Automatic test method, system and equipment for aircraft power system and storage medium

Abstract

The invention relates to the technical field of aircraft power system testing, in particular to an aircraft power system automatic testing method, system and device and a storage medium, and the method comprises the steps: obtaining detection data correspondingly collected by a plurality of data collection terminals; analyzing and processing the detection data, and judging whether the detection data is in a normal range or not; if the detection data is within the normal range, analyzing the data change trend of the detection data under different test conditions according to preset program logic; and if the detection data or the data change trend is not in a normal range, triggering a safety monitoring mechanism and generating an abnormal record. The method has the effect of improving the testing efficiency of the aircraft power system.

Description

Technical Field

[0001] The present application relates to the technical field of aircraft power system testing, and in particular to an automatic testing method, system, equipment and storage medium for an aircraft power system. Background Art

[0002] In the process of research and development, production and maintenance of aircraft power systems, it is crucial to conduct comprehensive and accurate testing of their performance. Traditional testing methods rely on manual operations to a certain extent, such as manually collecting data from various sensors, which is not only inefficient, but also faces complex situations in power system tests, such as high-speed rotating propellers. There are great safety risks in manual intervention. At the same time, manual judgment of data and fault diagnosis are easily affected by subjective factors, resulting in a high error rate, making it difficult to ensure the accuracy and reliability of test results. In addition, traditional testing methods have poor flexibility when dealing with a variety of test conditions, and it is difficult to achieve fast and accurate condition switching and data collection. These problems seriously restrict the efficiency and quality of aircraft power system testing, and there is an urgent need for a more advanced and more automated testing method and related technical means to solve the above problems.

[0003] At present, with the continuous development of science and technology, automated testing technology has gradually been applied in various fields, but in the field of aircraft power system testing, related technologies still need to be further optimized and improved to meet the growing aircraft performance requirements and safety standards. Especially in the testing of key performance indicators such as electrical transmission, electromagnetic compatibility, and mechanical structure, how to achieve efficient, accurate, and safe automated testing has become an important direction for the development of current aircraft power system testing technology. Summary of the invention

[0004] The purpose of this application is to provide an automatic testing method, system, device and storage medium for an aircraft power system, aiming to solve the problem of low testing efficiency in existing aircraft power system testing.

[0005] The first object of this application is to provide an automatic test method for an aircraft power system, comprising: Obtaining detection data collected by multiple data collection terminals; Analyze and process the detection data to determine whether the detection data is within a normal range; If the test data is within the normal range, then according to the preset program logic, the data change trend of the test data under different test conditions is analyzed; If the detection data or the data change trend is not within the normal range, the safety monitoring mechanism is triggered and an abnormal record is generated.

[0006] By adopting the above technical solutions, a high degree of automation of the test process is achieved, which effectively solves the safety hazards caused by manual operation close to high-speed rotating parts and improves the safety of the test environment; precise data collection and intelligent analysis and processing mechanisms improve the accuracy of data judgment, reduce the error rate, and can more accurately judge the operating status of the power system; analysis of data change trends under different test conditions helps to gain an in-depth understanding of the performance of the power system under various conditions, providing a strong basis for optimizing the design; the safety monitoring mechanism and abnormal recording function can promptly detect and handle abnormal situations, reduce the risk of equipment damage, and provide detailed reference information for troubleshooting and subsequent improvements, which comprehensively improves the reliability, efficiency and scientificity of aircraft power system testing.

[0007] In a possible implementation manner of the present application, the step of acquiring detection data correspondingly collected by multiple data collection terminals includes: Collect temperature data of power motors, propellers and related components through temperature sensors; The speed data of the propeller or the power motor is collected through the speed sensor; Collect torque data of the power system through a torque sensor; Collect sound data during the test process through sound sensors; Monitor the smoke conditions in the test environment through smoke sensors; Monitor the vibration of the power system through vibration sensors; Collect voltage data of the motor controller through a voltage probe; Collect current data of the motor controller through the current probe; Analyze the power data of the power system through the power analyzer; Establish an intelligent collaboration mechanism among sensors to achieve collaborative processing and interactive verification of data; Using multi-source data fusion algorithms, the raw data from different sensors are deeply fused and processed to generate a data packet containing comprehensive status information of the power system; Establish a distributed storage architecture to classify, store and manage received data packets.

[0008] By adopting the above technical solutions, the diversified sensor layout realizes the accurate collection of all-round physical parameters of the power motor, propeller and related components, providing a rich data basis for the comprehensive evaluation of the power system status; the intelligent collaboration mechanism between sensors promotes data collaborative processing and interactive verification, further improving data accuracy and reliability; the multi-source data fusion algorithm can deeply explore the inherent connection of the data, and the generated comprehensive status information data packet can accurately reflect the actual operating status of the power system; the distributed storage architecture facilitates efficient classification and management of data, and facilitates data traceability and subsequent analysis, thereby providing strong support for performance analysis, fault diagnosis and optimization design of the aircraft power system, ensuring that the entire test process is carried out scientifically, efficiently and orderly, and effectively improving the overall test level and quality of the aircraft power system.

[0009] In a possible implementation manner of the present application, the step of analyzing the data change trend of the detection data under different test conditions includes: Obtain the design parameters, performance indicators and a large amount of historical test data of the aircraft power system, and build a multi-dimensional test condition simulation model; According to a preset test plan, a specific working condition combination is selected from the multi-dimensional test working condition simulation model, and related equipment is automatically controlled to realize the switching of the test working conditions; Under each test condition, continuously collecting the detection data transmitted by the data collection terminal; Using data mining and machine learning algorithms to conduct in-depth analysis of the collected detection data; Based on the analysis results of the data change trend of the detection data under different test conditions, a power system performance evaluation report is generated.

[0010] By adopting the above technical solutions, the multi-dimensional test condition simulation model constructed based on the design parameters, performance indicators and historical test data of the aircraft power system can highly simulate the actual complex conditions, making the test more comprehensive and realistic; the automatic control equipment can realize precise switching of working conditions and continuously collect data, which greatly improves the test efficiency and data integrity; the use of data mining and machine learning algorithms for in-depth analysis can effectively explore the inherent laws and potential problems of the data, providing a scientific basis for performance evaluation; the performance evaluation report finally generated can intuitively present the performance of the power system under different conditions, provide strong guidance for optimizing design, performance improvement and fault prediction, and effectively promote the development of aircraft power systems in a more efficient and reliable direction, enhancing the overall performance and safety of aircraft.

[0011] In a possible implementation manner of the present application, according to the analysis results of the change trend of the detection data under different test conditions, the step of generating the power system performance evaluation report further includes: Obtain real-time data change trends and power system performance evaluation information; Dynamically adjust the test conditions and data collection strategy according to the real-time data change trend and power system performance evaluation information; Generate real-time feedback information based on the test conditions and data acquisition strategy, and send the real-time feedback information to the data acquisition terminal, so that the data acquisition terminal can automatically adjust the acquisition accuracy and range according to actual conditions; Establishing a predictive maintenance model for the power system using the historical test data and the machine learning algorithm; Based on the current detection data and the data change trend, possible failures and performance degradation trends of the power system are predicted, and maintenance warning information is issued in advance.

[0012] By adopting the above-mentioned technical solutions, data change trends and performance evaluation information can be obtained in real time, and the test conditions and data collection strategies can be dynamically adjusted accordingly, thus realizing intelligent adaptive optimization of the test process and ensuring the acquisition of the most valuable data; real-time feedback information is sent to the data acquisition terminal to automatically adjust its accuracy and range, further improving the accuracy and effectiveness of data collection; a predictive maintenance model is established using historical test data and machine learning algorithms, and the current detection data and trends are combined to predict faults and performance degradation trends, which can issue maintenance warning information in advance, effectively avoid the occurrence of potential faults, reduce maintenance costs, extend the service life of the power system, and greatly improve the reliability, stability and safety of the aircraft power system operation, providing a solid guarantee for the efficient and safe operation of the aircraft.

[0013] In a possible implementation of the present application, if the detection data and the data change trend are not within a normal range, the step of triggering a safety monitoring mechanism and generating an abnormal record includes: When it is detected that the detection data and the data change trend are not within the normal range, the abnormal situation is classified and evaluated to determine the severity of the abnormality, which is divided into slight abnormality, moderate abnormality and severe abnormality; Based on the minor anomaly, a warning message is issued; Based on the moderate anomaly, automatically adjusting the test conditions until the detection data and the data trend are within a normal range; Based on the serious anomaly, trigger an emergency shutdown procedure and send a control signal to relevant safety equipment; Record the time when the abnormality occurred, the specific value of the abnormal data, the corresponding test condition parameters and the response measures taken, and generate an abnormal record report.

