Train gravity energy storage system energy evaluation method, device, medium and equipment

Abstract

The embodiment of the invention discloses an energy evaluation method and device for a train gravity energy storage system, a medium and equipment. The method comprises the following steps: acquiring a panoramic picture of the train gravity energy storage system; setting at least three positioning points in the panoramic picture, performing coordinate correction on the panoramic picture through the positions of the positioning points, and determining a selected area of the positioning points in the panoramic picture; determining the number of gravity energy blocks in the selected area of the positioning point according to the deep neural network hybrid architecture model; determining the relative height of each gravity energy block relative to the reference point according to the panoramic picture proportional relation and the topographic parameters; and based on the relative height of each gravity energy block, determining the sum of potential energy of all the gravity energy blocks in the selected area of the positioning point. By means of the processing capacity of the artificial intelligence technology on images and graphs, the accuracy and efficiency of counting the number of the gravity energy blocks are improved, manual intervention and errors are reduced, the calculation cost is greatly reduced, and then relatively accurate energy storage energy data can be rapidly obtained.

Description

Technical Field

[0001] The present invention relates to the field of gravity energy storage technology, and in particular to an energy evaluation method, device, medium and equipment for a train gravity energy storage system. Background Art

[0002] With the rapid growth of the global economy and the continuous increase in population, the transportation industry is facing huge challenges, among which energy issues are particularly prominent. As an important means of transportation, the energy consumption and emissions of trains have a significant impact on the environment. Therefore, researching and developing train energy storage technology, improving energy efficiency and reducing emissions have become important issues at present. As a form of gravity energy storage, train energy storage uses scenes such as hillsides and abandoned mines to transport heavy objects by train to achieve peak regulation, frequency regulation, phase regulation, energy storage, system backup and other functions. As a gravity energy storage, the energy storage calculation is calculated by the gravitational potential difference of the energy storage block, and the rising relative position of all energy storage blocks will be calculated as the final energy storage.

[0003] In the prior art, the distance of the pulled wire rope or the position sensor added to the gravity vehicle can be used as a calculation method. The energy storage data can be obtained by summarizing the pulling amount of the traction wire rope or the position of the gravity vehicle in all energy storage sites. The above method is certainly very good, but it is not intuitive. It needs to be calculated and counted one by one. Whether the data is correct requires other methods to verify; the length of the traction wire rope will change due to the influence of seasonal temperature and the size of the traction force. As time accumulates, the elastic coefficient of the wire rope will also change, and the length will be elongated. These situations will cause deviations in energy calculations. If position sensors are used, huge equipment costs and maintenance costs will be added.

[0004] With the development of artificial intelligence, computing power and models are growing at the rate of Moore's Law. We can make full use of the computing model of neural networks and the relatively easy processing capabilities of images and graphics to solve the traditionally difficult problems mentioned above. We can also reduce computing costs to a great extent and quickly obtain relatively accurate energy storage data, saving equipment costs and computing costs. Summary of the invention

[0005] Based on this, it is necessary to propose an energy evaluation method, device, medium and terminal for a train gravity energy storage system to address the above problems.

[0006] A method for evaluating energy of a train gravity energy storage system, the method comprising:

[0007] Get a panoramic picture of the train's gravity energy storage system.

[0008] At least three positioning points are set in the panoramic picture, coordinate correction is performed on the panoramic picture according to the positions of the positioning points, and a positioning point selected area in the panoramic picture is determined.

[0009] The number of gravity energy blocks in the area selected by the positioning point is determined according to the deep neural network hybrid architecture model.

[0010] The relative height of each gravity energy block relative to the reference point is determined according to the proportion relationship of the panoramic picture and the terrain parameters.

[0011] Based on the relative height of each of the gravity energy blocks, the sum of the potential energies of all the gravity energy blocks in the area selected by the positioning point is determined.

[0012] The step of setting at least three positioning points in the panoramic picture, performing coordinate correction on the panoramic picture according to the positions of the positioning points, and determining a selected area of ​​the positioning points in the panoramic picture specifically includes:

[0013] At least three positioning points are set in the panoramic picture.

[0014] The coordinate transformation matrix is ​​used to determine the distortion parameters by analyzing the positions of the positioning points in the panoramic image.

[0015] The coordinates of the panoramic image are corrected according to the distortion parameters.

