A rocket engine abnormality monitoring method and system

Abstract

The present application provides a method and system for monitoring rocket engine anomalies, which relates to the field of data processing technology. The method includes: collecting the operating status data of multiple parallel rocket engines; generating a linear spectrum of each operating status data changing with time; performing time correction on the horizontal axis of the linear spectrum based on the delay time of the collected data; inputting the time-corrected linear spectrum into a pre-built neural network anomaly recognition model for recognition, obtaining abnormal operating status data and corresponding abnormal time intervals; performing trend fusion analysis on the abnormal operating status data and corresponding abnormal time intervals of each rocket engine, and calculating the fusion abnormal trend value of the rocket engine. The present application performs fusion analysis on the operating status information of rocket engines collected by multiple sensors, obtains more comprehensive operating status information of rocket engines, more accurately monitors the abnormalities of rocket engines, and reduces the misjudgment rate of rocket engine abnormalities.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for monitoring rocket engine abnormalities. Background Art

[0002] A rocket engine is a jet engine that uses its own propellant (energy) and does not use external air. It can work in space outside the dense atmosphere. The energy is converted into the kinetic energy of the working fluid (working medium) in the rocket engine, forming a high-speed jet discharge to generate thrust. The rocket engine is the core power component of the launch vehicle. Therefore, the reliability of the rocket engine will directly affect the launch and subsequent flight quality of the launch vehicle.

[0003] At present, the engines used in the first stage of domestic rockets are generally 2-machine parallel, 3-machine parallel or 4-machine parallel structures, and they are all started at the same time. However, when the existing 2~4 rocket engines are started at the same time, when one engine fails, the rocket cannot take off and the launch needs to be terminated urgently. In other words, for the method of starting multiple engines in parallel at the same time, the probability of successfully starting all engines at once is reduced due to the increase in the number of engines. Therefore, for the form of multiple engines in parallel, there is still a large risk that the failure of engine start will affect the subsequent flight procedures.

[0004] At present, common engine monitoring methods include: sensor monitoring methods (pressure sensors, temperature sensors, flow sensors, vibration sensors), data analysis methods (time domain analysis, frequency domain analysis, correlation analysis), model comparison methods, and machine learning methods. However, the single sensor monitoring method currently used has problems such as incomplete information and misjudgment. Therefore, how to fuse and analyze the information collected by multiple sensors to obtain more comprehensive rocket engine operating status information, more accurately monitor rocket engine anomalies, and reduce the misjudgment rate of rocket engine anomalies is a technical problem that needs to be solved urgently.

[0005] Therefore, the technical problem that urgently needs to be solved is how to provide a rocket engine abnormality monitoring method and system to integrate and analyze the rocket engine operating status information collected by multiple sensors, obtain more comprehensive rocket engine operating status information, more accurately monitor the rocket engine abnormalities, and reduce the misjudgment rate of rocket engine abnormalities. Summary of the invention

[0006] The purpose of this application is to provide a rocket engine abnormality monitoring method and system, to perform fusion analysis on the rocket engine operating status information collected by multiple sensors, to obtain more comprehensive rocket engine operating status information, to more accurately monitor the rocket engine abnormalities, and to reduce the misjudgment rate of rocket engine abnormalities.

[0007] To achieve the above-mentioned purpose, as a first aspect of the present application, the present application provides a method for monitoring abnormality of a rocket engine, the method comprising the following steps:

[0008] Conduct risk monitoring on the power supply system of the parallel rocket engine. If the risk monitoring passes, the parallel rocket engine is allowed to operate; otherwise, the parallel rocket engine is prohibited from operating;

[0009] If the risk monitoring passes, the operating status data of multiple parallel rocket engines will be collected in real time through various sensors;

[0010] Divide the collected operating status data corresponding to each rocket engine into a group, and generate a linear graph of each type of operating status data changing over time;

[0011] Obtaining the data collection delay time of the sensor corresponding to each type of operating status data, and performing time correction on the horizontal axis of the linear graph of each type of operating status data changing with time based on the data collection delay time;

[0012] The linear graph of each time-corrected operating status data changing with time is input into a pre-built neural network anomaly recognition model for recognition, and the abnormal operating status data and the corresponding abnormal time interval are obtained;

[0013] Perform trend fusion analysis on the abnormal operating status data of each rocket engine and the corresponding abnormal time interval, and calculate the fusion abnormal trend value of the rocket engine.

[0014] The rocket engine abnormality monitoring method as described above, wherein the method further comprises:

[0015] According to the fusion abnormal trend value of each rocket engine, the overall abnormal trend value of the parallel rocket engines is calculated;

[0016] According to the abnormal trend value of the fusion of the rocket engine and the overall abnormal trend value of the parallel rocket engine, an abnormal alarm prompt is issued for the rocket engine.