[0014] By adopting the above technical solution, abnormal situations can be classified and evaluated, the severity of the abnormality can be accurately judged, and different response measures can be taken in a targeted manner, thereby improving processing efficiency and accuracy; warning information is issued in case of minor abnormalities, so that relevant personnel can pay attention in time and take preventive measures to avoid abnormal deterioration; moderate abnormalities automatically adjust the test conditions, reflecting the system's self-repair and optimization capabilities, ensuring continuous testing and reliable data; serious abnormalities trigger emergency shutdown and safety equipment linkage, effectively preventing accidents and protecting personnel and equipment safety; detailed records of abnormal information generate reports, which provide a comprehensive and detailed basis for subsequent fault analysis and system improvement, and help to continuously improve the aircraft power system test process and enhance the overall stability and safety of the system.

[0015] In a possible implementation of the present application, if the detection data or the data change trend is not within a normal range, the steps after triggering the safety monitoring mechanism and generating an abnormal record include: Conducting an in-depth analysis of the abnormal records in the abnormal record report, and determining possible causes of the abnormalities corresponding to the abnormal records in combination with historical abnormal data and the operating status of the current aircraft power system; Generate temporary response strategies and long-term solution recommendations based on the severity of the anomaly and the possible causes of the anomaly; The status record of the aircraft power system is updated, and the abnormal record and the processing process information thereof are recorded and stored.

[0016] By adopting the above technical solutions, in-depth analysis of exception records and combining historical data with current operating status to determine possible causes can help accurately locate the root cause of the problem and provide a solid foundation for subsequent effective resolution of the exception; generating temporary and long-term solution suggestions based on the severity and cause of the exception can not only quickly respond to exceptions in the short term to ensure basic system operation, but also optimize and improve the system from a long-term perspective to improve the overall performance and reliability of the system; updating status records and storing exception handling information for easy traceability and review, which helps to accumulate experience and optimize test processes, and provide strong data support and decision-making basis for the continuous optimization, efficient operation and future research and development of aircraft power systems, thereby promoting the continuous advancement of aircraft power system technology.

[0017] In a possible implementation manner of the present application, the method further includes: Obtaining information on changes in environmental parameters outside the aircraft power system; Obtain feedback data from the aircraft power system during actual operation; Combining the environmental parameter change information with the detection data to analyze the impact of environmental factors on the performance of the aircraft power system to obtain test results; Verifying and calibrating the test results using the feedback data from actual operation; Output analysis report on the impact of environmental factors on aircraft power system performance; Output a comparison report of the test result and the feedback data.

[0018] By adopting the above technical solutions, the information on changes in external environmental parameters is obtained and combined with the detection data, which can deeply explore the impact of environmental factors on the performance of the power system, make the test results more in line with the actual operation scenario, and enhance the authenticity and effectiveness of the test; introduce actual operation feedback data for verification and calibration, which further improves the accuracy and reliability of the test results, and provides a more solid basis for the performance evaluation of the power system; the output environmental factor impact analysis report helps to deeply understand the relationship between the environment and system performance, and provide guidance for optimizing system design and operating environment; the comparison report of test results and feedback data clearly presents the difference between the two, which is convenient for discovering potential problems and improving test methods and power systems in a targeted manner, thereby comprehensively improving the performance, stability and adaptability of the aircraft power system, and ensuring the safe and efficient operation of the aircraft in complex and changing environments.

[0019] The second purpose of this application is to provide an automatic test system for an aircraft power system, the system comprising: Detection data acquisition module: obtains the detection data collected by multiple data acquisition terminals; Detection data processing module: analyzes and processes the detection data to determine whether the detection data is within a normal range; Data change trend analysis module: if the test data is within the normal range, the data change trend of the test data under different test conditions is analyzed according to the preset program logic; Abnormal record generation module: If the detection data or the data change trend is not within the normal range, the safety monitoring mechanism is triggered and an abnormal record is generated.

[0020] By adopting the above technical solutions, a high degree of automation of the test process is achieved, which effectively solves the safety hazards caused by manual operation close to high-speed rotating parts and improves the safety of the test environment; precise data collection and intelligent analysis and processing mechanisms improve the accuracy of data judgment, reduce the error rate, and can more accurately judge the operating status of the power system; analysis of data change trends under different test conditions helps to gain an in-depth understanding of the performance of the power system under various conditions, providing a strong basis for optimizing the design; the safety monitoring mechanism and abnormal recording function can promptly detect and handle abnormal situations, reduce the risk of equipment damage, and provide detailed reference information for troubleshooting and subsequent improvements, which comprehensively improves the reliability, efficiency and scientificity of aircraft power system testing.

[0021] The third object of this application is to provide an automatic test device for an aircraft power system, the device comprising: A memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the above-mentioned aircraft power system automatic testing method.

[0022] The fourth objective of this application is to provide a storage medium.

[0023] The fourth application objective of this application is achieved through the following technical solutions: A storage medium stores a computer program that can be loaded by a processor and execute the above-mentioned aircraft power system automatic testing method.

[0024] In summary, the present application includes at least one of the following beneficial technical effects: 1. Through automated data collection and working condition switching, human intervention is reduced, safety risks are reduced, test efficiency is greatly improved, development cycle is shortened, and data accuracy and human resource utilization are improved. For example, during the test process, multiple sensor data are automatically collected to avoid manual operation close to dangerous parts, and different test conditions can be quickly switched according to the preset program to efficiently complete the test task.

[0025] 2. Real-time monitoring of data and performance evaluation information, dynamic adjustment of test strategies, automatic optimization of the acquisition accuracy range, establishment of predictive maintenance models to warn of failures in advance, and combined with abnormal handling mechanisms to ensure stable and reliable operation of the system. When an abnormality is detected, it can be timely classified and evaluated, corresponding measures can be taken, abnormal conditions can be recorded and analyzed, and solution suggestions can be generated to facilitate timely maintenance and long-term optimization, reduce the probability of failures, and extend the service life of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of an automatic test method for an aircraft power system provided in an embodiment of the present application; Figure 2 It is a virtual structural diagram of an aircraft power system automatic test system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below 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 ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0029] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0030] The present application embodiment provides an automatic test method for an aircraft power system, referring to Figure 1 , the main process of the method is described as follows: S1: Acquire detection data collected by multiple data collection terminals; Among them, various data of the power system are collected by deploying temperature, speed, torque, sound, smoke, vibration and other sensors at key locations such as power motors, propellers and related components, and connecting data acquisition terminals such as voltage probes, current probes and power analyzers at the motor controller. Each sensor is connected to the data acquisition equipment, and the data is transmitted to the host computer after conversion and processing.

[0031] S2: Analyze and process the detection data to determine whether the detection data is within a normal range; The collected detection data is compared with pre-stored normal range values, which are determined based on power system design parameters, performance indicators and empirical data.

[0032] S3: If the detection data is within the normal range, analyzing the data change trend of the detection data under different test conditions according to the preset program logic; Among them, if the detection data is within the normal range, the upper computer uses the acquired power system design parameters, performance indicators and a large amount of historical test data to build a multi-dimensional test condition simulation model, select a specific condition combination and control the related equipment to switch the condition, continuously collect data under each condition, and use data mining and machine learning algorithms to analyze data change trends, and finally generate a power system performance evaluation report.

[0033] S4: If the detection data or the data change trend is not within the normal range, the safety monitoring mechanism is triggered and an abnormal record is generated.

[0034] If the detection data or data change trend is not within the normal range, the host computer immediately starts the abnormal situation classification and evaluation program, and classifies and handles it according to the severity of the abnormality. A warning is issued for a minor abnormality; the test condition is automatically adjusted for a moderate abnormality; a serious abnormality triggers the emergency shutdown program and sends a control signal to the safety equipment. At the same time, the abnormality time, abnormal data, operating parameters and response measures are recorded to generate an abnormality record report. Through such a set of processes, automatic testing of the aircraft power system and safe and reliable operation guarantee are achieved.

[0035] Specifically, in some possible embodiments, the step of acquiring detection data corresponding to the collected detection data of multiple data collection terminals includes: Collect temperature data of power motors, propellers and related components through temperature sensors; The speed data of the propeller or the power motor is collected through the speed sensor; Collect torque data of the power system through a torque sensor; Collect sound data during the test process through sound sensors; Monitor the smoke conditions in the test environment through smoke sensors; Monitor the vibration of the power system through vibration sensors; Collect voltage data of the motor controller through a voltage probe; Collect current data of the motor controller through the current probe; Analyze the power data of the power system through the power analyzer; Establish an intelligent collaboration mechanism among sensors to achieve collaborative processing and interactive verification of data; Using multi-source data fusion algorithms, the raw data from different sensors are deeply fused and processed to generate a data packet containing comprehensive status information of the power system; Establish a distributed storage architecture to classify, store and manage received data packets.

[0036] Among them, various sensors are deployed at key parts of the aircraft power system, including but not limited to temperature sensors, speed sensors, torque sensors, sound sensors, smoke sensors, vibration sensors, voltage probes, current probes and power analyzers, etc. These sensors are closely connected to the aircraft power system as data acquisition terminals. For example, temperature sensors are installed on power motors, propellers and related components to accurately measure their operating temperatures; speed sensors are set at propellers or power motors to obtain speed data; torque sensors are installed at appropriate locations to monitor torque changes in the power system.

