Novel power supply energy storage device for power transmission line

Abstract

The invention provides a novel power supply energy storage device for a power transmission line, and belongs to the technical field of power system energy storage. The device is composed of a hybrid energy storage module, an embedded fault prediction unit, a dynamic balance controller and a composite heat dissipation shell. The hybrid energy storage module integrates an all-vanadium redox flow battery, a solid-state lithium capacitor and a super capacitor to cooperatively meet the energy and power requirements of a power transmission line; the embedded fault prediction unit monitors current harmonics and temperature data in real time, and predicts a fault and deals with the fault in advance by using a neural network accelerator; the dynamic balance controller adjusts the working state of the energy storage unit according to the fault probability and optimizes energy management; the composite heat dissipation shell is designed by adopting a phase change material and a bionic air duct, so that efficient dynamic heat dissipation is realized. According to the novel power supply energy storage device for the power transmission line, the performance, the reliability and the safety of the energy storage device are remarkably improved, the service life is prolonged, the maintenance cost is reduced, and the novel power supply energy storage device is suitable for the power transmission line under complex working conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage in power systems, and particularly to a novel power energy storage device for transmission lines. Background Art

[0002] With the continuous growth of global energy demand and the large-scale access of renewable energy, the stability and reliability of transmission lines are facing severe challenges. Traditional energy storage devices for transmission lines mainly use a single type of energy storage element, such as lead-acid batteries, lithium-ion batteries, or supercapacitors. However, these single energy storage devices often have certain limitations when facing complex and changing transmission environments.

[0003] On the one hand, a single energy storage element is difficult to meet the requirements of the energy storage system for transmission lines in terms of energy density, power density, cycle life, and cost-effectiveness. For example, although lead-acid batteries have relatively low costs, they have small energy density and short cycle life, and cannot quickly respond to instantaneous power fluctuations in transmission lines; lithium-ion batteries have high energy density and long cycle life, but their power output capacity is limited, and performance degradation and safety hazards are likely to occur during high-rate charge and discharge; supercapacitors can provide high power output, but their energy storage capacity is small and cannot maintain the stable operation of transmission lines for a long time.

[0004] On the other hand, most existing energy storage devices lack the ability of real-time monitoring and intelligent management of their own states and the operating conditions of transmission lines. When a fault occurs in a transmission line, the energy storage device cannot predict in advance and take effective countermeasures, often resulting in the expansion of the fault range and the extension of the recovery time, seriously affecting the reliability of the power transmission system and the power supply quality.

[0005] In addition, the heat dissipation performance of some energy storage devices is not good, and thermal runaway is likely to be caused by heat accumulation during long-term operation, further shortening the service life of the energy storage device and even possibly causing safety accidents. Moreover, the heat dissipation design of existing energy storage devices is often relatively fixed and cannot dynamically adjust the heat dissipation efficiency according to actual working conditions, resulting in energy waste and unsatisfactory heat dissipation effects.

[0006] In the prior art, such as Patent CN203445632U, a novel power energy storage device for transmission lines is installed on the transmission line conductor and consists of a high-performance lithium battery, a DC-DC converter, a super energy storage capacitor, and a switching control circuit. The device switches between different power supply modes through the switching control circuit to supply power to the monitoring terminal, solving the problem of power supply for the monitoring terminal when the line is powered off at the moment of a fault. However, this solution still has some deficiencies: 1. Energy storage elements mainly rely on high-performance lithium batteries and supercapacitors, and do not fully utilize the synergistic advantages of multiple energy storage technologies, making it difficult to simultaneously meet the high requirements of transmission lines for energy density and power density.

[0007] 2. There is a lack of real-time monitoring and intelligent management of the internal state of the energy storage system, unable to predict faults and take measures in advance, which affects the reliability and stability of the system.

[0008] 3. The heat dissipation design of the energy storage device is not mentioned, and heat accumulation problems may occur during long-term operation, affecting the life and safety of the energy storage device. Summary of the Invention

[0009] The purpose of the present invention is to provide a new type of power energy storage device for transmission lines, which significantly improves the performance, reliability and safety of the energy storage device, extends the service life, reduces the maintenance cost, and is applicable to transmission lines under complex working conditions.

