272results about How to "Achieve lightweight" patented technology

The invention relates to the technical field of multi-unmanned-aerial-vehicle cooperative operation and three-dimensional modeling, in particular to a multi-unmanned-aerial-vehicle cooperative three-dimensional rapid modeling method for a highway accident scene, and the method comprises the steps: generating a three-dimensional grid map of an accident area through the scanning of a millimeter-wave radar by a main control unmanned aerial vehicle; subareas are divided according to a load balancing strategy and are distributed to slave unmanned aerial vehicles, the slave unmanned aerial vehicles traverse grids along a snake-shaped track, laser radar point clouds and five-view-angle images are synchronously collected, data are bound through double time stamps and space coordinates, the point clouds are preprocessed through edge computing nodes, and the point clouds are stored in a database; the master control unmanned aerial vehicle evaluates quality based on density standard deviation and overlapping matching degree and instructs to reacquire, performs high-precision Poisson reconstruction on an accident core area, performs voxelization processing on a peripheral area, maps image textures, optimizes vehicle deformation details, simplifies a model and retains key element precision, and finally performs data processing. License plate coordinates, a scattered object thermodynamic diagram and an emergency lane occupation state are automatically marked, a visual model is generated, and rapid and accurate restoration of an accident scene is realized.

The utility model provides a lamp holder light reflecting structure and a lamp. A pull aluminum profile of the device comprises a lamp plate clamping groove for clamping a light emitting unit, a light guide clamping groove for clamping a light guide plate, a radian shaping section for clamping a light reflecting plate and a second light reflecting clamping groove, the radian shaping section and the second light reflecting clamping groove are oppositely arranged at an angle, and the radian shaping section comprises a radian shaping section; when the reflecting plate is clamped and fixed in the radian shaping section and the second reflecting clamping groove, the overall radian is shaped through the arc-shaped shaping section. The lamp panel clamping groove, the light guide clamping groove and the light reflection clamping groove are integrally formed in the drawn aluminum profile, the core components of the lamp panel, the light reflection panel and the light guide plate are all integrated on the drawn aluminum profile made of the metal material, the working performance of the core components of the lamp is guaranteed, only two ends of the light reflection panel are clamped in the clamping grooves, and the bent appearance of the light reflection panel is limited by only one radian shaping section. The structure is simplified, the using amount of aluminum materials is reduced as much as possible, and light weight of the lamp is achieved to the maximum extent.

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.

This invention discloses an online search method for particle spelling variants and properties usable by intelligent agents. The steps are as follows: inputting the baseline spelling of a particle and the constructed particle-specific prompt words into a large language model to generate a core variant corresponding to the particle; integrating the core variant of each particle with the authoritative benchmark information corresponding to the particle to form a full variant set for each particle; each record in the full variant set contains a unique identifier for a particle, a multi-scene benchmark name, a core variant, and extended attributes; dynamically mapping a remotely callable interface set on the server to a local proxy object on the client; after receiving a query request, the local proxy object parses the particle spelling parameters in the query request and performs multi-dimensional spelling matching in the full variant set to realize online search for particle spelling variants and properties. This invention effectively improves the ability of AI intelligent agents to handle domain-specific tasks.

This invention belongs to the field of robot joint technology, specifically relating to a rope-driven, decoupled, dual-parallel five-DOF bionic shoulder joint, including a scapulothoracic joint mechanism, a glenohumeral joint mechanism, a drive base device, and drive ropes. The scapulothoracic joint mechanism and the glenohumeral joint mechanism are internally rotatably connected. The drive base device is used to fix the scapulothoracic joint mechanism and to provide drive ropes for both mechanisms. The scapulothoracic joint mechanism is constrained by a first constraint branch, a second constraint branch, and a decoupling through-line branch, satisfying the pure rolling two-DOF rotation requirement, driven by two sets of antagonistic drive ropes. The glenohumeral joint mechanism is driven by four independent drive ropes to achieve three-DOF rotational motion. The decoupling through-line branches distribute the drive ropes of the glenohumeral joint mechanism, achieving physical decoupling and ensuring that the drives of the two mechanisms do not interfere with each other. Through rope-driven and dual-parallel passive mechanisms, a larger range of motion can be achieved, improving the stiffness and load-bearing capacity of the mechanism.

