Fault processing method and system of anti-icing simulation system

Abstract

The invention belongs to the technical field of data processing, particularly relates to a fault processing method and system for an anti-icing simulation system, and aims to solve the problems that the early warning accuracy is not high and processing instructions are easy to mismatch in the prior art. The method provided by the invention comprises the following steps: acquiring multi-source simulation data of an anti-icing simulation system; determining a temperature drop rate and a humidity change rate according to the environment simulation data, and determining a dynamic regulation and control factor in combination with the system characteristic data; valve time sequence data of the anti-icing simulation system are obtained, the valve time sequence data and the dynamic regulation and control factors are input into a pre-trained time sequence prediction model for fault prediction, and a fault prediction probability is obtained; taking the fault prediction probability as a query vector, retrieving a plan node in a pre-constructed knowledge graph, and generating a predictive instruction; and when the fault prediction probability reaches a preset threshold value, executing the predictive instruction. Based on the method, the early warning accuracy and the instruction adaptability in the fault processing stage are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of data processing, and particularly relates to a fault processing method and system of an anti-icing simulation system. BACKGROUND

[0002] The simulation of the anti-icing system of an aircraft usually includes multiple subsystems such as wing anti-icing, engine anti-icing, windshield heating, and pitot tube heating. The performance of the anti-icing system is evaluated by simulating the meteorological conditions (such as temperature, humidity, and flight speed) in the real flight environment in coordination between different subsystems. For the fault processing scenario of the anti-icing simulation system, the related technology mainly realizes fault early warning and processing by using the following two schemes: One is to trigger an alarm by using predefined environmental parameter thresholds (such as temperature ≤ 0℃ and humidity ≥ 85%). However, this method easily ignores the influence of dynamic changes in the environment on the fault sensitivity, thereby reducing the accuracy of fault early warning. Specifically, if a constant threshold is used, icing may be missed due to response delay in the sudden temperature drop scenario, and false alarms may occur when the humidity fluctuates gently. The other scheme is to map a preset disposal scheme based on a historical fault database. However, the preset disposal nodes are usually divided into discrete probability intervals (such as "high / medium / low risk"), which lack fine analysis of real-time prediction probabilities, resulting in mismatch of processing instructions. Specifically, when the prediction result is a boundary probability, an error disposal type is easily triggered, thereby causing mismatch between the final execution instruction and the actual risk.

[0003] Therefore, it is necessary to provide a fault processing method of an anti-icing simulation system to solve the problem of low early warning accuracy and easy occurrence of processing instruction mismatch in the related art when performing fault processing. SUMMARY

[0004] To solve the above problems in the prior art, i.e., the problem of low early warning accuracy and easy occurrence of processing instruction mismatch in the related art when performing fault processing, the present application provides, in a first aspect, a fault processing method of an anti-icing simulation system, which comprises: obtaining multi-source simulation data of the anti-icing simulation system, wherein the multi-source simulation data comprises environmental simulation data and system characteristic data; determining a temperature drop rate and a humidity change rate according to the environmental simulation data, and determining a dynamic regulation factor in combination with the system characteristic data, wherein the dynamic regulation factor comprises a valve response threshold and a fault detection sensitivity, the valve response threshold is in a negative correlation with the humidity change rate, and the fault detection sensitivity is in a positive correlation with the temperature drop rate; Obtaining valve timing data of the anti-icing simulation system, inputting the valve timing data and the dynamic regulation factor into a pre-trained timing prediction model for fault prediction to obtain a fault prediction probability, the valve timing data serving as timing feature input of the timing prediction model, and the timing prediction model determining a fault prediction boundary according to the dynamic regulation factor; Taking the fault prediction probability as a query vector, searching for a preplan node in a pre-constructed knowledge graph, and generating a predictive instruction, the knowledge graph including a static topology network constructed based on historical fault cases, the static topology network including a plurality of nodes, each node being configured to store a mapping relationship between at least one fault prediction probability and an execution instruction; When the fault prediction probability reaches a preset threshold, the predictive instruction is executed.

