17results about How to "Avoid complex calculations" patented technology

The invention discloses a non-linear state rapid fitting method for an aircraft, and belongs to the field of aircraft control. The implementation method comprises the following steps: constructing a two-loop attitude pilot and a three-loop attitude pilot, and discretizing to obtain a guidance instruction with a time-delay effect; according to coordinate conversion, forward deriving each aerodynamic parameter of the aircraft and an aircraft overload instruction equation; the method comprises the following steps: calculating all pneumatic data according to part of pneumatic data obtained by a blowing experiment of an aircraft, and fitting a guidance instruction with a balance attack angle, a sideslip angle and a rudder deflection angle of the aircraft to obtain a corresponding interpolation table; all aerodynamic parameters in the flight process of the aircraft are obtained according to an aircraft guidance instruction and an interpolation table in the actual situation, namely, nonlinear state rapid fitting of the aircraft is achieved, and simulation reproduction of the aircraft as a mass point in the whole guidance process is achieved according to the nonlinear state rapid fitting result. And the precision and efficiency of aircraft guidance control are improved.

The embodiment of the invention provides a clock gating circuit conversion method and device and related equipment, and the method comprises the steps: obtaining target circuit design data of a clock gating circuit before conversion, the target circuit design data being part of data in the circuit design data of the clock gating circuit before conversion; predicting the power consumption income of the clock gating circuit before conversion based on the target circuit design data by using a pre-established power consumption income prediction model to obtain a power consumption income prediction result; wherein the power consumption income prediction model is used for predicting a power consumption change trend between the clock gating circuit before conversion and the clock gating circuit after conversion so as to form a power consumption income prediction result; if it is determined that the power consumption income prediction result is the forward power consumption income, the clock gating circuit before conversion is converted into the clock gating circuit after conversion. According to the technical scheme provided by the embodiment of the invention, the efficiency of determining the switching effectiveness of the clock gating circuit can be improved.

The invention discloses a similar surgery picture retrieval method, system and equipment for minimally invasive surgery based on deep learning and a medium, and relates to the technical field of image processing. Respectively extracting original image features in the preprocessed video stream and original text features in the preprocessed text content; performing interactive fusion on the original image features and the original text features by adopting a feature fusion module; using a feature codebook module to map the fusion feature into a codebook vector; a mapping feature decoding module is adopted to decompose the codebook vector into compressed image features and compressed text features, finally, the compressed image features are decoded into similar images, and the compressed text features are decoded into text descriptions corresponding to the similar images; and the operation picture can be quickly and accurately retrieved.

The invention discloses a secret key following transmission system and method based on dynamic window encryption, and the system comprises a transmitting end which is configured to obtain a chaotic initial value and an original signal to be transmitted; processing the chaotic initial value through a public key encryption module and a first constellation mapping module to obtain encryption key information; the original signal is processed by a bit stream encryption module, a second constellation mapping module and a symbol encryption module to obtain encrypted information, the bit stream encryption module realizes bit stream encryption by using a disturbance sequence generated by a chaotic initial value, and the symbol encryption module realizes symbol-level scrambling by using a'dynamic window structure '; superposing the encrypted information and the encrypted key information by using a power division multiplexing module to obtain to-be-transmitted composite information; the composite information is converted into a time domain signal through fast inverse Fourier transform (IFFT), and signal transmission is carried out through a channel; and dual improvement of communication safety and communication efficiency is realized.

The invention relates to the technical field of information, in particular to an artificial intelligence decision support method and system for high-frequency transactions. The method comprises the steps of collecting order book data, and obtaining a fluctuation rate and a trading price difference based on the order book data; the window at the current moment is adjusted based on the volatility to obtain a window at the next moment, and window detection is completed through the hash value; counting the order quantity difference of the key prices at the current moment and the adjacent moment and the difference between the buying and selling price difference at the current moment and the maximum buying and selling price difference for the window with the data change, and obtaining a dynamic compression ratio based on the two differences; the DPCM algorithm and the dictionary compression algorithm are adjusted based on the dynamic compression rate, and then compression is carried out; and generating a decision signal based on the compressed data to complete decision support. The compression speed is increased, and the accuracy and integrity of the data are improved.