[0037] During the test, the temperature sensor monitors the temperature of the power motor, propeller and related components in real time, and converts the temperature data into electrical signals and transmits them to the subsequent processing unit. The speed sensor collects and transmits the speed data of the propeller or power motor by sensing the movement of the rotating parts. The torque sensor accurately measures the torque data and outputs it according to the mechanical changes inside the power system. The sound sensor collects sound information in the test environment and converts it into digital signals, which are used to analyze the sound characteristics generated when the power system is running and determine whether there is abnormal noise. The smoke sensor continuously monitors the smoke concentration in the test environment and immediately sends a signal once it detects an abnormal increase in smoke. The vibration sensor fits the power system tightly, senses its vibration, and transmits the vibration data to the data processing system. The voltage probe and current probe are connected to the motor controller respectively to accurately collect voltage and current data, and the power analyzer performs real-time analysis of the power of the power system.

[0038] After the test begins, these sensors continuously collect various physical quantity data and convert them into digital signals or analog signals (further converted into digital signals in subsequent processing), and transmit the data to the data concentration device through wired communication cables (such as data cables, shielded cables, etc.) or wireless communication technologies (such as Bluetooth, Wi-Fi, ZigBee, etc.). During the data collection process, the data collection software runs simultaneously. The software has built-in intelligent collaboration algorithms that enable collaborative data processing between sensors. For example, when the temperature sensor detects a sudden increase in temperature in a certain area, the software will automatically trigger the sound sensor and vibration sensor to increase the frequency of data collection, and correlate the data of these sensors in the same time period to determine whether there are any abnormal conditions and realize data interactive verification.

[0039] Next, the data acquisition software uses a multi-source data fusion algorithm to perform deep fusion processing on the raw data from different sensors. Before fusion, a series of pre-processing operations are performed on the data, such as temperature compensation for temperature data, filtering and denoising for vibration data, and calibration of current and voltage data. Then, according to the preset fusion model, different types of data are organically integrated, such as the temperature, speed, torque, and input and output voltage and current of the power motor are fused into a data packet, which contains the comprehensive status information of the power system at a certain moment, such as the working efficiency, load condition, and health status of the power system.

[0040] Finally, a distributed storage architecture is established, such as using a distributed file system (such as Ceph, GlusterFS, etc.) or a distributed database (such as Cassandra, HBase, etc.) to store the fused data according to predetermined classification rules. Data can be classified according to dimensions such as data acquisition time, sensor type, and power system components, so that data can be quickly and accurately queried, retrieved, and called later, providing a solid data foundation for subsequent data analysis and processing, performance evaluation, and fault diagnosis.

[0041] Specifically, in some possible embodiments, the step of analyzing the data change trend of the detection data under different test conditions includes: Obtain the design parameters, performance indicators and a large amount of historical test data of the aircraft power system, and build a multi-dimensional test condition simulation model; According to a preset test plan, a specific working condition combination is selected from the multi-dimensional test working condition simulation model, and related equipment is automatically controlled to realize the switching of the test working conditions; Under each test condition, continuously collecting the detection data transmitted by the data collection terminal; Using data mining and machine learning algorithms to conduct in-depth analysis of the collected detection data; Based on the analysis results of the data change trend of the detection data under different test conditions, a power system performance evaluation report is generated.

[0042] Among them, the various parameters of the power motor in the aircraft power system are obtained in detail, such as motor type (DC motor, AC motor, etc.), rated power, rated voltage, rated current, rated speed, torque constant, back electromotive force constant, motor internal resistance, inductance, etc.; propeller parameters include diameter, pitch, number of blades, material properties (such as strength, elastic modulus, etc.), aerodynamic characteristics (such as lift coefficient, drag coefficient curve, etc.); motor controller parameters such as control mode (such as vector control, direct torque control, etc.), switching frequency, maximum output current, voltage adjustment range, etc.; the overall structural parameters of the aircraft such as aircraft type (fixed-wing, rotorcraft, etc.), fuselage weight, wing area, aspect ratio, center of gravity position, etc., these parameters will directly affect the operating characteristics and performance of the power system. Clarify the key performance indicators of the power system, such as the maximum power output requirement, which determines the power capacity of the power system under extreme conditions; the maximum efficiency index, which reflects the energy utilization efficiency of the power system during operation, is crucial to the endurance of the aircraft; the starting characteristic indicators, including starting time, starting current, starting torque, etc., affect the take-off performance of the aircraft; the speed range indicator determines the speed adjustment range that the power system can achieve to meet the needs of different flight conditions. Collect the power system test data under different environmental conditions (such as different temperature ranges: -20℃ to 50℃, different humidity ranges: 20% to 90%, different air pressure ranges: air pressure values ​​from plains to plateaus, etc.) and different flight states (such as take-off stage: full throttle high load state, cruising stage: stable load state, landing stage: low load state, etc.). These data include but are not limited to the power motor temperature, speed, torque, electrical parameters (voltage, current, power) collected by each sensor, as well as environmental parameters and operating state related data (sound, vibration, etc.). The amount of data should be large enough to cover various possible operating conditions and provide rich samples for model construction.

[0043] According to the characteristics of the collected data and the complex nonlinear characteristics of the power system, you can choose a neural network modeling method (such as multilayer perceptron neural network, radial basis function neural network, etc.), a fuzzy logic modeling method, or a combination of mechanism modeling based on physical principles and data-driven modeling. For example, the electromagnetic characteristics of the power motor are modeled based on the physical principles of the motor, while some parts that are difficult to accurately model (such as the coupling loss between the motor and the propeller) are supplemented by a data-driven neural network modeling method. The input variables of the model include the control input of the power system (such as the input voltage and current command of the motor controller), environmental parameters (temperature, humidity, air pressure, etc.), aircraft state parameters (flight attitude angle, flight speed, altitude, etc.) and internal state parameters of the power system (such as the initial temperature of the motor, accumulated running time, etc.); the output variables are the key performance parameters of the power system (such as the actual speed of the power motor, output torque, efficiency, power, etc.) and operating state parameters (such as temperature change, vibration amplitude, etc.). The collected historical test data is divided into a training set and a validation set. The constructed model is trained using the training set. The model parameters (such as the weight and threshold of the neural network) are adjusted to make the output of the model as close as possible to the actual test data. During the training process, appropriate error evaluation indicators (such as mean square error, mean absolute error, etc.) are used to evaluate the accuracy of the model. After the training is completed, the model is verified using the validation set to check the generalization ability of the model on unseen data. If the verification result is not ideal, the model is adjusted and retrained until the model meets the accuracy requirements. Finally, a multi-dimensional test condition simulation model that can accurately simulate the operating state of the aircraft power system under different test conditions is obtained.

[0044] According to the test objectives and requirements of the aircraft power system, a detailed test plan is formulated. For example, if the purpose is to evaluate the performance of the power system under different load conditions, the test plan will include a series of test conditions with different load values ​​(such as no load, 25% rated load, 50% rated load, 75% rated load, full load, etc.); if the purpose is to study the impact of ambient temperature on the power system, the test plan will cover tests under different temperature ranges (such as low temperature -20℃, normal temperature 25℃, high temperature 40℃, etc.). At the same time, consider factors such as different voltage inputs (such as 80%, 90%, 100%, 110%, 120% of the rated voltage, etc.), different flight speeds (corresponding to different power requirements), and formulate a comprehensive combination of working conditions. The test plan should also specify parameters such as the test time and data acquisition frequency for each working condition to ensure the accuracy and effectiveness of the test. The host computer selects the corresponding working condition combination from the multi-dimensional test working condition simulation model according to the formulated test plan. For each working condition combination, the host computer sends a control signal to the relevant equipment through the communication interface. For example, send voltage setting value signals to the programmable power supply to achieve control of different voltage inputs; send load instructions to the load simulator to simulate different load conditions; send temperature setting signals to devices that simulate ambient temperature changes (such as temperature control boxes, etc.). At the same time, the host computer also controls the start and stop of the data acquisition equipment to ensure that the detection data transmitted by the data acquisition terminal can be accurately collected under each test condition. During the condition switching process, the host computer executes in sequence according to the predetermined order and time interval to ensure that the power system can stably transition to the next test condition, avoiding damage to the power system due to sudden changes in the condition or affecting the accuracy of the test results.

[0045] Before the test begins, ensure that all data acquisition terminals (sensors, probes, analyzers, etc.) are correctly installed, connected, and calibrated. Calibrate the temperature sensor to keep its measurement error within the allowable range; calibrate the speed sensor to ensure the accuracy of the speed measurement; calibrate the torque sensor to obtain accurate torque measurements; and perform accuracy checks on electrical parameter measurement equipment (voltage probes, current probes, power analyzers, etc.). At the same time, check whether the communication link of the data acquisition system is normal to ensure that the data can be transmitted to the host computer stably and quickly. Under each test condition, the data acquisition terminal continuously collects test data according to the preset data acquisition frequency (such as 10Hz, 100Hz, 1kHz, etc., select the appropriate frequency according to the test requirements and data change speed). The temperature sensor monitors the temperature changes of the power motor, propeller and related components in real time, converts the temperature data into digital signals and transmits them; the speed sensor accurately measures the speed of the propeller or power motor and sends the speed data; the torque sensor collects the torque value of the power system in real time; the sound sensor collects the sound signal during the test and transmits the audio data after processing; the smoke sensor continuously monitors the smoke concentration in the environment and sends a signal immediately if there is an abnormal change; the vibration sensor senses the vibration of the power system and transmits the vibration amplitude, frequency and other data to the host computer. The voltage probe, current probe and power analyzer of the motor controller synchronously collect electrical parameter data, and all data are aggregated through the data concentrator and transmitted to the host computer for subsequent processing. During the data collection process, the host computer displays the data collection status in real time, including the amount of data collected, the data collection time, the real-time value of each sensor data, etc., so that the tester can monitor the test process at any time.

