CN111259515A - Aircraft health management method and system - Google Patents

Abstract

The invention discloses an aircraft health management method and system, relating to the technical field of aerospace and used for realizing the following steps: the system integrates fault monitoring, fault diagnosis, influence evaluation, fault prediction and the like of various subsystems of the aircraft, corresponding processing measures, arrangement of logistics support and the like into a comprehensive management system for the health condition of the aircraft. The invention has the beneficial effects that: the failure occurrence time, failure modes and the like are predicted according to certain failure signs, the maintenance guarantee of the aircraft is improved, the maintenance according to the conditions is correctly implemented, and the failure occurrence rate of the aircraft is reduced.

Description

Aircraft health management method and system

Technical Field

The invention relates to the technical field of aerospace, in particular to an aircraft health management method and system.

Background

With the development of aerospace technologies, the safety and reliability of aircrafts, the high efficiency and economy of aircraft logistics support systems and the like become more and more unavoidable problems in the development of aerospace technologies. Statistical data from the united states federal aviation administration and the national transport safety commission have shown that over the past 17 years, flight accidents worldwide have been caused by failures of aircraft subsystems and components, by flight runaway 26%, and by hardware and system failures for a significant portion of flight runaway, and that the aerospace industry has been under tremendous economic pressure, with airlines costing $ 310 million per year on aircraft logistics, with an average flight time per hour of 12 hours of logistics.

In order to improve the reliability and safety of the aircraft and reduce the cost, how to establish a set of aircraft ground health management system is urgent.

Disclosure of Invention

In order to solve at least one of the technical problems in the prior art, the present invention provides an aircraft health management method and system, which integrates fault monitoring, fault diagnosis, impact evaluation, fault prediction, etc. of various subsystems of an aircraft, and corresponding processing measures and logistics support arrangement, etc. into a comprehensive management system for the health condition of the aircraft.

The first aspect of the technical scheme adopted by the invention to solve the problems is as follows: an aircraft health management method, comprising the steps of: a state monitoring step, namely establishing an abnormity monitoring library and setting a monitoring parameter range, and judging whether abnormity occurs or not by acquiring flight parameters of the aircraft; a health evaluation step, namely establishing a health behavior model and a health evaluation algorithm, and comparing real-time output parameters of the flight control system with results output by the health behavior model based on the health evaluation algorithm to obtain a health state evaluation result of the current flight control system; the method comprises the following steps of failure prediction, wherein aircraft equipment information is collected, and according to the aircraft equipment information, the damage judgment, the degradation state identification and the residual service life prediction of an aircraft are carried out to obtain the probability and the time of the occurrence of the predicted failure; and maintenance management, namely establishing a database for storing and managing aircraft historical data and state information, analyzing and researching the corresponding aircraft based on output results of the three steps, and generating a maintenance scheme.

Has the advantages that: the failure occurrence time, failure modes and the like are predicted according to certain failure signs, the maintenance guarantee of the aircraft is improved, the maintenance according to the conditions is correctly implemented, and the failure occurrence rate of the aircraft is reduced.

According to the first aspect of the present invention, establishing the anomaly monitoring library specifically includes: and establishing an alarm monitoring condition, and performing logical processing to obtain a decision tree based on a judgment condition.

According to the first aspect of the present invention, the health assessment step further comprises: setting corresponding fault modes according to the mutual influence factors of all components of the flight control system so as to establish a health mode table; simulating each health mode one by one, and acquiring response data under the corresponding health mode to form a neural network training sample space; training the neural network training sample space one by one to generate a health behavior model corresponding to the health mode; sorting the plurality of health behavior models to obtain a normal system model; and evaluating the data vector of the designated test point of the flight control system based on a health evaluation algorithm, and comparing, comparing and analyzing the result output by combining the normal system model to obtain the evaluation result of the health state of the current flight control system.

According to the first aspect of the present invention, the failure prediction step further comprises: acquiring aircraft historical record data and corresponding state conditions, modeling based on a neural network, and acquiring a mapping model between the historical record data and a predicted output state; and carrying out fault test on the aircraft, comparing, matching and evaluating based on the mapping model according to test information and the historical record data, setting a known state corresponding to the historical record data with the highest matching degree as the current state of the aircraft, and carrying out fault prediction according to the current state of the aircraft.

According to the first aspect of the present invention, the damage determination includes: acquiring observation data of an aircraft in a specified time period, performing phase space reconstruction on the observation data and establishing a local linear model; estimating a tracking function according to the local linear model and constructing a tracking matrix, wherein the tracking matrix comprises tracking slowly-varying damage and working condition change; and separating the variation trend of the slowly varying damage from the tracking matrix by using a modal decomposition method to obtain a damage evolution process.

According to the first aspect of the present invention, the degradation state identification includes: the method comprises the steps of information acquisition, wherein the working information of each time period is acquired for each component of the aircraft based on a plurality of types of sensors; an information processing step, namely extracting relevant characteristic vectors from the working state information by using a time domain analysis method and a time-frequency domain analysis method to obtain vector spaces constructed by different state characteristic vectors, and modeling the corresponding state type spaces; the method comprises the steps of information identification, wherein a nonlinear relation between a state feature vector space and a state type space is constructed, and an experiment sample data is adopted to train a model to obtain an information source state identification result; and a decision fusion step, namely comprehensively summarizing the state recognition results of the information sources, obtaining the total probability distribution of the state types based on fusion rules according to the basic confidence degrees of different recognition results, and further obtaining the final recognition result.

