Electric power optical cable ground-air intelligent laying all-in-one machine and electric power optical cable laying method

Abstract

The invention belongs to the technical field of power construction equipment, and particularly relates to a power optical cable ground-air intelligent laying all-in-one machine and a power optical cable laying method. The electric power optical cable ground-air intelligent laying all-in-one machine comprises an optical cable intelligent laying machine, a threading apparatus and a traction medium unreeling machine, the traction medium unreeling machine is connected with the threading apparatus through a fixing hook, an electric power optical cable to be laid is arranged in the threading apparatus, the electric power optical cable is connected with the optical cable intelligent laying machine, and the traction medium unreeling machine is connected with the optical cable intelligent laying machine. The head end and the tail end of the intelligent optical cable laying machine are respectively provided with an upper limiting wheel and a lower limiting wheel, and the power optical cable passes through the upper limiting wheels and the lower limiting wheels. According to the invention, the BP neural network is adopted to predict the optimal traction torque and traction speed of power optical cable laying under the current working condition, laying parameters can be automatically adjusted in the optimal interval, over-traction of an all-dielectric self-supporting optical cable and a common cable is avoided, the labor intensity of field operators is reduced, and the intrinsic safety of power optical cable operation is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power construction equipment, and specifically relates to an integrated ground-to-air intelligent laying machine for electric optical cables and a method for laying electric optical cables. Background Art

[0002] With the continuous improvement of the construction goals of new power systems, the scale and quality requirements of power grid construction are increasing. Traditional power grid construction methods have many shortcomings in terms of safety, labor consumption and operating efficiency, and it is difficult to adapt to the ever-changing needs. Especially in the process of power grid maintenance and construction, the traditional manual operation method not only consumes a lot of manpower, but also has low operating efficiency and high safety risks. Therefore, power grid construction urgently needs to improve work efficiency and safety through mechanized construction methods to promote the high-quality development of power grid construction.

[0003] The laying of power optical cables is an important part of power construction, especially in the optical cable pulling process, which often requires a lot of manpower. Especially when laying optical cables in pipelines, traditional optical cable conveyors are difficult to carry, noisy, and difficult to adapt to underground operations due to size and other reasons. Therefore, in these working environments, the pulling media (such as Dyneema ropes, wire ropes, pipe threaders, etc.) often need to be manually retracted and released, resulting in high labor intensity and low efficiency.

[0004] The Chinese patent with patent application number CN208818873U discloses an electric optical cable traction machine, which belongs to the technical field of optical cable laying and laying equipment. It includes a base frame, a support frame, a drag handle, and a casing; the traction device includes an electric motor, a reduction box, a driving gear, a reverse gear, an upper belt on the driving roller, a driven roller is arranged below the driving roller, and a lower belt is arranged on the driven roller. The side of the casing is provided with a power interface, a power switch, a frequency converter, and a high and low speed switch; the top of the casing is provided with a counter device, a panel button device, a receiving antenna, a cable threading device special button, and an emergency stop button: a spring locking structure is arranged on both sides of the roller frame of the driving roller, and a front limiter and a rear limiter are also arranged on both sides, and a guide wheel is arranged below the front limiter, and a guide joint is also arranged on the roller bracket, and a ground nail is also arranged on the side of the casing. The above device cannot realize the intelligent control of torque and traction speed, and cannot spread and recover the traction medium, and the degree of automation is low. Therefore, it is urgent for those skilled in the art to solve the above technical problems. Summary of the invention

[0005] The technical problem to be solved by the present invention is that the above-mentioned prior art cannot realize intelligent control of torque and traction speed, and cannot deploy and recover traction medium, and has a low degree of automation.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] An integrated ground-to-air intelligent laying machine for electric power optical cables, characterized in that it comprises an intelligent optical cable laying machine, a threading device and a traction medium unwinding machine, wherein the traction medium unwinding machine is connected to the threading device via a fixed hook, a power optical cable to be laid is arranged inside the threading device, the power optical cable is connected to the intelligent optical cable laying machine, an upper limit wheel and a lower limit wheel are arranged at both the head end and the tail end of the intelligent optical cable laying machine, and the power optical cable passes through the upper limit wheel and the lower limit wheel;

[0008] The optical cable intelligent laying machine is provided with a control cabinet, which controls the operating parameters of the optical cable intelligent laying machine through a built-in PLC and servo controller to ensure stable laying of the power optical cable.

[0009] By adopting the above technical solution, the efficiency of optical cable laying is greatly improved through the coordinated work of the traction medium unwinding machine and the optical cable intelligent laying machine. The traction medium unwinding machine can automatically unwind the traction medium and work synchronously with the optical cable intelligent laying machine, avoiding the low efficiency and high labor intensity brought by traditional manual unwinding. The equipment has a high degree of automation, especially in the automatic retracting and releasing function of the traction medium, which significantly reduces manual participation and reduces the labor intensity of construction personnel, especially in the laying operation that requires long-term and high-intensity operation. In addition, the optical cable intelligent laying machine ensures that the optical cable maintains a stable trajectory during the laying process through the design of the upper limit wheel and the lower limit wheel, avoiding deviation or damage caused by excessive or insufficient traction. The equipment also effectively protects the optical cable, prevents the optical cable from being subjected to excessive tension or impact during the laying process, and avoids damage. Combined with the threader and the optical cable intelligent laying machine, the equipment can adapt to a variety of working environments, especially in pipeline laying and underground operations, overcoming the problems of difficult handling and high noise of traditional equipment.

[0010] Furthermore, the optical cable intelligent laying machine also includes an adjustment hand wheel, a transmission belt, a meter wheel detection wheel, a transmission wheel, a fixed bracket, a drag roller, a tension wheel, a power supply, a control cabinet, a guide pulley and a buckle slide rail;

[0011] The upper limit wheel and the lower limit wheel are fixed on a fixing bracket by bolts;

[0012] The adjusting hand wheel is connected to the fixed bracket and the roller through a connecting shaft, and the transmission belt is connected to the transmission wheel and the meter wheel detection wheel through a pulley and the tensioning wheel;

[0013] The meter wheel detection wheel is fixed to the transmission belt and the fixed bracket through a bearing, and the transmission wheel is connected to the fixed bracket through a bearing;

[0014] The roller is connected to the fixed bracket via a bearing, and the tensioning wheel is mounted on the fixed bracket;

[0015] The lower limit wheel is fixed to the fixing bracket by bolts, the power supply is connected to the control cabinet by cables, and the control cabinet is fixed to the fixing bracket and the power supply by bolts;

[0016] The guide pulley is fixed to the bracket through the buckle slide rail and the buckle slide rail, and the buckle slide rail is fixed to the fixed bracket and the guide pulley through bolts.