[0046] Clean the collected detection data to remove outliers and noise data. For data points that obviously deviate from the normal range (such as the sudden maximum or minimum value of the temperature sensor, which may be caused by sensor failure or interference), use data interpolation or filtering methods to correct or remove them. For example, for spike noise in temperature data, the median filtering method can be used for smoothing; for abnormal fluctuations in speed data, compare with adjacent data points and statistical analysis to determine whether it is an outlier, and if so, correct or delete it. Normalize data of different types and ranges to make them of the same order of magnitude and comparability. Normalization makes it easier for subsequent algorithms to analyze and process the data.

[0047] According to the operating characteristics and test purpose of the power system, meaningful features are extracted from the collected data. For example, for temperature data, the average, maximum, minimum, and temperature change rate (obtained by calculating the difference between the temperatures at adjacent time points) of the temperature can be extracted; for speed data, the average, standard deviation, and fluctuation frequency of the speed can be extracted; for torque data, the peak, average, and variance of the torque can be calculated; for electrical parameter data, the power factor and harmonic content can be extracted. At the same time, different sensor data can be combined to generate new features, such as combining temperature with speed to calculate the temperature change under unit speed. Use appropriate feature selection methods to select the most valuable features for power system performance evaluation from the many extracted features. Common feature selection methods include correlation analysis, calculating the correlation coefficient between each feature and the target variable (such as the efficiency and power output of the power system), and selecting features with higher correlation; or using dimensionality reduction methods such as principal component analysis (PCA) to convert multiple related features into a few unrelated principal components, retaining the main information while reducing the data dimension, reducing the amount of calculation and model complexity, and improving analysis efficiency and accuracy. According to the characteristics of the data and the purpose of analysis, select appropriate data mining and machine learning algorithms. For example, for analyzing the trend of detection data over time, you can choose a time series analysis algorithm (such as ARIMA model, LSTM neural network, etc.); for classification problems (such as determining whether the power system is in a normal or abnormal state), you can use decision trees, support vector machines (SVM), neural network classification algorithms, etc.; for clustering problems (such as classifying the operating status of the power system under different working conditions), you can use K-means clustering, hierarchical clustering and other algorithms. If you need to consider the complex relationship between multiple variables and predict the performance indicators of the power system at the same time, you can choose a neural network regression algorithm (such as multilayer perceptron regression, convolutional neural network regression, etc.) or a model-based regression algorithm (such as Gaussian process regression, etc.). Divide the preprocessed detection data into a training set and a test set (usually divided at a ratio of 70%-30% or 80%-20%), and use the training set to train the selected algorithm model. During the training process, adjust the parameters of the model (such as the weight of the neural network, the split threshold of the decision tree, etc.) to minimize the loss function (such as mean square error, cross entropy, etc.). After training is completed, the model is evaluated using the test set, and evaluation indicators (such as accuracy, recall, root mean square error, etc.) are calculated to measure the performance of the model. If the model performance does not meet the requirements, adjust the algorithm parameters, feature selection, or use ensemble learning methods (such as random forest, Adaboost, etc.) to improve the model performance until satisfactory results are obtained. Through the trained model, the collected test data is deeply analyzed to explore the potential laws and relationships in the data, such as the mutual influence relationship between various parameters under different working conditions, and the trend of power system performance changing with working conditions.

[0048] According to the collected power data (input power and output power), calculate the efficiency of the power system under different test conditions. Analyze the change trend of efficiency under different working conditions (such as different loads, different voltages, different ambient temperatures, etc.), determine the highest and lowest efficiency working points, and evaluate the efficiency level of the power system in the entire working range. Calculate the standard deviation or fluctuation coefficient of power output to measure the stability of power output. Analyze the stability of power output under different test conditions, and judge whether the power output of the power system is stable during the conversion of different working conditions or long-term operation, and whether the fluctuation is within the allowable range. Analyze the temperature change curves of power motors, propellers and other components under different working conditions, and calculate the temperature rise rate and maximum temperature value. Evaluate the heat dissipation performance of the power system, judge whether the temperature will exceed the safety threshold under high load or harsh environmental conditions, and the impact of temperature changes on the performance and life of the power system. Evaluate its dynamic response characteristics by analyzing the response time and overshoot of key parameters (such as speed, torque, power, etc.) of the power system when switching working conditions (such as load mutation, voltage change, etc.). Response time refers to the time required for the system parameter to reach a certain percentage (such as 95% or 98%) of the stable value from the change of working conditions, and overshoot refers to the ratio of the maximum amplitude of the parameter exceeding the stable value during the response process to the stable value. Good dynamic response characteristics are crucial to the maneuverability and stability of the aircraft during flight.

[0049] The power system performance evaluation report should include an introduction, which introduces the purpose, background and test method of the test; the main part lists the calculation results of the performance evaluation indicators under different test conditions in detail, and presents them in a combination of tables, charts (such as line charts, bar charts, scatter plots, etc.) and text descriptions. For example, a line chart can be used to show the trend of efficiency changing with load, a bar chart can be used to compare the power output stability under different voltages, and a scatter plot can be used to analyze the relationship between temperature and running time. At the same time, the performance of the power system should be analyzed and evaluated in the report, and the advantages and disadvantages should be pointed out. According to the performance evaluation results, targeted improvement suggestions should be put forward. If it is found that the power system is less efficient under certain conditions, it can be suggested to optimize the motor control strategy, improve the propeller design or adjust the transmission system parameters; if the problem of excessive temperature is prominent, measures to strengthen heat dissipation (such as increasing the area of ​​the heat sink, improving the ventilation design, using better heat dissipation materials, etc.) are proposed; for the case of poor power output stability, it is recommended to optimize the stability of the power supply and improve the adjustment algorithm of the controller. The report should end with a summary of the test results and suggestions to provide a reference for further optimization of the design, performance improvement and safe and reliable operation of the aircraft power system. The report should be output in the form of electronic documents (such as PDF, Word, etc.) or printed documents to facilitate relevant personnel to review and use.

[0050] Specifically, in some possible embodiments, according to the analysis results of the change trend of the detection data under different test conditions, the step of generating the power system performance evaluation report further includes: Obtain real-time data change trends and power system performance evaluation information; Dynamically adjust the test conditions and data collection strategy according to the real-time data change trend and power system performance evaluation information; Generate real-time feedback information based on the test conditions and data acquisition strategy, and send the real-time feedback information to the data acquisition terminal, so that the data acquisition terminal can automatically adjust the acquisition accuracy and range according to actual conditions; Establishing a predictive maintenance model for the power system using the historical test data and the machine learning algorithm; Based on the current detection data and the data change trend, possible failures and performance degradation trends of the power system are predicted, and maintenance warning information is issued in advance.

[0051] Among them, during the test of the aircraft power system, the data acquisition terminal continuously collects test data and transmits it to the host computer in real time. The data processing software in the host computer analyzes the data in real time, calculates the current values ​​of various performance indicators (such as efficiency, power output stability, temperature change, etc.), and compares them with previous data to determine the data change trend. For example, by fitting the continuously collected power motor temperature data, the temperature change curve over time is obtained, and its rising, falling or stable trend is analyzed; for power data, its mean, variance and other statistics are calculated to observe the fluctuation of power output. At the same time, the host computer evaluates the current performance status of the power system according to the preset performance evaluation algorithm, combined with the currently collected data and historical data (if comparative analysis is required). The evaluation information includes whether the power system is in normal operation, whether the performance meets the expected standards, and whether there are potential risks. These evaluation results are updated in real time and stored in the memory together with the data change trend information, so that they can be called at any time in the subsequent steps. In order to facilitate the test personnel to intuitively understand the operating status of the power system, the host computer can use a visual interface (such as a dashboard, chart, etc.) to display real-time data change trends and performance evaluation information. For example, a line graph is used to show the temperature change trend of the power motor over time under different test conditions, a bar graph is used to compare the power output values ​​at different times, and indicator lights or color changes are used to indicate the performance status of the power system (such as green for normal, yellow for potential risks, and red for abnormalities).

