Transportation monitoring method of power equipment and electronic device

Abstract

The application discloses a kind of transport monitoring method of electric power equipment and electronic equipment.The method comprises the following steps: obtaining the event data of electric power equipment in current transport period;Determine the event distribution characteristics of electric power equipment in current transport period based on event data;Determine the equipment pixel area of electric power equipment in current transport period based on event distribution characteristics;In equipment pixel area, determine the target abnormal area of electric power equipment in current transport period;Determine the transport monitoring result of electric power equipment in current transport period based on target abnormal area and equipment pixel area.The present application solves the technical problems of inaccurate positioning of transport abnormal area and inaccurate transport monitoring result in long-distance transport of high-value electric power equipment monitoring in related technologies.

Description

Technical Field

[0001] This invention relates to the fields of new energy and energy-saving technology, and more specifically, to a method and electronic device for monitoring the transportation of power equipment. Background Technology

[0002] During long-distance transportation of high-value electrical equipment (such as transformers and switchgear), continuous vibration can easily lead to loosening of fasteners, deformation of cushioning materials, or structural damage, seriously threatening equipment safety. Related technologies typically employ accelerometers for point monitoring or rely on pre-defined weak point models for targeted detection. However, these methods have significant drawbacks:

[0003] Significant structural differences between different equipment and manufacturing tolerances within the same model lead to uncertain weak point locations and an inability to pre-define unified detection targets. Monitoring suffers from blind spots; sensors only cover the installation point, failing to comprehensively reflect the complex and ever-changing surface conditions of the equipment, and lead wires exhibit low reliability under vibration. Engine vibration and road bumps in the vehicle environment create strong background noise, easily masking the subtle vibration characteristics caused by localized loosening. Furthermore, it is difficult to effectively separate and identify abnormally moving parts from the overall vehicle sway. In summary, related technologies for monitoring high-value electrical equipment during long-distance transportation suffer from problems such as the inability to predict loosening locations, monitoring blind spots, susceptibility to noise interference, and difficulty in distinguishing between overall sway and localized anomalies, resulting in inaccurate location of abnormal areas and inaccurate monitoring results.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, and non-volatile storage medium for monitoring the transportation of power equipment, in order to at least solve the technical problems of inaccurate location of abnormal transportation areas and inaccurate transportation monitoring results in the monitoring of high-value power equipment transported over long distances.

[0006] According to one aspect of the present invention, a method for monitoring the transportation of power equipment is provided, comprising: acquiring event data of the power equipment during the current transportation period, wherein the event data includes at least: pixels of brightness change events occurring on the surface of the power equipment, and the position coordinates of the pixels; determining event distribution characteristics of the power equipment during the current transportation period based on the event data, wherein the event distribution characteristics are used to indicate the density of brightness change events occurring on the surface of the power equipment; determining device pixel regions of the power equipment during the current transportation period based on the event distribution characteristics, wherein the device pixel regions are used to indicate the pixel range of the power equipment surface after removing background interference; determining target abnormal regions of the power equipment during the current transportation period within the device pixel regions; and determining the transportation monitoring result of the power equipment during the current transportation period based on the target abnormal regions and the device pixel regions.

[0007] According to another aspect of the present invention, a transportation monitoring device for power equipment is provided, comprising: an acquisition module, configured to acquire event data of the power equipment during the current transportation period, wherein the event data includes at least: pixels of brightness change events occurring on the surface of the power equipment, and the position coordinates of the pixels; a statistics module, configured to determine event distribution characteristics of the power equipment during the current transportation period based on the event data, wherein the event distribution characteristics are used to indicate the density of brightness change events occurring on the surface of the power equipment; a segmentation module, configured to determine the device pixel region of the power equipment during the current transportation period based on the event distribution characteristics, wherein the device pixel region is used to indicate the pixel range of the power equipment surface after removing background interference; an identification module, configured to determine a target abnormal region of the power equipment during the current transportation period within the device pixel region; and a determination module, configured to determine the transportation monitoring result of the power equipment during the current transportation period based on the target abnormal region and the device pixel region.

[0008] According to another aspect of the present invention, a non-volatile storage medium is provided, which stores a plurality of instructions adapted for a power equipment transportation monitoring method, any one of which is loaded by a processor.

[0009] According to another aspect of the present invention, an electronic device is provided, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any one of the methods for monitoring the operation of power equipment.

[0010] According to another aspect of the embodiments of this application, a computer program product is provided, which, when executed on a data processing device, is a program adapted to perform the steps of a method for monitoring the transportation of power equipment.

