29results about How to "Reduced Quantity Requirements" patented technology

The invention discloses a novel Internet of Vehicles congestion simulation method oriented to a 5G V2X Uu interface, a semi-physical simulation test platform oriented to the 5G V2X Uu interface is included, the test platform architecture comprises a traffic simulator, data packet software, a receiving end OBU, a sending end OBU and a 5G comprehensive tester, and the problem that the semi-physical simulation is limited by the number of terminals and is difficult to simulate a congestion scene is solved. By limiting available resources of the network, the requirement of semi-physical simulation on the number of terminals is reduced, and meanwhile, the increase of the number of vehicles in the network is simulated by increasing the network traffic load. The adjustment of the traffic load is realized by setting a data packet sending period and the size of a data packet. And selecting a required channel model to calculate fading according to a traffic simulation scene and vehicle time-position information, and then adding the fading into a corresponding data packet. And for a V2N2V link, respectively adding uplink fading and downlink fading for a data packet according to different environments and positions of receiving and transmitting end vehicles.

A large nut inversion device comprises a device screw rod, a nut tray, a spring, a spring tray and a hexagon nut, the device screw rod is used for being matched with a large nut to be installed, the nut tray is located above the device screw rod and used for bearing the large nut, and the spring is located between the nut tray and the spring tray. Through the elastic effect of the spring, when the nut tray makes contact with the threaded section of the nut screw, threads can be automatically aligned, centered and leveled, so that a large nut can be quickly and efficiently screwed into the nut screw, the spring tray is used for fixing the spring and limiting the displacement of the spring, and the hexagonal nut is used for locking the spring tray and the device screw. Therefore, a complete inversion device is formed. The device adopts a split type design, is convenient to carry and adapts to different scenes; meanwhile, the device is provided with a safety locking mechanism to prevent the nut from overturning or falling off; the upside-down mounting device is simple in structure, the mounting efficiency is remarkably improved, the labor intensity is reduced, the operation safety is enhanced, and the upside-down mounting device has wide application prospects.

The invention discloses a ship route planning method and system based on deep learning large-scale extreme wind speed forecast, and relates to the technical field of artificial intelligence and maritime navigation. An incremental principal component analysis method is introduced, a large-scale sea surface extreme wind speed forecasting model based on depth separable convolution is constructed, and potential physical sudden change disturbance information is decoded and reserved in a variable high-dimensional mapping space by the model through integration of an attention mechanism module and a residual learning algorithm; the attention mechanism module maps high-dimensional feature information in an extreme wind field time sequence to a multi-dimensional feature matrix of a coder-decoder. The method can perform refined dynamic forecasting on the large-scale sea surface extreme wind speed, accurately detect the extreme wind speed sea area and the boundary thereof, forecast and master the intermittent sudden change rule of the sea extreme wind speed in advance, help a ship driver to dynamically adjust the ship route in real time and avoid severe storm weather, and further ensure the navigation safety.

The invention provides an intelligent leak detection system and leak detection method for a super-large-scale space film type low-temperature storage tank, and the system comprises an unmanned plane acoustic imaging subsystem, a leak comprehensive recognition and judgment subsystem, and the unmanned plane acoustic imaging subsystem can achieve the quick scanning of a detected region, and carries out the three-dimensional laser scanning. Sound field scanning is carried out on the detected area by using the sound imaging module; the leakage comprehensive identification and judgment subsystem under the unmanned aerial vehicle detection framework can perform three-dimensional reconstruction of a detection area based on laser scanning information and form a defect distribution three-dimensional image of the detection area by superposing sound field scanning information; through automatic scanning of the unmanned aerial vehicle in a detection area and leakage comprehensive identification and judgment under the unmanned aerial vehicle detection framework, automatic scanning and defect position three-dimensional imaging of the super-large-scale space film type low-temperature storage tank can be realized under the unmanned aerial vehicle framework, the detection working condition requirements are met, the requirements for the number and experience of detection personnel are reduced, and the detection efficiency is improved. And the detection efficiency and reliability are improved.

