Cable margin management method and related device

Abstract

The invention belongs to the field of electric power material management, and discloses a cable margin management method and a related device, and the method comprises the steps: obtaining the feature data of a cable reel at a plurality of continuous collection moments, including the rotation angular velocity, the driving voltage of a winder and the cable winding and unwinding length; generating a cable change dynamic image at each acquisition moment based on the feature data; calling a pre-trained cable reel type discrimination model to analyze the dynamic image sequence, and automatically identifying the type of the cable reel; and finally, by combining the current weight of the cable reel, the collected weight data, the identified cable reel type and the cable winding and unwinding length, the accurate real-time cable allowance is calculated. According to the method, through a multi-source data fusion and visual analysis technology, automatic identification of the type of the cable reel and dynamic perception of the remaining amount are realized, the cable checking efficiency and the management level are remarkably improved, and effective data support is provided for accurate management and timely supply of electric power materials.

Description

Technical Field

[0001] This invention belongs to the field of power material management and relates to a method and related device for cable surplus management. Background Technology

[0002] With the accelerated development of green, modern, and intelligent supply chains, the refined management of power materials is increasingly becoming a core demand and basic requirement for power warehouse operations. Cables, as the most critical and representative material category, directly impact the green, efficient, and safe level of the entire supply chain through their management effectiveness. Cables are indispensable arteries in the power system, characterized by large reserves, high daily consumption, and a wide variety of models and specifications. This leads to numerous challenges in cable management during actual warehousing and requisition processes.

[0003] Currently, the core pain point in cable management lies in the lack of convenient and efficient inventory counting methods. Because it's impossible to accurately determine the length of cables in their coiled state visually, warehouse managers struggle to grasp inventory levels in real time and accurately, leading to delayed inventory data updates and compromised accuracy. In actual requisitioning, discrepancies frequently arise between estimated and actual usable lengths, resulting in frequent issues such as insufficient cable reserves or over-requisition. This not only affects on-site work progress, forcing staff to repeatedly travel to the warehouse for requisition or returns, causing a double waste of manpower and time, but may also lead to project delays and increased unnecessary operating costs. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a cable margin management method and related apparatus.

[0005] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, the present invention provides a cable surplus management method, comprising: acquiring feature data of a cable reel at several consecutive acquisition times; wherein the feature data includes rotational angular velocity, reel drive voltage, and cable winding / unwinding length; generating a dynamic image of cable changes at several consecutive acquisition times based on the feature data of the cable reel; calling a pre-trained cable reel type discrimination model to obtain the type of the cable reel based on the dynamic image of cable changes at several consecutive acquisition times; acquiring the current weight of the cable reel and the weight at several consecutive acquisition times, and combining the type of the cable reel and the cable winding / unwinding length at several consecutive acquisition times to obtain the cable surplus of the cable reel.

[0006] Optionally, generating dynamic images of cable changes at several consecutive acquisition times of the cable reel includes obtaining the normalized reel drive voltage at each acquisition time using the following formula. :

[0007] in, The rotational angular velocity of the cable reel. The maximum angular velocity of the cable reel. This is the drive voltage for the cable reel's winding mechanism.

[0008] Using the normalized winding drive voltage at the current acquisition moment as... The standard deviation of the dimensional data and the length of the take-up and take-up cable at the current acquisition time are: The standard deviation of the dimensional data, 0 is Dimensional data and The average value of the dimensional data and 0 as Dimensional data and The correlation coefficient of the dimensional data is used to generate two-dimensional normal distribution data at the current acquisition time; based on the two-dimensional normal distribution data at the current acquisition time, a dynamic image of cable changes at the current acquisition time is drawn; wherein, the color of the dynamic image of cable changes is determined based on the probability density of the two-dimensional normal distribution data.

[0009] Optionally, the cable reel type discrimination model is constructed based on the fusion of convolutional neural networks and long short-term memory networks.