[0017] By adopting the above technical solutions, the intelligent cable laying machine ensures the stable transmission of the optical cable during the laying process through the cooperation of the transmission belt, transmission wheel and meter wheel detection wheel. The meter wheel detection wheel can accurately measure the laying length of the optical cable and accurately record it during forward and reverse rotation, avoiding the inaccuracy of traditional manual measurement, thereby improving the work efficiency and data accuracy. The upper limit wheel and the lower limit wheel are fixed to the fixed bracket by bolts to ensure that the optical cable always maintains a stable track during the laying process and avoid the risk of deviation, knotting or damage to the optical cable. The design of the roller, transmission wheel and tension wheel further enhances the stability of the equipment and ensures that the optical cable is not prone to jamming or instability during transportation. The adjustment handwheel is connected to the fixed bracket and the roller, providing a simple adjustment method. It can easily adjust the traction and tension according to different optical cable materials and laying environments, ensuring stable traction and smooth transmission of the optical cable during the entire laying process. In addition, the bearing connection design of the tension wheel and the meter wheel detection wheel makes equipment maintenance and maintenance more convenient and quick.

[0018] Further, the traction medium unwinding machine includes an operating rod, a telescopic joint, a cabin, a driving wheel, a frame, an adjustment hand wheel, a small wheel, an external power supply, a fixing hook and a control panel;

[0019] The operating rod is fixed to the frame by bolts, the telescopic joint is installed in the center of the operating rod, the cabin is fixed to the frame by bolts, the driving wheel is connected to the frame by bearings, and the frame is connected to the operating rod, the cabin, and the fixing hook by bolts;

[0020] The adjusting hand wheel is connected to the frame and the fixing hook through a connecting shaft, the small wheel is installed at the bottom of the frame, and the control panel is fixed on the top of the cabin.

[0021] By adopting the above technical solution, the operating rod, telescopic joint, cabin, drive wheel and frame components are connected by bolts and bearings, which ensures the stable connection between the components and enhances the overall stability of the equipment. In particular, the drive wheel is connected to the frame through the bearing, which effectively ensures the smooth operation of the drive system and avoids vibration or instability during the working process, thereby ensuring the long-term reliability of the equipment. The design of the telescopic joint allows the length of the operating rod to be adjusted according to different operating requirements, enhancing the adaptability of the equipment in different operating environments. Especially in a small space or when the operating angle needs to be adjusted, the telescopic nature of the operating rod facilitates the operator to make flexible adjustments and facilitates on-site operations. The control panel is installed on the top of the cabin, which is convenient for the operator to monitor and adjust the operating status of the equipment at any time, simplifying the operation process. The connection between the adjusting hand wheel and the frame and the fixed hook allows the tightness and position of the traction medium to be adjusted quickly and easily, thereby ensuring precise control of the traction force.

[0022] Furthermore, the upper limit wheel and the lower limit wheel are provided with U-shaped grooves;

[0023] A linkage cross bar is provided on the adjusting hand wheel, and the linkage cross bar is connected to the fixing hook, and the fixing hook is located at the bottom of the traction medium unwinding machine.

[0024] By adopting the above technical solution, a linkage cross bar is provided on the adjustment hand wheel, and the linkage cross bar is connected to the fixed hook, so that the traction force and the tension of the optical cable can be easily adjusted by adjusting the hand wheel. This design enables the operator to accurately control the traction force and tension of the optical cable, thereby avoiding excessive traction or insufficient traction, and ensuring that the optical cable is not damaged during the laying process. The design of the linkage cross bar can realize the linkage between the adjustment hand wheel and the fixed hook, which is convenient for rapid response to the needs of different working environments. Through simple operation, the tightness of the optical cable can be quickly adjusted, making the traction process more efficient and precise. The fixed hook is located at the bottom of the traction medium unwinding machine, and the connection design with the linkage cross bar makes the unwinding and retracting process of the traction medium more automated, reducing the need for manual intervention and simplifying the operation process. This can significantly reduce the labor intensity and operation complexity for laying work that requires long-term operation.

[0025] Furthermore, a tensioning spring is provided on the meter wheel detection wheel, the meter wheel is mounted on the side wall of the transmission belt, the fixing bracket is made of aluminum alloy, and the tensioning wheel is mounted on the transmission belt.

[0026] By adopting the above technical solution, a tension spring is provided on the meter wheel detection wheel, which can maintain close contact between the meter wheel and the optical cable, avoiding measurement errors caused by loose or sliding optical cables. The design of the tension spring enables the meter wheel to always maintain stable measurement accuracy under different loads, thereby ensuring accurate length recording during the laying of optical cables. The meter wheel is installed on the side wall of the transmission belt to ensure the precise matching of the meter wheel and the transmission belt, avoiding friction or offset problems caused by improper installation position. This design ensures that the meter wheel can stably measure the laying length of the optical cable, while making the transmission of the optical cable smoother and reducing resistance during the laying process. The fixed bracket is made of aluminum alloy, which has strong bearing capacity, corrosion resistance and lightness. Aluminum alloy materials can not only improve the stability and durability of the equipment, but also maintain good working performance in long-term use, reduce the wear of the equipment in harsh environments, and extend the service life of the equipment. The tension wheel is installed on the transmission belt, which can effectively adjust the tension of the transmission belt and ensure stability during the transmission process. By precisely controlling the tension of the transmission belt, it is possible to ensure that the optical cable maintains appropriate tension during the laying process, preventing damage or unstable operation caused by excessive tension or looseness of the optical cable.