The present invention provides a confidence evaluation method for artificial intelligence image recognition results. The method performs quantitative confidence analysis on the sample conditions of algorithm model training and the corresponding generated recognition results. The confidence value is calculated through two strongly correlated indicators, sample conformity and algorithm capability. The obtained confidence value allows the user to clearly understand the distribution of training sample features in the iterative training process of the artificial intelligence image recognition algorithm model. The credibility of the final recognition result, thereby further improving the training samples and clarifying the specific indicators that need to be optimized in the model.

The present invention discloses a signal processing method, device, system and storage medium for a display device, wherein the method comprises: a mainboard chip acquires a control signal, performs a first encoding on the control signal, and obtains multiple groups of first parallel signals; a signal output chip performs a second encoding on multiple groups of the first parallel signals, and obtains compressed signals; a signal receiving chip decodes the compressed signal, and obtains multiple groups of second parallel signals; a logic board chip performs a third encoding on multiple groups of the second parallel signals, and obtains display signals, and transmits the display signals to a display screen. The present application simplifies the wiring process during the transmission process by compressing and then decompressing the parallel signal during the signal transmission process.

The present invention relates to the field of non-standard parts defect detection methods, and in particular to a non-standard parts defect detection method based on pixel-level deep network feature matching. The method is based on a point matching and alignment algorithm based on deep features and a pixel comparison algorithm based on deep features. The network structure of the point matching and alignment algorithm includes an image encoder, a point feature extractor, a pixel feature extractor, and a pixel comparison network. The present invention proposes a novel deep learning defect detection method that can effectively make high-precision pixel-level predictions based on smaller samples. Since a pixel-level comparison strategy is adopted instead of pixel-level prediction or anomaly detection, deep learning can more easily transfer the knowledge learned from the original similar data set to the current data, thereby avoiding the overfitting problem often encountered in deep learning to a large extent.

The invention discloses a fan rotating speed adjusting circuit, power equipment, an energy storage system and a control method. The fan rotating speed adjusting circuit comprises a comparison circuit, the input end of the comparison circuit is connected with all device temperature sensors, and the comparison circuit is used for inputting sampling voltages output by all the device temperature sensors, determining the maximum voltage value in the sampling voltages output by all the device temperature sensors and outputting the maximum voltage value to a main control chip; and the main control chip is used for determining the highest temperature detected by the temperature sensors of all the devices according to the maximum voltage value and adjusting the rotating speed of the first fan according to the highest temperature. According to the invention, the problems that the number of I / O ports of the main control chip is insufficient and the computing power of the main control chip is insufficient when the number of the power switch devices detected by the fan rotating speed adjusting circuit is large can be solved, and the requirement on the number of the I / O ports and the requirement on the computing power of the main control chip are reduced.

The application discloses a kind of weakly supervised image semantic understanding methods based on multi-task learning, comprising the following steps: obtaining task missing image, constructing multi-level task sharing encoder, extracting high-level semantic information layer by layer, input corresponding decoder branch;Construct public space-task space feature mapping module, through the unaligned task fusion module and task interaction mapping module, update each subtask feature by mapping;Task adaptive feature update module is constructed, and multi-level iterative update unaligned task feature;Task adaptive weakly supervised image semantic understanding framework is constructed, model loss function is established, image data with task missing is input into model, and obtains multi-task prediction result such as semantic segmentation, depth estimation, surface normal estimation.The application is according to the data information of task label unaligned, through the mapping interaction of public space and task space, fully fuses unaligned task feature, iteratively generates high-quality multi-task prediction result, can effectively handle weakly supervised problem with task missing, and simultaneously improves each task prediction accuracy.