[0005] In some preferred embodiments, the determining of the temperature drop rate and the humidity change rate according to the environment simulation data comprises: determining environment temperature timing data according to the environment simulation data; determining a time window formed by a current time and a target historical time based on the environment temperature timing data according to a preset sampling duration, the time interval between the target historical time and the current time satisfying the sampling duration; determining a difference between environment temperatures corresponding to a start time and an end time in the time window; determining the temperature drop rate according to the sampling duration and the difference between the environment temperatures.

[0006] In some preferred embodiments, the determining of the temperature drop rate and the humidity change rate according to the environment simulation data comprises: determining dew point temperature timing data according to the environment simulation data; performing sliding average filtering processing on the dew point temperature timing data, and determining dew point temperature values of two sampling points closest to a current time node in the dew point temperature timing data after the filtering processing; determining a dew point temperature increment in a preset unit of time based on the dew point temperature values of the two closest sampling points; determining the humidity change rate according to the dew point temperature increment.

[0007] In some preferred embodiments, the determining of the dynamic regulation factor in combination with the system feature data comprises: extracting a structure parameter of a valve from the system feature data, the valve structure parameter including an opening and closing delay time and a steady-state leakage rate; determining a response delay compensation coefficient of the valve according to the opening and closing delay time; determining a leakage compensation rate of the valve according to the steady-state leakage rate; determining a negative correlation adjustment coefficient according to the humidity variation rate; determining the valve response threshold value in combination with the response delay compensation coefficient, the leakage compensation rate, and the negative correlation adjustment coefficient.

[0008] In some preferred embodiments, the determining a dynamic regulation factor in combination with the system characteristic data comprises: determining a system heating unit degradation parameter according to the system characteristic data; determining a basic sensitivity gain according to the heating unit degradation parameter; determining a positive correlation reinforcement factor according to the temperature drop rate; determining the fault detection sensitivity according to the basic sensitivity gain and the positive correlation reinforcement factor.

[0009] In some preferred embodiments, the valve response threshold value satisfies the following formula: ; In the formula, V th is the valve response threshold value, V base is a basic response threshold value, is a valve opening and closing delay time, and ϵ is a preset safety parameter, is an average valve opening and closing delay time, is a delay compensation coefficient, k η is a leakage compensation rate, V h is a humidity variation rate, σ is an environmental modulation intensity coefficient, β is an abruptness factor of a humidity variation rate modulation curve, and η is a steady-state leakage rate.

[0010] In some preferred embodiments, the fault detection sensitivity satisfies the following formula: ; In the formula, S det is the fault detection sensitivity, S base is a preset reference sensitivity, ΔR is a system resistance aging rate, δ is a root mean square deviation of heat flow distribution, α is an aging influence gain coefficient, V c is a temperature drop rate, V0 is a temperature drop reinforcement starting threshold value, γ min , γ max are extreme values of system safety constraint parameters, and k is a preset coefficient of a control gain growth rate.

[0011] In some preferred embodiments, the taking the fault prediction probability as a query vector, searching for a preplan node in a pre-constructed knowledge graph, and generating a predictive instruction comprise: An absolute difference between the target failure probability value in the failure prediction result and a failure probability weight value stored in each node of the knowledge graph is calculated. Based on the preset topological distance weight coefficient and the probability tolerance threshold, a candidate node set meeting a condition is screened in the knowledge graph, and an absolute interpolation between each node in the candidate node set and the target failure probability value is less than the probability tolerance threshold. A node with the minimum topological distance is selected from the candidate node set as a matched preplan node, and a preset instruction set mapped by the preplan node is called as the predictive instruction set.

[0012] In some preferred embodiments, the candidate node set meets: ; In the formula, V candidate is a candidate node set, is a target failure probability value in a failure prediction result, V is all nodes in a knowledge graph, is a historical failure probability weight value stored in a node V i in the knowledge graph, is a preset probability tolerance threshold; The matched preplan node meets: ; In the formula, is a matched preplan node, and λ is a topological structure weight coefficient, is a shortest path edge weight sum from a current node V current to V i , and argmin() is a minimum value traversal function.

