Fault diagnosis method and fault diagnosis system based on multi-source data fusion

Abstract

The invention relates to a fault diagnosis method and a fault diagnosis system based on multi-source data fusion. The method comprises the following steps: acquiring an image of a rotating object in a coverage range, and determining a fixed analysis point on the image of the rotating object; continuously acquiring images of the rotating object on the rotating track of the rotating object; separating an image of a fixed analysis point from the analysis image; establishing a vibration curve of the fixed analysis point by using the image of the fixed analysis point; the vibration curves of the multiple fixed analysis points are compared, and early warning is given out when abnormity is found through comparison; and within the time range corresponding to the early warning, the early warning and detection report data of other sensors are integrated, and then a fault early warning packet is sent out. The invention provides a fault diagnosis method and a fault diagnosis system based on multi-source data fusion, which are used for determining a far-end working state of a rotating machine through a non-contact detection mode deployed at a far end so as to realize pre-detection of bad states and faults.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a fault diagnosis method and a fault diagnosis system based on multi-source data fusion. Background Art

[0002] As a clean and renewable energy source, new energy generation is of great significance to regulating climate change and environmental protection. One route of new energy generation is to use the power provided by the external environment to drive rotating machinery. These rotating machinery need to work all year round, so it is particularly important to detect them.

[0003] The deployment of remote sensors can solve this problem to a certain extent. The combination of multiple locations and multiple data can enable staff to make preliminary judgments remotely. However, external monitoring is still quite difficult, mainly due to factors such as distance affecting detection accuracy and harsh environment affecting service life.

[0004] If the sensor is deployed at the root, the coverage of the sensor is limited and the adverse condition can only be detected when it is transmitted to the root, which will cause a considerable lag in detection. Summary of the invention

[0005] The present application provides a fault diagnosis method and a fault diagnosis system based on multi-source data fusion, which determine the remote working state of a rotating machine by a non-contact detection method deployed at a remote end, so as to realize pre-detection of an undesirable state and a fault.

[0006] The above-mentioned purpose of the present application is achieved through the following technical solutions: In a first aspect, the present application provides a fault diagnosis method based on multi-source data fusion, comprising: Acquire an image of the rotating object within the coverage area and determine a fixed analysis point on the image of the rotating object; Continuously acquiring images of the rotating object on the rotating trajectory of the rotating object, which are recorded as analysis images; Separate the image of the fixed analysis point from the analysis image; Use the images of fixed analysis points to establish vibration curves of fixed analysis points; Compare the vibration curves of multiple fixed analysis points and issue an early warning when an abnormality is found in the comparison; Obtain detection report data from other sensors within the time range corresponding to the warning; Integrate the warning and detection report data of other sensors to issue a fault warning package; There are multiple fixed analysis points, which are arranged at intervals in a direction close to the rotation center.

[0007] In a possible implementation manner of the first aspect, using an image of the fixed analysis point to establish a vibration curve of the fixed analysis point includes: Generate an analysis reference line based on the rotation trajectory of the rotating object, the analysis reference line includes continuously set time points, each time point corresponds to an image of a fixed analysis point; Analyze the image clarity of a fixed analysis point at each time point to obtain a clarity value; Use the clarity values ​​to create vibration curves for fixed analysis points.

[0008] In a possible implementation manner of the first aspect, analyzing the image clarity of a fixed analysis point at each sampling point includes: Establish multiple parallel straight line segments based on fixed analysis points; Determine one or two edge points of the fixed analysis point on the straight line segment that belong to the fixed analysis point; When there is only one edge point, calculating the image clarity of the one edge point; When there are only two edge points, calculating the distance between the two edge points; The image clarity of the one edge point or the distance between the two edge points is used as the image clarity of the fixed analysis point at the sampling point.

[0009] In a possible implementation manner of the first aspect, the focal length is dynamically adjusted so that the number of edge points belonging to the fixed analysis point is one; The focal length change amount during dynamic adjustment is recorded in the image clarity of the corresponding edge point or the distance between the two edge points.