According to a first aspect of the invention, the remaining useful life prediction comprises: acquiring information of corresponding parts of the aircraft with fault characteristics, and acquiring observation data of the corresponding parts in a specified time period; selecting corresponding prediction characteristics according to the components with the fault characteristics, preprocessing the prediction characteristics, and performing noise smoothing on the observation data to obtain a preprocessed degradation characteristic sequence; performing regression fitting on the degradation characteristic sequence, and extracting a plurality of set data points corresponding to non-zero basis functions; establishing a degradation model according to the characteristic sequence, predicting and determining a priori degradation model based on a correlation vector machine method, and selecting the most appropriate degradation model or determining optimization improvement on the model; performing homographic fitting on the observation data according to the degradation model, and determining a model parameter value; and carrying out extrapolation prediction on the degradation model according to the parameter values to obtain the estimation of the evolution trend of the predicted characteristics, including the range estimation value of the residual service life of the corresponding component.

According to the first aspect of the present invention, the maintenance managing step includes: a personalization step for designating corresponding maintenance items according to the maintenance manual of each aircraft; and a maintenance planning step, which is used for generating a maintenance plan early warning according to the state parameters of the corresponding aircraft and issuing a maintenance task.

The second aspect of the technical scheme adopted by the invention to solve the problems is as follows: an aircraft health management system, comprising: the state monitoring module is used for establishing an abnormity monitoring library, setting a monitoring parameter range and judging whether abnormity occurs or not by acquiring flight parameters of the aircraft; the health evaluation module is used for establishing a health behavior model and a health evaluation algorithm, and comparing real-time output parameters of the flight control system with results output by the health behavior model based on the health evaluation algorithm to obtain a health state evaluation result of the current flight control system; the fault prediction module is used for acquiring aircraft equipment information, and obtaining the probability and time of predicting the occurrence of a fault according to the aircraft equipment information for aircraft damage judgment, degradation state identification and residual service life prediction; and the maintenance management module is used for establishing a database for storing and managing aircraft historical data and state information, analyzing and researching the corresponding aircraft based on the output results of the three modules and generating a maintenance scheme.

Has the advantages that: the failure occurrence time, failure modes and the like are predicted according to certain failure signs, the maintenance guarantee of the aircraft is improved, the maintenance according to the conditions is correctly implemented, and the failure occurrence rate of the aircraft is reduced.

According to a second aspect of the invention, the fault prediction module further comprises: the acquisition unit is used for acquiring aircraft historical record data and corresponding state conditions; the modeling unit is used for modeling based on a neural network according to the information acquired by the acquisition unit and acquiring a mapping model between historical record data and a prediction output state; the testing unit is used for carrying out fault testing on the aircraft to obtain testing information; and the evaluation unit is used for comparing, matching and evaluating the historical record data based on the mapping model according to the test information, setting the known state corresponding to the historical record data with the highest matching degree as the current state of the aircraft, and performing fault prediction according to the current state of the aircraft.

Drawings

FIG. 1 is a schematic flow diagram of a method according to an embodiment of the invention;

FIG. 2 is a schematic diagram of a system architecture according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of condition monitoring and determination according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a health assessment model according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a reconstructed phase spatial relationship according to an embodiment of the invention;

FIG. 6 is a schematic illustration of a remaining useful life prediction according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a management system host interface according to an embodiment of the invention;

FIG. 8 is a schematic view of an information collection interface according to an embodiment of the present invention;

FIG. 9 is a schematic view of a condition monitoring interface according to an embodiment of the present invention;

FIG. 10 is a schematic view of a health interface according to an embodiment of the present invention;

FIG. 11 is a schematic diagram of a fault prediction interface according to an embodiment of the present invention;

FIG. 12 is a schematic view of a service interface according to an embodiment of the invention;

FIG. 13 is a schematic diagram of a comprehensive query interface in accordance with an embodiment of the present invention.

Detailed Description

The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention.

Referring to fig. 1, a schematic flow chart of a method according to an embodiment of the present invention includes the following steps:

a state monitoring step, namely establishing an abnormity monitoring library and setting a monitoring parameter range, and judging whether abnormity occurs or not by acquiring flight parameters of the aircraft;

a health evaluation step, namely establishing a health behavior model and a health evaluation algorithm, and comparing real-time output parameters of the flight control system with results output by the health behavior model based on the health evaluation algorithm to obtain a health state evaluation result of the current flight control system;

the method comprises the following steps of failure prediction, wherein aircraft equipment information is collected, and according to the aircraft equipment information, the damage judgment, the degradation state identification and the residual service life prediction of an aircraft are carried out to obtain the probability and the time of the occurrence of the predicted failure;

and maintenance management, namely establishing a database for storing and managing aircraft historical data and state information, analyzing and researching the corresponding aircraft based on output results of the three steps, and generating a maintenance scheme.

FIG. 2 is a schematic diagram of a system architecture according to an embodiment of the present invention;

the aircraft ground health management system functional structure is an open system structure and comprises a state monitoring module, a health assessment module, a fault prediction module, a maintenance management module and an interface module, wherein the state monitoring module comprises two basic functions of abnormity monitoring and alarming. Firstly, establishing an abnormity monitoring library and a monitoring parameter range standard as a basis for judging whether equipment is abnormal, then receiving data from an aircraft flight parameter collector, judging whether the equipment is abnormal according to an equipment alarm monitoring condition stored in a fault library, and if the equipment is abnormal, alarming by adopting various modes such as voice, logs, a man-machine interaction interface and the like. The state monitoring module is implemented as shown in fig. 3.

FIG. 3 is a schematic diagram of status monitoring and determination according to an embodiment of the present invention;

anomaly monitoring

The anomaly monitoring library is used for storing all alarm monitoring conditions, and various alarm monitoring conditions must be researched to abstract out universal monitoring logic. The present invention uses XML files to store alarm conditions, and forms decision conditions into a decision tree for facilitating

And processing the complex exception and giving reasonable suggestions.