[0013] In a second aspect, the present application further provides a failure handling system of an anti-icing simulation system, comprising: A data acquisition module is configured to acquire multi-source simulation data of the anti-icing simulation system, wherein the multi-source simulation data comprises environmental simulation data and system characteristic data. A parameter calculation module is configured to determine a temperature drop rate and a humidity change rate according to the environmental simulation data, and determine a dynamic control factor in combination with the system characteristic data, wherein the dynamic control factor comprises a valve response threshold and a failure detection sensitivity, the valve response threshold is negatively correlated with the humidity change rate, and the failure detection sensitivity is positively correlated with the temperature drop rate. A fault prediction module is configured to acquire valve timing data of the anti-icing simulation system, perform fault prediction based on the valve timing data and the dynamic regulation factor by using a pre-trained timing prediction model, and obtain a fault prediction probability, wherein the valve timing data is used as input data of the timing prediction model, and the dynamic regulation factor is used as a prediction control parameter of the timing prediction model; An instruction generation module is configured to match a plan node in a pre-constructed knowledge graph according to the fault prediction probability, and generate a predictive instruction, wherein the knowledge graph comprises a static topology network constructed based on historical fault cases of the anti-icing simulation system, and the static topology network comprises a plurality of nodes, each of which is configured to store a mapping relationship between at least one fault prediction probability and an execution instruction. A fault response module is configured to execute the predictive instruction in response to a fault trigger signal of the anti-icing simulation system.

[0014] Advantages of the present application: (1) According to the method proposed in the present application, a negative / positive correlation relationship between a valve response threshold, fault detection sensitivity and environmental parameters is established by using a dynamic regulation factor. When the environmental humidity rapidly rises, the system automatically reduces the valve response threshold, so that the anti-icing device is started earlier, thereby avoiding the response lag problem caused by the fixed threshold in the traditional scheme. When the temperature sharply drops, the system actively improves the fault detection sensitivity, enhances the capture ability of the icing risk, and eliminates the protection blind area in the sudden temperature drop scene.

[0015] (2) According to the method proposed in the present application, the valve timing data and the dynamic regulation factor are synchronously input into the timing prediction model, so that the timing prediction model dynamically adjusts the probability boundary according to the environmental parameters, the prediction mechanism is evolved from single data driving to environmental-device double-track coupling, and the fault early warning has meteorological flexibility and equipment adaptability. BRIEF DESCRIPTION OF DRAWINGS

[0016] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments made with reference to the accompanying drawings: Figure 1 FIG. 1 is a flow diagram of a fault handling method of an anti-icing simulation system according to an embodiment of the present application; Figure 2 FIG. 2 is a structural diagram of a fault handling system of an anti-icing simulation system according to an embodiment of the present application; Figure 3 FIG. 3 is a structural diagram of a computer system according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] The application will be described in further detail below with reference to the drawings and embodiments. It is to be understood that the specific embodiments described herein are intended to be illustrative only and not limiting of the application. It is also to be understood that the terminology used herein is for the purpose of describing the specific embodiments only and is not intended to be limiting.

[0018] It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict. The present application will be described in further detail below with reference to the drawings and embodiments.

[0019] Please refer to Figure 1 The first embodiment of the present application provides a fault handling method of an anti-icing simulation system, which comprises: Step S10, acquiring multi-source simulation data of the anti-icing simulation system, wherein the multi-source simulation data comprises environmental simulation data and system characteristic data; In the embodiment, the multi-source simulation data of the anti-icing simulation system essentially refers to a heterogeneous data set integrating environmental dynamic simulation characteristics and system running state. Specifically, for the environmental simulation data, it mainly refers to real-time environmental parameters and their derived indicators generated by the sensor network or weather model of the anti-icing simulation system; for the system characteristic data, it mainly refers to working parameters about the real-time working state and historical performance of the anti-icing simulation system. According to different data properties, it can be roughly divided into two categories: static device attributes and dynamic running parameters. The static device attributes include but are not limited to valve types, heating power, pipeline layout topology, etc. of the system, and the dynamic running parameters include but are not limited to historical valve timing data, historical fault records, etc.

