Method, device and equipment for measuring residual coal quantity of train, medium and product
The three-dimensional point cloud model is generated through image acquisition and laser scanning technology, and the comparison is performed using the extended Kalman filtering algorithm, which solves the inaccuracy problem of the remaining coal measurement of trains, achieving higher measurement accuracy and more effective vehicle cleaning management.
Patent Information
- Application Number
- CN202510235341.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-28
- Publication Date
- 2025-05-30
AI Technical Summary
The prior art has deviations and inaccuracies when measuring the amount of coal remaining in the train compartment, especially under natural light and fixed light sources, whereas artificial intelligence visual measurements have large errors; while laser three-dimensional modeling requires that the train moves at a uniform speed, and the measurement is inaccurate when the train speed is unstable.
The image acquisition device obtains the contour features of each position of the target car and determines the target plane information; the laser scanning device obtains three-dimensional coordinates and generates a three-dimensional point cloud model; then, the three-dimensional point cloud model and the original model are compared through the extended Kalman filtering algorithm to calculate the remaining coal in the target car.
It reduces the measurement errors in the external environment, improves the measurement accuracy of the remaining coal amount of trains, and can accurately guide manual cleaning and dispatching of labor to avoid waste of human resources.
Smart Images
Figure CN120070542A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of data processing, and in particular to a method, device, equipment, medium and product for measuring the remaining coal quantity of a train. Background Art
[0002] The adhesion of residual coal in the coal-carrying train carriage is a thorny problem, which will have a great impact on the loss and benefit of train transportation. When transferring coal through a port, in order to avoid transfer loss, the port needs a set of accurate, environmentally unaffected, stable and reliable solutions to accurately measure the remaining coal quantity in the train carriage after unloading.
[0003] In the prior art, the measurement of the remaining coal quantity mainly adopts the methods of artificial intelligence vision and laser three-dimensional modeling. However, in the prior art, there will be a large deviation in the measurement of the remaining coal quantity in the carriage by artificial intelligence vision under natural light and fixed light sources; when measuring the remaining coal quantity in the carriage by the method of laser three-dimensional modeling in the prior art, it is required that the moving speed of the train is uniform, and inaccurate measurement of the remaining coal quantity in the carriage will occur when the train speed is unstable. In view of this, how to accurately measure the remaining coal quantity of the train has become an urgent problem to be solved at present. Summary of the Invention
[0004] The present disclosure provides a method, device, equipment, medium and product for measuring the remaining coal quantity of a train.
[0005] In a first aspect, the present disclosure provides a method for measuring the remaining coal quantity of a train, including:
[0006] Obtaining the contour features of each position of the target carriage through an image acquisition device, and determining the target plane information of the target carriage based on the contour features;
[0007] Obtaining the three-dimensional coordinates of the target carriage through a laser scanning device, and generating a three-dimensional point cloud model of the target carriage based on the three-dimensional coordinates and the target plane information;
[0008] Comparing the three-dimensional point cloud model with the original model of the target carriage through an extended Kalman filter algorithm to obtain the remaining coal quantity of the target carriage; wherein, the original model is used to indicate the three-dimensional model of the target carriage when the target carriage does not carry coal.
[0009] In some embodiments, the obtaining the contour features of each position of the target carriage through an image acquisition device, and determining the target plane information of the target carriage based on the contour features includes:
[0010] During the train operation, images of various positions of the target carriage are collected by the image acquisition device, and the contour features of each position of the target carriage are determined based on the images;
[0011] Image merging is performed based on the contour features determined from each of the images to obtain the target plane information of the target carriage.
[0012] In some embodiments, the obtaining the three-dimensional coordinates of the target carriage by the laser scanning device includes:
[0013] Calculating the difference between the length of the target carriage and a first value to obtain the abscissa of the target carriage; wherein, the first value is the product of the ray length of the vertical laser scanner ray and the cosine value of the corresponding angle of the vertical laser scanner ray;
[0014] Calculating the product of the ray length of the horizontal laser scanner ray and the cosine value of the corresponding angle of the horizontal laser scanner ray to obtain the ordinate of the target carriage;
[0015] Calculating the product of the ray length of the horizontal laser scanner ray and the sine value of the corresponding angle of the horizontal laser scanner ray to obtain the vertical coordinate of the target carriage.
[0016] In some embodiments, the generating the three-dimensional point cloud model of the target carriage based on the three-dimensional coordinates and the target plane information includes:
[0017] Determining the three-dimensional coordinates of each contour point of the target plane information based on the three-dimensional coordinates to obtain the three-dimensional point cloud model of the target carriage.
