Fault detection method and device

Abstract

The embodiment of the invention provides a fault detection method and device, and the method comprises the steps: obtaining the vibration data and attribute information of a to-be-detected object, and determining the fault feature frequency corresponding to the attribute information; analyzing the vibration data to obtain a plurality of vibration frequencies corresponding to the to-be-detected object; the method comprises the following steps: screening a target vibration frequency matched with a fault characteristic frequency from a plurality of vibration frequencies, determining fault detection information of a to-be-detected object according to the target vibration frequency, and analyzing vibration data to obtain a plurality of vibration frequencies by obtaining the vibration data of the to-be-detected object; by acquiring the attribute information of the to-be-detected object, the fault characteristic frequency corresponding to the to-be-detected object can be determined, so that fault detection and analysis can be performed on the vibration frequency corresponding to the vibration data according to the fault characteristic frequency, fault analysis on the to-be-detected object is realized, and the fault analysis efficiency and the accuracy of fault detection information are improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of rail transit, and particularly to a fault detection method and device. Background Art

[0002] With the acceleration of the urbanization process and the continuous growth of traffic demand, rail transit has become an important part of the modern urban traffic system. Rail transit is closely related to important production activities such as material transportation and people's travel. Therefore, the safety of trains running on the tracks is one of the key issues in the development of rail transit technology.

[0003] Currently, the detection of various potential safety hazards is often achieved through a combination of traditional detection instruments and manual inspections. However, this detection method has poor timeliness, high costs, and is difficult to accurately and flexibly analyze the increasingly complex influencing factors. Therefore, there is an urgent need for a more accurate and efficient fault detection method. Summary of the Invention In view of this, the embodiments of this specification provide a fault detection method. One or more embodiments of this specification also relate to a fault detection device, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects existing in the prior art.

[0004] According to the first aspect of the embodiments of this specification, a fault detection method is provided, including: Obtaining vibration data and attribute information of an object to be detected, and determining a fault characteristic frequency corresponding to the attribute information; Analyzing the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected; Selecting a target vibration frequency that matches the fault characteristic frequency from the multiple vibration frequencies, and determining fault detection information of the object to be detected according to the target vibration frequency.

[0005] According to the second aspect of the embodiments of this specification, a fault detection device is provided, including: An obtaining module configured to obtain vibration data and attribute information of an object to be detected, and determine a fault characteristic frequency corresponding to the attribute information; An analyzing module configured to analyze the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected; A determining module configured to select a target vibration frequency that matches the fault characteristic frequency from the multiple vibration frequencies, and determine fault detection information of the object to be detected according to the target vibration frequency.

[0006] According to the third aspect of the embodiments of this specification, a computing device is provided, including: A memory and a processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned fault detection method are implemented.

[0007] According to a fourth aspect of the embodiments of the present specification, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the above-mentioned fault detection method are implemented.

[0008] According to a fifth aspect of the embodiments of the present specification, a computer program product is provided, including a computer program / instructions. When the computer program / instructions are executed by a processor, the steps of the above-mentioned fault detection method are implemented.

[0009] An embodiment of the present specification realizes obtaining vibration data and attribute information of an object to be detected, and determining a fault characteristic frequency corresponding to the attribute information; parsing the vibration data to obtain a plurality of vibration frequencies corresponding to the object to be detected; screening, from the plurality of vibration frequencies, a target vibration frequency that matches the fault characteristic frequency, and determining fault detection information of the object to be detected according to the target vibration frequency. By obtaining the vibration data of the object to be detected, the vibration data can be parsed to obtain a plurality of vibration frequencies; by obtaining the attribute information of the object to be detected, the fault characteristic frequency corresponding to the object to be detected can be determined, so that the fault analysis of the object to be detected can be realized according to the vibration frequency corresponding to the vibration data and the fault characteristic frequency, and the efficiency and accuracy of fault analysis can be improved. Description of the Drawings

[0010] Figure 1 is an architecture diagram of a fault detection system provided by an embodiment of the present specification; Figure 2 is an architecture diagram of a rail transit vibration monitoring system provided by an embodiment of the present specification; Figure 3 is a flowchart of a fault detection method provided by an embodiment of the present specification; Figure 4 is a processing process flowchart of a fault detection method provided by an embodiment of the present specification; Figure 5 is a data analysis process flowchart of a fault detection method provided by an embodiment of the present specification; Figure 6 is a fault frequency update process flowchart of a fault detection method provided by an embodiment of the present specification; Figure 7 is a structural schematic diagram of a fault detection device provided by an embodiment of the present specification; Figure 8 is a structural block diagram of a computing device provided by an embodiment of the present specification. Specific Embodiments

[0011] In the following description, numerous specific details are set forth in order to provide a thorough understanding of this specification. However, this specification can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the connotation of this specification. Therefore, this specification is not limited by the specific embodiments disclosed below.

[0012] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a", "the", and "said" used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0013] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first can also be referred to as the second, and similarly, the second can also be referred to as the first. Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining".

[0014] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of the relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation entrances are provided for the user to select to authorize or reject.

[0015] First, the noun terms involved in one or more embodiments of this specification are explained.

[0016] CAN (Controller Area Network) communication: It is a serial communication protocol for high-speed real-time data transmission, capable of communicating at a rate of up to 1 Mbps and supporting real-time data transmission requirements.

[0017] Vibration amplitude: It is a physical quantity that describes the size of the deviation of the vibrating body from its equilibrium position and can reflect the intensity of the vibration received by the device.

[0018] Stator and Rotor: The stator and rotor are two key components in an electric motor, which work together to convert electromagnetic energy into mechanical energy. Among them, the stator is the stationary part of the motor; the rotor is the rotating part of the motor. The stator is usually composed of an iron core and windings. The iron core is laminated by thin silicon steel sheets to reduce energy loss and eddy current loss. The windings are made by winding wires and are used to generate a magnetic field. The main function of the stator is to generate a rotating magnetic field. When current passes through the stator windings, a changing magnetic field will be generated, and this magnetic field interacts with the magnetic field in the rotor, thereby generating torque to drive the rotor to rotate.

[0019] In this specification, a fault detection method is provided. This specification also relates to a fault detection device, a computing device, a computer-readable storage medium, and a computer program product, which will be described in detail one by one in the following embodiments.

[0020] See Figure 1 , Figure 1 shows an architecture diagram of a fault detection system provided according to an embodiment of this specification.

[0021] The fault detection system includes a rail transit vibration monitoring system, a train, and a track. Among them, the rail transit vibration monitoring system includes five modules: sensors, data acquisition, data analysis, data transmission, and display and alarm. )]]

[0022] The sensors include an acceleration sensor and a temperature sensor. The acceleration sensor is used to obtain the acceleration change in the vertical direction of the track running direction, and the temperature sensor is used to obtain the ambient temperature.

[0023] The data acquisition module includes a main control chip, a DSP chip, a GPS positioning unit, and a power management unit.

[0024] The data analysis module integrates a spectrum analysis algorithm and a fault diagnosis algorithm.

[0025] The data transmission module includes two communication units: wireless 4G communication and wired CAN communication.