[0020] It is easy to understand that the embodiment realizes environmental-system double closed-loop feedback by simultaneously collecting environmental simulation data and system characteristic data, and establishes the coupling relationship between the two kinds of data through dynamic control factors in the subsequent steps, so as to break through the response lag of static threshold to environmental mutation (such as valve delay when humidity suddenly rises), and effectively avoid the instruction jump of discrete preplan at the critical probability point (such as triggering sharp increase of power when the probability is 59%→61%).

[0021] Step S20, determining the temperature drop rate and humidity change rate according to the environmental simulation data, and determining the dynamic control factor combining the system characteristic data, wherein the dynamic control factor comprises a valve response threshold and a fault detection sensitivity, the valve response threshold is negatively correlated with the humidity change rate, and the fault detection sensitivity is positively correlated with the temperature drop rate; The cooling rate in this step specifically refers to the temperature reduction rate of the anti-icing simulation system per unit time, with the unit of time being minutes, and the unit of the cooling rate being ℃ / min. Based on the cooling rate, the heat exchange imbalance speed inside the system can be determined, and the heat exchange imbalance speed is directly related to the phase change efficiency of liquid water to ice crystals, which further serves as the basis for analyzing the icing process.

[0022] The humidity variation rate in this step specifically refers to the humidity variation percentage of the anti-icing simulation system per unit time, with the unit of time being minutes, and the unit of the humidity variation rate being % / min. The humidity variation rate can effectively reflect the water vapor transport strength inside the system, and further determine the ice layer growth rate.

[0023] It is easy to understand that by further analyzing the cooling rate and the humidity variation rate, a dynamic control factor coupled with the environmental simulation data and the system characteristic data is obtained, which is composed of a valve response threshold and a fault detection sensitivity. Based on this, in the subsequent step, the valve response threshold and the fault detection sensitivity are used as the basis for early warning detection, which can effectively improve the accuracy of fault early warning.

[0024] In step S30, valve timing data of the anti-icing simulation system is obtained, and the valve timing data and the dynamic control factor are input into a pre-trained timing prediction model for fault prediction to obtain a fault prediction probability. The valve timing data is used as the timing feature input of the timing prediction model, and the timing prediction model determines a fault prediction boundary according to the dynamic control factor. The valve timing data is a millisecond-level record reflecting the dynamic behavior of the anti-icing system actuator, which at least includes: a timestamp sequence about valve opening and closing, a state curve about opening percentage change, and action correlation indicators (such as response delay, which refers to the time difference between command issuance and action execution; and oscillation frequency, which refers to the number of start-stop times per unit time).

[0025] In this embodiment, the valve timing data is used as the main feature input, and through necessary feature engineering processing, time series statistics (mean, variance, autocorrelation, etc.) are extracted, and the dynamic control factor is used to define the prediction boundary, so that the timing prediction model uses different parameters for prediction under different conditions. For example, when the cooling rate increases, the timing prediction model uses the dynamic control factor to compress the confidence interval, so that it predicts more accurately in high-risk scenarios, and when the humidity variation rate increases, the timing prediction model expands the fault probability judgment range to respond to the risk of sudden humidity increase in advance.

[0026] In this embodiment, the time series prediction model can adopt LSTM (Long Short-Term Memory), RNN (Recurrent Neural Network) and other feasible frameworks. The specific configuration, training process, parameter configuration and the like of the time series prediction model can be set by the person skilled in the art as needed, and the present embodiment does not limit this.

[0027] In step S40, the failure prediction probability is taken as a query vector to search for a preplan node in a pre-constructed knowledge graph, and a predictive instruction is generated. The knowledge graph includes a static topology network constructed based on historical failure cases, and the static topology network includes a plurality of nodes, each of which is used to store a mapping relationship between at least one failure prediction probability and an execution instruction. The preplan node is the smallest decision unit in the static topology network of the knowledge graph, is constructed based on historical failure cases, and is used to store an accurate mapping relationship between the failure prediction probability and the execution instruction.

