Fault monitoring method and device, equipment and storage medium

Abstract

The invention relates to a fault monitoring method and device, equipment and a storage medium. The invention provides a fault monitoring scheme of an air compression unit, and the method comprises the steps: enabling each sensor to be installed at a preset position of the air compression unit, and enabling the sensors to comprise a sound sensor and an acceleration sensor; and then obtaining target data collected by each sensor, identifying abnormal data in the target data, extracting characteristic parameters of the abnormal data, and determining fault information of the air compression unit by using the characteristic parameters. Therefore, fault monitoring is carried out through the target data collected by the sound sensor and the acceleration sensor, possible faults of the air compression unit can be timely and accurately detected based on the sound and vibration characteristics of the air compression unit, and specific fault positions can be rapidly positioned through the mounting positions of the sensors, so that the fault detection accuracy is improved. And the reliability and the safety of the air compression unit are effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of fault monitoring, and in particular to a fault monitoring method, device, equipment and storage medium. Background Art

[0002] The air spring system is a system that controls the hardness of the spring by charging and discharging high-pressure gas. It has been widely used in the fields of automobiles and rail transportation. As the core component of the air spring system, the air compression unit mainly sucks in and compresses the outside air, increases the air pressure, and provides high-pressure air for the automobile air spring system. The air compression unit is usually composed of a motor, a cylinder, a piston, a crankshaft, a connecting rod, a valve and other components. The motor provides power to drive the crankshaft to rotate, and drives the piston to reciprocate in the cylinder through the connecting rod to achieve air intake and compression. The valve is used to control the inlet and outlet of air and pressure regulation, and its working state directly affects the performance and reliability of the entire system. The air compression unit is a typical mechatronic system. In daily operation, there may be both electrical and mechanical faults. At present, the fault diagnosis of the air compression unit mainly relies on regular manual inspections and fault diagnosis and monitoring methods based on motor-driven voltage and current acquisition. However, these methods have problems such as untimely diagnosis, insensitivity to mechanical faults, and difficulty in locating specific fault locations.

[0003] Therefore, how to timely and accurately monitor the failure of the air compression unit is a technical problem that needs to be solved by those skilled in the art. Summary of the invention

[0004] The present application provides a fault monitoring method, device, equipment and storage medium to timely and accurately monitor the faults of an air compression unit.

[0005] In a first aspect, the present application provides a fault monitoring method, comprising:

[0006] Acquire target data collected by each sensor; each sensor is installed at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor;

[0007] Identifying abnormal data in the target data;

[0008] Extracting characteristic parameters of the abnormal data;

[0009] The characteristic parameter is used to determine fault information of the air compression unit.

[0010] Optionally, the identifying abnormal data in the target data includes:

[0011] Selecting K initial centroids from the collected target data; wherein the target data includes: sound data and acceleration data;

[0012] According to the distance between each target data and the K initial centroids, each target data is divided into K categories corresponding to different initial centroids;

[0013] Determine the target centroid of each category based on the target data of each category;

[0014] If the target centroid of each category is different from the initial centroid, the target centroid is used as the initial centroid, and the step of dividing each target data into K categories corresponding to different initial centroids is continued according to the distance value between each target data and the K initial centroids;

[0015] If the target centroid of each category is the same as the initial centroid, the clustering result is obtained;

[0016] Determine abnormal data based on clustering results.

[0017] Optionally, determining abnormal data according to the clustering result includes:

[0018] Determine the target data and final centroid of each category from the clustering results;

[0019] Calculate the distance between each type of target data and the corresponding final centroid;

[0020] The discrete data is determined as abnormal data; wherein the discrete data is target data whose distance value is greater than a predetermined distance threshold.

[0021] Optionally, the determining the fault information of the air compression unit by using the characteristic parameter includes:

[0022] If the characteristic parameter does not conform to the signal characteristic under normal operating conditions, it is determined that the air compression unit is faulty and fault information is generated.

[0023] Optionally, generating fault information includes:

[0024] Determining a target sensor for collecting the abnormal data;

[0025] Determining an installation position of the target sensor;

[0026] Determining a fault location in the air compression unit using the installation position;

[0027] Determine the fault type according to the fault location and the abnormal data;

[0028] determining the severity of the fault according to the abnormal data;

[0029] Fault information is generated according to the fault type and the fault severity.

[0030] Optionally, determining a fault location in the air compression unit using the installation position includes:

[0031] If the target sensor is a target acceleration sensor, determining the installation location according to the installation position of the target acceleration sensor;

[0032] The installation location of the target acceleration sensor is determined as a fault location in the air compression unit.

[0033] Optionally, determining a fault location in the air compression unit using the installation position includes:

[0034] If the target sensor is a target sound sensor, determining an installation type of the target sound sensor;

[0035] If the installation type is an independent installation type, the installation location is determined according to the installation position of the target sound sensor, and the installation location of the target sound sensor is determined as the fault location in the air compression unit;

[0036] If the installation type is a centralized installation type, the fault location in the air compression unit is determined based on abnormal data collected by a sound sensor array; wherein the sound sensor array is composed of various sound sensors.