[0010] Optionally, the cable reel type discrimination model includes a convolutional neural network, a long short-term memory network, an attention layer, a fully connected layer, a random dropout layer, and a normalized exponential function layer connected in sequence.

[0011] Optionally, obtaining the current weight of the cable reel and the weight at several consecutive sampling times, combined with the type of the cable reel and the cable length at several consecutive sampling times, to obtain the cable allowance of the cable reel includes: obtaining the cable allowance of the cable reel using the following formula:

[0012] in, This represents the remaining cable length on the cable reel. This represents the total length of the take-up and extendable cables over several consecutive data acquisition points. This represents the total weight change of the cable reel over several consecutive data collection points. Current weight of the cable reel The weight of the cable reel is determined based on the type of cable reel.

[0013] In a second aspect, the present invention provides a cable slack management device, comprising: a data acquisition module for acquiring feature data of a cable reel at several consecutive acquisition times; wherein the feature data includes rotational angular velocity, reel drive voltage, and cable winding / unwinding length; an image processing module for generating dynamic images of cable changes at several consecutive acquisition times based on the feature data of the cable reel; a type discrimination module for calling a pre-trained cable reel type discrimination model to obtain the type of the cable reel based on the dynamic images of cable changes at several consecutive acquisition times; and a slack calculation module for acquiring the current weight of the cable reel and the weight at several consecutive acquisition times, and combining the type of the cable reel with the cable winding / unwinding length at several consecutive acquisition times to obtain the cable slack of the cable reel.

[0014] Optionally, generating dynamic images of cable changes at several consecutive acquisition times of the cable reel includes obtaining the normalized reel drive voltage at each acquisition time using the following formula. :

[0015] in, The rotational angular velocity of the cable reel. The maximum angular velocity of the cable reel. This is the drive voltage for the cable reel's winding mechanism.

[0016] Using the normalized winding drive voltage at the current acquisition moment as... The standard deviation of the dimensional data and the length of the take-up and take-up cable at the current acquisition time are: The standard deviation of the dimensional data, 0 is Dimensional data and The average value of the dimensional data and 0 as Dimensional data and The correlation coefficient of the dimensional data is used to generate two-dimensional normal distribution data at the current acquisition time; based on the two-dimensional normal distribution data at the current acquisition time, a dynamic image of cable changes at the current acquisition time is drawn; wherein, the color of the dynamic image of cable changes is determined based on the probability density of the two-dimensional normal distribution data.

[0017] Optionally, the cable reel type discrimination model is constructed based on the fusion of convolutional neural networks and long short-term memory networks.

[0018] Optionally, the cable reel type discrimination model includes a convolutional neural network, a long short-term memory network, an attention layer, a fully connected layer, a random dropout layer, and a normalized exponential function layer connected in sequence.

[0019] Optionally, obtaining the current weight of the cable reel and the weight at several consecutive sampling times, combined with the type of the cable reel and the cable length at several consecutive sampling times, to obtain the cable allowance of the cable reel includes: obtaining the cable allowance of the cable reel using the following formula:

[0020] in, This represents the remaining cable length on the cable reel. This represents the total length of the take-up and extendable cables over several consecutive data acquisition points. This represents the total weight change of the cable reel over several consecutive data collection points. Current weight of the cable reel The weight of the cable reel is determined based on the type of cable reel.

[0021] In a third aspect, the present invention provides a cable slack management system, comprising a first cable reel, a weighing device, and a cable length measuring device; the first cable reel is used to mount a cable reel and drive the cable reel to rotate; the weighing device is disposed below the first cable reel and is used to weigh the weight of the cable reel mounted on the first cable reel; the cable length measuring device is used to measure the length of cable winding and unwinding when the cable reel rotates; wherein, the motor of the first cable reel is a voltage-regulated motor.

[0022] Optionally, the cable length measuring device includes a guide wheel and a counter; the guide wheel is axially and evenly provided with a plurality of trigger marks for triggering the counter to count, and the guide wheel is used to guide the cable reel to rotate when winding and unwinding the cable; the detection end of the counter is positioned toward the trigger mark setting area of ​​the guide wheel.