[0011] In this embodiment of the invention, a method for monitoring the transportation of power equipment is employed. This method acquires event data of the power equipment during the current transportation period. The event data includes at least the pixels of the power equipment surface experiencing brightness changes, and the coordinates of these pixels. Based on the event data, the method determines the event distribution characteristics of the power equipment during the current transportation period, where the event distribution characteristics indicate the density of brightness change events on the power equipment surface. Based on the event distribution characteristics, the method determines the device pixel region of the power equipment during the current transportation period, where the device pixel region indicates the pixel range on the power equipment surface after removing background interference. Within the device pixel region, the method identifies the target abnormal region of the power equipment during the current transportation period. Based on the target abnormal region and the device pixel region, the method determines the transportation monitoring result of the power equipment during the current transportation period. This achieves the goal of constructing event distribution characteristics from the event data of the power equipment during the current transportation period, further removing background interference to determine the device pixel region, and thus accurately identifying the target abnormal region within the device pixel region. This precisely determines the transportation monitoring result of the power equipment, improving the accuracy of abnormal region location and the accuracy of transportation monitoring results. This solves the technical problems of inaccurate abnormal region location and inaccurate transportation monitoring results in the monitoring of high-value power equipment during long-distance transportation. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0013] Figure 1 This is a flowchart of a method for monitoring the transportation of power equipment according to an embodiment of the present invention;

[0014] Figure 2 This is a flowchart of an optional method for determining an abnormal target region according to an embodiment of the present invention;

[0015] Figure 3 This is a flowchart of an optional method for monitoring the transportation of power equipment according to an embodiment of the present invention;

[0016] Figure 4 This is a schematic diagram of a power equipment transportation monitoring device according to an embodiment of the present invention;

[0017] Figure 5 This is a schematic diagram of a transportation monitoring electronic device for power equipment according to an embodiment of this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, environmental visual information, user location information, user preference information, and user behavior information, etc.) and data (including but not limited to data used for display and analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding operation entry points for them to choose to agree to or refuse automated decision results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0021] According to an embodiment of the present invention, a method embodiment for monitoring the transportation of power equipment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0022] Figure 1 This is a flowchart of a transportation monitoring method for power equipment according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0023] Step S101: Obtain event data of the power equipment during the current transportation period. The event data includes at least the pixels of the power equipment surface brightness change event and the position coordinates of the pixels.

[0024] Optionally, the current transportation period refers to a specific time segment of an ongoing transportation process. For example, the current transportation period could be the first stable section of road after the transportation task has started, such as a highway or a smooth road surface. This current transportation period is used to define the temporal attributes of the data, ensuring that event data is collected when the power equipment is in a stable state. The power equipment is the object being monitored, including but not limited to high-value equipment with surface structural features (such as exposed bolts, panel seams, and cable interfaces), such as transformers, switchgear, and enclosed modules. During transportation, these devices experience continuous vibration, leading to attenuation, loosening, or deformation of fastener preload. Event data consists of frame image data output by a Dynamic Vision Sensor (DVS). This event data is sparse, asynchronous, and event-based visual signals, recording only pixel information of brightness change events on the surface of the power equipment, unlike the dense image frames in related technologies. A brightness change event is an event triggered by a change in the intensity of reflected light on the object's surface, and is the basic building block of event data. In the physical sense of transportation monitoring, a brightness change event corresponds to the movement, deformation, or relative position change of the object's surface. A pixel is the smallest spatial unit of a photosensitive unit in an image sensor and also the carrier of event data; position coordinates are the spatial position index of a pixel on the sensor's two-dimensional imaging plane, used to provide a spatial reference system for the occurrence of events, facilitating subsequent spatial distribution analysis.

[0025] Step S104: Based on the event data, determine the event distribution characteristics of the power equipment during the current transportation period, wherein the event distribution characteristics are used to indicate the density of events causing brightness changes on the surface of the power equipment.

[0026] Optionally, event distribution characteristics refer to macroscopic attributes obtained after spatial statistics of event data. They are used to summarize the spatial clustering trend of events and indicate the density of brightness change events on the surface of power equipment (i.e., the frequency of brightness change events per unit space or unit area). These event distribution characteristics are used to distinguish the surface of power equipment from the background and serve as the basis for subsequent segmentation.

[0027] In one optional embodiment, determining the event distribution characteristics of the power equipment during the current transportation period based on event data includes: dividing the surface of the power equipment into multiple regions; determining the event occurrence rate corresponding to each of the multiple regions based on event data, wherein the event occurrence rate is used to quantify the total number of brightness change events occurring in the corresponding region during the current transportation period; and obtaining the event distribution characteristics based on the event occurrence rates corresponding to each of the multiple regions.