[0037] In a second aspect, the present application provides a fault monitoring device, comprising:

[0038] An acquisition module is used to acquire target data collected by each sensor; each sensor is installed at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor;

[0039] An identification module, used to identify abnormal data in the target data;

[0040] An extraction module, used for extracting characteristic parameters of the abnormal data;

[0041] A determination module is used to determine the fault information of the air compression unit using the characteristic parameters.

[0042] In a third aspect, the present application provides an electronic device, including:

[0043] A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the above-mentioned fault monitoring method of the present application through the computer program.

[0044] In a fourth aspect, the present application further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute the steps of the above-mentioned fault monitoring method of the present application.

[0045] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the present application provides a fault monitoring solution for an air compression unit, and the present application installs each sensor at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor; then the target data collected by each sensor is obtained, the abnormal data in the target data is identified, the characteristic parameters of the abnormal data are extracted, and the fault information of the air compression unit is determined using the characteristic parameters. It can be seen that the present application performs fault monitoring through the target data collected by the sound sensor and the acceleration sensor, and can detect possible faults of the air compression unit in a timely and accurate manner based on the sound and vibration characteristics of the air compression unit. The specific fault location can be quickly located through the installation position of the sensor, effectively improving the reliability and safety of the air compression unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0049] Figure 1 A schematic diagram of a fault monitoring method flow chart provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of another fault monitoring method flow chart provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a clustering result provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of another fault monitoring method flow chart provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of a system structure provided for an embodiment of the present application;

[0054] Figure 6A schematic diagram of another fault monitoring method flow chart provided in an embodiment of the present application;

[0055] Figure 7 A schematic diagram of the structure of a fault monitoring device provided in an embodiment of the present application;

[0056] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In the related art, the fault diagnosis and monitoring method based on the voltage and current acquisition of the motor drive mainly reflects the electrical state of the pump motor. It is often not sensitive enough to some mechanical faults, such as bearing wear, rotor imbalance, shaft bending, etc. These mechanical faults may not directly cause significant changes in voltage or current, so it is difficult to diagnose through voltage and current acquisition. For example, in the early stage of bearing wear, the current of the motor may not change much. Only when the wear is serious enough to affect the operating efficiency of the motor or cause the motor to heat up, the current will change significantly. In addition, although voltage and current acquisition can detect the existence of motor faults, it is often difficult to accurately determine the specific location of the fault. For example, when the current increases abnormally, there may be problems in multiple parts inside the motor, such as winding short circuit, bearing damage, etc., and it is necessary to further combine other detection methods to determine the specific fault location.

[0058] Therefore, in this solution, a fault monitoring method, device, equipment and storage medium are provided to diagnose the fault of the air compression unit in real time and accurately, and issue a warning in advance to improve the reliability and safety of the air spring system.

[0059] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0060] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0061] See also Figure 1 , Figure 1A schematic diagram of a fault monitoring method provided in an embodiment of the present application, the method specifically comprises the following steps:

[0062] S101, acquiring target data collected by each sensor; each sensor is installed at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor;

[0063] In this embodiment, the possible faults of the air compression unit are detected timely and accurately mainly based on the sound and vibration characteristics of the air compression unit. Therefore, the sensor in this solution can be a sound sensor and an acceleration sensor. The sound sensor is used to collect sound data, and the acceleration sensor is used to collect acceleration data. Among them, the sound sensor in this application is a high-precision sound sensor, which has high sensitivity and a wide frequency response range, and can accurately capture various sound data generated when the air compression unit is working, including the sound under normal operating conditions and abnormal sounds under fault conditions.

[0064] In this application, the acceleration sensor can be installed on the surface of the equipment. The acceleration sensor is usually composed of a mass block, a damper, an elastic element, a sensitive element, and an adaptive circuit. During the acceleration process, the sensor measures the inertial force exerted on the mass block and obtains the acceleration value using Newton's second law. When the equipment vibrates or moves, the acceleration sensor also vibrates or moves. When the electromechanical equipment operates normally, its vibration frequency and amplitude are within a certain range, and the inertial force generated by the mass block in the acceleration sensor is relatively stable. If the equipment fails, such as loose parts, increased wear, imbalance, etc., the vibration frequency and amplitude of the equipment will change, causing the inertial force of the acceleration sensor mass block to change accordingly. Therefore, the change in acceleration data can indirectly reflect the change in the operating status of the equipment.

[0065] The present application installs a sound sensor and an acceleration sensor at a predetermined position of the air compression unit, which is a fixed position near the air compression unit. The predetermined position can ensure that the distance between the sensor and the air compression unit is moderate, so that the sound signal can be effectively collected without being interfered with by other factors. Among them, the present application can install the sensor near each component of the air compression unit, so as to accurately locate the faulty part of the air compression unit through the difference in data collected by different sensors.