[0018] In some embodiments, the obtaining the remaining coal quantity of the target carriage by comparing the three-dimensional point cloud model with the original model of the target carriage through the extended Kalman filter algorithm includes:
[0019] Determining the model errors of the three-dimensional point cloud model and the original model of the target carriage to obtain a first model error and a second model error respectively;
[0020] Fitting the first model error and the three-dimensional point cloud model through the extended Kalman filter algorithm to obtain the corrected three-dimensional point cloud model;
[0021] Fitting the second model error and the original model of the target carriage through the extended Kalman filter algorithm to obtain the corrected original model;
[0022] Determining the remaining coal quantity of the target carriage based on the corrected three-dimensional point cloud model and the corrected original model.
[0023] In some embodiments, determining the remaining coal quantity of the target carriage based on the corrected three-dimensional point cloud model and the corrected original model includes:
[0024] Inputting the corrected three-dimensional point cloud model and the corrected original model into an objective function for processing, and obtaining the remaining coal quantity of the target carriage by performing an optimal solution to the objective function; wherein, the objective function is a mathematical model between the three-dimensional model of the carriage and the remaining coal quantity of the carriage.
[0025] In a second aspect, the present disclosure provides a device for measuring the remaining coal quantity of a train, including:
[0026] A determination module, configured to obtain the contour features of each position of the target carriage through an image acquisition device, and determine the target plane information of the target carriage based on the contour features;
[0027] A generation module, configured to obtain the three-dimensional coordinates of the target carriage through a laser scanning device, and generate a three-dimensional point cloud model of the target carriage based on the three-dimensional coordinates and the target plane information;
[0028] A comparison module, configured to compare the three-dimensional point cloud model and the original model of the target carriage through an extended Kalman filter algorithm to obtain the remaining coal quantity of the target carriage; wherein, the original model is used to indicate the three-dimensional model of the target carriage when the target carriage is not carrying coal.
[0029] In a third aspect, the present disclosure provides a computer device, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the steps of the method described in the above aspect.
[0030] In a fourth aspect, the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the above aspect are implemented.
[0031] In a fifth aspect, the present disclosure provides a computer program product, including a computer program / instructions, and when the computer program is executed by a processor, the steps of the method described in the above aspect are implemented.
[0032] A method, device, equipment, medium and product for measuring the remaining coal quantity of a train provided by the present disclosure. First, contour features of each position of a target carriage are obtained through an image acquisition device, and target plane information of the target carriage is determined based on the contour features. Then, three-dimensional coordinates of the target carriage are obtained through a laser scanning device, and a three-dimensional point cloud model of the target carriage is generated based on the three-dimensional coordinates and the target plane information. Finally, the remaining coal quantity of the target carriage is obtained by comparing the three-dimensional point cloud model with an original model of the target carriage through an extended Kalman filter algorithm, where the original model is used to indicate the three-dimensional model of the target carriage when it is not carrying coal.
[0033] As can be seen from the above description, the technical solution of the present disclosure generates a three-dimensional point cloud model of a target carriage through an image acquisition device and a laser scanning device, and obtains the remaining coal quantity of the target carriage by comparing the three-dimensional point cloud model with an original model of the target carriage through an extended Kalman filter algorithm. The technical solution of the present disclosure reduces the error generated by the external environment for measurement through the extended Kalman filter algorithm, and improves the measurement accuracy of the remaining coal quantity of the train. And after improving the measurement accuracy of the remaining coal quantity of the train through the technical solution of the present disclosure, it can accurately guide the manual car cleaning dispatch, thus avoiding the waste of human resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] By describing the embodiments of the present disclosure in more detail in conjunction with the drawings, the above and other objects, features and advantages of the present disclosure will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present disclosure, and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure, and do not constitute a limitation to the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.
[0035] Figure 1 It is a flowchart of a method for measuring the remaining coal quantity of a train provided by an exemplary embodiment of the present disclosure;
[0036] Figure 2 It is a schematic diagram of the deployment of car cleaning track equipment provided by an exemplary embodiment of the present disclosure;
[0037] Figure 3 It is a schematic diagram of a network architecture provided by an exemplary embodiment of the present disclosure;
[0038] Figure 4 It is a schematic block diagram of the functional modules of a device for measuring the remaining coal quantity of a train provided by an exemplary embodiment of the present disclosure;
[0039] Figure 5 It is a block diagram of the structure of an electronic device provided by an exemplary embodiment of the present disclosure;
[0040] Figure 6Block diagram of a computer system provided by an exemplary embodiment of the present disclosure;
[0041] Figure 7 Block diagram of a computer program product provided by an exemplary embodiment of the present disclosure. Detailed implementation manners
[0042] In order to enable those skilled in the art of the present technology to better understand the technical solutions of the present disclosure, and to fully understand how the present disclosure uses technical means to solve technical problems and the implementation process of achieving corresponding technical effects and implement accordingly, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The embodiments of the present disclosure and each feature in the embodiments can be combined with each other without conflict, and the formed technical solutions are all within the protection scope of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present disclosure.