[0016] According to the corrected coordinates, a region selected by the positioning point is determined in the panoramic image.

[0017] The method of determining the number of gravity energy blocks according to the deep neural network hybrid architecture model specifically includes:

[0018] Obtain a data set containing gravity energy blocks in the area selected by the current positioning point.

[0019] Each gravity energy block is labeled with its bounding box and category.

[0020] Faster R-CNN (Faster Region-based Convolutional Network) is selected as the basic target detection framework, and the deep neural network hybrid architecture model is constructed by combining feature pyramid network, group normalization and deformable convolutional network.

[0021] Training parameters are set, the deep neural network hybrid architecture model is trained, and the joint loss function is used to optimize the parameters.

[0022] The panoramic image is input into the trained deep neural network hybrid architecture model to extract feature maps.

[0023] A region proposal network is applied on the feature map to generate several gravitational energy blocks.

[0024] The gravity energy block is mapped onto a feature map, and classification and bounding box regression are performed to obtain a bounding box and a category of each gravity energy block.

[0025] According to the bounding box and category of each gravity energy block, the number of detected gravity energy blocks is counted.

[0026] The step of determining the relative height of each gravity energy block relative to the reference point according to the panoramic image ratio and terrain parameters specifically includes:

[0027] The vertical coordinate of the lowest gravity energy block in the area selected by the current positioning point is set as the reference point, and its initial energy is zero.

[0028] According to the proportion relationship of the panoramic picture, the vertical coordinate value of each gravity energy block is determined.

[0029] The relative height of each gravity energy block relative to the reference point is determined according to the ordinate value of each gravity energy block and in combination with the terrain parameters.

[0030] Wherein, the determining the sum of the potential energies of all the gravity energy blocks in the area selected by the positioning point based on the relative height of each of the gravity energy blocks specifically includes:

[0031] The sum of the potential energies of all the gravity energy blocks in the area selected by the positioning point is determined according to P=ΣW*Y*Sin(θ), wherein W is the weight of a single gravity energy block, Y is the relative height of the gravity energy block, and θ is the inclination angle of the mountain slope.

[0032] Wherein, after determining the sum of the potential energies of all the gravity energy blocks in the selected area of ​​the positioning point based on the coordinate value of each gravity energy block, the method further specifically includes:

[0033] The potential energy in the area selected by each positioning point in the panoramic picture is aggregated to obtain the stored energy of the train gravity energy storage system.

[0034] An energy evaluation device for a train gravity energy storage system, the device comprising:

[0035] The panoramic picture acquisition module is used to acquire a panoramic picture of the train gravity energy storage system.

[0036] The coordinate correction module is used to set at least three positioning points in the panoramic picture, perform coordinate correction on the panoramic picture according to the positions of the positioning points, and determine the area selected by the positioning points in the panoramic picture.

[0037] The module for determining the number of gravity energy blocks is used to determine the number of gravity energy blocks in the area selected by the positioning point according to the deep neural network hybrid architecture model.

[0038] The relative height determination module is used to determine the relative height of each gravity energy block relative to the reference point according to the proportion relationship of the panoramic picture and the terrain parameters.

[0039] The potential energy determination module is used to determine the total potential energy of all gravity energy blocks in the area selected by the positioning point based on the relative height of each gravity energy block.

[0040] Wherein, the device further comprises:

[0041] The energy storage acquisition module is used to summarize the potential energy in the area selected by each positioning point in the panoramic image to obtain the energy storage capacity of the train gravity energy storage system.

[0042] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the method described above.

[0043] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0044] The embodiments of the present invention have the following beneficial effects:

[0045] The present invention uses a panoramic picture of the train gravity energy storage system to comprehensively and intuitively understand the layout and status of the entire gravity energy storage system. Further, coordinate correction is performed on the panoramic picture, and combined with a deep neural network hybrid architecture model, the processing capability of the image and graphics using artificial intelligence technology is used to improve the accuracy and efficiency of the gravity energy block quantity statistics. It can automatically learn and identify features in the picture, effectively segment and count targets in complex backgrounds, reduce manual intervention and errors, greatly reduce computing costs, and thus quickly obtain relatively accurate energy storage data. According to the proportion relationship of the panoramic picture and the terrain parameters, the relative height of each gravity energy block relative to the reference point is determined. Based on the relative height of each gravity energy block, the potential energy sum of all gravity energy blocks in the selected area of ​​the positioning point is determined, which is a quantitative evaluation of the system's energy storage capacity, and also provides an important reference basis for the system's optimal design and operation and maintenance management. By comparing the potential energy sum of different time periods or different areas, the system's energy storage efficiency and usage can be analyzed, providing data support for further improving system performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] in:

