A method and system for diagnosing abnormal noise of a transmission

Abstract

The present invention provides a method and system for diagnosing abnormal noises in a transmission. The method includes obtaining abnormal noise data, analyzing whether there is historical case data matching the abnormal noise data in a historical case database. If not, calculating the characteristics of the abnormal noise audio to obtain an abnormal noise characteristic value, and judging whether there is abnormal noise characteristic data matching the abnormal noise characteristic value in a characteristic database. If not, obtaining vibration, sound, and TCU signals and analyzing them to obtain data characteristics, and judging whether there is abnormal noise characteristic data matching the analyzed data characteristics in the characteristic database. If so, outputting the cause of the abnormal noise. By establishing a system for diagnosing abnormal noises in a transmission, the present application can quickly diagnose abnormal noise problems through the system, whether for difficult-to-diagnose abnormal noises or general abnormal noise problems, improving the diagnosis efficiency and ensuring the diagnosis accuracy at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of transmission fault diagnosis, and particularly relates to a method and system for diagnosing abnormal noises of a transmission. Background Art

[0002] An automotive transmission is a rotating machine, and abnormal noise is an abnormal sound emitted by the transmission during operation. Continuous abnormal noise will not only affect the riding experience of passengers and cause discomfort, but serious abnormal noise may lead to vehicle failure and affect driving safety. Therefore, the reasons for the abnormal noise of the transmission need to be investigated and solved in a timely manner.

[0003] Due to the relatively complex structure of the transmission and various reasons for abnormal noise, the diagnosis of abnormal noise in the transmission is relatively difficult and requires certain professional knowledge and experience. At present, after-sales maintenance personnel generally rely on experience to judge abnormal noise. For abnormal noise that is difficult to diagnose, professional engineers need to go to the site for testing and analysis to find out the reasons for the abnormal noise. This often results in low timeliness and is likely to cause customer complaints. Therefore, for the problem of abnormal noise in the gearbox, a fast and effective diagnosis system and method are needed, which can help after-sales maintenance personnel quickly find out the reasons for the abnormal noise, and is of great significance for improving work efficiency and reducing customer complaints. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a method and system for diagnosing abnormal noise of a transmission, so as to solve the technical problems in the prior art that the diagnosis of abnormal noise in the transmission generally relies on the experience of after-sales maintenance personnel, resulting in low accuracy, and the solution for diagnosing abnormal noise that requires professional engineers to go to the site for testing and analysis for abnormal noise that is difficult to diagnose, resulting in low efficiency.

[0005] Another aspect of the present invention provides a system for diagnosing abnormal noise of a transmission, including:

[0006] A human-machine interaction interface for inputting and outputting information for information interaction;

[0007] A knowledge acquisition module, connected to the human-machine interaction interface and the knowledge base, for inputting the information into the human-machine interaction interface and converting it into an internal form that can be stored by a computer and storing it in the knowledge base;

[0008] A knowledge base, connected to the knowledge acquisition module and the inference engine, the knowledge base includes a case database and a feature database. The case database includes abnormal noise case data, and the abnormal noise case data includes transmission bench abnormal noise cases and vehicle abnormal noise cases. The feature database includes abnormal noise feature data, and the abnormal noise feature data includes vibration data features, sound data features, and transmission TCU signal features;

[0009] An inference engine, which is respectively connected to the knowledge base, the interpreter, and the database, is used to diagnose abnormal noises by calling the facts and abnormal noise diagnosis rules in the knowledge base according to existing parameters or user inputs;

[0010] A database, which is respectively connected to the inference engine and the interpreter, is used to store working data, and the working data includes the abnormal noise inference process, message records, and historical data of abnormal noise diagnosis;

[0011] An interpreter is used to output the diagnosis result of the inference engine to the user in a conventional form through a man-machine interface;

[0012] A network interface, which is connected to the network, is used to receive and update the change information and professional knowledge of transmission components, communicate remotely with experts, and upgrade algorithms.

