Fault diagnosis method for helicopter transmission system

Abstract

The invention belongs to the technical field of helicopter transmission fault diagnosis, and discloses a fault diagnosis method for a helicopter transmission system, and the method comprises the following steps: S1, building an analysis experiment table for vibration data collection, and obtaining the name and vibration data of each transmission part; s2, performing data analysis on the vibration data of each transmission part to obtain fault vibration characteristics of each transmission part; s3, establishing a query engine and a database, and storing the name, the vibration data and the fault vibration characteristics of each transmission part into the database; according to the invention, the fault part and the fault type thereof can be identified, the diagnosis accuracy can be improved, and a powerful guarantee is provided for timely repair and maintenance of equipment; through the construction of a query engine, the system can be easily expanded to meet higher data processing requirements along with the increase of the number of transmission parts and the accumulation of vibration data.

Description

Technical Field

[0001] The present invention relates to the technical field of helicopter transmission fault diagnosis, and more specifically, to a fault diagnosis method for a helicopter transmission system. Background Art

[0002] When a helicopter transmission system fails during operation, it is often difficult for relevant personnel to diagnose the type of failure in a timely and accurate manner. In addition, with the continuous accumulation of usage records, a large amount of flight parameter data, vibration data, and process processing data are stored on the aviation equipment big data management, intelligent analysis, and application service platform. How to quickly and efficiently retrieve the required data information from such a huge database has become an important issue that needs to be solved urgently.

[0003] In view of this, the present invention proposes a fault diagnosis method for a helicopter transmission system to solve the above problem. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a fault diagnosis method for a helicopter transmission system, comprising the following steps:

[0005] S1. Establish an analysis test bench for vibration data collection, and then obtain the name of each transmission part and its vibration data;

[0006] S2. Analyze the vibration data of each transmission component to obtain the fault vibration characteristics of each transmission component;

[0007] S3, establishing a query engine and a database, and storing the name, vibration data and fault vibration characteristics of each transmission part in the database;

[0008] S4. Input the name of each transmission component and the current vibration data into the query engine to obtain the fault type corresponding to each transmission component.

[0009] Preferably, the step of establishing an analysis test bench for collecting vibration data and obtaining the name of each transmission component and its vibration data includes:

[0010] Establish an analysis test bench and obtain the names of the transmission parts in the analysis test bench. The establishment of the analysis test bench includes: reduction box design, sensor layout design, typical fault design and fault part replacement design;

[0011] The sensor layout design is used to obtain the vibration data corresponding to each transmission part of the analysis test bench under normal working conditions and fault types.

[0012] Preferably, the analysis test bench is mainly composed of a reduction gearbox, a shaft assembly, a load and a fault simulation component, and the reduction gearbox includes a main reduction gearbox, an intermediate reduction gearbox and a tail reduction gearbox.

[0013] Preferably, the step of obtaining vibration data corresponding to each transmission part of the analysis test bench under normal working conditions and under fault types through sensor layout design includes:

[0014] Arrange vibration sensors on each transmission part of the analysis test bench, and the vibration sensors record vibration data of each transmission part, and the vibration data includes normal vibration data and fault vibration data;

[0015] The vibration data of the transmission parts under the ideal state at different speeds are recorded as normal vibration data;

[0016] The vibration data of the transmission parts under the fault type at different speeds are recorded as fault vibration data.

[0017] Preferably, the step of designing a replacement for a faulty part includes:

[0018] Record each transmission component with a fault type as a faulty component;

[0019] Obtain replacement steps for each fault type of each fault component in the historical records;

[0020] Associate the faulty part with the replacement steps for the corresponding fault type.

[0021] Preferably, the step of analyzing the vibration data of each transmission component to obtain the fault vibration characteristics of each transmission component includes:

[0022] Apply demodulation spectrum and envelope spectrum analysis to the normal vibration data and fault vibration data of the transmission component, thereby obtaining distinguishing features between the normal vibration data and the fault vibration data, and using the distinguishing features as the fault vibration features of the transmission component;

[0023] By performing demodulation spectrum and envelope spectrum analysis on the remaining transmission parts in turn, the fault vibration characteristics of each transmission part can be obtained.