[0010] To achieve the above object, the present invention provides a new type of power energy storage device for transmission lines, including: a hybrid energy storage module, an embedded fault prediction unit, a dynamic balancing controller, and a composite heat dissipation housing; The hybrid energy storage module is composed of a vanadium redox flow battery unit, a solid-state lithium capacitor unit, and a supercapacitor unit connected in parallel through a bidirectional DC-DC converter, and the output ends of each unit are electrically connected through a DC bus; The embedded fault prediction unit is connected to the hybrid energy storage module through a data bus, and includes a current harmonic analysis module, a temperature field reconstruction module, and a neural network accelerator. The output end of the current harmonic analysis module is signal-connected to the input end of the neural network accelerator; The dynamic balancing controller is respectively connected to the bidirectional DC-DC converter in the hybrid energy storage module, the active balancing circuit of the solid-state lithium capacitor unit, and the microfluidic pump of the vanadium redox flow battery unit through a plurality of PWM signal lines, receives the fault probability value output by the neural network accelerator, and generates a control instruction; The composite heat dissipation housing is wrapped outside the hybrid energy storage module, and the internal bionic air duct is closely attached to the surface of the hybrid energy storage module, and the heat dissipation efficiency is dynamically adjusted through the signal feedback of the temperature sensor.

[0011] Preferably, the structure of the solid-state lithium capacitor unit includes: the positive electrode material is single-crystal LiNi 0.8 Mn 0.1 Co 0.1 O2, the specific capacity ≥ 200 mAh / g; the negative electrode material is a silicon-carbon nanowire array, the diameter ≤ 80 nm, and the loading amount ≥ 4 mg / cm 2 ; the solid electrolyte layer is Li 1.5 Al 0.5 Ge 1.5(PO4)3 thin film with a thickness ≤ 20 μm and an ionic conductivity ≥ 1 mS / cm; the battery cells are connected by copper-aluminum composite foils, and the gap between adjacent battery cells is filled with an aerogel thermal insulation layer with a thermal conductivity ≤ 0.02 W / m·K.

[0012] Preferably, the circuit topology of the hybrid energy storage module includes: a triple interleaved parallel DC-DC converter is used between the all-vanadium redox flow battery unit and the solid-state lithium capacitor unit, with an efficiency ≥ 97% and a ripple ≤ 1%; the supercapacitor unit is directly connected to the DC bus, and high-frequency oscillations are suppressed by a distributed micro inductor with an inductance value of 20 nH ± 5%; redundant switching channels are set between each unit, and the switching response time ≤ 100 μs, and the switching trigger signal is transmitted by the dynamic equalization controller through an opto-isolation circuit.

[0013] Preferably, the coefficient update rule of the FIR filter bank of the current harmonic analysis module is as follows: Based on historical fault data, the center frequency is dynamically adjusted, and the update formula is: ; Where, represents the new center frequency, represents the old center frequency, represents the learning rate, represents the th harmonic amplitude, represents the th harmonic corresponding frequency; The filter coefficients are updated online once every 24 hours through the JTAG interface; During the update, a sliding window mechanism is used to select the most recent 100,000 groups of sampling points as the update data window.

[0014] Preferably, the current harmonic analysis module real-time collects the line current signal, and extracts the characteristic harmonic spectrum data through a programmable FIR filter bank, whose center frequency is dynamically configured as 6 kHz, 12 kHz, 18 kHz, and the extracted characteristic harmonic spectrum data is transmitted to the neural network accelerator through the SPI interface.

[0015] Preferably, the temperature field reconstruction module collects temperature data through a distributed optical fiber sensor, and sends the collected temperature data to the neural network accelerator through the I2C bus.

[0016] Preferably, the neural network accelerator is built-in with an LSTM-TCN hybrid model, which calculates the input harmonic distortion rate, temperature gradient matrix and historical fault time series, and outputs the fault probability value; The weights of the LSTM-TCN hybrid model are obtained by training with an improved whale optimization algorithm: Step S1: Initialize the positions of the whale population. Each whale represents the connection weights and bias parameters of a group of LSTM-TCN hybrid models. Step S2: Define the fitness function, and the calculation formula is: ; where, represents the fitness value, represents the harmonic mean of the accuracy and recall rate predicted by the model, represents the time required for the model to calculate and output the fault probability value, represents the energy consumption during the operation of the model; Step S3: Iteratively update the positions of the whale population: Calculate the fitness value of each whale; Select the optimal whale according to the fitness value; Simulate the encirclement, spiral update, and prey search behaviors of the whales to update the positions of the whale population; Step S4: Introduce gradient information during the iteration process, combine with the gradient descent method, calculate the gradient of the loss function with respect to the model parameters, and adjust the parameters along the gradient direction when updating the whale positions; Step S5: Normalize the model weights in each iteration; Step S6: Repeat Step S2 to Step S5 until the maximum number of iterations is reached or the convergence condition is satisfied, and output the final optimized connection weights and bias parameters of the LSTM-TCN hybrid model.