The utility model provides a high-melting-point graphite pipe for elemental analysis, which belongs to the technical field of spectral analysis and comprises a circular hollow graphite pipe main body and transverse support parts symmetrically arranged on two sides of the graphite pipe main body, an inner pyrolytic carbon layer is deposited on the inner wall of the graphite pipe, a porous structure is arranged in the inner pyrolytic carbon layer, and an outer compact pyrolytic carbon layer is further deposited on the surface of the inner pyrolytic carbon layer. Through the inner pyrolytic carbon layer and the outer compact pyrolytic carbon layer, in the high-temperature working process, the inner wall pyrolytic carbon layer can be selectively consumed to form a compact glassy carbon film, a self-adaptive protection mechanism enables the graphite tube to still keep stable analysis performance under extreme conditions, reaction or permeation of a detected element and graphite at high temperature is reduced, and the analysis accuracy of the graphite tube is improved. The phenomenon of cross contamination is reduced, the memory effect of the graphite pipe is reduced by 70%, but the memory effect of a traditional pyrolytic graphite pipe can only be reduced by 30-40%, and the graphite pipe is particularly suitable for analysis of high-melting-point elements.

This application relates to the field of commercial vehicle body technology, and particularly to a front bulkhead structure for a commercial vehicle. The front bulkhead structure includes a front bulkhead beam, which comprises an upper crossbeam and a lower crossbeam, connected by a front bulkhead longitudinal beam. The upper crossbeam includes an upper crossbeam body and an upper crossbeam armrest mounting location, with the thickness of the armrest mounting location greater than the thickness of the upper crossbeam body. The lower crossbeam includes a mounting bracket, one end of which connects to the front bulkhead longitudinal beam, with the thickness of the mounting bracket greater than the thickness of the upper crossbeam body. This application provides a front bulkhead structure for commercial vehicles to address the problem in related technologies where adding reinforcing plates to strengthen the front bulkhead increases the number of parts and welding processes, making it difficult to achieve lightweight design.

The utility model discloses a kind of rear subframe, rear suspension assembly and car, comprising: main body frame, including front crossbeam, rear crossbeam, left side sill and right side sill, the front crossbeam, rear crossbeam, left side sill and right side sill are all made of hollow pipe material, the main body frame forms rear drive motor installation space between the front crossbeam and rear crossbeam, the middle part of left side sill and right side sill is curved upwards, the main body frame forms transmission shaft arrangement space below the curved position of left side sill and right side sill;Rear suspension mounting bracket is set in the main body frame.The utility model realizes the maximization of rear subframe universality of front drive and rear drive vehicle type, improves development efficiency, reduces rear subframe development cost, shortens development cycle.

This invention discloses a wind-resistant reinforced intelligent utility pole, which relates to the field of power construction technology. A connecting base is positioned on the upper side of the utility pole and remains fixed thereto. The lighting fixture is fixedly connected to an external support rod, which in turn is fixedly connected to a mounting frame. The mounting frame is inserted from the top of the utility pole, allowing it to mate snugly with the connecting base. A threaded connection exists between the mounting frame and the connecting base, improving installation efficiency and supporting the lighting mechanism. A rotating device is positioned on an annular groove. When the utility pole encounters strong winds, the wind force acts on the rotating device, causing it to rotate and reducing the frontal wind force and wind load. Furthermore, when the utility pole is installed on the adjustment device, the pole aligns the external plate with the U-shaped plate. The external plate and the U-shaped plate are then plugged in and threaded together, enhancing the fixation effect between components.

The embodiment of the present application provides a motor, a power assembly and a vehicle. The motor comprises: a shell assembly, a cooling cavity for cooling oil flow being arranged in the shell assembly, the shell assembly being provided with an oil inlet and an oil outlet communicating with the cooling cavity; a stator assembly, at least part of the stator assembly being arranged in the cooling cavity, so that the stator assembly can be at least partially immersed in the cooling oil; and a rotor assembly, rotatably sleeved on the inner side of the stator assembly. In the scheme, at least part of the stator assembly can be immersed in the cooling oil in the cooling cavity and directly contact with the cooling oil, so that the contact type oil cooling is realized. In this way, the cooling oil can be in full contact with the stator assembly under the hydraulic action as much as possible, so that the stator assembly and the cooling oil can have a relatively large contact area, the heat dissipation area of the stator assembly is improved, and the flowing cooling oil can timely take away the heat of the stator assembly, so that the heat dissipation efficiency of the motor can be greatly improved compared with the oil shower type cooling scheme.