[0023] Optionally, a second cable reel is also included, which is used to mount the take-up reel and drive the take-up reel to rotate so as to take the cable from the cable reel via the cable length measuring device or to attach the cable reel to the cable reel via the cable length measuring device.

[0024] Optionally, the aforementioned cable slack management device may also be included.

[0025] In a fourth aspect, the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described cable margin management method.

[0026] In a fifth aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described cable margin management method.

[0027] Compared with the prior art, the present invention has the following beneficial effects: This invention relates to a cable surplus management method. It acquires feature data from a cable reel over several consecutive acquisition times, constructs dynamic images of cable changes over these times, and then uses a pre-trained cable reel type discrimination model to identify the type of cable reel based on the features of each dynamic image. This achieves automated and accurate identification of the cable reel type. Finally, based on the current weight of the cable reel, the weight over several consecutive acquisition times, the cable reel type, and the cable length during those acquisition times, the cable surplus is calculated. This method enables refined and real-time dynamic sensing of cable surplus, allowing for rapid confirmation of cable surplus during cable handling, effectively improving cable length inventory efficiency, and promptly identifying insufficient cable surplus, providing data support for advance planning. Attached Figure Description

[0028] Figure 1 This is a flowchart of the cable margin management method according to an embodiment of the present invention.

[0029] Figure 2 This is a schematic diagram illustrating a dynamic image example of cable changes according to an embodiment of the present invention.

[0030] Figure 3 This is a structural block diagram of a cable margin management device according to an embodiment of the present invention.

[0031] Figure 4 This is a schematic diagram of the cable margin management system according to an embodiment of the present invention.

[0032] Figure 5 This is a schematic diagram of the line length measuring device according to an embodiment of the present invention.

[0033] Figure 6 This is a schematic diagram of another cable margin management system according to an embodiment of the present invention.

[0034] Among them, 1-first winding device; 2-weighing device; 3-line length measuring device; 31-guide wheel; 32-counter; 4-second winding device. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0037] The present invention will now be described in further detail with reference to the accompanying drawings: See Figure 1 In one embodiment of the present invention, a cable surplus management method is provided, which can quickly complete the cable surplus inventory during the cable retrieval process, improve inventory efficiency, and promptly detect insufficient surplus.

[0038] Specifically, the cable margin management method of the present invention includes the following steps: S1: Acquire feature data of the cable reel at several consecutive acquisition times; wherein, the feature data includes rotational angular velocity, reel drive voltage, and cable winding / unwinding length.

[0039] S2: Based on the feature data of the cable reel at several consecutive acquisition times, generate dynamic images of cable changes at several consecutive acquisition times of the cable reel.

[0040] S3: Based on the dynamic images of cable changes at several consecutive acquisition times of the cable reel, call the pre-trained cable reel type discrimination model to obtain the type of the cable reel.

[0041] S4: Obtain the current weight of the cable reel and the weight at several consecutive sampling times. Combine the cable reel type and the cable length at several consecutive sampling times to obtain the cable reel's remaining cable capacity.

[0042] This invention relates to a cable surplus management method. It acquires feature data from a cable reel over several consecutive acquisition times, constructs dynamic images of cable changes over these times, and then uses a pre-trained cable reel type discrimination model to identify the type of cable reel based on the features of each dynamic image. This achieves automated and accurate identification of the cable reel type. Finally, based on the current weight of the cable reel, the weight over several consecutive acquisition times, the cable reel type, and the cable length during those acquisition times, the cable surplus is calculated. This method enables refined and real-time dynamic sensing of cable surplus, allowing for rapid confirmation of cable surplus during cable handling, effectively improving cable length inventory efficiency, and promptly identifying insufficient cable surplus, providing data support for advance planning.

[0043] Explanatoryly, in this invention, the weight of the cable reel refers to the sum of the reel's weight and the weight of the cable it carries.