[0052] The control algorithm in the host computer makes judgments based on real-time performance evaluation information and data change trends. If it is found that the performance of the power system is not optimal under the current test conditions, or the data change trend shows that there may be potential problems (such as continuous temperature rise close to the safety threshold, unstable power output, etc.), a test condition adjustment strategy is formulated. For example, if the temperature of the power motor is too high, it may be decided to reduce the load or adjust the motor input voltage to reduce the burden on the motor and improve the heat dissipation; if the power output fluctuates greatly, it may be possible to try to adjust the control parameters of the motor controller to optimize the power output stability. When formulating the working condition adjustment strategy, the overall operating requirements and test objectives of the aircraft power system must also be considered. For example, in some cases, in order to comprehensively evaluate the performance of the power system under extreme conditions, even if certain abnormalities are found in the data, the load may continue to be increased or the environmental conditions may be changed according to the predetermined plan, but monitoring will be strengthened and corresponding safety measures will be taken. According to the real-time data change trend, the data acquisition strategy is optimized. If the data of a certain parameter changes rapidly or fluctuates abnormally, the host computer can instruct the data acquisition terminal to increase the acquisition frequency of the parameter in order to record its change process in more detail. For example, when the vibration sensor detects a sudden increase in the vibration amplitude, the host computer increases the frequency of vibration data acquisition from 100Hz to 1kHz to obtain more accurate vibration change information, which helps to analyze the cause of the fault. On the contrary, if certain data remains stable for a period of time and has little impact on the current performance evaluation, its acquisition frequency can be appropriately reduced to reduce data storage and processing and improve system efficiency. At the same time, according to the adjustment of the test conditions, determine the type of data that needs to be focused on, and adjust the scope and accuracy of data acquisition. For example, under high load conditions, it may be necessary to measure the temperature and torque data of the power motor more accurately, and the host computer adjusts the data acquisition accuracy settings of the temperature sensor and torque sensor accordingly.

[0053] The host computer generates corresponding real-time feedback information according to the formulated test condition adjustment strategy and data acquisition strategy. The feedback information includes control instructions (such as adjusting the value of the load, changing the size of the motor input voltage, modifying the parameters of the motor controller, etc.) and data acquisition parameter settings (such as the acquisition frequency and accuracy requirements of each sensor). This information is encoded in a specific data format so that the data acquisition terminal can accurately identify and execute it. For the feedback information of the test condition adjustment, it also includes control logic such as the time node and sequence of execution adjustment. For example, if the load and voltage need to be adjusted at the same time, the host computer needs to clearly stipulate that the load should be adjusted to the specified value first, and the voltage should be adjusted after a certain time (such as 5 seconds) to ensure that the power system can smoothly transition to the new test condition and avoid damage to the system due to sudden changes in the working condition. The host computer sends the real-time feedback information to the data acquisition terminal through the communication interface. After receiving the feedback information, the data acquisition terminal first decodes and verifies the information to ensure the accuracy and completeness of the information. Then, according to the control instructions in the feedback information, the corresponding operation is performed. For example, after the load simulator receives the instruction to reduce the load, it adjusts the load size through the motor drive system or hydraulic system; after the motor controller receives the instruction to modify the parameters, it updates the internal control algorithm parameters to implement a new control strategy for the power motor. For the adjustment of data acquisition parameters, the relevant chip or software module in the data acquisition terminal resets the sampling frequency, accuracy and other parameters according to the feedback information to ensure that the subsequent collected data meets the new requirements. During the execution process, the data acquisition terminal returns confirmation information of the execution result to the host computer so that the host computer can understand whether the instruction is executed correctly. If an error occurs during the execution process (such as equipment failure, communication interruption, etc.), the data acquisition terminal will send an error report to the host computer in a timely manner, and the host computer will take corresponding measures according to the error situation (such as resending instructions, performing fault diagnosis, etc.).

[0054] Collect a large amount of historical test data, including operating data of different aircraft power systems under various test conditions, maintenance records (such as fault occurrence time, fault type, maintenance measures, etc.), and related environmental data (such as temperature, humidity, air pressure, etc.). Clean these data to remove outliers and erroneous data, for example, delete obviously unreasonable temperature or pressure data caused by sensor failure. Normalize the data to make data of different types and magnitudes comparable, for example, map temperature data to the [0,1] interval and standardize power data. Select appropriate features as model input based on the failure mode and performance degradation characteristics of the power system. For example, for predicting motor bearing failure, motor temperature, vibration amplitude, vibration frequency and other features can be selected; for predicting battery performance degradation, battery voltage, current, number of charges, temperature and other features can be selected. Divide historical data into training set and validation set according to a certain proportion (such as 70%-80% for training and 20%-30% for validation). Select appropriate machine learning algorithms to build a predictive maintenance model based on data characteristics and prediction goals. For example, for classification problems (such as predicting whether a certain fault will occur), decision trees, support vector machines, neural network classification algorithms, etc. can be selected; for regression problems (such as predicting the remaining service life, the trend of performance indicators, etc.), linear regression, neural network regression, support vector regression and other algorithms can be selected. Taking neural networks as an example, a multi-layer perceptron (MLP) neural network is constructed to determine the number of input layer nodes (equal to the number of selected features), the number of hidden layers and nodes (determined by experiments or experience), and the number of output layer nodes (determined according to the prediction target, such as predicting a single fault type, the output layer can be a node, indicating the probability of the fault; predicting multiple fault types can be multiple nodes). The selected model is trained using the training set, and the prediction error of the model on the training set is minimized by adjusting the parameters of the model (such as the weight and bias of the neural network). During the training process, appropriate loss functions (such as mean square error, cross entropy, etc.) and optimization algorithms (such as gradient descent, Adam optimization algorithm, etc.) are used. After the training is completed, the model is evaluated using the validation set, and the evaluation indicators (such as accuracy, recall, root mean square error, etc.) are calculated. If the model performance does not meet the requirements, adjust the model structure (such as increasing the number of hidden layers, changing the number of nodes, etc.), algorithm parameters, or use ensemble learning methods (such as random forest, Adaboost, etc.) to improve the model performance until a satisfactory predictive maintenance model is obtained.

[0055] During the operation of the aircraft power system, the currently collected detection data is input into the established predictive maintenance model in real time. The model predicts the future operating state of the power system based on the input data and the previously learned patterns. For example, it predicts whether the power motor will have an overheating failure in the future (such as 1 hour, 10 hours, etc.) under the current working conditions, or predicts how many hours of remaining battery life are left. The prediction results include the possible fault type (if any), the estimated time of the fault, and the degree and trend of performance degradation (such as the rate of efficiency degradation, the magnitude of power output reduction, etc.). Based on the prediction results, the corresponding maintenance warning information is generated. The warning information includes the warning level (such as low risk warning, medium risk warning, high risk warning), fault description (if a fault is predicted), recommended measures (such as checking a component, adjusting operating parameters, preparing maintenance tools and spare parts, etc.), and the estimated time of fault occurrence or the time when performance drops to a critical value. The warning level is determined according to the predicted severity and probability of the fault. For example, if it is predicted that the power motor has a high probability (such as more than 80%) of a serious overheating fault within 1 hour, a high-risk warning may be issued; if it is predicted that the battery performance will slowly decline to a certain level in the next 10 hours, but can still maintain normal operation for a period of time, a low-risk warning may be issued. The host computer releases warning information in a variety of ways, such as the sound and light alarm at the test site sounds an alarm and flashes a light, pops up a striking warning prompt box on the monitoring interface, and sends the warning information to relevant maintenance personnel (such as aircraft ground staff, equipment maintenance engineers, etc.) through SMS, email or other communication methods to ensure that timely measures are taken to avoid or reduce the impact of power system failures on aircraft operation safety and performance. Maintenance personnel arrange maintenance work in advance based on the warning information, such as inspecting the power system, replacing vulnerable parts, optimizing operating parameters, etc., to improve the reliability and maintainability of the aircraft power system.

[0056] Specifically, in some possible embodiments, if the detection data and the data change trend are not within a normal range, the step of triggering a safety monitoring mechanism and generating an abnormality record includes: When it is detected that the detection data and the data change trend are not within the normal range, the abnormal situation is classified and evaluated to determine the severity of the abnormality, which is divided into slight abnormality, moderate abnormality and severe abnormality; Based on the minor anomaly, a warning message is issued; Based on the moderate anomaly, automatically adjusting the test conditions until the detection data and the data trend are within a normal range; Based on the serious anomaly, trigger an emergency shutdown procedure and send a control signal to relevant safety equipment; Record the time when the abnormality occurred, the specific value of the abnormal data, the corresponding test condition parameters and the response measures taken, and generate an abnormal record report.