The invention provides a building cooling and heating load prediction method based on a generative adversarial network. The method comprises the following steps: constructing a cooling and heating load prediction model and an indoor temperature judgment model; the indoor temperature judgment model can obtain an indoor predicted temperature by taking a mixture of cooling and heating load real data and cooling and heating load prediction data output by the cooling and heating load prediction model as input; based on a generative adversarial network, alternately training the two models to obtain a target cooling and heating load prediction model; the indoor temperature judgment model judges whether the input cooling and heating load data is true or false by judging whether the output indoor predicted temperature and the indoor true temperature are true or false, and then model parameters are optimized; and predicting the cooling and heating load of the building according to the target cooling and heating load prediction model to obtain a cooling and heating load prediction value of the building. According to the invention, the accuracy and convenience of building cooling and heating load prediction are improved, and continuous evolution and updating can be realized through data accumulation.

The application relates to a destructive sleeve dismounting structure capable of avoiding the generation of excess materials, which comprises a support (1), a positioning shaft (2), a bolt (3), a bearing (4), a pressing sleeve (5), a nut (6), a screw (7), a gasket (8), a nut (9), a handle (10), a vertical rod (11), a wrench (12), a tap screw (13), a tap screw (14), a wrench (15), a vertical rod (16) and a handle (17), for the sleeve with a large interference amount with the casing, the positioning shaft (2) is inserted into the sleeve of the casing, and tapping is carried out between the sleeve and the positioning shaft (2), and for the sleeve with a small interference amount with the casing, only the nut (6) is turned to realize the dismounting of the sleeve. The sleeve dismounting structure can be applied to the sleeve with a large interference size and difficult to dismount, and no excess materials are generated, and the dismounting efficiency of the casing sleeve is improved.

The invention provides a blood specific methylation site detection primer group, a kit and a blood trace identification method, and belongs to the technical field of molecular biological identification. The problems that in the prior art, a blood trace identification method is poor in specificity and insufficient in sensitivity, has high requirements for sample quality and quantity and cannot be compatible with subsequent DNA detection are solved. The requirements for the number and quality of body fluid detection materials can be remarkably reduced, the method can be well compatible with subsequent DNA detection, detection does not depend on a single source or a large number of samples any more, and the high stability, accuracy, sensitivity and specificity of the method enable the blood identification result to be reliable. Meanwhile, the method does not depend on a PCR instrument or complex laboratory equipment, so that professional requirements on instruments and operators are reduced. The whole detection process can be completed in a short time, the method has important significance in forensic on-site rapid identification, the case processing efficiency can be improved, and the cost is reduced.

This utility model discloses a gas distributor for a chloromethane synthesis reactor. The main support pipe and the main distribution pipe are arranged parallel to each other and positioned below the main distribution pipe. Distribution branch pipes are provided on the main distribution pipe, symmetrically arranged at a 45-degree angle to the horizontal line of the main distribution pipe. A supporting inclined pipe connects the distribution branch pipes to the main support pipe at a 90-degree angle. Both the main distribution pipe and the distribution branch pipes have three rows of distribution holes, arranged on the lower side of the main distribution pipe and the distribution branch pipes. Two rows are symmetrically arranged at a 45-degree angle to the horizontal line of the main distribution pipe and the distribution branch pipes, and one row is arranged at a 90-degree angle to the horizontal line of the main distribution pipe and the distribution branch pipes. This utility model's gas distributor device has a simple structure, uniform stress on the distribution pipes, and a firm connection. It requires fewer pipe openings at the bottom of the equipment, reducing the risk of material leakage. The steel-lined support rods with a double-layer anti-corrosion design have strong corrosion resistance, extending the service life of components and the equipment maintenance cycle.

The invention relates to an adjustable corner reflector which comprises three supporting rods which are arranged in an umbrella shape, and every two supporting rods are perpendicular to each other to form a supporting vertex part; and the three variable reflecting surfaces are arranged between every two of the three supporting rods. According to the invention, the change of the radar scattering sectional area of the corner reflector is changed by changing the unfolding and folding area of the reflecting surface of the triangular metal film, and the adjustable range of the RCS is 5-40dBsm, so that space-based radar radiometric calibration is realized; by adopting a folding and unfolding mechanism, the requirement of the satellite on the space is reduced; by adopting the adjustable corner reflector with the variable RCS, a plurality of RCS values can be obtained through equivalence, and the requirement for the number of satellites is reduced; the satellite-borne adjustable passive calibrator can make up for the airspace limitation of ground calibration, and realizes global calibration.

