Sensor-based and clustering analysis model-based machine consumption intelligent metering method and system

Abstract

The application provides a kind of intelligent metering method and system based on sensor and clustering analysis model of machine consumption, the application obtains the video image of work object in the process of electric power operation operation and the track video image of work vehicle in mechanical shift through visual sensor;Respectively, first sample data and second sample data are obtained by preprocessing;Second sample data is processed to obtain vehicle trip information and vehicle identity information;Extract the start and end time of each work action in the action information in first sample data;Classify the action information based on the pre-constructed clustering analysis model to determine the work type;According to the start and end time of vehicle and the start and end time of each work action, work type determines the work object and work type of vehicle in mechanical shift;According to the work type of vehicle, the machine consumption data of vehicle in mechanical shift is metered according to vehicle track.The application can automatically and accurately obtain the actual consumption of mechanical shift in each work.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power data metering, and in particular to a machine consumption intelligent metering method and system based on sensors and clustering analysis models. BACKGROUND

[0002] The premise of realizing business and finance integration is to accurately meter the resource consumption generated by the business end and to collect real-time information.

[0003] However, the current resource consumption metering and information collection technology is not highly intelligent. The existing resource consumption is mainly obtained through the work ticket filled out by business personnel. For example, personnel work hour information is collected mainly through the work group members and time information filled out on the work ticket, and the work hour information is calculated according to the actual start / end time. According to the current recording method, manual work hours can be metered based on work tickets. However, if the vehicle usage in the mechanical shift is also recorded by using the traditional task sheet, although there is destination (involving the substation) and mileage information on the task sheet, it is impossible to determine which project or work the vehicle is used for. Therefore, it is impossible to accurately obtain the actual consumption of the mechanical shift.

[0004] Therefore, the present application provides a machine consumption intelligent metering method and system based on sensors and clustering analysis models. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a machine consumption intelligent metering method and system based on sensors and clustering analysis models to solve the problem of being unable to accurately obtain the actual consumption of the mechanical shift. The specific technical solutions are as follows:

[0006] In a first aspect, a machine consumption intelligent metering method based on sensors and clustering analysis models is provided, and the method comprises:

[0007] obtaining work object video images in the process of electric power operation and vehicle trajectory video images in the mechanical shift through a visual sensor;

[0008] respectively pre-processing the work object video images and the vehicle trajectory video images to obtain first sample data and second sample data;

[0009] processing the second sample data based on a trajectory tracking analysis algorithm and a target detection algorithm to obtain vehicle travel information and vehicle identity information; the vehicle travel information includes vehicle start / end time and vehicle trajectory;

[0010] extracting action information and start / end time of each work action in the first sample data;

[0011] classify the action information based on a pre-constructed clustering analysis model to determine a work type;

[0012] determine a work object and a work type of the vehicle in a mechanical shift based on the vehicle start and end time and the start and end time and the work type of each work action;

[0013] measure the machine consumption data of the vehicle in the mechanical shift based on the work type of the vehicle and the vehicle trajectory.

[0014] Optionally, the pre-processing of the work object video image and the work vehicle trajectory video image respectively to obtain first sample data and second sample data comprises:

[0015] respectively performing noise reduction processing on the work object video image and the work vehicle trajectory video image;

[0016] After noise reduction processing, respectively performing image segmentation processing to obtain image blocks;

[0017] respectively extracting image blocks containing work objects and vehicles as first sample data and second sample data.

[0018] Optionally, the processing of the second sample data based on the trajectory tracking analysis algorithm and the target detection algorithm to obtain vehicle travel information and vehicle identity information comprises:

[0019] processing the second sample data based on the target detection algorithm to obtain vehicle identity information, the vehicle identity information comprising a vehicle model and a vehicle type;

[0020] sorting vehicles in the second sample data in chronological order based on the trajectory tracking analysis algorithm to obtain vehicle trajectories and vehicle start and end times.

