17 results about "Nonlinear methods" patented technology

Disclosed is a dynamic and visually-driven interface that revolutionizes AI-based content creation. This interface leverages graphical tools, enabling users to intuitively prompt a generative AI model. Instead of relying solely on text-based prompts, users employ a combination of drag-to-prompt, file imports, tap-for-value, dial-for-value, and other visually intuitive tools. The system offers capabilities like long-form prompting, adaptive prompting, augmented reality integration, and collaborative prompting. One standout feature is the flexibility of inserting, replacing, or dragging blocks from different conversation chains, allowing users to influence content direction. This facilitates a non-linear approach to AI content creation, offering more control over outputs. Enhancements also include a fact-checking module and stylistic filters, elevating content accuracy and appropriateness.

The present invention discloses a multi-agent collaborative task allocation method based on an improved particle swarm algorithm with non-dominated sorting, establishes a model for multi-agent collaborative task allocation, and realizes the simultaneous optimization of multiple indicators such as attack benefits, resource consumption, and damage probability. In view of the characteristics of the problem of multi-agent collaborative task allocation, the present invention combines the multi-objective particle swarm algorithm with the non-dominated sorting algorithm, incorporates the non-dominated sorting algorithm and the cross-mutation mechanism, designs a nonlinear method for improving the inertia weight value, and proposes a maximum distance method for obtaining the optimal solution of the Pareto solution obtained by the algorithm, which greatly improves the global search and optimization ability of the algorithm and its engineering application value. Compared with traditional optimization methods, the method of the present invention has better convergence and accuracy when solving multi-objective optimization problems in dynamic environments.

The invention discloses a cross arm and insulator installation robot motor control method based on a T-S fuzzy model, and the method comprises the following steps: building a permanent magnet synchronous motor nonlinear model according to electromagnetism and motor dynamics; based on a sector nonlinear method, establishing a permanent magnet synchronous motor T-S fuzzy model; designing an observer to obtain a load torque estimated value; designing an L-infinity robust controller to ensure that the angular velocity of the motor can track a reference instruction; and an anti-control gain matrix solving criterion is formulated, and it is ensured that the system meets performance indexes. According to the method, the nonlinear control problem of the permanent magnet synchronous motor system is effectively solved, the influence of continuous interference signals on the system can be effectively suppressed, and the robustness of the system is enhanced.

The application relates to a kind of electric rudder control quantity increment processing and commutation short-circuit prevention control method and device, method includes: control quantity increment processing step: the output control quantity of previous control cycle is divided into three kinds of conditions greater than 0, less than 0 or equal to 0, the size and symbol of current control quantity are combined, the amplitude of current control quantity is adjusted dynamically to output control quantity increment processing current output control quantity respectively;Commutation short-circuit prevention control step: according to the sign change of the input commutation short-circuit prevention control input quantity and the output control quantity of previous control cycle, the control direction and control quantity size of electric rudder driver control are processed, the commutation short-circuit prevention output logic is executed, and the current output control quantity of commutation short-circuit prevention control is output.The application adopts nonlinear method, solves the problem of electric rudder heating and driver commutation short circuit when electric rudder instruction changes rapidly.

The application proposes an aero-engine health index modeling method fusing linear and nonlinear characteristics, specifically comprising the following steps: arranging a multi-source sensor detection system to collect aero-engine operation state multi-source data; normalizing the collected data and performing reliability screening; based on the remaining sensor data after screening, respectively using VAE to extract nonlinear degradation features and SPCA to extract linear degradation features; according to the obtained nonlinear and linear degradation features, designing dynamic fusion weights, and combining a weighted moving average optimization algorithm to construct a composite health index. The application effectively fuses multi-source sensor data, fully utilizes the complementary characteristics of linear and nonlinear methods, constructs a more reliable composite health index, and can intuitively reflect the degradation state of the aero-engine, providing an important reference for the evaluation of the aero-engine operation state, the prediction of the remaining life and the scientific formulation of the maintenance strategy.

The invention discloses a T-S fuzzy rule reduction modeling method for a photovoltaic power generation system, and belongs to the technical field of new energy photovoltaic power generation system modeling. The modeling method comprises the following steps: constructing a nonlinear dynamic model of the photovoltaic power generation system; establishing a system state equation based on the dynamic model, and dividing non-linear terms in the equation into direct non-linear terms and indirect non-linear terms; defining a antecedent variable, a membership function and a fuzzy rule, performing fuzzy linearization on direct and indirect non-linear terms by using a sector non-linear method, and giving a T-S fuzzy model; and carrying out defuzzification to obtain a T-S fuzzy photovoltaic power generation system model. According to the method, the fuzzy coupling relation between the nonlinear terms of the system is reconstructed by using the method for dividing the nonlinear terms, the fuzzy rule of the T-S fuzzy photovoltaic power generation system model is effectively reduced, and the calculation complexity of a model-based algorithm in actual engineering can be remarkably reduced.

