807 results about "Energy technology" patented technology

The invention provides an energy coordination control system and scheduling method for multi-energy complementary new energy storage, and belongs to the technical field of new energy storage and energy technology management. The data acquisition and processing module is connected with a current and voltage sensor, a power transmitter, a meteorological station sensor and a battery management system sensor, and is used for acquiring voltage, current, power, state of charge and environmental data of photovoltaic power, wind power, energy storage and load through the sensors; and sliding window filtering and wavelet de-noising processing are carried out through the embedded processor. The method has the beneficial effects that the uncertainty of wind and light output is effectively processed by establishing a layered distributed optimization architecture and adopting a method of combining multi-objective optimization and robust optimization, and the consumption rate of renewable energy sources can be remarkably improved, the net load fluctuation can be reduced and the energy consumption can be reduced on the premise of meeting various system operation constraints. Therefore, dependence on conventional fossil energy is reduced, and the economic operation level and the environmental protection benefit of the whole energy system are improved.

The invention discloses a fusion power generation system, a power generation control method, a storage medium and a controller, and relates to the technical field of fusion energy. The fusion power generation system comprises a steam generator set, a plurality of Tokamak devices and a plurality of thermal conversion units, the Tokamak devices and the thermal conversion units are in one-to-one correspondence, each thermal conversion unit is provided with a first channel and a second channel, and the Tokamak devices and the first channels of the corresponding thermal conversion units form a cladding cooling loop. The steam generator set and a plurality of second channels connected in sequence form a power generation loop; wherein the plurality of Tokamak devices are configured to operate in an alternating or complementary manner; the thermal conversion units are configured to receive heat from the corresponding cladding cooling loops and convert working media in the power generation loops into steam through the heat so as to drive the steam generator set to generate power. According to the system, the plurality of Tokamak devices operate in an alternating or complementary mode, so that heat loss can be reduced, the power generation efficiency is improved, and the plasma control difficulty is reduced.

The invention belongs to the technical field of new energy, and particularly relates to a fault voltage ride-through optimization method and system for a network construction type energy storage converter. Carrying out positive and negative sequence separation and Clark-Park coordinate transformation on the three-phase power grid voltage and the inversion current, calculating active power and reactive power of the network-forming type energy storage converter, and carrying out power loop control to obtain three-phase reference voltage and angular velocity; performing voltage loop control, and dynamically adjusting a positive sequence active current and a positive sequence reactive current according to whether a low-voltage-crossing indication signal exists or not; performing positive-sequence current loop control and negative-sequence current loop control, and then performing inverse Clark-park conversion to obtain positive-sequence three-phase reference voltage and negative-sequence three-phase reference voltage; and superposing the positive-sequence three-phase reference voltage and the negative-sequence three-phase reference voltage for PWM (Pulse Width Modulation). According to the invention, when the power grid voltage is unbalanced due to a fault, the oscillation of the direct current side voltage and power caused by the negative sequence component is eliminated, and the power angle stability is improved and the fault current is suppressed by dynamically adjusting the related reference value during the fault voltage ride-through period.

The invention provides a network construction current limiting method, network construction type converter equipment and a new energy system, and relates to the technical field of new energy. The method comprises the following steps: in response to a condition that a power grid signal meets a preset condition, determining that network-forming converter equipment enters a current-limiting mode, and determining virtual impedance of a first stage of the current-limiting mode; determining that the network construction type converter equipment is in a first stage, and controlling the network construction type converter equipment by using the virtual impedance; and determining that the network construction type converter equipment is in a second stage of the current limiting mode, adjusting the virtual impedance according to the power grid signal, and controlling the network construction type converter equipment by using the adjusted virtual impedance. According to the embodiment of the invention, the current limiting mode of the network-forming converter equipment is divided into the first stage and the second stage, and the virtual impedance of the first stage is adjusted in the second stage, so that fault current limitation and power grid voltage support can be considered at the same time.