[0066] For example: the sound sensor can be installed directly opposite the air compression pump motor, at a distance of about 5 cm. If the pump motor and pump body parts are not damaged and in good working condition, it will produce a continuous and uniform sound. At this time, the sound collected by the sound sensor should be stable in frequency and volume, without sharp sounds, loud friction sounds or metal knocking sounds, etc.; the acceleration sensor can be installed on the pump motor or compression pump. During normal operation, the acceleration data collected by the acceleration sensor should be moderate in amplitude and relatively stable, and have a certain regularity with load changes. When the load of the air compression pump changes, the vibration amplitude will also change accordingly. This change should be relatively stable and predictable. If the vibration amplitude changes too drastically or irregularly, it may be that the air compression pump or air spring system has a fault. Therefore, this application can determine whether the air compression unit has a fault by analyzing the target data collected by each sensor and analyzing it.

[0067] S102, identifying abnormal data in target data;

[0068] In this embodiment, abnormal data refers to data whose values ​​in the target data are obviously abnormal, such as: if the target data is sound data, and the sound data represents sound intensity, the value of the sound intensity should be within a predetermined range under normal operating conditions. If there is a value of a certain sound data that exceeds the predetermined range, the sound data is determined to be abnormal data; if the target data is acceleration data, similarly, the value of the acceleration data should be within a predetermined range under normal operating conditions. If there is a value of a certain acceleration data that exceeds the corresponding predetermined range, the acceleration data is determined to be abnormal data.

[0069] S103, extracting characteristic parameters of abnormal data;

[0070] In the present application, in order to improve the accuracy of fault identification, after identifying the abnormal data in the target data, it is also necessary to extract the characteristic parameters of the abnormal data so as to detect whether the air compression unit is faulty through the characteristic parameters. The characteristic parameter is a parameter that can reflect the operating state of the air compression unit, that is: if the air compression unit is in a normal operating state, the value of the characteristic parameter should be relatively stable and predictable, and if the air compression unit is in a faulty state, the value of the characteristic parameter will change. In the present embodiment, the characteristic parameter can be the vibration frequency, amplitude, energy distribution, etc. of the abnormal data, which is not specifically limited here.

[0071] S104: Determine fault information of the air compression unit using characteristic parameters.

[0072] When the present application uses characteristic parameters to determine the fault information of the air compression unit, the specific value of the characteristic parameters can be used to determine whether the air compression unit is faulty. If the value of the characteristic parameters is within the normal range under normal operation, it is determined that the air compression unit is not faulty. If the value of the characteristic parameters is not within the normal range, it indicates that the air compression unit may be faulty. Furthermore, when the characteristic parameters are not within the normal range, it is possible that the air compression unit is faulty, or that the characteristic parameters are abnormal due to a sensor fault. In this case, the sensor self-check can be used for troubleshooting. If the sensor fault is found, it is determined that the air compression unit is not faulty, and a sensor fault prompt message can be generated.

[0073] In this embodiment, the sensor includes a sound sensor and an acceleration sensor, so the target data includes sound data and acceleration data. Correspondingly, the abnormal data in the target data also includes abnormal sound data and abnormal acceleration data. If the characteristic parameters in the abnormal sound data and the characteristic data in the abnormal acceleration data are consistent with the signal characteristics of the normal operation of the system, it is determined that the air compression unit is in a normal working state and there is no fault. If the characteristic parameters in the abnormal sound data do not meet the signal characteristics of the normal operation of the system, or the characteristic data in the abnormal acceleration data do not meet the signal characteristics of the normal operation of the system, it is determined that the air compression unit is in a fault state, and fault information can be generated at this time. Among them, the fault information is relevant information reflecting the fault of the air compression unit, such as abnormal data, characteristic parameters, fault time, fault type, fault severity, etc., which are not specifically limited here.

[0074] In summary, it can be seen that in this application, a fault monitoring scheme for an air compression unit is provided. This application installs each sensor at a predetermined position of the air compression unit, and the sensors include a sound sensor and an acceleration sensor; then the target data collected by each sensor is obtained, the abnormal data in the target data is identified, the characteristic parameters of the abnormal data are extracted, and the fault information of the air compression unit is determined using the characteristic parameters. It can be seen that this application performs fault monitoring through the target data collected by the sound sensor and the acceleration sensor, and can detect possible faults of the air compression unit in a timely and accurate manner based on the sound and vibration characteristics of the air compression unit. Through the installation position of the sensor, the specific fault location can be quickly located, effectively improving the reliability and safety of the air compression unit.

[0075] See also Figure 2 , Figure 2 Another fault monitoring method provided in the present application is a flow chart of a method, the method specifically comprising the following steps:

[0076] S201, acquiring target data collected by each sensor; each sensor is installed at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor;

[0077] S202, selecting K initial centroids from the collected target data; wherein the target data includes: sound data and acceleration data;

[0078] S203, dividing each target data into K categories corresponding to different initial centroids according to the distance value between each target data and the K initial centroids;

[0079] S204, determining the target centroid of each category according to the target data of each category;

[0080] S205, if the target centroid of each category is different from the initial centroid, the target centroid is used as the initial centroid and S203 is continued;

[0081] S206. If the target centroid of each category is the same as the initial centroid, a clustering result is obtained;

[0082] S207, determining abnormal data according to the clustering result;

[0083] S208, extracting characteristic parameters of abnormal data;

[0084] S209: Determine the fault information of the air compression unit using the characteristic parameters.