[0013] On the one hand, the present invention provides a method for diagnosing abnormal noises in a transmission, which is implemented by using the above-mentioned transmission abnormal noise diagnosis system. The method is specifically applied to the inference engine, and the method includes:

[0014] Obtain abnormal noise data, where the abnormal noise data includes abnormal noise audio and a text description of the abnormal noise;

[0015] According to the historical case data in the historical case database, analyze whether there is historical case data matching the abnormal noise data in the historical case database. The analysis methods include timbre analysis and frequency analysis;

[0016] If not, perform feature calculation on the abnormal noise audio to obtain an abnormal noise feature value. The feature calculation methods include fast Fourier transform and envelope spectrum analysis;

[0017] According to the abnormal noise feature data in the feature database, judge whether there is abnormal noise feature data matching the abnormal noise feature value in the feature database;

[0018] If not, obtain test data, where the test data includes vibration, sound, and TCU signals, and analyze the data characteristics of vibration, sound, and TCU signals;

[0019] According to the abnormal noise feature data in the feature database, judge whether there is abnormal noise feature data matching the analyzed data characteristics in the feature database;

[0020] If it exists, output the cause of the abnormal noise.

[0021] In addition, according to the above-mentioned method for diagnosing abnormal noises in a transmission of the present invention, the following additional technical features may also be provided:

[0022] Further, after the step of judging whether there is abnormal noise feature data matching the analyzed data characteristics in the feature database according to the abnormal noise feature data in the feature database, it further includes:

[0023] If there is no abnormal sound feature data that matches the analyzed data features, the cause of the abnormal sound is analyzed based on the analyzed data features.

[0024] Further, after the step of analyzing the cause of the abnormal sound based on the analyzed data features, the following steps are also included:

[0025] New abnormal sound case data is established according to the analyzed cause of the abnormal sound;

[0026] The newly established abnormal sound case data is incorporated into the knowledge base to update the knowledge base.

[0027] Further, after the step of analyzing whether there is historical case data that matches the abnormal sound data in the historical case database according to the historical case data in the historical case database, the following steps are also included:

[0028] If there is historical case data that matches the abnormal sound data, the cause of the abnormal sound is output.

[0029] Further, after the step of judging whether there is abnormal sound feature data that matches the abnormal sound feature value in the feature database according to the abnormal sound feature data in the feature database, the following steps are also included:

[0030] If there is abnormal sound feature data that matches the abnormal sound feature value, the cause of the abnormal sound is output.

[0031] Further, the step of judging whether there is abnormal sound feature data that matches the analyzed data features in the feature database according to the abnormal sound feature data in the feature database includes:

[0032] Obtain the analysis result, and compare the analysis result with the abnormal sound feature data in the feature database;

[0033] Judge whether there is abnormal sound feature data that matches the analysis result according to the abnormal sound feature data.

[0034] Further, in the step of obtaining the abnormal sound data, the abnormal sound data of each case includes abnormal sound audio information and abnormal sound text information corresponding to the abnormal sound audio information.

[0035] Further, the step of outputting the cause of the abnormal sound according to the feature data that matches the analyzed data features includes:

[0036] Obtain the abnormal sound case data according to the feature data that matches the analyzed data features, and the abnormal sound case data matches the feature data that matches the analyzed data features;

[0037] Determine and output the cause of the abnormal sound according to the abnormal sound case data.

[0038] Further, the method for outputting the cause of abnormal noise includes:

[0039] Outputting the cause of abnormal noise in the form of text or graph.

