Fault diagnosis method for pneumatic cabin pressure regulating system

Abstract

The invention relates to the technical field of aircraft environment control, in particular to a pneumatic type cabin pressure adjusting system fault diagnosis method. A fault diagnosis logic is established by researching a cabin pressure regulating system fault mode and a historical database, extracting feature data, specifying a feature data threshold value, and when onboard detection data exceeds the threshold value, a fault part is judged according to the fault diagnosis logic. After the aircraft cockpit pressure regulating system breaks down, a user can quickly judge the fault reason and accurately isolate the fault position, the problem that the cockpit pressure regulator returns to a factory without faults due to the fact that the fault of a client is difficult to locate is solved, and therefore the troubleshooting efficiency of an aircraft system is improved, and the troubleshooting period is shortened.

Description

Technical Field

[0001] The invention relates to the technical field of aircraft environment control, and in particular to a method for diagnosing faults of a pneumatic cabin pressure regulating system. Background Art

[0002] As aircraft become more complex, integrated and intelligent. In order to meet the continuous guarantee requirements, the integrated technology of fault diagnosis, prognosis and health management (PHM) has received more and more attention, development and application from all over the world. In September 2023, during the fifth "Aviation Fault Diagnosis and Health Management Forum" seminar, a certain institute made special topics such as aviation guarantee system construction, focusing on the challenges and opportunities currently facing the construction of the aviation guarantee system, from the demand and problem orientation a) the scale of carrying guarantee is large, and maneuvering is difficult to achieve; b) the readiness rate is not high, and high-intensity maneuvering is difficult to sustain; c) the cost of using guarantee is high and large-scale maneuvering cannot be achieved; d) there are many basic problems in the guarantee field, which leads to the overall concept of aviation guarantee system construction, namely "agile" and "intelligent" guarantee system, one of its important contents is system fault diagnosis and health management.

[0003] At present, the research and application of fault diagnosis and health management technology is started from top to bottom, especially starting from a certain model platform, starting from the large aircraft system, and then extending to each molecular system, and starting to study and apply fault diagnosis and health management technology to the cabin pressure regulation system.

[0004] The function of the aircraft cabin pressure regulation system is to provide flight personnel with a cabin pressure and its changing rules that meet the physiological requirements of the human body. Various types of faults in the cabin pressure system have different degrees of impact on flight missions and flight safety, and the faults are difficult to locate and the troubleshooting cycle is long (from weeks to months), which has attracted much attention from users. For example: On October 12, 2023, a certain aircraft had a high-altitude low-pressure fault. Due to the lack of fault diagnosis data information, the fault was difficult to locate. The on-board product (CYT-41 / 42 / 25 cabin pressure regulator) was returned to the factory for inspection twice. The fault inspection members came from multiple units. The first appearance inspection, industrial perspective, and performance retest; the second disassembly inspection, the second accessory vacuum bellows was returned to the manufacturing unit for inspection, which lasted for 3 months. Although it was finally proved that it was not a problem with the product itself, it consumed a lot of manpower, material resources and time.

[0005] Carry out research on fault diagnosis technology of cabin pressure regulation system, based on various data analysis and fault diagnosis method research, form fault diagnosis model and logic, support rapid fault analysis and location, and rapid troubleshooting. Summary of the invention

[0006] Purpose of the Invention

[0007] A fault diagnosis method for a pneumatic cabin pressure regulating system is proposed, which can diagnose typical faults and quickly determine the fault location, thereby reducing the troubleshooting time.

[0008] Technical Solution

[0009] A method for diagnosing a fault of a pneumatic cabin pressure regulating system is disclosed. The method studies the fault mode and history database of the cabin pressure regulating system, extracts characteristic data, specifies the characteristic data threshold, and establishes a fault diagnosis logic. When the on-board detection data exceeds the threshold, the fault location is determined according to the fault diagnosis logic.

[0010] The steps include:

[0011] Step 1, extended failure mode analysis, including system definition, failure mode and effect analysis, fault detection method analysis, fault symptom analysis, sensor layout analysis, and available technology analysis for fault diagnosis.

[0012] Step 2, establish the cabin pressure regulation system historical database, including normal data and fault data, divided into simulation data, historical flight data, maintenance data, BIT data, model data and structure data.