[0027] The present invention also discloses a method for laying a power optical cable, which uses a ground-to-air intelligent laying machine for power optical cables to achieve laying of the power optical cable, and specifically includes the following steps:

[0028] S1: firstly install a traction medium unwinding machine, and pass the fixed hook of the traction medium unwinding machine through the threading device, and the cable to be laid of the threading device passes through the optical cable intelligent laying machine and is clamped;

[0029] S2: Initializing the traction medium unwinding machine through the control panel to ensure that the unwinding machine is in a standby state and is ready to start the unwinding operation;

[0030] S3: Initialize the intelligent optical cable laying machine through the control cabinet, input the laying parameters of the power optical cable, and the intelligent optical cable laying machine uses the BP neural network trained in the PLC system to predict the traction torque range and the traction speed range;

[0031] S4: Start the traction medium unwinding machine and the optical cable intelligent laying machine. The power optical cable is pulled by the intelligent laying machine, and the traction medium unwinding machine simultaneously unwinds the traction medium.

[0032] S5: the power optical cable starts to be laid, and the traction medium unwinding machine simultaneously recycles the traction medium;

[0033] S6: During the laying process, the PLC system built into the control cabinet verifies the laying parameter information output in real time by the optical cable intelligent laying machine to ensure the accuracy of the operation process.

[0034] By adopting the above technical solutions, the widespread application of automation systems during the laying of optical cables, especially the automatic unwinding and recovery of traction media, significantly reduces manual intervention and reduces the labor intensity of construction personnel, especially in long-term and high-intensity laying operations. This advantage is particularly prominent. Through the neural network prediction of the intelligent cable laying machine, the optimal traction torque and traction speed can be accurately calculated and controlled, avoiding the errors and instability of traditional manual control, ensuring the precise adjustment of traction force, and avoiding over-traction or damage of the optical cable, thereby improving the accuracy of the operation and the safety of the optical cable. During the entire laying process, the equipment design can ensure that the optical cable is pulled with appropriate tension to prevent damage caused by excessive traction. At the same time, the synchronous recovery function of the traction medium unwinding machine reduces the excess tension of the traction medium, further protecting the optical cable. In addition, the real-time monitoring and proofreading system ensures the accuracy of laying parameters (such as traction force, laying speed, etc.), can detect problems in time, and avoid damage to the optical cable or unsmooth operation. The equipment design enables it to adapt to different operating environments, especially in complex environments such as underground and pipelines, ensuring efficient and stable operation, and overcoming the problems of difficult handling and high noise of traditional equipment. Through intelligent control systems and real-time data monitoring, empirical errors in manual operations are reduced, ensuring the safe laying of optical cables, especially while avoiding over-pulling and other potential dangers, improving the safety of construction. The introduction of automation and intelligence enables each operation link to be executed efficiently, reducing unnecessary adjustments and accelerating the progress of the entire optical cable laying project.

[0035] Further, in step S1, the adjusting hand wheel of the traction medium unwinding machine is rotated to clamp the fixing hook onto the threader;

[0036] In step S3, by inputting the laying length, material, diameter, ground-air identification, and quantitative parameters of the traction medium of the power optical cable, the optimal traction torque and traction speed of the optical cable conveyor are predicted through the BP network.

[0037] By adopting the above technical solution,

[0038] Furthermore, the BP neural network adopts forward propagation and back propagation algorithms, and is composed of an input layer, a hidden layer, and an output layer. The input is a column vector provided by a data sample, which is multiplied with each connection matrix to obtain each node neuron. Substituting each neuron node value into the transfer function can obtain the expected output result;

[0039] In the input layer, x1, x2, ...xi, xn are used as input quantities, and in the output layer, y1, y2, ym are used as output quantities. The BP network input vector set is {(x, y)};

[0040] In the hidden layer, let n be the number of input layers, α be the adjustment constant, and m be the number of output layers. Then the number of hidden layers is:

[0041]

[0042] Forward propagation is the process of signal from input layer to hidden layer and then to output layer. Assume the connection parameter of neuron is ωji, the threshold is bi, f(s) is the activation function, xi is the neuron input, yj is the neuron output, then the expression is as follows:

[0043] sj=x1*ωj1+bj1+x2*ωj2+bj2+…x1*ωji+bji+…+xn*ωjn+bjn;

[0044] yj=f(sj);

[0045] Back propagation is the process of error from the output layer to the hidden layer and then to the input layer. The gradient descent method is used to adjust the connection weights and bias terms in the network to reduce the error between the network output and the expected output. The error function is the mean square error, assuming d k is the expected output, o k is the actual output, then the mean square error is:

[0046]

[0047] The weight gradient error is calculated by the chain method, and the weight adjustment formula of the connection parameter is:

[0048] Where η is the learning rate;

[0049] In the output layer, the sigmoid function is used as the excitation function, and the output is between [0, 1]. The expression of the sigmoid function is:

[0050] By adopting the above technical solution, by inputting the length, material, diameter, ground-air mark and other parameters of the optical cable, combined with BP network prediction, the optimal traction torque and traction speed can be calculated in real time. This precise control not only improves the safety of laying operations, but also avoids errors and instability in traditional manual control. Through forward propagation and back propagation algorithms, the BP neural network can automatically adjust the connection weights and bias items, so that the network can gradually reduce errors and optimize control parameters. This makes the optical cable laying process more flexible and adaptive, able to adapt to different types of optical cables and different operating environments. The network's automated learning and adjustment process reduces subjective judgment bias in manual operations, thereby reducing the occurrence of human errors and improving the accuracy and safety of optical cable laying. The BP neural network uses the gradient descent method to optimize parameters and effectively adjusts the connection weights in the network, thereby enhancing the stability of the system and avoiding operation interruptions or optical cable damage caused by inaccurate parameters or improper adjustments. Through automated calculation and adjustment, manual intervention is reduced and work efficiency is improved. Especially in long-term and high-intensity laying operations, this technology can significantly save time and improve work progress. Based on the prediction and adjustment functions of the neural network, the solution can adapt to a variety of complex operating environments, ensure that the equipment can operate stably, overcome the problems of difficult handling and high noise that may exist in traditional equipment, and further improve the reliability and efficiency of optical cable laying.