[0040] For the above transmission abnormal noise diagnosis method, by establishing a transmission abnormal noise diagnosis system, whether for difficult-to-diagnose abnormal noises or general abnormal noise problems, the system can quickly diagnose the abnormal noise problems, improving the diagnosis efficiency while ensuring the diagnosis accuracy, and avoiding the technical problems in the prior art that the diagnosis of transmission abnormal noise generally depends on the experience of after-sales maintenance personnel, resulting in low accuracy, and for difficult-to-diagnose abnormal noises, a solution that requires professional engineers to go to the site for testing and analysis to diagnose the abnormal noise leads to low efficiency; specifically, by establishing a knowledge base and a database, the abnormal noise data can be diagnosed through the case database and the feature database in the knowledge base. Specifically, the user can diagnose by inputting the recorded abnormal noise audio, reducing the workload of data testing; for abnormal noise problems that cannot be diagnosed only through audio, vibration, sound, and TCU signals are collected for diagnosis and analysis to obtain the cause of abnormal noise. Through the transmission abnormal noise diagnosis method and system in this application, difficult-to-diagnose abnormal noise problems can be quickly identified, reducing the professional threshold of abnormal noise diagnosis, which is of great significance for the rapid diagnosis of after-sales abnormal noises. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a system schematic diagram of the transmission abnormal noise diagnosis system in the first embodiment of the present invention;

[0042] Figure 2 It is a schematic diagram of the knowledge base in the present invention;

[0043] Figure 3 It is a schematic diagram of the transmission abnormal noise fault tree in the present invention;

[0044] Figure 4 It is a schematic diagram of the establishment of the case library in the present invention;

[0045] Figure 5 It is a method flow chart of the transmission abnormal noise diagnosis method in the second embodiment of the present invention.

[0046] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. SPECIFIC EMBODIMENTS

[0047] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used in the specification of this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0049] In this application, by quickly recording abnormal sound audio on-site; importing it into the system and inputting a text description of the abnormal sound; analyzing parameters such as the timbre and frequency of the abnormal sound audio and the matching degree between the text description of the abnormal sound and the cases in the case library, if they match, the cause of the abnormal sound is output; if they do not match, feature calculations (such as envelope spectrum, fast Fourier transform, etc.) are performed on the abnormal sound audio to obtain abnormal sound feature values, and the matching degree between the abnormal sound features and the feature data in the fault feature library is analyzed; if they match, the cause of the abnormal sound is output; if they do not match, it indicates that it is not sufficient to diagnose the fault cause only based on the audio and text description, and detailed data testing is required; test vibration, sound, and TCU signals and import them into the system; analyze the characteristics of vibration, sound, and TCU signals; analyze the matching degree between the signal characteristics and a certain fault feature in the fault feature library, if they match, the cause of the abnormal sound is output. By establishing a transmission abnormal sound diagnosis system, whether for difficult-to-diagnose abnormal sounds or general abnormal sound problems, the system can quickly diagnose the abnormal sound problem, improving the diagnosis efficiency while also ensuring the diagnosis accuracy, avoiding the technical problems in the prior art that the diagnosis of transmission abnormal sounds generally relies on the experience of after-sales maintenance personnel, resulting in low accuracy, and for difficult-to-diagnose abnormal sounds, a solution that requires professional engineers to go to the site for testing and analysis to diagnose the abnormal sound, resulting in low efficiency.

[0050] Embodiment 1

[0051] Please refer to Figure 1 , which shows the transmission abnormal sound diagnosis system in the first embodiment of the present invention, including:

[0052] A human-computer interaction interface for inputting and outputting information for information interaction;

[0053] A knowledge acquisition module, connected to the human-computer interaction interface and the knowledge base, for inputting the information into the human-computer interaction interface and converting it into an internal form that can be stored by a computer and storing it in the knowledge base;

[0054] A knowledge base, connected to the knowledge acquisition module and the inference engine, the knowledge base includes a case database and a feature database, the case database includes abnormal sound case data, and the abnormal sound case data includes transmission bench abnormal sound cases and vehicle abnormal sound cases, the feature database includes abnormal sound feature data, and the abnormal sound feature data includes vibration data features, sound data features, and transmission TCU signal features;

[0055] An inference engine, which is respectively connected to a knowledge base, an interpreter, and a database, is used to diagnose abnormal noises according to existing parameters or user inputs by invoking facts and abnormal noise diagnosis rules in the knowledge base;

[0056] A database, which is respectively connected to the inference engine and the interpreter, is used to store working data, and the working data includes the abnormal noise inference process, message records, and historical data of abnormal noise diagnosis;

[0057] An interpreter is used to output the diagnosis result of the inference engine to the user in a predefined form through a man-machine interaction interface;

[0058] A network interface, which is connected to the network, is used to receive and update the change information and professional knowledge of transmission components, communicate remotely with experts, and upgrade algorithms.

