A method and system for calculating the quantity of tower coating work

Abstract

This invention pertains to the power industry, and particularly relates to a method and system for calculating the quantity of pole coating work. The method includes: identifying target poles and obtaining pole parameters based on a PowerNet model; calculating the estimated coating work quantity based on the pole parameters and spraying operation parameters; and measuring the coating thickness on-site to update the estimated coating work quantity. Identifying the target poles and obtaining pole parameters based on the PowerNet model accurately identifies various parameters of the target poles, facilitating subsequent operations; calculating the estimated coating work quantity based on the pole parameters and spraying operation parameters yields the theoretical work quantity; and measuring the coating thickness on-site to update the estimated coating work quantity allows for accurate calculation of the work quantity in conjunction with actual operational conditions.

Description

Technical Field

[0001] This invention belongs to the field of power, and in particular relates to a method and system for calculating the engineering quantity of pole and tower coating. Background Technology

[0002] Electricity needs to be transmitted via power lines. To improve safety and facilitate installation, power lines are generally suspended in the air by setting up poles or towers.

[0003] Power poles are generally made of metal and are required to have a long service life. Since power poles are usually built in the field, in harsh environments, if the external environment causes abnormalities in the power poles, it will seriously affect the safety of the power transmission system.

[0004] To extend the lifespan of power poles, it is necessary to apply protective coatings to reduce environmental impact. To improve the efficiency of pole maintenance, it is essential to control the relevant work processes, specifically by clearly defining the scope of work. Currently, much of the spraying work is done manually, resulting in insufficient accuracy in calculating the scope of work, which hinders effective control. Summary of the Invention

[0005] To address or improve the above problems, this invention provides a method and system for calculating the quantity of tower coating work, the specific technical solution of which is as follows:

[0006] This invention provides a method for calculating the amount of coating work on power poles, comprising: identifying target power poles based on a PowerNet model to obtain power pole parameters; calculating the expected amount of coating work based on the power pole parameters and spraying operation parameters; and measuring the coating thickness on-site to update the expected amount of coating work.

[0007] Preferably, the tower parameters include the tower model, type, and tower area; correspondingly, the step of calculating the expected coating quantity based on the tower parameters and spraying operation parameters includes: determining the spraying standard according to the tower model and / or type; determining the spraying quantity according to the spraying standard and the tower area; and determining the expected coating quantity according to the spraying quantity and unit spraying efficiency.

[0008] Preferably, the spraying standard includes the spraying range, the spraying material, and the spraying thickness; determining the spraying amount based on the spraying standard and the tower area includes: determining the spraying area based on the spraying range, the tower model, and / or the type; and determining the spraying amount based on the spraying area, the spraying material, and the spraying thickness.

[0009] Preferably, the on-site measurement of coating thickness to update the estimated coating work volume includes: identifying the location of the test point on the target tower to determine the corresponding spraying standard; if the coating thickness does not meet the spraying standard, the spraying operation is re-performed in the spraying area corresponding to the test point and the corresponding correction work volume is increased.

[0010] Preferably, the step of re-performing the spraying operation on the spraying area corresponding to the test point and correspondingly increasing the correction work includes: selecting a judgment test point from the spraying area, and determining the area to be re-performed based on the coating thickness corresponding to the judgment test point, so as to correspondingly increase the correction work.

[0011] This invention provides a system for calculating the amount of coating work on power poles, comprising: a first module for identifying target power poles based on a PowerNet model to obtain power pole parameters; a second module for calculating the estimated amount of coating work based on the power pole parameters and spraying operation parameters; and a third module for measuring the coating thickness on-site to update the estimated amount of coating work.

[0012] Preferably, the tower parameters include the tower model, type, and tower area; correspondingly, the step of calculating the expected coating quantity based on the tower parameters and spraying operation parameters includes: determining the spraying standard according to the tower model and / or the type; determining the spraying quantity according to the spraying standard and the tower area; and determining the expected coating quantity according to the spraying quantity and the unit spraying quantity.