[0051] Furthermore, the training process of the BP neural network includes the following steps:

[0052] S31: Determine the number of nodes in the hidden layer and adjust the weight matrix of the BP model;

[0053] S32: Determine the number of nodes in the hidden layer, use the number of neurons in the hidden layer as an input parameter, and test the same sample set data;

[0054] The optimal number of neurons in the hidden layer can be determined by following the steps below:

[0055] S311: Testing from a small number of nodes;

[0056] S312: Conduct network testing and training;

[0057] S313: Increase the number of nodes for testing;

[0058] S314: Determine the number of nodes;

[0059] During the training process, the generalization ability of the network is increased and interference factors are reduced. Samples with the same number of iterations are selected to test different numbers of hidden nodes. The obtained error and maximum number of cycles are used as input parameters for testing again to obtain the model with the best number of hidden nodes.

[0060] By adopting the above technical solution and optimizing the number of hidden layer nodes, overfitting or underfitting can be avoided, ensuring that the model has a good fit on the training data, and improving the generalization ability, so that the model can maintain a high prediction accuracy under different types of optical cables, materials, ground and air signs, etc. This optimization process can reduce the impact of external interference, improve the stability of the network, and ensure consistent performance in different environments. By dynamically adjusting the number of hidden layer nodes and conducting multiple tests, the model can adapt to the needs of different operating environments, thereby achieving the best prediction of traction torque and traction speed. Gradually increasing the number of nodes and conducting tests can also efficiently train the network, shorten training time, and improve work efficiency and safety. Ultimately, this training method can improve the stability and reliability of the network, ensure consistent and accurate prediction results under complex operating conditions, and thus improve the overall quality and safety of optical cable laying.

[0061] Further, in step S2, initializing the traction medium unwinding machine includes the following steps:

[0062] S21: Initialize the network, assign random values ​​in the interval [-1, 1] to the connection parameter weight ω and threshold b, and calculate the number of hidden layers p based on the number of input layers, output layers and the adjustment constant a;

[0063] S22: training model assignment, providing the learning pattern pair [Xk Yk] consisting of power optical cable laying parameters to the neural network;

[0064] S23: Forward propagation signal, calculate the net input and output of each unit in the hidden layer and output layer in turn.

[0065] S24: Back propagate the error, calculate the expected output dj and the mean square error E, and calculate the generalized error of each unit in the output layer and the hidden layer in turn;

[0066] S25: adjusting the connection weights between the hidden layer and the output layer and between the input layer and the hidden layer and the thresholds of each unit of the output layer;

[0067] S26: randomly provide the next optional learning data pair to the BP neural network, and return to step S23 until the training of all learning data pairs is completed;

[0068] S27: Determine whether the global error of the network model can reach the required accuracy, that is, whether it is established. If it is established, jump to step S28. If it is not established, if the number of learning times is sufficient, return to step S23, otherwise continue to step S28;

[0069] S28: The BP neural network inputs the laying length, material, diameter, ground-air identification, and traction medium quantitative parameters of the power optical cable, and completes the normalization process;

[0070] S29: The BP neural network outputs the corresponding optimal traction torque and traction speed, and restores the real data.

[0071] The present invention has the following beneficial effects:

[0072] 1. The present invention realizes full-process automated operation through the coordinated work of the optical cable intelligent laying machine and the traction medium unwinding machine, combined with the intelligent prediction and adjustment of the traction torque and traction speed by the BP neural network. Through real-time calculation and precise adjustment, errors and instability in manual operation are avoided, and the efficiency and safety of laying operations are significantly improved, especially in high-intensity and long-term operations, which greatly reduces the need for manual intervention;

[0073] 2. The present invention adopts the design of meter wheel detection wheel and transmission belt to ensure the stable transmission of optical cable during the laying process, and measures the laying length in real time, avoiding the error of traditional manual measurement. Combined with the learning and optimization process of BP neural network, it can automatically adjust the optimal traction torque and traction speed according to the parameters of the optical cable, ensure the accuracy of optical cable laying, reduce the occurrence of human errors, and improve the working efficiency;

[0074] 3. The design of the integrated intelligent ground-to-air laying machine for electric optical cables of the present invention takes into account the adaptability to different working environments, especially in complex environments. It overcomes the transportation difficulties and noise problems of traditional equipment through efficient and stable operation. Through intelligent control systems and real-time monitoring, it avoids over-pulling and damage of optical cables during the laying process, effectively improving the safety of the construction process and ensuring the stable operation of the equipment and the inherent safety of the optical cables. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 It is a structural schematic diagram of the optical cable intelligent laying machine of the present invention;

[0076] Figure 2 It is a structural schematic diagram of the traction medium unwinding machine of the present invention;

[0077] Figure 3 It is the structural diagram of BP neural network of the present invention;

[0078] Figure 4 Graph of the sigmoid function of the present invention;

[0079] Figure 5 This is a control flow chart of the present invention;

[0080] Figure 6 It is the speed control flow chart of the present invention;

[0081] Figure 7 is a flow chart of the method of the present invention;

[0082] Figure 8 It is a schematic diagram of the overall connection of the present invention.

[0083] Among them, 1-optical cable intelligent laying machine; 11-adjusting hand wheel one; 12-transmission belt; 13-meter wheel detection wheel; 131-tensioning spring; 14-transmission wheel; 15-fixed bracket; 16-drag roller; 17-tensioning wheel; 18-power supply; 19-control cabinet; 20-guide pulley; 21-buckle slide rail; 2-threader; 3-traction medium unwinder; 31-operating lever; 32-telescopic joint; 33-cabin; 34-driving wheel; 35-frame; 36-adjusting hand wheel two; 361-linkage cross bar; 37-small wheel; 38-external power supply; 39-fixed hook; 40-control panel; 4-power optical cable; 5-upper limit wheel; 6-lower limit wheel. DETAILED DESCRIPTION

[0084] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific preferred embodiments.

[0085] In the description of the present invention, it should be understood that the terms "left side", "right side", "upper part", "lower part" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. "First", "second" and the like do not indicate the importance of the components, and therefore cannot be understood as limiting the present invention. The specific dimensions used in this embodiment are only for illustrating the technical solution, and do not limit the scope of protection of the present invention.