The application discloses a kind of quick cross path scheduling methods of inter-city area customized public transport system, the shortest distance method between regions is used to build start point area end point set and end point area start point set, to generate start point area travel sequence Yo by insertion method, to generate end point area travel sequence Yd by insertion method, then the Yo and Yd are optimized by quick exchange method, finally the minimum value of start point × Yo × Yd is solved, which is the final inter-city area customized public transport system target path, with the shortest bus travel distance as the target;The method does not use probability distribution, effectively avoids the fluctuation of the final path result, according to the characteristics that the distance between nodes in different regions is much larger than the distance between nodes in the same region, the inter-regional traffic node set is established, and it is used as the end point of the start point region and the start point of the end point region, respectively, to maximize the range of optimal solution, effectively reducing the overall calculation scale.

The present invention discloses a method for obtaining a gas-water relative permeability curve of tight sandstone based on a DAE-DNN model. The relative permeability curve is obtained by a Brooks-Corey model, and combined with fracture parameters, construction parameters, and seepage characteristic parameters, production data is obtained through numerical simulation of gas reservoirs, including water production, gas production, and pressure. The production data, fracture parameters, construction parameters, and seepage characteristic parameters are subjected to dimensionality reduction processing using DAE, and the dimensionality reduction data is used as input, and the parameters related to the relative permeability curve are used as output. The parameters related to the relative permeability curve are imported into DNN to predict, and finally the relative permeability curve is determined by normalizing 10 groups of relative permeability curves predicted by the prediction simulation set. The present invention can quickly and accurately calculate the gas-water relative permeability curve, better reflect the actual gas-water flow capacity, and can provide strong support and guidance for gas field development and production.

The invention provides an express delivery path planning method based on a shortest loop, and aims to optimize the delivery path of a courier and improve the delivery efficiency. Firstly, express stations are determined as a starting point and an ending point, and longitudes and latitudes of all delivery places are recorded; then, whether the places are dispersed or not is detected through a distribution place dispersion judgment formula; and for the scattered places, constructing an outermost convex polygon path planning loop, and recursively constructing convex polygon loops for the remaining places until the number of the remaining places is not more than three. A path is systematically planned through a hierarchical convex polygon loop and a corresponding set of vertexes. Then, a migration site and a judgment site are determined, an FMP is inserted into the outermost loop in the clockwise direction, and path planning is updated; finally, when all places are included in a single convex polygon loop, an optimal path planning result is obtained. According to the method, the efficiency and accuracy of path planning are remarkably improved, and the method is suitable for various logistics distribution scenes.

The low-power pulse wave signal arrhythmia classification method and system of the application comprises the following steps: using a large convolution kernel to extract the bottom local features of the original signal, and reducing the sequence length by half through pooling; adopting a leaky integral-discharge neuron activation to make the data pulsed; using a large convolution kernel and a hollow convolution to expand the receptive field and capture longer-range local timing features; dimensionally reducing the output features, cooperating with batch normalization, leaky integral-discharge neurons and maximum pooling, and aggregating the local features; calculating self-attention in each subsequence, combining a linear mapping layer, focusing the model on the feature correlation in the local subsequence through the aggregation of the sub-attention map, and extracting the waveform dependence in the short time window of the pulse wave signal; calculating QKV interaction on the whole sequence, combining a linear layer and a pulse neuron, capturing long-distance global feature correlation, and mining the waveform dependence in different time periods of the pulse wave signal. The application can achieve a classification performance equivalent to that of a deep artificial neural network.

The present invention relates to a method for analyzing the online cycle of a continuous casting machine sector guide roller based on finite element analysis, which comprises the following steps: establishing a finite element mathematical model for a group of down rollers of the continuous casting machine sector guide roller, collecting relevant data of the down rollers of the continuous casting machine sector, simulating the dynamic behavior of the material during high temperature deformation by using bilinear materials, and generating material constitutive curves; using augmented Lagrangian to perform theoretical analysis on the nonlinear contact between the roller surface and the slab surface, and by artificially introducing the penetration amount and the initial contact stiffness coefficient, performing iterative calculations, completing the estimation of the external fatigue cycle of the down roller, generating a life cloud map and a damage cloud map, and finding the lowest life point for estimation. Sub-model calculations are used to further verify the results. The method is simple and reliable, and the estimation of the external fatigue cycle of the down roller is completed within the finite element software, which is fast and efficient. The present invention can be widely used in the estimation and analysis of the online cycle of the sector guide roller of the continuous casting machine.

This application discloses a method for determining a display mode and a vehicle, relating to the field of vehicle control technology. The method includes: determining the first importance of a vehicle function to be displayed to the occupants based on their attribute information; determining the second importance of the vehicle function to the current driving process based on the vehicle's current driving scenario; determining the vehicle's usage preference for the vehicle function based on its historical usage information; and fusing the first importance, second importance, and usage preference levels to determine the target display mode corresponding to the vehicle function based on the fusion processing result. The technical solution of this application embodiment can make the target display mode more closely match the actual driving conditions of the vehicle and the actual needs of the occupants, thereby improving the convenience and experience of occupants using vehicle functions.

