56results about How to "Easy to keep" patented technology

The utility model belongs to battery processing forming technical field especially relates to battery cover forming device, including punch upper die, punch lower die and adaptive mechanism, punch lower die sets up on punch upper die's output end stamping path, adaptive mechanism swing joint is in punch lower die, set up the mounting groove for loading the battery cover of to be shaped on adaptive mechanism, wherein, punch lower die is provided with the movable slot for accommodating adaptive mechanism, adaptive mechanism can be along the horizontal direction sliding connection in movable slot, adaptive mechanism is used for loading the end of battery cover and can rotate after the output end stamping effect of punch upper die, makes the orientation angle change of mounting groove, through dynamic adjustment battery cover's space posture in the stamping process, effectively solve the convex ring inclination defect of traditional punch forming when the workpiece deflection leads to.

The application discloses a micro-fluidic chip and a method for recovering nucleic acids with different fragment sizes. The method can realize recovery of nucleic acids with different fragment sizes by repeatedly washing and recovering magnetic beads through the micro-fluidic chip. The method can improve the overall nucleic acid recovery effect by adjusting the adding concentration of the magnetic beads and PEG salt and the washing times, and can distinguish and control the nucleic acid length, and all the nucleic acids with different fragment lengths can be obtained by continuously adjusting the concentration. Moreover, the method can realize small volume, high throughput and automation.

This invention belongs to the field of medical signal processing technology, specifically a method and prediction system for constructing a three-dimensional tumor motion trajectory prediction model. It involves collecting temporal data of point clouds from the human chest and abdomen, as well as temporal location information of the tumor, and establishing a unified spatial coordinate system. The temporal data of the point clouds are divided into n time periods of total duration T1, and the temporal location information of the tumor is divided into n time periods of total duration T2, resulting in n training samples. The point clouds of the training samples are further divided into several pseudo-voxel sub-blocks according to the human projection plane, and K pseudo-voxel sub-blocks are selected based on motion saliency to obtain the temporal feature vector of the tumor motion. The temporal feature vector of the tumor three-dimensional motion trajectory prediction is used as input, and the corresponding tumor temporal location information is used as output to train an attention-enhanced dilated convolutional prediction network. This invention enables high-precision, non-invasive prediction of the three-dimensional tumor motion trajectory.

The invention relates to a food processing technology, and discloses a stress relaxation microchannel guided low-fat high-oxidation-stability nut preparation method. The method comprises the following steps: adjusting the content of nut meat in an aqueous solution containing an antioxidant to 8-12% (dry basis), and then carrying out phase change induced stress treatment to form a micro-fracture network communicated with the outer surface in the interior; then increasing the pressure to 3 to 10 MPa at the speed of 1.0 to 2.5 MPa / min, and maintaining the pressure, wherein the hot / trap is 1.5 to 1.8; and rapidly relieving pressure and discharging residual oil at (2.5-3.5) v1, and rapidly shaping by adopting high-energy drying for 2-10 minutes by adopting radio frequency / infrared / microwave vacuum and the like. According to the method, the degreasing efficiency and the size stabilization rate are improved under the low pressure intensity, surface residual oil is reduced, flavoring is promoted, and the storage oxidation stability is improved.

The present application provides a kind of night image halo removal method, including constructing prior knowledge, according to prior knowledge, construct initialization network and depth unfolding network, using initialization network to extract variable initial value set from night halo pollution image;Night halo pollution image and variable initial value set are input into depth unfolding network and are operated multiple iterations, and the final halo removal image is extracted from night halo pollution image;Wherein, depth unfolding network includes multiple proximal networks, and each proximal network participates in an iteration operation.The present application makes full use of prior knowledge, uses the depth unfolding network with multiple proximal networks to iterate mapping diagram, halo-free feature map, constraint variable and halo removal image, so as to extract the final halo removal image, to better preserve image texture and restore image details, under the premise of not increasing application cost, the halo and stripe artifact in image are preferably removed.