[0048] Figure 1 A schematic flow chart of an embodiment of an energy evaluation method for a train gravity energy storage system provided by the present invention;

[0049] Figure 2 A schematic flow chart of another embodiment of a method for evaluating energy of a train gravity energy storage system provided by the present invention;

[0050] Figure 3 A schematic structural diagram of an embodiment of an energy evaluation device for a train gravity energy storage system provided by the present invention;

[0051] Figure 4 A schematic structural diagram of an embodiment of the device provided by the present invention;

[0052] Figure 5 A schematic structural diagram of an embodiment of the medium provided by the present invention. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0054] like Figure 1 As shown, Figure 1 A flow chart of an embodiment of a method for evaluating energy of a train gravity energy storage system provided by the present invention. A method for evaluating energy of a train gravity energy storage system, the method comprising:

[0055] S101: Acquire a panoramic image of a train gravity energy storage system.

[0056] For example, a camera can be set at a fixed position. In addition to monitoring the train gravity energy storage system, the camera can also conveniently capture panoramic image frames at any time, obtain panoramic pictures, and use the panoramic pictures to obtain real-time energy storage data of the train gravity energy storage system.

[0057] It should be noted that if a surveillance area cannot be covered by one camera, multiple cameras can be used for linkage. There is no specific limit on the number of cameras.

[0058] S102: at least three positioning points are set in the panoramic picture, coordinate correction is performed on the panoramic picture according to the positions of the positioning points, and an area selected by the positioning points in the panoramic picture is determined.

[0059] Exemplarily, firstly, the positioning points are set, and at least three positioning points are selected in the panoramic picture. Further, the known positions of these positioning points and their pixel positions in the panoramic picture are used to determine the distortion parameters, and the coordinates of the panoramic picture are corrected by the distortion parameters. Further, according to the corrected coordinates, the area selected by the positioning points is determined in the panoramic picture, that is, the area containing the gravity energy block.

[0060] S103: Determine the number of gravity energy blocks in the area selected by the positioning point according to the deep neural network hybrid architecture model.

[0061] Exemplarily, a data set containing gravity energy blocks in the area selected by the current positioning point is obtained; a bounding box and category label is performed for each gravity energy block; Faster R-CNN is selected as the basic target detection framework, and the deep neural network hybrid architecture model is constructed in combination with a feature pyramid network, group normalization, and a deformable convolutional network; training parameters are set, the deep neural network hybrid architecture model is trained, and the joint loss function is used for parameter optimization; the panoramic image is input into the trained deep neural network hybrid architecture model to extract a feature map; a region proposal network is applied to the feature map to generate a number of gravity energy blocks; the gravity energy block is mapped to the feature map, and classification and bounding box regression are performed to obtain the bounding box and category of each gravity energy block; and the number of detected gravity energy blocks is counted according to the bounding box and category of each gravity energy block.

[0062] S104: Determine the relative height of each gravity energy block relative to the reference point according to the ratio relationship of the panoramic image and the terrain parameters.

[0063] Exemplarily, the ordinate of the lowest gravity energy block in the area selected by the current positioning point is set as the reference point, and its initial energy is zero; the ordinate value of each gravity energy block is determined by utilizing the proportional relationship of the panoramic image, including the scale in the panoramic image or the known size of the reference object; based on the ordinate value of each gravity energy block and in combination with terrain parameters (such as slope, elevation, etc.), the relative height of each gravity energy block relative to the reference point is determined through three-dimensional reconstruction or terrain analysis software.

[0064] S105: Based on the relative height of each gravity energy block, determine the total potential energy of all gravity energy blocks in the area selected by the positioning point.

[0065] Exemplarily, the sum of the potential energies of all gravity energy blocks in the region selected by the positioning point is determined according to the following formula:

[0066] P = ΣW*Y*Sin(θ);

[0067] Where W is the weight of a single gravity energy block, Y is the relative height of the gravity energy block, and θ is the inclination angle of the mountain slope.