The system analyzes the flight parameter data collected by the flight parameter collector to obtain parameter information such as the exhaust temperature of an aircraft engine, the engine speed, the exhaust temperature of an auxiliary power device, the alternating-current power supply frequency of a generator, the pressure of a hydraulic system, the pressure of left and right lubricating oil, the oil quantity, the cabin pressure, the existence of a hanging point, the instantaneous fuel consumption, the displacement of a steering column, the displacement of a steering wheel, the deflection angles of left and right ailerons, the heating of an airspeed head, the states of front and rear undercarriages and the like, then judges whether abnormal parameters exist according to alarm conditions, and alarms if the abnormal parameters.

Alarm device

And when the system state is monitored to be abnormal, starting an alarm function at the first time. Alarms will be generated in a multi-faceted fashion to ensure that the current abnormal conditions are notified to the logistics support personnel. The alarm system can send out an alarm signal by adopting an alarm sound, simultaneously display the abnormity on a human-computer interaction interface, send the abnormity to logistics support personnel by a short message and write the abnormity information into a system log file.

Referring to FIG. 4, a schematic diagram of a health assessment model according to an embodiment of the invention:

the health status directly affects the safety of the aircraft during flight, and therefore, the need for health assessment techniques is particularly acute. The health assessment is mainly divided into two parts: health behavior modeling and health assessment algorithm design.

Modeling the health behaviors:

the health behavior model is a model which is established based on dynamic system analysis and can reflect the mapping relation between input excitation and behavior output in different health modes. And constructing a healthy behavior model by using a system identification method based on full analysis of the dynamic characteristics of the system.

Health assessment algorithm

And designing a reasonable health evaluation algorithm, and correspondingly comparing and analyzing the actual output of the system and the predicted output of the health behavior model, thereby realizing the evaluation of the current health state of the system.

The overall scheme of the health evaluation module is designed as follows: firstly, establishing a clear health mode table, fully considering fault modes corresponding to various influence factors in each component, secondly, obtaining response data of the system under different health modes by using computer simulation to form a neural network training sample space, respectively training to generate a health behavior model under the corresponding health mode, forming a system model under a normal state, and finally, analyzing a test point data vector based on a health evaluation index to realize the evaluation of the health state of the system.

Fault prediction is an important link in aircraft ground health management systems. The main purpose is to reduce the use and guarantee cost, improve the umbrella safety, integrity and task success of the equipment system, and realize maintenance and autonomous guarantee based on the state.

The fault prediction technology aims at the fault prediction of equipment, estimates the residual service life at the time when a prejudgment system fails, so as to guide the task planning before the equipment failure occurs, formulate the maintenance strategy of the equipment, furthest exert the efficiency of the equipment and reduce the maintenance cost on the basis of avoiding the occurrence of accidents and reducing the loss of manpower, physics and financial resources.

The failure prediction function in the present invention is defined as follows:

(1) the main application object of the fault prediction technology is the first level of the parts, and the fault prediction accuracy and stability of the parts are guaranteed to reach a high level.

(2) Failure prediction behavior is the whole process from the occurrence of early damage to complete failure. No prediction was made before damage did occur. When early damage is detected, estimating the evolution trend of specific damage according to known monitoring data, a fault model or prior knowledge, and predicting the residual service life of the target until the target completely fails.

(3) And determining the operation condition of the equipment in a future period of time after the current moment, and predicting the fault mode and the evolution process of the damage.

(4) Due to the fact that the process from failure to complete failure of target equipment is very unstable due to a plurality of factors such as environmental factors, working condition factors and material damage, high uncertainty exists in a failure prediction result, a failure growth probability model needs to be established by means of simulation or experimental data verification, sufficient aging data statistical samples are collected and used for training, verifying and adjusting a failure prediction algorithm, and the safety, reliability and accuracy of failure prediction are guaranteed to the maximum extent.

1. The failure prediction method comprises the following steps:

the invention uses data drive to combine with neural network to model the obtained state monitoring data, and establishes a mapping model between historical record data and prediction output. Comparing, matching and evaluating the test information output by the current system with the historical test information under the known state condition, judging the known state which is best matched with the current test information as the current state of the system, and predicting the normal or different-degree damage or fault of the current equipment.

2. The failure prediction content is as follows:

the damage, degradation state identification and residual service life of the aircraft equipment need to be predicted in the fault prediction, and the probability and time of the fault occurrence are predicted from the quantization, description and evolution trend of the health state of the equipment, and reasonable probability form expression of a target component is given.

(1) Lesion tracking

Existing or impending damage patterns are tracked, evaluated and predicted. The damage degradation of the component is a slow accumulation process, and a complex nonlinear relation exists between the damage state and the measured data, so that various nonlinear theories and methods are adopted to solve the problem.

Phase space warping: in a nonlinear system, when a certain parameter changes (no matter the change size), the phase space of the system is distorted. The phenomenon shows that the slow accumulation of the damage can be expressed in a micro-curvature form in a reconstruction phase space of the system, and based on the phenomenon, the phase space of the system can be reconstructed by using observable fast-changing parameters, so that characteristic parameters describing the slow-changing damage accumulation process are extracted from the reconstructed phase space.

Reconstructing the phase space: the phase space of the reconstruction system is characterized in that the spatial dimension of the reconstruction system not only comprises fast-changing vibration and slow-changing damage, but also external time-varying factors (such as external excitation, environmental conditions, operating conditions and the like) from the information contained in the phase space. Assuming that the slowly-varying damage is monotonous in time, an observation data section is intercepted, the data length is medium time scale, namely the slowly-varying damage degree can be considered to be approximately constant in the data section. Therefore, the phase space trajectory corresponding to the data segment can be regarded as slices in the slowly varying damage dimension, as shown in fig. 5, refer to fig. 5, which is a schematic diagram of a reconstructed phase space relationship according to an embodiment of the present invention, each slice represents one state of the slowly varying damage of the system, and a set of damage states of all slices represents the whole process of the system during the damage evolution. According to the principle of occurrence of the phase space warping phenomenon, if the tiny warping of the phase space trajectory caused by the accumulated change of the damage between each data segment in the graph can be quantified, the evolution process of the slowly-varying damage state can be described.