The present application relates to a kind of surface layer silicon source enrichment type ablation-resistant prepreg and its preparation method.The method first uses the inner impregnation solution containing boron phenolic resin and curing agent to impregnate quartz fiber fabric and discharge, and forms main body impregnation layer;Then the surface is treated with surface back wetting liquid containing boron phenolic resin and superfine silicon powder, and the maturation below gel temperature is obtained after discharge and lowing, to obtain ablation-resistant prepreg.The method can make superfine silicon powder more stably arranged in surface layer area, form boron-containing silicon vitrification protective structure in the ablation process, and improve the problem of local ablation deepening in edge area.

This invention provides a strong wind-resistant double-glass photovoltaic module structure, which includes multiple photovoltaic panels. Multiple connectors are slidably connected to the bottom of each photovoltaic panel, and adjacent photovoltaic panels are staggered together via these connectors. Each photovoltaic panel has a limiting component 1 and a limiting component 2 on both sides. When the photovoltaic panels are in the unfolded state, adjacent photovoltaic panels are fixed together by the limiting components 1 and 2, achieving rapid unfolding / storage and high space-efficiency folding. Through the sliding hinge block and groove design, adjacent photovoltaic panels can be folded around an axis or slid horizontally and stacked for storage. Combined with the detachable limiting components, users can quickly lock or release the panels without tools, achieving a seamless transition from the unfolded state to the compact folded state. This greatly improves the module's space storage efficiency, facilitates transportation and storage, and supports rapid deployment and dismantling.

The fan blade defect detection method based on the APF-YOLO model comprises the following steps: acquiring a fan blade defect data set, and preprocessing the fan blade defect data set; randomly dividing the data set into a training set and a test set according to a certain proportion; the method comprises the following steps: on the basis of YOLOv8n, constructing an APF-YOLO defect detection model; and training the APF-YOLO defect detection model through the training set to obtain a detection result. The invention provides a fan blade defect detection method based on an APF-YOLO model so as to solve the interference of a complex environment on fan blade detection and improve the precision of small target defect detection.

The embodiment of the invention provides an image noise reduction method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring an original image; wherein the original image comprises at least two channels; for each channel, determining image data of the channel under at least two preset resolutions according to the original image; according to the image data of the channel under the at least two preset resolutions, determining denoised data corresponding to the channel; and according to the denoised data corresponding to each channel, determining a denoised image corresponding to the original image. For different channels in the original image, image data under different resolutions are obtained, information of multiple scales in the image is reserved, for each channel, independent noise reduction is performed on the channel in combination with the image data under each preset resolution, mutual influence of the channels is avoided, and the image noise reduction precision is effectively improved.

The invention discloses an image generation method and the like, which are used for generating a high-quality image. The method comprises the following steps: acquiring a target vector; respectively inputting the target vector into a first generator and a second generator to correspondingly generate a first sub-graph and a second sub-graph, the first generator being obtained by training an initially configured first generative adversarial network GAN by a server according to a low-frequency image and a first random noise variable satisfying normal distribution, and the second generator being obtained by training an initially configured second generative adversarial network GAN according to a second random noise variable satisfying normal distribution; the second generator is obtained by training an initially configured second generative adversarial network (GAN) by the server according to the high-frequency image and a second random noise variable satisfying normal distribution, and the frequency of the low-frequency image is lower than that of the high-frequency image; and synthesizing the first sub-image and the second sub-image to obtain a target image.

The application discloses a vehicle-mounted snake venom processing device and a method for processing snake venom by using the same. The vehicle-mounted snake venom processing device comprises a vehicle body, a workbench and a power supply device arranged in the vehicle body, and the workbench is provided with a separation device, a drying device, a detection device and a storage device. The drying device comprises a vehicle-mounted freeze dryer and an oil-free vacuum pump, and the crude snake venom separated by the separation device is subjected to freeze drying to obtain freeze-dried snake venom powder. The detection device comprises one or more of an enzyme label instrument, an ultraviolet spectrophotometer and a moisture tester for detecting biochemical indexes of the freeze-dried snake venom powder. The storage device is used for storing the freeze-dried snake venom powder which passes the detection. The vehicle-mounted snake venom processing device has a compact structure and is convenient to move and use, is suitable for collecting and processing snake venom in the scattered snake breeding of present snake breeders, significantly shortens the snake venom processing time, effectively retains active ingredients of the snake venom, improves the medicinal value of the snake venom, and is favorable for classified storage of the snake venom through on-site detection and analysis.