[0028] Optionally, dividing the surface of the power equipment into multiple regions means dividing the surface into several sub-space sets. These multiple regions are the basic statistical units for calculating the event occurrence rate. By counting the total number of brightness change events occurring in each region during the current transportation period, the event occurrence rate corresponding to each region is obtained. The event occurrence rate is equivalent to the total number of events and is an absolute value rather than a relative ratio. The event distribution characteristics are used to indicate the density of brightness change events on the surface of the power equipment, and to indicate the spatial distribution of the density of brightness change events on the surface of the power equipment.

[0029] Step S106: Based on the event distribution characteristics, determine the device pixel region of the power equipment during the current transportation period, wherein the device pixel region is used to indicate the pixel range of the power equipment surface after removing background interference.

[0030] Optionally, the device pixel region refers to the set of pixels identified as belonging to the electrical equipment itself after filtering. It is the effective monitoring area separated from the entire field of view, used to exclude background noise from the carriage walls, supports, etc. Background interference refers to non-electrical equipment parts in the scene, such as carriage walls, fixed supports, and other cargo. These parts remain relatively stationary during transportation or have different motion patterns than the equipment; the events they generate are considered noise.

[0031] In an optional embodiment, when the surface of the power equipment includes multiple regions, determining the device pixel region of the power equipment during the current transportation period based on event distribution characteristics includes: determining a grayscale histogram corresponding to the event distribution characteristics, wherein the grayscale histogram is used to indicate the distribution characteristics of the event occurrence rate corresponding to each of the multiple regions included in the event distribution characteristics; determining a target segmentation threshold based on the grayscale histogram, wherein the target segmentation threshold is used to divide the device pixel region and the background interference region; and determining the device pixel region based on the target segmentation threshold.

[0032] Optionally, in determining the device pixel region, firstly, given that the event distribution features are in matrix form, a gray-level histogram of the event rate spatial distribution matrix is ​​calculated. This gray-level histogram reflects the frequency distribution of different event rate values ​​in the field of view, thereby quantifying the difference in event density between the device surface and the background of the carriage. Next, a statistical method can be used to automatically calculate the optimal segmentation threshold (i.e., the target segmentation threshold) from the gray-level histogram. This target segmentation threshold maximizes the inter-class variance, thus accurately defining the boundary between the device pixel region and the background region without manual intervention. This embodiment, through statistical segmentation based on event density, can effectively suppress low-frequency or random noise interference from non-target areas such as carriage walls and supports, ensuring that subsequent motion vector analysis is performed only within the actual surface area of ​​the power equipment. This significantly improves the accuracy and robustness of device pixel region extraction, laying a reliable spatial foundation for subsequent accurate location of abnormally loose parts.

[0033] In one optional embodiment, determining the device pixel region based on the target segmentation threshold includes: identifying the region with an event occurrence rate greater than the target segmentation threshold from among the multiple regions as the initial region of the power equipment during the current transportation period; performing morphological processing on the initial region to obtain the device pixel region, wherein the morphological processing includes at least: dilation processing and erosion processing.

[0034] Optionally, grids with an event occurrence rate greater than the target segmentation threshold are marked as high-activity regions. These high-activity regions correspond to the initial regions on the surface of the power equipment. However, the initial segmentation results may contain small holes or boundary breaks due to weak local motion or noise occlusion. Therefore, a morphological closing operation is performed on the initial regions marked as high-activity areas to obtain the device pixel regions. This involves first performing dilation to expand the region boundaries, fill in the small holes, and connect adjacent broken regions, followed by erosion to shrink the over-expanded boundaries, restore the original size of the region, and maintain its connectivity. Morphological processing refers to a non-linear operation in image processing used to change the geometry of foreground objects in a binary image. In this embodiment, the closing operation can correct detection discontinuities caused by sensor noise or local features on the device surface (such as gloss reflection and shadows), ensuring the topological integrity of the device region and avoiding misjudging background noise as abnormal regions or incorrectly dividing the internal structure of the device into multiple independent parts. This optimized device pixel region can provide a unified and accurate analysis boundary for subsequent calculation of the full-surface motion vector field, enabling anomaly detection based on motion direction deviation to be strictly limited to the power equipment body, thereby significantly improving the reliability and anti-interference capability of anomaly localization.

[0035] Step S108: In the device pixel area, determine the target abnormal area of ​​the power equipment during the current transportation period.