[0026] The display and alarm include an embedded display screen and an alarm system.

[0027] Applying this embodiment, during the operation of a train on the track, the rail transit vibration monitoring system can collect the vibration data of the train and the track through an acceleration sensor, report the vibration data to the train through a data acquisition module, perform spectral analysis on the vibration data through a data analysis module to obtain multiple vibration frequencies, and obtain a fault detection result through fault diagnosis. The rail transit vibration monitoring system can inform the staff of the specific fault types existing in the train and the track through an alarm system, and can display the fault information on an embedded display screen for easy manual viewing and monitoring.

[0028] See Figure 2 , Figure 2 shows an architecture diagram of a rail transit vibration monitoring system provided according to an embodiment of this specification.

[0029] STM32F407IGT6 is the main control chip, responsible for data acquisition, processing, and transmission. The DSP chip is used to call the Fourier transform to convert the sensor vibration signal from the time domain to the frequency domain, facilitating data analysis of vibrations at specific frequencies and locating fault problems through vibrations. ADXL345 is an acceleration sensor, and LM35 is a temperature sensor, which are used to collect available data. The Ublox NEO-6M module is used to obtain positioning information.

[0030] The rail transit vibration monitoring system is also configured with two optional communication transmission methods: wireless 4G communication and wired CAN communication, which can be used in different usage scenarios. The two can be used simultaneously, or can be reasonably used with reference to the installation environment of the system.

[0031] The data collected by the sensor includes the real-time vibration data of the track and the train and the environmental temperature data, and the temperature data is used to compensate for the influence of temperature on the vibration data.

[0032] Exemplarily, when the system is installed on the train as a safety component for train operation, the data can be reported to the train through CAN communication and then reported to the control center via the train. When the system is installed on the track as a separate component, the data can be reported to the control center through 4G wireless communication. The two communication methods can also be combined to improve the redundancy ability.

[0033] See Figure 3 , Figure 3 shows a flowchart of a fault detection method provided according to an embodiment of this specification, which specifically includes the following steps.

[0034] Step 302: Obtain the vibration data and attribute information of the object to be detected, and determine the fault characteristic frequency corresponding to the attribute information.

[0035] In practical applications, when a train is running on a track, the vibrations of the running train and the track passed by the train can be analyzed to monitor the vibration conditions of the train and the track in real time, ensuring that potential safety hazards can be detected and handled in a timely manner.

[0036] Specifically, the object to be detected may include a train and / or a track. The vibration data may specifically include the vibration data of the train and / or the vibration data of the track. The attribute information can reflect the attributes of the object to be detected, including the type, status, structural information, operation information, etc. of the object to be detected. Exemplarily, when the object to be detected is a train, the attribute information may include that the type of the object to be detected is a train, the structural information and operation information of each component of the train; when the object to be detected is a track, the attribute information may include that the type of the object to be detected is a track, the section location where the track is located, the track structure and other information.

[0037] The fault characteristic frequency can be understood as the frequency at which a fault is likely to occur. One fault characteristic frequency can correspond to one or more specific fault types. The fault characteristic frequency can be a single certain frequency (such as 30 Hz), or a continuous frequency range, that is, a frequency band (such as 30 Hz - 300 Hz). One attribute information can correspond to multiple fault characteristic frequencies, and the fault types corresponding to different fault characteristic frequencies are different.

[0038] In one or more alternative embodiments of the present specification, the fault characteristic frequencies of the object to be detected can be pre-recorded and maintained in a fault information table.

[0039] Specifically, the fault information table is a structure for storing fault types and the fault characteristic frequencies corresponding to the fault types. The fault characteristic frequencies can include static fault characteristic frequencies and dynamic fault characteristic frequencies.

[0040] Optionally, for the static fault characteristic frequencies, the fault types and the frequency data of the static fault characteristic frequencies can be directly recorded in the fault information table.

[0041] Exemplarily, static fault types can include: track irregularity, poor contact between wheels and the track, stator fault, etc. Among them, the static fault characteristic frequency corresponding to track irregularity is between 1 - 30 Hz; the static fault characteristic frequency corresponding to poor contact between wheels and the track is between 30 - 300 Hz; the static fault characteristic frequency corresponding to stator fault is usually 50 Hz and its higher harmonics (such as 50 Hz, 100 Hz, 150 Hz, etc.).

[0042] Optionally, for the dynamic fault characteristic frequencies, the fault types and the calculation methods of the dynamic fault characteristic frequencies can be recorded in the fault information table. The calculation methods of different dynamic fault characteristic frequencies are different.

[0043] Exemplarily, dynamic fault types may include: wheel imbalance, bearing fault, rotor imbalance, gear fault, etc. Among them, bearing faults may further include outer ring faults of the bearing, inner ring faults of the bearing, cage faults, and rolling element faults.

[0044] In the actual implementation process, according to the attribute information of the object to be detected, the fault characteristic frequency corresponding to the object to be detected can be obtained from the fault information table, and thus, according to the fault characteristic frequency, the possible fault types of the object to be detected can be analyzed.

[0045] According to an optional embodiment of this specification, obtaining the vibration data of the object to be detected may include the following steps: Collect the vibration data of the object to be detected through a first sensor deployed on the object to be detected, where the vibration data includes at least one of velocity data, displacement data, and acceleration data.

[0046] Specifically, the first sensor can be understood as a sensor deployed on the object to be detected for collecting vibration data. Specifically, it can be a velocity sensor, a displacement sensor, an acceleration sensor, etc. The vibration data may include, but is not limited to, velocity data, displacement data, acceleration data, etc., and can be specifically determined according to the requirements in actual applications. Among them, the velocity data reflects the speed and direction of the position change of an object per unit time during the vibration process, and can also be understood as the rate of vibration. Exemplarily, when the train wheels rotate at high speed, if there are problems such as local wear or imbalance, it will cause the vibration velocity to be significantly abnormal. Therefore, it is possible to judge whether there is a fault in the object to be detected and the type of the fault based on the collected velocity data. The displacement data is the amount of position change of an object relative to the initial position during the vibration process, that is, the distance from the equilibrium position, and can represent the amplitude of the vibration. The displacement data can be a vector including magnitude and direction. Exemplarily, long-term train operation may cause the track to settle or deform, resulting in the displacement data of the track exceeding the normal range. By monitoring the displacement data of the track, the abnormal deformation of the track can be detected in time. The acceleration data represents the rate of change of velocity with time, including the speed and direction of the velocity change during the vibration process of the object to be detected. The acceleration data is usually a vector, and its unit in the International System of Units can be expressed as meters per second squared (m / s²). By collecting the acceleration data, it is also possible to analyze whether there are abnormalities or faults in the vibration frequency of the train wheels or the track, so as to determine the type of the fault.

[0047] The attribute information of the object to be detected may include that the object to be detected is a train and / or the object to be detected is a track. In the case where the object to be detected is a train, the attribute information may further include the structural information and operation information of each component on the train. In the case where the object to be detected is a track, the attribute information may further include information such as the section position where the current track is located and the track structure.