[0043] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0044] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.
[0045] In one embodiment, as Figure 1 shown, a method for measuring the remaining coal amount of a train is provided, including the following steps:
[0046] Step 101, obtain the contour features of each position of the target carriage through an image acquisition device, and determine the target plane information of the target carriage based on the contour features.
[0047] Here, when it is necessary to measure the remaining coal quantity of the target carriage of the train, the executing entity can obtain the contour features of each position of the target carriage traveling on the car cleaning track through the image acquisition device provided on the car cleaning track, and can determine the target plane information of the target carriage based on the contour features.
[0048] In a possible embodiment, obtaining the contour features of each position of the target carriage through the image acquisition device and determining the target plane information of the target carriage based on the contour features include the following steps:
[0049] During the train's travel, the image acquisition device is used to collect images of each position of the target carriage, and the contour features of each position of the target carriage are determined based on the images;
[0050] Image merging is performed based on the contour features determined from each image to obtain the target plane information of the target carriage.
[0051] Specifically, first, during the train's travel, the executing entity collects images of each position of the target carriage through the image acquisition device, and determines the contour features of each position of the target carriage based on the images. Exemplarily, in one embodiment, the executing entity collects images of each position of the target carriage through the image acquisition device installed on the car cleaning track, as Figure 2 shown, Figure 2 Exemplarily shows a schematic diagram of the deployment of the car cleaning track equipment. There is an overhead camera on the car cleaning track. The target carriage travels on the car cleaning track. There is a car dumper on the car cleaning track. When the car dumper finishes tipping the target carriage, the executing entity can obtain the visible light data of the target carriage at each position during the train's travel through the overhead camera 3 on the track, the side camera 4 on the track, and the side camera 5 on the track, so as to collect images of each position of the target carriage. After the executing entity finishes collecting the images of the target carriage at each position, it determines the contour features of each position of the target carriage based on the collected images. It should be noted that the position and number of the cameras can be set flexibly and are not limited here, as long as it can achieve the collection of images of each position of the target carriage.
[0052] Then, the executing entity performs image merging based on the contour features determined from each image to obtain the target plane information of the target carriage. Exemplarily, in one embodiment, the executing entity performs image merging on the contour features determined from each image through OpenCV (a cross-platform computer vision and machine learning software library). The image merging algorithm can adopt the stitching algorithm of Normalized Cross Correlation (NCC). This algorithm calculates the similarity between the windows of each displacement in two images, and this algorithm is defined as:
[0053]
[0054] Among them, and are the average value images of the window, and I 1 and I 2 are the average value images of the window, I 1 (x, y) and I 2 (x, y) are respectively two pictures to be stitched, N is the window size, x i =(x i , y i ) are the pixel coordinates of the window, u=(u, v) is the displacement or offset calculated through the NCC coefficient, the range of the NCC coefficient is [-1, 1], the displacement parameter corresponding to the NCC peak represents the geometric transformation between the two images, and the fast merging of the images is realized by obtaining the geometric change, and finally the target plane information of the complete target carriage is obtained.
[0055] It should be noted that for image merging, other algorithms can also be used, as long as the image merging of the contour features can be realized, and the specific algorithm selection is not limited here.
[0056] Step 102, obtain the three-dimensional coordinates of the target carriage through a laser scanning device, and generate a three-dimensional point cloud model of the target carriage based on the three-dimensional coordinates and the target plane information.
[0057] Here, after the execution subject obtains the contour features of each position of the target carriage through the image acquisition device and determines the target plane information of the target carriage based on the contour features, the three-dimensional coordinates of the target carriage can be obtained through the laser scanning device installed on the car cleaning track, and a three-dimensional point cloud model of the target carriage can be generated based on the three-dimensional coordinates and the target plane information.
[0058] In a possible embodiment, obtaining the three-dimensional coordinates of the target carriage through a laser scanning device includes the following steps:
[0059] Calculate the difference between the length of the target carriage and the first value to obtain the abscissa of the target carriage;
[0060] Calculate the product of the ray length of the horizontal laser scanner ray and the cosine value of the corresponding angle of the horizontal laser scanner ray to obtain the ordinate of the target carriage;
[0061] Calculate the product of the ray length of the horizontal laser scanner ray and the sine value of the corresponding angle of the horizontal laser scanner ray to obtain the vertical coordinate of the target carriage.