[0044] Explanatory methods that rely solely on static appearance features (such as size and nameplate) to determine cable reel type are susceptible to contamination, obstruction, or visual errors, and require manual intervention, making automated identification impossible.

[0045] This invention first generates dynamic images of cable changes at several consecutive acquisition times based on the feature data of the cable reel, thereby achieving the fusion of different feature data. Then, based on the dynamic images of cable changes at several consecutive acquisition times, the cable reel type is identified, which effectively improves the accuracy of cable reel type identification and provides a basis for accurate cable margin calculation.

[0046] In one possible implementation, generating dynamic images of cable changes at several consecutive acquisition times of the cable reel includes: obtaining the normalized reel drive voltage at each acquisition time using the following formula. :

[0047] in, The rotational angular velocity of the cable reel. The maximum angular velocity of the cable reel. This is the drive voltage for the cable reel's winding mechanism.

[0048] Using the normalized winding drive voltage at the current acquisition moment as... The standard deviation of the dimensional data and the length of the take-up and take-up cable at the current acquisition time are: The standard deviation of the dimensional data, 0 is Dimensional data and The average value of the dimensional data and 0 as Dimensional data and The correlation coefficients of the dimensional data are used to generate two-dimensional normally distributed data at the current acquisition time.

[0049] Based on the two-dimensional normal distribution data at the current acquisition time, a dynamic image of cable changes at the current acquisition time is drawn; wherein, the color of the dynamic image of cable changes is determined based on the probability density of the two-dimensional normal distribution data.

[0050] Explaining this, the rotational angular velocity, reel drive voltage, and cable winding / unwinding length of different cable reels change during operation as the cable is wound and unwound. Therefore, the type of cable reel can be determined by analyzing the characteristic data of the cable reel at several consecutive sampling moments, namely the rotational angular velocity, reel drive voltage, and cable winding / unwinding length at several consecutive sampling moments. To analyze the characteristic data of the cable reel at several consecutive sampling moments, this embodiment uses visualized images to fuse these characteristic data to obtain a dynamic image of cable changes, and then performs analysis based on this dynamic image of cable changes.

[0051] Specifically, before feature data fusion, the cable reel drive voltage is normalized. During normalization, the ratio of the cable reel's rotational angular velocity to its maximum rotational angular velocity is used as the normalization standard. This ensures that the normalized cable reel drive voltage reflects the voltage intensity under actual operating conditions, rather than simply a control signal value, thus establishing a correlation between the cable reel's rotational angular velocity and the cable reel drive voltage.

[0052] For example, in the visualization stage, a two-dimensional normal distribution data is constructed based on the normalized reel drive voltage and the length of the cable winding and unwinding. Based on the two-dimensional normal distribution data, Matlab or other plotting tools can be used to visualize and transform the two-dimensional normal distribution data to form a dynamic image of cable changes.

[0053] Specifically, in the dynamic image of cable changes, the color of each pixel is determined based on the probability density of two-dimensional normal distribution data, where the probability density of the two-dimensional normal distribution data can be obtained by the following formula:

[0054] in, Two-dimensional normal distribution data The probability density, for Standard deviation of dimensional data for Standard deviation of dimensional data for The average value of the dimensional data. for The average value of the dimensional data.

[0055] For example, when determining the color of each pixel based on the probability density of two-dimensional normal distribution data, this can be achieved using a pre-defined probability density color correspondence table. Generally, as the probability density increases, the color of the corresponding pixel is designed to be brighter. (See [reference needed]). Figure 2 The image shows a possible dynamic picture of cable changes, where the probability density increases sequentially from blue to yellow.

[0056] In one possible implementation, the cable reel type discrimination model is constructed based on a fusion of convolutional neural networks and long short-term memory networks.

[0057] For interpreting dynamic images of cable changes at several consecutive acquisition times of a cable reel, in order to incorporate both image features and temporal variation features into the reasoning process, a fusion of convolutional neural networks and long short-term memory networks is adopted. The spatial features of the dynamic images of cable changes are extracted by the convolutional neural network, and the temporal dependence features of the dynamic images of cable changes at multiple acquisition times are learned by the long short-term memory network.