[0048] Optionally, when the object to be detected is a train, the first sensor can be deployed on the train. Further, the vibration data collected by the first sensor can be reported to the train via CAN communication and then reported to the control center via the train.

[0049] Optionally, when the object to be detected is a track, the first sensor can be deployed at a specified position on the track. Further, the vibration data collected by the first sensor can be reported to the train via 4G wireless communication and then reported to the control center via the train; or the data can be directly reported to the control center via 4G wireless communication.

[0050] Applying this embodiment, by collecting the vibration data of the object to be detected through the first sensor deployed on the object to be detected and obtaining the attribute information of the object to be detected, it is possible to collect the vibration data of the train and the track during the operation of the train on the track, realize the real-time collection of the vibration data, and thus be able to perform real-time analysis on the vibration data to ensure timely detection of faults.

[0051] In the actual implementation process, the first sensor collects the vibration data according to the sampling method preset by the system. Therefore, according to an optional embodiment of this specification, collecting the vibration data of the object to be detected through the first sensor deployed on the object to be detected may include the following steps: Collect the acceleration data of the object to be detected through the first sensor according to the preset sampling frequency and the preset number of sampling points; Process the acceleration data according to the preset processing rules to obtain the vibration data.

[0052] In practical applications, before collecting the vibration data, the frequency range to be analyzed can be determined first. Based on the frequency range, the preset sampling frequency and the preset number of sampling points can be determined.

[0053] Generally, the frequency range of 1 - 500 Hz can cover various conventional fault information. Therefore, 1 - 500 Hz can be used as the default frequency range, and the corresponding sampling frequency ( ) 1000 Hz and the number of sampling points (N) 1024 can be used as the default values of the preset sampling frequency and the preset number of sampling points. If a larger frequency range wants to be analyzed, it can be achieved by adjusting the preset sampling frequency or the preset number of sampling points. For example, the sampling frequency can be increased from 1000 Hz to 2000 Hz while the number of sampling points remains unchanged. In this way, the frequency range that can be analyzed can be expanded to 1 - 1000 Hz.

[0054] Specifically, the preset sampling frequency can be understood as the data sampling frequency when the first sensor collects vibration data, and the preset number of sampling points can be understood as the number of acceleration data collected by the first sensor within each sampling period. When the preset sampling frequency is 1000 Hz and the preset number of sampling points is 1024, one sampling period is 1.024 s, and the number of acceleration data collected within one sampling period is 1024. The acceleration data can specifically be the data of the acceleration change in the vertical direction of the track running direction.

[0055] Optionally, when the first sensor is a velocity sensor or a displacement sensor, the corresponding acceleration data can also be calculated based on the velocity data collected by the velocity sensor or the displacement data collected by the displacement sensor.

[0056] In practical applications, due to the influence of the environment, acquisition equipment, signal truncation, etc., the collected acceleration data may not be directly used for vibration analysis. Therefore, it is also necessary to process the acceleration data according to the preset processing rules to obtain vibration data.

[0057] Specifically, the preset processing rules can be used to indicate at least one of the following processes for the acceleration data: Process the acceleration data according to the environmental parameters; Eliminate the DC component from the acceleration data; Process the acceleration data through a window function.

[0058] Specifically, the environmental parameters can include environmental information such as temperature and humidity. The window function can be used to reduce spectral leakage. There are various window functions, such as rectangular window, Hanning window, Hamming window, etc., which can be specifically determined according to the requirements in practical applications.

[0059] In the rail transit vibration monitoring and analysis system, temperature is an important indicator affecting the measurement accuracy. When the train runs at high speed, the high-temperature environment will interfere with the measurement results of the acceleration sensor. Therefore, it is necessary to weaken the influence of temperature on the acceleration sensor data to improve the accuracy of vibration analysis.

[0060] According to an optional embodiment of this specification, before the system is deployed, a calibration experiment of the sensor can be carried out. By collecting the data of the first sensor at different temperatures, a relationship model between the output value of the first sensor and the temperature is established. This step usually needs to be carried out in a laboratory environment, and the calibration curve is obtained through multiple measurements. According to the data of the calibration experiment, a temperature compensation model is established. Common temperature compensation models include linear models and non-linear models. Taking the linear temperature compensation model as an example below, the linear temperature compensation formula can be seen in the following formula (1): Formula (1) Wherein, is the output value of the first sensor after compensation, is the output value of the first sensor measured actually, is the temperature coefficient, determined by calibration experiment, is the current ambient temperature, is the reference temperature (usually the temperature during calibration is generally 25 degrees Celsius).

[0061] After temperature compensation, the acceleration data output by the first sensor is , wherein . Since the data may contain a DC component without available frequency information at this time, therefore, in order to successfully convert the time-domain data into frequency-domain data and obtain more accurate vibration frequency and vibration amplitude subsequently, it is also necessary to eliminate the DC component. Specifically, the DC component can be eliminated through the following formula (2).

[0062] Formula (2) Furthermore, in order to reduce spectral leakage, can be processed by the Hanning window function to obtain vibration data that can be used for vibration analysis . Specifically, the Hanning window function can be processed through the following formula (3).

[0063] Formula (3) Applying this embodiment, by the first sensor, according to the preset sampling frequency and preset number of sampling points, the acceleration data of the object to be detected is collected, and real-time collection of vibration data can be realized; by processing the acceleration data according to the preset processing rules to obtain vibration data, the accuracy and efficiency of subsequent vibration analysis can be improved, thereby improving the accuracy and efficiency of the fault detection result, and realizing real-time vibration analysis and fault detection of the train and the track during the train operation.

[0064] In practical applications, the object to be detected may include a train and a track, and the corresponding attribute information and fault types of different objects to be detected are different.

[0065] According to an optional embodiment of this specification, the object to be detected includes a train, and the attribute information includes structural information and operation information. Obtaining the attribute information of the object to be detected may include the following steps: Obtain the structural information and operation information corresponding to at least one component of the train.

[0066] Specifically, the train body may include multiple components, that is, multiple train parts, such as wheels, bearings, motors, gears, and so on. The corresponding structural information and operation information of different components are different.

[0067] In practical applications, during the operation of a train, the operating information of the wheels can include the wheel speed; the structure of the bearing can include an outer bearing ring, an inner bearing ring, a cage, and rolling elements, and the corresponding structure information can include the diameter of the rolling elements (d), the diameter of the inner bearing ring (D), the contact angle ( ), etc. The operating information of the bearing can include the shaft speed; the structure of the motor can include a rotor and a stator, and the operating information can include the rotor speed; the operating information of the gear can include the gear speed.

[0068] Applying this embodiment, by obtaining the structure information and operating information corresponding to at least one component of the train, it is possible to determine which components of the train may have faults, and based on the components that may have faults, obtain the corresponding fault characteristic frequencies of these components, so as to quickly detect whether there are potential safety hazards in each component of the train.

[0069] In practical applications, the flatness and safety of the track also play an important role in the safety of the train operation process. Therefore, the object to be detected can include not only the train but also the track.

[0070] According to another optional embodiment of this specification, the object to be detected includes the track, and the attribute information includes the status information of the track.

[0071] Specifically, the status information of the track can include information such as the position, structure, and type of the track, such as the section position where the track is located, the gauge type, and the geometric structure.