[0085] In the present application, after acquiring the target data collected by each sensor, the normal working state of the air compression unit can be identified by analyzing the target data, and when a fault may occur. For example, if there is no abnormal data in the target data collected within a certain period of time, it means that the air compression unit is in a normal working state during the period of time. If there is abnormal data in the target data collected within a certain period of time, it means that the air compression unit may have a fault, and it is necessary to perform subsequent steps for further detection. In this embodiment, a clustering algorithm can be used to identify abnormal data, such as identifying abnormal data in the target data through a K-means clustering algorithm.

[0086] When using the K-means clustering algorithm to identify abnormal data in target data, it is first necessary to collect enough target data. The number of target data can be customized according to actual needs and is not specifically limited here. In addition, since each target data includes sound data and acceleration data, each target data can be used as a data point in the coordinate system, the sound data of the target data is used as the horizontal coordinate of the data point, and the acceleration data of the target data is used as the vertical coordinate of the data point. Then, K data points are randomly selected from each target data as the initial cluster center, and the distance value of each target data from the K cluster centers is calculated respectively. According to the distance value, each target data is divided into the category of the cluster center closest to each sample; after each target data is classified, the average value of each category is calculated to determine the new cluster centroid; if the cluster centroid changes, the new centroid is recalculated, otherwise, clustering is stopped and the clustering result is output.

[0087] See Table 1, which is a schematic table of data points corresponding to the sound data and acceleration data provided in this embodiment. A to F in Table 1 represent data points corresponding to target data collected at different time points, and each target data is collected at the same time interval, such as: if the time interval is 1s, then A is the data point corresponding to the target data collected at the 1st second, B is the data point corresponding to the target data collected at the 2nd second, and so on; X in Table 1 represents the sound data in each target data, and Y in Table 1 represents the acceleration data in each target data.

[0088] Table 1

[0089] Data Name A B C D E F X dB1 dB2 dB3 dB4 dB5 dB6 Y a1 a2 a3 a4 a5 a6

[0090] Assumption: The number of clusters K = 3, and the initial cluster centers are B, D, and F;

[0091] In the first iteration, the initial centroids are set to B, D, and F, and the distance values ​​of data points A, C, and E to the initial centroids B, D, and F are calculated respectively. Data points A, C, and E are divided into the categories corresponding to the nearest initial centroids. For example, if data point A is closest to the initial centroid B, then data point A and data point B are divided into a cluster. If data point C is closest to the initial centroid D, then data point C and data point D are divided into a cluster. If data point E is closest to the initial centroid F, then data point E and data point F are divided into a cluster. The generated division results are:

[0092] The first cluster: {A, B}; the second cluster: {C, D}; the third cluster: {E, F}.

[0093] Calculate the average value of each cluster, which is the newly calculated centroid of the cluster. In this application, the newly calculated centroid is called the target centroid, that is:

[0094] The target centroid of the first cluster is: G[(dB2-dB1) / 2,(a1-a2) / 2];

[0095] The target centroid of the second cluster is: I[(dB4-dB3) / 2,(a4-a3) / 2];

[0096] The target centroid of the third cluster is: H[(dB6-dB5) / 2,(a6-a5) / 2].

[0097] If the target centroid is different from the initial centroid, it is necessary to continue iterating, taking the target centroid as the initial centroid, continue to divide different clusters and calculate a new centroid until the centroid no longer changes and clustering ends; for example: if the target centroid of the first cluster is different from the initial centroid B, take the target centroid as the initial centroid, and continue iterating by performing the following process: calculate the distance values ​​between other data points and the updated initial centroids, and divide them into different clusters, calculate the average values ​​of different clusters to determine the newly calculated target centroid, and if the newly calculated target centroid is the same as the corresponding initial centroid, clustering ends, otherwise, continue to the next iteration process.

[0098] In this application, the clustering results can be verified by Euclidean distance: first, the sum of the squares of the distances from all data points in each cluster to the centroid CSS (Cluster Sum of Square, intra-cluster sum of squares) is calculated, and then the overall sum of squares (TCSS, Total Cluster Sum of Square) is calculated based on the CSS of each cluster. The specific calculation formula is:

[0099]

[0100] Among them, in the intra-cluster sum of squares formula, m is the number of target data in a cluster, j is the number of each target data, n represents the number of features in each target data, i represents each feature that makes up the target data x, x represents a target data in the cluster, and μ represents the cluster center in the cluster; in the overall sum of squares formula, k is the number of clusters, i is the number of each cluster, the smaller the overall sum of squares, the better the clustering effect. Therefore, after the clustering is completed, the application can verify the clustering effect by calculating the overall sum of squares.