[0017] Preferably, the dynamic balance controller receives the fault probability value output by the neural network accelerator. When the fault probability value ≥ 0.6, it sends a three-level pre-charge instruction to the hybrid energy storage module to control the working states of the supercapacitor unit, the solid-state lithium capacitor unit, and the all-vanadium redox flow battery unit. Among them, the PWM duty cycle of the pre-charge instruction and the fault probability value satisfy a linear relationship: ; where, represents the PWM duty cycle of the pre-charge instruction, represents the fault probability value.

[0018] Preferably, the design of the composite heat dissipation housing includes: the phase change material layer is a paraffin-expanded graphite-boron nitride composite material, the phase change latent heat ≥ 200 J / g, the thermal conductivity ≥ 18 W / m·K, and the thickness is 2.5 mm ± 0.1 mm; the bionic air duct structure has a shark skin non-smooth surface, the groove depth is 50 μm ± 5 μm, the spacing is 200 μm, and the inclination angle is 55° ± 2°; the heat dissipation efficiency adjustment logic satisfies: ; where, Indicates the heat dissipation efficiency, Indicates the real-time temperature, with the unit of °C, Indicates the base of the natural logarithm.

[0019] Therefore, the present invention adopts the above-mentioned novel power energy storage device for transmission lines, and the beneficial technical effects are as follows: (1) Cooperative operation of multiple types of energy storage elements: The present invention adopts a hybrid energy storage module composed of a vanadium redox flow battery unit, a solid-state lithium capacitor unit and a supercapacitor unit, which are connected in parallel through a bidirectional DC-DC converter. This cooperative working mode gives full play to the advantages of different energy storage technologies. The vanadium redox flow battery unit can provide large-scale energy storage to meet the long-term stable power supply requirements of transmission lines; the solid-state lithium capacitor unit has a high specific capacity and high power density and can quickly charge and discharge at a large current; the supercapacitor unit can instantaneously provide high-power output or absorb energy shocks. Compared with the prior art, this solution overcomes the limitation that it is difficult to balance the energy density and power density of a single energy storage element, can better cope with the complex and changeable working conditions of transmission lines, and improves the overall performance and reliability of the energy storage system.

[0020] (2) Intelligent fault prediction and dynamic balancing control: The embedded fault prediction unit includes a current harmonic analysis module, a temperature field reconstruction module and a neural network accelerator, which can collect and analyze the line current signal and temperature data in real time. Through the LSTM-TCN hybrid model built in the neural network accelerator, the input harmonic distortion rate, temperature gradient matrix and historical fault time series are calculated, and the fault probability value is output. The dynamic balancing controller adjusts the working state of each unit in the hybrid energy storage module according to the fault probability value. Compared with the prior art, this intelligent fault prediction and dynamic balancing control function can predict faults in advance and take measures in advance, such as adjusting the output power of the energy storage unit or performing charge and discharge control, to avoid the expansion and spread of faults, effectively improving the reliability and stability of the energy storage device for transmission lines, and reducing the impact of faults on the power transmission system.

[0021] (3) Efficient heat dissipation design: The composite heat dissipation shell is wrapped outside the hybrid energy storage module, and the internal bionic air duct is closely attached to the surface of the energy storage unit. The heat dissipation efficiency is dynamically adjusted through the signal feedback of the temperature sensor. The phase change material layer is a paraffin-expanded graphite-boron nitride composite material with a thermal conductivity ≥ 18 W / m·K, which can quickly conduct and dissipate the heat generated by the energy storage unit. The bionic air duct structure has a non-smooth shark skin surface, which can optimize the air flow distribution and enhance the heat dissipation effect. Compared with the prior art, this heat dissipation design can not only effectively solve the problem of heat accumulation during the long-term operation of the energy storage device, but also dynamically adjust the heat dissipation efficiency according to the actual working conditions, avoiding energy waste, ensuring the stable operation of the energy storage device under different environmental conditions, extending the service life of the energy storage device, and reducing the maintenance cost. Description of the Drawings

[0022] Figure 1 This is the structural diagram of a new type of power energy storage device for a transmission line in the present invention; Figure 2 This is the training flow chart of the improved whale optimization algorithm. Detailed implementation manners

[0023] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] Unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs.

