10results about How to "Delay decay" patented technology

This application provides a method and related equipment for detecting small target vehicles from a low-altitude perspective, belonging to the fields of computer vision and intelligent transportation technology. The method includes: acquiring low-altitude images and performing multi-level feature extraction, performing feature preservation operations during the extraction process to retain high-resolution detail information; adaptively enhancing the extracted features to improve target-related feature responses; constructing a high-resolution feature response path, fusing shallow high-resolution features with deep semantic features to form enhanced features; and performing target detection based on the enhanced features. This application also optimizes feature representation through feature compression and path pruning to reduce computational complexity. Through a collaborative design of feature information preservation and reconstruction during multi-scale propagation, this application achieves a simultaneous improvement in the performance and computational efficiency of small target vehicle detection in complex low-altitude scenarios.

This invention proposes a multi-scale feature enhancement and training method and apparatus for underwater sonar small target detection. The method includes: constructing a backbone network for a target detection model, with the network outputting four layers of multi-scale features at different resolutions; implementing sub-pixel-based skip connections to fuse high-level features; implementing sub-pixel-based context enhancement to fuse features at all scales; implementing channel attention sharing guidance to optimize the generated feature pyramid; constructing an overall target detection model, loading a pre-trained model and a sonar image dataset, and starting training; weighting the multi-scale loss values, selecting the two scales with the highest variance reduction rate for enhancement, and increasing their weights; calculating the overall loss, backpropagating to update the model parameters, and obtaining the target detection model after training. This invention achieves good detection accuracy in underwater sonar small target detection tasks.

This invention provides an antistatic fabric based on modified acrylic fiber and its preparation process, belonging to the field of textile fabric technology. The process includes the following steps: first, preparing modified acrylic fiber and organosilicon quaternary ammonium salt modified CNW; then, mixing and stirring the modified acrylic fiber, DMF, and organosilicon quaternary ammonium salt modified CNW to obtain a spinning solution; mixing anhydrous ethanol and organosilicon quaternary ammonium salt modified CNW, and ultrasonically treating to obtain a dispersion; in a conjugate electrospinning device, feeding the spinning solution and dispersion into two sets of needles respectively, and electrospinning the spinning solution to form nanofibers under the action of a high-voltage electric field; feeding cotton yarn into the electric field region, causing the nanofibers to spirally wind around the surface of the cotton yarn and form a coating shell; and electrostatically spraying the dispersion to deposit the organosilicon quaternary ammonium salt modified CNW onto the surface of the coating shell; collecting and winding to obtain a fiber core-spun yarn, and weaving the fiber core-spun yarn to obtain the antistatic fabric. This invention can improve the antistatic performance of the fabric while also possessing certain antibacterial properties.

This invention provides a wireless bladder volume monitoring system based on inductive coupling, comprising a passive LC sensor unit attached close to the bladder, an external reading coil integrated into clothing or a belt, and a portable impedance measurement unit located in a clothing pocket. This system utilizes the strong penetrating power of low-to-medium frequency scanning signals to wirelessly monitor the state of the bladder through electromagnetic coupling between the passive LC sensor unit and the external reading coil, effectively overcoming the influence of relative pose changes between the passive LC sensor unit and the external reading coil on the measurement results. This invention obtains the system resonant frequency of the passive LC resonant unit by continuously detecting the impedance at the input terminal of the external reading coil, thereby realizing a wearable, wireless, passive, real-time bladder volume monitoring system. It features a simple structure, high reliability, and portability, making it suitable for long-term monitoring scenarios.

The invention relates to the technical field of carbon dioxide adsorbents, in particular to an SBA-15 solid amine adsorbent as well as a preparation method and application thereof. The preparation method comprises the following steps: S1, carrying out vacuum drying activation on the SBA-15 carrier; s2, preparing a composite impregnation liquid: dissolving organic amine and PEG-200 in absolute ethyl alcohol together, and fully stirring to form a uniform and transparent solution; s3, adding an activated SBA-15 carrier into the composite impregnation liquid, and carrying out impregnation and aging treatment; and S4, carrying out gradient drying and curing on the impregnated and aged product to obtain the SBA-15 solid amine adsorbent. Polyethylene glycol (PEG) with a specific molecular weight is introduced as a functional additive to synergistically optimize an impregnation solvent and amine loading capacity, so that the dispersion state of amine is improved on the molecular level and the anchoring effect of the amine is enhanced, and the adsorption capacity, dynamics and stability are synergistically improved.