[0024] Preferably, the step of establishing a query engine and a database, and storing the name, vibration data and fault vibration characteristics of each transmission component in the database includes:

[0025] Build and run a Hadoop cluster, which includes HDFS and YARN;

[0026] Install and configure Hive and the Hive database, install Impala and connect Impala to the Hive database to obtain the query engine and database;

[0027] The name, vibration data and fault vibration characteristics of each transmission component are configured to impalad and the configuration paths of Hadoop and Hive are specified, wherein the name, vibration data and fault vibration characteristics of each transmission component are stored in the Hive database.

[0028] Preferably, the step of inputting the name of each transmission component and the current vibration data into the query engine comprises:

[0029] Get the name of each transmission part and the corresponding current vibration data;

[0030] Load the names of each transmission component into the HDFS of the query engine;

[0031] The names of each transmission component create a table pointing to the database in Hive, and the database can be accessed through Hive metadata;

[0032] The database can output the normal vibration data and fault vibration characteristics corresponding to each transmission component.

[0033] Preferably, the loading method is:

[0034] This is done through Hive's LOAD-DATA statement.

[0035] Preferably, the step of obtaining the fault type corresponding to each transmission component includes:

[0036] Compare the current vibration data of each transmission component with the normal vibration data, and record the transmission component corresponding to the different current vibration data as the current faulty component;

[0037] The current vibration data corresponding to the current faulty component is matched with the fault vibration feature, and the fault type corresponding to the matched fault vibration feature is used as the fault type of the faulty component.

[0038] The technical effects and advantages of the fault diagnosis method for a helicopter transmission system of the present invention are as follows:

[0039] 1. By comparing the current vibration data with the normal vibration data and matching it with the fault vibration characteristics, the system can accurately identify the faulty parts and their fault types; this data-based fault diagnosis method not only improves the accuracy of diagnosis, but also greatly shortens the diagnosis time, providing a strong guarantee for the timely repair and maintenance of equipment;

[0040] 2. Through the construction of the query engine, the system can be easily expanded to meet higher data processing requirements as the number of transmission parts increases and vibration data accumulates; at the same time, it is also convenient for subsequent functional upgrades and optimizations, providing the possibility of continuous development and improvement for subsequent queries and the addition of transmission parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic flow chart of a fault diagnosis method for a helicopter transmission system according to the present invention;

[0042] Figure 2 It is a structural schematic diagram of a fault diagnosis system for a helicopter transmission system of the present invention;

[0043] Figure 3 This is a schematic diagram of the sensor layout design of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Example 1

[0046] See also Figure 1 As shown, this embodiment provides a fault diagnosis method for a helicopter transmission system, comprising:

[0047] S1. Establish an analysis test bench for vibration data collection, and then obtain the name of each transmission part and its vibration data. The establishment of the analysis test bench includes: reduction box design, sensor layout design, typical fault design and fault part replacement design;

[0048] S2. Analyze the vibration data of each transmission component to obtain the fault vibration characteristics of each transmission component;

[0049] S3, establishing a query engine and a database, and storing the name, vibration data and fault vibration characteristics of each transmission part in the database;

[0050] S4. Input the name of each transmission component and the current vibration data into the query engine to obtain the fault type corresponding to each transmission component.