[0013] Step 3: Establish a data analysis model and process the data. Since the cabin pressure regulation system has a complex structure and variable working conditions, the onboard system is greatly disturbed by the environment, upstream and downstream systems, and components during flight. Therefore, the monitored signals need to be processed before fault diagnosis.

[0014] Step 4: effectively extract fault features, eliminate interference effects, highlight fault features, and process raw data into feature data required for fault diagnosis through data preprocessing, feature extraction, and feature dimension reduction data optimization algorithms;

[0015] Step 5: Establish fault diagnosis logic. The main function of the fault diagnosis model is to select a suitable fault diagnosis algorithm, establish and train the fault diagnosis model for the fault data after data preprocessing by the data analysis model, so that it has a good fault diagnosis effect and a certain degree of robustness.

[0016] Step 6, establish fault diagnosis logic: 1) Clean, check for deficiencies, and fill in gaps in the historical data of the pressure regulation system, and divide the training set and test set according to a certain ratio; 2) By analyzing the data feature distribution of the training set, select the appropriate sensor monitoring threshold, convert the preprocessed data into Boolean values, and establish a diagnostic rule table; 3) According to the selected sensor monitoring threshold, convert the test set data into Boolean values, and generate a Boolean value comparison table; 4) Based on the diagnostic rule table and the Boolean value comparison table, determine whether a fault has occurred and the location of the fault, and achieve fault isolation.

[0017] Furthermore, the fault diagnosis logic of the failure mode of the cabin adjustment altitude being lower than 2400m: two conditions are met:

[0018] (1. When the flight altitude is within the range of 2400-7000m, the absolute cabin pressure is maintained at A±1.33kPa, where A is greater than 78kPa and less than 100kPa;

[0019] (2. When the flight altitude is greater than 7000m and the cabin residual pressure is 34.5±1.33) kPa, it is a product failure. The fault location is the reduction in the tension value of the vacuum bellows assembly in the product.

[0020] Furthermore, the fault diagnosis logic of the failure mode of the cabin adjustment altitude being lower than 2400m: two conditions are met:

[0021] 1. When the flight altitude is within the range of 2400-7000m, the absolute cabin pressure is maintained at A±1.33kPa, where A is greater than 78kPa and less than 100kPa;

[0022] 2. When the flight altitude is greater than 7000m, the cabin residual pressure is 34.5±1.33kPa, which is a product failure. The fault location is the reduction of the tension value of the vacuum bellows assembly in the product.

[0023] Furthermore, the diagnostic logic of the high cabin pressure fault mode satisfies the following three conditions:

[0024] 1) When the flight altitude is below 2400m, the cabin residual pressure is greater than 4kPa as the altitude increases; or when the flight altitude is within the range of 2400-7000m, the cabin absolute pressure is greater than 80.3kPa as the altitude increases; or when the flight altitude is above 7000m, the cabin residual pressure is greater than 36kPa as the altitude increases; 2) The cabin air supply is normally greater than 200kg / h and less than 700kg / h; 3) The system exhaust pipe is not blocked. This is a product failure, and the fault location is the blockage of the internal control valve of the product, the blockage of the internal exhaust pipe of the product, and the leakage of the control cavity in the product.

[0025] Furthermore, the diagnostic logic of the low cabin pressure fault mode satisfies the following conditions:

[0026] 1) In the flight altitude range of 2400-7000m, the cabin pressure is less than 70.3kPa; or when the flight altitude is greater than 7000m, the cabin residual pressure is less than 29.5kPa; 2) The cabin air supply is normal, greater than 200kg / h and less than 700kg / h; 3) The ground cabin air tightness inspection is qualified. This is a product failure, and the fault part is the internal control valve leakage or control cavity leakage or shock absorber leakage or sizing hole blockage.

[0027] Furthermore, the diagnostic logic for the fault mode of cabin pressure growth rate exceeding the standard by more than 0.67 kPa / s was established. The following conditions are met:

[0028] 1) In the regulation area, the cabin pressure growth rate is greater than 0.67 kPa / s from the flight altitude above 2400m to the ceiling;

[0029] 2) The increase in cabin air supply within 3 seconds is less than 300kg / h;

[0030] 3) If the cabin residual pressure is greater than 4kPa, it is a product failure, and the fault location is air leakage in the product control chamber.