[0062] Specifically, after the execution entity obtains the contour features of each position of the target carriage through the image acquisition device and determines the target plane information of the target carriage based on the contour features, the execution entity calculates the difference between the length of the target carriage and the first value to obtain the abscissa of the target carriage, where the first value is the product of the ray length of the vertical laser scanner ray and the cosine value of the corresponding angle of the vertical laser scanner ray; the execution entity calculates the product of the ray length of the horizontal laser scanner ray and the cosine value of the corresponding angle of the horizontal laser scanner ray to obtain the ordinate of the target carriage; the execution entity calculates the product of the ray length of the horizontal laser scanner ray and the sine value of the corresponding angle of the horizontal laser scanner ray to obtain the vertical coordinate of the target carriage.
[0063] Exemplarily, in one embodiment, as Figure 2 shown, a laser scanner is provided above the car cleaning track, and the target carriage travels on the car cleaning track. The execution entity can calculate the abscissa x of the target carriage through the product of the length of the target carriage and the product of the ray length of the vertical laser scanner 2 ray on the track and the cosine value of the corresponding angle of the vertical laser scanner 2 ray. The calculation formula is as follows:
[0064] x = L (length of the carriage) - l (ray length of the vertical laser scanner ray) * Cos(θ (angle corresponding to the vertical scanner ray)).
[0065] The execution entity can calculate the ordinate y of the target carriage by calculating the product of the ray length of the horizontal laser scanner 1 ray and the cosine value of the corresponding angle of the horizontal laser scanner 1 ray. The calculation formula is as follows:
[0066] y = l (ray length of the horizontal scanner laser ray) * Cos(θ (angle corresponding to the horizontal scanner ray)).
[0067] The execution entity can calculate the vertical coordinate of the target carriage by calculating the product of the ray length of the horizontal laser scanner 1 ray and the sine value of the corresponding angle of the horizontal laser scanner 1 ray. The calculation formula is as follows:
[0068] z = l (ray length of the horizontal scanner laser ray) * Sin(θ (angle corresponding to the horizontal scanner ray)).
[0069] It should be noted that the laser scanner can also be replaced by other devices that can achieve the positioning of the three-dimensional coordinates of the target carriage, such as millimeter-wave radar, which is not limited here.
[0070] In a possible embodiment, generating a three-dimensional point cloud model of the target carriage based on the three-dimensional coordinates and the target plane information includes the following steps:
[0071] Determine the three-dimensional coordinates of each contour point of the target plane information based on the three-dimensional coordinates to obtain the three-dimensional point cloud model of the target carriage.
[0072] Specifically, after the execution entity obtains the three-dimensional coordinates of the target carriage through the laser scanning device, it determines the three-dimensional coordinates of each contour point of the target plane information based on the three-dimensional coordinates, and obtains the three-dimensional point cloud model of the target carriage. Exemplarily, in one embodiment, continuing from the previous example, the three-dimensional coordinates F(x, y, z) of the target carriage obtained by the execution entity through the laser scanning device are as follows:
[0073]
[0074] The execution entity obtains the relative position of the current vertical laser scanner 2 in the target carriage through the horizontal laser scanner 1 installed above the car cleaning track, and uses the clock built in the laser scanner to accurately match the three-dimensional coordinate data F(x, y, z) of the scan and the target plane information of the target carriage, and obtains the three-dimensional point cloud model of the target carriage.
[0075] Step 103: Compare the three-dimensional point cloud model with the original model of the target carriage through the extended Kalman filter algorithm to obtain the remaining coal volume of the target carriage.
[0076] Here, after the execution entity obtains the three-dimensional coordinates of the target carriage through the laser scanning device and generates the three-dimensional point cloud model of the target carriage based on the three-dimensional coordinates and the target plane information, it can compare the three-dimensional point cloud model with the original model of the target carriage through the extended Kalman filter algorithm to obtain the remaining coal volume of the target carriage, where the original model is used to indicate the three-dimensional model of the target carriage when the target carriage is not carrying coal.
[0077] In a possible embodiment, comparing the three-dimensional point cloud model with the original model of the target carriage through the extended Kalman filter algorithm to obtain the remaining coal volume of the target carriage includes the following steps:
[0078] Determine the model errors of the three-dimensional point cloud model and the original model of the target carriage, and obtain the first model error and the second model error respectively;
[0079] Fit the first model error and the three-dimensional point cloud model through the extended Kalman filter algorithm to obtain the corrected three-dimensional point cloud model;
[0080] Fit the second model error and the original model of the target carriage through the extended Kalman filter algorithm to obtain the corrected original model;
[0081] Determine the remaining coal volume of the target carriage based on the corrected three-dimensional point cloud model and the corrected original model.
[0082] Specifically, after the execution entity obtains the three-dimensional coordinates of the target carriage through the laser scanning device and generates the three-dimensional point cloud model of the target carriage based on the three-dimensional coordinates and the target plane information, first, the execution entity determines the model errors between the three-dimensional point cloud model and the original model of the target carriage, and obtains the first model error and the second model error respectively. Exemplarily, in one embodiment, the execution entity calibrates the three-dimensional point cloud model and the original model of the target carriage through the ultrasonic radar, and determines the first model error A of the two models in the detection quantity of the ultrasonic radar 1 and the second model error A 2 .