[0086] like Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 6 , Figure 7 and Figure 8As shown, the present invention discloses an integrated ground-to-air intelligent laying machine for power optical cables, including an intelligent laying machine for optical cables 1, a threader 2, and a traction medium unwinding machine 3; the intelligent laying machine for optical cables 1 is composed of an upper limit wheel 5 and a lower limit wheel 6, which are installed on a fixed bracket 15 by bolts to ensure that the power optical cable 4 passes through the upper limit wheel 5 and the lower limit wheel 6 stably during the laying process to avoid deviation. The upper limit wheel 5 and the lower limit wheel 6 are provided with a U-shaped groove to guide the power optical cable 4 more stably. The intelligent laying machine for optical cables 1 also includes an adjusting hand wheel 11, a transmission belt 12, a meter wheel detection wheel 13, a transmission wheel 14, a fixed bracket 15, a drag roller 16, a tensioning wheel 17, a power supply 18, a control cabinet 19, a guide pulley 20, and a buckle slide rail 21, wherein the adjusting hand wheel 11 is connected to the fixed bracket 15 and the roller 16 through a connecting shaft, and is used to adjust the tension and traction of the power optical cable 4. The transmission belt 12 is connected to the transmission wheel 14 and the meter wheel detection wheel 13 through the tension wheel 17 to ensure smooth transmission of the power optical cable 4. The meter wheel detection wheel 13 is used to accurately measure the length of the laid power optical cable 4 and provide real-time data to the control system to ensure the accuracy of the laying of the power optical cable 4. The traction medium unwinding machine 3 includes an operating rod 31, a telescopic joint 32, a cabin 33, a driving wheel 34, a frame 35, an adjustment hand wheel 2 36, a small wheel 37, an external power supply 38, a fixed hook 39 and a control panel 40. The operating rod 31 is fixed to the frame by bolts, and the telescopic joint 32 allows the equipment to adjust the height and angle of the traction medium unwinding machine 3 according to the operation requirements. The adjustment hand wheel 2 36 is connected to the frame 35 and the fixed hook 39 through a connecting shaft to facilitate the adjustment of the tightness of the traction medium. The fixed hook 39 is located at the bottom of the traction medium unwinding machine 3 to facilitate the connection of the threader 2. The small wheel 37 is installed at the bottom of the frame 35 to improve the mobility of the equipment and facilitate movement in the working environment. The traction medium unwinding machine 3 is connected to the threading device 2 through a fixed hook 39, and the power optical cable 4 to be laid is set in the threading device 2. The power optical cable 4 is transmitted to the optical cable intelligent laying machine 1 through the upper limit wheel 5 and the lower limit wheel 6, and is pulled and controlled by the optical cable intelligent laying machine 1. Through the power supply and the control cabinet 19 connection, the operation status of the equipment is monitored and adjusted in real time to ensure the efficiency and safety of the operation.

[0087] Working principle: before starting the equipment, first adjust the traction medium unwinder 3 to a suitable height through the operating rod 35, and use the fixed hook 39 to connect it to the bottom of the threader 2 to ensure that the power optical cable 4 passes steadily. The optical cable intelligent laying machine 1 adjusts the traction force and tension of the power optical cable 4 by adjusting the hand wheel 11 to ensure smooth transmission of the power optical cable 4. After the equipment is started, the power optical cable 4 is pulled by the optical cable intelligent laying machine 1, and the traction medium unwinder 3 synchronously unwinds the traction medium. The transmission belt 12 and the meter wheel detection wheel 13 ensure the accurate transmission of the power optical cable 4 and measure its length. The meter wheel detection wheel 13 provides real-time data to the control system for accurately calculating the laying progress of the power optical cable 4. During the laying process, the monitoring system verifies the output data of the optical cable intelligent laying machine 1 in real time to ensure that the traction force and speed are adjusted within the optimal range, thereby avoiding over-traction or optical cable damage.

[0088] The present invention further discloses a method for laying a power optical cable, which uses a ground-to-air intelligent laying machine for power optical cables to achieve laying of the power optical cable 4, and specifically includes the following steps:

[0089] S1: First, install the traction medium unwinding machine 3, and pass the fixed hook 39 of the traction medium unwinding machine 3 through the threading device 2, and the cable to be laid of the threading device 2 passes through the optical cable intelligent laying machine 1 and is clamped;

[0090] S2: Initializing the traction medium unwinding machine 3 to ensure that the unwinding machine is in a standby state and is ready to start the unwinding operation;

[0091] S3: Initialize the optical cable intelligent laying machine 1, input the laying parameters of the power optical cable 4, and the optical cable intelligent laying machine 1 uses a BP neural network to predict the optimal traction torque and traction speed;

[0092] S4: starting the traction medium unwinding machine 3 and the optical cable intelligent laying machine 1, the power optical cable 4 is pulled by the intelligent laying machine, and the traction medium unwinding machine 3 simultaneously unwinds the traction medium;

[0093] S5: the power optical cable 4 starts to be laid, and the traction medium unwinding machine 3 simultaneously recycles the traction medium;

[0094] S6: During the laying process, the laying parameter information output in real time by the optical cable intelligent laying machine 1 is checked to ensure the accuracy of the operation process.

[0095] In step S1, the adjusting hand wheel 2 36 of the traction medium unwinding machine 3 is rotated to clamp the fixing hook 39 on the threading device 2;

[0096] In step S3, by inputting the laying length, material, diameter, ground-air identification, and traction medium quantitative parameters of the power optical cable 4, the optimal traction torque and traction speed of the optical cable conveyor are predicted through the BP network.