[0021] Optionally, the classification of the action information based on a pre-constructed clustering analysis model to determine a work type comprises:

[0022] extracting feature values in the action information;

[0023] inputting the feature values into a KNN (k-Nearest Neighbor) clustering model to output a classification result;

[0024] determining a work type corresponding to the action information based on the classification result.

[0025] Optionally, the determination of a work object and a work type of the vehicle in a mechanical shift based on the vehicle start and end time and the start and end time and the work type of each work action comprises:

[0026] calculating a time difference between a stop time of the vehicle and a start time of each work action;

[0027] If the time difference between the two times is less than a preset threshold, the work type and work object of the work action are determined as the work object and work type of the vehicle in the mechanical shift.

[0028] Optionally, the method further comprises:

[0029] obtaining vehicle travel information according to the vehicle trajectory;

[0030] calculating the machine consumption data of the vehicle in the work type according to the vehicle travel information and the oil consumption unit price information.

[0031] In a second aspect, the present application provides a machine consumption intelligent metering system based on a sensor and a clustering analysis model, the system comprising:

[0032] an acquisition unit configured to acquire, by a visual sensor, work object video images in a power work operation process and work vehicle trajectory video images in a mechanical shift;

[0033] a preprocessing unit configured to respectively pre-process the work object video images and the work vehicle trajectory video images to obtain first sample data and second sample data;

[0034] a processing unit configured to process the second sample data based on a trajectory tracking analysis algorithm and a target detection algorithm to obtain vehicle travel information and vehicle identity information; the vehicle travel information comprising vehicle start and stop times and a vehicle trajectory;

[0035] an extraction unit configured to extract action information and start and stop times of each work action in the first sample data;

[0036] a classification unit configured to classify the action information based on a pre-constructed clustering analysis model to determine a work type;

[0037] a determination unit configured to determine a work object and a work type of a vehicle in a mechanical shift according to the vehicle start and stop times and the start and stop times of each work action and the work type;

[0038] a metering unit configured to meter machine consumption data of the vehicle in the mechanical shift according to the work type of the vehicle and the vehicle trajectory.

[0039] Optionally, the preprocessing unit further comprises:

[0040] a noise reduction sub-unit configured to respectively perform noise reduction processing on the work object video images and the work vehicle trajectory video images;

[0041] The segmentation subunit is configured to perform image segmentation processing on the noise-reduced image to obtain image blocks;

[0042] The extraction subunit is configured to extract the image blocks containing the work object and the vehicle as first sample data and second sample data, respectively.

[0043] In a third aspect, the present application provides an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus;

[0044] The memory is configured to store a computer program;

[0045] The processor is configured to execute the program stored on the memory to implement the method steps of any one of the first aspect.

[0046] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method steps of any one of the first aspect.

[0047] In a fifth aspect, a computer program product containing instructions is provided, which, when executed on a computer, causes the computer to perform the above-mentioned any one of the method steps of the intelligent metering method based on sensors and clustering analysis models.

[0048] The embodiments of the present application have the following beneficial effects:

[0049] The embodiments of the present application provide an intelligent metering method and system based on sensors and clustering analysis models. The present application obtains work object video images in the process of electric power operation and vehicle trajectory video images in the process of mechanical shift through a visual sensor; pre-processes the work object video images and the vehicle trajectory video images to obtain first sample data and second sample data; processes the second sample data based on a trajectory tracking analysis algorithm and a target detection algorithm to obtain vehicle travel information and vehicle identity information; the vehicle travel information includes vehicle start and end time and vehicle trajectory; extracts action information in the first sample data and start and end time of each work action; classifies the action information based on a pre-constructed clustering analysis model to determine the work type; determines the work object and the work type of the vehicle in the mechanical shift based on the vehicle start and end time and the start and end time of each work action, and the work type; and measures the machine consumption data of the vehicle in the mechanical shift based on the work type of the vehicle and the vehicle trajectory. The present application can automatically and accurately obtain the actual consumption data of the mechanical shift in various operations, and accurately match the vehicle with the electric power work object.