The utility model belongs to the technical field of ground cleaning equipment, and particularly relates to an anti-tangling rolling brush which comprises a rolling brush body, the rolling brush body is rotatably connected to a rolling brush seat, the rolling brush body comprises a brush shaft shell, a first shaft cover and a second shaft cover, and the first shaft cover and the second shaft cover are installed at the two ends of the rolling brush shell. The first shaft cover is rotationally connected to the rolling brush base through a first transmission shaft, the second shaft cover is connected with the driving device through a transmission piece, and the brush shaft shell is formed by splicing a first shaft shell and a second shaft shell. The first comb teeth which are integrally formed with the first shaft shell in an injection molding mode are adopted to replace a traditional split type metal tool apron, the production cost of the part is reduced to a large extent, light weight is achieved, and meanwhile the first comb teeth and the second comb teeth are matched so that the protection function of a tool tooth piece can be achieved; the arranged cutter tooth piece can be made of plastic or metal materials, a user can choose by himself according to the use environment humidity, the cutter tooth piece replacement cost and the mute requirement, and the user requirement is further met.

This utility model relates to the field of new energy battery support structure technology, specifically to a lightweight battery pack composite material bracket, including a skeleton layer and a reinforcing layer covering the skeleton layer. Connection holes are provided on the skeleton layer and the reinforcing layer, with metal bushings pre-embedded in the connection holes. The skeleton layer includes a lower support plate connected to the battery pack and an upper support plate connected to the vehicle base. The reinforcing layer includes outer reinforcing ribs covering the outer end faces of the lower and upper support plates and inner reinforcing ribs covering the inner end face of the upper support plate. The skeleton layer is made of continuous fiber nylon, and the reinforcing layer is made of short fiber plastic. The upper and lower support plates are connected by side support plates, and the reinforcing layer also includes a side covering layer covering the side support plates. This battery pack composite material bracket solution achieves both lightweight design and high load-bearing capacity while reducing costs.

The application provides a phosphogypsum-based light high-strength steel pipe concrete and a preparation method thereof, and relates to the technical field of the steel pipe concrete.The steel pipe concrete comprises the following raw materials in parts by weight: 450-500 parts of a hydraulic cementitious material, 255-272 parts of phosphogypsum light aggregate, 480-610 parts of gravel with a particle size of 4.75-19.0 mm, 708-743 parts of medium-coarse sand, 3.24-5.85 parts of a water reducing agent and 150-156 parts of water; the hydraulic cementitious material is a gypsum-slag cement containing modified phosphogypsum.The application realizes the lightness, controllable micro-expansion property and good corrosion resistance of the steel pipe concrete on the basis of ensuring the strength of the steel pipe concrete, and controls the manufacturing cost of the steel pipe concrete.

The invention discloses a theme style sharing method and device and a server, and relates to the technical field of computers.The method comprises the steps that a first terminal adjusts configuration parameters of a local artificial intelligence model in response to personalized configuration operation on theme styles, and style configuration parameters are obtained; wherein the artificial intelligence model generates a target digital asset of a personalized theme style corresponding to the personalized configuration operation under the condition that the artificial intelligence model runs based on the style configuration parameters; performing structured processing on the style configuration parameters to generate a style configuration file; and sharing the style configuration file to a second terminal to enable the second terminal to restore the style configuration parameters based on the style configuration file, and generating a target digital asset based on a local artificial intelligence model and the style configuration parameters of the second terminal to reproduce the personalized theme style. According to the method and the device, the user can be supported to perform personalized creation on the theme style and perform efficient sharing on the creation result, and meanwhile, the shared theme style can be ensured to be accurately reproduced at the receiving end.

The utility model provides a vibrating diaphragm, which belongs to the technical field of vibrating diaphragms, and comprises at least one bonding layer, at least one side of each bonding layer is provided with a conductive layer, the connecting surface of the conductive layer and the bonding layer is a roughening treatment surface or a surface activation treatment surface, and the bonding layer and the conductive layer are in hot-pressing composite connection or bonding connection. According to the utility model, the bonding layer and the conductive layer are directly compounded, so that the requirement of bonding strength is met, the process is simplified, the problem of insufficient thickness of a magnetron sputtering coating can be effectively solved, and the negative influence of a glue bonding process on the compliance of the vibrating diaphragm can be avoided; therefore, the light weight of the planar diaphragm structure, the high sensitivity of the performance and the simplification of the manufacturing process are realized.