[0097] The BP neural network adopts forward propagation and back propagation algorithms, and is composed of an input layer, a hidden layer, and an output layer. The input is a column vector provided by a data sample, which is multiplied with each connection matrix to obtain each node neuron. Substituting each neuron node value into the transfer function can obtain the expected output result;

[0098] In the input layer, x1, x2, ...xi, xn are used as input quantities, and in the output layer, y1, y2, ym are used as output quantities. The BP network input vector set is {(x, y)};

[0099] In the hidden layer, let n be the number of input layers, α be the adjustment constant, and m be the number of output layers. Then the number of hidden layers is:

[0100]

[0101] Forward propagation is the process of signal from input layer to hidden layer and then to output layer. Assume the connection parameter of neuron is ωji, the threshold is bi, f(s) is the activation function, xi is the neuron input, yj is the neuron output, then the expression is as follows:

[0102] sj=x1*ωj1+bj1+x2*ωj2+bj2+…x1*ωji+bji+…+xn*ωjn+bjn;

[0103] yj=f(sj);

[0104] Back propagation is the process of error from the output layer to the hidden layer and then to the input layer. The gradient descent method is used to adjust the connection weights and bias terms in the network to reduce the error between the network output and the expected output. The error function is the mean square error, assuming d k is the expected output, o k is the actual output, then the mean square error is:

[0105]

[0106] The weight gradient error is calculated by the chain method, and the weight adjustment formula of the connection parameter is:

[0107] Where η is the learning rate;

[0108] In the output layer, the sigmoid function is used as the excitation function, and the output is between [0, 1]. The expression of the sigmoid function is:

[0109]

[0110] During the training process, the network is first initialized by randomly initializing the connection weights and bias items, and assigning values ​​in the range of [-1,1] to ensure that the initial state of the network is not biased in a certain direction. Then, the optical cable laying data provided by the training set is used for training, and various parameters of the optical cable (such as length, material, traction medium quantization, etc.) are input for calculation. The output result is calculated by forward propagation and compared with the expected output. Then the error is calculated by the back propagation algorithm and gradient descent optimization is performed to update the weights and bias items. During the training process, when the set number of iterations or error accuracy requirements are reached, the training process ends and the network model reaches the optimal state. In the actual optical cable laying operation, the trained BP neural network can predict the optimal traction torque and traction speed in real time according to the specific parameters of the optical cable, thereby automatically adjusting the working state of the optical cable laying machine to ensure the smooth progress of the optical cable laying process. This intelligent control greatly improves the accuracy and safety of optical cable laying, and avoids the problem of optical cable damage or low operation efficiency caused by manual operation errors. Specifically, it includes the following steps:

[0111] S21: Initialize the network, assign random values ​​in the interval [-1, 1] to the connection parameter weight ω and threshold b, and calculate the number of hidden layers p based on the number of input layers, output layers and the adjustment constant a;

[0112] S22: training model assignment, providing the learning pattern pair [Xk, Yk] consisting of the laying parameters of the power optical cable 4 to the neural network;

[0113] S23: Forward propagation signal, calculate the net input and output of each unit in the hidden layer and output layer in turn.

[0114] S24: Back propagate the error, calculate the expected output dj and the mean square error E, and calculate the generalized error of each unit in the output layer and the hidden layer in turn;

[0115] S25: adjusting the connection weights between the hidden layer and the output layer and between the input layer and the hidden layer and the thresholds of each unit of the output layer;

[0116] S26: randomly provide the next optional learning data pair to the BP neural network, and return to step S23 until the training of all learning data pairs is completed;

[0117] S27: Determine whether the global error of the network model can reach the required accuracy, that is, whether it is established. If it is established, jump to step S28. If it is not established, if the number of learning times is sufficient, return to step S23, otherwise continue to step S28;

[0118] S28: the BP neural network inputs the laying length, material, diameter, ground-air identification, and traction medium quantitative parameters of the power optical cable 4, and completes normalization processing;

[0119] S29: The BP neural network outputs the corresponding optimal traction torque and traction speed, and restores the real data.

[0120] In another embodiment, step S21: initialize the network. Before training begins, the connection weights and bias items (thresholds) of the network are randomly initialized. During initialization, each connection weight and bias item is assigned a random value in the interval [-1, 1]. Next, the number of hidden layers is calculated based on the input layer (the number of eigenvalues ​​of the optical cable parameters), the output layer (the number of predicted values ​​of the traction torque and traction speed), and the adjustment constant (usually related to the complexity of the network). The number of hidden layer nodes is determined by experiments or optimization methods, and is usually adjusted according to the complexity of the input and output data to ensure the learning ability and generalization ability of the model;

[0121] Step S22: training model assignment, after initialization, the optical cable laying parameters (such as length, material, traction medium quantitative parameters, etc.) in the training set are organized into learning pattern pairs. Each pair of learning data is input into the neural network as training data for subsequent forward propagation and error calculation;

[0122] Step S23: Forward propagation signal In the network, the data of the input layer is weighted and passed to the hidden layer through the activation function (such as sigmoid or ReLU). The neurons in the hidden layer further process the signal and pass the result to the output layer. In each neuron, a weighted summation operation is first performed, and then the output value is generated through the activation function. The forward propagation process transfers the signal from the input layer to the output layer layer by layer, and finally obtains the network's prediction results (traction torque and traction speed);

[0123] Step S24: Back propagation error. Back propagation is the core of the neural network optimization process. It reduces the error by calculating the error between the output layer and the hidden layer and adjusting the network weights. In the back propagation process, the error between the expected output (target value) and the actual output is first calculated. The mean square error (MSE) is usually used as the error function. The error formula is:

[0124]

[0125] Among them, d i is the expected output, y i is the actual output, and m is the number of output nodes. Then, the error gradient is used to correct the output of each neuron, and the error signal is gradually propagated from the output layer back to the hidden layer through the chain rule, and finally to the input layer.

[0126] Step S25: Adjust the connection weights and thresholds, and update the connection weights and bias terms (thresholds) between each layer according to the error signal calculated by the back propagation algorithm. The weight update rule usually uses the gradient descent method, and the formula is:

[0127]

[0128] Where η is the learning rate, which controls the step size of the update. Through multiple iterations, the network gradually reduces the output error and optimizes the connection weights and bias terms;

[0129] Step S26: Continue training. The network will randomly provide the next learning data pair and continue to execute steps S23 and S24. Through multiple forward propagation and back propagation iterations, the weights and bias items are continuously updated until all learning data are trained. After each iterative update, the network will be gradually optimized to reduce the error;

[0130] Step S27: Determine the stop condition. During each iteration, the system will calculate the global error and compare it with the set accuracy standard. If the global error has met the set accuracy requirement or the maximum number of learning times has been reached, the training will be stopped; if the error still does not meet the requirement, the iteration will continue and return to step S23 for further training;

[0131] Step S28: Data normalization processing. After completing the network training, the optical cable laying parameters (such as laying length, material, diameter, ground-to-air identification, and traction medium quantitative parameters) input into the BP neural network will be normalized first. This process ensures that data of different dimensions and ranges can be effectively processed by the neural network to avoid the data range being too large or too small to affect the training effect;

[0132] Step S29: Output of optimal traction torque and traction speed: The trained and optimized BP neural network outputs the optimal traction torque and traction speed according to the input optical cable laying parameters. These output values ​​will be restored to actual control parameters for use by the optical cable intelligent laying machine 1 to adjust its working state to ensure the smooth progress of the optical cable laying process.