[0050] Of course, implementing any product or method of the present application does not necessarily require all the advantages described above to be achieved at the same time. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A flowchart illustrating an intelligent metering method for machine consumption based on sensors and clustering analysis models, provided in this application embodiment;

[0053] Figure 2 A schematic diagram of the structure of an intelligent metering system for machine consumption based on sensors and cluster analysis models provided in this application embodiment;

[0054] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0056] This application provides an intelligent measurement method for machine consumption based on sensors and cluster analysis models. The following detailed description, in conjunction with specific implementation methods, will illustrate this intelligent measurement method for machine consumption based on sensors and cluster analysis models. Figure 1 As shown, the specific steps are as follows:

[0057] Step S101: Acquire video images of the work object and the trajectory video images of the work vehicle during the power operation using a vision sensor.

[0058] In this step, video images of the work object are acquired through vision sensors installed at various locations on the work object, such as equipment in a substation, recording the operator's information on the various power devices. Video images of the work vehicle's trajectory during machine shifts can be acquired through vision sensors installed at various points along the power plant's power lines.

[0059] Step S102: Preprocess the video images of the work object and the video images of the work vehicle trajectory to obtain the first sample data and the second sample data respectively.

[0060] Step S103: Process the second sample data based on the trajectory tracking analysis algorithm and the target detection algorithm to obtain vehicle travel information and vehicle identity information; the vehicle travel information includes the vehicle start and end times and the vehicle trajectory.

[0061] In summary, the vehicle start and end times refer to the times when the vehicle starts and stops at its destination.

[0062] Step S104: Extract the action information and the start and end times of each operation action from the first sample data.

[0063] In the embodiments of this application, each type of operation has a typical marker action, and the operation type can be identified by analyzing the typical marker action.

[0064] Step S105: Classify the action information based on the pre-built clustering analysis model to determine the job type.

[0065] Optionally, classifying the action information based on a pre-built clustering analysis model to determine the job type includes:

[0066] Extract the feature values ​​from the action information;

[0067] The feature values ​​are input into the KNN clustering model to output the classification results;

[0068] The job type corresponding to the action information is determined based on the classification results.

[0069] In this step, the KNN clustering analysis model determines the class closest to the sample to be tested by calculating the distance. In one example, the algorithm of the KNN clustering analysis model is as follows: First, a large amount of typical marker action information of various task types is obtained as training samples. The training samples are preprocessed, and after preprocessing, the marker samples of each class are determined. Then, the threshold of each class is calculated, and the marker score of the marker samples is calculated. Candidate classes of the first sample to be tested are selected, the distance between the marker scores of the candidate samples and the marker scores of the marker samples is calculated, and finally, the class of the first sample is decided.

[0070] Step S106: Determine the work object and work type of the vehicle in the machine shift based on the vehicle start and end times, the start and end times of each work action, and the work type.

[0071] Step S107: Based on the vehicle's operation type and vehicle trajectory, measure the vehicle's machine consumption data in the machine shift.

[0072] In the embodiments of this application, engine consumption includes vehicle fuel consumption and other consumption amounts.

[0073] Optionally, the preprocessing of the video images of the work object and the video images of the work vehicle trajectory to obtain the first sample data and the second sample data includes:

[0074] Noise reduction processing is performed on the video images of the work object and the video images of the work vehicle trajectory, respectively;

[0075] After noise reduction, image segmentation is performed to obtain image blocks;

[0076] Image blocks containing the work objects and vehicles were extracted as the first sample data and the second sample data, respectively.

[0077] Optionally, the process of processing the second sample data based on the trajectory tracking analysis algorithm and the target detection algorithm to obtain vehicle travel information and vehicle identity information includes:

[0078] Based on the target detection algorithm, the second sample data is processed to obtain vehicle identity information, which includes vehicle model and vehicle type.

[0079] Based on the trajectory tracking analysis algorithm, the vehicles in the second sample data are sorted in chronological order to obtain the vehicle trajectories and vehicle start and end times.

