recommending a review.
[0061] In one embodiment, step S160, which involves initiating a test of the propellant supply system based on a control field, further includes: when the determination result is to initiate a test, outputting user authorization selection information; and if an authorization command is received in response to the user authorization selection information, initiating a test of the propellant supply system based on the control field.
[0062] The user authorization selection information prompts the user to choose whether to authorize the test. This can be displayed as a selection box, a voice message, or other methods. In response to the user authorization selection information, the user can input an authorization command, thus initiating the test. Conversely, if the user inputs a non-authorization command, the propellant supply system test will not be initiated. Therefore, after obtaining the test initiation decision, a manual authorization confirmation step is retained. The test only proceeds after manual authorization, preventing directly starting a fully automated test and ensuring test safety.
[0063] In one embodiment, after initiating the test of the propellant supply system based on the control field, the process further includes: collecting test data during the test, generating visualization results based on the test data, wherein the visualization results include the test data, analysis results after analyzing the test data, and / or a test report generated based on the test data.
[0064] During the experiment execution phase, the intelligent agent continuously collects data such as pressure, temperature, flow rate, six-component force, sound pressure, and images to monitor the experiment status online. After the experiment, visualization results are generated based on the experimental data, automatically completing the visualization of experimental data, annotation of key events, parameter correlation analysis, and / or generation of experimental reports. This achieves standardized data accumulation and knowledge closure, enabling knowledge accumulation, experience reuse, and document standardization, while reducing the workload of manual time sequence writing and data processing.
[0065] like Figure 2 The diagram illustrates the main task operation flow of a test control method for a propellant supply system in a specific embodiment. Preferably, a hierarchical state machine structure is used to implement the test control method for the propellant supply system, rather than a single sequential script. For example, it includes at least a main task state machine M, a safety monitoring state machine S, an actuator diagnostic state machine V, and a knowledge and decision-making state machine K. These four types of state machines work in parallel and collaboratively to form a unified closed-loop intelligent agent scheme that integrates task understanding, multimodal perception, data normalization, historical experience retrieval, state machine interlocking, safety judgment, and automatic report generation. Each state machine does not directly read the raw signals collected by the sensors, but rather reads data that has undergone data standardization processing, thereby improving the stability and interpretability of the state switching logic.
[0066] (1) Main task state machine M Specifically, the main task state machine can be used to drive the main task operation process, and state transitions can be performed through the main task state machine. For example, the main task state machine M can be set to the following multiple states: M0, Standby; M1, Experimental Task Analysis; M2, control fields and timing generation; M3. On-site safety confirmation (analyzing whether there are people in the test area based on image data); M4, Initial Operating Condition Verification; M5, Actuator (Valve) Test; M6, airtightness test; M7, depressurization / filling / pressurization; M8. Comprehensive judgment of opening conditions; M9, manual authorization; M10, Test Execution and Online Monitoring; M11. Post-trial analysis and report generation; In addition, an asynchronous, preemptible exception state is set: M12, Safety Hold / Abnormal Shutdown; Its basic switching logic is as follows: Upon receiving the test task information, the process switches from M0 to M1; after task parsing is complete, it enters M2; after the timing and control fields are generated, it enters M3; only when conditions are met in M3 and M4 is entry into M5 permitted; after all actuators (valves) have passed the test, it enters M6; after the airtightness test is passed, it enters M7; after depressurization / filling / pressurization is completed and meets the requirements for on-site safety verification and real-time data detection, it enters M8; after M8 outputs the test start conclusion, it enters M9; after manual authorization, it enters M10; after the test is completed, it enters M11. If a safety anomaly is detected at any time, the process immediately switches to M12.
[0067] (2) Safety monitoring state machine S The safety monitoring state machine is responsible for preemptive interlocking with the main task state machine, and can be configured as follows: S0, standby for safety; S1. Personnel monitoring in the test area; S2, Pressure / Leakage Monitoring; S3, Interlocking passed; S4, Alarm; S5, Emergency Stop; The safety monitoring state machine has a higher priority than the main task state machine. That is to say, even if the main task state machine has entered M7, M8 or even M10, as long as the safety monitoring state machine detects safety anomalies such as personnel entering the test area, system overpressure, abnormal leakage, loss of connection of key sensors, or abnormal valve operation, it can directly interrupt the main task state machine and force it to switch to the M12 safety hold / abnormal shutdown state.
[0068] (3) Actuator diagnostic state machine V The actuator diagnostic state machine is used to verify the operation of each valve individually, and can be set as follows: V0, To be tested; V1. Issue a single action command; V2, Collect action responses; V3, Multimodal Consistency Comparison; V4. Valve test passed; V5, Valve test failed; The response input of pneumatic valves mainly consists of acoustic and temporal characteristics, while the response input of solenoid valves mainly consists of contact signals and / or visual characteristics. Preferably, the V3 multimodal consistency comparison steps include: reading one or more local judgment results from the acoustic recognition sub-model, visual recognition sub-model, and contact response recognition sub-model, and performing temporal consistency verification in conjunction with the action command timing to generate the final test conclusion for the valve.