[0013] Preferably, the spraying standard includes the spraying range, the spraying material, and the spraying thickness; determining the spraying amount based on the spraying standard and the tower area includes: determining the spraying area based on the spraying range, the tower model, and / or the type; and determining the spraying amount based on the spraying area, the spraying material, and the spraying thickness.

[0014] Preferably, the on-site measurement of coating thickness to update the estimated coating work volume includes: identifying the location of the test point on the target tower to determine the corresponding spraying standard; if the coating thickness does not meet the spraying standard, the spraying operation is re-performed in the spraying area corresponding to the test point and the corresponding correction work volume is increased.

[0015] Preferably, the step of re-performing the spraying operation on the spraying area corresponding to the test point and correspondingly increasing the correction work includes: selecting a judgment test point from the spraying area, and determining the area to be re-performed based on the coating thickness corresponding to the judgment test point, so as to correspondingly increase the correction work.

[0016] The beneficial effects of this invention are as follows: Based on the PowerNet model, target towers are identified to obtain tower parameters, which can accurately identify various parameters of the target towers, facilitating subsequent operations; based on the tower parameters and spraying operation parameters, the expected coating quantity is calculated, yielding the theoretical quantity; on-site measurement of the coating thickness updates the expected coating quantity, allowing for accurate calculation of the quantity in conjunction with actual operational conditions. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of a method for calculating the quantity of tower coating work according to the present invention;

[0018] Figure 2 This is a schematic diagram of a tower coating engineering quantity calculation system according to the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the 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 effort are within the scope of protection of the present invention.

[0020] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0021] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0022] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0023] To address or improve the problems mentioned in the background, the present invention provides, as follows: Figure 1 The method for calculating the amount of coating work on a pole / tower includes: S1, identifying the target pole / tower based on the PowerNet model to obtain the pole / tower parameters; S2, calculating the expected amount of coating work based on the pole / tower parameters and the spraying operation parameters; and S3, measuring the coating thickness on-site to update the expected amount of coating work.

[0024] The tower parameters include the tower model, type, and tower area; correspondingly, the calculation of the expected coating work volume based on the tower parameters and spraying operation parameters includes: determining the spraying standard according to the tower model and / or type; determining the spraying volume according to the spraying standard and the tower area; and determining the expected coating work volume according to the spraying volume and unit spraying efficiency.

[0025] Different types / models of poles may require different coating materials and have different requirements. Furthermore, different poles have different shapes and surface areas; therefore, it is necessary to first analyze the actual situation (type / model).

[0026] In practical work, due to the remote location or low importance of poles, and the slow updating of pole information such as images, workers may not be able to accurately identify target poles. Image recognition can greatly reduce the requirements for pole identification, improve accuracy, and reduce the burden on workers carrying standard documents by establishing standards through recognition, while also preventing workers from cutting corners. Pole area refers to the surface area of ​​the pole. Furthermore, different locations on the pole may require different coatings; therefore, the pole surface area can specifically include the collection of areas from different locations. Unit coating efficiency refers to the efficiency of manual or mechanical operations, such as how many square meters are coated per hour.

[0027] The spraying standard includes the spraying range, spraying material, and spraying thickness; determining the spraying amount based on the spraying standard and the tower area includes: determining the spraying area based on the spraying range, the tower model, and / or the type; and determining the spraying amount based on the spraying area, the spraying material, and the spraying thickness.

[0028] Different models and types of poles may require different materials and locations for coating because the external environment varies at different locations, and the structure and materials of the pole itself may also have different coating requirements. The amount of coating can be equal to the coating area multiplied by the coating thickness.

[0029] The on-site measurement of coating thickness to update the estimated coating work volume includes: identifying the location of the test point on the target tower to determine the corresponding spraying standard; if the coating thickness does not meet the spraying standard, the spraying operation is re-performed in the spraying area corresponding to the test point and the corresponding correction work volume is increased.