[0059] This embodiment provides a transmission abnormal noise diagnosis system, which includes a network interface, a man-machine interaction interface, a knowledge acquisition module, a knowledge base, a database, an inference engine, and an interpreter. The system is connected to the network through the network interface to regularly update the change information of transmission components, professional knowledge, remotely communicate between users and experts, and upgrade the diagnosis algorithm.

[0060] Users input the professional knowledge (fault feature knowledge, cases) of the transmission into the system through the man-machine interaction interface, realizing information interaction between the system modules and completing the input and output work.

[0061] The knowledge acquisition module acquires the professional knowledge input into the man-machine interaction interface and converts it into an internal form that can be stored by a computer, and stores it in the knowledge base.

[0062] The knowledge base is respectively connected to the inference engine and the knowledge acquisition module, and includes case data and feature data, as shown in Figure 2 shown. The feature database is the feature data of the vibration and sound of various abnormal noises of the transmission. It is established according to the fault number analysis method and reasons for faults are deduced according to the reverse thinking logic. The fault tree takes the faults that the system does not want to appear as the top event, finds all intermediate events that can cause the top event to occur, and then finds all factors that cause the intermediate events to occur. In this way, it is traced back to the bottom events that cause the faults all the time, and the top event and the bottom events are connected by logical relationships to form the fault tree. The construction of the abnormal noise feature library is shown in Figure 3 shown. The abnormal noise of the transmission may be caused by hardware faults or software abnormalities, and the hardware faults may be caused by gear wear. The gears include multiple gear pairs such as gears from the 1st to the 5th gears, and each gear pair includes a driving gear and a driven gear. The wear faults of the driving gear and the driven gear are the bottom events. Similarly, other faults such as bearing wear, oil pump faults, clutch faults, and shaft end rubbing are established with complete connection relationships in the above manner. The case data is the abnormal noise case data. The case data is established in the form of a case database, and the establishment method is shown inFigure 4 As shown, each case includes audio data and the corresponding text description of the audio data. The sources of case data acquisition include:

[0063] Abnormal sound fault cases of the transmission accumulated in the early stage or abnormal sound fault cases obtained by artificially introducing different faults on the test prototype; cases completed and saved by the system through diagnosis; cases on the Internet, which are saved in the case library after screening. As the case data expands continuously, the diagnostic accuracy also improves continuously.

[0064] The database is connected to the interpreter and the inference engine respectively, and is used to store data including the abnormal sound inference process, message records, and abnormal sound diagnosis history.

[0065] The inference engine integrates algorithms such as data analysis and machine learning. When the user inputs the text description and the abnormal sound audio file, the inference engine calls the cases and abnormal sound diagnosis rules in the cases to diagnose the abnormal sound. When the user imports the vibration, sound, and TCU signals for testing, the inference engine calls the data in the feature library and the abnormal sound diagnosis rules to diagnose the abnormal sound.

[0066] The interpreter outputs the cause of the abnormal sound to the user in the form of text, pictures, etc. through the man-machine interaction interface according to the diagnostic result of the inference engine.