This invention relates to the field of oil and gas exploration technology and discloses an automatic identification method for drilling cuttings lithology. The method includes: acquiring drilling cuttings images collected from different well areas; preprocessing the drilling cuttings images to obtain target images that meet preset requirements; using a deep learning model to identify the target images and segment them into multiple individual cuttings images; extracting features from the individual cuttings images based on a neural network algorithm; classifying and labeling rock types in the feature space based on the extracted features using the KNN algorithm to establish an automatic identification model for drilling cuttings lithology; and using the automatic identification model to identify the target drilling cuttings. The automatic identification method for drilling cuttings lithology disclosed in this invention is simple to operate, has high identification efficiency, accurate lithology identification, and a wide range of applications.

This invention relates to the field of coating preparation technology, specifically to a current-carrying friction and wear protective coating with good electrical conductivity, its preparation method, and its application. The coating is prepared by granulation, sintering, and sieving of Ti2AlC powder. The coating raw materials are Ti2AlC powder and metallic Cu powder, with the Ti2AlC phase ratio being 10%~40%. A composite coating is prepared on the surface of boiler steel using supersonic flame spraying technology. The spraying process parameters are: kerosene flow rate 23~29 L / h, oxygen flow rate 53 m³ / h. 3 With a powder feed rate of 30 g / min, a step size of 3 mm, a spraying distance of 320 mm, and a spray gun moving speed of 800 mm / min, the application of Ti2AlC phase-reinforced Cu-based composite coating under current-carrying friction and wear conditions is realized. This provides a method to improve the current-carrying friction protection performance of Cu alloy surfaces without affecting the coating conductivity, which helps to improve the reliability, efficiency, lifespan, and safety of related equipment.

This invention belongs to the field of materials processing and preparation technology, and provides a method for accelerating the martensitic decomposition of additive titanium alloys with high-energy short-time pulsed current. By designing pulsed current parameters, this invention establishes a quantitative relationship between current density, action time and microstructure evolution, thereby effectively suppressing grain coarsening while efficiently driving the rapid decomposition of acicular martensite. Ultimately, it breaks through the traditional constraint between strength and plasticity in additively manufactured titanium alloys, and achieves significant optimization of its comprehensive mechanical properties.

The application relates to the technical field of water resource sampling, in particular to a water conservancy and water resource sampling device which comprises a ship body, a sampling assembly and a pulling assembly, a placing groove area is arranged in the middle of the ship body, an oscillatable parallel sampling frame is arranged in the placing groove area, a plurality of sampling bottle groups arranged at equal intervals are arranged in the parallel sampling frame, a resistance triggering structure is adopted for the sampling bottle group, when the ship body moves, water pressure pushes the sampling outer cylinder to move backward, an inlet is automatically opened to complete sampling; when the ship body stops, a spring can reset the sampling outer cylinder, the sampling outer cylinder seals the sampling inner cylinder, and water samples are prevented from being polluted; the pulling assembly controls the depth of the parallel sampling frame, and the water area with different water depths is adapted, the device can automatically and synchronously collect water samples with different depths at a time, the sampling depth can be adjusted, and the device is suitable for water resource sampling in water areas such as rivers and lakes.

The utility model relates to positioning pin technical field discloses a kind of quick replacement positioning pin of oil press mould, including pin body, the bottom of pin body is equipped with pre-install seat, the both sides of pre-install seat inner wall are all set with connecting groove, the inner wall of two connecting grooves is all installed with limiting component, the both sides of pin body bottom are all set with limiting slot, the top of pin body is set with lubricating groove, and the limiting component includes spring piece, limiting piece and unlocking assembly, the spring piece is fixedly connected to the side of limiting slot inner wall. In the utility model, when oil press replaces different mould, the pin body of the positioning pin can be quickly disassembled, the working efficiency is improved, the lubricating groove of spiral shape is set on the positioning pin, the retention of lubricating grease is facilitated, the replenishment frequency can be reduced, and when being inserted with the positioning hole on the mould, the lubricating grease can be uniformly flowed to the surface of pin body after being extruded, and the lubrication effect is better.