In order to quantitatively describe the phase space distortion, firstly, reconstructing the phase space, then establishing a local linear model, estimating a tracking function, and finally constructing a tracking matrix. The tracking matrix simultaneously reflects the change processes of slowly-varying damage, working condition change and other possible factors, and the change trend of the slowly-varying damage is separated by using a modal decomposition method, so that the damage evolution process is finally and reasonably represented.

(2) Degradation state identification

The degraded state of the device refers to the state from the healthy state of normal function to the degraded function of the device in its entirety

The substrate loses basic functions, and is in a state of a certain stage in the degradation process in the process of complete failure.

The degradation state is an abstract concept, so that the degradation state of the device belongs to an undetectable "parameter", which needs to be estimated by some definite or empirical correspondence using other measurable physical quantities, and the latter is calculated by a measurable time-frequency domain signal. The identification and evaluation of the device is completely dependent on measurable information about the device.

And (3) a multi-information source state identification algorithm: the invention adopts a multi-information source state identification algorithm to realize the identification of the degradation state. When the equipment performance degradation state begins, the state characteristics generally have the following characteristics: the degraded state characteristic signal is weak, so that the state characteristic presents uncertain characteristics; because the difference of the internal structure is different from the difference of the transmission line, weak characteristic signals of the degradation state usually appear in a certain local position of the equipment at first, so that one sensor cannot comprehensively and accurately capture the state information of the equipment. The degradation state can be effectively identified by fusing information of a plurality of sensors, the sensors positioned at a plurality of key positions are constructed into an information network, the measurement information of different positions is fully acquired, and the measurement information is fused by applying an information fusion technology to obtain a final identification result.

The main steps of the degradation state identification are as follows:

information processing and feature extraction

According to the working state information of different time periods and different parts of the equipment in working, different sensors are respectively adopted to collect the data of the equipment in working, then, a time domain analysis method and a time-frequency domain analysis method are used for extracting relevant characteristic vectors from the state information of the equipment, vector spaces constructed by different state characteristic vectors are obtained, and modeling is carried out on corresponding state type spaces.

Information source state identification

And constructing a nonlinear relation between the state feature vector space and the type space of the state, and training the model by adopting experimental sample data.

State attribute decision fusion

And comprehensively summarizing different recognition results, and obtaining the total probability distribution of the state types by applying a fusion rule according to the basic confidence degrees of the different recognition results so as to obtain the final recognition result.

(3) Remaining service life

The remaining service life refers to the remaining time for effectively operating and realizing the established function at a certain time in the operation process. Estimation and prediction of remaining service life is a central task of the ground health management system, and needs to be implemented by using available equipment operation state information, health monitoring information, statistical information and the like.

The remaining service life prediction needs to be based on early damage detection and degradation state identification, support the prediction characteristics, associate the prediction characteristics with a service life curve of the device, and predict the remaining service life of the device by estimating the change of the characteristics, and referring to fig. 6, a diagram of the remaining service life prediction according to an embodiment of the present invention is shown.

And according to the change condition of a selected health index capable of reflecting the performance of the equipment, the whole process of predicting the residual service life of the equipment is explained. Regardless of the failure of the target equipment (parts) caused by the failure in the initial break-in stage, the initial state is considered as a healthy state and is also the life starting point of the equipment. And when the equipment completely fails and cannot be pulled through maintenance means, the end of the service life of the equipment is reached. The time span from the initial state to the end of the life of the device is the full life of the device. The life-cycle of a device can be divided into two parts, a healthy state and a fault state, wherein for most devices the healthy state is usually maintained for a considerable period of time, and accordingly the health indicator is maintained at a relatively stable level. However, long-term operation entails fatigue and wear of the equipment concerned, which initially occurs inside the material, in the form of extremely small internal cracks and the like, and which is not clearly manifested in the various physical quantities observable on the outside. With further increase in the operating time, the microscopic damage inside the material gradually increases and starts to manifest itself in observables. At this time, the presence of a fault can be found by various fault diagnosis methods, and the fault which can be found at the earliest is considered as an initial fault, and is considered to enter a fault state from this time.

In the case of the entire fault state phase, the process of gradual increase of the fault of the equipment until complete failure, and corresponding to this process, the health index also gradually decreases with the health state of the equipment until reaching the level corresponding to complete failure. However, the occurrence of a fault does not represent a loss of functionality of the device, and in fact, until the fault reaches a certain level, the intended task can be effectively accomplished despite the fact that the operation of the device is somewhat affected. In the health management technology, in order to maximize the efficiency utilization rate of the equipment, after an initial fault is found, degradation state identification and fault prediction are carried out on the equipment, and the equipment is enabled to continue to operate until functional failure occurs on the basis of ensuring the safety of the equipment.

The functional failure state refers to a state in which the equipment cannot normally complete a given task, and the corresponding health index level is referred to as a failure threshold. If the forced operation is continued, the equipment will fail completely in a short time. Therefore, the failure state is the best time for maintaining the equipment at the beginning, and the safety and the efficiency utilization rate of the equipment can be balanced. Through measures such as maintenance or replacement of parts, the system and the equipment can recover the health state and operate in service again, and the guarantee cost of the equipment is effectively reduced.

The period from the discovery of the initial failure to the failure of the device functionality is the development of the remaining useful life prediction stage.