[0031] Furthermore, the cabin pressure drop rate exceeds the standard, greater than 1.33 kPa / s, and the fault mode diagnostic logic meets the following conditions:

[0032] 1) In the adjustment zone (flight altitude above 2400m to the ceiling), the cabin pressure drop rate is greater than 1.33kPa / s;

[0033] 2) The decrease in cabin air supply within 3 seconds is less than 500kg / h;

[0034] 3) If the cabin residual pressure is greater than 4kPa, it is a product failure, and the fault location is air leakage in the product control chamber.

[0035] Furthermore, the fault diagnosis algorithms in step 5 include support vector machine SVM, decision tree algorithm, and KNN algorithm.

[0036] The beneficial effects of this application are:

[0037] When an aircraft cabin pressure regulation system fails, users can quickly determine the cause of the failure, accurately isolate the faulty part, and resolve the problem of the cabin pressure regulator being returned to the factory without a fault due to customers' difficulty in locating the fault, thereby improving the efficiency of aircraft system troubleshooting and shortening the troubleshooting cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Schematic diagram of the diagnostic method. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical scheme and advantages of the implementation of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail in combination with the embodiment of the present invention. In the example, the same or similar reference numerals throughout represent the same or similar originals or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of them. The embodiments described below by reference are exemplary and intended to be used to explain the present invention, and should not be construed as limitations on the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention. The following is a detailed description in combination with the embodiments of the present invention.

[0040] Core invention point: Construct a state detection model and fault diagnosis logic of the pneumatic cabin pressure regulation system to implement fault location.

[0041] Secondary invention point 1: Construct a cabin pressure regulation system status detection model, which mainly detects parameters such as atmospheric pressure, atmospheric altitude, cabin pressure, cabin air supply, static pressure felt by the cabin pressure regulator, and cabin pressure regulator control chamber pressure.

[0042] Secondary invention point 2: A fault diagnostic device is set up to receive parameters such as atmospheric pressure, atmospheric altitude, cabin pressure, cabin air supply, static pressure felt by the cabin pressure regulator, and cabin pressure regulator control chamber pressure.

[0043] Secondary invention point 3: Construct fault diagnosis steps, including sensor detection, fault detection, troubleshooting and repair, status detection and continuous fault diagnosis.

[0044] Secondary invention point 4: Building airborne fault diagnosis logic, including data training, data feature distribution, sensor detection threshold, fault isolation, etc.

[0045] Minor invention point 5: A fault diagnosis logic for the failure mode of the cabin starting altitude being lower than 2400m is established: if two conditions are met (1. When the flight altitude is within the range of (2400-7000)m, the absolute cabin pressure is maintained at (A±1.33)kPa, where A is greater than 78kPa and less than 100kPa; 2. When the flight altitude is greater than 7000m, the cabin residual pressure is (34.5±1.33)kPa), it is a product failure, and the fault location is the reduction in the tension value of the vacuum bellows assembly in the product.

[0046] Secondary invention point 6: The diagnostic logic of the high cabin pressure fault mode is established. The following three conditions are met: 1) When the flight altitude is below 2400m, the cabin residual pressure is greater than 4kPa as the altitude increases; or when the flight altitude is within the range of (2400-7000)m, the cabin absolute pressure is greater than 80.3kPa as the altitude increases; or when the flight altitude is above 7000m, the cabin residual pressure is greater than 36kPa as the altitude increases; 2) The cabin air supply is normal (greater than 200kg / h and less than 700kg / h); 3) The system exhaust pipe is not blocked. It is a product failure, and the fault location is the blockage of the internal control valve of the product, the blockage of the internal exhaust pipe of the product, and the leakage of the control cavity in the product.

[0047] Minor invention point 7: The diagnostic logic of the low cabin pressure fault mode is established. The following conditions are met: 1) In the flight altitude range of (2400-7000)m, the cabin pressure is less than 70.3kPa; or when the flight altitude is greater than 7000m, the cabin residual pressure is less than 29.5kPa; 2) The cabin air supply is normal (greater than 200kg / h and less than 700kg / h); 3) The ground cabin air tightness inspection is qualified. It is a product failure, and the fault location is the internal control valve leakage or control cavity leakage or shock absorber leakage or sizing hole blockage, etc.

[0048] Minor invention point 8: The diagnostic logic of the failure mode of cabin pressure growth rate exceeding the standard (greater than 0.67kPa / s) is established. The following conditions are met: 1) In the adjustment area (flight altitude above 2400m to the ceiling), the cabin pressure growth rate is greater than 0.67kPa / s; 2) The increase in cabin air supply within 3 seconds is less than 300kg / h; 3) The cabin residual pressure is greater than 4kPa. It is a product failure, and the fault location is the leakage of the product control chamber.