This invention relates to the field of warehousing management technology for pre-packaged rice, flour, and oil products, and particularly to a method and system for agricultural product sales forecasting and inventory management based on big data analysis. The method includes: a data collection step, where multimodal time-series quality characteristic data of agricultural products are collected in real time using a composite sensing array deployed in the storage unit; an analysis step, where the data is input into a physical information fusion neural network to output the theoretical aging cycle and dynamic quality decay curve of individual batches; a depreciation measurement step, where the book inventory is dynamically converted into standardized effective inventory equivalent based on the decay curve; a procurement decision step, where a procurement plan is generated; and an inventory decision step, where outbound instructions are generated based on the effective inventory equivalent and remaining aging cycle, and inventory parameters are adaptively adjusted. This invention solves the technical problems of discrepancies between book inventory and actual sellable inventory, distorted replenishment decisions, and high loss rates caused by factors such as aging, moisture absorption, and mold growth in agricultural products. It achieves synergistic optimization of procurement and inventory, significantly reducing losses and capital occupation.

The application provides a battery management system and a multi-battery-pack cooperative control method thereof, single-battery-pack comprehensive data is obtained by separately collecting voltage and current data, temperature data and health state data of each battery pack, so that the collection and management of the battery pack data are realized, and a data basis is provided for the management and operation among the battery packs; based on the charging and discharging demand and the single-battery-pack comprehensive data, a globally optimal charging and discharging power distribution ratio is determined, the problem of unbalanced charging and discharging is solved, the charging efficiency and the available capacity of the battery are improved; based on the temperature data and the position distribution of all the battery packs, a joint thermal management strategy of adjacent battery packs is determined; by establishing the joint thermal management strategy, local overheating or overcooling is avoided, the battery attenuation is delayed, and the battery life is prolonged.

This invention relates to a selenium-containing compound vitamin chewable tablet and its preparation method, comprising the following raw materials in parts by weight: 10-16 parts selenium-enriched yeast, 25-35 parts L-ascorbic acid, 0.5-1 part vitamin K, 10-20 parts sorbitol, 1-3 parts DL-α-tocopherol acetate, 3-8 parts sodium octenyl succinate starch, 1-5 parts acetylated distarch adipate, 0.7-1.2 parts magnesium stearate, 0.3-0.5 parts potassium citrate, 0.04-0.07 parts steviol glycosides, and 5-10 parts modified silica. This invention improves the crispness and palatability of the chewable tablet by adding acetylated distarch adipate and sodium octenyl succinate starch; the addition of modified silica effectively reduces vitamin attenuation and improves the stability of the components.

The invention provides a fuel cell heavy truck energy management method and system considering energy-saving driving. The method comprises the steps that an energy-saving driving index is determined according to driving state parameters obtained in real time; based on the energy-saving driving index, the front road information, the driving motor power and the driving state parameters, utilizing a space time sequence fused graph neural network prediction model to predict an instantaneous vehicle power demand; constructing a multi-objective optimization model and solving the model to obtain the target output power of the fuel cell stack and the target charging and discharging power of the energy storage device; issuing a power instruction to the fuel cell stack and the energy storage device according to the target output power and the target charging and discharging power, and triggering an energy storage compensation mode when the deviation between the actual driving power and the predicted power demand exceeds a preset condition; and the weight of the model is updated based on the deviation and the change of the energy-saving driving index, and energy-saving driving information is fed back to the driver. In this way, the driver is guided to optimize operation so as to further excavate the energy-saving potential, and the energy consumption economy and the driving range of the whole vehicle are improved.

The invention discloses an energy recovery voltage protection method for an electro-tricycle, belongs to the technical field of crossing of electric control and battery management of electro-tricycles, and aims to remarkably enhance driving safety and stability, avoid sudden interruption risks, abandon a hard overvoltage protection mode depending on a fixed threshold value in a traditional scheme and improve the safety of the electro-tricycle. Constructing a progressive power regulation mechanism, calculating an error between an actual voltage and a target voltage to obtain a proportional gain and an integral gain when a communication-free battery voltage is between a power limiting point and an overvoltage point, further determining a current value for maintaining the target voltage, and smoothly limiting the generated power; according to the technical scheme, vehicle running interruption caused by direct cut-off of MCU output is avoided, running safety under key working conditions such as abrupt slope slow descent and braking is guaranteed, protection for cutting off MCU output is triggered only when the voltage exceeds an overvoltage point, battery overcharge is completely eradicated, sudden rise of bus voltage of the whole vehicle is prevented, battery attenuation is effectively delayed, and electrical elements such as vehicle-mounted electric appliances are protected against damage.