[0057] Among them, the normal range boundary of the detection data is pre-set. For example, for the temperature of the power motor, the maximum safe temperature value is determined according to the insulation level and design specifications of the motor. The situation where the temperature exceeds the normal working range but does not exceed a certain proportion of the safe temperature value (such as 10%-20%) is defined as a slight abnormality; the temperature exceeds the safe temperature value by a large proportion (such as 20%-50%) is defined as a moderate abnormality; the temperature rises sharply and exceeds the safe temperature value by a lot (such as more than 50%) or the temperature fluctuates abnormally and cannot be stabilized is defined as a serious abnormality. For speed data, if the speed deviates from the normal range by a small amount (such as within ±5%), it is a slight abnormality, and if it deviates greatly (such as ±5%-±15%), it is a moderate abnormality. If it exceeds ±15% or there is a violent fluctuation and cannot be stabilized, it is a serious abnormality. Similar judgment criteria are also formulated for other detection data such as torque, voltage, and current. At the same time, consider the abnormal situation of data change trend. If the data change trend shows a continuous rapid rise, fall, or violent fluctuation, and exceeds the normal range of change, a comprehensive judgment is made in combination with the current data value. For example, if the temperature of the power motor rises rapidly in a short period of time, even if the current temperature does not reach the threshold of severe abnormality, it should be evaluated as severe abnormality if it will soon exceed the temperature value of severe abnormality according to the current trend. During the test of the aircraft power system, the detection data and data change trend are monitored in real time. When the data is found to be out of the normal range, the abnormal situation assessment program is immediately started. The program classifies and evaluates the abnormal situation according to the pre-set judgment criteria. First, analyze the degree of deviation of the specific value of the current abnormal data from the normal range and calculate the deviation ratio. Then, observe the data change trend and judge its change speed and stability. Taking these factors into consideration, determine the severity of the abnormality as slight abnormality, moderate abnormality or severe abnormality. For example, if the temperature of the power motor exceeds the normal range by 15%, and the temperature rises rapidly but is still within the controllable range, it can be evaluated as moderate abnormality; if the temperature exceeds the normal range by more than 50% and is still rising rapidly, or the temperature fluctuates greatly and cannot be stabilized, it is evaluated as severe abnormality.

[0058] When it is determined to be a slight abnormality, the system issues early warning information in a variety of ways. An audible and visual alarm can be set up at the test site to emit a low-volume alarm sound and flashing yellow light to alert the tester. At the same time, a prompt box with a description of the abnormal information pops up on the monitoring interface, showing the type of abnormal data (such as "slight abnormality in the temperature of the power motor"), the current value, and the degree of deviation from the normal range. In addition, the early warning information can be sent to the relevant person in charge by SMS or email to ensure that the abnormal situation can be understood in time even if not at the test site. After the early warning information is issued, the tester should pay close attention to the development of the abnormal situation. The operating status of the relevant equipment can be further checked to see if there are other signs of abnormality. At the same time, the system continues to monitor the detection data and data change trends in real time to promptly detect whether the abnormal situation has deteriorated. If the abnormal situation does not deteriorate further within a period of time and gradually returns to the normal range, the system can automatically cancel the early warning. If the abnormal situation persists or deteriorates further, further measures need to be taken according to the situation.

[0059] When a moderate abnormality occurs, the system automatically formulates a test condition adjustment strategy. For example, if the moderate abnormality is caused by the excessive temperature of the power motor, the system can reduce the load of the motor and reduce the power output, thereby reducing the working intensity and heat generation of the motor. Or adjust the parameters of the motor controller, such as reducing the input voltage or current of the motor to reduce the power consumption of the motor. If it is a speed abnormality, the speed control parameters of the motor controller may be adjusted to gradually return to the normal range. When adjusting the test conditions, the system should select the appropriate adjustment method and adjustment range according to the characteristics and actual situation of the power system to avoid system instability or new abnormal conditions caused by excessive adjustment. In the process of adjusting the test conditions, the system continuously monitors the detection data and data change trends in real time. According to the monitoring results, the adjustment strategy is continuously optimized. If the abnormal situation improves after adjustment, but it is still not completely restored to normal, the system can further adjust the test conditions until the detection data and data trends are within the normal range. For example, if the temperature of the power motor drops after reducing the load, but is still higher than the normal range, the system can continue to reduce the load or adjust other parameters at the same time, such as increasing the speed of the cooling fan, to speed up the heat dissipation. Once the test data returns to within the normal range, the system can gradually restore the test conditions to normal and continue monitoring to ensure that the abnormal situation does not occur again.

[0060] When a serious abnormality is detected, the system immediately triggers the emergency shutdown procedure. For aircraft power systems, emergency shutdown usually includes cutting off the power supply to the power motor and stopping the operation of the motor. At the same time, the motor controller and other related equipment are turned off to prevent the fault from further expanding. During the emergency shutdown process, the system should ensure the rapidity and reliability of the shutdown operation to avoid serious equipment damage or safety accidents caused by untimely shutdown. While triggering the emergency shutdown procedure, the system sends a control signal to the relevant safety equipment. For example, if it is a serious abnormality caused by fire risk, the system can send a start signal to the fire extinguishing equipment to automatically start the fire extinguishing device to extinguish the fire. If it is a serious abnormality caused by a mechanical failure, the system can send a signal to the emergency brake device to prevent the aircraft from losing control due to a power system failure. In addition, the system can also send a signal to the alarm device to issue a strong sound and light alarm to remind on-site personnel to quickly evacuate the dangerous area.

[0061] During the entire process of the abnormal situation, the system automatically records the time of the abnormal situation, the specific value of the abnormal data, the corresponding test condition parameters and the countermeasures taken. This information can be stored in the local database or cloud server for subsequent query and analysis. The recorded content includes but is not limited to: the timestamp of the abnormal situation, the type of abnormal data (such as temperature, speed, torque, etc.), the specific value of the abnormal data, the test condition parameters at that time (such as load size, voltage, current, etc.), the time of issuing the warning, and the countermeasures taken (such as the specific operation of adjusting the working condition, the time of triggering the emergency shutdown, etc.). According to the recorded information, the system automatically generates an abnormal record report. The report can be in the form of text, table or chart to clearly show the occurrence process and processing results of the abnormal situation. The report content includes the description of the abnormal situation, the analysis of the abnormal data, the countermeasures taken, and the suggestions for subsequent testing and maintenance. For example, in the case of severe abnormal temperature of the power motor, the report can describe in detail the process of temperature rise, the highest temperature value, the emergency shutdown and fire extinguishing measures taken, etc., and recommend a comprehensive inspection and repair of the motor, while analyzing the reasons that may cause the abnormal temperature rise, providing a reference for subsequent testing and maintenance. Abnormal record reports can be printed out or sent to relevant personnel via email to facilitate fault analysis and responsibility identification. It also helps to continuously improve test methods and enhance the safety and reliability of power systems.

[0062] Specifically, in some possible embodiments, if the detection data or the data change trend is not within a normal range, the steps after triggering the safety monitoring mechanism and generating an abnormal record include: Conducting an in-depth analysis of the abnormal records in the abnormal record report, and determining possible causes of the abnormalities corresponding to the abnormal records in combination with historical abnormal data and the operating status of the current aircraft power system; Generate temporary response strategies and long-term solution recommendations based on the severity of the anomaly and the possible causes of the anomaly; The status record of the aircraft power system is updated, and the abnormal record and the processing process information thereof are recorded and stored.

[0063] Among them, detailed information in the abnormal record report is collected, including the time when the abnormality occurred, the specific value of the abnormal data, the corresponding test condition parameters, and the countermeasures taken. At the same time, the historical abnormal data database is retrieved to obtain historical records similar to the current abnormal situation. These historical data can provide valuable references to help determine the possible patterns and causes of the abnormality. In addition, the operating status of the current aircraft power system is monitored in real time, including the data of each sensor, the operating parameters of the equipment, and the overall performance indicators of the system. These data are sorted and summarized to provide a comprehensive information basis for subsequent analysis. A variety of analysis methods are used to determine the possible causes of the abnormality. For example, data trend analysis can be performed to observe the changing trend of abnormal data in the time series to determine whether there is a gradually deteriorating trend or periodic fluctuations. For the case of abnormal temperature rise, the load condition of the power motor, the ambient temperature, and the operating status of the cooling system can be combined for analysis. If the temperature rises abnormally under high load, it may be caused by motor overload or poor heat dissipation; if the ambient temperature is high, it may be caused by external environmental factors affecting the heat dissipation effect. For abnormal speed, the parameter settings of the motor controller, the connection of the transmission system, and the change of load can be checked. Fault tree analysis can also be used to analyze various possible causes and combinations of abnormalities based on abnormal phenomena, so as to determine the most likely fault point. An expert system is established to input the professional knowledge and experience rules of the aircraft power system into the system. When an abnormal situation occurs, the expert system can make inferences and analyses based on the input abnormal data and operating status information, combined with historical experience and rules in the knowledge base, and give suggestions on possible causes of the abnormality. For example, if the smoke sensor detects smoke, the expert system can determine whether it is caused by overheating and fire caused by motor short circuit, overload, or partial discharge caused by poor electrical connection based on the concentration, color and other parameters of the power system. At the same time, the expert system can also provide corresponding detection methods and solution suggestions based on different abnormal causes to help technicians quickly locate and solve problems.