[0049] Minor invention point 9: The diagnostic logic of the fault mode of cabin pressure drop rate exceeding the standard (greater than 1.33kPa / s) is established. If the following conditions are met: 1) In the adjustment area (flight altitude above 2400m to the ceiling), the cabin pressure drop rate is greater than 1.33kPa / s; 2) The drop in cabin air supply within 3 seconds is less than 500kg / h; 3) The cabin residual pressure is greater than 4kPa. This is a product failure, and the fault location is the leakage of the product control chamber.

[0050] Step 1, extended failure mode analysis, including system definition, failure mode and effect analysis, fault detection method analysis, fault symptom analysis, sensor layout analysis, and available technology analysis for fault diagnosis.

[0051] Step 2, establish the cabin pressure regulation system historical database, including normal data and fault data, which are divided into simulation data, historical flight data, maintenance data, BIT data, model data and structure data.

[0052] Step 3: Establish a data analysis model and process the data. Since the cabin pressure regulation system has a complex structure and variable working conditions, the onboard system is greatly disturbed by the environment, upstream and downstream systems, and components during flight. Therefore, the monitored signals need to be processed before fault diagnosis.

[0053] Step 4: effectively extract fault features, eliminate interference effects, highlight fault features, and process raw data into feature data required for fault diagnosis through data preprocessing, feature extraction, feature dimension reduction and other data optimization algorithms;

[0054] Step 5, establish fault diagnosis logic. The main function of the fault diagnosis model is to select a suitable fault diagnosis algorithm, establish and train the fault diagnosis model for the fault data after data preprocessing by the data analysis model, so that it has a good fault diagnosis effect and a certain robustness. Currently, the commonly used fault diagnosis algorithms include support vector machine (SVM), decision tree algorithm, KNN algorithm, etc.

[0055] Step 6, establish fault diagnosis logic: ① Clean, check for deficiencies, and fill in gaps in the historical data of the pressure regulation system, and divide the training set and test set according to a certain ratio; ② By analyzing the data feature distribution of the training set, select the appropriate sensor monitoring threshold, convert the preprocessed data into Boolean values, and establish a diagnostic rule table; ③ According to the selected sensor monitoring threshold, convert the test set data into Boolean values, and generate a Boolean value comparison table; ④ Based on the diagnostic rule table and the Boolean value comparison table, determine whether a fault has occurred and the location of the fault, and achieve fault isolation.

[0056] It is understood by those skilled in the art that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of ordinary technicians in the field to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and unless defined as here, will not be interpreted with idealized or overly formal meanings. The specific implementation methods described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the present invention. Within the spirit and principle of the present invention, any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment of equivalent changes for application in other fields, but any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the technical solution content of the present invention, any modification, equivalent replacement, improvement, etc., made according to the technical essence of the present invention, should be included in the protection scope of the present invention.

Claims

1. A method for diagnosing a fault in a pneumatic cabin pressure regulating system, characterized in that: By studying the fault modes and historical database of the cabin pressure regulation system, extracting characteristic data, defining characteristic data thresholds, and establishing fault diagnosis logic, when the onboard detection data exceeds the threshold, the fault location is determined based on the fault diagnosis logic.

2. The method according to claim 1, characterized in that The steps include: Step 1, extended failure mode analysis, including system definition, failure mode and effect analysis, fault detection method analysis, fault symptom analysis, sensor layout analysis, and available technology analysis for fault diagnosis; Step 2, establish a historical database of the cabin pressure regulation system, including normal data and fault data, which are divided into simulation data, historical flight data, maintenance data, BIT data, model data and structure data; Step 3: Establish a data analysis model and process the data. Since the cabin pressure regulation system has a complex structure and variable working conditions, the onboard system is greatly disturbed by the environment, upstream and downstream systems, and components during flight. Therefore, the monitored signals need to be processed before fault diagnosis. Step 4: effectively extract fault features, eliminate interference effects, highlight fault features, and process raw data into feature data required for fault diagnosis through data preprocessing, feature extraction, and feature dimension reduction data optimization algorithms; Step 5: Establish fault diagnosis logic. The main function of the fault diagnosis model is to select a suitable fault diagnosis algorithm, establish and train the fault diagnosis model for the fault data after data preprocessing by the data analysis model, so that it has a good fault diagnosis effect and a certain degree of robustness. Step 6, establish fault diagnosis logic: 1) clean, check for deficiencies, and fill in gaps in the historical data of the pressure regulation system, and divide the training set and the test set according to a certain ratio; 2) select the appropriate sensor monitoring threshold by analyzing the data feature distribution of the training set, convert the preprocessed data into Boolean values, and establish a diagnosis rule table; 3) convert the test set data into Boolean values ​​based on the selected sensor monitoring threshold, and generate a Boolean value comparison table; 4) Based on the diagnostic rule table and the Boolean value comparison table, determine whether a fault has occurred and the location of the fault, and achieve fault isolation.