[0028] The knowledge graph is a multi-dimensional relationship network constructed based on historical failure cases, and its core structure includes: The nodes include but are not limited to: a failure probability node used to store a continuous probability value; an instruction node used to bind an execution command (such as "valve opening degree 85% + heating power 5kW"); and an environmental constraint node used to record the meteorological condition boundary triggering the instruction. The topological relationship between the nodes, each node stores the mapping relationship of at least 256 historical cases, forming a continuous mapping space of probability→instruction.

[0029] In step S50, when the failure prediction probability reaches a preset threshold, the predictive instruction is executed.

[0030] In this embodiment, the preset threshold refers to a boundary value for judging the failure prediction probability. The failure prediction probability obtained in the foregoing step is compared based on the boundary value. When the failure prediction probability satisfies the boundary value, it is determined that the failure risk reaches a certain level at this time, and the system should be called to execute the pre-stored instruction set.

[0031] In a feasible implementation, the preset threshold is not a fixed value, but a dynamic boundary that is adjusted in real time with the environmental risk. The calculation formula is specifically: ; In the formula, T dynamic is the preset threshold, T base is a basic threshold (which can be determined by the equipment operation standard), R h is the humidity change rate, and R c is the temperature drop rate.

[0032] Further, in the above embodiment, the determining the temperature drop rate and the humidity change rate according to the environment simulation data comprises: determining environment temperature time series data according to the environment simulation data; determining a time window constituted by a current time and a target historical time based on the environment temperature time series data according to a preset sampling duration, a time interval between the target historical time and the current time satisfying the sampling duration; determining a difference between environment temperatures corresponding to a first end time and a last end time in the time window; and determining the temperature drop rate according to the sampling duration and the difference between the environment temperatures.

[0033] Further, in the above embodiment, the determining the temperature drop rate and the humidity change rate according to the environment simulation data comprises: determining dew point temperature time series data according to the environment simulation data; performing sliding average filtering processing on the dew point temperature time series data, and determining dew point temperature values of two sampling points closest to a current time node in the dew point temperature time series data after the filtering processing; determining a dew point temperature increment in a preset unit time based on the dew point temperature values of the two closest sampling points; and determining the humidity change rate according to the dew point temperature increment.

[0034] Further, in the above embodiment, the determining the dynamic control factor in combination with the system characteristic data comprises: extracting a structure parameter of a valve in the system characteristic data, the valve structure parameter comprising an opening / closing delay time and a steady-state leakage rate; determining a response delay compensation coefficient of the valve according to the opening / closing delay time; determining a leakage compensation rate of the valve according to the steady-state leakage rate; determining a negative correlation adjustment coefficient according to the humidity change rate; and determining the valve response threshold in combination with the response delay compensation coefficient, the leakage compensation rate, and the negative correlation adjustment coefficient.

[0035] Still further, the determining the dynamic control factor in combination with the system characteristic data comprises: determining a system heating unit degradation parameter according to the system characteristic data; determining a basic sensitivity gain according to the heating unit degradation parameter; determining a positive correlation reinforcement factor according to the temperature drop rate; and determining the fault detection sensitivity according to the basic sensitivity gain and the positive correlation reinforcement factor.

[0036] Still further, the valve response threshold satisfies a calculation formula as follows: ; In the formula, Vth is a valve response threshold, Vbase is a basic response threshold, Tdesign is a valve opening and closing delay time, epsilon is a preset safety parameter, Tactual is a valve average opening and closing delay time, kT is a delay compensation coefficient, keta is a leakage compensation rate, Vh is a humidity change rate, sigma is an environmental modulation intensity coefficient, beta is a humidity change rate modulation curve steepness factor, and eta is a steady-state leakage rate.