The invention provides a composite insulating layer of a light superconducting cable and a preparation method and application of the composite insulating layer. The composite insulating layer is prepared from the following raw materials in parts by weight: 40-60 parts of fusible polytetrafluoroethylene, 30-50 parts of fluorinated ethylene propylene, 0.5-5 parts of an auxiliary agent, 1-5 parts of filler and 0.1-0.6 part of a nucleating agent. The composite insulating layer of the light superconducting cable has relatively high tensile strength, relatively low dielectric constant and dielectric loss factor, good mechanical property and high insulating strength; compared with the prior art, the composite insulation layer has the advantages of low average cell diameter and high cell density, which indicates that a uniform and fine cell structure is formed in the composite insulation layer, the overall density of the material can be effectively reduced, the insulation layer is light, and the composite insulation layer can be applied to preparation of light superconducting cables for medical equipment and realizes integrity and low loss of high-frequency signal transmission.

This invention discloses a multi-layer composite midsole capable of mounting airbag pads, belonging to the field of shoe midsole technology. The midsole comprises a body formed by stacking and fixing multiple layers of boards. The midsole body includes at least a top plate and a support layer located below the top plate. The midsole body has pre-reserved mounting positions for front and rear airbags. The top plate has a front mounting opening in the forefoot area and a rear mounting opening in the heel area, with different external dimensions for the front and rear mounting openings. The support layer has support surfaces in at least the rear half of the forefoot area and the heel area. The dimensions of both the front and rear mounting openings are larger than the horizontal projection size of the airbag. After installation, the top of the airbag protrudes from or is flush with the top surface of the top plate, while the lower half rests on the support surface, with a gap between the outer periphery of the airbag and the inner wall of the mounting opening. This invention achieves the dual effect of fixed-point support at the bottom of the airbag and buffer force transmission at the top by combining layered plates with assembly ports. It has the advantages of lightweight structure, simple processing, airbag can be replaced individually, and smooth exhaust. It overcomes the defects of existing airbag midsole that is easy to collapse or completely closed and cannot contact the sole of the foot.

This application relates to the field of nuclear reactors, specifically to a reactor comprising: a reactor vessel, a core assembly, a support member, a shielding assembly, a coolant heat exchange and delivery assembly, and a reactivity control assembly. The reactor vessel forms a top opening; the support member provides support for the core assembly within the reactor vessel, and a coolant flow channel is formed between the support member and the reactor vessel for coolant flow; the shielding assembly is disposed within the reactor vessel to provide shielding for the core assembly; the coolant heat exchange and delivery assembly is configured to drive coolant to flow within the coolant flow channel to the core assembly to cool the core assembly, and to guide and cool the coolant flowing out of the core assembly; the reactivity control assembly controls the reactivity of the reactor; the support member also supports the coolant heat exchange and delivery assembly, and together with the coolant heat exchange and delivery assembly, closes the top opening. The reactor components of this application are relatively concentrated and compact, achieving a small reactor design.

This application belongs to the field of ultrasonic testing equipment, specifically disclosing an automatic focusing mechanism for ultrasonic testing that follows the curvature of a curved surface. The mechanism includes a linear module, a frameless motor, and an automatic focusing module. The automatic focusing module is connected to the lead screw structure of the linear module, and the frameless motor is also connected to the linear module. The automatic focusing module drives the lead screw structure of the linear module to reciprocate along the Z-axis to move closer to or further away from the sample to be tested. The automatic focusing module includes a voice coil motor and an ultrasonic probe. The voice coil motor is fixedly connected to the lead screw structure, and the ultrasonic probe is fixedly connected to the voice coil motor. The voice coil motor drives the ultrasonic probe to reciprocate along the Z-axis according to the curvature of the sample to be tested. This application enables the dynamic maintenance of a constant focal length for the ultrasonic probe, ensuring that both the center and edge areas of the product under test can be detected completely and clearly, thereby obtaining a clear acoustic image and achieving consistent imaging across the entire field of view.