The invention discloses a wind-solar-storage integrated direct-current micro-grid device and a control method, and relates to the technical field of rural distributed energy. The device comprises a perovskite photovoltaic module array, a vertical axis fan set, a lithium iron phosphate energy storage module, a direct-current power distribution unit, an intelligent control module and a household direct-current terminal, each energy unit and a load are directly connected through a direct current bus, AC / DC conversion loss is reduced, the intelligent control module dynamically adjusts a wind-solar-storage cooperative operation strategy based on illumination, wind speed and electrical load data, and the functions of five-hour stable off-grid power supply and peak-valley arbitrage are achieved. The method adapts to a rural farm house roof resource concentration scene, solves the problems of high loss and poor off-grid stability of a traditional alternating current micro-grid, remarkably improves the energy utilization efficiency, reduces the electricity utilization cost of farmers, and can be widely applied to energy transformation projects in rural areas such as coastal areas.

The invention relates to a lithium ion battery multilayer metal foil and dissimilar metal connection optimization method in the technical field of new energy, and the method comprises the following steps: constructing a geometric model of multilayer metal foil and dissimilar metal connection by adopting a finite element simulation method according to initial interface bonding parameters, and applying a preset load condition in a simulation environment, determining an atomic-scale combined stress distribution diagram; for a heat balance state formed by metallurgical bonding, quantitative indexes, including shear strength and tensile strength, of connection point strength are extracted from a finite element simulation result, and a preliminary optimization data set of high-energy-density battery connection is obtained; and outputting a final metallurgical bonding formation parameter set according to a judgment result of a connection point strength stability threshold value, and applying the final metallurgical bonding formation parameter set to simulation verification of multi-layer metal foil connection so as to obtain an interface optimization scheme for improving the battery performance.

The invention relates to the technical field of new energy, in particular to a negative pole piece for a battery without a negative active material, a preparation method and application. The preparation method comprises the following steps: under the protection of inert gas, dissolving a fluoroborate-containing oxalate material in an in-situ polymerization monomer to form a solution; and then uniformly coating the surface of a metal current collector and carrying out heating in-situ polymerization to obtain the negative pole piece for the battery without the negative active material. The negative pole piece is applied to the battery, so that lithium (sodium) can be prevented from directly contacting with other components of the battery to generate side reaction, and high-temperature gas expansion of the battery is inhibited; meanwhile, the negative pole piece without the negative active material has a certain lithium (sodium) supplementing effect, can effectively induce uniform deposition of lithium (sodium) and inhibit generation of dendrites and dead lithium (sodium), and the first efficiency and the cycle capacity retention ratio of the battery are greatly improved.

The invention relates to the technical field of new energy, and discloses an optimization method for an intelligent yaw system of a wind generating set, and the method comprises the steps: building the intelligent yaw system, enabling the system to be internally provided with seven modules, and enabling a multi-sensor data collection module to collect wind direction, wind speed and yaw angle data in real time, the data fusion module performs Kalman filtering fusion processing to obtain a high-confidence state estimation value, the intelligent decision output module generates an optimal yaw control instruction by adopting a multi-mode control strategy and a parameter self-adaptive mechanism based on fused data, an execution mechanism is driven to realize accurate wind alignment, and the system integrated hardware-in-the-loop test module is used for realizing accurate wind alignment. Omnibearing verification can be carried out before deployment, after actual operation, operation indexes are continuously monitored through the performance evaluation module, control parameters and fusion algorithm parameters are adjusted online through the optimization module on the basis of methods such as machine learning, closed-loop optimization is formed, finally, yaw precision, response speed and system stability are remarkably improved, and maintenance cost is reduced.