[0067] Specifically, the feature database is established according to the fault tree analysis method, and the cause of the fault is deduced according to the reverse thinking logic. The fault tree takes the fault that the system does not want to occur as the top event, finds out all intermediate events that can lead to the occurrence of the top event, and then finds out all factors that cause the occurrence of the intermediate events. In this way, it is traced back to the bottom event that causes the fault, and the top event and the bottom event are connected by logical relationships to form the fault tree. The case data is established in the form of a case database (abbreviation: case library). The sources of case data acquisition include: abnormal sound fault cases of the transmission accumulated in the early stage or abnormal sound fault cases obtained by artificially introducing different faults on the test prototype; cases completed and saved by the system through diagnosis; cases on the Internet, which are saved in the case database after screening. As the case database expands continuously, the diagnostic accuracy also improves continuously.

[0068] The data stored in the feature database in the knowledge base are vibration data features, sound data features, and transmission TCU signal features. The data stored in the case database are transmission bench abnormal sound cases and vehicle abnormal sound cases, including audio data and the corresponding text description of the audio data.

[0069] In summary, the abnormal noise diagnosis system of the transmission in the above embodiments of the present invention can quickly diagnose abnormal noise problems through the established abnormal noise diagnosis system of the transmission, whether it is difficult-to-diagnose abnormal noise or general abnormal noise problems. While improving the diagnosis efficiency, it also ensures the diagnosis accuracy, avoiding the technical problems in the prior art that the diagnosis of abnormal noise in the transmission generally depends on the experience of after-sales maintenance personnel, resulting in low accuracy, and the solution for difficult-to-diagnose abnormal noise requires professional engineers to go to the site for testing and analysis, resulting in low efficiency. Specifically, by establishing a knowledge base and a database, the abnormal noise data can be diagnosed through the case database and the feature database in the knowledge base. Specifically, the user can diagnose by inputting the recorded abnormal noise audio, reducing the workload of data testing. For abnormal noise problems that cannot be diagnosed only through audio, vibration, sound, and TCU signals are collected for diagnostic analysis to obtain the cause of the abnormal noise. Through the abnormal noise diagnosis method and system in the present application, abnormal noise problems that were previously difficult to diagnose can be quickly identified, reducing the professional threshold for abnormal noise diagnosis, which is of great significance for the rapid diagnosis of after-sales abnormal noise.

[0070] Embodiment 2

[0071] Please refer to Figure 5 , which shows the abnormal noise diagnosis method in the second embodiment of the present invention. The method includes steps S201 to S207:

[0072] S201. Obtain abnormal noise data, where the abnormal noise data includes abnormal noise audio and abnormal noise text description.

[0073] The abnormal noise data of each case includes abnormal noise audio information and corresponding abnormal noise text information. The user first describes the observed abnormal noise phenomenon in detail in text or records the audio when the abnormal noise occurs using a mobile phone or the like, without collecting vibration, noise, and TCU signals, reducing the workload. The text description or abnormal noise audio data is input into the system according to the prompts of the human-computer interaction interface.

[0074] S202. Analyze whether there is historical case data matching the abnormal noise data in the historical case database according to the historical case data in the historical case database.

[0075] Specifically, the analysis methods include timbre analysis and frequency analysis.

[0076] If not, execute step S203;

[0077] If so, execute step S207;

[0078] S203. Calculate the abnormal noise feature value by calculating the features of the abnormal noise audio.

[0079] Specifically, the feature calculation method includes fast Fourier transform and envelope spectrum analysis.

[0080] S204. Determine whether there is abnormal sound feature data matching the abnormal sound feature value in the feature database according to the abnormal sound feature data in the feature database.

[0081] If not, execute step S205;

[0082] If so, execute step S207;

[0083] S205. Obtain test data, where the test data includes vibration, sound, and TCU signals, and analyze the data characteristics of vibration, sound, and TCU signals.

[0084] S206. Determine whether there is abnormal sound feature data matching the analyzed data characteristics in the feature database according to the abnormal sound feature data in the feature database.

[0085] Specifically, obtain the analysis result, compare the analysis result with the abnormal sound feature data in the feature database; determine whether there is abnormal sound feature data matching the analysis result according to the abnormal sound feature data.