[0069] If a valve enters V5, the main task state machine must not continue to M6 or later, but should return to the maintenance / review process or directly enter M12.
[0070] (4) Knowledge and Decision State Machine K The knowledge and decision state machine is used for historical data retrieval, allowing interval generation, and outputting the results of test opening condition determination. It can be set as follows: K0, Historical Data Retrieval; K1, allows interval modeling; K2, Real-time Data Comparison; K3, Output of the test opening condition judgment result; K4. Post-exam knowledge archiving; Specifically, K0 and K1 can be started in advance during stages M1-M2 of the main task state machine; K2 and K3 run synchronously with real-time data during stages M7-M8; and K4 completes data visualization, report generation, and experience sample accumulation during stage M11. Preferably, the real-time data comparison step of K2 not only performs threshold comparison on the original values, but also performs joint analysis on the normalized historical statistical features, current feature vectors, and abnormal event labels to form a more structured input suitable for test opening judgment.
[0071] The coordination and switching relationships between the state machines are as follows: The prerequisite for M2 to enter M3 is that the control fields and action timing have been generated.
[0072] The prerequisite for M3 to enter M4 is that the safety monitoring state machine is in S3, that is, the test area is unmanned for several consecutive frames and the on-site camera link is normal.
[0073] The prerequisites for M4 to enter M5 are: the system pressure is below the safety threshold, the tank meets the conditions of being empty or equivalent to being empty, and the signals at key measuring points are online and the data are within a reasonable initial value range.
[0074] The prerequisite for M5 to enter M6 is that all valves have reached V4 in the actuator diagnostic state machine.
[0075] The prerequisite for M6 to enter M7 is that the leakage rate does not exceed the set threshold.
[0076] The prerequisite for M7 to enter M8 is that depressurization / addition / increase is completed, and the knowledge and decision state machine has completed real-time data comparison.
[0077] The prerequisite for M8 to enter M9 is that the values of the current key measuring points all fall within the allowable range, the safety monitoring state machine does not trigger an alarm, and the decision module outputs the conclusion of starting the test.
[0078] For M9 to enter M10, manual authorization must be received.
[0079] Triggering conditions for entering M12 under any state: personnel accidentally entering the test area, overpressure, abnormal leakage, key measuring points exceeding limits, sensor disconnection, valve malfunction, communication anomaly, etc.
[0080] Furthermore, the above switching can be formally described as: if and only if The condition of no one being present in the test area has been met; The system is depressurized / the storage tank is empty; All valves passed the test; The leakage rate is less than a preset threshold; All key measuring points are within the initial allowable range; And the manual authorization was valid; Only the main task state machine is allowed to switch from the ready state to the formal test state.
[0081] This application provides a test control device for a propellant supply system, such as... Figure 3 As shown, the device includes: The task parsing module 310 is used to receive test task information and extract key information from the test task information to generate control fields; The initial operating condition analysis module 320 is used to acquire the initial operating condition data of the propellant supply system collected by the data acquisition device before the test and the image data captured in real time by the on-site camera, and to determine whether the initial conditions are met based on the initial operating condition data and the current image data. The valve test module 330 is used to control the propellant supply system to perform valve tests one by one when the initial conditions are met, and to acquire the corresponding valve action signals collected by the data acquisition unit, and to determine whether the valve passes the test based on the action signals. The air tightness test module 340 is used to control the air tightness test of the pressurization circuit of the propellant supply system after each valve has passed the test, and to acquire test data and determine whether the air tightness test has been passed based on the test data. The test start determination module 350 is used to start the pressure regulation operation and acquire the real-time detection data collected by the acquisition device after the air tightness test is passed. Based on the real-time detection data and the currently updated image data, the test start conditions are determined to obtain the determination result. The test execution module 360 is used to initiate the test of the propellant supply system based on the control field when the determination result is to start the test.
[0082] In one embodiment, the test control device for the propellant supply system further includes a data normalization module, which performs data / signals normalization processing before the initial condition analysis module 320 determines whether the initial conditions are met based on the initial condition data and the current image data, before the valve test module 330 determines whether the valve has passed the test based on the action signal, before the airtightness test module 340 determines whether the airtightness test has passed based on the test data, and before the test start determination module 350 determines the test start conditions based on the real-time detection data and the currently updated image data to obtain the determination result.
[0083] It should be understood that the specific features, operations, and details described herein with respect to the methods of this application can also be similarly applied to the apparatus and system of this application, or vice versa. Furthermore, each step of the methods of this application described above can be performed by a corresponding component or unit of the apparatus or system of this application.