[0037] Meanwhile, the fault detection sensitivity satisfies the following formula: ; In the formula, S det is a fault detection sensitivity, S base is a preset reference sensitivity, delta R is a system resistance aging rate, delta is a thermal flow distribution root mean square deviation, alpha is an aging influence gain coefficient, V c is a temperature drop rate, V0 is a temperature drop intensification starting threshold, gamma min , gamma max is an extreme value of a system safety constraint parameter, and k is a preset coefficient of a control gain growth rate.

[0038] Further, the matching of the pre-constructed knowledge graph according to the dynamic fault probability, the generation of the predictive instruction set containing the hierarchical control logic, comprises: calculating an absolute difference value between a target fault probability value in a fault prediction result and a fault probability weight value stored in each node of a knowledge graph; based on a preset topological distance weight coefficient and a probability tolerance threshold, filtering a candidate node set satisfying a condition in the knowledge graph, an absolute interpolation value between each node in the candidate node set and the target fault probability value being less than the probability tolerance threshold; selecting a node with the smallest topological distance from the candidate node set as a matched preplan node, and calling a preset instruction set mapped by the preplan node as the predictive instruction set.

[0039] wherein the candidate node set satisfies: ; In the formula, V candidate is a candidate node set, is a target fault probability value in a fault prediction result, V is all nodes in a knowledge graph, is a historical fault probability weight value stored in a node V i in the knowledge graph, is a preset probability tolerance threshold. The matched preplan node satisfies: ; In the formula, is a matched preplan node, and lambda is a topological structure weight coefficient, the current node V current the shortest path edge weight sum of V i , argmin() is the minimum value traversal function.

[0040] Please refer to Figure 2 , the second embodiment of the application provides a fault handling system of an anti-icing simulation system, comprising: a data acquisition module 210, configured to acquire multi-source simulation data of the anti-icing simulation system, wherein the multi-source simulation data comprises environmental simulation data and system characteristic data; a parameter calculation module 220, configured to determine a temperature drop rate and a humidity change rate according to the environmental simulation data, and determine a dynamic regulation factor in combination with the system characteristic data, wherein the dynamic regulation factor comprises a valve response threshold and a fault detection sensitivity, the valve response threshold is in a negative correlation with the humidity change rate, and the fault detection sensitivity is in a positive correlation with the temperature drop rate; a fault prediction module 230, configured to acquire valve timing data of the anti-icing simulation system, perform fault prediction by using a pre-trained timing prediction model based on the valve timing data and the dynamic regulation factor, and obtain a fault prediction probability, wherein the valve timing data is used as input data of the timing prediction model, and the dynamic regulation factor is used as a prediction control parameter of the timing prediction model; an instruction generation module 240, configured to match a plan node in a pre-constructed knowledge graph according to the fault prediction probability, and generate a predictive instruction, wherein the knowledge graph comprises a static topology network constructed based on historical fault cases of the anti-icing simulation system, and the static topology network comprises a plurality of nodes, each of which is configured to store a mapping relationship between at least one fault prediction probability and an execution instruction; a fault response module 250, configured to execute the predictive instruction in response to a fault trigger signal of the anti-icing simulation system.

[0041] The third embodiment of the application further provides an electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the method of the first embodiment.

[0042] The fourth embodiment of the application further provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to be executed by the computer to implement the method of the first embodiment.

[0043] The following refers to Figure 3, which shows a structural diagram of a server computer system suitable for implementing the method, system, and device embodiments of the present application. Figure 3 The server shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0044] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303. Various programs and data required for system operation are also stored in the RAM 303. The CPU 301, ROM 302 and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0045] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, and the like; an output section 307 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like, is installed in the drive 310 as needed so that computer programs read therefrom can be installed into the storage section 308 as needed.

[0046] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program in accordance with embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309, and / or installed from the removable media 311. When the computer program is executed by the central processing unit (CPU) 301, the above-described functions defined in the methods of the present application are performed. Note that the computer readable medium described above in the present application can be either a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the foregoing.