[0072] Optionally, obtaining the status information of the track can include: obtaining the status information of the specified track to be detected.

[0073] In the actual implementation process, the status information of the track can be understood as a type of system configuration information, which can be recorded in an electronic map and can also be stored in a database, a data monitoring module, etc. Based on the specified track to be detected, such as a specific section or a specific position area, the corresponding status information can be obtained.

[0074] Optionally, obtaining the status information of the track can also include: determining the track that the target train is currently passing through as the track to be detected; obtaining the status information corresponding to the track to be detected.

[0075] In the actual implementation process, it is also possible to determine the track to be detected based on the track that the target train is currently passing through, so as to obtain the status information corresponding to the track to be detected. The target train can be any train in operation.

[0076] Applying this embodiment, based on the status information of the track, the corresponding fault characteristic frequency can be obtained, so as to realize the vibration detection of the track. Moreover, in the case of detecting a fault or an anomaly, an alarm message corresponding to the status information can also be generated to improve the safety of the track.

[0077] In practical applications, when the attribute information of the object to be detected is determined, the corresponding fault characteristic frequency of the object to be detected can be obtained according to the attribute information, so that the fault troubleshooting of the vibration data of the object to be detected can be realized based on the fault characteristic frequency.

[0078] In one or more alternative embodiments of this specification, determining the fault characteristic frequency corresponding to the attribute information may include the following steps: Obtain a fault information table, where the fault information table is used to record the static fault information and dynamic fault information of the object to be detected; Read the static fault characteristic frequency in the static fault information, and read the dynamic fault characteristic frequency algorithm in the dynamic fault information, where the dynamic fault characteristic frequency algorithm includes algorithms corresponding to at least one fault type and is pre-configured based on the attribute information and the fault type; Generate the dynamic fault characteristic frequency corresponding to the attribute information according to the dynamic fault characteristic frequency algorithm.

[0079] Specifically, the fault information table can be understood as a structure for recording the static fault information and dynamic fault information of the object to be detected. Various types of faults corresponding to the object to be detected and the fault characteristic frequencies corresponding to each fault type can be stored in the fault information table.

[0080] Among them, the static fault information is the fault information that does not need to be calculated and can be directly read. That is, the static fault information is not affected by the operating state of the object to be detected and the structure of the object to be detected, and is a relatively fixed fault information. The dynamic fault information is the fault information that is affected by the operating state and structure information of the object to be detected and needs to be calculated in real time. The static fault information may include the static fault type and the static fault characteristic frequency corresponding to the fault type; the dynamic fault characteristic frequency may include the dynamic fault type and the dynamic fault characteristic frequency algorithm. The dynamic fault characteristic frequency algorithm can be used to guide the calculation method of the dynamic fault characteristic frequency, and specifically can be one or a group of calculation formulas for the dynamic fault characteristic frequency. The dynamic fault characteristic frequency algorithm may include one or more, and each algorithm is used to calculate the dynamic fault characteristic frequency under different fault types. One fault type may correspond to one or a group of dynamic fault characteristic frequency calculation formulas.

[0081] Optionally, the dynamic fault characteristic frequency algorithm is pre-configured based on the fault type and the attribute information of the object to be detected. Exemplarily, in the case where the object to be detected is a train, the corresponding fault characteristic frequency calculation formula can be configured based on the train structure attributes and the fault types corresponding to the structure attributes, so as to obtain the dynamic fault characteristic frequency algorithm.

[0082] In the actual implementation process, technicians can regularly perform structural analysis and fault troubleshooting on the train or track, and can add new dynamic fault characteristic frequency algorithms or configure and update the original dynamic fault characteristic frequency algorithms based on the collected historical data and with the help of expert experience or large models.

[0083] It should be noted that the fault characteristic frequency refers to the typical frequencies corresponding to different fault types when analyzing the vibration data of the train or track. These typical frequencies can be used for diagnosing and detecting faults in the track and related equipment.

[0084] Optionally, the static fault characteristic frequency can be read from the fault information table based on the attribute information; the dynamic fault characteristic frequency can be read from the fault information table based on the attribute information, and the corresponding calculation formula of the dynamic fault characteristic frequency algorithm can be obtained, and calculated based on the attribute information and the calculation formula.

[0085] Exemplarily, the fault types included in the static fault information can be: track irregularity, poor contact between wheel and track, stator fault, etc. The static fault characteristic frequency corresponding to the track irregularity is between 1 - 30 Hz; the static fault characteristic frequency corresponding to the poor contact between wheel and track is between 30 - 300 Hz; the static fault characteristic frequency corresponding to the stator fault is 50 Hz and its higher harmonics (such as 50 Hz, 100 Hz, 150 Hz, etc.).

[0086] The fault types included in the dynamic fault information can be: wheel imbalance, bearing fault, rotor imbalance, gear fault, etc.

[0087] The calculation formula for the dynamic fault characteristic frequency corresponding to the wheel imbalance is shown in the following formula (4): Formula (4) Where n is the wheel speed. The wheel speed can be transmitted in real time through CAN communication.

[0088] It should be noted that when the calculated characteristic frequency is 30 Hz, that is, the wheel speed is 1800 RPM, if there is an amplitude at this frequency, it can be first judged whether the wheel is in an unbalanced state, and then it can be detected whether it is a track irregularity.

[0089] The bearing fault can specifically include bearing outer ring fault, bearing inner ring fault, cage fault and rolling element fault.

[0090] Among them, the calculation formula for the dynamic fault characteristic frequency corresponding to the outer ring fault of the bearing is shown in the following formula (5): Formula (5) The calculation formula for the dynamic fault characteristic frequency corresponding to the inner ring fault of the bearing is shown in the following formula (6): Formula (6) The calculation formula for the dynamic fault characteristic frequency corresponding to the cage fault is shown in the following formula (7): Formula (7) The calculation formula for the dynamic fault characteristic frequency corresponding to the rolling element fault is shown in the following formula (8): Formula (8) Among them, is the rotational speed of the shaft (unit: RPM), d is the diameter of the rolling element, D is the diameter of the inner ring of the bearing, is the contact angle. The above data are all updated and input in real time.

[0091] Rotor imbalance is the fault information under the motor fault type, and the calculation formula for the corresponding dynamic fault characteristic frequency is shown in the following formula (9): Formula (9) The gear fault can be obtained by calculating the gear meshing frequency, and the calculation formula for the corresponding dynamic fault characteristic frequency is shown in the following formula (10): Formula (10) Among them, is the rotational speed of the gear (RPM), and N is the number of teeth on each gear.

[0092] Applying this embodiment, by reading the static fault characteristic frequency and the preset algorithm corresponding to the attribute information based on the fault information table; according to the preset algorithm, generating the dynamic fault characteristic frequency corresponding to the attribute information, the fault characteristic frequency corresponding to each attribute information during the current real-time operation of the object to be detected can be obtained based on the pre-recorded fault characteristic frequency related to the object to be detected, so that the accurate detection of vibration faults can be realized based on the current corresponding fault characteristic frequency.