[0133] When controlling the speed of the intelligent optical cable laying machine 1, first the main command switch of the control cabinet 19 sends start, stop, jog, acceleration, deceleration and other commands to the PLC. After receiving the signal, the PLC as the lower computer will calculate the traction and pay-off frequency (or speed) according to the control command of the main command switch and the calculated corresponding speed and torque, and then send the corresponding control instructions to the traction servo drive controller through the RS485 serial port bus.

[0134] like Figure 6As shown, the control method adopted by the AC servo motor of the optical cable intelligent laying machine 1 is closed-loop control. The speed control block diagram is as follows. The traction servo driver receives the control signal from the PLC to drive the servo motor output. The traction force is limited to the optimal traction torque value of the current working condition and is adjusted by the torque limit of the traction motor.

[0135] The AC servo motor control principle of the traction medium unwinding machine 3 is that the control method adopted by the unwinding drive is closed-loop control. In the working mode of spreading the traction medium or the power optical cable 4, the servo motor adopts constant torque control, and the speed adjustment range is 0-100.2%. In the working mode of winding the traction medium, the servo motor adopts constant speed control, and the torque adjustment range is 0-100.2%.

[0136] In actual optical cable laying operations, the trained BP neural network can predict the optimal traction torque and traction speed in real time according to the characteristics of different optical cables and the construction environment, thereby automatically adjusting the working parameters of the optical cable laying machine. Through intelligent control, the equipment can adjust the operating status according to real-time feedback, effectively avoiding problems such as over-traction or optical cable damage, and ensuring the accuracy, efficiency and safety of optical cable laying operations.

[0137] The preferred embodiments of the present invention are described in detail above; however, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all belong to the protection scope of the present invention.

Claims

1. An integrated machine for intelligent ground-to-air laying of power optical cables, characterized by: The invention comprises an intelligent optical cable laying machine (1), a threading device (2) and a traction medium unwinding machine (3), wherein the traction medium unwinding machine (3) is connected to the threading device (2) via a fixed hook (39), an electric power optical cable (4) to be laid is arranged inside the threading device (2), the electric power optical cable (4) is connected to the intelligent optical cable laying machine (1), and the head end and the tail end of the intelligent optical cable laying machine (1) are both provided with an upper limit wheel (5) and a lower limit wheel (6), and the electric power optical cable (4) passes through the upper limit wheel (5) and the lower limit wheel (6); The optical cable intelligent laying machine (1) is provided with a control cabinet (19), and the control cabinet (19) controls the operating parameters of the optical cable intelligent laying machine (1) through a built-in PLC and a servo controller, thereby ensuring stable laying of the power optical cable (4).

2. The integrated ground-to-air intelligent laying machine for power optical cables according to claim 1 is characterized by: The optical cable intelligent laying machine (1) also includes an adjusting hand wheel (11), a transmission belt (12), a meter wheel detection wheel (13), a transmission wheel (14), a fixed bracket (15), a drag roller (16), a tension wheel (17), a power supply (18), a guide pulley (20) and a buckle slide rail (21); The upper limit wheel (5) and the lower limit wheel (6) are fixed on a fixing bracket (15) by means of bolts; The adjusting hand wheel (11) is connected to the fixed bracket (15) and the roller via a connecting shaft; the transmission belt is connected to the transmission wheel (14) and the meter wheel detection wheel (13) via a pulley and the tensioning wheel (17); the meter wheel detection wheel (13) is electrically connected to a control cabinet (19); the control cabinet (19) records the number of rotations of the meter wheel detection wheel (13) and converts it into the laying length of the power optical cable (4); The meter wheel detection wheel (13) is fixed on the transmission belt (12) and the fixed bracket (15) through a bearing, and the transmission wheel (14) is connected to the fixed bracket (15) through a bearing; The roller is connected to the fixed bracket (15) via a bearing, and the tensioning wheel (17) is mounted on the fixed bracket (15); The lower limit wheel (6) is fixed to the fixed bracket (15) by bolts, the power supply (18) is electrically connected to the control cabinet (19), and the control cabinet (19) is fixed to the fixed bracket (15) and the power supply (18) by bolts; The guide pulley (20) is fixed to the bracket via a snap-on slide rail (21), and the snap-on slide rail (21) is fixed to the fixed bracket (15) and the guide pulley (20) via bolts.

3. The integrated ground-to-air intelligent laying machine for power optical cables according to claim 1 is characterized by: The traction medium unwinding machine (3) comprises an operating rod (31), a telescopic joint (32), a cabin (33), a driving wheel (34), a frame (35), a second adjusting hand wheel (36), a small wheel (37), an external power supply (38), a fixing hook (39) and a control panel (40); The operating rod (31) is fixed to the frame (35) by bolts, the telescopic joint (32) is installed at the center of the operating rod (31), the cabin (33) is fixed to the frame (35) by bolts, the driving wheel (34) is connected to the frame (35) by bearings, and the frame (35) is connected to the operating rod (31), the cabin (33) and the fixing hook (39) by bolts; The second adjusting hand wheel (36) is connected to the frame (35) and the fixing hook (39) via a connecting shaft, the small wheel (37) is installed at the bottom of the frame (35), and the control panel (40) is fixed on the top of the cabin (33).