[0068] Furthermore, the potential energies of all the gravity energy blocks are added together to obtain the sum of the potential energies of all the gravity energy blocks in the area selected by the positioning point.

[0069] It can be seen from the above description that the present invention uses a panoramic picture of the train gravity energy storage system to comprehensively and intuitively understand the layout and status of the entire gravity energy storage system. Further, the panoramic picture is corrected for coordinates, and combined with a deep neural network hybrid architecture model, the processing capability of the image and graphics using artificial intelligence technology is used to improve the accuracy and efficiency of the gravity energy block quantity statistics, and the features in the picture can be automatically learned and recognized, and the targets in the complex background can be effectively segmented and counted, reducing manual intervention and errors, greatly reducing the calculation cost, and thus being able to quickly obtain relatively accurate energy storage data. According to the proportion relationship of the panoramic picture and the terrain parameters, the relative height of each gravity energy block relative to the reference point is determined, and based on the relative height of each gravity energy block, the sum of the potential energy of all gravity energy blocks in the selected area of ​​the positioning point is determined, which is a quantitative evaluation of the energy storage capacity of the system, and also provides an important reference basis for the optimization design and operation and maintenance management of the system. By comparing the sum of the potential energy in different time periods or different areas, the energy storage efficiency and usage of the system can be analyzed, providing data support for further improving the system performance.

[0070] like Figure 2 As shown, Figure 2 A flow chart of another embodiment of a train gravity energy storage system energy evaluation method provided by the present invention. A train gravity energy storage system energy evaluation method, the method comprising:

[0071] S201: Acquire a panoramic image of the train gravity energy storage system.

[0072] It should be noted that step S201 Figure 1 This has been discussed in detail in the implementation scenario shown and will not be repeated here.

[0073] S202: Setting at least three positioning points in the panoramic picture.

[0074] Exemplarily, at least three obvious and easily identifiable points in the panoramic image are selected as positioning points, and these positioning points include fixed reference objects with known positions or can be accurately measured in the real world, such as corners of buildings, intersections of roads, etc. The position of each positioning point is marked in the panoramic image using image processing software.

[0075] S203: Determine distortion parameters by analyzing the positions of the positioning points in the panoramic image using the coordinate transformation matrix.

[0076] Exemplarily, a world coordinate system is defined, whose coordinate axes are consistent with the directions of the real world. At the same time, an image coordinate system is defined on the panoramic image, and the coordinate axes are aligned with the pixel grid of the image. The real coordinates of each positioning point are measured or determined in the world coordinate system. The pixel coordinates of each positioning point are recorded in the image coordinate system. A coordinate transformation matrix is ​​used to describe the mapping relationship from the world coordinate system to the image coordinate system. The distortion parameters are solved by analyzing the coordinate differences of the positioning points in the two coordinate systems.

[0077] S204: performing coordinate correction on the panoramic image according to the distortion parameters.

[0078] Exemplarily, the panoramic image is corrected using the distortion parameters to eliminate image distortion caused by lens distortion.

[0079] S205: Determine the area selected by the positioning point in the panoramic image according to the corrected coordinates.

[0080] Exemplarily, in the corrected panoramic image, a selected area of ​​at least three positioning points is determined according to actual needs, and the pixel coordinate range or coordinate information of the boundary points of the selected area is recorded for subsequent further analysis or processing.

[0081] S206: Acquire a data set containing gravity energy blocks in the area selected by the current positioning point.

[0082] S207: Label each gravity energy block with a bounding box and a category.

[0083] For example, first, an image of the area selected by the positioning point is cropped from the panoramic image as a data set, and the gravity energy blocks in the image are annotated. The annotation should include the bounding box and category of each energy block.

[0084] S208: Select Faster R-CNN as the basic target detection framework, and combine it with feature pyramid network, group normalization and deformable convolutional network to build a deep neural network hybrid architecture model.

[0085] For example, Faster R-CNN is selected as the basic target detection framework because it combines the advantages of the region proposal network and Fast R-CNN and can efficiently detect targets. In combination with the feature pyramid network, the feature pyramid network is introduced on the basis of Faster R-CNN to enhance the model's ability to detect targets of different scales. By constructing a feature pyramid, feature maps of different levels are combined, so that the model can capture both fine-grained and coarse-grained information.