[0093] It should be noted that the vibration data collected by the first sensor are vibration data distributed in the time domain. In order to obtain the frequencies at which the vibration data are distributed and obtain the vibration amplitudes corresponding to each frequency, it is also necessary to convert the vibration data from the time domain to the frequency domain.

[0094] Step 304: Analyze the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected.

[0095] Specifically, the multiple vibration frequencies corresponding to the object to be detected can be understood as the multiple vibration frequencies at which the vibration data of the object to be detected is distributed.

[0096] In one or more alternative embodiments of this specification, parsing the vibration data to obtain the multiple vibration frequencies corresponding to the object to be detected may include the following steps: Perform a discrete Fourier transform on the vibration data to obtain the multiple vibration frequencies included in the vibration data and the vibration amplitudes corresponding to each vibration frequency respectively.

[0097] Specifically, the discrete Fourier transform (DFT) transforms a wave (function) into a form of superposition of multiple simple harmonic waves (trigonometric functions), thereby transforming the signal from the time domain to the frequency domain. After the DFT transformation, the obtained frequency-domain signal is a complex number sequence, where each complex number corresponds to a frequency point. The modulus value of the complex number represents the vibration amplitude at that frequency.

[0098] The time domain is used to describe the relationship of a mathematical function or a physical signal with respect to time. In its coordinate system, the horizontal axis is time and the vertical axis is the function value. The frequency domain is used to describe the corresponding relationship between the frequency and the amplitude of a signal. In its coordinate system, the horizontal axis is frequency and the vertical axis is the vibration amplitude.

[0099] Optionally, the formula corresponding to the discrete Fourier transform can be seen in the following formula (11): Formula (11) In the actual implementation process, through the above formula (11), the data at different frequency indices can be calculated. Among them is the frequency index data. When = 1, represents the amplitude of the component with a frequency of = 0.9766 Hz in the signal; when = 100, it represents the amplitude of the component with a frequency of = 97.66 Hz in the signal. The larger the amplitude, the higher the proportion of the frequency component in the vibration signal. Through the amplitudes of these frequency components, fault diagnosis can be carried out by comparing with the fault characteristic frequencies.

[0100] Applying this embodiment, by performing a discrete Fourier transform on the vibration data, the vibration data can be parsed to obtain the multiple vibration frequencies at which the vibration data is distributed and the vibration amplitudes corresponding to each vibration frequency, so that fault diagnosis can be carried out based on the vibration frequencies and vibration amplitudes by comparing with the fault characteristic frequencies, and specific fault detection information about the train and the track during the train operation can be obtained.

[0101] Step 306: From multiple vibration frequencies, screen out the target vibration frequency that matches the fault characteristic frequency, and determine the fault detection information of the object to be detected according to the target vibration frequency.

[0102] In practical applications, when the fault characteristic frequency of the object to be detected and the multiple vibration frequencies corresponding to the vibration data of the object to be detected are determined, the target vibration frequency that matches the fault characteristic frequency can be screened out from the multiple vibration frequencies, and the fault detection information of the object to be detected can be determined according to the target vibration frequency.

[0103] Specifically, the target vibration frequency can be understood as the vibration frequency that matches the fault characteristic frequency, that is, the target vibration frequency is the same as the fault characteristic frequency. The fault detection information may include whether there is a fault in the object to be detected, and if there is a fault, what the corresponding fault type is.

[0104] According to an optional embodiment of this specification, determining the fault detection information of the object to be detected according to the target vibration frequency may include the following steps: Obtain the target vibration amplitude corresponding to the target vibration frequency, and determine whether the target vibration amplitude exceeds the preset vibration amplitude threshold corresponding to the fault characteristic frequency; If so, determine the fault type corresponding to the fault characteristic frequency that matches the target vibration frequency as the fault type of the object to be detected, and obtain the fault detection information.

[0105] Specifically, the target vibration amplitude is the vibration amplitude corresponding to the target vibration frequency. The preset vibration amplitude threshold can be used to determine whether there is a fault in the target vibration frequency.

[0106] Optionally, the target vibration amplitude can be calculated according to the above formula (11). When the target vibration amplitude exceeds the preset vibration amplitude threshold, it can be considered that there is a fault in the target vibration frequency; when the target vibration amplitude does not exceed the preset vibration amplitude threshold, it can be considered that there is no fault in the target vibration frequency.

[0107] In practical applications, when the target vibration amplitude exceeds the preset vibration amplitude threshold, there is a fault in the target vibration frequency, and the fault type corresponding to the fault characteristic frequency that matches the target vibration frequency can be determined as the fault type of the object to be detected.

[0108] Applying this embodiment, by obtaining the target vibration amplitude corresponding to the target vibration frequency and determining whether the target vibration amplitude exceeds the preset vibration amplitude threshold corresponding to the fault characteristic frequency, it is possible to diagnose whether there is a fault in the object to be detected, and in the case of a fault, determine the fault type of the object to be detected, so as to realize the fault diagnosis of the object to be detected and obtain a more accurate and detailed fault detection result.

[0109] In practical applications, it is also possible to obtain unidentifiable vibration frequencies by analyzing vibration data. According to an optional embodiment of this specification, after analyzing the vibration data and obtaining multiple vibration frequencies corresponding to the object to be detected, the following steps may further be included: Obtain the vibration frequencies to be identified that do not match the fault characteristic frequencies and whose corresponding vibration amplitudes are not zero from the multiple vibration frequencies; Generate an analysis instruction, where the analysis instruction is used to instruct the analysis object to analyze whether there is a fault in the vibration frequencies to be identified; Receive the analysis result returned by the analysis object.

[0110] Specifically, the vibration frequencies to be identified are the vibration frequencies that do not match the fault characteristic frequencies and whose corresponding vibration amplitudes are not zero. Such vibration frequencies may have unrecognized faults or may not have faults. The analysis instruction is an instruction used to instruct the analysis object to analyze whether there is a fault in the vibration frequencies to be identified. The analysis object can be a detection device in the system or relevant staff.

[0111] Applying this embodiment, by obtaining the vibration frequencies to be identified that do not match the fault characteristic frequencies and whose corresponding vibration amplitudes are not zero from the multiple vibration frequencies and generating an analysis instruction, it is possible to further analyze the vibration frequencies for which faults cannot be identified, so as to timely discover abnormal situations of the train and the track, which is beneficial to improving the train operation safety.

[0112] In the case of receiving the analysis result, further, according to an optional embodiment of this specification, the analysis result includes that there is a fault in the vibration frequencies to be identified; after receiving the analysis result returned by the analysis object, the following steps may further be included: Update the fault characteristic frequencies according to the vibration frequencies to be identified.

[0113] In the actual implementation process, in the case where there is a fault in the vibration frequencies to be identified, the fault may be a new type of fault or an existing type of fault.

[0114] In the case where the fault type corresponding to the vibration frequencies to be identified is a new fault type, the vibration frequencies to be identified can be added to the fault characteristic frequencies, so as to further enrich the fault types and the corresponding fault characteristic frequencies; in the case where the fault type corresponding to the vibration frequencies to be identified is an existing type of fault, it indicates that the fault information of the existing type needs to be updated, and then the fault characteristic frequencies corresponding to the existing type of fault can be updated to the vibration frequencies to be identified.