[0080] Optionally, determining the work object and work type of the vehicle in the machine shift based on the vehicle's start and end times, the start and end times of each work action, and the work type includes:

[0081] Calculate the time difference between the stopping time of the vehicle and the starting time of each operation action;

[0082] If the time difference between the two is less than a preset threshold, then the operation type and operation object of the operation action are determined as the operation object and operation type of the vehicle in the machine shift.

[0083] Optionally, the step of measuring the vehicle's machine consumption data in the machine shift based on the vehicle's operation type and vehicle trajectory includes:

[0084] Vehicle travel information is obtained based on the vehicle trajectory.

[0085] The vehicle's engine consumption data for this type of operation is calculated based on the vehicle's travel information and fuel consumption unit price information.

[0086] Secondly, based on the same inventive concept, this application provides an intelligent metering system for machine consumption based on sensors and cluster analysis models, such as... Figure 2 As shown, the system includes:

[0087] The acquisition unit 201 is used to acquire video images of the work object and video images of the trajectory of the work vehicle during the power operation process through a vision sensor.

[0088] Preprocessing unit 202 is used to preprocess the video image of the work object and the video image of the work vehicle trajectory to obtain first sample data and second sample data respectively;

[0089] Processing unit 203 is used to process the second sample data based on trajectory tracking analysis algorithm and target detection algorithm to obtain vehicle travel information and vehicle identity information; the vehicle travel information includes vehicle start and end times and vehicle trajectory;

[0090] Extraction unit 204 is used to extract action information and the start and end times of each operation action from the first sample data;

[0091] Classification unit 205 is used to classify the action information based on a pre-built clustering analysis model to determine the job type;

[0092] The determining unit 206 is used to determine the work object and work type of the vehicle in the machine shift based on the start and end times of the vehicle and the start and end times of each work action and the work type.

[0093] Metering unit 207 is used to measure the machine consumption data of the vehicle in the machine shift according to the operation type and vehicle trajectory of the vehicle.

[0094] Optionally, the preprocessing unit further includes:

[0095] The noise reduction subunit is used to perform noise reduction processing on the video image of the work object and the video image of the trajectory of the work vehicle, respectively.

[0096] The segmentation subunit is used to perform image segmentation processing to obtain image blocks after noise reduction processing;

[0097] The extraction subunit is used to extract image blocks containing the work object and the vehicle as the first sample data and the second sample data, respectively.

[0098] Based on the same technical concept, embodiments of the present invention also provide an electronic device, such as... Figure 3 As shown, it includes a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304.

[0099] Memory 303 is used to store computer programs;

[0100] The processor 301, when executing the program stored in the memory 303, implements the steps of the intelligent metering method for machine consumption based on sensors and cluster analysis models.

[0101] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0102] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0103] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0104] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0105] In another embodiment of the present invention, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the above-described intelligent metering methods for machine consumption based on sensors and clustering analysis models.

[0106] In another embodiment of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the intelligent metering methods for machine consumption based on sensors and clustering analysis models in the above embodiments.

[0107] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0108] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0109] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A smart metering method for machine consumption based on sensors and cluster analysis models, characterized in that, The method includes: Video images of the work objects and the trajectory of the work vehicles during the machinery shift are acquired through visual sensors. The video images of the work object and the video images of the work vehicle trajectory are preprocessed to obtain the first sample data and the second sample data, respectively. The second sample data is processed using trajectory tracking analysis algorithms and target detection algorithms to obtain vehicle travel information and vehicle identity information; the vehicle travel information includes vehicle start and end times and vehicle trajectory. Extract the action information and the start and end times of each operation action from the first sample data; The action information is classified based on a pre-built clustering analysis model to determine the job type; The work objects and work types of the vehicles in the machine shift are determined based on the start and end times of the vehicles and the start and end times of each work action, as well as the work type. Based on the vehicle's operation type and vehicle trajectory, the machine consumption data of the vehicle in the machine shift is measured. The process of determining the work objects and work types of vehicles in a machine shift based on the vehicle's start and end times, the start and end times of each work action, and the work type includes: Calculate the time difference between the stopping time of the vehicle and the starting time of each operation action; If the time difference between the two is less than a preset threshold, then the operation type and operation object of the operation action are determined as the operation object and operation type of the vehicle in the machine shift.