The failure degradation stage of the equipment has strong nonlinearity, and is characterized in that the descending speed (the severity of the failure) of the health index is gradually accelerated along with the continuous time. Therefore, the predictable stage is divided into an early degradation stage and an accelerated degradation stage of the fault, in the early degradation stage, the weak fault starts to degrade gradually, the fault degree aggravation speed is relatively slow, and the health index decline amplitude is not large in a relatively long time; after entering the accelerated degradation stage, the fault degree aggravation speed is obviously increased, and the healthy index is rapidly reduced to the failure threshold value in a short time.

After entering the predictable stage, the residual service life of the equipment can be predicted at any time according to the requirement. Since the prediction needs to be modeled and calculated by means of operating state information, health monitoring information, statistical information, etc. of the device prior to the current time, the available observed signals have to be determined. And taking the initial fault finding time as a starting point, intercepting observation data between the time and the prediction time as known observation data, predicting the evolution trend of the health index after the current time, estimating when the health index is reduced to a failure threshold value, and calculating the predicted value of the residual service life at the time.

In the prediction process, the following key points are selected:

selection of a prediction point: when prediction is performed after a predictable stage, known observation data samples with a certain length are required to be used as a basis for modeling or calculation, and different prediction methods are different from the required data length. Therefore, when determining the initial observation point, it is necessary to determine whether the known observation data at that time is sufficient for performing the corresponding counting. Ensuring the safety of the equipment and reducing unnecessary over-calculation.

Selection of observation data starting point: the observation starting point is selected in conjunction with the particular prediction algorithm employed, taking into account the known observation length. The observation data starting point is not limited to the time when the initial fault is found, and the required known observation data can be intercepted from any time when the observation data is recorded in the health state stage according to needs.

Determination of the failure threshold: an approximate failure threshold is set based on the specific situation or historical experience of the equipment. According to different adopted health indexes, the numerical value of the failure threshold value can also have certain influence on steps such as modeling in a prediction algorithm.

The implementation process of the residual service life can be divided into feature extraction and sparse data set construction, and a degradation model and residual service life prediction are determined.

Feature extraction and sparse data set construction: firstly, selecting proper prediction characteristics according to the characteristics of equipment to be predicted, then preprocessing the prediction characteristics, and performing noise smoothing on an observed value sequence or eliminating the influence of factors such as working conditions and the like as far as possible to obtain a preprocessed degradation characteristic sequence. And finally, performing regression fitting on the degradation characteristic sequence of the known observation data, extracting a plurality of most representative data points corresponding to the non-zero basis functions, and predicting the occurrence of a certain future event in a probability form.

Determining a degradation model: after the degradation characteristics are determined, a degradation model can be determined according to the degradation characteristic sequence of the historical data, a priori degradation model is determined through prediction based on a correlation vector machine method, and the most appropriate degradation model is selected or optimized and improved.

Predicting the remaining service life: and fitting the sparse data set by adopting the degradation model, and determining the model parameter value of the degradation model. And carrying out extrapolation prediction on the degradation model on the basis to obtain the estimation of the evolution trend of the predicted characteristic. And calculating the estimated value of the residual service life of the equipment and the upper boundary and the lower boundary of the estimated value.

Maintenance management module

The maintenance time and the maintenance efficiency of the aircraft directly determine the maintenance guarantee level, and most of the existing China air force maintenance modes adopt timing maintenance. The timing maintenance is a traditional maintenance mode, and embodies the maintenance thought taking accident prevention as the center. This maintenance method only uses time as a control parameter, and cannot effectively prevent a failure that has no direct relation with the use time. Theories and practices show that the fault generation of the engine is random, the fault rate is always 1 constant and is not in a linear relation, and unnecessary work cannot be avoided in this way, so that waste of manpower and material resources is caused. And the timing maintenance has poor predictability, excessive additional maintenance and ineffective disassembly, which adversely affects the working precision of the aircraft or the engine and shortens the effective life of the aircraft or the engine.

The on-the-fly maintenance is based on the fact that a large number of faults occur with 1 developing process, not instantaneously, i.e. most faults have some warning signal (called latent fault) as soon as they occur. If condition monitoring techniques are used to monitor these signals, it is possible to discover that the process of fault is continuing and take steps to prevent the occurrence of a fault or to avoid the consequences of a fault.

After the steps of state monitoring, health assessment and fault prediction are carried out by the aircraft ground health management system, the components with faults and the health conditions of the components can be accurately given, and a maintenance scheme can be analyzed.

Ground logistics support personnel can replace or overhaul components in time, reliability and usability of the aircraft system are improved, maintenance load is reduced, and comprehensive maintenance efficiency is improved.

The maintenance management module improves the efficiency of maintenance management work, realizes informatization and intellectualization of the maintenance management work, and realizes the state information input and monitoring of the aircraft and the automatic generation of maintenance plan early warning. The main work of the module is:

1. and storing relevant data in maintenance management work by using an efficient database system, and constructing an intelligent maintenance management system of the aircraft.

2. The aircraft state parameter information is stored through the database, and recording and monitoring are carried out in the whole life cycle of the aircraft, so that the digital management of the aircraft information is realized.

3. The maintenance project information is stored in the database, and the system can be used for making and modifying the maintenance projects, so that the online digital management of the maintenance projects is realized.

4. The system automatically generates the early warning of the maintenance plan according to the state information of the aircraft and the maintenance project information, reduces the burden of maintenance plan personnel, and improves the efficiency of the maintenance management work of the aircraft.

5. The system can visually display maintenance task information, and can perform full-flow operation of generating, issuing, submitting and ending the tasks on line, so that the execution flow of the tasks is more efficient.