[0010] In a possible implementation manner of the first aspect, determining one or two edge points of the fixed analysis point belonging to the fixed analysis point on the straight line segment includes: Generate an analysis curve using the pixel points on the straight line segment; Generate a drop value wavelet and use the drop value wavelet to screen the analysis curve to obtain the change area; Adjust the frequency, amplitude and decay rate of the drop value wavelet and repeat the screening process until the number of changed regions is one or two; Sequentially calculate the difference between two adjacent pixels in the change area and use the difference to establish a difference sequence; Determine the extreme points of the difference sequence and use the extreme points of the difference sequence as edge points of fixed analysis points.

[0011] In a possible implementation manner of the first aspect, calculating the image clarity of the one edge point includes: Determine the middle position pixel points that constitute the edge points and the edge position pixel points that constitute the edge points; Determine the distance between the pixel point at the middle position and the pixel point at the edge position and use the distance as the image clarity; The shortest distance between the two edge points is calculated and the distance is used as the image clarity.

[0012] In a possible implementation of the first aspect, comparing vibration curves of multiple fixed analysis points and issuing an early warning when an abnormality is found in the comparison includes: The vibration curve is transferred into the frequency domain for decomposition to obtain a vibration curve group; Calculate the proportion of the frequency exceeding the set allowable frequency in the vibration curve group, and when the proportion of the frequency exceeding the set allowable frequency is greater than or equal to the first set allowable value, record the corresponding fixed analysis point as an abnormal fixed analysis point; Calculate the proportion of abnormal fixed analysis points in all fixed analysis points; When the proportion of abnormal fixed analysis points in all fixed analysis points is greater than or equal to the second set allowable value, an early warning is issued.

[0013] In a second aspect, the present application provides a fault diagnosis device based on multi-source data fusion, comprising: a position determination unit, configured to acquire an image of the rotating object within the coverage area and determine a fixed analysis point on the image of the rotating object; An image acquisition unit, used for continuously acquiring an image of the rotating object on a rotation trajectory of the rotating object, which is recorded as an analysis image; An image separation unit, used for separating an image of a fixed analysis point from an analysis image; A vibration curve establishing unit, used for establishing a vibration curve of a fixed analysis point using an image of the fixed analysis point; Vibration curve analysis and alarm unit, used to compare the vibration curves of multiple fixed analysis points and issue an early warning when an abnormality is found in the comparison; A collaborative data acquisition unit, used to acquire detection report data of other sensors within the time range corresponding to the warning; The first warning unit is used to integrate the warning and detection report data of other sensors and then issue a fault warning package; There are multiple fixed analysis points, which are arranged at intervals in a direction close to the rotation center.

[0014] In a third aspect, the present application provides a fault diagnosis system based on multi-source data fusion, the system comprising: one or more memories for storing instructions; and One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising: Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0016] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0017] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0018] The chip system may be composed of chips, or may include chips and other discrete devices.

[0019] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic block diagram of the steps of a fault diagnosis method based on multi-source data fusion provided by the present application.

[0021] Figure 2 It is a distribution diagram of fixed analysis points provided in this application.

[0022] Figure 3 It is a schematic diagram of separating an image of a fixed analysis point from an analysis image provided by the present application.

[0023] Figure 4 It is a schematic diagram for establishing an analysis reference line provided by the present application.

[0024] Figure 5 This is a schematic diagram provided by the present application in which there is an edge point.

[0025] Figure 6 This is a schematic diagram provided by the present application with two edge points.

[0026] Figure 7 This is a schematic diagram of the principle of obtaining a change area provided by the present application. DETAILED DESCRIPTION

[0027] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.