[0025] Embodiment 1 As Figure 1-2 , the present invention provides a new type of power energy storage device for a transmission line, including: a hybrid energy storage module, an embedded fault prediction unit, a dynamic equalization controller, and a composite heat dissipation housing.

[0026] The hybrid energy storage module is composed of a vanadium redox flow battery unit, a solid-state lithium capacitor unit, and a supercapacitor unit connected in parallel through a bidirectional DC-DC converter, and the output ends of each unit are electrically connected through a DC bus.

[0027] The vanadium redox flow battery unit is composed of multiple single battery stacks, and its electrolyte uses a high-purity vanadium ion solution. The positive electrolyte and the negative electrolyte are respectively stored in two independent liquid storage tanks, and the volume of each liquid storage tank is 0.5 cubic meters. The electrolyte is circulated between the battery stack and the liquid storage tank through a pump circulation system to ensure the normal charge and discharge of the battery.

[0028] In actual operation, when the transmission line is in a normal power supply state, the vanadium redox flow battery unit is connected to the DC bus through a bidirectional DC-DC converter and supplies power to the power grid with a stable power, and its output power can be adjusted within the range of 0-50 kW according to the needs of the power grid.

[0029] The structure of the solid-state lithium capacitor unit includes: the positive electrode material is single crystal LiNi 0.8 Mn 0.1 Co 0.1 O2, the specific capacity ≥ 200 mAh / g; the negative electrode material is a silicon-carbon nanowire array, the diameter ≤ 80 nm, and the loading amount ≥ 4 mg / cm 2 ; the solid electrolyte layer is a Li 1.5 Al 0.5 Ge 1.5 (PO4)3 thin film, the thickness ≤ 20 μm, and the ionic conductivity ≥ 1 mS / cm; the battery cores are connected through a copper-aluminum composite foil, and the adjacent battery core gaps are filled with an aerogel thermal insulation layer, and the thermal conductivity ≤ 0.02 W / m·K.

[0030] The supercapacitor uses a carbon-based electric double-layer capacitor, which uses activated carbon with a high specific surface area as the electrode material inside. After being impregnated with the electrolyte and wound into a shape, it has good rate performance and cycle life.

[0031] Multiple supercapacitors are directly connected to the DC bus after suppressing high-frequency oscillations through distributed micro-inductors. The inductance value is 20 nH ± 5%, which can effectively filter out high-frequency noise and improve the power quality. In extreme cases such as short-circuit faults occurring in the transmission line, the supercapacitor unit can release a power of up to 200 kW within 1 millisecond, providing strong support for power compensation during the fault moment.

[0032] The bidirectional DC-DC converter adopts a triple interleaved parallel topology structure. The switching frequency of each parallel branch is 100 kHz, and voltage conversion and electrical isolation are achieved through a high-frequency transformer. Its efficiency ≥ 97% and the ripple ≤ 1%, which can effectively ensure the energy transfer efficiency and voltage stability between different energy storage units.

[0033] The control circuit of the converter is implemented by a digital signal processor (DSP), which has a fast response speed and precise control accuracy. It can complete the sampling and control of the input and output voltages and currents within 10 microseconds, realizing the real-time dynamic management of the hybrid energy storage module.

[0034] The circuit topology of the hybrid energy storage module includes: a triple interleaved parallel DC-DC converter is used between the all-vanadium redox flow battery unit and the solid-state lithium capacitor unit, with an efficiency ≥ 97% and a ripple ≤ 1%; the supercapacitor unit is directly connected to the DC bus and suppresses high-frequency oscillations through a distributed micro-inductor, with an inductance value of 20 nH ± 5%; redundant switching channels are set between each unit, and the switching response time ≤ 100 μs. The switching trigger signal is transmitted by the dynamic equalization controller through an opto-isolation circuit.