[0036] Optionally, the target anomaly area refers to a sub-region within the device's pixel area that is identified as having abnormal motion characteristics (such as loosening or shaking), and is an object of interest further separated from the normal main body of the device. By identifying the target anomaly area, full-surface, autonomous detection monitoring of loose parts on the surface of power equipment can be achieved, and overall vibration can be effectively distinguished from local anomalies.

[0037] In one alternative embodiment, Figure 2 This is a flowchart of an optional target anomaly region determination method according to an embodiment of the present invention, such as... Figure 2 As shown, when the device pixel area includes multiple pixels, the target abnormal area of ​​the power equipment during the current transportation period is determined within the device pixel area, including:

[0038] Step S202: Among the multiple pixels, the pixels whose movement speed is greater than a preset speed threshold in the current transportation period are identified as target pixels.

[0039] Step S204: When there are multiple target pixels, the movement direction with a frequency greater than a preset occurrence frequency among the movement directions corresponding to each of the multiple target pixels is determined as the target movement direction of the device pixel area during the current transportation period.

[0040] Step S206: Based on the movement directions of multiple pixels during the current transportation period and the target movement direction, determine the target abnormal area.

[0041] Optionally, this embodiment uses motion vector field analysis to separate abnormal local motions from the global motion of the power equipment surface to determine the target abnormal region, thereby achieving accurate capture and effective separation of local loosening features under strong background noise interference. The method for determining the target abnormal region in this embodiment can automatically identify any abnormal parts that cause independent local motion, such as loose bolts, cracked panel joints, and deformed cable interfaces, based solely on the consistency difference in the direction of motion, without prior knowledge of the specific structural weaknesses of the power equipment. This solves the problem in related technologies where single-point sensors cannot cover the entire surface and are difficult to distinguish between overall vibration and local anomalies, significantly improving the accuracy and robustness of anomaly localization.

[0042] In one optional embodiment, determining the target abnormal region based on the respective movement directions of multiple pixels during the current transportation period and the target movement direction includes: determining multiple directional deviation angles based on the respective movement directions of multiple pixels during the current transportation period and the target movement direction, wherein the multiple directional deviation angles correspond one-to-one with the multiple pixels, and the multiple directional deviation angles are used to indicate the degree to which the movement direction of the corresponding pixel deviates from the target movement direction; determining the pixels corresponding to the directional deviation angles that are greater than a preset deviation angle threshold as abnormal pixels; and determining the target abnormal region based on the abnormal pixels.

[0043] Optionally, the angle difference between the motion vector direction of each pixel within the device's pixel region and the target motion direction (i.e., the main direction representing the overall synchronous motion of the vehicle body) determined statistically is calculated to generate a direction deviation angle corresponding to each pixel. This deviation angle quantifies the degree to which local motion deviates from the overall rigid body motion law, and any direction deviation angle can be obtained in the following way. ,in, This indicates the direction of movement of any pixel during the current transportation period. This indicates the direction of target motion. Abnormal pixels represent parts with relatively independent motion characteristics. Since electrical equipment is primarily affected by vehicle vibration during transportation, its intact structural parts should move synchronously with the vehicle body, with a consistent direction of motion. However, loose parts (such as bolts and seams) will exhibit independent motion relative to the vehicle body, causing a significant deviation between their motion direction and the target motion direction. Through angular deviation analysis, without relying on accelerometers or complex transfer functions, and unaffected by broadband noise such as low-frequency engine vibration or high-frequency road bumps, it can directly distinguish between overall rigid body motion and local flexible deformation based on kinematic characteristics. This enables autonomous anomaly localization without pre-set detection targets and without blind spots across the entire surface.

[0044] In one optional embodiment, when there are multiple abnormal pixels, determining the target abnormal region based on the abnormal pixels includes: performing clustering processing on the multiple abnormal pixels to obtain multiple initial abnormal regions; and determining the initial abnormal region whose total number of pixels is greater than a preset pixel number threshold as the target abnormal region.

[0045] Optionally, clustering is used to aggregate discrete noise points or real anomalies into meaningful regions. Initial anomaly regions refer to the set of regions formed after preliminary clustering but before area filtering. The DBSCAN equal-density clustering algorithm can be used to group spatially adjacent anomaly pixels, separating scattered noise points from real physical anomaly regions, forming several initial anomaly regions containing adjacent anomaly pixels. Further, the total number of pixels contained in each initial anomaly region is calculated and compared with a preset pixel count threshold. Only regions with an initial anomaly region area greater than the preset pixel count threshold are retained as the final target anomaly regions, thereby eliminating isolated erroneous detection points caused by sensor noise or minor disturbances. The method in this embodiment does not require a preset detection target and can automatically detect parts of the power equipment surface with independent movement characteristics. Whether the power equipment is a transformer (with bolts), a switchgear (with panel seams), or a closed module (smooth casing with cable interfaces), clustering and analysis can accurately identify loose parts such as bolts, clips, panel seams, seal edges, and cable interfaces, and output their precise spatial locations.