The invention discloses a charging station dynamic pricing method based on multi-source information fusion, and belongs to the technical field of new energy, and the method comprises the steps: obtaining the environment data of a current moment in a region, building an urban fast charging load simulation model, and constructing a charging selection model; constructing a charging station dynamic pricing model based on a reinforcement learning network to calculate the city fast charging load data at the current moment and the pricing strategy of each charging station, and calculating the charging cost of each electric vehicle going to each charging station according to the pricing strategy of each charging station at the current moment; calculating the probability that each vehicle selects each charging station based on the charging selection mathematical model, and updating the city fast charging load simulation model according to the probability that each vehicle selects each charging station; and judging whether the previous charging station pricing strategy update reaches a preset update period interval or not to update the pricing strategy. The technical problems that the charging station is low in operation efficiency, long in charging waiting time and uneven in power grid load distribution are solved.

The invention relates to the field of ocean renewable energy technology utilization, and provides an oscillating water column type wave energy power generation device based on a superstructure, which comprises an oscillating water column main body, a superstructure assembly, a top shell and a power generation unit, and is characterized in that the interior of the oscillating water column main body is provided with the superstructure assembly formed by a plurality of guide plates which are arranged along the radial direction and extend in a horn shape; the oscillating water column body is internally divided into a plurality of independent oscillating water column cavities with gradually-changed sizes by combining with the partition plate assembly, an air chamber is defined by the top shell and the oscillating water column body, and airflow energy generated by water column oscillation driving is converted into electric energy through the power generation unit. The power generation unit can adopt a plurality of split type air turbines to generate power or a general type air turbine to generate power. The special fluctuation performance of the superstructure is fully exerted, efficient broadband capture and wave absorption are achieved, meanwhile, wave loads are effectively reduced, diversified integration of wave energy power generation devices is developed, sea area resources and operation and maintenance cost are saved, and negative environmental influences are reduced.

The invention discloses a hydrogen production system flexibility improving method based on multi-source cooperation and self-adaptive regulation and control, and belongs to the technical field of new energy. The method is executed by taking a digital twinborn body as a global decision center, and comprises the following steps: acquiring predicted data of wind-solar power generation power, a real-time frequency deviation signal of a power grid and an operation state of each electrolytic cell in a hydrogen production system; based on the prediction data and the frequency deviation signal of the wind-solar power generation power, a global optimization scheduling instruction is generated by taking improvement of the flexibility and the economy of the system as a target; according to the global optimization scheduling instruction, cooperatively controlling dynamic reconfiguration of the electrolytic cell and applying virtual synchronous generator (VSG) control to a hydrogen production load; and actual operation data after cooperative control are collected and fed back to the equipment fatigue loss analysis model and the wind and light output prediction model for dynamic correction of fatigue damage evaluation and power prediction in the next period. According to the method, the operation cost of the system is effectively reduced, and meanwhile the flexibility of the new energy hydrogen production system is greatly improved.

The invention discloses a tidal current energy water turbine array flow field sensing and intelligent control system, which relates to the technical field of ocean renewable energy sources and comprises a flow field sensing module, an array state monitoring module, an intelligent control module, a data storage and analysis module and an emergency response module. The flow field sensing module comprises a dynamic calibration sub-module and a short-term prediction sub-module, and equipment such as an acoustic Doppler current meter is adopted; the array state monitoring module comprises a fault grading diagnosis sub-module; the intelligent control module comprises a wake flow avoidance sub-module, a yaw self-adaption sub-module and a power optimization sub-module, and adjustment is achieved through combination of a PLC and a PID. The data storage and analysis module adopts a mode of combining local solid-state storage and cloud, and BP and LSTM models are built in the data storage and analysis module; the emergency response module can dispose six types of scenes in a grading manner. The flow field sensing error is effectively reduced, the array generating capacity standard-reaching rate is improved, the fault response time is shortened, the operation and maintenance cost is reduced, the grid-connected stability is enhanced, and the comprehensive energy efficiency is improved.