[0086] At the same time, group normalization and deformable convolution are introduced. Specifically, group normalization is used after the convolution layer to replace the traditional batch normalization to improve the adaptability and stability of the model to small batch data. Deformable convolution is introduced in some or all convolution layers to increase the flexibility of the convolution kernel, so that it can be adaptively adjusted according to the shape and size of the target, thereby improving the accuracy of detection.

[0087] S209: Set training parameters, train the deep neural network hybrid architecture model, and use the joint loss function to optimize the parameters.

[0088] Exemplarily, training parameters are set, including learning rate, number of iterations, batch size, optimizer, etc. The labeled data set is divided into a training set and a test set, the training set is used to train the deep neural network hybrid architecture model, and the test set is used to evaluate the performance of the model. During the training process, a joint loss function is used to optimize the parameters of the model.

[0089] S210: Input the panoramic image into the trained deep neural network hybrid architecture model to extract the feature map.

[0090] Exemplarily, necessary preprocessing operations are performed on the panoramic image, such as resizing, normalization, etc. The preprocessed image is input into a trained deep neural network hybrid architecture model, and a feature map is extracted through the deep neural network hybrid architecture model.

[0091] S211: Apply a region proposal network on the feature map to generate several gravity energy blocks.

[0092] S212: Map the gravity energy block to the feature map, and perform classification and bounding box regression to obtain the bounding box and category of each gravity energy block.

[0093] Exemplarily, a region proposal network is run on the feature map to generate several gravity energy blocks. According to the several gravity energy blocks generated by the region proposal network, a pooling operation is performed on the feature map to map each gravity energy block to a feature map of a fixed size. Classification and bounding box regression are performed using the pooled feature map to obtain the bounding box and category of each gravity energy block.

[0094] S213: Count the number of detected gravity energy blocks according to the bounding box and category of each gravity energy block.

[0095] Exemplarily, the bounding boxes of all gravity energy blocks are traversed and their number is counted, and this number is the total number of gravity energy blocks detected.

[0096] S214: Set the vertical coordinate of the lowest gravity energy block in the area selected by the current positioning point as the reference point, and its initial energy is zero.

[0097] Exemplarily, first, it is necessary to determine the one with the lowest ordinate among all the gravity energy blocks in the area selected by the positioning point, and set the ordinate of the lowest gravity energy block as the ordinate of the reference point, and the initial energy (or potential energy) of this point is zero.

[0098] S215: Determine the vertical coordinate value of each gravity energy block according to the proportion relationship of the panoramic image.

[0099] Exemplarily, the pixel ordinate of each gravity energy block is converted into an actual ordinate using the proportional relationship of the panoramic image.

[0100] S216: Determine the relative height of each gravity energy block relative to the reference point based on the ordinate value of each gravity energy block and in combination with the terrain parameters.

[0101] The terrain parameters may include the slope, undulation, and unevenness of the ground, which will affect the actual height position of the gravity energy block. For each gravity energy block, the ordinate of the reference point is subtracted from its actual ordinate to obtain the initial relative height relative to the reference point. Further, the initial relative height is adjusted in combination with the terrain parameters to determine the relative height of each gravity energy block relative to the reference point.

[0102] S217: Based on the relative height of each gravity energy block, determine the total potential energy of all gravity energy blocks in the area selected by the positioning point.

[0103] S218: Summarize the potential energy in the selected area of ​​each positioning point in the panoramic image to obtain the stored energy of the train gravity energy storage system.

[0104] Exemplarily, all gravity energy blocks in the area selected by the positioning point are traversed, their potential energies are accumulated, and the sum of the potential energies of all gravity energy blocks in the area is obtained. For each area selected by the positioning point in the panoramic image, the sum of the potential energies of the area selected by each positioning point in the panoramic image is accumulated to obtain the sum of the potential energies of the areas selected by all the positioning points in the panoramic image, that is, the stored energy of the train gravity energy storage system.

[0105] like Figure 3 As shown, Figure 3A schematic diagram of an energy evaluation device for a train gravity energy storage system provided by the present invention. An energy evaluation device 10 for a train gravity energy storage system, the device comprising:

[0106] The panoramic picture acquisition module 11 is used to acquire a panoramic picture of the train gravity energy storage system.

[0107] The coordinate correction module 12 is used to set at least three positioning points in the panoramic picture, perform coordinate correction on the panoramic picture according to the positions of the positioning points, and determine the area selected by the positioning points in the panoramic picture.