[0101] After multiple iterations, m centroids and m clusters can be obtained. The m clusters correspond to the combination of sound data and acceleration amplitude data under m common working conditions of the air compression unit. Figure 3 , Figure 3 A schematic diagram of a clustering result provided in an embodiment of the present application; dimension 1 in the figure can be understood as X in Table 1, and dimension 2 can be understood as Y in Table 1. Figure 3 It can be seen that the data points of the target data under different working conditions can be divided into the three point clouds in the figure. If the data points collected by the sound sensor and the acceleration sensor at a certain time deviate significantly from the above point clouds, it is determined that the air compression unit may be faulty, and the target data that deviates significantly from the point cloud is called abnormal data.

[0102] In some embodiments of the present application, when determining abnormal data based on clustering results, the target data of each category and the final centroid can be determined from the clustering results, the distance value between each type of target data and the corresponding final centroid is calculated, and the discrete data is determined as abnormal data; wherein, the discrete data is the target data whose distance value is greater than a predetermined distance threshold.

[0103] The clustering results in the present application include m final centroids and m clusters after the final iteration, each cluster includes multiple target data belonging to the same category. In order to find abnormal data, the distance value between each type of target data and the corresponding final centroid can be calculated, and the distance value can be compared with a predetermined distance threshold. If the distance value is greater than the predetermined distance threshold, the target data is determined to be discrete data, and the discrete data is the abnormal data in the present application. In this way, the present application can accurately identify abnormal data from the target data.

[0104] Among them, the data points of abnormal data collected when the air compression unit is in abnormal working conditions, the sensor fails, or there is external interference will deviate from the normal point cloud. Therefore, after the abnormal data is identified through the point cloud map, a prompt message can also be generated to allow the user to manually check the cause; if it is determined that the air compression unit is faulty, the validity of the point cloud map can be recorded once; if the data deviation is caused by other factors, such as: the sensor failure is found through the sensor self-check, it will be recorded as a misjudgment and the cause will be recorded; the validity of the point cloud map can be evaluated and calibrated based on the data recorded multiple times.

[0105] From the above, it can be seen that in the present application, in order to accurately identify abnormal data from the target data, each target data can be clustered according to the K-means clustering algorithm. According to the clustering results and the predetermined distance threshold, the abnormal data can be accurately identified from the target data, so as to accurately detect the fault condition of the air compression unit.

[0106] See also Figure 4 , Figure 4 A flow chart of another fault monitoring method provided in an embodiment of the present application is provided. The fault monitoring method is applied to a vehicle-mounted audio and video system, and the fault of an air compression unit is monitored in real time through the vehicle-mounted audio and video system. The method specifically comprises the following steps:

[0107] S301, acquiring target data collected by each sensor; each sensor is installed at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor;

[0108] S302, performing filtering and noise reduction processing on the target data;

[0109] S303, identifying abnormal data in the processed target data;

[0110] S304, extracting characteristic parameters of abnormal data;

[0111] S305, determining fault information of the air compression unit using characteristic parameters;

[0112] S306. Display fault information on the vehicle-mounted display.

[0113] In this application, in order to remove environmental noise and other interference signals and improve the quality and clarity of sound data and acceleration data, the collected sound data and acceleration data can be filtered and denoised by digital signal processing technology, so as to better analyze the characteristics of sound and acceleration. Among them, filtering and denoising are technologies used to improve data quality in the field of digital signal processing. In practical applications, specific filtering schemes and denoising schemes can be selected according to actual needs to process the target data. Accordingly, when identifying abnormal data, this application identifies abnormal data from the processed target data.

[0114] Furthermore, the sound data and acceleration data obtained by the present application from the sound sensor and the acceleration sensor can be input into the vehicle-mounted audio and video system, and the fault monitoring method described in the present application is executed by the vehicle-mounted audio and video system to realize real-time monitoring of the fault of the air compression unit. Among them, the vehicle-mounted audio and video system includes an audio processing unit, and the audio processing unit can be used to realize the filtering, noise reduction, fault analysis and other processes of the target data to determine whether the air compression unit is operating normally, whether there are potential faults, etc. After the present application uses characteristic parameters to determine the fault information of the air compression unit, the fault information can be displayed through the vehicle-mounted display so that the user can understand the operating status of the air compression unit in a timely manner.

[0115] See also Figure 5 , Figure 5 A schematic diagram of a system structure provided in an embodiment of the present application, through Figure 5It can be seen that the system includes: an active suspension controller, an air compression pump, an air spring valve, an airway switching valve, an on-board audio and video system, an on-board display, an acceleration sensor, and a piezoelectric acoustic sensor; among them, the active suspension controller is used to control the operation of the air compression pump, the air spring valve, and the airway switching valve, the acceleration sensor is used to collect acceleration data, and the pressure point acoustic sensor is used to collect sound data. The acceleration data and sound data are sent to the on-board audio and video system for processing to generate fault information, and the fault information is displayed through the on-board display to interact with the user.