[0064] For abnormal situations of different severity, formulate corresponding temporary response strategies. If it is a minor abnormality, you can adopt a monitoring and observation strategy, continue to run the system but pay close attention to the changes in abnormal data, and be ready to take further measures at any time. For example, when the temperature of the power motor rises slightly, you can increase the speed of the cooling fan to strengthen ventilation and heat dissipation, while continuing to monitor temperature changes. If it is a moderate abnormality, some emergency measures need to be taken to alleviate the abnormal situation and ensure the safe operation of the system. For example, reduce the load of the power system, adjust the parameters of the motor controller, or suspend some non-critical functions to reduce the heat and pressure of the system. For serious abnormalities, take emergency shutdown measures immediately and start safety equipment such as fire extinguishing devices and emergency brake devices to ensure the safety of personnel and equipment. At the same time, formulate emergency response plans, such as organizing personnel to conduct on-site inspections and repairs to restore the normal operation of the system as soon as possible. According to the possible causes of the abnormality, propose long-term solution suggestions. If the abnormality is caused by aging and wear of the equipment, it is recommended to maintain the equipment, replace key components or upgrade the system. For example, if the bearing of the power motor is severely worn and causes abnormal speed, it is recommended to replace the bearing and regularly maintain the motor. If the abnormality is caused by design defects or system mismatch, it is recommended to optimize the design and improvement of the system. For example, if the temperature is too high due to unreasonable heat dissipation system design, the heat dissipation solution can be redesigned to increase the heat dissipation area, improve the air duct design, or use more efficient heat dissipation materials. For frequently occurring abnormal situations, an early warning mechanism and preventive maintenance plan can be established to regularly inspect and test the system, identify potential problems in advance and deal with them to avoid abnormal situations.

[0065] Update the status record of the aircraft power system in a timely manner, and record the abnormal records and their processing information in full. The status record can include basic information of the system (such as model, configuration, installation date, etc.), operation history (including the time, working conditions, results of previous tests, etc.), maintenance records (such as maintenance time, maintenance content, replacement parts, etc.) and abnormal records (including the time, cause, and processing process of abnormal occurrence). When updating the status record, ensure the accuracy and completeness of the information for subsequent query and analysis. The updated status record can be stored in a local database, network storage, or cloud storage to ensure the security and reliability of the data. At the same time, establish an effective data management mechanism to classify, index, and back up the stored information for easy and quick retrieval and query. For example, it can be classified and stored according to time sequence, abnormal type, or equipment components, so that relevant abnormal records and processing information can be quickly found when needed. Clean and organize the stored data regularly, delete unnecessary information, free up storage space, and ensure that important data is preserved for a long time. In addition, a data sharing mechanism can be established to provide status record information to relevant technicians, managers, and maintenance personnel so that they can understand the operating status and history of the system and provide a basis for decision-making.

[0066] Specifically, in some possible embodiments, the method further includes: Obtaining information on changes in environmental parameters outside the aircraft power system; Obtain feedback data from the aircraft power system during actual operation; Combining the environmental parameter change information with the detection data to analyze the impact of environmental factors on the performance of the aircraft power system to obtain test results; Verifying and calibrating the test results using the feedback data from actual operation; Output analysis report on the impact of environmental factors on aircraft power system performance; Output a comparison report of the test result and the feedback data.

[0067] Among them, a series of environmental parameter sensors are deployed in the test environment or actual operating environment where the aircraft power system is located. For example, a temperature sensor is installed to measure the ambient temperature. A high-precision digital temperature sensor can be selected and placed at a certain distance from the power system but can accurately reflect the ambient temperature, such as the outside of the aircraft fuselage or a specific location of the test site. A humidity sensor is installed to monitor the ambient humidity. A capacitive or resistive humidity sensor can be used and placed in a suitable position to obtain accurate humidity data. For the air pressure sensor, it can be installed in a relatively stable part of the aircraft to measure the air pressure changes caused by the change in flight altitude. In addition, a wind direction and wind speed sensor can be installed to obtain wind direction and wind speed information in the environment. It can be installed in a position such as the wing or fuselage side of the aircraft to ensure that the direction and speed of the airflow can be accurately sensed. These sensors are connected to the data acquisition system through wired or wireless communication, and continuously collect environmental parameter data according to the preset sampling frequency. For example, the temperature sensor can collect temperature data once a second, and the humidity sensor can collect humidity data every few minutes. The specific sampling frequency is determined according to actual needs and sensor performance. After the collected data is processed by analog-to-digital conversion, it is transmitted to the host computer for storage and analysis. The data recording software in the host computer records the collected environmental parameter change information in chronological order and stores it in the database. The recorded information includes the type of environmental parameters (such as temperature, humidity, air pressure, wind direction and speed, etc.), collection time, specific values, etc. Relational databases (such as MySQL, Oracle, etc.) or non-relational databases (such as MongoDB, Redis, etc.) can be used for storage for subsequent query and analysis. At the same time, in order to ensure the security and reliability of the data, the data can be backed up regularly to prevent data loss.

[0068] The aircraft power system will generate various feedback data during the actual operation process, and these data can be obtained in a variety of ways. For example, the flight data recorder (black box) on the aircraft can record the key operating parameters of the power system, such as engine speed, power output, fuel consumption rate, etc. In addition, feedback data can also be obtained through the aircraft's onboard sensor system. For example, sensors such as accelerometers and gyroscopes can measure the acceleration, attitude and other information of the aircraft, indirectly reflecting the performance of the power system. For some aircraft with remote communication functions, real-time operation data can be transmitted to the ground control center through satellite communication or ground base station communication to achieve remote data collection. For test runs conducted on the ground, feedback data can be directly obtained through data acquisition equipment connected to the power system. These devices can include various sensors, data recorders, etc., which are connected to the key parts of the power system to collect real-time operation data of the power system, such as motor temperature, propeller speed, torque, etc. The collected data is transmitted to the host computer for processing by wired or wireless means. The collected feedback data is sorted and preprocessed to remove noise and outliers. Data filtering algorithms, such as median filtering and mean filtering, can be used to smooth the data and remove abnormal fluctuations caused by sensor noise or interference. At the same time, the data is converted and normalized to make different types of data comparable. For example, the speed is converted from revolutions per minute (RPM) to radians per second (rad / s), and the temperature is converted from degrees Celsius to Kelvin. The pre-processed data is more accurate and reliable, which is convenient for subsequent analysis and processing.

[0069] Use appropriate data analysis methods to study the impact of environmental factors on power system performance. Multiple regression analysis methods can be used to take environmental parameters (such as temperature, humidity, air pressure, etc.) as independent variables and power system performance parameters (such as power output, efficiency, speed, etc.) as dependent variables to establish a regression model and analyze the relationship between environmental factors and performance parameters. For example, multiple regression analysis can determine the degree of influence of each degree increase in temperature on the power output of the power system. Correlation analysis methods can also be used to calculate the correlation coefficient between environmental parameters and performance parameters to determine the strength of the correlation between them. For example, calculate the correlation coefficient between ambient humidity and power system efficiency to determine whether there is a significant correlation between them. For complex environmental factors and power system performance relationships, machine learning algorithms such as neural networks and support vector machines can be used for modeling and analysis. These algorithms can automatically learn the nonlinear relationship between environmental parameters and performance parameters to improve the accuracy and reliability of the analysis. For example, a neural network algorithm is used to establish a prediction model between environmental factors and power system performance, and the performance of the power system is predicted by inputting different combinations of environmental parameters. Design a series of experiments to study the impact of environmental factors on power system performance. For example, the performance test of the power system can be carried out under different ambient temperature, humidity and air pressure conditions, and the corresponding test data and environmental parameter change information can be recorded. Then, these data are sorted and analyzed, grouped according to different environmental parameter combinations, the average performance parameter value of each group of data is calculated, and the correlation analysis with the environmental parameters is performed. For example, compare the efficiency changes of the power system at different temperatures and analyze the influence of temperature on efficiency. Through such experimental design and data analysis process, we can fully understand the impact of environmental factors on the performance of the aircraft power system.

[0070] Compare and analyze the feedback data obtained during the actual operation with the test results. For example, compare the power output, efficiency and other data of the power system in actual operation with the corresponding performance parameters obtained by the test, and calculate the error between them. The accuracy of the test results can be measured by indicators such as absolute error and relative error. If the error is within an acceptable range, it means that the test results have high reliability; if the error is large, further analysis of the cause is required, which may be due to inaccurate test methods, incomplete consideration of environmental factors, or unconsidered situations in the actual operation of the power system. According to the comparative analysis results of the feedback data and the test results, adjust and calibrate the test model. If it is found that there is a large deviation between the test model and the actual operation, the accuracy of the model can be improved by adjusting the parameters of the model, adding new environmental factor variables, or improving the data analysis method. For example, if it is found that the impact of temperature on the performance of the power system is more significant in actual operation than in the test results, the weight of the temperature variable in the model can be increased, or a more complex temperature model can be used to describe its impact on performance. At the same time, the model is calibrated using feedback data, and the model parameters are continuously adjusted to make the model's prediction results closer to the actual operation data, thereby improving the reliability and practicality of the test results.