The invention discloses an interpretability method for a decision basis of a medical image classification model, and relates to an interpretability method for a classification model. A channel and a space attention mechanism are introduced in a prototype concept extraction stage, the model is guided to focus on a key semantic region related to a disease, background interference is reduced, and semantic discrimination and stability of a prototype concept vector are remarkably improved; a CARAFE up-sampling method based on content awareness is adopted to replace a traditional up-sampling mode, the problems of edge blur and structure distortion are effectively relieved in the prototype concept vector positioning and deconvolution visualization process, and important anatomical structures and focus contour information in medical images are better reserved; according to the method, semantic suppression of prototype concept vectors in a high-level semantic space is quantitatively analyzed in combination with an anti-fact intervention strategy, contribution of each prototype concept vector to model prediction can be objectively evaluated, and potential error correlation or redundant prototype concept vectors can be revealed, so that the fineness and credibility of model decision interpretation are improved.

The utility model relates to the technical field of kitchen cooking utensils, and particularly discloses a vacuum cooking utensil with a good sealing effect, which comprises a pot body, a pot cover and a sealing ring. The pot body comprises a pot body and an inner pot arranged in the pot body, and the opening part of the inner pot is provided with a flange extending outwards; the sealing ring comprises a connecting part and a sealing part connected with the connecting part; the sealing part comprises a first sealing lip and a second sealing lip; the first sealing lip is configured to obliquely extend from the connecting part to the inner side of the sealing ring, and is attached to the part, close to the interior of the inner pot, of the turned-over edge in a cover closing state so as to prevent gas in the inner pot from escaping during positive pressure; and the second sealing lip is configured to obliquely extend from the connecting part to the outer side of the sealing ring, and is attached to the part, far away from the interior of the inner pot, of the flange in a cover closing state so as to prevent external air from entering the internal space of the inner pot under negative pressure. The sealing requirements in two pressure states can be met at the same time, and the problem of unstable pressure caused by gas leakage or external gas entering is solved.

The utility model discloses an automatic gear shifting speed reducer, include: speed reducer body, motor drive system, controller and sensor component, the cavity structure of being equipped with the accommodation space in the inside is to speed reducer body, and speed reducer body includes shell, differential mechanism, variable speed gear assembly, and differential mechanism, variable speed gear assembly are connected through the bearing of corresponding setting with the shell activity, and differential mechanism and variable speed gear assembly are connected through the meshing of corresponding gear, and motor drive system includes motor, shift fork mechanism, and motor receives controller signal and is driven through shift fork mechanism corresponding gear switch its meshing state, and the closed -loop control system of sensor component and controller constitution, and controller sends the gear shift instruction based on preset algorithm, and controller preset speed band gear shift logic. The utility model discloses simple structure, low in cost, is convenient for maintaining, and high reliability, and can self -adaptation working condition, utilizes motor and controller and realizes automation, through sensor real -time monitoring, avoids the gear shift impact, prolongs the gear life.

The application provides a method for in-situ regeneration of Tl-poisoned SCR catalyst and recovery of Tl resources, and belongs to the field of waste SCR catalyst recovery; the Tl-poisoned SCR catalyst is placed in a glycine solution, and after solid-liquid separation, a thallium leaching solution and a regenerated SCR catalyst are obtained; then, the thallium leaching solution is subjected to thallium precipitation treatment, and after solid-liquid separation, a thallium-containing precipitate is obtained. The application utilizes the specific coordination of glycine and Tl to selectively extract Tl from the catalyst, restores the activity of the SCR catalyst, recovers the extracted Tl, realizes the resource utilization of waste, and reduces the environmental risk.

The invention provides an image restoration method and device, relates to the technical field of image restoration, and is used for performing high-quality restoration on a shielding region of a BSA hole in a BSA image. The image restoration method comprises the following steps: acquiring a BSA image, and pre-processing the BSA image to obtain a to-be-restored projection image; the BSA image is a projection image of the target object formed by rays passing through the BSA and the target object; based on the gray value interval of the to-be-restored projection image, segmenting the single-channel to-be-restored projection image into multi-channel to-be-restored projection images; the gray value intervals of the to-be-restored projection images of different channels are different; inputting the multi-channel projection image to be restored into an image restoration model to obtain a target restoration image; the image repairing model is used for repairing the shielding area of the BSA hole in the projection image to be repaired.