[0047] More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus or device. In the present application, a computer readable signal medium can include a computer readable program code carried by a data signal in a baseband or as part of a carrier wave. Such a propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. Computer readable signal media can be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0048] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0049] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0050] The terms "first", "second", etc. are used to distinguish similar objects, not to describe or indicate a particular order or sequence.

[0051] The term "comprising" or any other similar term is intended to encompass the inclusion of one or more elements, steps, or components, but not to the exclusion of any other elements, steps, or components. It is noted that some of the features and blocks can have been presented in terms of sequences of actions, but the ordering of such actions can not necessarily be indicative of the specific sequencing, depending on the functionality involved. Some actions can be performed concurrently, in response to interrupts, and the like, and the ordering of actions can not necessarily be construe as critical.

[0052] Thus far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the drawings.

[0053] The above merely provides an example of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the scope of claims of the present application.

Claims

1. A fault handling method for an anti-icing simulation system, characterized in that: The method comprises: Acquiring multi-source simulation data of an anti-icing simulation system, wherein the multi-source simulation data includes environmental simulation data and system characteristic data; Determine the temperature drop rate and humidity change rate based on the environmental simulation data, and determine a dynamic control factor in combination with the system characteristic data, wherein the dynamic control factor includes a valve response threshold and a fault detection sensitivity, wherein the valve response threshold is negatively correlated with the humidity change rate, and the fault detection sensitivity is positively correlated with the temperature drop rate; Obtaining valve timing data of the anti-icing simulation system, inputting the valve timing data and the dynamic control factor into a pre-trained timing prediction model for fault prediction to obtain a fault prediction probability, wherein the valve timing data is used as a timing feature input of the timing prediction model, and the timing prediction model determines a fault prediction boundary according to the dynamic control factor; Using the fault prediction probability as a query vector, searching for a plan node in a pre-constructed knowledge graph and generating a predictive instruction, the knowledge graph comprising a static topology network constructed based on historical fault cases, the static topology network comprising a plurality of nodes, each of the nodes being used to store a mapping relationship between at least one fault prediction probability and an execution instruction; When the fault prediction probability reaches a preset threshold, the predictive instruction is executed.

2. The fault handling method of the anti-icing simulation system according to claim 1, characterized in that: Determining the temperature drop rate and humidity change rate according to the environmental simulation data includes: Determining ambient temperature time series data according to the environmental simulation data; According to the preset sampling duration, a time window formed by the current moment and the target historical moment is determined based on the ambient temperature time series data, and the time interval between the target historical moment and the current moment meets the sampling duration; Determine the difference in ambient temperature between the first and last moments in the time window; The temperature drop rate is determined according to the sampling time and the difference between the ambient temperatures.

3. The fault handling method of the anti-icing simulation system according to claim 1, characterized in that: Determining the temperature drop rate and humidity change rate according to the environmental simulation data includes: Determining dew point temperature time series data according to the environmental simulation data; Performing a sliding average filtering process on the dew point temperature time series data, and determining the dew point temperature values ​​of two sampling points closest to the current time node in the filtered dew point temperature time series data; Determine the dew point temperature increment within a preset unit time based on the dew point temperature values ​​of the two most recent sampling points; The humidity change rate is determined based on the dew point temperature increment.

4. The fault handling method of the anti-icing simulation system according to claim 1, characterized in that: Determining the dynamic control factor in combination with the system characteristic data includes: Extracting valve structural parameters from the system characteristic data, wherein the valve structural parameters include opening and closing delay time and steady-state leakage rate; determining a valve response delay compensation coefficient according to the opening and closing delay time; Determine the valve leakage compensation rate based on the steady-state leakage rate; determining a negative correlation adjustment coefficient according to the humidity change rate; The valve response threshold is determined by combining the response delay compensation coefficient, the leakage compensation rate, and the negative correlation adjustment coefficient.