[0028] This application discloses a fault diagnosis method based on multi-source data fusion, please refer to Figure 1 In some examples, the fault diagnosis method based on multi-source data fusion disclosed in this application includes the following steps: S101, acquiring an image of a rotating object within a coverage range and determining a fixed analysis point on the image of the rotating object; S102, continuously acquiring images of the rotating object along the rotating trajectory of the rotating object, recorded as analysis images; S103, separating the image of the fixed analysis point from the analysis image; S104, using the image of the fixed analysis point to establish a vibration curve of the fixed analysis point; S105, comparing vibration curves of multiple fixed analysis points and issuing an early warning when an abnormality is found in the comparison; S106, obtaining detection report data of other sensors within the time range corresponding to the warning; S107, integrating the warning and detection report data of other sensors and issuing a fault warning package; There are multiple fixed analysis points, which are arranged at intervals in a direction close to the rotation center.

[0029] In general, the fault diagnosis method based on multi-source data fusion provided by the present application is used to detect the far end of the rotating machinery, and the detection method is non-contact. In step S101, firstly, an image of the rotating object is obtained within the coverage range and a fixed analysis point is determined on the image of the rotating object. The coverage range here refers to the coverage range of the image sensor. During the operation of the rotating machinery, the blades will pass through the coverage range of the image sensor, and the image sensor will capture an image at this time to obtain an image of the rotating object.

[0030] The obtained image is sent to the server for analysis. For the image of the rotating object, firstly, fixed analysis points are extracted on the image of the rotating object. In some possible implementations, the fixed analysis points are marked with colors or shapes for easy identification.

[0031] See also Figure 2 , the arrow indicates the direction of rotation, the solid circle indicates the fixed analysis point, and the number of the fixed analysis points is multiple and they are spaced apart in the direction close to the rotation center.

[0032] In step S102, the image of the rotating object is continuously acquired on the rotation trajectory of the rotating object, which is recorded as the analysis image. Then, in step S103, the image of the fixed analysis point is separated from the analysis image, that is, the analysis image is cropped. Figure 3As shown, the purpose is to reduce the processing volume.

[0033] Next, in step S104, the image of the fixed analysis point is used to establish a vibration curve of the fixed analysis point. At this time, multiple vibration curves of the fixed analysis points are obtained. In step S105, the vibration curves of the multiple fixed analysis points are compared and an early warning is issued when an abnormality is found in the comparison. The purpose of comparing the vibration curves of multiple fixed analysis points here is to improve the accuracy of the early warning.

[0034] It should be understood that a rotating machine has multiple rotating objects (fan blades). When a problem occurs in one of the rotating objects, it may be that only the rotating object has a problem, or it may be that multiple rotating objects have problems at the same time. In this case, a comparison method is needed to handle it.

[0035] The comparison method is to first compare the vibration curve with the standard vibration curve. If an abnormality occurs, the vibration curves are then compared with each other.

[0036] In step S106, the detection report data of other sensors will be obtained within the time range corresponding to the warning. This is because for a rotating machine, sensors are generally deployed at multiple locations. For the warning detected by this application, it is also necessary to analyze and view it in combination with the data of other sensors. Therefore, in this application, the detection report data of other sensors will be packaged synchronously when an abnormality is found. Finally, in step S107, the warning and the detection report data of other sensors will be integrated to issue a fault warning package.

[0037] In some examples, the vibration curves of fixed analysis points are constructed using images of fixed analysis points in the following ways: S201, generating an analysis reference line based on a rotation trajectory of the rotating object, the analysis reference line comprising continuously set time points, each time point corresponding to an image of a fixed analysis point; S202, analyzing the image clarity of a fixed analysis point at each time point to obtain a clarity value; S203, using the clarity value to establish a vibration curve of a fixed analysis point.

[0038] In step S201 to step S204, an analysis reference line is first generated based on the rotation trajectory of the rotating object. There are continuously set time points on the analysis reference line, and each time point corresponds to an image of a fixed analysis point. Figure 4 shown.