[0051] Furthermore, the steps of establishing an analysis test bench for collecting vibration data and obtaining the names of each transmission part and its vibration data include:

[0052] Establish an analysis test bench. The analysis test bench (helicopter transmission system) is mainly composed of a reduction box, shaft components, load and fault simulation parts, etc. The mechanical parts (box, gears and shafts) are made of alloy steel to ensure that the strength meets safety requirements, there is no cold welding on the welded parts, and the surface is smoothed;

[0053] Through sensor layout design (arranging sensors at different positions), the vibration data corresponding to each transmission part (gears, bearings, shaft systems, etc. in the transmission system) of the analysis test bench under normal working conditions and fault types are obtained;

[0054] Among them, the reduction gearbox design includes the main reduction gearbox, the intermediate reduction gearbox and the tail reduction gearbox;

[0055] Specifically, the main reducer box is composed of a box body and a multi-stage reducer, which is used to simulate the main reducer box of a helicopter. Its input shaft is connected to the output shaft of the external power input motor, and the output shaft is connected to the horizontal transmission shaft and the load respectively; the load adopts a magnetic powder brake, and the brake provides a load range of 0-100Nm. The brake can be adjusted manually and by PC software. According to the actual working conditions, the parameters of the power motor are selected: the rated speed is 3000 rpm, the maximum speed is 5000 rpm, and the rated power consumption is 3kW; the driven gear parameter design of the main reducer box completes the output of two transmission ratios of 1.6924 and 28.5749, and thus, this requires the design of two independent output shafts;

[0056] The middle reduction box is composed of a box body and a middle reducer, which is used to simulate the middle reducer box of a helicopter. Its input shaft is connected to the horizontal transmission shaft, and its output shaft is connected to the tail transmission shaft. The power source of the middle reduction box is the output shaft of the main reducer input through the horizontal transmission shaft. The middle reduction box uses bevel gears to achieve a transmission ratio of 1.2068. Therefore, this smaller value can be achieved by a single-stage bevel gear transmission.

[0057] The tail reduction box consists of a box body and a tail reducer, which is used to simulate the tail speed box of a helicopter. Its input shaft is connected to the tail transmission, and the output shaft is connected to the load. The load adopts a magnetic powder brake, and the brake provides a load range of 0-100Nm. The brake can be adjusted manually and by PC software. The tail reduction box uses bevel gears to achieve a transmission ratio of 2.9282. Therefore, this smaller value can be achieved by using a single-stage bevel gear transmission.

[0058] Furthermore, the steps of obtaining the vibration data corresponding to each transmission part of the analysis test bench under normal working conditions and under fault types through sensor layout design include:

[0059] Arrange vibration sensors (or other sensors, such as displacement sensors, etc.) on each transmission part of the analysis test bench, and the vibration sensors record vibration data of each transmission part, and the vibration data includes normal vibration data and fault vibration data;

[0060] The vibration data of the transmission parts under the ideal state at different speeds are recorded as normal vibration data;

[0061] The vibration data of the transmission parts under the fault type at different speeds are recorded as fault vibration data.

[0062] It should be noted that the main sensor layout is designed as follows: Figure 3 :

[0063] Position 1, three-axis vibration acceleration, monitoring gear fault vibration value;

[0064] Position 2, three-axis vibration acceleration, monitoring gear fault vibration value;

[0065] Position 3, three-axis vibration acceleration, monitoring the vibration value of the transmission shaft eccentricity fault;

[0066] Position 4, single-axis vibration acceleration, monitors the vibration value of the transmission shaft eccentricity fault;

[0067] Position 5, single-axis vibration acceleration, monitoring the vibration value of the transmission shaft eccentricity fault;

[0068] Position 6, single-axis vibration acceleration, monitoring gear fault vibration value;

[0069] Position 7 and position 8, displacement sensors, monitor the vibration displacement of the transmission shaft.

[0070] Typical fault designs include:

[0071] The name of the transmission component and the fault component and fault type (typical fault state) corresponding to the transmission component are obtained, and then an association relationship is established between the name of the transmission component and the fault component and fault type corresponding to the transmission component.

[0072] It should be noted that the faulty parts and fault types include: main reducer spur gear cracking faulty parts, main reducer spur gear eccentric faulty parts, main reducer spur gear missing tooth faulty parts, main reducer spur gear pitting faulty parts, tail reducer bevel gear missing tooth faulty parts, tail reducer bevel gear cracking faulty parts, tail reducer bevel gear eccentric faulty parts, tail reducer bevel gear pitting faulty parts, rolling bearing outer ring fault, rolling bearing inner ring fault, rolling bearing cage fault and rolling bearing rolling element fault.