The invention discloses an underwater robot multi-source energy system and an energy management method, and relates to the technical field of underwater robot energy, and the system comprises a lithium ion battery which is directly connected in parallel with a DC bus; the super capacitor is connected to the direct current bus through the bidirectional DC / DC converter; the flexible power generation module is used for capturing water flow disturbance and mechanical vibration energy in the environment where the underwater robot is located; the propelling kinetic energy recycling unit has a driving mode and a power generation mode and is used for recycling kinetic energy in the propelling and braking processes of the robot; the battery management system is used for monitoring the voltage, the current, the temperature and the SOC state of each energy unit in real time and executing an energy distribution strategy based on multi-source information fusion; wherein the battery management system communicates with the bidirectional DC / DC converter through a CAN bus, and cooperatively controls an energy flow path. The method has the advantages that the energy utilization efficiency is improved, the dynamic response capability is enhanced, and the cruising ability is prolonged.

The invention relates to the technical field of new energy, and discloses a battery and a battery pack, the battery comprises: a shell, the shell contains a Ti element, and the mass of the Ti element accounts for more than or equal to 60% of the total mass of the shell; the pole column is arranged on the shell; the battery cell comprises a battery cell body and tabs, the tabs comprise a positive tab and a negative tab, one of the positive tab and the negative tab is electrically connected with the pole, and the other one of the positive tab and the negative tab is electrically connected with the shell; the ratio of the mass of the Ti element of the shell to the total mass of the shell is a, the conductivity of the shell is b, and the lead-out size of the tab from the cell body is c; a. C / b is greater than or equal to 99 and less than or equal to 3650. According to the battery provided by the invention, the relationship among a, b and c is comprehensively controlled, so that the light weight of the shell is realized, the over-current capability of the battery can be met, the battery is prevented from generating relatively large temperature rise, and the condition that the safety performance of the battery is poor is prevented.

The invention provides a transformer area two-stage distribution robust line loss optimization method considering wind and light uncertainty, and belongs to the technical field of new energy. Firstly, a day-ahead-real-time two-stage line loss optimization method is constructed, and in the day-ahead stage, a K-means clustering algorithm and a conditional generative adversarial network are combined to generate a multi-scene sample set capable of reflecting the uncertainty of wind and light output; in a real-time stage, based on a day-ahead optimization result and updated output information, a multi-scene distribution robust optimization model is utilized to realize joint correction of line loss and economic dispatching; in the optimization solution process, a forward-backward substitution method is adopted to embed the load flow calculation model so as to accurately reflect the line transmission loss of the transformer area power distribution network; secondly, a distributed robust optimization method based on scene generation is constructed, historical wind and light data are utilized, a diversified scene set is generated through K-means clustering and a conditional generative adversarial network, and distributed robust optimization planning and correction are carried out in different scenes.

The invention discloses a hydrogen energy production and production-and-use distributed energy supply system, which relates to the technical field of new energy, and comprises a hydrogen production module which comprises a proton exchange membrane electrolytic tank, an alkaline electrolytic tank and a solid oxide electrolytic tank and runs through a three-mode collaborative architecture, in combination with a light-electricity-heat synergistic catalysis device and a wastewater or industrial tail gas coupling hydrogen production device, the hydrogen storage and safety management module comprises a metal hydride hydrogen storage unit, a metal organic framework material hydrogen storage unit and a liquid organic hydrogen storage unit. According to the invention, multi-source, high-efficiency and low-cost hydrogen production is realized through the hydrogen production module with a three-mode collaborative architecture in combination with light-electricity-heat collaborative catalysis and wastewater / industrial tail gas coupling hydrogen production, and meanwhile, a solid oxide fuel cell and micro gas turbine combined cycle, a hydrogen combustion turbine direct drive and a multi-type energy storage unit in the energy supply module realize multi-source, high-efficiency and low-cost hydrogen production. And in cooperation with waste heat-cold energy gradient utilization, the energy conversion efficiency and the comprehensive energy utilization rate are greatly improved.