The invention discloses an automatic grinding and chamfering method for a steel structure part, which comprises the following steps of: analyzing the physical characteristics of the part and the connection relationship between other parts associated with the part in a steel structure 3D model so as to generate grinding and chamfering information of the part, and generating a grinding and chamfering processing program; the intelligent grinding and chamfering work station completes matching of the incoming part and the grinding and chamfering machining program and executes grinding and chamfering operation. According to the automatic grinding and chamfering method for the steel structure part, the stability of grinding and chamfering operation of the part can be guaranteed, the quality requirements of welding and coating are met, the investment of technicians and operators can be greatly reduced, meanwhile, the skill level of the technicians and the operators is greatly reduced, and the production efficiency is improved. Dependence on skills and quantity of personnel is avoided; and the labor intensity and the occupational health risk of personnel can be greatly reduced, the comprehensive machining cost of steel structure parts is reduced, and the application prospect is good.

The invention discloses a quantum state amplitude coding method and device based on a Gray code, equipment and a medium. The method comprises the following steps: carrying out normalization processing on a real vector to be coded; generating a Gray code queue according to the normalized real vector to be coded; according to the generation sequence of each Gray code in the Gray code queue, calculating any two adjacent Gray codes to obtain a corresponding target XOR value; encoding the normalized real vector to be encoded by adopting a quantum state encoding algorithm to obtain a parameter of an Ry gate; constructing a target quantum circuit according to the Gray code queue; the target quantum circuit comprises a plurality of X gates and Ry gates, and each X gate and each Ry gate are alternately arranged; the application position of each X gate is determined according to a target exclusive-or value; the application position of each Ry gate containing parameters is determined according to each Gray code; and obtaining a target quantum state through target quantum circuit evolution. According to the invention, the amplitude coding efficiency can be effectively improved under the condition that the number of quantum gates using quantum circuits is reduced.

The invention relates to a method for predicting system intelligent horizontal driving combat effectiveness based on small samples, belongs to the technical field of combat system simulation and evaluation, and aims to solve the problem of data scarcity and technical bottleneck existing in combat system effectiveness prediction. A correlation degree matrix is obtained through mechanism analysis under the condition that simulation data samples are few, and prediction quantity of combat effectiveness change caused by intelligent horizontal change is superposed on simulation experiment samples, so that the prediction quantity of combat effectiveness is formed. Therefore, a set of system intelligent level combat effectiveness prediction method with good feasibility and interpretability under the condition of small simulation experiment samples is established, and effective theoretical and technical support is provided for intelligent upgrading of a combat system.

The application provides a communication radiation source identification method, device and equipment and a storage medium. The method comprises the following steps: obtaining a signal feature of a radio signal; inputting the signal feature into a pre-trained communication radiation source identification model to obtain a communication radiation source identification result corresponding to the radio signal; wherein the communication radiation source identification model comprises a feature reconstruction subnetwork and a feature classification subnetwork, and the feature reconstruction subnetwork is obtained through feature reconstruction training by taking the signal feature of a radio signal sample as a training sample and a training label respectively. The communication radiation source identification method greatly reduces the quantity requirement of labeled samples, can achieve the purpose of communication radiation source identification under the condition of a small number of labeled samples, and thus makes the method competent for more communication radiation source identification tasks.