[0035] The embedded fault prediction unit is connected to the hybrid energy storage module through a data bus and includes a current harmonic analysis module, a temperature field reconstruction module, and a neural network accelerator. The output end of the current harmonic analysis module is signal-connected to the input end of the neural network accelerator.

[0036] The current harmonic analysis module real-time collects the line current signal and extracts the characteristic harmonic spectrum data through a programmable FIR filter bank. Its center frequencies are dynamically configured as 6 kHz, 12 kHz, and 18 kHz, and the extracted characteristic harmonic spectrum data is transmitted to the neural network accelerator through an SPI interface.

[0037] The coefficient update rule of the FIR filter bank of the current harmonic analysis module is as follows: Based on historical fault data, the center frequency is dynamically adjusted, and the update formula is: ; Among them, represents the new center frequency, represents the old center frequency, represents the learning rate, represents the amplitude of the th harmonic, and represents the frequency corresponding to the th harmonic; The filter coefficients are updated online once every 24 hours through the JTAG interface; When updating, a sliding window mechanism is adopted to select the nearest 100,000 groups of sampling points as the update data window.

[0038] Temperature field reconstruction module: Distributed optical fiber sensors are laid along the key parts of the power transmission line and the energy storage device. Fiber Bragg grating (FBG) sensors are used, with a temperature measurement range of -40°C to 150°C, an accuracy of ±1°C, and a spatial resolution of ≤1 m. The optical signals reflected by the FBG sensors are demodulated by a wavelength demodulator to obtain the temperature data of each measurement point.

[0039] The temperature field reconstruction algorithm uses the finite element analysis method to construct a temperature field distribution model of the entire energy storage device and the power transmission line based on the measured discrete temperature data. During the operation of the energy storage device, when the temperature of a certain energy storage battery rises abnormally, the temperature field reconstruction module can accurately identify the hot spot position and send its temperature data to the neural network accelerator for comprehensive judgment of the fault risk.

[0040] Neural network accelerator: The specific structural parameters of the LSTM-TCN hybrid model are: the LSTM layer contains 64 neurons, the TCN layer contains 3 convolutional blocks, the convolutional kernel size of each convolutional block is 3, and the number of channels is 32. The input dimension of the model is 100, and the output dimension is 1, that is, the fault probability value.

[0041] The weights of the LSTM-TCN hybrid model are trained by an improved whale optimization algorithm: Step S1, Initialize the positions of the whale population, where each whale represents a set of connection weights and bias parameters of the LSTM-TCN hybrid model; Step S2, Define the fitness function, and the calculation formula is: ; Among them, represents the fitness value, represents the harmonic mean of the accuracy and recall rate predicted by the model, represents the time required for the model to calculate and output the fault probability value, represents the energy consumption during the operation of the model; Step S3. Iteratively update the positions of the whale population: Calculate the fitness value of each whale; Select the optimal whale according to the fitness value; Simulate the encircling, spiral updating, and prey searching behaviors of the whales to update the positions of the whale population; The updating formula for encircling the prey is: ; ; where, represents the distance vector between the current whale and the prey, which is used to determine the position updating direction and distance when the whale encircles the prey, and represent the coefficient vectors, , , represents the control parameter, which linearly decreases with the number of iterations and is used to balance the global and local search capabilities, and represent independent standard random vectors, which are used to increase the randomness and diversity of the search, represents the position of the prey (optimal solution), represents the position of the current whale, represents the position of the whale updated based on the encircling prey strategy at moment; The formula for updating the position in a spiral is: ; ; where, represents the position of the whale updated based on the spiral path strategy at moment, represents the spiral shape parameter, which determines the tightness of the spiral, represents a random vector taking values in the range of [-1, 1], which is used to control the direction of the spiral movement, represents the distance vector between the current position of the whale and the position of the prey, represents the base of the natural logarithm, represents element-wise multiplication.

[0042] Step S4. Introduce gradient information during the iteration process, combine with the gradient descent method, calculate the gradient of the loss function with respect to the model parameters, and adjust the parameters along the gradient direction when updating the whale positions; Step S5. Normalize the model weights in each iteration; Step S6: Repeat steps S2 to S5 until the maximum number of iterations is reached or the convergence condition is satisfied, and output the connection weights and bias parameters of the finally optimized LSTM-TCN hybrid model.