3. The method according to claim 2, characterized in that Fault diagnosis logic for the failure mode of the cabin altitude adjustment being lower than 2400m: two conditions are met: (1. When the flight altitude is within the range of 2400-7000m, the absolute cabin pressure is maintained at A±1.33kPa, where A is greater than 78kPa and less than 100kPa; (2. When the flight altitude is greater than 7000m, the cabin residual pressure is 34.5±1.33kPa, which indicates a product failure. The failure location is the reduction in the tension value of the vacuum bellows assembly in the product.

4. The method according to claim 3, characterized in that Fault diagnosis logic for the failure mode of the cabin altitude adjustment being lower than 2400m: two conditions are met:

1. When the flight altitude is within the range of 2400-7000m, the absolute cabin pressure is maintained at A±1.33kPa, where A is greater than 78kPa and less than 100kPa; 2. When the flight altitude is greater than 7000m, the cabin residual pressure is 34.5±1.33kPa, which is a product failure. The fault location is the reduction of the tension value of the vacuum bellows assembly in the product.

5. The method according to claim 4, characterized in that Diagnostic logic for high cabin pressure fault mode; meets the following three conditions: 1) When the flight altitude is below 2400m, the cabin residual pressure is greater than 4kPa as the altitude increases; or when the flight altitude is between 2400-7000m, the cabin absolute pressure is greater than 80.3kPa as the altitude increases; or when the flight altitude is above 7000m, the cabin residual pressure is greater than 36kPa as the altitude increases; 2) The cabin air supply is normally greater than 200kg / h and less than 700kg / h; 3) The system's exhaust pipe is not blocked; if so, it is a product failure, and the faulty parts are the blockage of the product's internal control valve, the blockage of the product's internal exhaust pipe, or air leakage in the product's internal control chamber.

6. The method according to claim 5, characterized in that Diagnostic logic for low cabin pressure fault mode; meets the following conditions: 1) When the flight altitude is between 2400m and 7000m, the cabin pressure is less than 70.3kPa; or when the flight altitude is greater than 7000m, the cabin residual pressure is less than 29.5kPa; 2) The cabin air supply is normal, greater than 200kg / h and less than 700kg / h; 3) The ground cockpit air tightness inspection is qualified; then it is a product failure, and the fault location is the product's internal control valve leakage or control cavity leakage or shock absorber leakage or sizing hole blockage.

7. The method according to claim 6, characterized in that The diagnostic logic of the fault mode of the cabin pressure growth rate exceeding the standard by more than 0.67 kPa / s; the following conditions are met: 1) In the regulation area, the cabin pressure growth rate is greater than 0.67 kPa / s from the flight altitude above 2400m to the ceiling; 2) The increase in cabin air supply within 3 seconds is less than 300kg / h; 3) If the cabin residual pressure is greater than 4kPa, it is a product failure and the fault location is air leakage in the product control chamber.

8. The method according to claim 7, characterized in that The cabin pressure drop rate exceeds the standard, greater than 1.33 kPa / s. The diagnostic logic of the fault mode meets the following conditions: 1) In the regulation area, the cabin pressure drop rate is greater than 1.33 kPa / s from the flight altitude above 2400m to the ceiling; 2) The decrease in cabin air supply within 3 seconds is less than 500kg / h; 3) If the cabin residual pressure is greater than 4kPa, it is a product failure and the fault location is air leakage in the product control chamber.

9. The method according to claim 8, characterized in that The fault diagnosis algorithms in step 5 include support vector machine SVM, decision tree algorithm, and KNN algorithm.

Images