[0039] Then analyze the image clarity of the fixed analysis point at each time point to obtain the clarity value. Finally, use the clarity value to establish the vibration curve of the fixed analysis point. The specific method is to sort the positions of the time points as the horizontal coordinate and the clarity value at the time point as the vertical coordinate. At this time, discrete points will be obtained. Connect these discrete points in sequence to obtain the vibration curve of the fixed analysis point.

[0040] The method of analyzing the image clarity of a fixed analysis point at each sampling point is: S301, establishing a plurality of mutually parallel straight line segments based on fixed analysis points; S302, determining one or two edge points of the fixed analysis point on the straight line segment that belong to the fixed analysis point; When there is only one edge point, calculating the image clarity of the one edge point; When there are only two edge points, calculating the distance between the two edge points; S303: Use the image clarity of the one edge point or the distance between the two edge points as the image clarity of the fixed analysis point at the sampling point.

[0041] First of all, it should be noted that vibration will affect the clarity of the photo. This is because vibration will cause the image in the photo to shake and blur. Even if the focus is very accurate, it will affect the clarity of the image. This vibration may come from the camera itself or from the subject. At the moment the lens shutter is opened, if the subject itself is in motion and the shutter time is not short enough to freeze the motion, the image will be blurred.

[0042] By setting the parameters of the image sensor, some low-frequency vibrations can be shielded.

[0043] When the image shakes, ghosting will occur at the edge of the fixed analysis point. At this time, multiple parallel straight line segments are established based on the fixed analysis point, and then one or two edge points belonging to the fixed analysis point are determined on the straight line segment. The vibration amplitude of the fixed analysis point within a unit time length can be calculated. At this time, the following two situations will occur: The number of edge points is one. The image clarity of an edge point is calculated by calculating the ratio of the actual area (length) of the edge point to the theoretical area (length), such as Figure 5 As shown, the right side represents the actual area (length) of the edge point, and the left side represents the theoretical area (length) of the edge point; See also Figure 6 , the number of edge points is two, and the distance between two edge points is calculated.

[0044] The edge points are located on the edge, that is, the edge points need to be selected after the edge is determined. Generally, the maximum value or the average value is used for calculation.

[0045] Finally, the image clarity of the one edge point or the distance between the two edge points is used as the image clarity of the fixed analysis point at the sampling point, so that the image clarity of the fixed analysis point can be converted into a numerical description.

[0046] In some possible implementations, the method further includes dynamically adjusting the focal length so that the edge point belonging to the fixed analysis point is one, and the focal length change during the dynamic adjustment is recorded in the image clarity of the corresponding edge point or the distance between the two edge points.

[0047] At this time, the ratio of the actual area (length) of the edge point to the theoretical area (length) needs to be a constant. If this cannot be achieved, the image clarity of the edge point or the distance between two edge points is calculated for processing.

[0048] The method of dynamically adjusting the focal length here is mainly applied to the case where the rotation speed of the rotating machinery is low. When the rotation speed of the rotating machinery is high, the method of dynamically adjusting the focal length is not applicable.

[0049] In some examples, determining one or two edge points of a fixed analysis point on a straight line segment that belong to the fixed analysis point includes: S401, generating an analysis curve using pixel points on the straight line segment; S402, generating a drop value wavelet and using the drop value wavelet to screen the analysis curve to obtain a change area; S403, adjusting the frequency, amplitude and attenuation rate of the drop value wavelet and repeating the screening process until the number of changed regions is one or two; S404, sequentially calculating the difference between two adjacent pixel points in the change area and using the difference to establish a difference sequence; S405, determining the extreme value points of the difference sequence and using the extreme value points of the difference sequence as edge points of fixed analysis points.

[0050] The above method is to use the drop value wavelet (wavelet) to decompose the analysis curve. At this time, multiple change areas may be obtained. Figure 7 As shown, these change areas are all potential edge points. When the number of potential edge points is multiple, the frequency, amplitude and attenuation rate of the drop value wavelet are adjusted and the screening process is repeated until the number of change areas is one or two.