[0017] The rocket engine abnormality monitoring method as described above, wherein the power supply system of the parallel rocket engine is subjected to risk monitoring, and if the risk monitoring passes, the parallel rocket engine is allowed to operate, otherwise, the parallel rocket engine is prohibited from operating, including:

[0018] The real-time status data of the power supply line of the parallel rocket engine is collected at multiple nodes through multiple power supply line sensors, and the environmental characteristic data of the environment where the multiple nodes of the power supply line are located is collected through environmental sensors;

[0019] Calculate the operation hazard value of the parallel rocket engine power supply line according to the real-time status data at each node of the parallel rocket engine power supply line and the environmental characteristic data of the environment where each node of the power supply line is located;

[0020] Compare the operating hazard value of the parallel rocket engine power supply line with the preset safety threshold. If the operating hazard value of the parallel rocket engine power supply line is greater than the preset safety threshold, the risk monitoring fails; otherwise, the risk monitoring passes.

[0021] The rocket engine abnormality monitoring method as described above, wherein the real-time status data of the parallel rocket engine power supply line is collected at multiple nodes by multiple power supply line sensors, and the environmental characteristic data of the environment where the multiple nodes of the power supply line are located is collected by environmental sensors, including:

[0022] A plurality of power supply line sensors and a plurality of environmental sensors are arranged at a plurality of nodes of a parallel rocket engine power supply line;

[0023] The real-time status data of each node of the power supply line is collected by setting multiple power supply line sensors;

[0024] The environmental characteristic data at each node of the power supply line is collected by setting up multiple environmental sensors.

[0025] The rocket engine abnormality monitoring method as described above, wherein, according to the real-time status data at each node of the parallel rocket engine power supply line and the environmental characteristic data of the environment where each node of the power supply line is located, calculating the operation risk value of the parallel rocket engine power supply line includes:

[0026] According to the real-time status data at each node of the parallel rocket engine power supply line and the state standard threshold range at each node, data of the real-time status data at each node exceeding the state standard threshold range is obtained as the suspicious abnormal data at each node;

[0027] According to the suspicious abnormal data at each node and the environmental characteristic data of the environment where each node is located, the operating hazard value of the parallel rocket engine power supply line is calculated.

[0028] In the above-mentioned rocket engine abnormality monitoring method, the calculation formula of the operation risk value of the parallel rocket engine power supply line is:

[0029] ;

[0030] in, Indicates the operational hazard value of the parallel rocket engine power supply circuit; Indicates the total number of nodes; Indicates The total number of types of suspicious abnormal data collected at each node; Indicates Node The influence weight of the suspicious abnormal data on the operational risk value of the parallel rocket engine power supply line; Indicates Node The measured value of the suspected abnormal data; Indicates Node The standard value of suspicious abnormal data, Indicates Node The allowable deviation value of the suspected abnormal data; Indicates collection of Node The calibration error value of the sensor with suspected abnormal data; Indicates the environmental characteristic data for the collection Node The measurement error influence value of the sensor with suspected abnormal data.

[0031] In the rocket engine abnormality monitoring method as described above, the method of pre-constructing the neural network abnormality recognition model is:

[0032] Acquire multiple sets of operating status data of rocket engines that are known to be working properly;

[0033] Convert multiple sets of operating status data of rocket engines that are known to be working normally into linear graphs that vary with time as training data sets;

[0034] The training data set is input into the basic neural network model for training to obtain a neural network anomaly recognition model.

[0035] The rocket engine abnormality monitoring method as described above, wherein:

[0036] While giving abnormal alarm prompts for the rocket engine, the abnormal alarm center prompts the abnormal operating status data of the rocket engine and the corresponding abnormal time interval.

[0037] As a second aspect of the present application, the present application provides a rocket engine abnormality monitoring system, wherein the rocket engine abnormality monitoring method is executed, and the system includes:

[0038] The power supply risk monitoring module is used to perform risk monitoring on the power supply system of the parallel rocket engine. If the risk monitoring passes, the parallel rocket engine is allowed to run; otherwise, the parallel rocket engine is prohibited from running;

[0039] A data acquisition module is used to collect the operating status data of multiple parallel rocket engines in real time through multiple sensors if the risk monitoring passes;

[0040] A generation module, used to divide the collected operation status data corresponding to each rocket engine into a group, and generate a linear graph of each operation status data changing with time;

[0041] A correction module is used to obtain the data collection delay time of the sensor corresponding to each type of operating status data, and based on the data collection delay time, perform time correction on the horizontal axis of the linear spectrum of each type of operating status data changing with time;

[0042] An acquisition module is used to input the linear graph of each operating state data after time correction with time into a pre-built neural network abnormality recognition model for recognition, and obtain abnormal operating state data and corresponding abnormal time interval;

[0043] The data processor is used to perform trend fusion analysis on the abnormal operation status data of each rocket engine and the corresponding abnormal time interval, and calculate the fusion abnormal trend value of the rocket engine.