[0058] For example, during the pre-training process of the cable reel type discrimination model, it is necessary to collect feature data of various cable reels and construct corresponding dynamic images of cable changes for training. This helps the model learn the correlation between the rotational angular velocity of the cable reel, the control voltage of the reel, and the length of cable winding and unwinding during training, so that the model can accurately determine the type of cable reel based on the dynamic images of cable changes.

[0059] In one possible implementation, the cable reel type discrimination model includes a convolutional neural network, a long short-term memory network, an attention layer, a fully connected layer, a random dropout layer, and a normalized exponential function layer connected in sequence.

[0060] The attention layer is used to weight the time steps so that the model focuses more on the key moments with stronger discriminative power; the fully connected layer is used to non-linearly combine all the integrated high-level features to prepare for the final classification; the random dropout layer is used to randomly block some neurons during training to prevent the model from overfitting to the training data; and the normalized exponential function layer is used to transform the output into a probability distribution to determine the most likely type of cable reel.

[0061] For example, in this embodiment, MobileNetV2 can be used for the convolutional neural network.

[0062] In one possible implementation, obtaining the current weight of the cable reel and the weight at several consecutive sampling times, combined with the type of the cable reel and the cable length at several consecutive sampling times, to obtain the cable allowance of the cable reel includes: obtaining the cable allowance of the cable reel using the following formula:

[0063] in, This represents the remaining cable length on the cable reel. This represents the total length of the take-up and extendable cables over several consecutive data acquisition points. This represents the total weight change of the cable reel over several consecutive data collection points. Current weight of the cable reel The weight of the cable reel is determined based on the type of cable reel.

[0064] For example, when calculating the cable allowance of a cable reel, the above method is used... The weight of a cable per unit length can also be calculated using the concept of averaging, through E( The weight of a cable per unit length is calculated using the method described above. Where E( ) for all The mean, For the first i The length of the take-up and take-up cable at each acquisition time. For cable reel number i The weight change at each acquisition time.

[0065] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not disclosed in the apparatus embodiments, please refer to the embodiments of the method of the present invention.

[0066] See Figure 3 In another embodiment of the present invention, a cable margin management device is provided, which can be used to implement the above-mentioned cable margin management method. Specifically, the cable margin management device includes a data acquisition module, an image processing module, a type identification module, and a margin calculation module.

[0067] The data acquisition module is used to acquire feature data of the cable reel at several consecutive acquisition times. The feature data includes rotational angular velocity, reel drive voltage, and cable winding / unwinding length. The image processing module is used to generate dynamic images of cable changes at several consecutive acquisition times based on the feature data of the cable reel. The type discrimination module is used to call a pre-trained cable reel type discrimination model to obtain the type of the cable reel based on the dynamic images of cable changes at several consecutive acquisition times. The remaining weight calculation module is used to acquire the current weight of the cable reel and the weight at several consecutive acquisition times, and combine the cable type of the cable reel with the cable winding / unwinding length at several consecutive acquisition times to obtain the remaining cable weight of the cable reel.

[0068] In one possible implementation, generating dynamic images of cable changes at several consecutive acquisition times of the cable reel includes: obtaining the normalized reel drive voltage at each acquisition time using the following formula. :

[0069] in, The rotational angular velocity of the cable reel. The maximum angular velocity of the cable reel. This is the drive voltage for the cable reel's winding mechanism.

[0070] Using the normalized winding drive voltage at the current acquisition moment as... The standard deviation of the dimensional data and the length of the take-up and take-up cable at the current acquisition time are: The standard deviation of the dimensional data, 0 is Dimensional data and The average value of the dimensional data and 0 as Dimensional data and The correlation coefficient of the dimensional data is used to generate two-dimensional normal distribution data at the current acquisition time; based on the two-dimensional normal distribution data at the current acquisition time, a dynamic image of cable changes at the current acquisition time is drawn; wherein, the color of the dynamic image of cable changes is determined based on the probability density of the two-dimensional normal distribution data.