[0046] Step S110: Based on the target anomaly area and the device pixel area, determine the transportation monitoring results of the power equipment during the current transportation period.

[0047] Optionally, the transportation monitoring results are the final assessment conclusions of the safety status of power equipment transportation, which are used to guide operation and maintenance personnel in conducting inspections and maintenance. This allows operation and maintenance personnel to take corresponding countermeasures (such as continued monitoring, shutdown inspection, or emergency reinforcement) according to the degree of risk, thereby optimizing the allocation efficiency of operation and maintenance resources while ensuring the safety of equipment transportation.

[0048] In one optional embodiment, the transportation monitoring result of the power equipment during the current transportation period is determined based on the target abnormal area and the device pixel area, including: determining the abnormal area corresponding to the target abnormal area and the total area corresponding to the device pixel area; determining the abnormal proportion of the power equipment during the current transportation period based on the abnormal area and the total area; and determining the transportation monitoring result based on the abnormal proportion.

[0049] Optionally, the number of pixels in the target anomaly area and the device pixel area can be counted separately and converted into corresponding anomaly area and total device area. Then, by calculating the ratio between the anomaly area and the total area, a key indicator, the anomaly percentage, is derived. This percentage reflects the proportion of the area on the power equipment surface where abnormal movement occurs to the total surface area of ​​the equipment. Finally, based on this anomaly percentage, the transportation monitoring results of the power equipment during the current transportation period are determined, enabling refined hierarchical management and dimensionless assessment of the power equipment's transportation status.

[0050] In one optional embodiment, determining the transportation monitoring result based on the anomaly ratio includes: if the anomaly ratio is less than a first preset ratio threshold, determining that the transportation monitoring result is that the power equipment is at a level 1 anomaly during the current transportation period; or if the anomaly ratio is greater than or equal to the first preset ratio threshold and less than a second preset ratio threshold, determining that the transportation monitoring result is that the power equipment is at a level 2 anomaly during the current transportation period; or if the anomaly ratio is greater than or equal to the second preset ratio threshold, determining that the transportation monitoring result is that the power equipment is at a level 3 anomaly during the current transportation period.

[0051] Optionally, a tiered judgment range can be constructed by setting multiple preset percentage thresholds (i.e., a first preset percentage threshold and a second preset percentage threshold). The first-level anomaly level corresponds to a normal state; the second-level anomaly level corresponds to a warning or medium-risk state, indicating that the power equipment has localized loosening but has not yet posed a serious threat; and the third-level anomaly level corresponds to a dangerous or high-risk state, indicating that the abnormal area of ​​the power equipment is large or the loosening is severe. This embodiment, by introducing multiple threshold levels instead of a single critical point, can distinguish between minor, moderate, and severe anomalies, avoiding false alarms or missed alarms caused by simplistic black-and-white judgments. This tiered mechanism allows maintenance personnel to adopt differentiated response strategies based on the risk level. For example, a first-level anomaly requires continued monitoring of the power equipment, a second-level anomaly requires increased attention or preparation for inspection, and a third-level anomaly requires immediate shutdown for investigation or emergency reinforcement measures. This tiered approach not only optimizes the allocation of human resources but also effectively prevents maintenance waste due to excessive warnings or equipment damage due to insufficient warnings, significantly improving the safety of long-distance power equipment transportation.

[0052] It should be noted that the Level 1, Level 2, and Level 3 anomaly levels used in this embodiment are merely level identifiers used to distinguish the severity of the safety status of power equipment transportation. Their specific numerical correspondences and business meanings can be adjusted according to actual application scenarios or operation and maintenance standards, and do not constitute a limitation of this invention. In other optional embodiments, other naming methods (such as normal level, warning level, and severe level) can also be used. Regardless of the naming or numbering rules used, the core logic is to divide the transportation status into at least three different risk levels based on the proportion of anomalies and generate corresponding transportation monitoring results. Those skilled in the art can flexibly set threshold ranges and level designations according to actual needs, all of which fall within the protection scope of this invention.