[0044] The rocket engine abnormality monitoring system as described above, wherein:

[0045] The data processor is further used to calculate the overall abnormal trend value of the parallel rocket engines based on the fusion abnormal trend value of each rocket engine;

[0046] The system also includes:

[0047] The abnormal alarm center is used to issue abnormal alarm prompts for rocket engines based on the fusion abnormal trend values ​​of the rocket engines and the overall abnormal trend values ​​of the parallel rocket engines.

[0048] The beneficial effects achieved by this application are as follows:

[0049] (1) Different types of sensors in this application can monitor the operating status of rocket engines from multiple angles. Through the coordinated work of multiple sensors, more comprehensive and richer engine status information can be obtained, avoiding the information omission that may occur in a single sensor. Multi-sensor fusion can comprehensively consider multiple parameters such as pressure, temperature, vibration, flow, etc., so as to more accurately judge the overall operating status of the engine.

[0050] (2) The data of each sensor in this application can complement and verify each other. When a sensor detects an abnormal situation, it can be further confirmed by the data of other sensors. The complementarity and verification of data can reduce the possibility of false positives and false negatives and improve the accuracy of abnormal monitoring. Even if a sensor fails or falsely reports, the data of other sensors can provide reference and reduce the impact on the monitoring results.

[0051] (3) The multi-sensor fusion of this application can combine the location information and measurement characteristics of different sensors to more accurately locate the location of the fault. Accurately locating the fault is crucial for timely maintenance and mission safety. Multi-sensor fusion technology can provide more detailed location information for fault diagnosis and improve maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For those skilled in the art, other drawings can also be obtained based on these drawings.

[0053] Figure 1 This is a flow chart of a method for monitoring abnormalities of a rocket engine according to an embodiment of the present application.

[0054] Figure 2 This is a schematic diagram of the structure of a rocket engine abnormality monitoring system according to an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application. Embodiment 1

[0056] like Figure 1 As shown, the present application provides a method for monitoring abnormality of a rocket engine, the method comprising:

[0057] Step S1, performing risk monitoring on the power supply system of the parallel rocket engine. If the risk monitoring passes, the parallel rocket engine is allowed to run, otherwise, the parallel rocket engine is prohibited from running.

[0058] Specifically, the power supply risk monitoring module is used to monitor the power supply system of the parallel rocket engine. If the risk monitoring passes, the parallel rocket engine is allowed to start and run, otherwise, the parallel rocket engine is prohibited from starting and running. The parallel rocket engine includes a plurality of rocket engines arranged in parallel.

[0059] Wherein, step S1 includes the following sub-steps:

[0060] Step S110, collect real-time status data of the parallel rocket engine power supply line at multiple nodes through multiple power supply line sensors, and collect environmental characteristic data of the environment where multiple nodes of the power supply line are located through environmental sensors.

[0061] Specifically, step S110 includes:

[0062] Step S111, setting multiple power supply line sensors and multiple environmental sensors at multiple nodes of the parallel rocket engine power supply line.

[0063] The power supply line sensor is, for example, a voltage sensor, a current sensor, etc. The environmental sensor is, for example, a temperature sensor, a vibration sensor, a humidity sensor, etc.

[0064] Among them, multiple nodes are located at multiple key positions of the rocket engine power supply line, such as: power output end (mainly monitoring the total voltage and total current of the power output to ensure that the output power parameters are within the range required for engine startup or operation, and to prevent excessive voltage or low voltage from affecting the operation of the rocket engine), key equipment access point (for example, ignition equipment access point), line branch point or connection point, etc. Line branch points and connection points are prone to problems such as poor contact and excessive resistance. Monitoring the voltage changes of these nodes can timely detect line connection faults and avoid power transmission interruptions or instability caused by line problems.

[0065] Step S112: collecting real-time status data at each node of the power supply line through multiple power supply line sensors.

[0066] Among them, the real-time status data of the rocket engine power supply line includes: the voltage or current of the power supply line, etc.

[0067] Step S113, collecting environmental characteristic data at each node of the power supply line through multiple environmental sensors.

[0068] The environmental characteristic data of the environment where the power supply line is located include: temperature, vibration amplitude or humidity of the environment where the power supply line is located.

[0069] Step S120, calculating the operating risk value of the parallel rocket engine power supply line based on the real-time status data at each node of the parallel rocket engine power supply line and the environmental characteristic data of the environment where each node of the power supply line is located.

[0070] Wherein, step S120 includes the following steps:

[0071] Step S121, based on the real-time status data at each node of the parallel rocket engine power supply line and the status standard threshold range at each node, obtain the data of the real-time status data at each node that exceeds the status standard threshold range as the suspicious abnormal data at each node.