[0083] Then, the execution entity fits the first model error A 1 and the three-dimensional point cloud model through the extended Kalman filter algorithm to obtain the corrected three-dimensional point cloud model; afterwards, the execution entity fits the second model error A 2 and the original model of the target carriage through the extended Kalman filter algorithm to obtain the corrected original model.
[0084] Exemplarily, in one embodiment, the execution entity fits the first model error A 1 and the three-dimensional point cloud model through the extended Kalman filter algorithm, and fits the second model error A 2 and the original model of the target carriage through the extended Kalman filter algorithm. After the two fitting processes are completed, the corrected three-dimensional point cloud model and the corrected original model can be obtained. Since the traditional non-linear Kalman algorithm uses the Taylor expansion as the way to convert non-linearity into linearity for calculation, but this embodiment does not involve the prediction of noise points in the original data and the prediction of the measurement position of the original model, so the non-linear measurement relationship can use the meshed image data as the state transition function set, and the data of the meshed three-dimensional point cloud model as the input of the observation value. The meshed architecture is a cloud-native architecture mode, and its core idea is to separate the middleware framework (such as RPC, cache, asynchronous message, etc.) from the business process, so that the middleware SDK and the business code are further decoupled. By calculating the sum of the z values of the points within the range of its coordinates (0~x, 0~y) for each mesh point, and calculating the sum of all points less than or equal to the current point x, y, the surface obtained by using the sum value calculation is a surface that increases as x and y increase. The deviation value of each point obtained by fitting the surface in this way, that is, the first model error A 1 and the second model error A 2 are averaged to all points. When calculating at a single point, A 1 and A 2 can be averaged to all points less than the current point to obtain the corrected three-dimensional point cloud model and the corrected original model.
[0085] It should be noted that the extended Kalman filter algorithm in this embodiment can also be replaced. For example, it can be replaced with the unscented Kalman algorithm. After replacement, the linear fitting part needs to be replaced with a sigma two-dimensional point set. The speed of the replaced unscented Kalman filter algorithm can be faster, but the accuracy of the data is highly correlated with the accuracy of the sigma points. Therefore, many additional calibration processing algorithms need to be added to the sigma point set.
[0086] Finally, the execution entity determines the remaining coal volume of the target carriage based on the corrected three-dimensional point cloud model and the corrected original model.
[0087] In a possible embodiment, determining the remaining coal volume of the target carriage based on the corrected three-dimensional point cloud model and the corrected original model includes the following steps:
[0088] Input the corrected three-dimensional point cloud model and the corrected original model into the objective function for processing, and obtain the remaining coal volume of the target carriage by performing an optimal solution to the objective function.
[0089] Exemplarily, in one embodiment, after the execution entity obtains the corrected three-dimensional point cloud model and the corrected original model, it inputs the corrected three-dimensional point cloud model and the corrected original model into the objective function for processing, and finally obtains the remaining coal volume of the target carriage by performing an optimal solution to the objective function, where the objective function is a mathematical model between the three-dimensional model of the carriage and the remaining coal volume of the carriage.
[0090] A method, device, equipment, medium and product for measuring the remaining coal volume of a train provided by the present disclosure. First, the contour features of each position of the target carriage are obtained through an image acquisition device, and the target plane information of the target carriage is determined based on the contour features; then, the three-dimensional coordinates of the target carriage are obtained through a laser scanning device, and a three-dimensional point cloud model of the target carriage is generated based on the three-dimensional coordinates and the target plane information; finally, the remaining coal volume of the target carriage is obtained by comparing the three-dimensional point cloud model with the original model of the target carriage through an extended Kalman filter algorithm, where the original model is used to indicate the three-dimensional model of the target carriage when it is not carrying coal.
[0091] As can be seen from the above description, the technical solution of the present disclosure generates a three-dimensional point cloud model of the target carriage through an image acquisition device and a laser scanning device, and compares the three-dimensional point cloud model with the original model of the target carriage through an extended Kalman filter algorithm to obtain the remaining coal volume of the target carriage. The technical solution of the present disclosure reduces the error caused by the external environment for measurement through the extended Kalman filter algorithm, improving the measurement accuracy of the remaining coal volume of the train; and after improving the measurement accuracy of the remaining coal volume of the train through the technical solution of the present disclosure, it can accurately guide the manual car cleaning dispatch, thus avoiding the waste of human resources.