[0043] The dynamic balance controller is respectively connected to the bidirectional DC-DC converter in the hybrid energy storage module, the active balance circuit of the solid-state lithium capacitor unit, and the microfluidic pump of the all-vanadium redox flow battery unit through multiple PWM signal lines, receives the fault probability value output by the neural network accelerator, and generates a control command.

[0044] The dynamic balance controller receives the fault probability value output by the neural network accelerator. When the fault probability value ≥ 0.6, it sends a three-stage pre-charge command to the hybrid energy storage module to control the working states of the supercapacitor unit, the solid-state lithium capacitor unit, and the all-vanadium redox flow battery unit. Among them, the PWM duty cycle of the pre-charge command and the fault probability value satisfy a linear relationship: ; where represents the PWM duty cycle of the pre-charge command, represents the fault probability value.

[0045] The composite heat dissipation housing is wrapped outside the hybrid energy storage module, and the internal bionic air duct is closely attached to the surface of the hybrid energy storage module. The heat dissipation efficiency is dynamically adjusted through the feedback signal of the temperature sensor.

[0046] The design of the composite heat dissipation housing includes: the phase change material layer is a paraffin-expanded graphite-boron nitride composite material, the phase change latent heat ≥ 200 J / g, the thermal conductivity ≥ 18 W / m·K, and the thickness is 2.5 mm ± 0.1 mm; the bionic air duct structure has a shark skin non-smooth surface, the groove depth is 50 μm ± 5 μm, the spacing is 200 μm, and the inclination angle is 55° ± 2°; the heat dissipation efficiency adjustment logic satisfies: ; where represents the heat dissipation efficiency, represents the real-time temperature, and the unit is °C.

[0047] The adjustment command is sent to the cooling fan and the thermoelectric cooler through the CAN bus to achieve dynamic adjustment of the heat dissipation efficiency.

[0048] Therefore, by adopting the above-mentioned novel power energy storage device for a transmission line, the performance, reliability, and safety of the energy storage device are significantly improved, the service life is extended, the maintenance cost is reduced, and it is applicable to transmission lines under complex working conditions.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions of the present invention or make equivalent replacements, and these modifications or equivalent replacements do not enable the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A novel power energy storage device for a transmission line, characterized in that Including: A hybrid energy storage module, an embedded fault prediction unit, a dynamic equalization controller, and a composite heat dissipation housing; The hybrid energy storage module is composed of a vanadium redox flow battery unit, a solid-state lithium capacitor unit, and a supercapacitor unit connected in parallel through a bidirectional DC-DC converter. The output terminals of each unit are electrically connected through a DC bus; The embedded fault prediction unit is connected to the hybrid energy storage module through a data bus and includes a current harmonic analysis module, a temperature field reconstruction module, and a neural network accelerator. The output terminal of the current harmonic analysis module is signal-connected to the input terminal of the neural network accelerator; The dynamic equalization controller is respectively connected to the bidirectional DC-DC converter, the active equalization circuit of the solid-state lithium capacitor unit, and the microfluidic pump of the vanadium redox flow battery unit in the hybrid energy storage module through multiple PWM signal lines, receives the fault probability value output by the neural network accelerator, and generates a control instruction; The composite heat dissipation housing covers the outside of the hybrid energy storage module. The internal bionic air duct fits the surface of the hybrid energy storage module, and the heat dissipation efficiency is dynamically adjusted through the signal feedback of the temperature sensor.

2. The novel power storage device for a transmission line according to claim 1, wherein The structure of the solid-state lithium capacitor unit includes: the positive electrode material is single-crystal LiNi 0.8 Mn 0.1 Co 0.1 O2, with a specific capacity ≥ 200 mAh / g; the negative electrode material is a silicon-carbon nanowire array with a diameter ≤ 80 nm and a loading amount ≥ 4 mg / cm 2 ; the solid electrolyte layer is a Li 1.5 Al 0.5 Ge 1.5 (PO4)3 thin film with a thickness ≤ 20 μm and an ionic conductivity ≥ 1 mS / cm; the battery cells are connected by a copper-aluminum composite foil, and the adjacent battery cell gaps are filled with an aerogel thermal insulation layer with a thermal conductivity ≤ 0.02 W / m·K.