[0073] Furthermore, the steps of designing a replacement of a faulty part include:

[0074] Record each transmission component with a fault type as a faulty component;

[0075] Obtain replacement steps for each fault type of each fault component in the historical records;

[0076] Associate the faulty part with the replacement steps for the corresponding fault type.

[0077] It should be noted that the design for replacing the missing tooth fault part of the main reduction gear is as follows:

[0078] Step 1: Use an Allen wrench to remove the fixing screws around the first-stage reduction box and the bearing cover fixing screws so that the upper and lower parts can be separated, and remove the upper half of the gearbox body;

[0079] Step 2: After taking out the upper part of the first-stage reduction gearbox, separate the marked gear shaft and take it out;

[0080] Step 3, remove the marked bearing using a puller or other tools;

[0081] Step 4: Use circlip pliers to remove the circlip, and then use a triangular puller to remove the cylindrical involute spur gear faulty part on the outside and replace it with the tooth-missing faulty part;

[0082] Step 5: Restore the components of the main reduction gearbox.

[0083] Furthermore, the step of analyzing the vibration data of each transmission component to obtain the fault vibration characteristics of each transmission component includes:

[0084] Apply demodulation spectrum and envelope spectrum analysis to the normal vibration data and fault vibration data of the transmission component, thereby obtaining distinguishing features between the normal vibration data and the fault vibration data, and using the distinguishing features as the fault vibration features of the transmission component;

[0085] By performing demodulation spectrum and envelope spectrum analysis on the remaining transmission parts in turn, the fault vibration characteristics of each transmission part can be obtained.

[0086] It should be noted that: the rolling bearing is assumed to have a fixed outer ring and a rotating inner ring, and the bearing is an ideal bearing, that is, the lubrication between the various components of the bearing is good, there is no relative sliding, and the bearing does not deform during normal operation;

[0087] Define the outer ring rotation frequency as fo=0, the inner ring rotation frequency as fi=N / 60 (N is the shaft speed), and the relative rotation frequency of the inner and outer rings as fr=fi. The theoretical fault characteristic frequency of the rolling bearing can be obtained as follows:

[0088] The outer race fault characteristic frequency (BPFO) fo is Fo=½z(1-cosɑ)fr(1);

[0089] The inner race fault characteristic frequency (BPFI) fi is fi = ½z(1-cosɑ)fr (2);

[0090] Rolling element fault characteristic frequency (BSF) fb is fb=½*D / d[1-(D / d*cosɑ) 2 ]fr(3);

[0091] The cage fault characteristic frequency (FTF) fc is fc=½(1-D / d*cosɑ)fr(4);

[0092] Where D, d, α, Z and fr are the pitch circle diameter, rolling element diameter, ball and cage contact angle, number of rolling elements and bearing speed (Hz) respectively; when the rolling element in the bearing encounters a local fault of the inner ring or outer ring or vice versa during operation, an impact signal will be generated within the period of one of the rolling bearing fault frequencies;

[0093] The empirical formula for failure frequency is:

[0094] Outer ring fault frequency: fo=0.4*z*fr, inner ring fault frequency: fi=0.6*z*fr,

[0095] Rolling element failure frequency: fb=0.23*z*fr, (z<10); fb=0.18*z*fr, (z>10);

[0096] Cage failure frequency: fc=0.381~0.4xfr;

[0097] Relationship between outer ring and cage: fo=z*fc;

[0098] The relationship between the outer ring and the inner ring is: fo+fi=z*fr, where fr is the rotation frequency and Z is the number of rolling elements;

[0099] For example, the specifications of NSK60 / 28 (28*52*12mm) rolling bearing are: outer diameter 52mm, inner diameter 28mm, thickness 12mm, pitch circle diameter D=40mm, rolling element diameter d=8mm, ball and cage contact angle α=0, number of rolling elements Z=10;