[0072] Among them, the state standard threshold range is expressed as: ;in, Indicates the allowable deviation value.

[0073] Step S122, calculating the operating risk value of the parallel rocket engine power supply line based on the suspicious abnormal data at each node and the environmental characteristic data of the environment where each node is located.

[0074] Specifically, the operational risk value of the parallel rocket engine power supply line is calculated regularly or in real time based on the suspicious abnormal data at each node and the environmental characteristic data of the environment where each node is located.

[0075] Among them, the calculation formula for the operating hazard value of the parallel rocket engine power supply line is:

[0076] ;

[0077] in, ;

[0078] in, Indicates the operational hazard value of the parallel rocket engine power supply circuit; Indicates the total number of nodes; Indicates The total number of types of suspicious abnormal data collected at each node; Indicates Node The influence weight of the suspicious abnormal data on the operational risk value of the parallel rocket engine power supply line; Indicates Node The measured value of the suspected abnormal data; Indicates Node The standard value of suspicious abnormal data, Indicates Node The allowable deviation value of the suspected abnormal data; Indicates collection of Node The calibration error value of the sensor with suspected abnormal data; Indicates the environmental characteristic data for the collection Node The measurement error influence value of the sensor with suspected abnormal data. Symbol Represents the absolute value symbol.

[0079] in, Indicates The total number of types of environmental characteristic data collected at each node; Indicates The environmental characteristics data are Influencing factors of sensor measurement errors at each node; Indicates The measured values ​​of various environmental characteristic data; Indicates the sensor is Calibration limit values ​​for various environmental characteristic data.

[0080] Step S130, compare the operating hazard value of the parallel rocket engine power supply circuit with the preset safety threshold. If the operating hazard value of the parallel rocket engine power supply circuit is greater than the preset safety threshold, the risk monitoring fails, the power supply circuit of the parallel rocket engine is inspected and maintained, and the parallel rocket engine is prohibited from starting. Otherwise, the risk monitoring passes, there is no need to inspect the power supply circuit of the parallel rocket engine, and the parallel rocket engine is allowed to start and run.

[0081] Step S2: If the risk monitoring passes, the operating status data of multiple parallel rocket engines are collected in real time through multiple sensors.

[0082] It should be explained that a parallel rocket engine is a rocket engine with greater thrust, which is composed of multiple rocket engines with their longitudinal axes parallel to each other and mounted on a common frame. Each engine in the parallel rocket engine is connected to a different fuel tank to make it work separately. If one of the rocket engines is abnormal, the entire parallel rocket engine will not be able to release the thrust that meets the predetermined requirements, resulting in the failure of the rocket launch or flight.

[0083] Each rocket engine in the parallel rocket engine is provided with a corresponding plurality of sensors to collect the operating status data of each rocket engine and monitor the operating status of each rocket engine.

[0084] Among them, the types of rocket engine operating status data include: rocket engine flow, engine pressure, engine temperature, engine vibration amplitude, engine noise value, engine power supply voltage, etc.

[0085] Among them, a variety of sensors are defined as A1, A2, A3, A4, A5, A6, etc. Sensors A1, A2, A3, A4, A5, and A6 collect rocket engine flow, engine pressure, engine temperature, engine vibration amplitude, engine noise value, and engine power supply voltage, respectively.

[0086] Among them, sensors A1, A2, A3, A4, A5, and A6 are different types of sensors, and the delay time of data collection varies due to different sensor types and settings. Therefore, the delay time of data collection of sensors A1, A2, A3, A4, A5, and A6 is defined as TA1, TA2, TA3, TA4, TA5, and TA6.

[0087] Step S3, dividing the collected operating status data corresponding to each rocket engine into a group, and generating a linear graph of each type of operating status data changing with time for each rocket engine.

[0088] The horizontal axis (X-axis) of the linear graph is time, and the vertical axis (Y-axis) is the value of the operating status data.

[0089] Step S4, obtaining the data collection delay time of the sensor corresponding to each type of operating status data, and performing time correction on the horizontal axis of the linear graph of each type of operating status data changing with time based on the data collection delay time.

[0090] As an example, the time correction of the horizontal axis of the linear graph of the rocket engine flow rate changing with time is performed as follows: sensor A1 collects the rocket engine flow rate. Sensor A1 is the engine flow meter. The delay time of the collected data of sensor A1 is TA1. The linear graph of the rocket engine flow rate changing with time collected by sensor A1 is moved along the horizontal axis (X-axis) by a distance TA1 in the negative direction (negative direction of the X-axis).