[0115] Applying this embodiment, by updating the fault characteristic frequency according to the vibration frequency to be recognized, the dynamic adaptability of the system to new fault types and frequencies can be improved, and the fault recognition information can be updated according to the actual operation conditions of the train, thereby improving the long-term effectiveness and adaptability of the system.

[0116] An embodiment of this specification provides a fault detection method, which acquires vibration data and attribute information of an object to be detected, and determines the fault characteristic frequency corresponding to the attribute information; analyzes the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected; screens out the target vibration frequencies that match the fault characteristic frequencies from the multiple vibration frequencies, and determines the fault detection information of the object to be detected according to the target vibration frequencies. By acquiring the vibration data of the object to be detected, the vibration data can be analyzed to obtain multiple vibration frequencies; by acquiring the attribute information of the object to be detected, the fault characteristic frequency corresponding to the object to be detected can be determined, so that the fault analysis of the object to be detected can be realized according to the vibration frequencies corresponding to the vibration data and the fault characteristic frequencies, and the fault analysis efficiency and accuracy can be improved.

[0117] The following combines the attached Figures 4 - 6 , taking the application of the fault detection method provided in this specification in the rail transit vibration monitoring system as an example, to further illustrate the fault detection method.

[0118] See Figure 4 , Figure 4 shows the processing flow chart of a fault detection method provided by an embodiment of this specification, which specifically includes the following S402 - S416.

[0119] S402: Initialize the sensor.

[0120] In practical applications, when the vibration monitoring system starts, relevant sensors can be initialized. The sensors can include speed sensors, displacement sensors, acceleration sensors, temperature sensors, humidity sensors, etc., and can be specifically determined according to the requirements in practical applications.

[0121] S404: Use the sensor to collect vibration data.

[0122] Specifically, the vibration data can include acceleration data in the direction perpendicular to the track.

[0123] S406: Determine the frequency resolution through data analysis.

[0124] In practical applications, since frequencies below 500Hz can already cover a variety of conventional fault information, this system can select a sampling rate = 1000Hz, the number of sampling points N = 1024, and the frequency resolution .

[0125] In the data analysis stage, other sampling rates and the number of sampling points can also be set according to the requirements in actual applications, so as to obtain a frequency resolution that meets the requirements.

[0126] S408: Perform temperature compensation on the vibration data.

[0127] Optionally, the temperature compensation can be achieved through a pre-established temperature compensation model; other compensations such as humidity can also be performed on the vibration data. Specifically, it can be determined according to the requirements in actual applications.

[0128] S410: Obtain the spectral signal through spectral analysis.

[0129] Optionally, the compensated vibration data can be successively subjected to DC component elimination processing, windowing processing, and fast Fourier transform processing to obtain the spectral signal.

[0130] S412: Determine whether there is a fault frequency band.

[0131] If it is detected that there is an unknown frequency band, then execute S414 - S416.

[0132] S414: Report the unknown frequency band information and the GPS-reported location.

[0133] S416: Notify the staff to check and update the frequency band information.

[0134] If there is no fault frequency band and all frequency bands are normal, then execute S414'.

[0135] S414': Report the inspection log.

[0136] If there is a fault frequency band, then execute S414".

[0137] S414": Report the fault and the GPS-reported location.

[0138] In actual applications, if there is a frequency that matches the fault characteristic frequency in the fault frequency band, then determine information such as the fault type based on the matched fault characteristic frequency, generate an alarm log, and report the fault location through GPS; if there is no frequency in the fault frequency band, then the frequency band is normal, and it can be considered that there is no fault at present, and report the detection log of no fault at present; if there is a frequency in the fault frequency band but it cannot be matched with the fault characteristic frequency, then it can be considered that there is an unknown anomaly or an unidentifiable fault. The unknown frequency band information and the location can be reported to the staff and wait for the staff to check and update the frequency band information.

[0139] The fault detection method may further include the following S402' - S404'.

[0140] S402': Receive the update content.

[0141] S404': Update the frequency band fault information table.

[0142] Specifically, the updated content can be the content for updating a specific fault frequency band and the fault information corresponding to the fault frequency band; it can also be a new version of the frequency band fault information table.

[0143] In practical applications, the staff can update the frequency band fault information table configured in the system, or re-upload a new version of the frequency band fault information table. The system will update the frequency band fault information table based on the updated content.

[0144] Applying this embodiment, through the rail transit vibration monitoring system, by analyzing data to determine the frequency resolution, collecting vibration data using sensors, and performing spectral analysis on the vibration data to obtain spectral signals, it is possible to collect vibration data during the train operation in real time, perform fault analysis on the vibration data, promptly detect possible problems with the train or the track, and timely locate the position where the fault occurs, which is beneficial to improving the safety of rail transit.

[0145] See Figure 5 , Figure 5 shows the data analysis process flow chart of a fault detection method provided by an embodiment of this specification, specifically including the following S502 - S538.

[0146] S502: Collect vibration data.

[0147] In practical applications, at the beginning of the current cycle of fault detection, vibration data can be collected through sensors.

[0148] S504: Obtain spectral signals based on Fourier transform.

[0149] S506: Extract the characteristic frequencies in the spectral signals.

[0150] S508: Check the low - frequency range.

[0151] Specifically, the low - frequency range can be pre - configured as 1 - 30 Hz. If the characteristic frequencies extracted from the spectral signals are within the range of 1 - 30 Hz, it is determined that there are characteristic frequencies in the low - frequency range, and the fault type is track irregularity.

[0152] If there are characteristic frequencies in the low - frequency range, execute S510; otherwise, execute S512.

[0153] S510: Record as track irregularity.

[0154] Optionally, if there are characteristic frequencies in the low - frequency range, it can be recorded as a fault of track irregularity, and corresponding alarm information, report the alarm information and the fault location can also be generated.

[0155] S512: Check the intermediate frequency range.

[0156] Specifically, the intermediate frequency range can be pre-configured to 30 - 300 Hz. If the characteristic frequency extracted from the spectrum signal is within the range of 30 - 300 Hz, it is determined that there is a characteristic frequency within the intermediate frequency range, and the fault type is poor contact between the wheel and the track.

[0157] If there is a characteristic frequency within the intermediate frequency range, execute S514; otherwise, execute S516.

[0158] S514: Record it as poor contact between the wheel and the track.

[0159] Optionally, if there is a characteristic frequency within the intermediate frequency range, it can be recorded as a fault of poor contact between the wheel and the track, and corresponding alarm information, report the alarm information and the fault location can also be generated.

[0160] It should be noted that the above low-frequency range and intermediate frequency range are both pre-configured static fault characteristic frequency bands.

[0161] S516: Calculate the wheel fault characteristic frequency.

[0162] S518: Detect whether there is a matching frequency.

[0163] If the characteristic frequency extracted from the spectrum signal matches the wheel fault characteristic frequency, execute S520; otherwise, execute S522.

[0164] S520: Record it as wheel imbalance.

[0165] S522: Calculate the bearing fault characteristic frequency.