[0100] Then, substituting the above rule data into the above formula, the actual data analysis of NSK60 / 28 (28*52*12mm) rolling bearing is:

[0101] fr=fi=N / 60=1477 / 60=24.6Hz\2954 / 60=49.2Hz;

[0102] fo=0.4*Z*fr=0.4*10*24.6=98.4Hz\0.4*10*49.2=196.9Hz;

[0103] fi=0.6*Z*fr =0.6*10*24.6=147.7Hz\0.6*10*49.2=295.4Hz;

[0104] fb=0.23*Z*fr=0.23*10*24.6=56.6Hz\0.23*10*49.2=113.2Hz;

[0105] fc=0.381*fr=0.381*24.6=9.3Hz\0.381*49.2=18.7Hz;

[0106] The vibration data of the normal rolling bearing at the rear end of the transmission shaft is analyzed, and the specific data is listed in the following table:

[0107] Motor speed (rpm) coaxial 1 2500 5000 Bearing speed (rpm) coaxial 2 1477.279442 2954.558884 Bearing speed frequency (Hz) 24.62132404 49.24264807 Outer race fault characteristic frequency BPFO (Hz) 98.48529615 196.9705923 Inner race fault characteristic frequency BPFI (Hz) 147.7279442 295.4558884 Rolling element fault characteristic frequency BSF (Hz) 59.09117769 118.1823554 Cage fault characteristic frequency FTF (Hz) 9.848529615 19.69705923

[0108] According to the vibration data analysis of the normal rolling bearing at the rear end of the transmission shaft at the vibration sensor position 5, the data of the simulated helicopter startup process was collected at a sampling rate of 4096, and the data at 50% of the maximum speed of 2500 from 40 seconds to 160 seconds were analyzed for spectrum and envelope spectrum; it can be seen that under the normal rolling bearing, there is no prominent fault characteristic frequency, only a slight rotation frequency of the rolling shaft and the resonance frequency of the bearing parts;

[0109] Motor speed (rpm) coaxial 1 2500 5000 Bearing speed (rpm) coaxial 2 1477.279442 2954.558884 Bearing speed frequency (Hz) 24.62132404 49.24264807 Outer race fault characteristic frequency BPFO (Hz) 98.48529615 196.9705923 Inner race fault characteristic frequency BPFI (Hz) 147.7279442 295.4558884 Rolling element fault characteristic frequency BSF (Hz) 59.09117769 118.1823554 Cage fault characteristic frequency FTF (Hz) 9.848529615 19.69705923

[0110] In the above table data, it is analyzed that in the time period of 40-160 seconds at a constant speed of 2500, there are obvious outer ring fault characteristic frequencies BPFO (98.48Hz) and their multiples, and in the time period of 170-200 seconds at a constant speed of 5000, there are obvious outer ring fault characteristic frequencies BPFO (196.97Hz) and their multiples; and in the acceleration process, it can also be clearly seen that the outer ring fault characteristic frequency changes with the speed;

[0111] Furthermore, when the inner ring of the bearing is defective, the inner ring defect frequency BPFI and its higher harmonics can be seen in the demodulated spectrum. For the bearing with rotating inner ring, the sideband of its rotational speed frequency may appear; because when the inner ring fails, if it is located in the loading area, the impact will be more severe, resulting in a higher amplitude. When the inner ring fault position moves out of the loading area, its amplitude will decrease again and reach the minimum value at the top of the bearing; in this case, the inner ring fault frequency is modulated by the (inner ring) rotation frequency, and the 1X sideband can be seen in the spectrum.

[0112] Furthermore, a query engine and a database are established, and the step of storing the name, vibration data and fault vibration characteristics of each transmission component in the database includes:

[0113] Build and run a Hadoop cluster, which includes HDFS and YARN;

[0114] Install and configure Hive and the Hive database, install Impala and connect Impala to the Hive database to obtain the query engine and database;

[0115] The name, vibration data and fault vibration characteristics of each transmission component are configured to impalad and the configuration paths of Hadoop and Hive are specified, wherein the name, vibration data and fault vibration characteristics of each transmission component are stored in the Hive database.