The maintenance management module is divided into the following parts:

aircraft information management: the management of aircraft information is decisive for the development of maintenance work, the aircraft information including the factory information of the aircraft and the state parameter information during service. The intelligent maintenance management system for the aircraft has the functions of storing, checking and timely updating the state parameter information of the aircraft. After the aircraft executes the operation task, the flight record table is required to be filled in to record various parameter information of the aircraft and update the parameter information into the system database, and after the maintenance task is executed, the state information of the aircraft is required to be changed in time.

And (4) maintenance project management: in daily maintenance work, a production department supervises the time control time of a time control project, the use time information of the time control project is from a daily flight record sheet used by the airplane in flight, and maintenance

Maintenance records of the squad. Then according to the basic information managed by the time control piece on the aircraft maintenance manual, the aircraft maintenance manual is built

The timed project management module is erected, so the maintenance project management module firstly establishes all maintenance projects of each airplane according to the maintenance manual of the airplane, and mainly comprises the following steps: the method comprises the following steps of a scheduled inspection item of the airplane, a component inspection item, a time control item, an engine scheduled inspection item and an engine scheduled service item. The regular inspection items refer to regular inspection tasks to be performed by the aircraft at regular intervals according to the inspection outline, the component inspection items refer to tasks in which the states of internal components of the aircraft need to be inspected at regular intervals, the control item refers to a task in which the components are disassembled and replaced when the service life of the control on the aircraft is reached, the engine regular inspection item refers to a task in which the components need to be inspected at regular intervals in the engine, and the engine-time service life task refers to a task in which the components in the engine are disassembled and replaced when the service life of the components in the engine is reached. The functions of the items are mainly to write related maintenance items according to the examination outline, and to view, update, modify and delete the maintenance items. The main content of the task includes the item number, content description, and the current state. In addition to management of maintenance items, work cards associated with maintenance items need to be managed, and work cards can be created, deleted, checked, and edited.

Maintenance planning management maintenance planning needs to be carried out according to the state parameters of the aircraft, such as flight hours, cycle number or landing times

When the upper limit of the manual or the maintenance outline requirement is approached, the early warning of the maintenance plan can be automatically generated, the worker carries out task issuing and other operations on the basis of the plan early warning, and finally the related personnel execute the task and feed back and report the task, the maintenance task is finished after the task is finished, and the finished maintenance plan has historical records for inquiring. The maintenance plan management can also pack a plurality of maintenance tasks according to the current situation, and then carry out the operation flows of issuing and executing the packing tasks, and the like, so that the maintenance work is executed more flexibly. The maintenance schedule can be viewed in different time ranges with weekly and monthly schedules, respectively. The user can inquire the maintenance plan specified by the history and can inquire according to different conditions. After each project is finished, the maintenance information is recorded, and the maintenance information comprises a finishing person, finishing time, piece changing information and the like.

Managing data files: the aircraft maintenance management work often uses some document data, such as training plans, post qualifications, maintenance outlines, etc., and the aircraft intelligent maintenance management system can store the data digitally and can be viewed conveniently. In the maintenance management workflow, there are places where files need to be uploaded, and the system can efficiently and reliably store and manage the files.

Interface module

The interface module is used for communication and information exchange between the airborne system of the aircraft and each part of the ground health management system and is mainly completed in a bus mode. The main function is to ensure correct, smooth, coordinated and safe information exchange among all parts in the whole ground health management system, thereby realizing informatization and integration of the whole ground health management system.

Use of the system

Mounting and connecting

The aircraft ground health management system mainly comprises an aircraft ground parameter collector, a power interface and aircraft ground health management system software.

Under normal temperature, an input 27V power supply of an aircraft ground parameter collector is connected to a direct-current adjustable voltage-stabilized power supply, a collector unloading line aircraft is connected with a circular aviation plug of a collector front panel and a PC network interface, the collector is electrified with 27V, under normal conditions, the current is 0.45A (+ -10%), the voltage is 27V +/-1V, a front panel indicator lamp normally displays blue at the moment of electrification, then the front panel indicator lamp always flashes as a green lamp, and a computer displays that the connection with a network is successful. And observing whether the indicator light, the network, the current and the voltage are normal or not.

After logging in, the system main interface can be accessed, referring to fig. 7, which is a schematic diagram of the main interface of the management system according to the embodiment of the present invention, in the system main interface, the function buttons of the organic library, data acquisition, state monitoring, health assessment, fault detection, maintenance management, and comprehensive query in the right main control menu can be seen, and the page switching can be performed by clicking the buttons.

And entering a main interface after the software successfully logs in. And the default hangar function interface is a system main interface, the available airplane models of the airport can be checked in the hangar interface, and the airplane models are switched and selected through buttons.

After a model is selected, the states of all the models in the base are displayed in a lower hangar list, one hangar is selected, and the fault condition of the aircraft in the hangar can be seen in a lower fault icon.

And basic parameter information such as the aircraft number of the aircraft, such as the important parameter information of the aircraft length, the aircraft height, the wingspan, the full aircraft empty weight, the maximum height, the maximum speed, the maximum voyage, the load capacity and the like, is displayed in the display area on the right side.

3. Data acquisition: and clicking a button of the left control menu to switch the functional interface to the data acquisition interface, so that the flight parameter information of the selected aircraft can be acquired. FIG. 8 is a schematic diagram of an information collection interface according to an embodiment of the present invention;

in the data acquisition interface, the hangar drawing displayed at the upper left part shows the name, the airplane number, the hangar number and the range information of the aircraft of the model in the middle.

Selecting the drop-down box from the resume, selecting resume information to be downloaded, clicking an acquisition button to start acquisition, seeing acquisition duration and acquisition progress below, clicking a pause button to pause data acquisition, and clicking a stop button to terminate the unloading of the resume information.