[0053] Through the above steps S102 to S110, the event distribution characteristics can be constructed by using the event data of the power equipment during the current transportation period, further removing background interference to determine the device pixel area, thereby accurately identifying the target abnormal area in the device pixel area, so as to accurately determine the transportation monitoring results of the power equipment. This achieves the technical effect of improving the accuracy of the location of abnormal transportation areas and the accuracy of transportation monitoring results, and solves the technical problems of inaccurate location of abnormal transportation areas and inaccurate transportation monitoring results in the monitoring of high-value power equipment in long-distance transportation.

[0054] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method. Figure 3 This is a flowchart of an optional power equipment transportation monitoring method according to an embodiment of the present invention, such as... Figure 3 As shown, the method includes:

[0055] S1: Determine the device pixel region of the power equipment, specifically including: dividing the surface of the power equipment into multiple regions, counting the total number of events accumulated in each region during the initial stable period to construct the event rate distribution feature, and calculating the target segmentation threshold based on the grayscale histogram corresponding to the event rate distribution feature to distinguish the device pixel region from the background region. The specific implementation process is the same as in the aforementioned embodiments, and will not be repeated here.

[0056] S2: In the device pixel area, determine the target abnormal area of ​​the power equipment. Specifically, this includes: calculating the target motion direction of the device pixel area, calculating the direction deviation angle between the motion direction of each pixel in the device pixel area and the target motion direction, marking the pixels with a direction deviation angle greater than a preset deviation angle threshold as abnormal pixels, and then determining the target abnormal area based on the abnormal pixels. The specific implementation process is the same as the aforementioned embodiment, and will not be repeated here.

[0057] S3: Based on the target abnormal area and the device pixel area, determine the transportation monitoring results of the power equipment. Specifically, this includes: counting the number of pixels in the target abnormal area as the abnormal area, counting the total number of pixels in the device pixel area as the total area, calculating the ratio of the abnormal area to the total area to obtain the abnormal proportion, comparing the abnormal proportion with the first preset proportion threshold and the second preset proportion threshold, and thus outputting the graded transportation monitoring results. The specific implementation process is the same as the aforementioned embodiment, and will not be repeated here.

[0058] This embodiment can achieve at least one of the following effects: (1) Completely independent, without relying on external assistance or historical baselines, with rapid deployment and strong versatility: It can work by relying only on dynamic vision sensors and edge computing terminals installed in the vehicle compartment, without relying on inertial measurement units for vehicle motion compensation, and without relying on external synchronization signals. (2) No need to preset detection targets, applicable to power equipment with any structural features, solving the problem of blind spots in monitoring in related technologies. (3) Effectively suppressing strong background noise, accurately distinguishing between overall vehicle body sway and local independent motion. Addressing the technical pain point that the broadband vibration energy caused by engine vibration and road bumps in the vehicle environment is much stronger than the weak features caused by local loosening, this method estimates the target motion direction and calculates the deviation angle between the motion direction of each pixel and the target motion direction. This method successfully separates local independent motion from global vibration, which can effectively overcome the overwhelming effect of strong background noise on local features, improve the signal-to-noise ratio and detection accuracy. (4) The combination of low computational load and high-precision positioning facilitates rapid on-site operation and maintenance. In terms of algorithm complexity, based on deviation angle statistics and area ratio calculation, the computational load is low and can be run in real time on edge computing terminals without relying on cloud big data processing.

[0059] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0060] This embodiment also provides a power equipment transportation monitoring device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0061] According to an embodiment of the present invention, an apparatus embodiment for implementing the above-described power equipment transportation monitoring method is also provided. Figure 4 This is a schematic diagram of a power equipment transportation monitoring device according to an embodiment of the present invention, such as... Figure 4 As shown, the aforementioned power equipment transportation monitoring device includes: a data acquisition module 400, an event distribution feature determination module 402, an equipment pixel region determination module 404, a target anomaly region determination module 406, and a transportation monitoring result determination module 408, wherein:

[0062] The data acquisition module 400 is used to acquire event data of the power equipment during the current transportation period. The event data includes at least the pixels of the power equipment surface brightness change event and the position coordinates of the pixels.

[0063] The event distribution feature determination module 402 is connected to the data acquisition module 400 and is used to determine the event distribution features of the power equipment during the current transportation period based on event data. The event distribution features are used to indicate the density of events causing brightness changes on the surface of the power equipment.

[0064] The device pixel region determination module 404 is connected to the event distribution feature determination module 402 and is used to determine the device pixel region of the power equipment during the current transportation period based on the event distribution features. The device pixel region is used to indicate the pixel range of the power equipment surface after removing background interference.