[0108] The gravity energy block quantity determination module 13 is used to determine the gravity energy block quantity of the area selected by the positioning point according to the deep neural network hybrid architecture model.

[0109] The relative height determination module 14 is used to determine the relative height of each gravity energy block relative to the reference point according to the ratio relationship of the panoramic image and the terrain parameters.

[0110] The potential energy determination module 15 is used to determine the total potential energy of all gravity energy blocks in the area selected by the positioning point based on the relative height of each gravity energy block.

[0111] Exemplarily, a panoramic picture of a train gravity energy storage system is obtained in the panoramic picture acquisition module 11. Further, in the coordinate correction module 12, at least three positioning points are set in the panoramic picture; the coordinate transformation matrix is ​​used to analyze the positions of the positioning points in the panoramic picture to determine the distortion parameters; the coordinates of the panoramic picture are corrected according to the distortion parameters; and the selected area of ​​the positioning points is determined in the panoramic picture according to the corrected coordinates. Furthermore, in the module 13 for determining the number of gravity energy blocks, a data set containing gravity energy blocks in the area selected by the current positioning point is obtained; a bounding box and category label is performed for each gravity energy block; Faster R-CNN is selected as the basic target detection framework, and a deep neural network hybrid architecture model is constructed by combining a feature pyramid network, group normalization, and a deformable convolutional network; training parameters are set, the deep neural network hybrid architecture model is trained, and the joint loss function is used for parameter optimization; the panoramic image is input into the trained deep neural network hybrid architecture model to extract a feature map; a region proposal network is applied to the feature map to generate a number of gravity energy blocks; the gravity energy blocks are mapped to the feature map, and classification and bounding box regression are performed to obtain the bounding box and category of each gravity energy block; and the number of detected gravity energy blocks is counted according to the bounding box and category of each gravity energy block. Furthermore, in the relative height determination module 14, the ordinate of the lowest gravity energy block in the area selected by the current positioning point is set as the reference point, and its initial energy is zero; the ordinate value of each gravity energy block is determined according to the proportional relationship of the panoramic image; the relative height of each gravity energy block relative to the reference point is determined according to the ordinate value of each gravity energy block and in combination with the terrain parameters. Further, in the potential energy determination module 15, based on the relative height of each gravity energy block, the sum of the potential energies of all gravity energy blocks in the area selected by the positioning point is determined. Finally, in the energy storage acquisition module (not shown), the potential energy in the area selected by each positioning point in the panoramic image is summarized to obtain the energy storage capacity of the train gravity energy storage system.

[0112] like Figure 4 As shown, Figure 4 The device 20 includes a memory 21 and a processor 22. The memory 21 stores a computer program, and the processor 22 executes the computer program when working to implement the following. Figure 1 and Figure 2 The method shown.

[0113] The specific technical details of a train gravity energy storage system energy assessment method implemented when the terminal 20 executes a computer program have been discussed in detail in the aforementioned method steps, so they will not be repeated here.

[0114] like Figure 5 As shown, Figure 5The structure diagram of an embodiment of the medium provided by the present invention is shown in FIG. The medium 30 stores at least one computer program 31, and the computer program 31 is executed by the processor 22 to implement the following Figure 1 and Figure 2 In one embodiment, the medium 30 may be a storage chip, a hard disk, a mobile hard disk, a USB flash drive, an optical disk, or other readable and writable storage tools, or a server, etc.

[0115] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0117] The apparatus, device, non-volatile computer-readable storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding apparatus, device, and non-volatile computer storage medium will not be repeated here.

[0118] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0119] For the convenience of description, the above device is described by being divided into various units according to their functions and described separately. Of course, when implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware. It should be understood by those skilled in the art that this specification embodiment can be provided as a method, system, or computer program product. Therefore, this specification embodiment can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification embodiment can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0124] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0125] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0126] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0127] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0128] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0129] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for evaluating the energy of a train gravity energy storage system, characterized in that: The method comprises: Get a panoramic picture of the train's gravity energy storage system; Setting at least three positioning points in the panoramic picture, performing coordinate correction on the panoramic picture according to the positions of the positioning points, and determining a selected area of ​​the positioning points in the panoramic picture; Determine the number of gravity energy blocks in the area selected by the positioning point according to the deep neural network hybrid architecture model; Determine the relative height of each of the gravity energy blocks relative to the reference point according to the panoramic image ratio and terrain parameters; Based on the relative height of each of the gravity energy blocks, the sum of the potential energies of all the gravity energy blocks in the area selected by the positioning point is determined.