[0091] As an example, the time correction of the horizontal axis of the linear graph of engine pressure changes with time is performed as follows: sensor A2 collects engine pressure, sensor A2 is an engine pressure sensor, and the delay time of sensor A2's collected data is TA2. The linear graph of engine pressure changes with time collected by sensor A2 is moved as a whole along the horizontal axis (X-axis) in the negative direction (negative direction of the X-axis) by a distance of TA2.

[0092] Step S5, inputting the linear graph of each type of operating status data changing with time after time correction into a pre-built neural network abnormality recognition model for recognition, and obtaining abnormal operating status data and corresponding abnormal time interval.

[0093] It needs to be explained that the present application performs time correction on the horizontal axis of the linear graph of each type of operating status data changing with time, thereby eliminating the influence of the delay time of sensor data acquisition on the real-time acquired operating status data. Therefore, in the process of fusion analysis of data acquired by multiple sensors, the analysis error caused by the difference in operating status data acquisition time due to the different delay times of different sensor data acquisition is avoided, the accuracy of the fusion analysis of the operating status data is improved, and then the accuracy and reliability of the abnormal prediction or abnormal judgment of the rocket engine is improved.

[0094] Among them, the method of pre-built neural network anomaly recognition model is:

[0095] S510, obtaining multiple sets of operating status data of rocket engines that are known to be operating normally.

[0096] Among them, the multiple groups of rocket engines known to be working normally are rocket engines in the parallel rocket engines. And the multiple groups of operating status data of rocket engines that have been working normally include the operating status data of each rocket engine in the parallel rocket engines. And the operating status data of each rocket engine includes multiple groups. Therefore, the trained neural network anomaly recognition model can recognize the operating status data of each rocket engine in the parallel rocket engines.

[0097] S520, converting multiple sets of operating status data of rocket engines known to be operating normally into linear graphs that vary with time as training data sets;

[0098] S530, input the training data set into the basic neural network model for training to obtain a neural network anomaly recognition model. The neural network anomaly recognition model is used to identify the linear graph of the input rocket engine operation status data changing with time, and obtain abnormal data, wherein the abnormal data includes the abnormal operation status data of the rocket engine and the corresponding abnormal time interval.

[0099] Specifically, the present application uses existing technology to input the training data set into the basic neural network model for training, which will not be described in detail here.

[0100] Step S6, performing trend fusion analysis on the abnormal operation status data of each rocket engine and the corresponding abnormal time interval, and calculating the fusion abnormal trend value of each rocket engine.

[0101] Among them, the calculation formula of the fusion anomaly trend value of the rocket engine is:

[0102] ;

[0103] ;

[0104] ;

[0105] ;

[0106] ;

[0107] in, Indicates the fusion anomaly trend value of the rocket engine; Indicates the fusion abnormal impact factor of abnormal operation status data; Indicates the initial sampling time of the rocket engine's operating status data; No. The total number of types of abnormal operating status data of rocket engines occurring at any moment; Indicates the end time of sampling of the rocket engine's operating status data; Represents parameters; Indicates the number of abnormal time intervals in which at least two abnormal operating status data occur within a certain abnormal time interval; Indicates that at least two abnormal operation status data have occurred. The number of types of abnormal operation status data that occurred in the abnormal time interval; Indicates The duration of the abnormal time interval; Indicates The first abnormal time interval Abnormal impact weights of abnormal operation status data; Indicates The first abnormal time interval The measured average value of abnormal operation status data; Indicates The first abnormal time interval Standard value of abnormal operation status data; Indicates the influence factor of rocket engine abnormal operation status data trend ; Indicates the total number of segments of abnormal operating status data of rocket engines (the continuous abnormality of operating status data in a continuous time period is regarded as a segment); Indicates Abnormal impact weight of abnormal operation status data of each section; Rocket engine The maximum value of abnormal operation status data of each segment, Rocket engine The minimum value of abnormal operation status data of each segment, Indicates that from the rocket engine The time it takes for the abnormal operation status data of each segment to change from the minimum value to the maximum value.

[0108] As an example, the linear graph of each time-corrected running state data changing with time is identified through the pre-built neural network abnormality recognition model, and the abnormal running state data and the corresponding abnormal time intervals are obtained, including: the engine temperature rises from C1 to C2 from t1 to t2, abnormally rising, and maintains the temperature of C2 from t2 to t5, and both C1 and C2 exceed the standard limit Cb, the engine vibration amplitude rises from Z1 to Z2 from t2 to t3, and both Z1 and Z2 exceed the standard limit Zb, and maintains the vibration amplitude of Z2 from t3 to t5. The engine noise value rises from F1 to F2 from t2 to t3, and both F1 and F2 exceed the standard limit Fb, and the engine noise value of F2 is maintained from t3 to t5.