[0051] So far, one or two change regions are obtained, but the length of the change region is relatively large, and it is necessary to further determine the edge points of the fixed analysis points in the change region, which is specifically performed in step S404 and step S404: First, the difference between two adjacent pixel points in the change area is calculated sequentially and a difference sequence is established using the difference. Then, the extreme points of the difference sequence are determined and used as edge points of fixed analysis points.

[0052] Here, the extreme point of the difference sequence refers to the point corresponding to the maximum difference. If the extreme point of the difference sequence cannot be determined, the difference sequence is used to generate a secondary difference sequence, and then the maximum change point in the secondary difference sequence is determined. The maximum change point indicates that the color change here is the largest, and the corresponding position is used as the edge point of the fixed analysis point.

[0053] In some examples, the image clarity of the edge point is calculated as follows: S501, determining the middle position pixel points constituting the edge points and the edge position pixel points constituting the edge points; S502, determining the distance between the pixel point at the middle position and the pixel point at the edge position and using the distance as the image clarity; S503, calculating the shortest distance between the two edge points and using the distance as the image clarity.

[0054] Specifically, the color of the pixel at the middle position is dark, and the color of the pixel at the edge position is light. The determination method is recorded in the above content and will not be repeated here.

[0055] Determine the distance between the pixel point at the middle position and the pixel point at the edge position and use the distance as the image clarity. In this method, the number of corresponding edge points is one; when the number of edge points is two, calculate the shortest distance between the two edge points and use the distance as the image clarity.

[0056] In some examples, the specific method of comparing vibration curves of multiple fixed analysis points and issuing an alarm when an abnormality is found in the comparison is: The vibration curve is transferred into the frequency domain for decomposition to obtain a vibration curve group; Calculate the proportion of the frequency exceeding the set allowable frequency in the vibration curve group, and when the proportion of the frequency exceeding the set allowable frequency is greater than or equal to the first set allowable value, record the corresponding fixed analysis point as an abnormal fixed analysis point; Calculate the proportion of abnormal fixed analysis points in all fixed analysis points; When the proportion of abnormal fixed analysis points in all fixed analysis points is greater than or equal to the second set allowable value, an early warning is issued.

[0057] The above method is to transfer the vibration curve into the frequency domain for decomposition, for example, using fast Fourier transform, and after obtaining the vibration curve group, calculate the proportion of the part exceeding the set allowable frequency in the vibration curve group, and then when the proportion of the part exceeding the set allowable frequency is greater than or equal to the first set allowable value, the corresponding fixed analysis point is recorded as an abnormal fixed analysis point.

[0058] When all fixed analysis points are analyzed, the proportion of abnormal fixed analysis points in all fixed analysis points is calculated, and then an early warning is issued when the proportion of abnormal fixed analysis points in all fixed analysis points is greater than or equal to a second set allowable value.

[0059] The present application also provides a fault diagnosis device based on multi-source data fusion, comprising: a position determination unit, configured to acquire an image of the rotating object within the coverage area and determine a fixed analysis point on the image of the rotating object; An image acquisition unit, used for continuously acquiring an image of the rotating object on a rotation trajectory of the rotating object, which is recorded as an analysis image; An image separation unit, used for separating an image of a fixed analysis point from an analysis image; A vibration curve establishing unit, used for establishing a vibration curve of a fixed analysis point using an image of the fixed analysis point; Vibration curve analysis and alarm unit, used to compare the vibration curves of multiple fixed analysis points and issue an early warning when an abnormality is found in the comparison; A collaborative data acquisition unit, used to acquire detection report data of other sensors within the time range corresponding to the warning; The first warning unit is used to integrate the warning and detection report data of other sensors and then issue a fault warning package; There are multiple fixed analysis points, which are arranged at intervals in a direction close to the rotation center.

[0060] Furthermore, it also includes: A first generating unit is used to generate an analysis reference line based on the rotation trajectory of the rotating object, the analysis reference line includes continuously set time points, each time point corresponds to an image of a fixed analysis point; An analysis unit, used for analyzing the image clarity of a fixed analysis point at each time point to obtain a clarity value; Use the clarity values ​​to create vibration curves for fixed analysis points.