[0071] In one possible implementation, the cable reel type discrimination model is constructed based on a fusion of convolutional neural networks and long short-term memory networks.

[0072] In one possible implementation, the cable reel type discrimination model includes a convolutional neural network, a long short-term memory network, an attention layer, a fully connected layer, a random dropout layer, and a normalized exponential function layer connected in sequence.

[0073] In one possible implementation, obtaining the current weight of the cable reel and the weight at several consecutive sampling times, combined with the type of the cable reel and the cable length at several consecutive sampling times, to obtain the cable allowance of the cable reel includes: obtaining the cable allowance of the cable reel using the following formula:

[0074] in, This represents the remaining cable length on the cable reel. This represents the total length of the take-up and extendable cables over several consecutive data acquisition points. This represents the total weight change of the cable reel over several consecutive data collection points. Current weight of the cable reel The weight of the cable reel is determined based on the type of cable reel.

[0075] All relevant content of each step involved in the aforementioned embodiments of the cable margin management method can be referenced to the functional description of the corresponding functional module of the cable margin management device in the embodiments of the present invention, and will not be repeated here.

[0076] The module division in this embodiment of the invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0077] See Figure 4 In another embodiment of the present invention, a cable surplus management system is provided, which can support the above-mentioned cable surplus management method. Specifically, the cable surplus management system of the present invention includes a first cable reel 1, a weighing device 2, and a cable length measuring device 3; the first cable reel 1 is used to hang the cable reel and drive the cable reel to rotate; the weighing device 2 is located below the first cable reel 1 and is used to weigh the weight of the cable reel hanging on the first cable reel 1; the cable length measuring device 3 is used to measure the length of cable winding and unwinding when the cable reel rotates; wherein, the motor of the first cable reel 1 is a voltage-regulated motor.

[0078] The cable surplus management system of this invention can support the implementation of the above-mentioned cable surplus management method. Specifically, the weighing device 2 can collect the weight of the cable reel in real time, the cable length measuring device 3 can collect the cable winding and unwinding length in real time, and the motor of the first winding machine 1 is a voltage-controlled speed motor, which can collect the winding drive voltage of the first winding machine 1 in real time. In addition, the rotational angular velocity of the cable reel can be synchronously obtained through the rotational angular velocity of the first winding machine 1, and the two rotational angular velocities are the same.

[0079] Explanatoryly, the cable surplus management system of the present invention can also realize cable reel quantity management. For example, the total length of the cable on the cable reel can be obtained by taking all the cables on the cable reel and using the cable length measuring device 3; or, after the cables are reeled onto the cable reel, the total length of the cables from the reel to the cable reel can be obtained by the cable length measuring device 3 for subsequent storage management.

[0080] See Figure 5 In one possible implementation, the cable length measuring device 3 includes a guide wheel 31 and a counter 32; the guide wheel 31 is axially and evenly provided with a plurality of trigger marks for triggering the counter 32 to count, and the guide wheel 31 is used to guide the cable reel to rotate when winding and unwinding the cable; the detection end of the counter 32 is positioned toward the trigger mark setting area of ​​the guide wheel 31.

[0081] Explanatoryly, the cable length measuring device 3 cleverly utilizes the guide wheel 31 to achieve measurement. The guide wheel 31 can guide the cable to be picked up and put down on the cable reel more effectively. Furthermore, by triggering the counter 32 through the trigger mark on the guide wheel 31, the angle through which the guide wheel 31 has rotated can be easily obtained. Based on this angle and the radius parameter of the guide wheel 31, the length of the cable can be calculated.

[0082] For example, counter 32 can be an infrared counter.