[0086] If so, execute step S207;

[0087] S207. Output the cause of the abnormal sound.

[0088] Specifically, obtain the abnormal sound case data according to the feature data matching the analyzed data characteristics, and the abnormal sound case data matches the feature data matching the analyzed data characteristics; determine and output the cause of the abnormal sound according to the abnormal sound case data. Further, output the cause of the abnormal sound in the form of text and pictures.

[0089] As a specific example, if there is no abnormal sound feature data matching the analyzed data characteristics, it means that the knowledge base in the transmission abnormal sound diagnosis system does not include the abnormal sound feature data matching the analyzed data characteristics at this time, and the analyzed data characteristics belong to new abnormal sound data. At this time, manually analyze the cause of the abnormal sound according to the analyzed data characteristics; establish new abnormal sound case data according to the analyzed cause of the abnormal sound; incorporate the established new abnormal sound case data into the knowledge base to update the knowledge base. With the continuous expansion of the case database and the continuous update and iteration of the algorithm, the accuracy of abnormal sound diagnosis is also continuously improved.

[0090] The knowledge base of the present invention simultaneously establishes a case database and a feature database, and diagnosis can be performed through the case database and the feature database. First, users can perform diagnosis by inputting the recorded abnormal sound audio, which reduces the workload of data testing. For abnormal sounds that cannot be diagnosed through the case database, vibration and noise data collection are required. As the case database is continuously expanded and the algorithm is continuously updated and iterated, the diagnostic accuracy of abnormal sounds will continuously improve. Through the transmission abnormal sound diagnosis system, abnormal sound problems that were previously difficult to diagnose can be quickly identified, the professional threshold for abnormal sound diagnosis is reduced, which is of great significance for the quick diagnosis of after-sales abnormal sounds.

[0091] In summary, for the transmission abnormal sound diagnosis method in the above embodiments of the present invention, by establishing a transmission abnormal sound diagnosis system, whether it is for abnormal sounds that are difficult to diagnose or general abnormal sound problems, the system can quickly diagnose the abnormal sound problems, improving the diagnostic efficiency while ensuring the diagnostic accuracy, and avoiding the technical problems in the prior art that the diagnosis of transmission abnormal sounds generally relies on the experience of after-sales maintenance personnel, resulting in low accuracy, and for abnormal sounds that are difficult to diagnose, a solution that requires professional engineers to go to the site for testing and analysis to diagnose the abnormal sounds, resulting in low efficiency; specifically, by establishing a knowledge base and a database, the abnormal sound data can be diagnosed through the case database and the feature database in the knowledge base. Specifically, users can perform diagnosis by inputting the recorded abnormal sound audio, which reduces the workload of data testing; for abnormal sound problems that cannot be diagnosed only through the audio, the vibration, sound, and TCU signals are collected for diagnostic analysis to obtain the cause of the abnormal sound. Through the transmission abnormal sound diagnosis method and system in the present application, abnormal sound problems that were previously difficult to diagnose can be quickly identified, the professional threshold for abnormal sound diagnosis is reduced, which is of great significance for the quick diagnosis of after-sales abnormal sounds.