The invention discloses a steel frame structure damage diagnosis method based on a one-dimensional depth separable convolutional neural network, and the method comprises the steps: constructing a neural network model for steel frame structure damage diagnosis through employing a one-dimensional depth separable convolutional kernel, carrying out the preprocessing of a to-be-diagnosed steel frame vibration response signal, dividing a training set and a test set, and carrying out the detection of the to-be-diagnosed steel frame vibration response signal. Inputting into a steel frame structure damage diagnosis model to determine a current damage type; according to the scheme, a neural network structure layer comprises a trunk part, three groups of one-dimensional depth separable convolution blocks, two independent depth separable convolution layers and three maximum pooling layers, the depth separable convolution blocks extract local features of input data, the maximum pooling layers carry out pooling operation on local areas of the input data, and the maximum pooling layers carry out pooling operation on the local areas of the input data. And finally inputting to a full connection layer to finish classification. According to the method, the damage type of the steel frame structure can be effectively identified, the model parameter quantity is small, the training cost is saved, the model accuracy is guaranteed through one-dimensional data training, and meanwhile important features can be prevented from being lost through time-frequency conversion.

This application discloses a vertical canned motor pump, belonging to the field of fluid machinery technology. A pump inlet is located at the bottom of the casing, and a pump outlet is located on its side wall. A gland is located at the top of the casing, and an exhaust pipe is provided on the gland. An impeller is located inside the casing and near the pump inlet. A drive unit is located inside the casing. A through shaft passes through the drive unit and drives its rotation. The impeller is fixed to the through shaft, which has an axially extending central hole that communicates with the exhaust pipe. A first bearing assembly and a second bearing assembly are respectively located on opposite axial sides of the drive unit. The first bearing assembly has an exhaust structure. This application reduces the axial dimension and weight of the pump unit by integrating the radial bearing and thrust bearing. Simultaneously, by providing an exhaust structure, the gas accumulated inside the first bearing assembly is discharged in an orderly manner, effectively suppressing vibration and improving acoustic performance.

The present invention provides a secondary barrier for liquefied gas storage tank, characterized by comprising: a blocking layer containing (a) metal or (b) one or more polymers selected from the group consisting of polyethylene, polyethylene terephthalate, polyvinyl alcohol, ethylene-vinyl alcohol copolymer, and nylon; and a fiber layer laminated on both sides of the blocking layer, containing one or more fibers selected from the group consisting of glass fiber, polyethylene fiber, poly-p-phenylene benzobisoxazole fiber (PBO), aramid fiber, and carbon fiber, the fiber layer being fixed by an adhesive layer suitable for surface properties.

The application discloses a kind of polymer solid electrolyte and its preparation method and application, the preparation method of polymer solid electrolyte includes precursor solution in 1~20T strong magnetic field in situ polymerization obtains the polymer solid electrolyte, the precursor solution includes polymer matrix, electrolyte salt and solvent, and does not contain magnetic material;The direction of the magnetic field is perpendicular to precursor solution surface.The application utilizes strong magnetic field to reduce polymer crystallinity, induces polymer molecular chain ordered arrangement, simultaneously locks this structure by in-situ polymerization.The technology constructs high-efficiency ion transmission network in polymer under the premise of not introducing magnetic filler, significantly improves ion conductivity (room temperature ion conductivity>1 mS / cm), assembles into all-solid-state battery, obtains good ion transference number, oxidation voltage window, first discharge capacity and first coulomb efficiency.

According to the composite component, the vehicle body frame and the vehicle, the composite component comprises a first component body, a second component body and a third component body which are sequentially arranged in a stacked mode from outside to inside, the first component body, the second component body and the third component body are independently arranged, and the second component body is connected with the first component body and the third component body; wherein the first component, the second component and the third component are all configured to be made of honeycomb materials, the density of the first component is set to be rho1, the yield strength of the first component is set to be Rp1, the density of the second component is set to be rho2, the yield strength of the second component is set to be Rp2, the density of the third component is set to be rho3, the yield strength of the third component is set to be Rp3, rho1, rho2 and rho3 meet rho1 < rho2 < rho3, and Rp1, Rp2 and Rp3 meet Rp1 < Rp2 < Rp3. In this way, differentiation and self-adaptive protection of low-speed, medium-speed and high-speed full-scene collision are achieved, overall light weight can be achieved due to the adoption of the variable design, and therefore the design requirement for light weight of the vehicle body frame is met while safety is guaranteed.

This invention proposes a method and system for diagnosing open-circuit faults in three-phase inverter IGBTs, relating to the technical field of power electronic device fault diagnosis. The method involves lightweight processing of acquired historical data to obtain feature vectors; training a pre-defined three-phase inverter IGBT open-circuit fault diagnosis model based on these feature vectors; real-time acquisition of three-phase current data to be processed, followed by bounded normalization to obtain normalized current amplitudes; and generating IGBT open-circuit fault judgment results based on these normalized current amplitudes. Real-time data related to the three-phase inverter IGBT open-circuit fault is collected based on the IGBT open-circuit fault judgment results, and this real-time data is input into the trained three-phase inverter IGBT open-circuit fault diagnosis model to output the three-phase inverter IGBT open-circuit fault diagnosis results. This invention effectively achieves lightweight, efficient, and accurate diagnosis of three-phase inverter IGBT open-circuit faults.