[0083] See Figure 6 In one possible implementation, the cable slack management system further includes a second cable reel 4, which is used to mount a take-up reel and drive the take-up reel to rotate so as to take the cable from the cable reel via the cable length measuring device 3 or to attach the cable reel to the cable reel via the cable length measuring device 3.

[0084] Explained, by setting the second cable reel 4 to work in conjunction with the first cable reel 1, the cable reeling process can be automated. For example, the motor of the second cable reel 4 is also a voltage-controlled speed motor, which can maintain the stability of the rotation speed of the cable reel and the take-up reel by dynamically controlling the voltage, thereby ensuring stable tension and uniform speed when picking up and putting down the cable. This makes the length data collected by the cable length measuring device 3 and the weight data collected by the weighing device 2 more accurate and reliable.

[0085] In one possible implementation, the cable margin management system further includes the aforementioned cable margin management device, thereby enabling real-time dynamic calculation of cable margin based on the cable margin management device.

[0086] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used for the operation of a cable margin management method.

[0087] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory). This computer-readable storage medium is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space containing the terminal's operating system. Furthermore, this storage space also contains one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs including program code. It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the cable margin management method in the above embodiments.

[0088] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code, including but not limited to disk storage, CD-ROM, optical storage, etc.

[0089] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus systems, and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0090] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0091] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0092] 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 it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for managing cable margin, characterized in that, include: Acquire feature data of the cable reel at several consecutive acquisition times; wherein, the feature data includes rotational angular velocity, reel drive voltage, and cable winding / unwinding length; Based on the feature data of the cable reel at several consecutive acquisition times, a dynamic image of cable changes at several consecutive acquisition times is generated. Based on the dynamic images of cable changes at several consecutive acquisition times of the cable reel, a pre-trained cable reel type discrimination model is called to obtain the type of the cable reel; The current weight of the cable reel and the weight at several consecutive sampling times are obtained. Combined with the type of cable reel and the length of cable winding and unwinding at several consecutive sampling times, the cable allowance of the cable reel is obtained.

2. The cable margin management method according to claim 1, characterized in that, The generated dynamic images of cable changes at several consecutive acquisition times of the cable reel include: The normalized winding drive voltage at each acquisition moment is obtained by the following formula. : in, The rotational angular velocity of the cable reel. The maximum angular velocity of the cable reel. The drive voltage for the cable reel's winding mechanism; Using the normalized winding drive voltage at the current acquisition moment as... The standard deviation of the dimensional data and the length of the take-up and take-up cable at the current acquisition time are: The standard deviation of the dimensional data, 0 is Dimensional data and The average value of the dimensional data and 0 as Dimensional data and The correlation coefficients of the dimensional data are used to generate two-dimensional normally distributed data at the current acquisition time; Based on the two-dimensional normal distribution data at the current acquisition time, a dynamic image of cable changes at the current acquisition time is drawn; wherein, the color of the dynamic image of cable changes is determined based on the probability density of the two-dimensional normal distribution data.

3. The cable margin management method according to claim 1, characterized in that, The cable reel type discrimination model is constructed based on the fusion of convolutional neural network and long short-term memory network.

4. The cable margin management method according to claim 3, characterized in that, The cable reel type discrimination model includes a convolutional neural network, a long short-term memory network, an attention layer, a fully connected layer, a random dropout layer, and a normalized exponential function layer connected in sequence.

5. The cable margin management method according to claim 1, characterized in that, The process of obtaining the current weight of the cable reel and the weight at several consecutive sampling times, combined with the type of cable reel and the cable length at several consecutive sampling times, yields the cable allowance of the cable reel, including: The cable allowance of the cable reel can be obtained using the following formula: in, This represents the remaining cable length on the cable reel. This represents the total length of the take-up and extendable cables over several consecutive data acquisition points. This represents the total weight change of the cable reel over several consecutive data collection points. Current weight of the cable reel The weight of the cable reel is determined based on the type of cable reel.