The invention relates to the technical field of efficient clean energy, and discloses a fuel Wobbe number stabilizing system for a chemical regenerative gas turbine and a control method, and the system comprises an exhaust bypass mixing regulation and control component which comprises a regulation and control module, a monitoring module and a control module; the regulation and control module comprises a diverter valve and a bypass flow regulating valve, the inlet end of the diverter valve is connected to an exhaust outlet of the turbine, the outlet end of the diverter valve is sequentially connected with the heat regenerator through a first branch, the bypass flow regulating valve is further connected between the diverter valve and the heat regenerator through a second branch, and the first branch and the second branch are connected to the cracker through a confluence pipeline; the monitoring module comprises a first temperature sensor, a first pressure sensor, a densimeter, a rapid component analyzer and a temperature monitoring unit; the control module generates a control instruction for the mixing temperature of exhaust gas entering the cracker according to the comparison result of the wobbe number estimated value and the wobbe number target reference value, and adjusts the opening degree of the bypass flow adjusting valve so as to solve the technical problem of unstable combustion.

The invention relates to a lightweight battery residual life prediction method and system based on step-by-step knowledge distillation, and belongs to the field of battery energy technologies. According to the method, a teacher model for local-global degradation feature reconstruction and a student model carrying working condition information monitoring are constructed, a two-stage parameter freezing distillation strategy is adopted, potential features and reconstruction features are aligned firstly, and then a soft and hard loss optimization prediction module is fused, so that high-precision and lightweight prediction of the residual life of the battery is realized; and the adaptability and the calculation efficiency under different working conditions are effectively improved.

The invention belongs to the technical field of building energy, and discloses a multi-energy complementary optimization design method of a negative carbon ecological building. Comprising the following steps: according to environment monitoring data and building geometric data of a target building site, constructing a hourly output characteristic spectrum of a photovoltaic module and a photo-thermal collector at the building site scale; extracting an output space-time correlation mode of the photovoltaic module and the photo-thermal collector based on the hourly output characteristic spectrum; according to the matching relationship between the output space-time correlation mode and the building energy load demand, combining the available area constraint of the target building site to construct a space arrangement scheme; evaluating the negative carbon performance index of the building according to the spatial arrangement scheme and the carbon emission in the whole life cycle of the building; outputting a multi-energy complementary optimization design scheme of the building site; according to the invention, the real carbon negative target of the building from building materials to the whole life cycle of operation is realized, and the energy utilization efficiency and the carbon emission reduction stability are obviously improved under the working conditions of all climate and full frequency band.

The invention provides multifunctional energy storage concrete, application thereof and an energy storage concrete member, and belongs to the technical field of concrete. The multifunctional energy storage concrete is prepared from the following components in parts by weight: 300 to 600 parts of ordinary Portland cement, 30 to 100 parts of mineral admixture, 300 to 700 parts of quartz sand, 5 to 60 parts of conductive material, 4 to 8 parts of admixture and 120 to 250 parts of water. The conductive material is added into the concrete, and a conductive network can be formed in the concrete material, so that the concrete has electric energy storage and conduction functions. The energy storage concrete provided by the invention can be used as a structural member for energy storage, and can also be combined with other energy technologies (such as solar energy and wireless charging) to realize integration of power generation, storage and utilization.

The invention belongs to the technical field of clean energy, particularly relates to a hydrogen production project economic evaluation method and system and electronic equipment, and aims to solve the problem that an existing hydrogen production project evaluation method is not accurate enough. The method comprises the following steps: acquiring each cash flow index influencing the corrected cash flow; analyzing the cash flow indexes of the tth year to obtain the correction probability of each cash flow index, and calculating the hydrogen production item correction cash flow of the tth year based on each cash flow index and the correction probability of each cash flow index; based on the corrected cash flow, calculating to obtain a corrected hydrogen production item net present value; and calculating the internal investment return rate of the corrected hydrogen production project based on the net present value of the corrected hydrogen production project. According to the method, the cost and income constituent elements of the hydrogen production project are comprehensively analyzed, the dynamic change condition of each actual influence factor is considered, and the obtained conclusion is more accurate and real.