[0116] In the present application, the vehicle-mounted audio and video system can also be used to implement functions such as fault record storage, data management and query. Among them, the present application uses the large-capacity memory of the vehicle-mounted audio and video system to store information such as fault codes, and record the fault diagnosis results, characteristic parameters, fault occurrence time and other information of the air compression unit. The storage device has sufficient storage capacity and data security to ensure the integrity and traceability of the fault record; the present application also provides convenient data management and query functions, and users can query, analyze and count the stored fault records through specific interfaces or software, which helps users understand the operating status and fault history of the air compression unit and provide a decision-making basis for the maintenance and management of the equipment.

[0117] In summary, in order to improve the signal quality and accuracy, the present application may perform filtering and noise reduction processing on the collected target data before identifying abnormal data; the present application may analyze the target data collected by the sensor through the vehicle-mounted audio and video system, detect faults in the air compression unit, improve data processing speed, and reduce processing delays caused by server-side processing; and, the present application may display fault information directly on the vehicle-mounted display, promptly remind users of possible faults, and improve vehicle driving safety.

[0118] See also Figure 6 , Figure 6 Another fault monitoring method provided in the present application is a flow chart of a method, the method specifically comprising the following steps:

[0119] S401, acquiring target data collected by each sensor; each sensor is installed at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor;

[0120] S402, identifying abnormal data in the target data;

[0121] S403, extracting characteristic parameters of abnormal data;

[0122] S404: If the characteristic parameters do not conform to the signal characteristics under normal operating conditions, it is determined that the air compression unit is faulty and fault information is generated.

[0123] In the present application, after identifying the abnormal data in the target data, the time domain and frequency domain of the sound data and acceleration data in the abnormal data can be analyzed by Fourier transform, and characteristic parameters that can reflect the fault state of the air compression unit, such as frequency, amplitude, energy distribution, etc., can be extracted from them. If the various components of the air compression unit are in good condition, the frequency, amplitude and frequency collected by the sound sensor or acceleration sensor during normal operation are relatively stable. When the load increases or decreases, each characteristic parameter should be relatively stable and predictable, which conforms to the signal characteristics under normal operation; if there is a fault, the characteristic parameter will change greatly and does not conform to the signal characteristics under normal operation. Therefore, the present application uses the characteristic parameters of the abnormal data as the basis for fault diagnosis. If the characteristic parameter conforms to the signal characteristics under normal operation, it is determined that there is no fault. If the characteristic parameter does not conform to the signal characteristics under normal operation, it is determined that there is a fault. Among them, the signal characteristics under normal operation in the present application can be the characteristic parameter range of different components under normal operation, or the change trend of different components under different working conditions. It is not specifically limited here, as long as the characteristic parameters under the fault state can be distinguished.

[0124] In some embodiments of the present application, the process of generating fault information specifically includes: determining a target sensor for collecting abnormal data, determining an installation position of the target sensor, using the installation position to determine a fault location in the air compression unit, determining a fault type based on the fault location and the abnormal data, determining a fault severity based on the abnormal data, and generating fault information based on the fault type and fault severity.

[0125] In the present application, the target sensor for collecting abnormal data is first determined, and the installation position of the target sensor is determined. According to the installation position, the fault location in the air compression unit can be determined, and then the fault type can be determined by the fault location and characteristic parameters. Since the specific values ​​of the parameter characteristics of different fault types are different, the present application can determine the specific fault type based on the signal frequency, signal amplitude, etc. of the abnormal data. The fault types in the present application include: motor failure, piston failure, air inlet blockage failure, etc. that drive the air compressor; motor failure is caused by motor winding short circuit, open circuit, brush wear, bearing wear, etc.; piston failure refers to the piston inside the compressor being stuck during long-term use due to poor lubrication, entry of foreign matter or component wear; air inlet blockage failure refers to the air inlet of the air compressor being blocked by dust, debris, etc., resulting in poor air intake.

[0126] Furthermore, the present application can also determine the severity of the fault according to the abnormal data, and the severity of the fault can be determined according to the degree to which the abnormal data deviates from the normal range of the normal operating state. If the degree to which the abnormal data deviates from the normal range is small, the severity of the fault is determined to be not serious, and if the degree to which the abnormal data deviates from the normal range is large, the severity of the fault is determined to be serious. If the degree of the fault is serious, a maintenance prompt message can also be generated at this time to prompt the user to terminate the operation of the air compression unit, or prompt the user to repair it as soon as possible.

[0127] In some embodiments of the present application, the process of determining the fault location in the air compression unit using the installation position is as follows:

[0128] If the target sensor is a target acceleration sensor, the installation location is determined according to the installation position of the target acceleration sensor; the installation location of the target acceleration sensor is determined as the fault location in the air compression unit; if the target sensor is a target sound sensor, the installation type of the target sound sensor is determined; if the installation type is an independent installation type, the installation location is determined according to the installation location of the target sound sensor, and the installation location of the target sound sensor is determined as the fault location in the air compression unit; if the installation type is a centralized installation type, the fault location in the air compression unit is determined according to abnormal data collected by the sound sensor array; wherein the sound sensor array is composed of various sound sensors.