[0030] In practice, poor coating results often occur due to manual spraying or contractors cutting corners. To avoid this, test points can be randomly or specifically selected to check the thickness. As mentioned above, the coating standards differ at different locations on the tower, requiring determination based on the test point's location on the target tower. Since this method relies on identification to determine tower information, the PowerNet model can also be used to determine the current test point's location on the tower to obtain the coating standard. This effectively utilizes the existing PowerNet model, reducing costs. Re-performing the spraying will obviously increase workload. Since the exact increase is uncertain, the theoretical workload is used as a correction. Specifically, the area requiring correction is determined, and then the coating standard is determined based on the area's location on the tower. Finally, the area is multiplied by the coating standard to determine the workload of the spraying operation.

[0031] The process of re-spraying the area corresponding to the test point and increasing the corresponding correction work includes: selecting a test point from the spraying area, determining the area to be re-sprayed based on the coating thickness corresponding to the test point, so as to increase the corresponding correction work.

[0032] If the spraying area is large, the spraying time limit is short, or the insufficient spray thickness is accidental, in order to improve the efficiency of the overall spraying operation, additional testing can be performed on the problematic spraying area. The selected test points become the judgment test points. If the thickness at these points is okay, only the area with insufficient thickness needs to be re-sprayed. This area with insufficient thickness mainly refers to the area around the test points.

[0033] This invention provides, for example Figure 2 The system for calculating the amount of coating work on a pole is shown, comprising: a first module 1, used to identify the target pole based on the PowerNet model to obtain the pole parameters; a second module 2, used to calculate the expected amount of coating work based on the pole parameters and the spraying operation parameters; and a third module 3, used to measure the coating thickness on site to update the expected amount of coating work.

[0034] The tower parameters include the tower model, type, and tower area; correspondingly, the calculation of the expected coating work volume based on the tower parameters and spraying operation parameters includes: determining the spraying standard according to the tower model and / or type; determining the spraying amount according to the spraying standard and the tower area; and determining the expected coating work volume according to the spraying amount and the unit spraying amount.

[0035] The spraying standard includes the spraying range, spraying material, and spraying thickness; determining the spraying amount based on the spraying standard and the tower area includes: determining the spraying area based on the spraying range, the tower model, and / or the type; and determining the spraying amount based on the spraying area, the spraying material, and the spraying thickness.

[0036] The on-site measurement of coating thickness to update the estimated coating work volume includes: identifying the location of the test point on the target tower to determine the corresponding spraying standard; if the coating thickness does not meet the spraying standard, the spraying operation is re-performed in the spraying area corresponding to the test point and the corresponding correction work volume is increased.

[0037] The process of re-spraying the area corresponding to the test point and increasing the corresponding correction work includes: selecting a test point from the spraying area, determining the area to be re-sprayed based on the coating thickness corresponding to the test point, so as to increase the corresponding correction work.

[0038] Example

[0039] PowerNet model pole identification method:

[0040] The PowerNet power-specific target detection model consists of three parts: a multi-scale feature extraction module, a context association module, and a relay module. The multi-scale feature extraction module utilizes a deep decomposable network to extract image features, reducing the model's computational cost while maintaining feature extraction quality. It also uses the softmax activation function to initially identify defect types and locations. The context association module fuses shallow and deep features, improving the model's detection accuracy for small-sized defects. The relay module is responsible for deconvolutionalizing deep features into a larger-dimensional feature map, maintaining the same dimensionality as the shallow features, and enabling matrix addition operations.

[0041] The PowerNet object detection model incorporates two key aspects. First, it adopts a two-stage model approach, progressively regressing from coarse to fine image resolution. This involves using a region proposal network to obtain candidate regions of varying sizes, followed by further regression through a conventional regression branch to achieve more precise bounding boxes. This is a major reason why the two-stage model outperforms the single-stage model. Second, it employs a context-aware model, fusing shallow and deep features from aerial images. This preserves details of small defects, reduces information loss and distortion, and effectively improves the detection of small targets.