[0092] In one embodiment, a network architecture of a method for measuring the remaining coal volume of a train is further provided, as Figure 3 shown Figure 3 Exemplarily shows a schematic diagram of the network architecture. Among them, the network for measuring the remaining coal volume of the train is divided into three levels, namely the front-end device layer, the data processing layer, and the office network.
[0093] Specifically, the front-end device layer includes Lane Cleaning Device 1, Lane Cleaning Device 2, and Lane Cleaning Device 3. In each lane cleaning device, there are a vertical laser scanner on the track, a horizontal laser scanner on the track, an overhead camera on the track, a side camera on the track, and a side camera on the track. Lane Cleaning Device 1 and Lane Cleaning Device 2 are connected to CD2 and CD3 switches, and Lane Cleaning Device 3 is connected to the lane cleaning switch. Lane Cleaning Device 1 and Lane Cleaning Device 2 upload the data of the target carriage collected to the CD2 and CD3 switches, and Lane Cleaning Device 3 uploads the data of the target carriage collected to the lane cleaning switch.
[0094] The data processing layer includes a data processing server, Core Switch 1, Core Switch 2, and an enterprise firewall. The office network includes a port virtual machine and an operation console. The CD2, CD3 switches, and the lane cleaning switch are uniformly connected to Core Switch 1. The data processing server synchronizes the data in Core Switch 1 to the port virtual machine through the enterprise firewall and Core Switch 2. The port virtual machine obtains interface data such as the car cleaning management system, the incoming train notice system, and the train information system, and communicates with the data processing server through the enterprise firewall. The operation station accesses the link of the train remaining coal volume measurement system within the office network for operation, realizing the measurement of the remaining coal volume of the target carriage. The specific measurement method can refer to the embodiments of the method for measuring the remaining coal volume of the train applied in the above embodiments, which will not be elaborated here.
[0095] Based on the above embodiments, this embodiment provides an application example. The technical solution of the present disclosure is applied in a certain car cleaning operation, and the remaining coal volume of the carriage after dumper operation is accurately measured through a laser scanner and a visible light camera installed outside the dumper workshop. The equipment installation method is as follows:
[0096] First, install two high-precision two-dimensional laser scanners on the maintenance platform above the outlet end of the car dumper to measure the longitudinal position of the carriage and the transverse comparison data respectively, and scan the outline of the carriage after train unloading in real time to generate a three-dimensional data point cloud model of the empty train carriage. Compare it with the standard carriage model, calculate the remaining coal volume in the carriage after tipping. Then, combine the empirical density of coal to generate the remaining coal weight and distribution in the carriage after tipping. Finally, install a car number recognition system at the outlet end of the car dumper to identify the number of each carriage, and require the video monitoring and fill light to be perpendicular to the carriage so as to directly face the carriage number, with a distance of not less than 2 meters, an installation height of 2 meters and corresponding one by one with the carriage scanning system data. Combine the time stamp to form a unique remaining coal volume data.
[0097] After multiple on-site data comparisons, the measurement accuracy of the single measurement method for the remaining coal volume in the carriage is much lower than that of this technical solution for the remaining coal volume. After multiple comparisons, the measurement accuracy error of this technical solution is less than 3%. While ensuring the accurate judgment of the remaining coal volume in the carriage when the train leaves the port, this technical solution can accurately guide the manual car cleaning work arrangement and avoid waste of human resources.
[0098] In the case of dividing each functional module according to the corresponding functions, the present disclosure provides an apparatus for measuring the remaining coal volume of a train. The apparatus for measuring the remaining coal volume of a train can be a server or a chip applied to a server. Figure 4 It is a schematic block diagram of the functional modules of the apparatus for measuring the remaining coal volume of a train provided by an exemplary embodiment of the present disclosure. As Figure 4 shown, the apparatus for measuring the remaining coal volume of a train includes:
[0099] A determination module 401, configured to obtain the contour features of each position of the target carriage through an image acquisition device, and determine the target plane information of the target carriage based on the contour features;
[0100] A generation module 402, configured to obtain the three-dimensional coordinates of the target carriage through a laser scanning device, and generate a three-dimensional point cloud model of the target carriage based on the three-dimensional coordinates and the target plane information;
[0101] A comparison module 403, configured to compare the three-dimensional point cloud model with the original model of the target carriage through an extended Kalman filter algorithm to obtain the remaining coal volume of the target carriage; wherein, the original model is used to indicate the three-dimensional model of the target carriage when the target carriage does not carry coal.
[0102] In one embodiment, the determination module 401 includes:
[0103] A first determination unit, configured to collect images of each position of the target carriage during the running of the train through the image acquisition device, and determine the contour features of each position of the target carriage based on the images;
[0104] A merging unit, configured to perform image merging based on the contour features determined from each of the images to obtain the target plane information of the target carriage.