[0129] In the present application, an acceleration sensor can be installed on the surface of a part of the air compression unit where a fault needs to be detected. If the target sensor for collecting abnormal data is an acceleration sensor, the installation location of the acceleration sensor can be directly determined as the fault location in the air compression unit. The installation types of the sound sensor include independent installation type and centralized installation type. The independent installation type refers to installing the sound sensor at a predetermined position of each part in the air compression unit, that is, each part where a fault needs to be detected has an independent sound sensor. Under this installation type, if the target sensor for collecting abnormal data is a sound sensor, the installation location of the sound sensor can be directly determined as the fault location in the air compression unit; the centralized installation type refers to setting a sound sensor array at a predetermined position of the air compression unit. The sound sensor array is composed of multiple sound sensors. Under this installation type, the sound source position can be located according to the signal strength and phase information of the data collected by each sound sensor in the sound sensor array, and then the fault location in the air compression unit is determined.

[0130] It can be seen that the present application takes into account that the characteristic parameter values ​​of the various components of the air compression unit are different under normal operating conditions and fault conditions. Therefore, the characteristic parameters can be compared with the signal characteristics under normal operating conditions to detect the faults in the air compression unit, and the user can be promptly reminded to deal with the faults through fault information; the fault information also includes the fault type and fault severity, so that the user can decide how to deal with the fault according to the specific fault situation. In addition, in order to more accurately detect the fault location, the present application can install the acceleration sensor at a certain part of the air compression unit, so that the fault location can be determined according to the installation location of the target acceleration sensor; the present application can install each sound sensor near different parts of the air compression unit, and the fault location can be directly determined according to the installation position; the present application can also install a sound sensor array in the air compression unit, and locate the fault location through the data collected by each sensor in the array, thereby accurately locating the fault location.

[0131] It can be seen from the above method embodiments that the present application can realize the fault diagnosis and record storage of the air compression unit based on the sound and vibration characteristics of the air compression unit; the present application combines the collection and processing of target data, the fault diagnosis process, and the storage and management functions of the fault records to provide an efficient, accurate and reliable solution for the fault diagnosis and maintenance of the air compression unit. Among them, efficient means that the present application can monitor the working status of the air compression unit in real time and detect faults in time; accurate means that the present application can accurately diagnose the fault type and severity of the air compression unit through the analysis of sound and acceleration signals. Reliable means that the present application can send out early warning signals to avoid further deterioration of the fault and improve the reliability and safety of the air spring system. In addition, compared with traditional fault diagnosis methods, the present invention has lower cost and is easy to implement and promote.

[0132] See also Figure 7 , Figure 7 A schematic diagram of a fault monitoring device provided in an embodiment of the present application, the device specifically comprises:

[0133] The acquisition module 11 is used to acquire target data collected by each sensor; each sensor is installed at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor;

[0134] An identification module 12, used to identify abnormal data in the target data;

[0135] An extraction module 13, used to extract characteristic parameters of the abnormal data;

[0136] The determination module 14 is used to determine the fault information of the air compression unit by using the characteristic parameters.

[0137] As an optional embodiment, the identification module includes:

[0138] A selection unit, used to select K initial centroids from the collected target data; wherein the target data includes: sound data and acceleration data;

[0139] A division unit, used for dividing each target data into K categories corresponding to different initial centroids according to the distance value between each target data and the K initial centroids;

[0140] The first determination unit is used to determine the target centroid of each category according to the target data of each category; if the target centroid of each category is different from the initial centroid, the target centroid is used as the initial centroid, and the step of dividing each target data into K categories corresponding to different initial centroids is continued according to the distance value between each target data and the K initial centroids; if the target centroid of each category is the same as the initial centroid, a clustering result is obtained;

[0141] The second determining unit is used to determine abnormal data according to the clustering result.

[0142] As an optional embodiment, the second determining unit includes:

[0143] A data determination subunit, used to determine target data and a final centroid of each category from the clustering result;

[0144] A calculation subunit, used to calculate the distance value between each type of target data and the corresponding final centroid;

[0145] The determination subunit is used to determine the discrete data as abnormal data; wherein the discrete data is target data whose distance value is greater than a predetermined distance threshold.

[0146] As an optional embodiment, the determining module includes:

[0147] A determination unit, configured to determine that a fault exists in the air compression unit when the characteristic parameter does not meet the signal characteristic in a normal operating state;

[0148] The generating unit is used to generate fault information.

[0149] As an optional embodiment, the generating unit includes:

[0150] A sensor determination subunit, used to determine a target sensor for collecting the abnormal data;

[0151] An installation position determination subunit, used to determine the installation position of the target sensor;

[0152] a fault location determination subunit, configured to determine a fault location within the air compression unit using the installation location;

[0153] A fault type determination subunit, used to determine the fault type according to the fault location and the abnormal data;

[0154] a severity determination subunit, configured to determine the severity of the fault according to the abnormal data;

[0155] The information generating subunit is used to generate fault information according to the fault type and the fault severity.

[0156] As an optional embodiment, the fault location determination subunit is specifically used for:

[0157] If the target sensor is a target acceleration sensor, the installation location is determined according to the installation position of the target acceleration sensor; and the installation location of the target acceleration sensor is determined to be a fault location in the air compression unit.