5. The fault handling method of the anti-icing simulation system according to claim 1, characterized in that: Determining the dynamic control factor in combination with the system characteristic data includes: determining degradation parameters of the system heating unit according to the system characteristic data; determining a basic sensitivity gain according to the heating unit degradation parameter; determining a positive correlation enhancement factor according to the temperature drop rate; The fault detection sensitivity is determined according to the basic sensitivity gain and the positive correlation enhancement factor.

6. The fault handling method of the anti-icing simulation system according to claim 4, characterized in that: The valve response threshold is calculated by the following formula: ； Where, is the valve response threshold, is the basic response threshold, is the valve opening and closing delay time, ϵ is the preset safety parameter, is the average opening and closing delay time of the valve, is the delay compensation coefficient, k η is the leakage compensation rate, V h is the humidity change rate, σ is the environmental modulation intensity coefficient, β is the steepness factor of the humidity change rate modulation curve, and η is the steady-state leakage rate.

7. The fault handling method of the anti-icing simulation system according to claim 5, characterized in that: The fault detection sensitivity is calculated by the following formula: ； Where S det is the fault detection sensitivity, S base is the preset reference sensitivity, ΔR is the system resistance aging rate, δ is the root mean square deviation of the heat flux distribution, α is the aging effect gain coefficient, V c is the temperature drop rate, V0 is the temperature drop enhancement starting threshold, γ min , γ max is the extreme value of the system safety constraint parameter, and k is the preset coefficient of the control gain growth rate.

8. The fault handling method of the anti-icing simulation system according to claim 1, characterized in that: The method uses the fault prediction probability as a query vector, retrieves the plan node in the pre-built knowledge graph, and generates predictive instructions, including: Calculate the absolute difference between the target fault probability value in the fault prediction result and the fault probability weight stored in each node of the knowledge graph; Based on a preset topological distance weight coefficient and a probability tolerance threshold, a set of candidate nodes that meet the conditions is screened in the knowledge graph, where the absolute interpolation between each node in the candidate node set and the target failure probability value is less than the probability tolerance threshold; A node with the smallest topological distance is selected from the candidate node set as a matching plan node, and a preset instruction set mapped to the plan node is called as the predictive instruction.

9. The fault handling method of the anti-icing simulation system according to claim 8, characterized in that: The candidate node set satisfies: ； Where V candidate is the candidate node set, is the target fault probability value in the fault prediction result, V is all the nodes in the knowledge graph, is a node V in the knowledge graph i The stored historical failure probability weights, is the preset probability tolerance threshold; The matching plan node satisfies: ； Where, is the matching plan node, λ is the topological structure weight coefficient, is the current node V current to V i The sum of the shortest path edge weights, argmin() is the minimum traversal function.

10. A fault handling system for an anti-icing simulation system, characterized in that: The system comprises: A data acquisition module, configured to acquire multi-source simulation data of an anti-icing simulation system, wherein the multi-source simulation data includes environmental simulation data and system characteristic data; a parameter calculation module, configured to determine a temperature drop rate and a humidity change rate based on the environmental simulation data, and determine a dynamic control factor in combination with the system characteristic data, wherein the dynamic control factor includes a valve response threshold and a fault detection sensitivity, wherein the valve response threshold is negatively correlated with the humidity change rate, and the fault detection sensitivity is positively correlated with the temperature drop rate; a fault prediction module, configured to obtain valve timing data of the anti-icing simulation system, and perform fault prediction based on the valve timing data and the dynamic control factor using a pre-trained timing prediction model to obtain a fault prediction probability, wherein the valve timing data serves as input data of the timing prediction model, and the dynamic control factor serves as a prediction control parameter of the timing prediction model; an instruction generation module, configured to match a plan node in a pre-constructed knowledge graph based on the fault prediction probability and generate a predictive instruction, wherein the knowledge graph includes a static topology network constructed based on historical fault cases of the anti-icing simulation system, the static topology network including a plurality of nodes, each of the nodes being configured to store a mapping relationship between at least one fault prediction probability and an execution instruction; A fault response module is used to respond to a fault trigger signal of the anti-icing simulation system and execute the predictive instruction.

Images