[0042] (1) Multi-scale feature extraction module

[0043] The PowerNet object detection model constructed by this method uses a feature extraction network based on a residual network (ResNets) model, whose significant feature is the addition of memory channels.

[0044] Residual networks fuse the output information x of the previous layer with the output information of the current layer. Traditional neural networks often suffer from information loss, distortion, or degradation, leading to poor detection results. ResNet networks, however, can directly add some input information to the output, preserving the integrity of the information and simplifying the complexity of model training. A schematic diagram of the ResNet network is shown in the figure.

[0045] This method constructs a deep convolutional neural network as the feature extraction model, setting the stride of the convolutional kernel to 2, thus shrinking the feature map by a factor of 2. As the model depth increases, the semantic expressive power of the features also continuously improves. The feedforward computation of the convolutional neural network follows a bottom-up path, defining a pyramid level for each stage. The feature map is processed by the convolutional kernel, and the output of the last layer of each stage is selected as the reference set for the feature map.

[0046] The feature extraction network of the PowerNet model uses a residual network model (ResNets), the structure of which is shown in Table 1. The feature activation output is used from the last residual structure of each stage. This method represents the outputs of these residual modules as {C2, C3, C4, C5}, corresponding to the outputs of conv2, conv3, conv4, and conv5, respectively, and sets the stride of each layer relative to the input image to {4, 8, 16, 32} pixels.

[0047] Table 1 ResNet Model Architecture

[0048]

[0049]

[0050] Similar to the Region Proposal Network (RPN) in the Faster R-CNN algorithm, the multi-scale feature extraction model in PowerNet can extract 300 target candidate regions and eliminate some negative samples, i.e., background information. Therefore, the final feature map of the convolutional network in the multi-scale feature extraction model splits into two branches: one branch is used to locate the coordinates of detection boxes for potential external damage to the distribution network, and the other branch is used to classify the fault type of the external damage within the detection boxes. Since the purpose of the RPN network in the Faster R-CNN algorithm is to generate image region information, these candidate regions provide good initial information for subsequent detection networks. This is a key difference between object detection algorithms based on integrated convolutional neural networks and those based on region proposal strategies.

[0051] Although PowerNet's multi-scale feature extraction module essentially plays a similar role to the region proposal policy network, the difference between PowerNet and the region proposal policy network in the Faster R-CNN model is that PowerNet uses features from multiple layers of feature maps, while the input to the region proposal policy network in the Faster R-CNN model is a single layer of features.

[0052] (2) Relay Module

[0053] Since the dimensions of shallow and deep feature maps are different, in order to ensure that the shallow and deep feature maps can perform matrix addition operations and realize the fusion of context information, i.e., shallow and deep feature maps, and in order to reduce information loss, PowerNet uses deconvolution instead of upsampling.

[0054] Convolution and deconvolution operations are essentially opposite. Assuming the input feature map of a convolutional layer is i×i, the kernel size is k×k, the kernel stride is s, and the padding in each dimension is p, then the output feature map is o×o, where:

[0055]

[0056] Similarly, deconvolution performs a similar operation, but the computation direction is opposite to that of convolution. Assuming the input feature map of the deconvolution layer is i′×i′, the kernel size is k′×k′, the kernel stride is s′, and the padding in each dimension is p′, then the output feature map is o′×o′, where:

[0057] o′=i′-k′+2p′+1=i′+(k-1)-2p (2)

[0058] In summary, the relay module performs feature map transformation operations, that is, it transforms the output feature map of the multi-scale feature extraction module into the input of the context association module.