[0158] As an optional embodiment, the fault location determination subunit is specifically used for:

[0159] If the target sensor is a target sound sensor, the installation type of the target sound sensor is determined; if the installation type is an independent installation type, the installation location is determined according to the installation position of the target sound sensor, and the installation location of the target sound sensor is determined as the fault location in the air compression unit; if the installation type is a centralized installation type, the fault location in the air compression unit is determined according to abnormal data collected by the sound sensor array; wherein the sound sensor array is composed of various sound sensors.

[0160] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0161] See also Figure 8 , Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, the electronic device specifically includes:

[0162] The processor 21, the memory 22 and the computer program stored in the memory 22 and executable on the processor 21, the processor 21 executes the steps of the fault monitoring method described in any of the above method embodiments through the computer program.

[0163] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0164] The memory 22 may include one or more computer-readable storage media, which may be non-transitory. The memory 22 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 22 is at least used to store the following computer program 221, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps in the fault monitoring method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 22 may also include an operating system 222 and data 223, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 222 may include Windows, Unix, Linux, etc.

[0165] In some embodiments, the electronic device may further include a display screen 23 , an input / output interface 24 , a communication interface 25 , a sensor 26 , a power source 27 , and a communication bus 28 .

[0166] certainly, Figure 8 The structure of the electronic device shown does not constitute a limitation on the electronic device in the embodiments of the present application. In actual applications, the electronic device may include Figure 8 More or fewer components than shown, or combinations of certain components.

[0167] In another exemplary embodiment, a computer storage medium is also provided, and when the program instructions are executed by a processor, the steps of the fault monitoring method described in any of the above method embodiments are implemented. The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0168] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0169] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0170] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A fault monitoring method, characterized in that: include: Acquire target data collected by each sensor; each sensor is installed at a predetermined position of the air compression unit, and the sensor includes a sound sensor and an acceleration sensor; Identifying abnormal data in the target data; Extracting characteristic parameters of the abnormal data; The characteristic parameter is used to determine fault information of the air compression unit.

2. The fault monitoring method according to claim 1, characterized in that: The identifying abnormal data in the target data includes: Selecting K initial centroids from the collected target data; wherein the target data includes: sound data and acceleration data; According to the distance between each target data and the K initial centroids, each target data is divided into K categories corresponding to different initial centroids; Determine the target centroid of each category based on the target data of each category; If the target centroid of each category is different from the initial centroid, the target centroid is used as the initial centroid, and the step of dividing each target data into K categories corresponding to different initial centroids is continued according to the distance value between each target data and the K initial centroids; If the target centroid of each category is the same as the initial centroid, the clustering result is obtained; Determine abnormal data based on clustering results.

3. The fault monitoring method according to claim 2, characterized in that: The determining of abnormal data according to the clustering result includes: Determine the target data and final centroid of each category from the clustering results; Calculate the distance between each type of target data and the corresponding final centroid; The discrete data is determined as abnormal data; wherein the discrete data is target data whose distance value is greater than a predetermined distance threshold.

4. The fault monitoring method according to any one of claims 1 to 3, characterized in that: The method of determining the fault information of the air compression unit by using the characteristic parameter includes: If the characteristic parameter does not conform to the signal characteristic under normal operating conditions, it is determined that the air compression unit is faulty and fault information is generated.

5. The fault monitoring method according to claim 4, characterized in that: The generating fault information comprises: Determining a target sensor for collecting the abnormal data; Determining an installation position of the target sensor; Determining a fault location in the air compression unit using the installation position; Determine the fault type according to the fault location and the abnormal data; determining the severity of the fault according to the abnormal data; Fault information is generated according to the fault type and the fault severity.

6. The fault monitoring method according to claim 5, characterized in that: Determining the fault location in the air compression unit using the installation position includes: If the target sensor is a target acceleration sensor, determining the installation location according to the installation position of the target acceleration sensor; The installation location of the target acceleration sensor is determined as a fault location in the air compression unit.

7. The fault monitoring method according to claim 5, characterized in that: Determining the fault location in the air compression unit using the installation position includes: If the target sensor is a target sound sensor, determining an installation type of the target sound sensor; If the installation type is an independent installation type, the installation location is determined according to the installation position of the target sound sensor, and the installation location of the target sound sensor is determined as the fault location in the air compression unit; If the installation type is a centralized installation type, the fault location in the air compression unit is determined based on abnormal data collected by a sound sensor array; wherein the sound sensor array is composed of various sound sensors.

8. A fault monitoring device, characterized in that: include: An acquisition module is used to acquire target data collected by each sensor; The sensors are installed at predetermined positions of the air compression unit, and the sensors include sound sensors and acceleration sensors; An identification module, used for identifying abnormal data in the target data; An extraction module, used for extracting characteristic parameters of the abnormal data; A determination module is used to determine the fault information of the air compression unit using the characteristic parameters.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the fault monitoring method described in any one of claims 1 to 7 of the present application through the computer program.

10. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute the steps of the fault monitoring method described in any one of claims 1 to 7 of the present application.

Images