[0065] The target abnormal area determination module 406 is connected to the device pixel area determination module 404 and is used to determine the target abnormal area of ​​the power equipment in the current transportation period in the device pixel area.

[0066] The transportation monitoring result determination module 408 is connected to the target abnormal area determination module 406 and is used to determine the transportation monitoring result of the power equipment during the current transportation period based on the target abnormal area and the device pixel area.

[0067] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0068] It should be noted that the data acquisition module 400, event distribution feature determination module 402, device pixel region determination module 404, target abnormal region determination module 406, and transportation monitoring result determination module 408 mentioned above correspond to steps S102 to S110 in the embodiments. The instances and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a computer terminal.

[0069] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0070] The aforementioned power equipment transportation monitoring device may also include a processor and a memory. The aforementioned data acquisition module 400, event distribution feature determination module 402, equipment pixel area determination module 404, target abnormal area determination module 406, transportation monitoring result determination module 408, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0071] The processor contains a core that retrieves the corresponding program modules from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0072] According to an embodiment of this application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein, when the program is running, it controls the device containing the non-volatile storage medium to execute any of the above-mentioned power equipment transportation monitoring methods.

[0073] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals, and the non-volatile storage medium includes stored programs.

[0074] Optionally, during program execution, the device containing the non-volatile storage medium may be controlled to perform the following functions: acquire event data of the power equipment during the current transportation period, wherein the event data includes at least: pixels of brightness change events on the surface of the power equipment, and the position coordinates of the pixels; based on the event data, determine the event distribution characteristics of the power equipment during the current transportation period, wherein the event distribution characteristics are used to indicate the density of brightness change events on the surface of the power equipment; based on the event distribution characteristics, determine the device pixel region of the power equipment during the current transportation period, wherein the device pixel region is used to indicate the pixel range on the surface of the power equipment after removing background interference; within the device pixel region, determine the target abnormal region of the power equipment during the current transportation period; based on the target abnormal region and the device pixel region, determine the transportation monitoring results of the power equipment during the current transportation period.

[0075] According to an embodiment of this application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein the program executes any of the above-described methods for monitoring the transportation of power equipment.

[0076] According to an embodiment of this application, an embodiment of a computer program product is also provided. Optionally, in this embodiment, the computer program product includes a computer program that, when executed by a processor, implements the steps of the power equipment transportation monitoring method described above.

[0077] Optionally, when the aforementioned computer program product is executed on a data processing device, it is suitable to execute an initialization program with the following method steps: acquiring event data of the power equipment during the current transportation period, wherein the event data includes at least: pixels of the power equipment surface brightness change event, and the position coordinates of the pixels; determining the event distribution characteristics of the power equipment during the current transportation period based on the event data, wherein the event distribution characteristics are used to indicate the density of the power equipment surface brightness change event; determining the device pixel region of the power equipment during the current transportation period based on the event distribution characteristics, wherein the device pixel region is used to indicate the pixel range of the power equipment surface after removing background interference; determining the target abnormal region of the power equipment during the current transportation period within the device pixel region; and determining the transportation monitoring result of the power equipment during the current transportation period based on the target abnormal region and the device pixel region.

[0078] like Figure 5 The diagram illustrates a transportation monitoring electronic device for power equipment according to an embodiment of the present invention. The electronic device 10 includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring event data of the power equipment during the current transportation period, wherein the event data includes at least: pixels of brightness change events occurring on the surface of the power equipment, and the position coordinates of the pixels; determining the event distribution characteristics of the power equipment during the current transportation period based on the event data, wherein the event distribution characteristics are used to indicate the density of brightness change events occurring on the surface of the power equipment; determining the device pixel region of the power equipment during the current transportation period based on the event distribution characteristics, wherein the device pixel region is used to indicate the pixel range on the surface of the power equipment after removing background interference; determining the target abnormal region of the power equipment during the current transportation period within the device pixel region; and determining the transportation monitoring result of the power equipment during the current transportation period based on the target abnormal region and the device pixel region.

[0079] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of modules described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between modules, and may be electrical or other forms.

[0081] The modules described above as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0082] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0083] If the aforementioned integrated modules are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0084] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for monitoring the transportation of power equipment, characterized in that, include: Acquire event data of the power equipment during the current transportation period, wherein the event data includes at least: pixels of the power equipment surface brightness change event, and the position coordinates of the pixels; Based on the event data, the event distribution characteristics of the power equipment during the current transportation period are determined, wherein the event distribution characteristics are used to indicate the density of the brightness change events occurring on the surface of the power equipment; Based on the event distribution characteristics, the device pixel region of the power equipment during the current transportation period is determined, wherein the device pixel region is used to indicate the pixel range of the power equipment surface after removing background interference; Within the device pixel area, the target abnormal area of ​​the power equipment during the current transportation period is determined; Based on the target anomaly area and the device pixel area, the transportation monitoring result of the power equipment during the current transportation period is determined.