[0084] It should be understood that the various modules / units of the apparatus of this application can be implemented wholly or partially through software, hardware, firmware, or a combination thereof. Each module / unit can be embedded in the server's processor in hardware or firmware form or independent of the processor, or it can be stored in the server's memory in software form for the processor to call to execute the operation of each module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.
[0085] This application provides a test system for a propellant supply system, including a data acquisition unit, a field camera, and a server. The data acquisition unit collects initial operating condition data, valve action signals, and real-time detection data, and sends these to the server. The field camera captures images of the test area of the propellant supply system and sends the image data to the server. The server implements the steps of the aforementioned test control method for the propellant supply system. Specifically, the server deploys an intelligent agent that implements the above-mentioned test control method, used for interface calls, timing generation, multimodal recognition, comprehensive judgment, and test data analysis.
[0086] In one embodiment, the test system for the propellant supply system further includes a data acquisition card. The data acquisition card is used to acquire data / signals collected by the acquisition unit and the field camera and send them to the server. It is understood that the data acquisition card can also receive control commands from the server and send them to the controlled object. For example, during valve testing, it receives valve opening / closing commands from the server and sends them to the valve to control its operation.
[0087] In one embodiment, the data acquisition device includes one or more of a pressure sensor, a flow meter, a temperature sensor, a sound pressure sensor, and a contact sensor. The pressure sensor is used to acquire the pressure at different measuring points in the propellant supply system, the temperature sensor is used to acquire the temperature at different measuring points in the propellant supply system, and the sound pressure sensor and the contact sensor are used to acquire the actuation signals of the valves in the propellant supply system.
[0088] In one embodiment, the aforementioned experimental system further includes a host computer that is communicatively connected to the server. The host computer is used to send information to the server or receive information sent by the server for display. For example, the host computer can display status, configure tasks, and perform manual authorization and anomaly intervention.
[0089] like Figure 4 As shown, the propellant supply system includes nitrogen cylinder groups, pneumatic ball valves, HAN storage tanks, supply pipelines, pneumatic ball valves (pneumatic valves), flow meters, flow regulating valves, downstream valves, and the test object. The server is connected to the host computer, data acquisition card, industrial camera, sound pressure sensor, pressure sensor (P), temperature sensor (T), flow meter (m), six-component force sensor, and various valve actuators. The data acquisition card is used to collect signals from each sensor and output control signals to the valves or actuators. The industrial camera is used to acquire the status of personnel, the appearance of equipment, and visible response information in the test area. The server runs an intelligent agent to complete the intelligent management of the entire process, including interface calls, timing generation, multimodal recognition, comprehensive judgment, and test data analysis.
[0090] In addition, this application provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the above-described experimental control method for the propellant supply system.
[0091] Those skilled in the art will understand that the method steps of this application can be performed by a computer program instructing related hardware, such as a server. The computer program can be stored in a non-transitory computer-readable storage medium, and its execution causes the steps of this application to be performed. Depending on the context, any reference herein to memory, storage, or other media may include non-volatile or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.
[0092] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, provided that such combination does not contain contradictions.
[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
Claims
1. A test control method of a propellant supply system, characterized by, This includes performing the following main tasks: Receive test task information and extract key information from the test task information to generate control fields; Acquire the initial operating condition data of the propellant supply system collected by the data acquisition device before the test and the real-time image data captured by the on-site camera, and determine whether the initial conditions are met based on the initial operating condition data and the current image data; When the initial conditions are met, the system controls the valves of the propellant supply system to be tested one by one, and acquires the action signals of the corresponding valves collected by the data acquisition unit. The system then determines whether the valves have passed the test based on the action signals. After all valves pass the test, the system controls the pressurization circuit of the propellant supply system to perform an airtightness test, and obtains the test data. Based on the test data, it is determined whether the airtightness test has been passed. After the airtightness test is passed, the pressure regulation operation is started and the real-time detection data collected by the acquisition device is obtained. Based on the real-time detection data and the currently updated image data, the start-up conditions are determined and the determination result is obtained. When the determination result indicates that the test should be initiated, the test of the propellant supply system is initiated based on the control field.
2. The method according to claim 1, characterized in that, The test data includes the leakage rate, and the method further includes: The system monitors in real time for any security anomalies. If a security anomaly is detected, the main task operation is paused. The security anomaly includes at least one of the following: Based on real-time captured image data, it was detected that the test area captured by the on-site camera was occupied; Based on the leakage rate described during the airtightness test, it was determined to be an abnormal leak; The valve failed the test. The data / signal acquisition device has lost connection.