[0116] Furthermore, the step of inputting the name of each transmission component and the current vibration data into the query engine includes:

[0117] Get the name of each transmission part and the corresponding current vibration data;

[0118] Load the names of each transmission component into the HDFS of the query engine;

[0119] The names of each transmission component create a table pointing to the database in Hive, and the database can be accessed through Hive metadata;

[0120] The database can output the normal vibration data and fault vibration characteristics corresponding to each transmission component.

[0121] Furthermore, the loading method is:

[0122] This is done through Hive's LOAD-DATA statement.

[0123] Furthermore, the step of obtaining the fault type corresponding to each transmission component includes:

[0124] Compare the current vibration data of each transmission component with the normal vibration data, and record the transmission component corresponding to the different current vibration data as the current faulty component;

[0125] The current vibration data corresponding to the current faulty component is matched with the fault vibration feature, and the fault type corresponding to the matched fault vibration feature is used as the fault type of the faulty component.

[0126] It should be noted that Impala is a high-concurrency MPP query engine built on Hadoop, which is used to balance the flexibility and scalability of Hadoop and provide low-latency, high-concurrency read-oriented queries for visual data analysis; the aviation equipment big data management, intelligent analysis and application service platform uses Impala's MPP (massive parallel processing) query engine for data query, realizing efficient flight parameter data and vibration data query services.

[0127] In this embodiment, by building and running a Hadoop cluster and making full use of its distributed storage (HDFS) and resource management (YARN) features, a large amount of vibration data of transmission parts can be efficiently processed; not only the data storage efficiency is improved, but also the data security and reliability are ensured; a powerful query engine is built by combining the use of Hive and Impala; Hive provides rich data definition, data operation and data query functions, while Impala is famous for its fast data query performance. This combination can quickly respond to various query requirements and provide strong support for fault analysis; through Hive's LOAD-DATA language, The name of the transmission part, vibration data and fault vibration characteristics are easily loaded into HDFS with the help of the built-in command line interface, and the corresponding table is created in Hive to point to these data. This simplifies the data management and access process, making data utilization more efficient and convenient. By comparing the current vibration data with the normal vibration data and matching them with the fault vibration characteristics, the faulty part and its fault type can be accurately identified. This fault diagnosis method not only improves the accuracy of diagnosis, but also greatly shortens the diagnosis time, providing a strong guarantee for the timely repair and maintenance of equipment. With the increase in the number of transmission parts and the accumulation of vibration data, it can be easily expanded to meet higher data processing requirements.

[0128] Example 2

[0129] See also Figure 2 As shown, this embodiment is a fault diagnosis system for a helicopter transmission system, comprising:

[0130] The data acquisition module establishes an analysis test bench for vibration data acquisition, and then obtains the name of each transmission part and its vibration data;

[0131] The data analysis module analyzes the vibration data of each transmission component to obtain the fault vibration characteristics of each transmission component;

[0132] The engine building module builds a query engine and a database, and stores the name, vibration data, and fault vibration characteristics of each transmission part in the database;

[0133] The query module inputs the name of each transmission component and the current vibration data into the query engine to obtain the fault type corresponding to each transmission component.

[0134] In this embodiment, through the construction of the query engine, the system can be easily expanded to meet higher data processing requirements as the number of transmission parts increases and vibration data accumulates; at the same time, it is also convenient for subsequent functional upgrades and optimizations, providing possibilities for the continuous development and improvement of the system.

[0135] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0136] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0137] The above are only preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A fault diagnosis method for a helicopter transmission system, characterized in that: The following steps are involved: S1. Establish an analysis test bench for vibration data collection, and then obtain the name of each transmission part and its vibration data; S2. Analyze the vibration data of each transmission component to obtain the fault vibration characteristics of each transmission component; S3, establishing a query engine and a database, and storing the name, vibration data and fault vibration characteristics of each transmission part in the database; S4. Input the name of each transmission component and the current vibration data into the query engine to obtain the fault type corresponding to each transmission component.