The application discloses a kind of reconfigurable intelligent surface auxiliary wireless environment modeling method based on three-dimensional Gaussian splash technology, belong to wireless communication field, this method will three-dimensional Gaussian splash technology from computer graphics field innovatively migrate to RIS auxiliary wireless communication system modeling field, the explicit parameterization thought of 3D-GS is applied to radio frequency electromagnetic field modeling, break through the limitation of traditional deep learning "black box" modeling;Adopt two-stage joint modeling framework: for the characteristics of RIS system, "TX→RIS" and "RIS→RX" cascade modeling strategy is designed, can accurately capture the electromagnetic regulation effect of RIS;With explicit physical parameterization: replace large-scale neural network weight with Gaussian parameter with clear physical meaning, realize light weight;In addition, by constructing complete differentiable rendering process, support efficient gradient descent optimization, ensure training efficiency and convergence.

The invention relates to the field of atmospheric environment monitoring and high-altitude sampling, and discloses an atmospheric trace nitrous acid and formaldehyde profile detection device carried by a small aircraft and a detection method. The absorption liquid is fed into the double-channel miniature spiral trapping trap through a peristaltic pump to be mixed and contacted with the sample gas to form a sample solution; a liquid storage bottle is arranged on the automatic sample disc, and the top of the first liquid inlet needle is connected with a liquid outlet of the dual-channel miniature spiral trapping trap; a color developing solution in the color developing solution storage bottle is injected into the liquid storage bottle through a second liquid inlet needle, and the constant-temperature reaction kettle controls the color developing reaction temperature to form a sample solution to be detected; a to-be-detected sample solution is pumped into the absorption cell through the liquid pumping needle, and the liquid pumping needle is driven by the liquid pumping arm to move up and down; the absorption cell is connected with a detector, and the detector is used for detecting the component concentration of the sample solution to be detected; the automatic sampler and the rapid reaction detector comprise the same automatic sample disc to realize rapid sample transfer.

The application discloses a gaze estimation method based on a hybrid pulse neural network and joint sparsity optimization, and belongs to the field of computer vision and human-computer interaction. The asymmetric hybrid network architecture with a front-end lightness and a rear-end self-adaptation is adopted, and the full-connection calculation of the front-end redundancy is removed. The structure effectively realizes the lightness of the network parameters while guaranteeing the modeling ability of the time sequence characteristics, effectively reduces the total energy consumption of the single-step system, and improves the deployment cost-effectiveness in the edge computing scene. The pulse sparsity joint optimization strategy is introduced, the MFR regularization penalty term is added in the loss function, and the accumulation speed of the membrane potential of the hidden layer neurons is effectively inhibited through the alternative gradient back propagation. The method reduces the overall pulse firing quantity at the physical level, reduces the redundant pulse firing irrelevant to the prediction accuracy, effectively reduces the synaptic operation number (SOPs) in the reasoning stage, and maintains good feature expression robustness under high sparsity.

This invention belongs to the field of vibration and noise reduction technology for new energy vehicles, specifically involving a low-noise design and evaluation method for electric drive systems based on acoustic metamaterials. The method involves determining the peak intensity and frequency of the vibration and noise response of the electric drive system, identifying the significant area of ​​working deformation of thin-walled components in the electric drive system, and determining the installation position of the acoustic metamaterial based on this area. It also involves determining the design boundary parameters of the acoustic metamaterial, designing a local resonant element, artificially constructing the local resonant element, prototyping the acoustic metamaterial based on the artificial construction scheme of the local resonant element in step five, installing the acoustic metamaterial in the determined installation area, and verifying its noise reduction performance. Finally, it determines whether the artificial construction scheme parameters are optimal; if optimal, the acoustic metamaterial scheme is determined. This invention systematically proposes a method for using acoustic metamaterials to mitigate single-frequency noise radiated by the thin-walled structure of the electric drive system, and clarifies the precise selection method for the installation position of the acoustic metamaterial on the thin-walled structure of the electric drive system.