2. The method according to claim 1, characterized in that, The step of determining the event distribution characteristics of the power equipment during the current transportation period based on the event data includes: The surface of the power equipment is divided into multiple regions; Based on the event data, the event occurrence rate corresponding to each of the multiple regions is determined, wherein the event occurrence rate is used to quantify the total number of times the brightness change event occurs in the corresponding region during the current transportation period; The event distribution characteristics are obtained based on the event occurrence rates corresponding to each of the multiple regions.

3. The method according to claim 1, characterized in that, When the surface of the power equipment comprises multiple regions, determining the device pixel region of the power equipment during the current transportation period based on the event distribution characteristics includes: Determine the grayscale histogram corresponding to the event distribution features, wherein the grayscale histogram is used to indicate the distribution features of the event occurrence rates corresponding to the plurality of regions included in the event distribution features; Based on the grayscale histogram, a target segmentation threshold is determined, wherein the target segmentation threshold is used to divide the device pixel region and the background interference region; The device pixel region is determined based on the target segmentation threshold.

4. The method according to claim 3, characterized in that, Determining the device pixel region based on the target segmentation threshold includes: The regions with event occurrence rates greater than the target segmentation threshold among the multiple regions are determined as the initial regions of the power equipment during the current transportation period; The initial region is subjected to morphological processing to obtain the device pixel region, wherein the morphological processing includes at least: dilation processing and erosion processing.

5. The method according to claim 1, characterized in that, When the device pixel region includes multiple pixels, determining the target abnormal region of the power equipment in the current transportation period within the device pixel region includes: Among the multiple pixels, those whose movement speed is greater than a preset speed threshold in the current transportation period are identified as target pixels. When there are multiple target pixels, the movement direction with a frequency greater than a preset occurrence frequency among the movement directions corresponding to each of the multiple target pixels is determined as the target movement direction of the device pixel region in the current transportation period. The target abnormal region is determined based on the movement direction of each of the multiple pixels during the current transportation period and the target movement direction.

6. The method according to claim 5, characterized in that, The step of determining the target abnormal region based on the movement direction corresponding to each of the plurality of pixels in the current transportation period and the target movement direction includes: Based on the movement direction corresponding to each of the multiple pixels in the current transportation period and the target movement direction, multiple directional deviation angles are determined, wherein the multiple directional deviation angles correspond one-to-one with the multiple pixels, and the multiple directional deviation angles are used to indicate the degree to which the movement direction of the corresponding pixel deviates from the target movement direction; Among the multiple directional deviation angles, the pixel corresponding to the directional deviation angle that is greater than the preset deviation angle threshold is determined as an abnormal pixel. Based on the abnormal pixels, the target abnormal region is determined.

7. The method according to claim 6, characterized in that, When there are multiple abnormal pixels, determining the target abnormal region based on the abnormal pixels includes: Multiple abnormal pixels are clustered to obtain multiple initial abnormal regions; The initial abnormal regions whose total number of pixels is greater than a preset pixel number threshold are identified as target abnormal regions.

8. The method according to any one of claims 1 to 7, characterized in that, The determination of the transportation monitoring results of the power equipment during the current transportation period based on the target anomaly region and the device pixel region includes: Determine the abnormal area corresponding to the target abnormal region, and the total area corresponding to the device pixel region; Based on the abnormal area and the total area, the abnormal percentage of the power equipment during the current transportation period is determined; The transportation monitoring results are determined based on the percentage of anomalies.

9. The method according to claim 8, characterized in that, The determination of the transportation monitoring results based on the anomaly ratio includes: If the percentage of abnormalities is less than a first preset percentage threshold, the transportation monitoring result is determined to be that the power equipment is at a first-level abnormality level during the current transportation period; or If the abnormal percentage is greater than or equal to the first preset percentage threshold and less than the second preset percentage threshold, the transportation monitoring result is determined to be that the power equipment is at a level two abnormality during the current transportation period; or If the percentage of abnormalities is greater than or equal to the second preset percentage threshold, the transportation monitoring result is determined to be that the power equipment is at a level three abnormality during the current transportation period.

10. An electronic device, characterized in that, include: One or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the power equipment transport monitoring method according to any one of claims 1 to 9.

Images