The characteristic information curve of the history, such as height, speed, atmospheric temperature and the like, can be viewed in the characteristic curve interface, the characteristic value curve to be viewed is selected from the characteristic value selection box, and the characteristic value curve is displayed in a graph.

In the switching value signal list on the left side, the switching value parameters of the current history information can be checked in real time, the indicator light is used for displaying the state of the switching value, red indicates that the switching value is not opened, and green indicates that the switching value is opened. More information is viewed by scroll bar dragging.

The analog quantity signal table with history information displayed in the analog quantity display area comprises signal parameters such as an engine beat signal, an alternating current analog signal, a frequency signal and the like, and more information is checked by dragging a scroll bar.

And (3) state monitoring: clicking a button of the left control menu to switch the function interface to the state monitoring interface, so that the state of each system of the aircraft can be monitored, as shown in fig. 9, the state monitoring interface is a schematic diagram according to the embodiment of the invention;

under the state monitoring page, the state information of a plurality of modules of the aircraft can be monitored, and after the module to be detected is selected in the module selection drop-down box, the state of each subsystem function of the module is displayed in the list below. The current monitoring module can also be switched by clicking a left switch or right switch button. And if the subsystem is found to have abnormal or fault conditions, the lower state early warning indicator lamp turns red, and an early warning message is sent to maintenance personnel.

The detailed state information of the module is listed in the information list on the right side, and the detailed information of each subsystem of the module is displayed. The information of the module can be generated in a report form by clicking a button, and the module can be printed, so that the module is convenient to browse. And a button may be clicked to save the current data as a historical data file. If the monitoring data in a certain period before needs to be viewed, a button can be clicked to load the previously saved data into a list for reference.

Health assessment: clicking a button of the left control menu can switch the function interface to the health assessment interface, and can check the health state of each system of the aircraft, as shown in fig. 10, which is a schematic view of the health condition interface according to the embodiment of the invention;

in the onboard data structure diagram, the component structure of the overall system of the aircraft can be clearly seen. The health condition interface of the system can be popped up by directly clicking the health condition of the system or the subsystem to be checked by using a mouse.

In the health status list below, the overall health status of the aircraft system may be viewed. The health and evaluation parameters of each subsystem under each system can be viewed.

The health assessment state can be generated in a reported mode by clicking a button, and the report can be printed, so that the report is convenient to browse. And a button may be clicked to save the current data as a historical data file. If the monitoring data in a certain period before needs to be viewed, a button can be clicked to load the previously saved data into a list for reference.

And (3) fault prediction: clicking a button of the left control menu can switch the function interface to the failure prediction interface, and can predict the possible failure of each function module of the aircraft, as shown in fig. 11, which is a schematic diagram of the failure prediction interface according to the embodiment of the invention.

In the failure prediction interface, failure prediction and early warning of the sub-equipment of each system of the aircraft can be seen. The aircraft selection function box can be seen in the upper left corner, and displayed aircraft modules are switched by clicking a button through a mouse. Basic information such as the total number of the current equipment, the total number of sensors, the total number of faults, the downtime, the utilization rate and the like can be checked and obtained in the equipment information on the right side, and the displayed basic information is different according to the change of the selected equipment.

In the equipment fault early warning list, the names of all equipment in the current system, the equipment states, the fault occurrence possibility, the estimated occurrence time, the early warning states, the last maintenance time and other information are listed in detail, and a user can perform corresponding maintenance work according to the prompt given in the fault early warning information.

The state curves of all the sensors of the system can be seen in the sensor list, and the display and hiding of the sensor curves can be controlled through a check box.

The operation condition and the fault occurrence probability of each device of the system in a future period can be seen in the device state, and the device which is possibly in fault can be maintained in advance according to the result given by the chart.

Maintenance and management: clicking a button of the control menu on the left side can switch the function interface to the maintenance management interface, and can record and view the maintenance condition of each system of the aircraft, as shown in fig. 12, which is a schematic view of the maintenance interface according to the embodiment of the invention.

When the aircraft system generates maintenance requirements, ground logistics personnel should fill in a maintenance bill first, record information such as time of aircraft system fault generation, maintenance reason, maintenance starting time and consumed working hours, register the information in a warehouse, and check historical maintenance information of the aircraft in a maintenance information list. The repair order may click a print button to generate a preview and print.

The accessory information shows basic information for replacement or repair of the accessory for the aircraft system. When each system needs to be replaced or newly added with accessories, the functions of newly added accessories and replacing accessories of the accessories are used, and if a certain accessory needs to be maintained, a maintenance accessory button is clicked to enter a maintenance accessory interface for operation. If a certain accessory is to be removed, the accessory deleting button is clicked, the accessory is deleted, and detailed accessory use, replacement and maintenance information can be seen in the accessory information list below.

And (4) comprehensive query: clicking a button of the left control menu can switch the function interface to the comprehensive query interface, and query the historical data of each system of the aircraft, as shown in fig. 13, which is a schematic diagram of the comprehensive query interface according to the embodiment of the invention.

The comprehensive query page function can be used for viewing detailed historical data such as health assessment data, fault prediction data, maintenance management data and the like of each system. The method can accurately search according to the input time period, search results are displayed in a lower list, and a query result can be generated into a report form to facilitate browsing.

It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.

Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.

Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein.

A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.

The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.

Claims (10)

1. An aircraft health management method, comprising the steps of:

a state monitoring step, namely establishing an abnormity monitoring library and setting a monitoring parameter range, and judging whether abnormity occurs or not by acquiring flight parameters of the aircraft;

a health evaluation step, namely establishing a health behavior model and a health evaluation algorithm, and comparing real-time output parameters of the flight control system with results output by the health behavior model based on the health evaluation algorithm to obtain a health state evaluation result of the current flight control system;

the method comprises the following steps of failure prediction, wherein aircraft equipment information is collected, and according to the aircraft equipment information, the damage judgment, the degradation state identification and the residual service life prediction of an aircraft are carried out to obtain the probability and the time of the occurrence of the predicted failure;

and maintenance management, namely establishing a database for storing and managing aircraft historical data and state information, analyzing and researching the corresponding aircraft based on output results of the three steps, and generating a maintenance scheme.