The present application relates to a kind of flame and smoke detection method based on improved YOLO11, comprising: the image of target to be detected is collected, the image of target to be detected is input into improved YOLO11 model, and detection result is obtained;The improved YOLO11 model is obtained using training set training;The training set includes: original target image and flame and smoke label;The improved YOLO11 model includes: replace the conventional down-sampling layer in backbone network by detail-context collaborative down-sampling module, use dynamic double-feature fusion module to reconstruct feature interaction unit in feature fusion network, and use shared regression and asymmetric classification module to replace original unified classification detection head.The present application improves the performance of flame and smoke detection under complex environment.

The application relates to the technical field of direction of arrival estimation, and specifically discloses a cross-platform complex domain feature enhancement coherent super-resolution DOA estimation method, which comprises the following steps: firstly, a complex domain CVSIMO learning model is constructed; sampling data is preprocessed; forward propagation of the CVSIMO learning model is carried out; backward propagation and parameter optimization of the CVSIMO learning model are carried out; data reconstruction and signal separation are carried out; cross-platform super-resolution DOA estimation is carried out; and finally, model simulation experiments are carried out. The cross-platform complex domain feature enhancement coherent super-resolution DOA estimation method can realize feature mining of multiple point source signals, converts a multi-source estimation problem into a single point source DOA estimation problem by using a complex domain neural network model, enhances the features of coherent signals by using the advantages of the complex domain neural network, improves the performance and precision of the super-resolution DOA estimation algorithm, can also realize data separation of multiple coherent signals and cross-platform DOA estimation, and realizes real angle estimation through ingenious feature solving.

The application relates to the technical field of deep learning and natural language processing, and discloses a voice conversion method based on a vocoder, a storage medium and an electronic device, which comprises the following steps: constructing an any-to-one voice conversion model, performing content coding on source voice audio, obtaining acoustic characteristics through an acoustic model, obtaining converted voice through a vocoder, extracting the mean and variance of a target speaker, inputting the spectrum of the converted voice obtained through the vocoder into a feature extractor composed of a convolution, a WaveNet module and a linear radiation transformation to obtain features Z_source, converting Z_source into Z_target by using the mean and variance of the target speaker, inputting the features Z_source into a UnivNet structure to obtain converted voice, the method not only has the function of the vocoder, but also can well convert voice input of any kind of language or dialect to a target timbre, and well retains other features in the original voice except the speaker and the content.

The invention discloses a composite membrane for a high-temperature proton exchange membrane fuel cell as well as a preparation method and application of the composite membrane. According to the composite membrane, polybenzimidazole (PBI) is used as a matrix, chloromethylated polysulfone (CMPSF) is introduced as a covalent cross-linking agent and reacts with imidazole groups in the PBI to form a three-dimensional covalent cross-linked network, and the mechanical strength and dimensional stability of the membrane are remarkably improved; meanwhile, a nitrogen-rich ionic polymer (NIP) synthesized by a specific precursor is introduced, and rich basic nitrogen sites of the NIP can form strong hydrogen bond interaction with phosphoric acid, so that the phosphoric acid adsorption and retention capability of the membrane is greatly enhanced, and additional proton jump sites are provided. Through the synergistic effect, the proton conductivity of the composite membrane exceeds 160 mS cm <-1 >, the tensile strength exceeds 10 MPa and the peak power density reaches 1000 mW cm <-2 > magnitude under the conditions of 160 DEG C and no water, and the composite membrane has excellent long-term stability. According to the invention, the contradiction between the mechanical property and proton conductivity of the traditional phosphoric acid doped PBI membrane is effectively solved, and a reliable electrolyte material is provided for a high-performance and long-life high-temperature proton exchange membrane fuel cell.