The present invention discloses a Rayleigh wave dispersion curve automatic extraction method based on an improved U-net neural network, including constructing a dispersion curve training set; constructing a dispersion curve test set; cutting the image data in the dispersion curve test set and the dispersion curve training set, and binarizing the theoretical dispersion curve in the dispersion curve training set; geometrically transforming the image data in the dispersion curve training set to obtain an expanded dispersion curve training set; constructing an improved U-net neural network model, and using the expanded dispersion curve training set for model training; and extracting multi-order Rayleigh wave dispersion curves from the dispersion curve test set using the trained improved U-net neural network model. The present invention makes full use of the image segmentation capability of deep learning, can quickly and accurately classify the dispersion energy map of field surface wave data, improves the efficiency of extracting Rayleigh wave dispersion curves, and further improves the efficiency of surface wave exploration.

The application discloses a kind of wide temperature range thermoplastic resin-based composite interface strength real-time testing methods, and the application belongs to the field of composite materials, to provide new method for the real-time testing of thermoplastic composite interface strength under variable temperature environment and the interface strength testing of thermoplastic resin softening under high temperature.The application realizes the real-time testing of fiber reinforced thermoplastic resin-based composite interface strength under wide temperature range by measuring the impedance of magnetic fiber embedded in thermoplastic resin in variable temperature environment.The method is simple to test, high in testing efficiency, widely applicable, can realize the real-time testing of thermoplastic resin-based composite interface strength under wide temperature range of-60 DEG C to 150 DEG C, and provides data support and performance guarantee for the service safety of materials under high and low temperature complex environment.

The application discloses a drill pipe box and a drill pipe conveying device, and relates to the technical field of geological drilling mechanical equipment, which comprises a box body, a lifting mechanism and an adjusting mechanism; the box body is used for storing drill pipes; the adjusting mechanism is arranged outside the box body and is used for adjusting the height and / or the inclination angle of the box body; the lifting mechanism is arranged on the box body and is used for lifting or lowering the drill pipes in the box body; the lifting mechanism can lift the drill pipes to the top outlet of the box body, so that the drill pipes are rolled and transferred under the action of gravity; the application also provides a drill pipe conveying device, which comprises a storage arm, a catwalk machine and a drill pipe box; the storage arm is arranged between the drill pipe box and the catwalk machine and is used for transferring the drill pipes from the drill pipe box to the catwalk machine or from the catwalk machine to the drill pipe box; therefore, the device can reduce the operation difficulty and improve the drilling operation efficiency.

The utility model discloses a system capable of being used for producing various preparations. The system comprises two tank bodies, the first tank body comprises a top stirring device and at least two output pipelines; wherein at least one first output pipeline is provided with a filtering device, and the output end of the filtering device is connected with the input end of the second tank body; a homogenizing device is arranged on at least one second output pipeline, and the output end of the homogenizing device is respectively connected with the input ends of the two tank bodies; a circulating pump is arranged on an output pipeline of the second tank body, and the output end of the circulating pump is connected with the input end of the second tank body and the input end of a filling device; the system also includes a valve and a pump for adjusting a fluid flow path in the conduit. According to the utility model, the system structure for processing various preparations can be greatly simplified, and the purposes of reducing the cost, improving the efficiency, reducing the space requirement and the like are achieved.

This invention discloses a natural electric field source inversion method based on a genetic algorithm, belonging to the field of geophysical inversion technology. It solves the technical problems of low inversion accuracy and large source location errors in natural electric field inversion caused by optimization algorithms. The key points of the technical solution are: first, expanding the input electrical resistivity data using head-to-tail cross-interpolation; second, using the extreme values ​​and dispersion of the electrical resistivity data as the center and radius of the population distribution area; third, forming a population by describing individuals based on the number and location of source sources; and finally, using a genetic algorithm based on double-threshold cross-iteration to achieve natural electric field source inversion with smaller source fitting errors. This application can effectively utilize a small amount of input electrical resistivity data, reasonably expand and extract extreme value features, and largely solve the problems of large inversion fluctuations caused by large spatial areas, small data volumes, and the inherent multiple solutions in geophysical inversion, while achieving smaller source fitting errors.