[0166] S524: Detect whether there is a matching frequency.

[0167] If the characteristic frequency extracted from the spectrum signal matches the bearing fault characteristic frequency, execute S526; otherwise, execute S528.

[0168] S526: Record it as bearing fault.

[0169] S528: Calculate the rotor fault characteristic frequency.

[0170] S530: Detect whether there is a matching frequency.

[0171] Specifically, the motor fault characteristic frequency can include the rotor fault characteristic frequency and the stator fault characteristic frequency. Among them, the rotor fault characteristic frequency is a dynamic fault characteristic frequency and needs to be calculated; the stator fault characteristic frequency can be directly read from the configuration information.

[0172] If the characteristic frequency extracted from the spectrum signal matches the rotor fault characteristic frequency and / or the stator fault characteristic frequency, then execute S532; otherwise, execute S534.

[0173] S532: Record it as a motor fault.

[0174] In the actual implementation process, based on the specific fault type, detailed fault information of the motor fault can be recorded, such as rotor fault, stator fault, both rotor and stator faults, etc.

[0175] S534: Calculate the gear fault characteristic frequency.

[0176] S536: Detect the gear fault characteristic frequency.

[0177] If the characteristic frequency extracted from the spectrum signal matches the gear fault characteristic frequency, then execute S538; otherwise, the fault detection for this period ends.

[0178] S538: Record it as a gear fault.

[0179] It should be noted that the above-mentioned wheel fault characteristic frequency, bearing fault characteristic frequency, rotor fault characteristic frequency, and gear fault characteristic frequency are all dynamic fault characteristic frequencies, which need to be calculated based on the information collected in real time during the train operation.

[0180] In practical applications, the monitoring system can start the fault detection for the next period in response to the end of the fault detection for the current period; it can also start the fault detection for the next period in response to other fault detection instructions.

[0181] Applying this embodiment, by collecting vibration data in each period and judging the fault type in sequence for the vibration data, a comprehensive detection of the track and train safety can be achieved, and the fault cause can be discovered and accurately located in a timely manner. It should be noted that S508 - S538 only gives an optional example of the detection sequence and is not used to limit the fault detection sequence of this specification.

[0182] See Figure 6 , Figure 6 shows the flowchart of the fault frequency update process of a fault detection method provided by an embodiment of this specification, specifically including the following S602 - S616.

[0183] S602: Receive communication data.

[0184] S604: Judge whether to update the dynamic frequency band.

[0185] Optionally, the communication data may include update information for dynamic frequency bands, which may be new dynamic frequency bands or modifications to the information of the original dynamic frequency bands. The dynamic frequency bands may be dynamic fault characteristic frequencies or dynamic fault characteristic frequency ranges.

[0186] In practical applications, since dynamic fault characteristic frequencies often involve complex calculation formulas, firmware upgrades are required to implement the updates. Specifically, the firmware update method can be through CAN communication updates and 4G network updates.

[0187] If so, execute S606; if not, return to S602.

[0188] S606: Store the file upgrade data in the upgrade area.

[0189] S608: Jump to the bootloader and store the running area code in the backup area.

[0190] Specifically, the bootloader can be the bootloader in the system, which is used to coordinate and manage the program codes in each area of the system and help the system start and run in a stable state.

[0191] In the actual implementation process, the rail transit vibration monitoring system can obtain a new upgrade package from the central control system and manage code updates through the system's bootloader.

[0192] S610: Based on the bootloader, add the upgrade area code to the running area.

[0193] S612: Check whether the running code is updated.

[0194] If the update of the running code fails, execute S614; if the update is successful, jump to execute S616.

[0195] S614: Restore the backup area code and discard the upgrade area code.

[0196] S616: Run the program.

[0197] In practical applications, in the case where the update of the running code fails, the upgrade area code with the update failure can be discarded and the backup area code can be restored so that the program can continue to run according to the version before the update.

[0198] In addition, the static fault characteristic frequency is the fault frequency band corresponding to a fixed frequency. These frequency bands do not require complex formula calculations and can be directly written into the system configuration. In the rail transit vibration monitoring system, a storage chip EEPROM is externally controlled by the main control and can be used to store static fault frequency bands. In the case where the static fault frequency band needs to be updated or modified, it can be directly written through the communication port according to the protocol.

[0199] Applying this embodiment to manage the system code through the bootloader can restore the data in the system before the upgrade even in case of upgrade failure, thereby improving the stability of system operation.

[0200] Corresponding to the above method embodiment, this specification also provides an embodiment of a fault detection device. Figure 7 The structural schematic diagram of a fault detection device provided by an embodiment of this specification is shown. As Figure 7 shown, the device includes: An acquisition module 702: configured to acquire the vibration data and attribute information of the object to be detected, and determine the fault characteristic frequency corresponding to the attribute information.

[0201] An analysis module 704: configured to analyze the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected.

[0202] A determination module 706: configured to screen out the target vibration frequencies that match the fault characteristic frequencies from the multiple vibration frequencies, and determine the fault detection information of the object to be detected according to the target vibration frequencies.

[0203] Optionally, the acquisition module 702 is further configured to: Collect the vibration data of the object to be detected through a first sensor deployed on the object to be detected, where the vibration data includes at least one of speed data, displacement data, and acceleration data.

[0204] Optionally, the acquisition module 702 is further configured to: Collect the acceleration data of the object to be detected through the first sensor according to a preset sampling frequency and a preset number of sampling points; Process the acceleration data according to a preset processing rule to obtain the vibration data.

[0205] Optionally, the object to be detected includes a train, and the attribute information includes structural information and operation information; the acquisition module 702 is further configured to: Acquire the structural information and operation information corresponding to at least one component of the train.

[0206] Optionally, the object to be detected includes a track, and the attribute information includes the state information of the track.

[0207] Optionally, the acquisition module 702 is further configured to: Acquire a fault information table, where the fault information table is used to record the static fault information and dynamic fault information of the object to be detected; Read the static fault characteristic frequencies in the static fault information, and read the dynamic fault characteristic frequency algorithms in the dynamic fault information, where the dynamic fault characteristic frequency algorithms include algorithms corresponding to at least one fault type and are pre-configured based on attribute information and fault types; Generate the dynamic fault characteristic frequencies corresponding to the attribute information according to the dynamic fault characteristic frequency algorithms.

[0208] Optionally, the parsing module 704 is further configured to: Perform a discrete Fourier transform on the vibration data to obtain multiple vibration frequencies included in the vibration data and the vibration amplitudes respectively corresponding to each vibration frequency.

[0209] Optionally, the determination module 706 is further configured to: Obtain the target vibration amplitude corresponding to the target vibration frequency, and determine whether the target vibration amplitude exceeds the preset vibration amplitude threshold corresponding to the fault characteristic frequency; If so, determine the fault type corresponding to the fault characteristic frequency that matches the target vibration frequency as the fault type of the object to be detected, and obtain the fault detection information.