[0109] The present application calculates the fusion anomaly trend value of the rocket engine, improves the calculation accuracy and reliability of the rocket engine anomaly, thereby accurately predicting the rocket engine anomaly and providing timely alarm reminders, which is conducive to timely correction of the rocket engine anomaly and improving the reliability of the rocket engine operation.

[0110] Step S7, calculating the overall abnormal trend value of the parallel rocket engines according to the fusion abnormal trend value of each rocket engine.

[0111] Among them, the calculation formula for the overall abnormal trend value of the parallel rocket engine is as follows:

[0112] ;

[0113] in, represents the number of rocket engines in a parallel rocket engine; Indicates The fusion anomaly trend value of a rocket engine.

[0114] Step S8, according to the fusion abnormal trend value of the rocket engine and the overall abnormal trend value of the parallel rocket engine, an abnormal alarm prompt is issued for the rocket engine.

[0115] Specifically, according to the fusion abnormality trend value of the rocket engine and the overall abnormality trend value of the parallel rocket engines, the abnormal alarm prompt for the rocket engine includes: comparing the fusion abnormality trend value of the rocket engine with the preset abnormality trend threshold value; if the fusion abnormality trend value of the rocket engine is greater than the preset abnormality trend threshold value, an abnormal alarm prompt is given to the rocket engine, and the fusion abnormality trend value of the rocket engine and the overall abnormality trend value of the parallel rocket engines are prompted, so that the management personnel can understand the abnormal situation of the rocket engine according to the fusion abnormality trend value of the rocket engine and the overall abnormality trend value of the parallel rocket engines, and repair the rocket engine in a timely and targeted manner; otherwise, there is no need to give an abnormal alarm prompt for the rocket engine.

[0116] Specifically, while the abnormal alarm prompts the rocket engine, the abnormal alarm center prompts the abnormal operation status data of the rocket engine and the corresponding abnormal time interval.

[0117] Embodiment 2

[0118] like Figure 2 As shown, the present application provides a rocket engine abnormality monitoring system 100, which executes a rocket engine abnormality monitoring method, and the system includes:

[0119] The power supply risk monitoring module 10 is used to perform risk monitoring on the power supply system of the parallel rocket engine. If the risk monitoring passes, the parallel rocket engine is allowed to run, otherwise, the parallel rocket engine is prohibited from running.

[0120] The data acquisition module 20 is used to collect the operating status data of multiple parallel rocket engines in real time through multiple sensors if the risk monitoring passes.

[0121] The generating module 30 is used to divide the collected operating status data corresponding to each rocket engine into a group, and generate a linear graph of each operating status data changing with time.

[0122] The correction module 40 is used to obtain the data collection delay time of the sensor corresponding to each type of operating status data, and based on the data collection delay time, perform time correction on the horizontal axis of the linear graph of each type of operating status data changing with time.

[0123] The acquisition module 50 is used to input the linear graph of each time-corrected operating status data changing with time into a pre-built neural network abnormality recognition model for recognition, and obtain abnormal operating status data and corresponding abnormal time interval.

[0124] The data processor 60 is used to perform trend fusion analysis on the abnormal operation status data of each rocket engine and the corresponding abnormal time interval, and calculate the fusion abnormal trend value of the rocket engine.

[0125] Among them, the calculation formula of the fusion anomaly trend value of the rocket engine is:

[0126] ;

[0127] ;

[0128] ;

[0129] ;

[0130] ;

[0131] in, Indicates the fusion anomaly trend value of the rocket engine; Indicates the fusion abnormal impact factor of abnormal operation status data; Indicates the initial sampling time of the rocket engine's operating status data; No. The total number of types of abnormal operating status data of rocket engines occurring at any moment; Indicates the end time of sampling of the rocket engine's operating status data; Represents parameters; Indicates the number of abnormal time intervals in which at least two abnormal operating status data occur within a certain abnormal time interval; Indicates that at least two abnormal operation status data have occurred. The number of types of abnormal operation status data that occurred in the abnormal time interval; Indicates The duration of the abnormal time interval; Indicates The first abnormal time interval Abnormal impact weights of abnormal operation status data; Indicates The first abnormal time interval The measured average value of abnormal operation status data; Indicates The first abnormal time interval Standard value of abnormal operation status data; Indicates the influence factor of rocket engine abnormal operation status data trend ; Indicates the total number of segments of abnormal operating status data of rocket engines (the continuous abnormality of operating status data in a continuous time period is regarded as a segment); Indicates Abnormal impact weight of abnormal operation status data of each section; Rocket engine The maximum value of abnormal operation status data of each segment, Rocket engine The minimum value of abnormal operation status data of each segment, Indicates that from the rocket engine The time it takes for the abnormal operation status data of each segment to change from the minimum value to the maximum value.

[0132] The data processor 60 is further used to calculate the overall abnormal trend value of the parallel rocket engines according to the fusion abnormal trend value of each rocket engine.