[0061] Furthermore, it also includes: A second generating unit, used for establishing a plurality of mutually parallel straight line segments based on the fixed analysis points; An edge point determination unit, used for determining one or two edge points belonging to the fixed analysis point on the straight line segment; When there is only one edge point, calculating the image clarity of the one edge point; When there are only two edge points, calculating the distance between the two edge points; The clarity calculation unit is used to use the image clarity of the one edge point or the distance between the two edge points as the image clarity of the fixed analysis point at the sampling point.

[0062] Further, the focal length is dynamically adjusted so that the edge point belonging to the fixed analysis point is one; The focal length change amount during dynamic adjustment is recorded in the image clarity of the corresponding edge point or the distance between the two edge points.

[0063] Furthermore, it also includes: A third generating unit, used to generate an analysis curve using pixel points on the straight line segment; A screening unit, used for generating a drop value wavelet and using the drop value wavelet to screen the analysis curve to obtain a change area; A wavelet adjustment unit is used to adjust the frequency, amplitude and decay rate of the drop value wavelet and repeat the screening process until the number of changed regions is one or two; A first calculation unit, used for sequentially calculating the difference between two adjacent pixel points in the change area and using the difference to establish a difference sequence; The first edge point determination unit is used to determine the extreme value points of the difference sequence and use the extreme value points of the difference sequence as edge points of fixed analysis points.

[0064] Furthermore, it also includes: A second edge point determination unit is used to determine the middle position pixel points constituting the edge points and the edge position pixel points constituting the edge points; A distance determination unit, used to determine the distance between the pixel point at the middle position and the pixel point at the edge position and use the distance as the image clarity; The second calculation unit is used to calculate the shortest distance between the two edge points and use the distance as the image clarity.

[0065] Furthermore, it also includes: A decomposition unit is used to transfer the vibration curve into the frequency domain for decomposition to obtain a vibration curve group; A second calculation unit is used to calculate the proportion of the part of the vibration curve group that exceeds the set allowable frequency, and when the proportion of the part of the vibration curve group that exceeds the set allowable frequency is greater than or equal to a first set allowable value, the corresponding fixed analysis point is recorded as an abnormal fixed analysis point; A third calculation unit is used to calculate the proportion of abnormal fixed analysis points in all fixed analysis points; The second warning unit is used to issue a warning when the proportion of abnormal fixed analysis points in all fixed analysis points is greater than or equal to a second set allowable value.

[0066] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0067] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0068] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0069] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0070] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0071] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0073] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.

[0074] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0075] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as 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.

[0076] The present application also provides a fault diagnosis system based on multi-source data fusion, the system comprising: one or more memories for storing instructions; and One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0077] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0078] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0079] The chip system may be composed of chips, or may include chips and other discrete devices.

[0080] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0081] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0082] Optionally, the computer instructions are stored in a memory.

[0083] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0084] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0085] The non-volatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0086] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0087] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A fault diagnosis method based on multi-source data fusion, characterized in that: include: Acquire an image of the rotating object within the coverage area and determine a fixed analysis point on the image of the rotating object; Continuously acquiring images of the rotating object on the rotating trajectory of the rotating object, which are recorded as analysis images; Separate the image of the fixed analysis point from the analysis image; Use the images of fixed analysis points to establish vibration curves of fixed analysis points; Compare the vibration curves of multiple fixed analysis points and issue an early warning when an abnormality is found in the comparison; Obtain detection report data from other sensors within the time range corresponding to the warning; Integrate the warning and detection report data of other sensors to issue a fault warning package; There are multiple fixed analysis points, which are arranged at intervals in a direction close to the rotation center.