3. The method according to claim 1, characterized in that, The step of determining whether the initial conditions are met based on the initial working condition data and the current image data further includes: Based on the current image data analysis, determine whether the test area captured by the on-site camera is unmanned; The initial operating condition data is checked and it is determined whether the check passes. If the test area is unmanned and the initial operating data passes verification, then the initial conditions are met.
4. The method according to claim 1, characterized in that, The step of determining whether the valve passes the test based on the action signal further includes: Extract the action features and timing features from the action signal; Based on the motion characteristics, a single-modal result is obtained to determine whether the valve's action is normal. Based on the timing characteristics and the timing of the action command issued during the valve test, a timing consistency check is performed. Based on the timing consistency check result and the single-modal result, a final result is generated to determine whether the valve has passed the test.
5. The method according to claim 1, characterized in that, Before determining whether the initial conditions are met based on the initial operating condition data and the current image data, before determining whether the valve passes the test based on the action signal, before determining whether the airtightness test is passed based on the test data, and before obtaining the determination result by determining the opening conditions based on the real-time detection data and the currently updated image data, the procedure further includes: Standardize the data / signals.
6. The method according to claim 1, characterized in that, The test data includes the leakage rate; determining whether the airtightness test is passed based on the test data includes: The leakage rate is compared with a preset threshold. If the leakage rate is lower than the preset threshold, the airtightness test is deemed to have passed.
7. The method according to claim 1, characterized in that, The pressure regulation operation includes depressurization, injection, and pressurization operations, and the real-time detection data includes: real-time data of key measuring points collected by the data acquisition device during the depressurization, injection, and pressurization processes; The step of determining the start-up conditions based on the real-time detection data and the currently updated image data to obtain the determination result further includes: Historical data of the key measurement points are retrieved from the historical test database, and the allowable range of the key measurement points for the current test is generated based on the historical data. The parameter results are obtained by comparing the real-time data of the key measuring points with the corresponding allowable intervals. Based on the currently updated image data captured by the on-site camera, the test area captured by the on-site camera is checked to determine whether it is unmanned, and the on-site verification result is obtained; Based at least on the parameter results and the on-site verification results, determine whether the conditions for starting the test are met, and output the determination result.
8. The method according to claim 1, characterized in that, The test of initiating the propellant supply system based on the control field further includes: When the determination result indicates that the test should be started, the user authorization selection information is output. If an authorization instruction is received in response to the user authorization selection information, the test of the propellant supply system is initiated based on the control field.
9. The method according to any one of claims 1-8, characterized in that, After initiating the test of the propellant supply system based on the control field, the method further includes: Collect experimental data during the experiment, and generate visualization results based on the experimental data. The visualization results include the experimental data, the analysis results after analyzing the experimental data, and / or the experimental report generated based on the experimental data.
10. A test control device for a propellant supply system, characterized in that, include: The task parsing module is used to receive test task information and extract key information from the test task information to generate control fields. The initial operating condition analysis module is used to acquire the initial operating condition data of the propellant supply system collected by the data acquisition device before the test and the image data captured in real time by the on-site camera, and to determine whether the initial conditions are met based on the initial operating condition data and the current image data. The valve testing module is used to control the propellant supply system to perform valve-by-valve testing when the initial conditions are met, and to acquire the corresponding valve action signals collected by the data acquisition unit, and to determine whether the valve passes the test based on the action signals. The airtightness testing module is used to control the airtightness test of the pressurization circuit of the propellant supply system after each valve has passed the test, and to acquire the test data and determine whether the airtightness test has been passed based on the test data. The test start determination module is used to initiate a pressure adjustment operation and acquire real-time detection data collected by the data acquisition device after the air tightness test is passed, and to determine the test start conditions based on the real-time detection data and the currently updated image data to obtain a determination result. The test execution module is used to initiate the test of the propellant supply system based on the control field when the determination result is to initiate the test.
11. A test system for a propellant supply system, characterized in that, Includes data acquisition devices, on-site cameras, and servers; The data acquisition device is used to collect initial operating condition data, valve action signals, and real-time detection data and send them to the server. The field camera is used to photograph the test area of the propellant supply system and send the image data to the server; The server is used to implement the steps of the method according to any one of claims 1-9.
12. The testing system according to claim 11, characterized in that, It also includes a data acquisition card, which is used to acquire data / signals collected by the acquisition device and the field camera and send them to the server.
13. The testing system according to claim 11, characterized in that, The data acquisition device includes one or more of a pressure sensor, a flow meter, a temperature sensor, a sound pressure sensor, and a contact sensor. The pressure sensor is used to acquire the pressure at different measuring points of the propellant supply system, the temperature sensor is used to acquire the temperature at different measuring points of the propellant supply system, and the sound pressure sensor and the contact sensor are used to acquire the actuation signals of the valves of the propellant supply system.
14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 9.