2. The intelligent metering method for machine consumption based on sensors and cluster analysis models according to claim 1, characterized in that, The preprocessing of the video images of the work object and the video images of the work vehicle trajectory to obtain the first sample data and the second sample data includes: Noise reduction processing is performed on the video images of the work object and the video images of the work vehicle trajectory, respectively; After noise reduction, image segmentation is performed to obtain image blocks; Image blocks containing the work objects and vehicles were extracted as the first sample data and the second sample data, respectively.

3. The intelligent metering method for machine consumption based on sensors and cluster analysis models according to claim 1, characterized in that, The vehicle trip information and vehicle identity information obtained by processing the second sample data based on the trajectory tracking analysis algorithm and the target detection algorithm include: Based on the target detection algorithm, the second sample data is processed to obtain vehicle identity information, which includes vehicle model and vehicle type. Based on the trajectory tracking analysis algorithm, the vehicles in the second sample data are sorted in chronological order to obtain the vehicle trajectories and vehicle start and end times.

4. The intelligent metering method for machine consumption based on sensors and cluster analysis models according to claim 1, characterized in that, The classification of the action information based on the pre-built clustering analysis model to determine the job type includes: Extract the feature values ​​from the action information; The feature values ​​are input into the KNN clustering model to output the classification results; The job type corresponding to the action information is determined based on the classification results.

5. The intelligent metering method for machine consumption based on sensors and cluster analysis models according to claim 1, characterized in that, The data on vehicle machine consumption during the machine shift, based on the vehicle's operation type and vehicle trajectory measurement, includes: Vehicle travel information is obtained based on the vehicle trajectory. The vehicle's engine consumption data for this type of operation is calculated based on the vehicle's travel information and fuel consumption unit price information.

6. A smart metering system for machine consumption based on sensors and cluster analysis models, characterized in that, The system includes: The acquisition unit is used to acquire video images of the work object and video images of the trajectory of the work vehicle during the power operation process through a vision sensor; The preprocessing unit is used to preprocess the video images of the work object and the video images of the work vehicle trajectory to obtain the first sample data and the second sample data, respectively. The processing unit is used to process the second sample data based on the trajectory tracking analysis algorithm and the target detection algorithm to obtain vehicle travel information and vehicle identity information; the vehicle travel information includes the vehicle's start and end times and the vehicle's trajectory. The extraction unit is used to extract the action information and the start and end times of each operation action from the first sample data. A classification unit is used to classify the action information based on a pre-built clustering analysis model to determine the job type; The determining unit is used to determine the work object and work type of the vehicle in the machine shift based on the start and end times of the vehicle and the start and end times of each work action and the work type. The metering unit is used to measure the machine consumption data of the vehicle in the machine shift according to the operation type and vehicle trajectory of the vehicle. The process of determining the work objects and work types of vehicles in a machine shift based on the vehicle's start and end times, the start and end times of each work action, and the work type includes: Calculate the time difference between the stopping time of the vehicle and the starting time of each operation action; If the time difference between the two is less than a preset threshold, then the operation type and operation object of the operation action are determined as the operation object and operation type of the vehicle in the machine shift.

7. The intelligent metering system for machine consumption based on sensors and cluster analysis models according to claim 6, characterized in that, The preprocessing unit further includes: The noise reduction subunit is used to perform noise reduction processing on the video image of the work object and the video image of the trajectory of the work vehicle, respectively. The segmentation subunit is used to perform image segmentation processing to obtain image blocks after noise reduction processing; The extraction subunit is used to extract image blocks containing the work object and the vehicle as the first sample data and the second sample data, respectively.

Images