2. A fault diagnosis method for a helicopter transmission system according to claim 1, characterized in that: The step of establishing an analysis test bench for collecting vibration data and obtaining the name of each transmission part and its vibration data includes: Establish an analysis test bench and obtain the names of the transmission parts in the analysis test bench. The establishment of the analysis test bench includes: reduction box design, sensor layout design, typical fault design and fault part replacement design; The sensor layout design is used to obtain the vibration data corresponding to each transmission part of the analysis test bench under normal working conditions and fault types.

3. A fault diagnosis method for a helicopter transmission system according to claim 2, characterized in that: The analysis test bench is mainly composed of a reduction gearbox, a shaft assembly, a load and a fault simulation component, and the reduction gearbox includes a main reduction gearbox, an intermediate reduction gearbox and a tail reduction gearbox.

4. A fault diagnosis method for a helicopter transmission system according to claim 2, characterized in that: The step of obtaining the vibration data corresponding to each transmission part of the analysis test bench under normal working conditions and under fault types through sensor layout design includes: Arrange vibration sensors on each transmission part of the analysis test bench, and the vibration sensors record vibration data of each transmission part, and the vibration data includes normal vibration data and fault vibration data; The vibration data of the transmission parts under the ideal state at different speeds are recorded as normal vibration data; The vibration data of the transmission parts under the fault type at different speeds are recorded as fault vibration data.

5. A fault diagnosis method for a helicopter transmission system according to claim 4, characterized in that: The steps of the faulty part replacement design include: Record each transmission component with a fault type as a faulty component; Obtain replacement steps for each fault type of each fault component in the historical records; Associate the faulty part with the replacement steps for the corresponding fault type.

6. A fault diagnosis method for a helicopter transmission system according to claim 4, characterized in that: The step of analyzing the vibration data of each transmission component to obtain the fault vibration characteristics of each transmission component includes: Apply demodulation spectrum and envelope spectrum analysis to the normal vibration data and fault vibration data of the transmission component, thereby obtaining distinguishing features between the normal vibration data and the fault vibration data, and using the distinguishing features as the fault vibration features of the transmission component; By performing demodulation spectrum and envelope spectrum analysis on the remaining transmission parts in turn, the fault vibration characteristics of each transmission part can be obtained.

7. A fault diagnosis method for a helicopter transmission system according to claim 5, characterized in that: The step of establishing a query engine and a database, and storing the name, vibration data and fault vibration characteristics of each transmission component in the database, comprises: Build and run a Hadoop cluster, which includes HDFS and YARN; Install and configure Hive and the Hive database, install Impala and connect Impala to the Hive database to obtain the query engine and database; The name, vibration data and fault vibration characteristics of each transmission component are configured to impalad and the configuration paths of Hadoop and Hive are specified, wherein the name, vibration data and fault vibration characteristics of each transmission component are stored in the Hive database.

8. A fault diagnosis method for a helicopter transmission system according to claim 7, characterized in that: The step of inputting the name of each transmission component and the current vibration data into the query engine comprises: Get the name of each transmission part and the corresponding current vibration data; Load the names of each transmission component into the HDFS of the query engine; The names of each transmission component create a table pointing to the database in Hive, and the database can be accessed through Hive metadata; The database can output the normal vibration data and fault vibration characteristics corresponding to each transmission component.

9. A fault diagnosis method for a helicopter transmission system according to claim 8, characterized in that: The loading method is: This is done through Hive's LOAD-DATA statement.

10. A fault diagnosis method for a helicopter transmission system according to claim 9, characterized in that: The step of obtaining the fault type corresponding to each transmission component includes: Compare the current vibration data of each transmission component with the normal vibration data, and record the transmission component corresponding to the different current vibration data as the current faulty component; The current vibration data corresponding to the current faulty component is matched with the fault vibration feature, and the fault type corresponding to the matched fault vibration feature is used as the fault type of the faulty component.

Images