2. The fault diagnosis method based on multi-source data fusion according to claim 1 is characterized in that: Using the image of a fixed analysis point to create a vibration curve for a fixed analysis point includes: Generate an analysis reference line based on the rotation trajectory of the rotating object, the analysis reference line includes continuously set time points, each time point corresponds to an image of a fixed analysis point; Analyze the image clarity of a fixed analysis point at each time point to obtain a clarity value; Use the clarity values ​​to create vibration curves for fixed analysis points.

3. The fault diagnosis method based on multi-source data fusion according to claim 2 is characterized in that: Analyzing the image clarity of fixed analysis points at each sampling point includes: Establish multiple parallel straight line segments based on fixed analysis points; Determine one or two edge points of the fixed analysis point on the straight line segment that belong to the fixed analysis point; When there is only one edge point, calculating the image clarity of the one edge point; When there are only two edge points, calculating the distance between the two edge points; The image clarity of the one edge point or the distance between the two edge points is used as the image clarity of the fixed analysis point at the sampling point.

4. The fault diagnosis method based on multi-source data fusion according to claim 3 is characterized in that: Dynamically adjust the focal length so that the edge points belonging to the fixed analysis point are one; The focal length change amount during dynamic adjustment is recorded in the image clarity of the corresponding edge point or the distance between the two edge points.

5. The fault diagnosis method based on multi-source data fusion according to claim 3 is characterized in that: One or two edge points belonging to a fixed analysis point are determined on a straight line segment and include: Generate an analysis curve using the pixel points on the straight line segment; Generate a drop value wavelet and use the drop value wavelet to screen the analysis curve to obtain the change area; Adjust the frequency, amplitude and decay rate of the drop value wavelet and repeat the screening process until the number of changed regions is one or two; Sequentially calculate the difference between two adjacent pixels in the change area and use the difference to establish a difference sequence; Determine the extreme points of the difference sequence and use the extreme points of the difference sequence as edge points of fixed analysis points.

6. The fault diagnosis method based on multi-source data fusion according to claim 5 is characterized in that: Calculating the image clarity of the one edge point includes: Determine the middle position pixel points that constitute the edge points and the edge position pixel points that constitute the edge points; Determine the distance between the pixel point at the middle position and the pixel point at the edge position and use the distance as the image clarity; The shortest distance between the two edge points is calculated and the distance is used as the image clarity.

7. The fault diagnosis method based on multi-source data fusion according to claim 1 is characterized in that: Compare the vibration curves of multiple fixed analysis points and issue an early warning when an abnormality is found in the comparison, including: The vibration curve is transferred into the frequency domain for decomposition to obtain a vibration curve group; Calculate the proportion of the frequency exceeding the set allowable frequency in the vibration curve group, and when the proportion of the frequency exceeding the set allowable frequency is greater than or equal to the first set allowable value, record the corresponding fixed analysis point as an abnormal fixed analysis point; Calculate the proportion of abnormal fixed analysis points in all fixed analysis points; When the proportion of abnormal fixed analysis points in all fixed analysis points is greater than or equal to the second set allowable value, an early warning is issued.

8. A fault diagnosis device based on multi-source data fusion, characterized in that: include: a position determination unit, configured to acquire an image of the rotating object within the coverage area and determine a fixed analysis point on the image of the rotating object; An image acquisition unit, used for continuously acquiring an image of the rotating object on a rotation trajectory of the rotating object, which is recorded as an analysis image; An image separation unit, used for separating an image of a fixed analysis point from an analysis image; A vibration curve establishing unit, used for establishing a vibration curve of a fixed analysis point using an image of the fixed analysis point; Vibration curve analysis and alarm unit, used to compare the vibration curves of multiple fixed analysis points and issue an early warning when an abnormality is found in the comparison; A collaborative data acquisition unit, used to acquire detection report data of other sensors within the time range corresponding to the warning; The first warning unit is used to integrate the warning and detection report data of other sensors and then issue a fault warning package; There are multiple fixed analysis points, which are arranged at intervals in a direction close to the rotation center.

9. A fault diagnosis system based on multi-source data fusion, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images