2. The aircraft health management method of claim 1, wherein the establishing an anomaly monitoring library specifically comprises:

and establishing an alarm monitoring condition, and performing logical processing to obtain a decision tree based on a judgment condition.

3. The aircraft health management method of claim 1, wherein the health assessment step further comprises:

setting corresponding fault modes according to the mutual influence factors of all components of the flight control system so as to establish a health mode table;

simulating each health mode one by one, and acquiring response data under the corresponding health mode to form a neural network training sample space;

training the neural network training sample space one by one to generate a health behavior model corresponding to the health mode;

sorting the plurality of health behavior models to obtain a normal system model;

and evaluating the data vector of the designated test point of the flight control system based on a health evaluation algorithm, and comparing, comparing and analyzing the result output by combining the normal system model to obtain the evaluation result of the health state of the current flight control system.

4. The aircraft health management method of claim 1, wherein the fault prediction step further comprises:

acquiring aircraft historical record data and corresponding state conditions, modeling based on a neural network, and acquiring a mapping model between the historical record data and a predicted output state;

and carrying out fault test on the aircraft, comparing, matching and evaluating based on the mapping model according to test information and the historical record data, setting a known state corresponding to the historical record data with the highest matching degree as the current state of the aircraft, and carrying out fault prediction according to the current state of the aircraft.

5. The aircraft health management method of claim 1, wherein the impairment determination comprises:

acquiring observation data of an aircraft in a specified time period, performing phase space reconstruction on the observation data and establishing a local linear model;

estimating a tracking function according to the local linear model and constructing a tracking matrix, wherein the tracking matrix comprises tracking slowly-varying damage and working condition change;

and separating the variation trend of the slowly varying damage from the tracking matrix by using a modal decomposition method to obtain a damage evolution process.

6. The aircraft health management method of claim 1, wherein the degradation state identification comprises:

the method comprises the steps of information acquisition, wherein the working state information of each time period is acquired for each component of the aircraft based on a plurality of types of sensors;

an information processing step, namely extracting relevant characteristic vectors from the working state information by using a time domain analysis method and a time-frequency domain analysis method to obtain vector spaces constructed by different state characteristic vectors, and modeling the corresponding state type spaces;

the method comprises the steps of information identification, wherein a nonlinear relation between a state feature vector space and a state type space is constructed, and an experiment sample data is adopted to train a model to obtain an information source state identification result;

and a decision fusion step, namely comprehensively summarizing the state recognition results of the information sources, obtaining the total probability distribution of the state types based on fusion rules according to the basic confidence degrees of different recognition results, and further obtaining the final recognition result.

7. The aircraft health management method of claim 1, wherein the remaining useful life prediction comprises:

acquiring information of corresponding parts of the aircraft with fault characteristics, and acquiring observation data of the corresponding parts in a specified time period;

selecting corresponding prediction characteristics according to the components with the fault characteristics, preprocessing the prediction characteristics, and performing noise smoothing on the observation data to obtain a preprocessed degradation characteristic sequence;

performing regression fitting on the degradation characteristic sequence, and extracting a plurality of set data points corresponding to non-zero basis functions;

establishing a degradation model according to the characteristic sequence, predicting and determining a priori degradation model based on a correlation vector machine method, and selecting the most appropriate degradation model or determining optimization improvement on the model;

performing homographic fitting on the observation data according to the degradation model, and determining a model parameter value;

and carrying out extrapolation prediction on the degradation model according to the parameter values to obtain the estimation of the evolution trend of the predicted characteristics, including the range estimation value of the residual service life of the corresponding component.

8. The aircraft health management method of claim 1, wherein the maintenance management step comprises:

a personalization step for designating corresponding maintenance items according to the maintenance manual of each aircraft;

and a maintenance planning step, which is used for generating a maintenance plan early warning according to the state parameters of the corresponding aircraft and issuing a maintenance task.

9. An aircraft health management system, comprising:

the state monitoring module is used for establishing an abnormity monitoring library, setting a monitoring parameter range and judging whether abnormity occurs or not by acquiring flight parameters of the aircraft;

the health evaluation module is used for establishing a health behavior model and a health evaluation algorithm, and comparing real-time output parameters of the flight control system with results output by the health behavior model based on the health evaluation algorithm to obtain a health state evaluation result of the current flight control system;

the fault prediction module is used for acquiring aircraft equipment information, and obtaining the probability and time of predicting the occurrence of a fault according to the aircraft equipment information for aircraft damage judgment, degradation state identification and residual service life prediction;

and the maintenance management module is used for establishing a database for storing and managing aircraft historical data and state information, analyzing and researching the corresponding aircraft based on the output results of the three modules and generating a maintenance scheme.

10. The aircraft health management system of claim 9, wherein the fault prediction module further comprises:

the acquisition unit is used for acquiring aircraft historical record data and corresponding state conditions;

the modeling unit is used for modeling based on a neural network according to the information acquired by the acquisition unit and acquiring a mapping model between historical record data and a prediction output state;

the testing unit is used for carrying out fault testing on the aircraft to obtain testing information;

and the evaluation unit is used for comparing, matching and evaluating the historical record data based on the mapping model according to the test information, setting the known state corresponding to the historical record data with the highest matching degree as the current state of the aircraft, and performing fault prediction according to the current state of the aircraft.

Images