[0105] In one embodiment, the generating module 402 includes:
[0106] A first calculation unit, configured to calculate the difference between the length of the target carriage and a first value to obtain the abscissa of the target carriage; wherein, the first value is the product of the ray length of the vertical laser scanner ray and the cosine value of the corresponding angle of the vertical laser scanner ray;
[0107] A second calculation unit, configured to calculate the product of the ray length of the horizontal laser scanner ray and the cosine value of the corresponding angle of the horizontal laser scanner ray to obtain the ordinate of the target carriage;
[0108] A third calculation unit, configured to calculate the product of the ray length of the horizontal laser scanner ray and the sine value of the corresponding angle of the horizontal laser scanner ray to obtain the vertical coordinate of the target carriage.
[0109] In one embodiment, the generating module 402 includes:
[0110] A second determination unit, configured to determine the three-dimensional coordinates of each contour point of the target plane information based on the three-dimensional coordinates to obtain the three-dimensional point cloud model of the target carriage.
[0111] In one embodiment, the comparison module 403 includes:
[0112] A third determination unit, configured to determine the model errors between the three-dimensional point cloud model and the original model of the target carriage, respectively obtaining a first model error and a second model error;
[0113] A first fitting unit, configured to fit the first model error and the three-dimensional point cloud model through an extended Kalman filter algorithm to obtain the corrected three-dimensional point cloud model;
[0114] A second fitting unit, configured to fit the second model error and the original model of the target carriage through an extended Kalman filter algorithm to obtain the corrected original model;
[0115] A fourth determination unit, configured to determine the remaining coal quantity of the target carriage based on the corrected three-dimensional point cloud model and the corrected original model.
[0116] In one embodiment, the comparison module 403 includes:
[0117] A fourth calculation unit, configured to input the corrected three-dimensional point cloud model and the corrected original model into an objective function for processing, and obtain the remaining coal amount of the target carriage by optimally solving the objective function; wherein, the objective function is a mathematical model between the three-dimensional model of the carriage and the remaining coal amount of the carriage.
[0118] The embodiments of the present disclosure further provide an electronic device, including: at least one processor; a memory for storing executable instructions of the at least one processor; wherein, the at least one processor is configured to execute the instructions to implement the above method disclosed in the embodiments of the present disclosure.
[0119] Figure 5 It is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. As Figure 5 shown, the electronic device 500 includes at least one processor 501 and a memory 502 coupled to the processor 501. The processor 501 can execute the corresponding steps in the above method disclosed in the embodiments of the present disclosure.
[0120] The above-mentioned processor 501 may also be referred to as a central processing unit (CPU). It may be an integrated circuit chip with signal processing capabilities. Each step in the above method disclosed in the embodiments of the present disclosure can be completed by the integrated logic circuit in the hardware of the processor 501 or the instructions in the form of software. The above-mentioned processor 501 may be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present disclosure can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in the memory 502, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register and other mature storage media in the art. The processor 501 reads the information in the memory 502 and combines its hardware to complete the steps of the above method.
[0121] In addition, when various operations / processes according to the present disclosure are implemented through software and / or firmware, they can be transferred from a storage medium or a network to a computer system with a dedicated hardware structure, such as Figure 6The computer system 600 shown installs the programs that make up the software. When various programs are installed, the computer system can perform various functions, including, for example, the functions described above and so on. Figure 6 The block diagram of the computer system provided by an exemplary embodiment of the present disclosure.
[0122] The computer system 600 is intended to represent various forms of digital electronic computer devices, such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, for example, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described herein and / or claimed.
[0123] As Figure 6 As shown, the computer system 600 includes a computing unit 601, which can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 602 or the computer programs loaded from the storage unit 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.
[0124] Multiple components in the computer system 600 are connected to the I / O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 can be any type of device that can input information into the computer system 600. The input unit 606 can receive input digital or character information and generate key signal inputs related to the user settings and / or function controls of the electronic device. The output unit 607 can be any type of device that can present information and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 608 can include, but is not limited to, magnetic disks and optical disks. The communication unit 609 allows the computer system 600 to exchange information / data with other devices through a network such as the Internet and can include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a BluetoothTM device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.
[0125] The computing unit 601 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 executes the various methods and processes described above. For example, in some embodiments, the above-described methods disclosed in the embodiments of the present disclosure may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 500 via the ROM 602 and / or the communication unit 609. In some embodiments, the computing unit 601 may be configured to execute the above-described methods disclosed in the embodiments of the present disclosure by any other suitable means (e.g., by means of firmware).
[0126] The embodiments of the present disclosure also provide a computer-readable storage medium, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the above-described methods disclosed in the embodiments of the present disclosure.