The invention relates to a borehole transient electromagnetic instrument azimuth angle misalignment error correction method based on particle swarm optimization, and belongs to the technical field of borehole transient electromagnetic imaging. Comprises: obtaining error correction data; initializing a misalignment error angle, a particle swarm number, a particle swarm position, an individual optimal position, a swarm optimal position and a fitness threshold; calculating the updating speed and the latest position of each misalignment error angle in each particle; calculating the attitude angle of the borehole transient electromagnetic probe rod, and calculating the fitness of each current particle in combination with the real attitude angle measured by the inclinometer calibration table; comparing with the fitness calculated by the historical optimal position of each particle and the swarm optimal position of the particle swarm to obtain a new historical optimal position and the swarm optimal position of the particle swarm; repeating the initialized steps in the above steps until the fitness meets the requirement; obtaining an optimal misalignment error angle; according to the method, the optimal error correction angle is directly fitted through a nonlinear method, and the bottleneck that an overdetermined equation needs to be inversely solved by adopting a complex numerical algorithm in a traditional plane correction method is broken through.

The present invention discloses a two-dimensional stable movement control method for a multi-degree-of-freedom wheeled inverted pendulum type robot, belonging to the field of robotics. The present invention divides the multi-degree-of-freedom wheeled inverted pendulum into an equivalent wheeled inverted pendulum and a multi-link part, and designs controllers separately. The first two lines of the dynamic equation of the multi-degree-of-freedom wheeled inverted pendulum are the dynamics-related terms of the equivalent wheeled inverted pendulum. The partial feedback linearization method is used to process the first two lines of the dynamic equation to obtain a new system with the angular acceleration of the driving wheel as the control input and a feedforward equation with the control torque of the driving wheel as the output. The controller of the new system is designed using a linearization or nonlinear method to calculate the angular acceleration of the driving wheel. Substituting it into the feedforward equation obtains the desired torque of the final driving wheel. The desired center of mass position or velocity is calculated by solving inverse kinematics to calculate the motion angle or angular velocity of the joint. The control method proposed by the present invention still has strong adaptability to large acceleration and deceleration motions and uneven road movement conditions.

The application provides a time-sensitive moving target multi-beam joint focusing method, a storage medium and an electronic device, and relates to the technical field of radars.A linear processing process is formed by a constructed generalized sliding window matching function and a multi-beam focusing matching function, the problem that a weak moving target is easily submerged in noise due to the fact that a non-linear method is used to compensate for energy defocusing of the moving target in the prior art method, resulting in serious energy loss, is overcome, and the performance of focusing on the weak moving target is improved.Furthermore, the initial beam time of the moving target, the target cross-beam time, the scene center slant range, the radial velocity, the radial acceleration and the radial jerk obtained by searching are used for compensating for additional azimuth window modulation due to the fact that the moving target crosses multiple beams and complex range-azimuth migration in a single beam, and precise focusing of the weak moving target is realized.

The invention relates to the technical field of non-contact near-infrared spectrum analysis, and discloses a non-contact online near-infrared spectrum analyzer and an analysis method.A light source module adopts a main light source and a plurality of auxiliary light sources with characteristic absorption peaks, so that enhanced analysis based on characteristic wavelength direct response can be realized; the inherent limitations of absorption peak overlapping and baseline drift in a traditional diffuse reflection spectrum are overcome, the prediction precision is improved, and the measurement effect is optimized. The receiving module adopts a plurality of optical fibers, the sampling ends of the plurality of optical fibers are uniformly distributed along the circumferential direction, the sampling ends of the plurality of optical fibers are distributed up and down in the direction vertical to the sample, and the detection ends of the optical fibers are uniformly distributed along the length direction of the slit of the spectrometer, so that the light collection efficiency is greatly improved, and the utilization efficiency of light source energy is maximized; and diffuse reflection / scattered light signals returned from the sample are efficiently captured, and the interference of environmental stray light is effectively isolated and weakened. In addition, a linear method and a nonlinear method are used in a mixed mode, and higher prediction precision is achieved.

The application discloses an electroencephalogram-based fatigue detection model system, method, electronic equipment and storage medium, wherein the electroencephalogram-based fatigue detection model system comprises a modal data acquisition unit configured to acquire different modal data; a multi-view embedding module comprising a dedicated embedding layer for the different modal data and configured to extract embedding sequences of the different modal data by using linear and nonlinear methods; a modal mixing transformer configured to perform multi-modal feature interaction on the embedding sequences to obtain a multi-modal mixing result; and an adversarial domain generalization module configured to perform transfer learning on the multi-modal mixing result, so that the model can learn more generalizable feature representations.