6. A cable margin management device, characterized in that, include: The data acquisition module is used to acquire characteristic data of the cable reel at several consecutive acquisition times; wherein, the characteristic data includes rotational angular velocity, reel drive voltage, and cable winding and unwinding length; The image module is used to generate dynamic images of cable changes at several consecutive acquisition times of the cable reel based on the feature data of the cable reel at several consecutive acquisition times. The type discrimination module is used to call a pre-trained cable reel type discrimination model to obtain the type of the cable reel based on the dynamic images of cable changes at several consecutive acquisition times. The margin calculation module is used to obtain the current weight of the cable reel and the weight at several consecutive sampling times. Combined with the type of cable reel and the cable length at several consecutive sampling times, the cable margin of the cable reel is obtained.

7. The cable margin management device according to claim 6, characterized in that, The generated dynamic images of cable changes at several consecutive acquisition times of the cable reel include: The normalized winding drive voltage at each acquisition moment is obtained by the following formula. : in, The rotational angular velocity of the cable reel. The maximum angular velocity of the cable reel. The drive voltage for the cable reel's winding mechanism; Using the normalized winding drive voltage at the current acquisition moment as... The standard deviation of the dimensional data and the length of the take-up and take-up cable at the current acquisition time are: The standard deviation of the dimensional data, 0 is Dimensional data and The average value of the dimensional data and 0 as Dimensional data and The correlation coefficients of the dimensional data are used to generate two-dimensional normally distributed data at the current acquisition time; Based on the two-dimensional normal distribution data at the current acquisition time, a dynamic image of cable changes at the current acquisition time is drawn; wherein, the color of the dynamic image of cable changes is determined based on the probability density of the two-dimensional normal distribution data.

8. The cable margin management device according to claim 6, characterized in that, The cable reel type discrimination model is constructed based on the fusion of convolutional neural network and long short-term memory network.

9. The cable margin management method according to claim 8, characterized in that, The cable reel type discrimination model includes a convolutional neural network, a long short-term memory network, an attention layer, a fully connected layer, a random dropout layer, and a normalized exponential function layer connected in sequence.

10. The cable margin management device according to claim 6, characterized in that, The process of obtaining the current weight of the cable reel and the weight at several consecutive sampling times, combined with the type of cable reel and the cable length at several consecutive sampling times, yields the cable allowance of the cable reel, including: The cable allowance of the cable reel can be obtained using the following formula: in, This represents the remaining cable length on the cable reel. This represents the total length of the take-up and extendable cables over several consecutive data acquisition points. This represents the total weight change of the cable reel over several consecutive data collection points. Current weight of the cable reel The weight of the cable reel is determined based on the type of cable reel.

11. A cable margin management system, characterized in that, It includes a first reel (1), a weighing device (2), and a line length measuring device (3); The first reel (1) is used to hang the cable reel and drive the cable reel to rotate; Weighing device (2) is located below the first reel (1) and is used to weigh the weight of the cable reel hanging on the first reel (1); The cable length measuring device (3) is used to measure the length of cable winding and unwinding when the cable reel rotates; Among them, the motor of the first winding device (1) is a voltage-regulated motor.

12. The cable margin management system according to claim 11, characterized in that, The line length measuring device (3) includes a guide wheel (31) and a counter (32); The guide wheel (31) is evenly provided with several trigger marks for triggering the counter (32) to count. The guide wheel (31) is used to guide the cable reel to rotate and retract the cable. The detection end of the counter (32) is set to the trigger mark setting area of ​​the guide wheel (31).

13. The cable margin management system according to claim 11, characterized in that, It also includes a second cable reel (4), which is used to mount the take-up reel and drive the take-up reel to rotate so as to take the cable from the cable reel by means of the cable length measuring device (3) or to transfer the cable reel to the cable reel by means of the cable length measuring device (3).

14. The cable margin management system according to claim 11, characterized in that, It also includes the cable balance management device as described in any one of claims 6 to 10.

15. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the cable margin management method as described in any one of claims 1 to 5.

16. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the cable margin management method as described in any one of claims 1 to 5.

Images