[0127] The computer-readable storage medium in the embodiments of the present disclosure may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The above computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specifically, the above computer-readable storage medium may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0128] The above computer-readable medium may be included in the above electronic device; or may exist separately and not be assembled into the electronic device.
[0129] Figure 7 A computer program product provided for an exemplary embodiment of the present disclosure, the computer program product 700 includes a computer program 701, wherein when the computer program 701 is executed by a processor, the above-described methods disclosed in the embodiments of the present disclosure are implemented.
[0130] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The foregoing programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer.
[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.
[0132] The modules, components, or units described in the embodiments of the present disclosure may be implemented in software or in hardware. Among them, the names of the modules, components, or units do not, in some cases, constitute a limitation on the modules, components, or units themselves.
[0133] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, by way of non-limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and so on.
[0134] The above description is only some embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.
[0135] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art should understand that the above examples are only for the purpose of illustration and not for the purpose of limiting the scope of the present disclosure. Those skilled in the art should understand that the above embodiments can be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims
1. A method for measuring the remaining coal quantity of a train, characterized in that: include: Acquire contour features of each position of the target compartment through an image acquisition device, and determine target plane information of the target compartment based on the contour features; Acquire the three-dimensional coordinates of the target compartment by means of a laser scanning device, and generate a three-dimensional point cloud model of the target compartment based on the three-dimensional coordinates and the target plane information; The three-dimensional point cloud model and the original model of the target carriage are compared by using an extended Kalman filter algorithm to obtain the remaining coal amount of the target carriage; wherein the original model is used to indicate the three-dimensional model of the target carriage when the target carriage is not carrying coal.
2. The method according to claim 1, characterized in that: The step of acquiring contour features of each position of the target compartment by an image acquisition device and determining target plane information of the target compartment based on the contour features includes: During the running of the train, the image acquisition device is used to acquire images of various positions of the target carriage, and contour features of various positions of the target carriage are determined based on the images; The images are merged based on the contour features determined in each of the images to obtain the target plane information of the target compartment.
3. The method according to claim 1, characterized in that The step of obtaining the three-dimensional coordinates of the target carriage by means of a laser scanning device includes: Calculate the difference between the length of the target carriage and a first value to obtain the horizontal coordinate of the target carriage; wherein the first value is the product of the ray length of the vertical laser scanner ray and the cosine value of the angle corresponding to the vertical laser scanner ray; Calculate the product of the ray length of the transverse laser scanner ray and the cosine value of the corresponding angle of the transverse laser scanner ray to obtain the longitudinal coordinate of the target compartment; The product of the ray length of the transverse laser scanner ray and the sine value of the corresponding angle of the transverse laser scanner ray is calculated to obtain the vertical coordinate of the target compartment.
4. The method according to claim 1, characterized in that: The step of generating a three-dimensional point cloud model of the target compartment based on the three-dimensional coordinates and the target plane information includes: The three-dimensional coordinates of each contour point of the target plane information are determined based on the three-dimensional coordinates to obtain a three-dimensional point cloud model of the target compartment.
5. The method according to claim 1, characterized in that The method of comparing the three-dimensional point cloud model with the original model of the target carriage by using an extended Kalman filter algorithm to obtain the remaining amount of coal in the target carriage includes: Determining model errors of the three-dimensional point cloud model and the original model of the target carriage to obtain a first model error and a second model error respectively; Fitting the first model error and the three-dimensional point cloud model by an extended Kalman filter algorithm to obtain the corrected three-dimensional point cloud model; Fitting the second model error and the original model of the target carriage by an extended Kalman filter algorithm to obtain the corrected original model; The remaining amount of coal in the target carriage is determined based on the corrected three-dimensional point cloud model and the corrected original model.
6. The method according to claim 5, characterized in that The determining the remaining amount of coal in the target carriage based on the corrected three-dimensional point cloud model and the corrected original model comprises: The corrected three-dimensional point cloud model and the corrected original model are input into the objective function for processing, and the remaining coal amount in the target carriage is obtained by optimally solving the objective function; wherein the objective function is a mathematical model between the three-dimensional model of the carriage and the remaining coal amount in the carriage.
7. A device for measuring the remaining coal quantity on a train, characterized in that: include: A determination module, used to obtain contour features of each position of the target compartment through an image acquisition device, and determine target plane information of the target compartment based on the contour features; A generating module, configured to obtain the three-dimensional coordinates of the target compartment by means of a laser scanning device, and generate a three-dimensional point cloud model of the target compartment based on the three-dimensional coordinates and the target plane information; A comparison module is used to compare the three-dimensional point cloud model and the original model of the target carriage through an extended Kalman filter algorithm to obtain the remaining coal amount of the target carriage; wherein the original model is used to indicate the three-dimensional model of the target carriage when the target carriage is not carrying coal.
8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product comprising a computer program / instructions, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.