[0133] Among them, the calculation formula for the overall abnormal trend value of the parallel rocket engine is as follows:

[0134] ;

[0135] in, represents the number of rocket engines in a parallel rocket engine; Indicates The fusion anomaly trend value of a rocket engine.

[0136] The system 100 further includes:

[0137] The abnormal alarm center 70 is used to issue abnormal alarm prompts for the rocket engine based on the fusion abnormal trend value of the rocket engine and the overall abnormal trend value of the parallel rocket engine.

[0138] Specifically, according to the fusion abnormality trend value of the rocket engine and the overall abnormality trend value of the parallel rocket engines, the abnormal alarm prompt for the rocket engine includes: comparing the fusion abnormality trend value of the rocket engine with the preset abnormality trend threshold value; if the fusion abnormality trend value of the rocket engine is greater than the preset abnormality trend threshold value, an abnormal alarm prompt is given to the rocket engine, and the fusion abnormality trend value of the rocket engine and the overall abnormality trend value of the parallel rocket engines are prompted, so that the management personnel can understand the abnormal situation of the rocket engine according to the fusion abnormality trend value of the rocket engine and the overall abnormality trend value of the parallel rocket engines, and repair the rocket engine in a timely and targeted manner; otherwise, there is no need to give an abnormal alarm prompt for the rocket engine.

[0139] The present application also provides a computer storage medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the address mapping method of the large-capacity solid-state hard disk. The computer storage medium contains one or more program instructions, and the one or more program instructions are used by the processor to execute a rocket engine abnormality monitoring method.

[0140] The embodiment disclosed in the present invention provides a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned rocket engine abnormality monitoring method.

[0141] An embodiment of the present invention provides a processor for processing the above-mentioned rocket engine abnormality monitoring method.

[0142] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0143] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0144] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0145] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct RAM bus random access memory (DRRAM).

[0146] The beneficial effects achieved by this application are as follows:

[0147] (1) Different types of sensors in this application can monitor the operating status of rocket engines from multiple angles. Through the coordinated work of multiple sensors, more comprehensive and richer engine status information can be obtained, avoiding the information omission that may occur in a single sensor. Multi-sensor fusion can comprehensively consider multiple parameters such as pressure, temperature, vibration, flow, etc., so as to more accurately judge the overall operating status of the engine.

[0148] (2) The data of each sensor in this application can complement and verify each other. When a sensor detects an abnormal situation, it can be further confirmed by the data of other sensors. The complementarity and verification of data can reduce the possibility of false positives and false negatives and improve the accuracy of abnormal monitoring. Even if a sensor fails or falsely reports, the data of other sensors can provide reference and reduce the impact on the monitoring results.

[0149] (3) The multi-sensor fusion of this application can combine the location information and measurement characteristics of different sensors to more accurately locate the location of the fault. Accurately locating the fault is crucial for timely maintenance and mission safety. Multi-sensor fusion technology can provide more detailed location information for fault diagnosis and improve maintenance efficiency.

[0150] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0151] In the description of the present application, the word "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0152] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for monitoring abnormality of a rocket engine, characterized in that: The method comprises the following steps: Conduct risk monitoring on the power supply system of the parallel rocket engine. If the risk monitoring passes, the parallel rocket engine is allowed to operate; otherwise, the parallel rocket engine is prohibited from operating; If the risk monitoring passes, the operating status data of multiple parallel rocket engines will be collected in real time through various sensors; Divide the collected operating status data corresponding to each rocket engine into a group, and generate a linear graph of each type of operating status data changing over time; Obtaining the data collection delay time of the sensor corresponding to each type of operating status data, and performing time correction on the horizontal axis of the linear graph of each type of operating status data changing with time based on the data collection delay time; The linear graph of each time-corrected operating status data changing with time is input into a pre-built neural network anomaly recognition model for recognition, and the abnormal operating status data and the corresponding abnormal time interval are obtained; Perform trend fusion analysis on the abnormal operation status data of each rocket engine and the corresponding abnormal time interval, and calculate the fusion abnormal trend value of the rocket engine; Conduct risk monitoring on the power supply system of the parallel rocket engine. If the risk monitoring passes, the parallel rocket engine is allowed to operate. Otherwise, the parallel rocket engine is prohibited from operating, including: The real-time status data of the power supply line of the parallel rocket engine is collected at multiple nodes through multiple power supply line sensors, and the environmental characteristic data of the environment where the multiple nodes of the power supply line are located is collected through environmental sensors; Calculate the operation hazard value of the parallel rocket engine power supply line according to the real-time status data at each node of the parallel rocket engine power supply line and the environmental characteristic data of the environment where each node of the power supply line is located; Compare the operating hazard value of the parallel rocket engine power supply line with the preset safety threshold. If the operating hazard value of the parallel rocket engine power supply line is greater than the preset safety threshold, the risk monitoring fails; otherwise, the risk monitoring passes.