[0210] Optionally, the fault detection device further includes an analysis module, which is configured to: Obtain the vibration frequencies to be identified that do not match the fault characteristic frequencies and whose corresponding vibration amplitudes are not zero from the multiple vibration frequencies; Generate an analysis instruction, where the analysis instruction is used to instruct the analysis object to analyze whether there is a fault in the vibration frequencies to be identified; Receive the analysis result returned by the analysis object.

[0211] Optionally, the analysis module is further configured to: Update the fault characteristic frequencies according to the vibration frequencies to be identified.

[0212] Applying this embodiment, by acquiring the vibration data of the object to be detected, the vibration data can be parsed to obtain multiple vibration frequencies; by acquiring the attribute information of the object to be detected, the fault characteristic frequencies corresponding to the object to be detected can be determined, so that the fault analysis of the object to be detected can be realized according to the vibration frequencies corresponding to the vibration data and the fault characteristic frequencies, improving the efficiency and accuracy of fault analysis.

[0213] The above is a schematic solution of a fault detection device according to this embodiment. It should be noted that the technical solution of this fault detection device and the technical solution of the above fault detection method belong to the same concept. For the details not described in the technical solution of the fault detection device, reference can be made to the description of the technical solution of the above fault detection method.

[0214] Figure 8FIG. 0 shows a block diagram of a computing device 800 provided according to an embodiment of the present specification. The components of the computing device 800 include, but are not limited to, a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0215] The computing device 800 further includes an access device 840, which enables the computing device 800 to communicate via one or more networks 860. Examples of these networks include the Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 840 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface.

[0216] In an embodiment of the present specification, the above components of the computing device 800, as well as Figure 8 other components not shown, may also be connected to each other, for example, via a bus. It should be understood that Figure 8 the block diagram of the computing device shown is for illustrative purposes only and is not a limitation on the scope of the present specification. Those skilled in the art may add or replace other components as needed.

[0217] The computing device 800 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.) or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 800 can also be a mobile or stationary server.

[0218] Wherein, the processor 820 is configured to execute the following computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the above-mentioned fault detection method are implemented.

[0219] The above is a schematic solution of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the above-mentioned fault detection method belong to the same concept. For the details not described in detail in the technical solution of the computing device, reference can be made to the description of the technical solution of the above-mentioned fault detection method.

[0220] An embodiment of this specification also provides a computer-readable storage medium, which stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the above-mentioned fault detection method are implemented.

[0221] The above is a schematic solution of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the above-mentioned fault detection method belong to the same concept. For the details not described in detail in the technical solution of the storage medium, reference can be made to the description of the technical solution of the above-mentioned fault detection method.

[0222] An embodiment of this specification also provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the above-mentioned fault detection method are implemented.

[0223] The above is a schematic solution of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the above-mentioned fault detection method belong to the same concept. For the details not described in detail in the technical solution of the computer program product, reference can be made to the description of the technical solution of the above-mentioned fault detection method.

[0224] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0225] The computer instructions include computer program code, which may be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0226] It should be noted that for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of this specification are not limited by the described order of actions, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this specification.

[0227] In the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0228] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The alternative embodiments do not elaborate on all the details and do not limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can well understand and utilize this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A fault detection method, characterized in that, Including: Obtain the vibration data and attribute information of the object to be detected, and determine the fault characteristic frequency corresponding to the attribute information; Analyze the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected; From the multiple vibration frequencies, screen the target vibration frequencies that match the fault characteristic frequency, and determine the fault detection information of the object to be detected according to the target vibration frequencies.

2. The method according to claim 1, wherein The obtaining of the vibration data of the object to be detected includes: Collect the vibration data of the object to be detected through a first sensor deployed on the object to be detected, where the vibration data includes at least one of speed data, displacement data, and acceleration data.

3. The method according to claim 2, wherein The collecting of the vibration data of the object to be detected through a first sensor deployed on the object to be detected includes: Collect the acceleration data of the object to be detected through the first sensor according to a preset sampling frequency and a preset number of sampling points; Process the acceleration data according to a preset processing rule to obtain the vibration data.

4. The method according to any one of claims 1 to 3, characterized in that, The object to be detected includes a train, and the attribute information includes structural information and operation information; The obtaining of the attribute information of the object to be detected includes: Obtain the structural information and operation information corresponding to at least one component of the train.

5. The method according to any one of claims 1 to 3, characterized in that, The object to be detected includes a track, and the attribute information includes the status information of the track.

6. The method according to claim 1, wherein The determining of the fault characteristic frequency corresponding to the attribute information includes: Obtain a fault information table, where the fault information table is used to record the static fault information and dynamic fault information of the object to be detected; Read the static fault characteristic frequencies in the static fault information, and read the dynamic fault characteristic frequency algorithms in the dynamic fault information, where the dynamic fault characteristic frequency algorithms include algorithms corresponding to at least one fault type, and are pre-configured based on the attribute information and the fault type; Generate the dynamic fault characteristic frequency corresponding to the attribute information according to the dynamic fault characteristic frequency algorithms.

7. The method according to claim 1, wherein The analyzing of the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected includes: Perform a discrete Fourier transform on the vibration data to obtain multiple vibration frequencies included in the vibration data and the vibration amplitudes corresponding to the respective vibration frequencies.

8. The method according to claim 7, wherein The determining of the fault detection information of the object to be detected according to the target vibration frequencies includes: Obtain the target vibration amplitude corresponding to the target vibration frequency, and determine whether the target vibration amplitude exceeds a preset vibration amplitude threshold corresponding to the fault characteristic frequency; If so, determine the fault type corresponding to the fault characteristic frequency that matches the target vibration frequency as the fault type of the object to be detected, and obtain the fault detection information.

9. The method according to claim 1, characterized in that After the analyzing of the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected, it further includes: Obtain the to-be-identified vibration frequencies that do not match the fault characteristic frequency and have non-zero corresponding vibration amplitudes from the multiple vibration frequencies; Generate an analysis instruction, where the analysis instruction is used to instruct an analysis object to analyze whether there is a fault in the to-be-identified vibration frequencies. Receive the analysis result returned by the analysis object.

10. The method according to claim 9, characterized in that, The analysis result includes that there is a fault in the vibration frequency to be identified; After receiving the analysis result returned by the analysis object, it further includes: Update the fault characteristic frequency according to the vibration frequency to be identified.

11. A fault detection device, characterized in that, It includes: An acquisition module, configured to acquire the vibration data and attribute information of the object to be detected, and determine the fault characteristic frequency corresponding to the attribute information; An analysis module, configured to analyze the vibration data to obtain multiple vibration frequencies corresponding to the object to be detected; A determination module, configured to screen the target vibration frequency that matches the fault characteristic frequency from the multiple vibration frequencies, and determine the fault detection information of the object to be detected according to the target vibration frequency.

12. A computing device, characterized in that, It includes: A memory and a processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the fault detection method according to any one of claims 1-10 are implemented.

13. A computer-readable storage medium, characterized in that, It stores computer programs / instructions, and when the computer programs / instructions are executed by the processor, the steps of the fault detection method according to any one of claims 1-10 are implemented.

14. A computer program product, characterized in that, It includes computer programs / instructions, and when the computer programs / instructions are executed by the processor, the steps of the fault detection method according to any one of claims 1-10 are implemented.

Images