The invention relates to the technical field of remote sensing image road extraction, in particular to a remote sensing image road extraction method based on frequency domain feature extraction and fusion, which comprises a feature extractor, a bottleneck layer and a segmentation branch. The feature extractor adopts FCB to replace traditional convolution operation, and performs frequency domain filtering operation on a frequency domain to perform feature extraction; the bottleneck layer adopts a KAN Layer to learn complex road features; according to the segmentation branch, the feature map is recovered to the original size through up-sampling, multi-scale feature learning and fusion are achieved through a multi-scale pyramid, and finally the feature map is sent to an output layer to output a prediction result. According to the method, the frequency domain convolution with the global receptive field, the bottleneck layer capable of learning the activation function and the multi-scale image reasoning fusion mechanism are introduced, the extraction precision is improved, the model parameter quantity and the energy consumption are reduced, and the high-efficiency and high-precision remote sensing image road real-time extraction requirement can be met.

The utility model relates to the technical field of clamps, in particular to a combined clamp for die forging pipe joint processing, which is characterized in that a lower die is fixed on a chuck, the lower die is connected with an upper die through a hinge, the upper die is provided with an upper die core through a second screw, and the lower die is provided with a lower die core through a first screw; an upper runner in the upper die core and a lower runner in the lower die core jointly form a pipe joint shape, a clamping handle is arranged on the outer side of the chuck, and the central axis of the clamping handle is located on the central axis of a cavity formed by the upper runner and the lower runner. Meanwhile, it is guaranteed that the gravity centers of the clamp and the parts are located on the central axis, high-rotating-speed cutting can be achieved, the production efficiency is greatly improved, and potential safety hazards and labor cost input are reduced.

The embodiment of the invention discloses a dam and high slope mass three-dimensional deformation monitoring data extraction method based on expert knowledge, and the method comprises the steps: carrying out the sampling of the three-dimensional deformation data of a dam and a high slope according to a certain time interval, dividing the three-dimensional deformation data into refined time periods with different characteristics, and carrying out the noise reduction; different indexes are adopted to measure deformation changes of different time segments, a comprehensive abnormal score of polynomial weighting is calculated, and a deformation mode is judged; and for an abnormal type deformation mode and a stable type deformation mode, subcategories are refined, and representative values of the Japanese deformation quantity are selected in a simplified mode according to the subcategories. Through segmented noise reduction driven by expert rules, customized noise reduction is carried out according to characteristics of different deformation stages; and an isolated forest anomaly detection and comprehensive anomaly scoring method is introduced, so that the automation level and accuracy of deformation mode judgment are greatly improved, and wide applicability of the method in different climate, terrain and hydrological environments is guaranteed.

This invention proposes a morphological template-based conformal filtering method for 3D terrain reconstruction, belonging to the technical field of 3D terrain reconstruction. It solves the problem that current surface filtering methods cannot accurately identify and preserve the edges and corners of terrain features, resulting in the inability to accurately restore the true contours of features. First, a terrain representation map of the target feature is obtained. Then, multiple morphological templates are designed based on the regular shapes of the corners. These templates are used to detect the positions of the edges and corners to be processed in the terrain representation map. Next, it is determined whether the pixel code of the terrain representation map matches any one of the morphological templates. If it does, a conformal weighted filtering process is applied to the current pixel code; otherwise, a median filtering process is applied. Finally, the filtered terrain representation map is post-processed, and the 3D model of the target feature is reconstructed based on the processing results. This method achieves accurate identification and preservation of feature edges and corners, and accurate restoration of the true contours of features.

The application discloses a kind of mobile device image denoising methods based on double-branch residual sparse network, belong to image processing technical field, which includes: residual sparse module, by mixed dilated convolution and residual connection capture local feature in image, while reducing the number of parameters and computational complexity of model;Attention guiding residual sparse module introduces channel attention and pixel attention mechanism on the basis of residual sparse block to adjust the weight of feature map, pay attention to important area in image, improve denoising effect and image quality;Feature fusion module, by adding double-branch output after residual module processing, combined with attention mechanism and activation function, realize high-frequency detail preservation and noise suppression.The application carries out image denoising in unmanned aerial vehicle and other resource-limited scenarios, solves the problems of large parameter quantity, low computational efficiency, insufficient detail preservation and other problems of existing denoising model.