4. The integrated ground-to-air intelligent laying machine for power optical cables according to claim 1 is characterized by: The upper limit wheel (5) and the lower limit wheel (6) are provided with U-shaped grooves; A linkage cross bar (361) is provided on the adjusting hand wheel, and the linkage cross bar (361) is connected to the fixing hook (39), and the fixing hook (39) is located at the bottom of the traction medium unwinding machine (3).

5. The integrated ground-to-air intelligent laying machine for power optical cables according to claim 1 is characterized by: The meter wheel detection wheel (13) is provided with a tension spring (131), the meter wheel detection wheel (13) is mounted on the side wall of the transmission belt (12), the fixed bracket (15) is made of aluminum alloy, and the tension wheel (17) is mounted on the transmission belt (12).

6. A method for laying a power optical cable, using the power optical cable ground-to-air intelligent laying integrated machine according to any one of claims 1 to 5 to achieve laying of a power optical cable (4), characterized in that: The specific steps include: S1: First, a traction medium unwinding machine (3) is installed, and a fixing hook (39) of the traction medium unwinding machine (3) is passed through the threading device (2), and the cable to be laid of the threading device (2) is passed through the optical cable intelligent laying machine (1) and clamped; S2: initializing the traction medium unwinding machine (3) through the control panel (40) to ensure that the unwinding machine is in a standby state and is ready to start the unwinding operation; S3: initializing the optical cable intelligent laying machine (1) through the control cabinet (19), inputting the laying parameters of the power optical cable (4), and the optical cable intelligent laying machine (1) using the BP neural network trained in the PLC system to predict the traction torque range and the traction speed range; S4: starting the traction medium unwinding machine (3) and the optical cable intelligent laying machine (1), the power optical cable (4) is pulled by the intelligent laying machine, and the traction medium unwinding machine (3) simultaneously unwinds the traction medium; S5: the power optical cable (4) starts to be laid, and the traction medium unwinding machine (3) simultaneously recycles the traction medium; S6: During the laying process, the PLC system built into the control cabinet (19) checks the laying parameter information output in real time by the optical cable intelligent laying machine (1) to ensure the accuracy of the operation process.

7. The method for laying power optical cables according to claim 6, characterized in that: In step S1, the adjusting hand wheel 2 (36) of the traction medium unwinding machine (3) is rotated to clamp the fixing hook (39) onto the threading device (2); In step S3, by inputting the laying length, material, diameter, ground-air identification, and traction medium quantitative parameters of the power optical cable (4), the traction torque range and traction speed range of the optical cable intelligent laying machine (1) are predicted through the BP network.

8. The method for laying power optical cables according to claim 7, characterized in that: The BP neural network adopts forward propagation and back propagation algorithms, and is composed of an input layer, a hidden layer, and an output layer. The input is a column vector provided by a data sample, which is multiplied with each connection matrix to obtain each node neuron. Substituting each neuron node value into the transfer function can obtain the expected output result; In the input layer, x1, x2, ...xi, xn are used as input quantities, and in the output layer, y1, y2, ym are used as output quantities. The BP network input vector set is {(x, y)}; In the hidden layer, let n be the number of input layers, α be the adjustment constant, and m be the number of output layers. Then the number of hidden layers is: Forward propagation is the process of signal from input layer to hidden layer and then to output layer. Assume the connection parameter of neuron is ωji, the threshold is bi, f(s) is the activation function, xi is the neuron input, yj is the neuron output, then the expression is as follows: sj=x1*ωj1+bj1+x2*ωj2+bj2+…x1*ωji+bji+…+xn*ωjn+bjn; yj=f(sj); Back propagation is the process of error from the output layer to the hidden layer and then to the input layer. The gradient descent method is used to adjust the connection weights and bias terms in the network to reduce the error between the network output and the expected output. The error function is the mean square error, assuming d k is the expected output, o k is the actual output, then the mean square error is: The weight gradient error is calculated by the chain method, and the weight adjustment formula of the connection parameter is: Where η is the learning rate; In the output layer, the sigmoid function is used as the excitation function, and the output is between [0, 1]. The expression of the sigmoid function is:

9. The method for laying power optical cables according to claim 7, characterized in that: The training process of the BP neural network comprises the following steps: S31: Determine the number of nodes in the hidden layer and adjust the weight matrix of the BP model; S32: Determine the number of nodes in the hidden layer, use the number of neurons in the hidden layer as an input parameter, and test the same sample set data; The optimal number of neurons in the hidden layer can be determined by following the steps below: S311: Testing from a small number of nodes; S312: Conduct network testing and training; S313: Increase the number of nodes for testing; S314: Determine the number of nodes; During the training process, the generalization ability of the network is increased and interference factors are reduced. Samples with the same number of iterations are selected to test different numbers of hidden nodes. The obtained error and maximum number of cycles are used as input parameters for testing again to obtain the model with the best number of hidden nodes.

10. The method for laying power optical cables according to claim 7, characterized in that: Initializing the traction medium unwinding machine (3) in step S2 comprises the following steps: S21: Initialize the network, assign random values ​​in the interval [-1, 1] to the connection parameter weight ω and threshold b, and calculate the number of hidden layers p based on the number of input layers, output layers and the adjustment constant a; S22: training model assignment, providing the learning pattern pair [Xk, Yk] consisting of the laying parameters of the power optical cable (4) to the neural network; S23: Forward propagation signal, calculate the net input and output of each unit in the hidden layer and output layer in turn. S24: Back propagate the error, calculate the expected output dj and the mean square error E, and calculate the generalized error of each unit in the output layer and the hidden layer in turn; S25: adjusting the connection weights ω between the hidden layer and the output layer and between the input layer and the hidden layer and the thresholds bji of each unit in the output layer; S26: randomly provide the next optional learning data pair to the BP neural network, and return to step S23 until the training of all learning data pairs is completed; S27: Determine whether the global error of the network model can reach the required accuracy, that is, whether E≤ε is established. If it is established, jump to step S28. If it is not established, if the number of learning times is ≤Nmax, return to step S23, otherwise continue to step S28; S28: the BP neural network inputs the laying length, material, diameter, ground-air identification, and traction medium quantitative parameters of the power optical cable (4), and completes normalization processing; S29: The BP neural network outputs the corresponding optimal traction torque and traction speed, and restores the real data.

Images