The application relates to a liquid flow energy storage device and relates to the technical field of new energy sources. The liquid flow energy storage device comprises an energy storage system and a discharge system, the energy storage system and the discharge system both comprise an electric membrane stack, the electric membrane stack comprises a positive electrode chamber, a proton chamber and a negative electrode chamber which are sequentially arranged and are in fluid communication, liquid in the proton chamber only transmits protons and does not participate in electrochemical reactions in the energy storage system and electrochemical reactions in the discharge system, so that even if a small amount of iodine ions enter the proton chamber, the iodine ions will leave the electric membrane stack along with the circulation of the liquid, and thus the iodine ions in the proton chamber cannot migrate to the positive electrode chamber, the membrane damage caused by the migration of the iodine ions is avoided, and therefore the service life and the efficiency of the electric membrane stack can be greatly improved.

The invention provides a network construction type energy storage system and a multi-phase multi-port motor, and relates to the technical field of energy. The networking type energy storage system comprises a plurality of battery energy storage units and a multi-phase multi-port motor. The multi-phase multi-port motor comprises a stator and a rotor, the stator is provided with a stator winding, the rotor is provided with m sets of rotor windings, the m sets of rotor windings form m mutually independent electrical ports, m is greater than or equal to 1, and m is an integer; the stator winding is connected with a power grid; each battery energy storage unit comprises a battery unit and a power adjusting unit, and the battery unit is electrically connected with an electrical port formed by one set of rotor windings through the power adjusting unit. By adopting the scheme, the technical problem that circulating current is easily generated when a plurality of power regulation systems in the existing energy storage system are operated in parallel can be solved, and the power loss and the equipment temperature are reduced.

The invention discloses a modular container type electric heat hydrogen co-production device, which belongs to the technical field of renewable energy sources and comprises a box body, and an electrical device, a hydrogen production device, a hydrogen storage device, a fuel cell, an explosion-proof wall, an isolation plate and a grating platform which are integrated in the box body, the interior of the box body is sequentially divided into a cabin A, a cabin B and a cabin C from one end to the other end in the length direction; the cabin A and the cabin B are separated through an explosion-proof wall, and the cabin B and the cabin C are separated through a separation plate; the grating platform is arranged in a cabin C, and the cabin C is divided into an upper space and a lower space; the electrical device is located in the cabin A, the hydrogen production device is located in the cabin B, the hydrogen storage device is located on the lower portion of the cabin C, and the fuel cell is located on the upper portion of the cabin C and arranged on the grating platform. According to the invention, an efficient and compact alkaline hydrogen production device is realized, a compact fuel cell system and a high-density solid hydrogen storage device are integrated, and a compact electric-thermal-hydrogen co-production system which can be flexibly deployed is formed.

The invention relates to the technical field of biological energy, and particularly discloses a method for producing hydrogen by using a coal mine goaf, which comprises the following steps: mixing pretreated agricultural organic wastes with fermentation liquor and a culture solution containing a methane inhibitor, and conveying the mixture to the coal mine goaf through an injection well; utilizing natural ground temperature conditions in the goaf to enable microorganisms to perform co-fermentation on residual coal in the goaf and the injected agricultural organic waste to produce hydrogen; produced hydrogen is collected and output through a gas producing well, and fermentation residues are discharged through a material producing well. According to the hydrogen production method provided by the invention, the goaf is used as a natural reactor, and two wastes are synergistically converted, so that the hydrogen production cost and energy consumption are greatly reduced, meanwhile, environmental pollution is effectively avoided, and a new green way is provided for resource utilization of waste mines.

The invention discloses a water management method of a coupling system based on a PEM water electrolysis module and an EHC module, and relates to the technical field of hydrogen energy. By controlling the optimal current density of the PEM electrolyzed water module, the content of water entering the EHC module is adjusted, so that the EHC module always operates in the optimal hydration state, and the overall efficiency of the system is improved. The method comprises the following steps: S1, establishing a relation model JPEM-r between the optimal current density of a PEM electrolyzed water module and the target pressure ratio of an EHC module; S2, obtaining the target pressure ratio of the EHC module; s3, according to the target pressure ratio of the EHC module, the optimal current density of the PEM electrolyzed water module is obtained through the JPEM-r relation model; and S4, adjusting the real-time current density of the PEM water electrolysis module to the target current density to realize water management of the EHC system. The invention further discloses a coupling system based on the PEM electrolyzed water module and the EHC module. The coupling system is used for improving the performance of the coupling system of the PEM electrolyzed water module and the EHC module.