2. A train gravity energy storage system energy assessment method according to claim 1, characterized in that: The step of setting at least three positioning points in the panoramic picture, performing coordinate correction on the panoramic picture according to the positions of the positioning points, and determining a selected area of ​​the positioning points in the panoramic picture specifically includes: Setting at least three positioning points in the panoramic picture; Determine the distortion parameters by analyzing the positions of the positioning points in the panoramic image using a coordinate transformation matrix; Performing coordinate correction on the panoramic image according to the distortion parameters; According to the corrected coordinates, a region selected by the positioning point is determined in the panoramic image.

3. A train gravity energy storage system energy assessment method according to claim 2, characterized in that: Determining the number of gravity energy blocks according to the deep neural network hybrid architecture model specifically includes: Obtaining a data set containing gravity energy blocks in the area selected by the current positioning point; Label each gravity energy block with a bounding box and category; Select Faster R-CNN as the basic target detection framework, and combine feature pyramid network, group normalization and deformable convolutional network to build the deep neural network hybrid architecture model; Setting training parameters, training the deep neural network hybrid architecture model, and optimizing the parameters using a joint loss function; Inputting the panoramic image into the trained deep neural network hybrid architecture model to extract feature maps; Applying a region proposal network on the feature map to generate a number of gravity energy blocks; Mapping the gravity energy block onto a feature map, and performing classification and bounding box regression to obtain a bounding box and category of each gravity energy block; According to the bounding box and category of each gravity energy block, the number of detected gravity energy blocks is counted.

4. A train gravity energy storage system energy assessment method according to claim 3, characterized in that: Determining the relative height of each gravity energy block relative to the reference point according to the panoramic image ratio relationship and terrain parameters specifically includes: The vertical coordinate of the lowest gravity energy block in the area selected by the current positioning point is set as the reference point, and its initial energy is zero; Determine the ordinate value of each of the gravity energy blocks according to the proportion relationship of the panoramic picture; The relative height of each gravity energy block relative to the reference point is determined according to the ordinate value of each gravity energy block and in combination with the terrain parameters.

5. A train gravity energy storage system energy assessment method according to claim 4, characterized in that: The determining, based on the relative height of each of the gravity energy blocks, the sum of the potential energies of all the gravity energy blocks within the region selected by the positioning point positioning point specifically includes: The sum of the potential energies of all the gravity energy blocks in the area selected by the positioning point is determined according to P=ΣW*Y*Sin(θ), wherein W is the weight of a single gravity energy block, Y is the relative height of the gravity energy block, and θ is the inclination angle of the mountain slope.

6. A train gravity energy storage system energy assessment method according to claim 5, characterized in that: After determining the sum of potential energies of all gravity energy blocks in the region selected by the positioning point based on the coordinate value of each gravity energy block, the method further specifically includes: The potential energy in the area selected by each positioning point in the panoramic picture is aggregated to obtain the stored energy of the train gravity energy storage system.

7. An energy evaluation device for a train gravity energy storage system, characterized in that: The device comprises: A panoramic picture acquisition module is used to acquire a panoramic picture of the train gravity energy storage system; A coordinate correction module, used to set at least three positioning points in the panoramic picture, perform coordinate correction on the panoramic picture according to the positions of the positioning points, and determine a selected area of ​​the positioning points in the panoramic picture; A module for determining the number of gravity energy blocks, used to determine the number of gravity energy blocks in the area selected by the positioning point according to a deep neural network hybrid architecture model; A relative height determination module, used to determine the relative height of each of the gravity energy blocks relative to the reference point according to the panoramic image ratio relationship and terrain parameters; The potential energy determination module is used to determine the total potential energy of all gravity energy blocks in the area selected by the positioning point based on the relative height of each gravity energy block.

8. The energy evaluation device for a train gravity energy storage system according to claim 7, characterized in that: The device also includes: The energy storage acquisition module is used to summarize the potential energy in the area selected by each positioning point in the panoramic image to obtain the energy storage capacity of the train gravity energy storage system.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor is caused to execute the steps of the method according to any one of claims 1 to 6.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 6.

Images