2. The method for monitoring abnormality of a rocket engine according to claim 1, characterized in that: The method further includes: According to the fusion abnormal trend value of each rocket engine, the overall abnormal trend value of the parallel rocket engines is calculated; According to the abnormal trend value of the fusion of the rocket engine and the overall abnormal trend value of the parallel rocket engine, an abnormal alarm prompt is issued for the rocket engine.

3. The rocket engine abnormality monitoring method according to claim 1, characterized in that: The real-time status data of the parallel rocket engine power supply line is collected at multiple nodes through multiple power supply line sensors, and the environmental characteristic data of the environment where multiple nodes of the power supply line are located is collected through environmental sensors, including: A plurality of power supply line sensors and a plurality of environmental sensors are arranged at a plurality of nodes of a parallel rocket engine power supply line; The real-time status data of each node of the power supply line is collected by setting multiple power supply line sensors; The environmental characteristic data at each node of the power supply line is collected by setting up multiple environmental sensors.

4. The method for monitoring abnormality of a rocket engine according to claim 1, characterized in that: According to the real-time status data of each node of the parallel rocket engine power supply line and the environmental characteristic data of the environment where each node of the power supply line is located, the operation risk value of the parallel rocket engine power supply line is calculated including: According to the real-time status data at each node of the parallel rocket engine power supply line and the state standard threshold range at each node, data of the real-time status data at each node exceeding the state standard threshold range is obtained as the suspicious abnormal data at each node; According to the suspicious abnormal data at each node and the environmental characteristic data of the environment where each node is located, the operating hazard value of the parallel rocket engine power supply line is calculated.

5. The method for monitoring abnormality of a rocket engine according to claim 4, characterized in that: in, The calculation formula for the operational hazard value of the parallel rocket engine power supply line is: ； in, Indicates the operational hazard value of the parallel rocket engine power supply circuit; Indicates the total number of nodes; Indicates The total number of types of suspicious abnormal data collected at each node; Indicates Node The influence weight of the suspicious abnormal data on the operational risk value of the parallel rocket engine power supply line; Indicates Node The measured value of the suspected abnormal data; Indicates Node The standard value of suspicious abnormal data, Indicates Node The allowable deviation value of the suspected abnormal data; Indicates collection of Node The calibration error value of the sensor with suspected abnormal data; Indicates the environmental characteristic data for the collection Node The measurement error influence value of the sensor with suspected abnormal data.

6. The method for monitoring abnormality of a rocket engine according to claim 1, characterized in that: The methods of the pre-built neural network anomaly recognition model are: Acquire multiple sets of operating status data of rocket engines that are known to be working properly; Convert multiple sets of operating status data of rocket engines that are known to be working normally into linear graphs that vary with time as training data sets; The training data set is input into the basic neural network model for training to obtain a neural network anomaly recognition model.

7. The method for monitoring abnormality of a rocket engine according to claim 2, characterized in that: While giving abnormal alarm prompts for the rocket engine, the abnormal alarm center prompts the abnormal operating status data of the rocket engine and the corresponding abnormal time interval.

8. A rocket engine abnormality monitoring system, characterized in that: The method according to any one of claims 1 to 7 is implemented, the system comprising: The power supply risk monitoring module is used to perform risk monitoring on the power supply system of the parallel rocket engine. If the risk monitoring passes, the parallel rocket engine is allowed to run; otherwise, the parallel rocket engine is prohibited from running; A data acquisition module is used to collect the operating status data of multiple parallel rocket engines in real time through multiple sensors if the risk monitoring passes; A generation module, used to divide the collected operation status data corresponding to each rocket engine into a group, and generate a linear graph of each operation status data changing with time; A correction module is used to obtain the data collection delay time of the sensor corresponding to each type of operating status data, and based on the data collection delay time, perform time correction on the horizontal axis of the linear spectrum of each type of operating status data changing with time; An acquisition module is used to input the linear graph of each operating state data after time correction with time into a pre-built neural network abnormality recognition model for recognition, and obtain abnormal operating state data and corresponding abnormal time interval; The data processor is used to perform trend fusion analysis on the abnormal operation status data of each rocket engine and the corresponding abnormal time interval, and calculate the fusion abnormal trend value of the rocket engine.

9. The rocket engine abnormality monitoring system according to claim 8, characterized in that: The data processor is further used to calculate the overall abnormal trend value of the parallel rocket engines based on the fusion abnormal trend value of each rocket engine; The system also includes: The abnormal alarm center is used to issue abnormal alarm prompts for rocket engines based on the fusion abnormal trend values ​​of the rocket engines and the overall abnormal trend values ​​of the parallel rocket engines.

Images