[0092] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0093] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0094] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0095] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0096] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A method for diagnosing abnormal noise of a transmission, characterized in that, Applied to a transmission abnormal noise diagnosis system, the system includes: A human-machine interaction interface for input and output of information for information interaction; A knowledge acquisition module connected to the human-machine interaction interface and the knowledge base, for the information input into the human-machine interaction interface and converting it into an internal form storable by a computer and storing it in the knowledge base; A knowledge base connected to the knowledge acquisition module and the inference engine. The knowledge base includes a case database and a feature database. The case database includes abnormal noise case data, and the abnormal noise case data includes transmission bench abnormal noise cases and vehicle abnormal noise cases. The feature database includes abnormal noise feature data, and the abnormal noise feature data includes vibration data features, sound data features, and transmission TCU signal features; An inference engine respectively connected to the knowledge base, the interpreter, and the database, for diagnosing abnormal noise by calling facts and abnormal noise diagnosis rules in the knowledge base according to existing parameters or user input; A database respectively connected to the inference engine and the interpreter, for storing working data, and the working data includes the abnormal noise inference process, message records, and historical data of abnormal noise diagnosis; An interpreter for outputting the diagnosis result of the inference engine to the user in a conventional form through the human-machine interaction interface; A network interface connected to the network, for receiving and updating change information and professional knowledge of transmission components, remotely communicating with experts, and algorithm upgrading; The method is specifically applied to the inference engine, and the method includes: Obtaining abnormal noise data, and the abnormal noise data includes abnormal noise audio and abnormal noise text description; Analyzing whether there is historical case data matching the abnormal noise data in the historical case database according to the historical case data in the historical case database, and the analysis methods include timbre analysis and frequency analysis; If not, performing feature calculation on the abnormal noise audio to obtain an abnormal noise feature value, and the feature calculation methods include fast Fourier transform and envelope spectrum analysis; Judging whether there is abnormal noise feature data matching the abnormal noise feature value in the feature database according to the abnormal noise feature data in the feature database; If not, obtaining test data, and the test data includes vibration, sound, and TCU signal, and analyzing the data features of vibration, sound, and TCU signal; Judging whether there is abnormal noise feature data matching the analyzed data features in the feature database according to the abnormal noise feature data in the feature database; If so, outputting the reason for the abnormal noise.

2. The transmission abnormal noise diagnosis method according to claim 1, characterized in that, After the step of judging whether there is abnormal noise feature data matching the analyzed data features in the feature database according to the abnormal noise feature data in the feature database, it further includes: If there is no abnormal noise feature data matching the analyzed data features, analyzing the reason for the abnormal noise according to the analyzed data features.

3. The transmission abnormal noise diagnosis method according to claim 2, characterized in that, After the step of analyzing the reason for the abnormal noise according to the analyzed data features, it further includes: Establishing new abnormal noise case data according to the analyzed reason for the abnormal noise; Incorporating the established new abnormal noise case data into the knowledge base to update the knowledge base.

4. The transmission abnormal noise diagnosis method according to claim 1, wherein, After the step of analyzing whether there is historical case data matching the abnormal noise data in the historical case database according to the historical case data in the historical case database, it further includes: If there is historical case data that matches the abnormal sound data, output the cause of the abnormal sound.

5. The transmission abnormal noise diagnosis method according to claim 1, characterized in that After the step of determining whether there is abnormal sound feature data that matches the abnormal sound feature value in the feature database according to the abnormal sound feature data in the feature database, the following steps are further included: If there is abnormal sound feature data that matches the abnormal sound feature value, output the cause of the abnormal sound.

6. The transmission abnormal noise diagnosis method according to claim 1, wherein The step of determining whether there is abnormal sound feature data that matches the data feature after analysis in the feature database according to the abnormal sound feature data in the feature database includes: Obtain the analysis result, and compare the analysis result with the abnormal sound feature data in the feature database; Determine whether there is abnormal sound feature data that matches the analysis result according to the abnormal sound feature data.

7. The transmission abnormal noise diagnosis method according to claim 1, characterized in that In the step of obtaining the abnormal sound data, the abnormal sound data of each case includes abnormal sound audio information and abnormal sound text information corresponding to the abnormal sound audio information.

8. The transmission abnormal noise diagnosis method according to claim 1, wherein The step of outputting the cause of the abnormal sound according to the feature data that matches the data feature after analysis includes: Obtain abnormal sound case data according to the feature data that matches the data feature after analysis, and the abnormal sound case data matches the feature data that matches the data feature after analysis; Determine and output the cause of the abnormal sound according to the abnormal sound case data.

9. The transmission abnormal noise diagnosis method according to claim 1, wherein The method for outputting the cause of the abnormal sound includes: Output the cause of the abnormal sound in text or graphical form.

Images