3. A novel power storage device for a transmission line according to claim 1, characterized in that, The circuit topology of the hybrid energy storage module includes: a triple interleaved parallel DC-DC converter is used between the vanadium redox flow battery unit and the solid-state lithium capacitor unit, with an efficiency ≥ 97% and a ripple ≤ 1%; the supercapacitor unit is directly connected to the DC bus and suppresses high-frequency oscillations through a distributed micro inductor with an inductance value of 20 nH ± 5%; redundant switching channels are set between each unit, and the switching response time ≤ 100 μs. The switching trigger signal is transmitted by the dynamic equalization controller through an optocoupler isolation circuit.

4. A novel power storage device for a transmission line according to claim 1, characterized in that, The coefficient update rule of the FIR filter bank of the current harmonic analysis module is as follows: Based on historical fault data, the center frequency is dynamically adjusted, and the update formula is: ； Among them, represents the new center frequency, represents the old center frequency, represents the learning rate, represents the amplitude of the th harmonic, represents the frequency corresponding to the th harmonic; The filter coefficients are updated online through the JTAG interface every 24 hours; During the update, a sliding window mechanism is used to select the nearest 100,000 groups of sampling points as the update data window.

5. A novel power storage device for a transmission line according to claim 1, characterized in that, The current harmonic analysis module real-time collects the line current signal, extracts the characteristic harmonic spectrum data through a programmable FIR filter bank, its center frequency is dynamically configured as 6 kHz, 12 kHz, 18 kHz, and the extracted characteristic harmonic spectrum data is transmitted to the neural network accelerator through the SPI interface.

6. A novel power storage device for a transmission line according to claim 1, characterized in that, The temperature field reconstruction module collects temperature data through a distributed fiber optic sensor and sends the collected temperature data to the neural network accelerator through the I2C bus.

7. A novel power storage device for a transmission line according to claim 1, characterized in that, The neural network accelerator internally has an LSTM-TCN hybrid model, which calculates the input harmonic distortion rate, temperature gradient matrix, and historical fault time series, and outputs a fault probability value; The weights of the LSTM-TCN hybrid model are obtained through an improved whale optimization algorithm training: Step S1, initialize the positions of the whale population. Each whale represents a set of connection weights and bias parameters of the LSTM-TCN hybrid model; Step S2, define the fitness function, and the calculation formula is: ； Among them, represents the fitness value, represents the harmonic mean of the accuracy and recall rate predicted by the model, represents the time required for the model to calculate and output the fault probability value, represents the energy consumption during the operation of the model; Step S3, iteratively update the positions of the whale population: Calculate the fitness value of each whale; Select the optimal whale according to the fitness value; Simulate the encirclement, spiral update, and prey search behaviors of the whales to update the positions of the whale population; Step S4: Introduce gradient information during the iteration process, combine with the gradient descent method, calculate the gradient of the loss function with respect to the model parameters, and adjust the parameters along the gradient direction when updating the whale position; Step S5: Normalize the model weights in each iteration; Step S6: Repeat Step S2 to Step S5 until the maximum number of iterations is reached or the convergence condition is satisfied, and output the connection weights and bias parameters of the finally optimized LSTM-TCN hybrid model.

8. A novel power storage device for a transmission line according to claim 1, characterized in that, The dynamic balance controller receives the fault probability value output by the neural network accelerator. When the fault probability value ≥ 0.6, it sends a three-level pre-charge instruction to the hybrid energy storage module to control the working states of the supercapacitor unit, the solid-state lithium capacitor unit, and the all-vanadium redox flow battery unit. Among them, the PWM duty cycle of the pre-charge instruction and the fault probability value satisfy a linear relationship: ； Among them, represents the PWM duty cycle of the pre-charge command, represents the fault probability value.

9. A novel power storage device for a transmission line according to claim 1, characterized in that, The design of the composite heat dissipation housing includes: the phase change material layer is a paraffin-expanded graphite-boron nitride composite material, with a phase change latent heat ≥ 200 J / g, a thermal conductivity ≥ 18 W / m·K, and a thickness of 2.5 mm ± 0.1 mm; the bionic air duct structure has a shark skin non-smooth surface, with a groove depth of 50 μm ± 5 μm, a spacing of 200 μm, and an inclination angle of 55° ± 2°; the heat dissipation efficiency adjustment logic satisfies: ； Among them, represents the heat dissipation efficiency, represents the real-time temperature, with the unit of °C, represents the base of the natural logarithm.

Images