[0071] The analysis report should include an introduction, which introduces the background, purpose and methods of the study. The main part elaborates on the analysis results of the impact of environmental factors on the performance of the power system, including the relationship between environmental parameters and performance parameters, the influence rules and trends, etc. It can be presented in a combination of charts, tables and text descriptions. For example, a line chart can be used to represent the influence curve of temperature on the efficiency of the power system, a table can be used to list the changes in the power output of the power system under different humidity conditions, and a text description can be used to describe the influence mechanism of air pressure on the performance of the power system. The report should also include a conclusion section, which summarizes the main findings and conclusions of the study and puts forward corresponding suggestions and measures. For example, based on the analysis results, suggestions can be put forward to optimize the performance of the power system under different environmental conditions, or corresponding maintenance and maintenance strategies can be formulated according to the influence of environmental factors. The analysis report can be output in PDF, Word and other document formats for easy reading and archiving. The report should contain clear elements such as titles, directories, page numbers, etc., which are convenient for users to find and browse. At the same time, different versions of the report can be generated as needed, such as detailed version and concise version, to meet the needs of different users. The report can be sent to relevant personnel, such as aircraft design engineers, maintenance personnel, managers, etc., by email, printout or online sharing, to provide them with decision-making basis and technical support.

[0072] The comparison report should first conduct a detailed comparative analysis of the test results and feedback data. The power system performance parameters obtained during the test can be compared one by one with the corresponding data in actual operation, and the differences between them can be calculated. For example, the motor speed obtained in the test can be compared with the speed value in actual operation, and the deviation between them can be analyzed. At the same time, the test results and feedback data under different environmental conditions can be compared to observe the impact of environmental factors on the difference between the two. For example, whether the deviation between the test results and the feedback data changes at different temperatures. Through comparative analysis, the accuracy and reliability of the test method and the performance of the power system in actual operation can be determined. The comparison report can be presented in a combination of charts and text. For example, a bar chart can be used to compare the power output values ​​of the test results and feedback data, a line chart can be used to show the changes in efficiency of the two at different time points, and text can be used to describe the causes and influencing factors of the difference between the two. The report can also include an evaluation of the test method and data acquisition process, and propose improvement suggestions and measures. For example, if it is found that there is a large difference between the test results and the feedback data, the accuracy of the data acquisition equipment, the stability of the test environment and other factors can be analyzed, and suggestions such as improving the data acquisition method and optimizing the test environment can be proposed. The comparison report can be output in the form of an electronic document for easy reference and analysis by users. It can also be presented at a project reporting meeting to provide a reference for the optimization and improvement of the aircraft power system.

[0073] Another embodiment of the present application provides an automatic test system for an aircraft power system, wherein, referring to Figure 2 , aircraft power system automatic test system, including: The detection data acquisition module 100 is used to acquire detection data corresponding to the detection data collected by multiple data collection terminals; The detection data processing module 200 analyzes and processes the detection data to determine whether the detection data is within a normal range; Data change trend analysis module 300: if the detection data is within the normal range, then analyze the data change trend of the detection data under different test conditions according to the preset program logic; Abnormal record generation module 400: If the detection data or the data change trend is not within the normal range, a safety monitoring mechanism is triggered and an abnormal record is generated.

[0074] The aircraft power system automatic test system provided in this embodiment can implement the various steps of the aforementioned embodiments due to the functions of its modules themselves and the logical connections between each other, and can therefore achieve the same technical effects as the aforementioned embodiments. The principle analysis can be found in the relevant description of the aforementioned aircraft power system automatic test method steps, which will not be repeated here.

[0075] An embodiment of the present application further provides an automatic test device for an aircraft power system, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the above-mentioned automatic test method for the aircraft power system.

[0076] An embodiment of the present application further provides a storage medium, which stores a computer program that can be loaded by a processor and execute the above-mentioned aircraft power system automatic testing method.

[0077] The storage medium provided in this embodiment can achieve the same technical effects as the aforementioned embodiments because the computer program therein implements the various steps of the aforementioned embodiments after being loaded and run on the processor. The principle analysis can be found in the relevant description of the aforementioned method steps, which will not be repeated here.

[0078] The storage medium includes, for example, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0079] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0080] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0081] In addition, the term "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined, and is only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.

[0082] Thus, any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0083] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. An automatic test method for an aircraft power system, characterized in that: include: Obtaining detection data collected by multiple data collection terminals; Analyze and process the detection data to determine whether the detection data is within a normal range; If the test data is within the normal range, then according to the preset program logic, the data change trend of the test data under different test conditions is analyzed; If the detection data or the data change trend is not within the normal range, the safety monitoring mechanism is triggered and an abnormal record is generated.

2. The automatic test method for aircraft power system according to claim 1, characterized in that: The steps of obtaining the detection data collected by the multiple data collection terminals include: Collect temperature data of power motors, propellers and related components through temperature sensors; The speed data of the propeller or the power motor is collected through the speed sensor; Collect the torque data of the power system through the torque sensor; Collect sound data during the test process through sound sensors; Monitor the smoke conditions in the test environment through smoke sensors; Monitor the vibration of the power system through vibration sensors; Collect voltage data of the motor controller through a voltage probe; Collect current data of the motor controller through the current probe; Analyze the power data of the power system through a power analyzer; Establish an intelligent collaboration mechanism among sensors to achieve collaborative processing and interactive verification of data; Use multi-source data fusion algorithms to deeply fuse raw data from different sensors and generate data packets containing comprehensive status information of the power system; Establish a distributed storage architecture to classify, store and manage received data packets.

3. The automatic test method for aircraft power system according to claim 1, characterized in that: The steps of analyzing the data change trend of the detection data under different test conditions include: Obtain the design parameters, performance indicators and a large amount of historical test data of the aircraft power system, and build a multi-dimensional test condition simulation model; According to a preset test plan, a specific working condition combination is selected from the multi-dimensional test working condition simulation model, and related equipment is automatically controlled to realize the switching of the test working conditions; Under each test condition, continuously collecting the detection data transmitted by the data collection terminal; Using data mining and machine learning algorithms to conduct in-depth analysis of the collected detection data; Based on the analysis results of the data change trend of the detection data under different test conditions, a power system performance evaluation report is generated.

4. The method for automatic testing of an aircraft power system according to claim 3, characterized in that: According to the analysis results of the change trend of the test data under different test conditions, the steps of generating the power system performance evaluation report also include: Obtain real-time data change trends and power system performance evaluation information; Dynamically adjust the test conditions and data collection strategy according to the real-time data change trend and power system performance evaluation information; Generate real-time feedback information based on the test conditions and data acquisition strategy, and send the real-time feedback information to the data acquisition terminal, so that the data acquisition terminal can automatically adjust the acquisition accuracy and range according to actual conditions; Establishing a predictive maintenance model for the power system using the historical test data and the machine learning algorithm; Based on the current detection data and the data change trend, possible failures and performance degradation trends of the power system are predicted, and maintenance warning information is issued in advance.

5. The automatic test method for aircraft power system according to claim 1, characterized in that: If the detection data and the data change trend are not within the normal range, the steps of triggering the safety monitoring mechanism and generating an abnormal record include: When it is detected that the detection data and the data change trend are not within the normal range, the abnormal situation is classified and evaluated to determine the severity of the abnormality, which is divided into slight abnormality, moderate abnormality and severe abnormality; Based on the minor anomaly, a warning message is issued; Based on the moderate anomaly, automatically adjusting the test conditions until the detection data and the data trend are within a normal range; Based on the serious anomaly, trigger an emergency shutdown procedure and send a control signal to relevant safety equipment; Record the time when the abnormality occurred, the specific value of the abnormal data, the corresponding test condition parameters and the response measures taken, and generate an abnormal record report.

6. The automatic test method for aircraft power system according to claim 1, characterized in that: If the detection data or the data change trend is not within the normal range, the steps after triggering the safety monitoring mechanism and generating the abnormal record include: Conducting an in-depth analysis of the abnormal records in the abnormal record report, and determining possible causes of the abnormalities corresponding to the abnormal records in combination with historical abnormal data and the operating status of the current aircraft power system; Generate temporary response strategies and long-term solution recommendations based on the severity of the anomaly and the possible causes of the anomaly; The status record of the aircraft power system is updated, and the abnormal record and the processing process information thereof are recorded and stored.

7. The automatic test method for aircraft power system according to claim 1, characterized in that: The method further comprises: Obtaining information on changes in environmental parameters outside the aircraft power system; Obtain feedback data from the aircraft power system during actual operation; Combining the environmental parameter change information with the detection data to analyze the impact of environmental factors on the performance of the aircraft power system to obtain test results; Verifying and calibrating the test results using the feedback data from actual operation; Output analysis report on the impact of environmental factors on aircraft power system performance; Output a comparison report of the test result and the feedback data.

8. The aircraft power system automatic test system is characterized by: include: Detection data acquisition module: obtains the detection data collected by multiple data acquisition terminals; Detection data processing module: analyzes and processes the detection data to determine whether the detection data is within a normal range; Data change trend analysis module: if the test data is within the normal range, the data change trend of the test data under different test conditions is analyzed according to the preset program logic; Abnormal record generation module: If the detection data or the data change trend is not within the normal range, the safety monitoring mechanism is triggered and an abnormal record is generated.

9. Automatic test equipment for aircraft power system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes any one of the aircraft power system automatic testing methods of claims 1-7.

10. A storage medium, characterized in that: The computer program is stored which can be loaded by a processor and execute the automatic test method of the aircraft power system according to any one of claims 1 to 7.

Images