The invention discloses an energy storage scheme evaluation method and system based on an entropy weight method, which is applied to the technical field of energy technology evaluation, and comprises the following steps: determining a plurality of dimension index values at least comprising a response dimension from each energy storage scheme, wherein the first index value of the response dimension is obtained by firstly extracting charging and discharging output and original load data in a scheme, determining a typical daily net load output curve through data processing, then extracting load characteristic data such as response time, power density and energy density from the curve, and further determining a response index value; the index values of all dimensions are processed through an entropy weight method, weighted data of each energy storage scheme are obtained, finally, comprehensive evaluation results are obtained based on the weighted data through an approximate ideal solution sorting method and sorted, and finally quantitative evaluation results of all the energy storage schemes are output. According to the energy storage scheme evaluation method based on the entropy weight method provided by the invention, a fair and credible quantitative basis can be provided for energy storage scheme evaluation.

This invention relates to the field of new energy technology and discloses a battery cell and an electrical device. The battery cell includes: a shell having an opening along a first direction; a top surface of the shell formed at the end face of the opening along the first direction; a cover plate disposed at the opening of the shell, the cover plate including a body portion and an overlapping portion, the overlapping portion abutting against the top surface of the shell along the first direction; and a welding portion adapted to weld the shell and the cover plate together, the welding portion forming a molten first end and a molten second end, the direction from the molten first end to the molten second end being the welding direction; in a plane perpendicular to the welding direction, the projected area of ​​the molten first end is larger than the projected area of ​​the molten second end; along the welding direction, the molten second end is located within the body portion area. The battery cell provided by this invention allows the heat-affected zone during welding to penetrate deep into the interior of the cover plate along a direction perpendicular to the first direction, reducing the impact of the heat-affected zone on the thickness direction of the shell and improving the strength of the shell.

This invention belongs to the fields of new energy technology and artificial intelligence technology, and provides a high-resolution long-term photovoltaic power prediction method and system based on a dual-branch architecture. By constructing a parallel dual-branch architecture, the baseline branch extracts multi-scale features, and the ramp branch identifies power ramping events. The features from both branches are embedded through multiple channels and then fed into a BiGRU-Enhanced Transformer model with shared weights. By strategically deploying BiGRU layers at the input and between the encoder and decoder, local instantaneous dependencies and global long-term trends are captured simultaneously. A multi-task joint optimization loss function is designed for the ramp branch, using weighted cross-entropy and... L The probability, temporal location, and fluctuation amplitude of slope occurrence are jointly optimized using the L1 norm. Finally, nonlinear residual correction is applied to the outputs of the two branches to achieve the final prediction. This invention effectively overcomes the oversmoothing effect of deep learning models, demonstrating extremely high capture accuracy and robustness in long-term prediction of one month's worth of data at 1-minute resolution.

This invention relates to the field of new energy technology and discloses a soft-pack battery and an electrical device. The soft-pack battery includes: a casing, a cell, and electrode sheets. The casing has a through-hole suitable for the electrode sheets to pass through, and the electrode sheets are at least partially disposed within the through-hole. A sealing and insulating member is disposed between the electrode sheets and the casing, and along a first direction, the sealing and insulating member is at least partially located within the through-hole. The electrode sheets have a notch at at least one end in a third direction, and the notch is connected to the casing through the sealing and insulating member. Along a second direction, the maximum size of the notch is A mm, and the thickness of the electrode sheet is B mm, satisfying: 0.069 ≤ A / B ≤ 0.889. The soft-pack battery provided by this invention controls A / B within a reasonable range, which can optimize the interlayer bonding form of the hot-press sealing while ensuring the conductivity of the electrode sheets, thereby improving the sealing reliability.