[0059] (3) Context association module

[0060] The context association module fuses features from different layers, and then classifies and locates objects based on the fused feature map. The input to the context association module consists of two parts: one is the target candidate region from the multi-scale feature extraction module, and the other is the fused feature map obtained through context association. Pyramid models often employ a top-down feature extraction path, upsampling more abstract and semantically stronger high-level feature maps and then horizontally connecting these features to the previous layer, thus strengthening the high-level features. Since pixel calculations are involved between different layers, the two horizontally connected layers must first be converted to the same size before feature fusion. Because the detailed information from the lower layers and the semantic information from the higher layers are fused, detailed localization information for objects of different sizes can be obtained. Compared to the classic feature pyramid model, the proposed model performs better for pole detection.

[0061] The thickness of the coating can be determined using the eddy current method.

[0062] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of each example have been generally described in terms of function in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0063] In the embodiments provided in this application, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for calculating the quantity of tower coating work, characterized in that, include: Target towers were identified and tower parameters were obtained based on the PowerNet model; Based on the tower parameters and spraying operation parameters, the estimated coating work volume is calculated; On-site measurement of coating thickness to update the estimated coating work volume; The tower parameters include tower model, type, and tower area; Correspondingly, the calculation of the estimated coating workload based on the tower parameters and spraying operation parameters includes: The coating standard shall be determined based on the tower model and / or the type. The amount of coating to be applied is determined based on the coating standard and the tower area. The estimated coating workload is determined based on the spraying volume and unit spraying efficiency. The spraying standards include the spraying range, spraying material, and spraying thickness; The process of determining the coating quantity based on the coating standard and the tower area includes: The spraying area is determined based on the spraying range, the tower model, and / or the type. The amount of coating is determined based on the coating area, the coating material, and the coating thickness.

2. The method for calculating the quantity of tower coating work according to claim 1, characterized in that, The on-site measurement of coating thickness to update the estimated coating work volume includes: Identify the location of the test point on the target tower to determine the corresponding coating standard; If the coating thickness does not meet the spraying standard, the spraying operation will be re-executed in the spraying area corresponding to the test point, and the corresponding correction work will be increased.

3. The method for calculating the quantity of tower coating work according to claim 2, characterized in that, The spraying operation is then re-executed on the sprayed area corresponding to the test point, and the corresponding correction work is increased, including: Select a test point from the sprayed area, and determine the area to be re-sprayed based on the coating thickness corresponding to the test point, so as to increase the amount of correction work accordingly.

4. A system for calculating the quantity of tower coating work, characterized in that, include: The first module is used to identify target towers and obtain tower parameters based on the PowerNet model. The second module is used to calculate the expected amount of coating work based on the tower parameters and spraying operation parameters; The third module is used for on-site measurement of coating thickness to update the estimated coating work volume. The tower parameters include tower model, type, and tower area; Correspondingly, the calculation of the estimated coating workload based on the tower parameters and spraying operation parameters includes: The coating standard shall be determined based on the tower model and / or the type. The amount of coating to be applied is determined based on the coating standard and the tower area. The estimated coating work volume is determined based on the spraying volume and the unit spraying volume; The spraying standards include the spraying range, spraying material, and spraying thickness; The process of determining the coating quantity based on the coating standard and the tower area includes: The spraying area is determined based on the spraying range, the tower model, and / or the type. The amount of coating is determined based on the coating area, the coating material, and the coating thickness.

5. The tower coating engineering quantity calculation system according to claim 4, characterized in that, The on-site measurement of coating thickness to update the estimated coating work volume includes: Identify the location of the test point on the target tower to determine the corresponding coating standard; If the coating thickness does not meet the spraying standard, the spraying operation will be re-executed in the spraying area corresponding to the test point, and the corresponding correction work will be increased.

6. The tower coating engineering quantity calculation system according to claim 5, characterized in that, The spraying operation is then re-executed on the sprayed area corresponding to the test point, and the corresponding correction work is increased, including: Select a test point from the sprayed area, and determine the area to be re-sprayed based on the coating thickness corresponding to the test point, so as to increase the amount of correction work accordingly.

Images