This invention discloses a machine learning-based method and system for predicting the production capacity of gas-water two-phase gas in tight sandstone. The method includes: constructing production capacity prediction models for different well types using an artificial neural network; inputting data such as critical flow saturation, water saturation, water phase relative permeability curve index, starting pressure gradient, permeability, reservoir thickness, fracture conductivity, fracture length, cluster number, and stress sensitivity coefficient as input variables into the production capacity prediction model, and using cumulative gas and water production as output variables. The input variables are then imported into the corresponding production capacity prediction model for different well types to obtain the cumulative gas and water production for each well type. This method uses an artificial neural network to construct a production capacity prediction model to predict the cumulative gas and water production in tight sandstone, achieving rapid and accurate prediction of the production capacity of the gas-water two-phase gas in tight sandstone, avoiding complex calculation processes, and reducing computation time and production costs.

The present invention belongs to the field of power electronics technology, and discloses a modeling method of a discontinuous conduction mode DC / DC converter based on a signal flow graph method, and analyzes three modes of the discontinuous conduction mode DC / DC converter in steady state to obtain voltage and current waveforms at both ends of the energy storage inductor. When the DC / DC converter is a non-isolated converter, the corresponding energy storage inductor is a pure inductor type, which can be equivalent to a control current source with a duty cycle disturbance as the control variable and an internal resistance in parallel; when the DC / DC converter is an isolated converter and the transformer has energy storage, the corresponding transformer is a coupled inductor type, and is connected in parallel with an ideal transformer on the basis of the pure inductor. In the derivation process of the model, the present invention has a clear physical meaning starting from the essence of the small signal model; the Mersenne formula is directly used in the model calculation, which avoids the complex calculations in the traditional modeling method, and can effectively reduce the difficulty of modeling the discontinuous conduction mode DC / DC converter.

The present application relates to a kind of geothermal wellbore scale intelligent scale removal system, including wellhead monitoring module, downhole monitoring module, main control system, injection module;Main control system includes the analysis module, dosing scheme generation module, control module connected in sequence;Injection module includes the lifting unit connected, injection unit;Analysis module, for according to the wellhead geothermal fluid data, downhole geothermal fluid data and multiple-field multiphase multi-component non-isothermal phase transition flow model obtained by real-time monitoring, inversion obtains the real-time flashing face depth of geothermal fluid in wellbore, and the real-time scale rate of different depth positions;Dosing scheme generation module, according to the real-time flashing face depth, the real-time scale rate of different depth positions, real-time generates corresponding scale inhibitor dosing scheme, scale inhibitor dosing scheme includes scale inhibitor injection rate, scale inhibitor injection depth;Control module, for according to real-time scale inhibitor dosing scheme to lifting unit, injection unit is controlled.The present application can realize intelligent scale removal.

The invention discloses a voice processing method of an early education robot and the early education robot, and relates to the technical field of voice processing, and the method comprises the steps: receiving a voice instruction inputted by a user for recognition, and when the voice instruction is recognized as a teaching instruction, displaying the teaching content in the teaching instruction to the user; after the teaching content is displayed, receiving feedback voice of a user and collecting a feedback image of the user; the feedback voice and the feedback image are subjected to content consistency verification, after the consistency verification is passed, whether the feedback voice and the feedback image conform to the teaching content is judged, an early education processing result is obtained and displayed to the user, and the early education processing result comprises feedback correctness or feedback error. The technical problems that in the prior art, an early education robot is large in voice recognition computing power consumption and poor in early education effect are solved.

A method and system for calculating customer indicators in the Internet field based on a rule engine, relating to the field of data processing technology. The method solves the problem that the existing customer indicator calculation method uses machine learning technology for data processing, consumes a lot of computing resources, cannot respond to market changes and customer needs in a timely manner, and customer indicators usually involve multiple dimensions and complex features. High-dimensional data makes the feature selection process complicated and time-consuming. The method includes: obtaining customer data and product data information, and preprocessing the customer data and product data information; encrypting the preprocessed customer data and product data information to obtain encrypted data information; constructing a feature extraction model, and extracting features from the encrypted data information according to the feature extraction model; constructing rule trigger conditions, and using the rule trigger conditions to match the data after feature extraction to calculate customer indicators. It is applied to risk assessment and e-commerce fields.