The embodiment of the application provides a kind of image denoising method, device, system, edge device and storage medium, the method comprises: obtaining to be denoised image;With preset multi-head attention mechanism module, the first feature matrix of to-be-denosed image is extracted, wherein, preset multi-head attention mechanism module includes self-attention mechanism and channel attention mechanism;First feature matrix is up-sampled, and second feature matrix is obtained;Based on second feature matrix, the denoised image corresponding to to-be-denosed image is generated. The technical scheme provided in the embodiment of the application can improve the image denoising efficiency, reduce the consumption of computing resources, and then reduce the performance requirements of the device.

The invention relates to a marine distributed air conditioning system which is composed of a fresh air conditioner, a distributed air conditioner, a variable air volume terminal device and a cabin temperature controller. After the fresh air conditioner processes fresh air outside the cabins, the fresh air is sent to the distributed air conditioners in all the areas, the processed cabin return air and the fresh air are mixed through the distributed air conditioners and then sent to all the cabins, and the opening degree of the variable air volume tail end is changed through the cabin temperature controllers in the cabins to adjust the air supply volume so as to achieve independent regulation and control over the temperatures of all the cabins. Only one to two fresh air conditioners can be arranged in one area, and the distributed air conditioners can be flexibly arranged in an outer aisle of a cabin or other equipment cabins, so that the independent temperature regulation and control capability of the cabin is improved and the noise of the cabin is reduced under the condition of reducing the occupation of total space resources.

The utility model relates to the technical field of reaction kettles, in particular to a stable reaction kettle which comprises an upper shell and a lower shell which are connected into a whole and distributed up and down, a cavity is formed between the upper shell and the lower shell, the upper shell is rotatably connected with a rotating shaft extending into the cavity, and the rotating shaft is fixedly connected with a plurality of stirring fan blades. A control device for dividing the cavity into an upper stirring area and a lower stirring area is arranged between the upper shell and the lower shell; through the structure of the first separation sheet and the second separation sheet, the cavity is divided into an upper stirring area and a lower stirring area on the cross section of the cavity, and when the first separation sheet is rotated, the covering part on the first separation sheet leaves from the channel on the other first separation sheet and the channel on the second separation sheet; in other words, the covering parts on the first partition piece and the second partition piece are gradually overlapped on the projection plane, so that the channels on the first partition piece and the second partition piece are communicated, the upper stirring area and the lower stirring area are communicated, the influence of foreign objects on the reaction process is reduced, and the product stability is improved.

The present invention discloses an image processing method of fusion splicing and target detection based on multi-task learning, and the multi-task learning processing model used includes a feature extraction module, an image splicing module, a target detection module and a fusion module. The feature extraction module is used to extract features from each original image respectively, and transmit the extracted feature map to the image splicing module and the target detection module. The image splicing module splices the original images into a complete image based on the feature maps of each original image. The target detection module detects the target in each original image and obtains the initial annotation information corresponding to each original image. The fusion module is used to map the initial annotation information of each original image to the complete image to obtain the final annotation information. The model of the present invention is constructed based on multi-task learning, which reduces the requirements for samples and improves the training efficiency, generalization ability and processing speed.

The application provides a polypeptide generation method and device, and relates to the technical field of polypeptide design. The method comprises the following steps: obtaining preset polypeptide information pool and structure information of a target protein, wherein the preset polypeptide information pool comprises amino acid sequence information of at least one existing polypeptide; performing ladder element extraction on the amino acid sequence information of the at least one existing polypeptide to obtain a plurality of ladder elements, wherein the ladder element is a repeated amino acid fragment in the amino acid sequence information of the at least one existing polypeptide or a basic amino acid constituting the amino acid sequence information; reconstructing at least one new amino acid sequence information according to the plurality of ladder elements; and determining a target new polypeptide from the at least one new amino acid sequence information according to a molecular docking result of the at least one new amino acid sequence information and the structure information of the target protein. The application can reduce the dependence on a large amount of training data and improve the interaction effect of the generated polypeptide and the target protein.