The application discloses a power system dynamic observability calculation method based on a data-driven Koopman operator, belongs to the technical field of power system dynamics and observability analysis, and comprises the following steps: establishing a power system dynamic observability analysis model based on system state variables and measured variables; converting the established dynamic state observability model into an augmented Koopman canonical coordinate system; constructing an observation matrix of the system in the augmented Koopman canonical coordinate system; and calculating the dynamic observability degree of the power system by using a matrix index in the Koopman space. The method of the application uses the data-driven Koopman operator, overcomes the inaccuracy of the model while considering the nonlinear characteristics of the power system dynamic model, effectively solves the low-precision problem of the traditional linear method and the problem of excessive calculation amount of the nonlinear method, and can realize efficient and rapid analysis and calculation of the dynamic observability of the power system.

The application discloses an infrared focal plane polarization correction method based on the reflection polarization characteristics of a polarizer and belongs to the technical field of polarization imaging and test measurement. The method of the application is as follows: a correction coefficient is added to adjust additional radiation to obtain a radiation transmission correction model of an infrared polarization imaging system with a front polarizer; a nonlinear method is used to fit the relationship between image gray scale and incident radiation to realize response correction of the infrared polarization imaging system with the front polarizer; the infrared polarization imaging system with the front polarizer is used to calibrate a temperature-controllable adjustable infrared polarization radiation source; a radiation transmission model of an infrared focal plane polarization imaging system is constructed; and the temperature-controllable adjustable infrared polarization radiation source is used to perform response correction and polarization correction on the infrared focal plane polarization imaging system. Compared with placing a high-extinction-ratio polarizer in front of a black body, the application can avoid over-correction of the parameters of a micro-polarizer array and improve the correction accuracy of the infrared focal plane polarization imaging system.

The invention relates to the technical field of wafer-level test anomaly detection, and discloses a chip wafer-level test anomaly detection method based on multi-dimensional parameter correlation analysis, which comprises the following steps: acquiring and preprocessing wafer test core parameters and equipment operation parameters, constructing a dynamic parameter correlation reference model, and establishing a dynamic parameter correlation reference model; the fusion correlation deviation degree of real-time parameters and a normal correlation coefficient matrix is calculated, a scene exclusive dynamic threshold value is set, explicit and implicit anomaly judgment is completed in combination with a single parameter specification, and anomaly source tracing is achieved through a dynamic correlation list, feature screening and time sequence-space two-dimensional detection. The hybrid algorithm is adopted to calculate the correlation deviation degree, linear and nonlinear methods are fused to screen features, the defect that only dominant anomalies can be recognized in the prior art is broken through, collaborative accurate detection of hidden anomalies and dominant anomalies in specifications is achieved, meanwhile, the anomaly root can be traced, dynamic changes of the wafer manufacturing process are adapted, and the detection accuracy is improved. And the comprehensiveness and accuracy of anomaly detection are improved.

The present application relates to the technical field of non-contact near-infrared spectrum analysis, and discloses a non-contact online near-infrared spectrum analyzer and an analysis method, wherein a main light source and a plurality of auxiliary light sources with characteristic absorption peaks are adopted in a light source module, so that enhanced analysis based on direct response of characteristic wavelengths can be realized, inherent limitations of absorption peak overlap and baseline drift in traditional diffuse reflection spectrum are overcome, prediction accuracy is improved, and measurement effect is optimized. A plurality of optical fibers are adopted in a receiving module, sampling ends of the plurality of optical fibers are uniformly distributed in a circumferential direction, the sampling ends of the plurality of optical fibers are distributed in a high-low manner in a direction perpendicular to a sample, and detection ends of the optical fibers are uniformly arranged in a length direction of a slit of a spectrometer, so that light collection efficiency is greatly improved, utilization efficiency of light source energy is maximized, diffuse reflection / scattering light signals returned from the sample are efficiently captured, and interference of environmental stray light is effectively isolated and weakened. In addition, linear and nonlinear methods are mixedly used in the present application, and higher prediction accuracy is achieved.

The present invention relates to a stress curve denoising method, device, electronic device and storage medium, and belongs to the technical field of geological exploration. The method comprises obtaining a sampling point time series and a stress value series on a stress curve; then sparsely resampling the sampling point time series and the stress value series based on a nonlinear method to obtain a sparsely resampled time point series and a sparsely resampled stress value series; and denoising the sparsely resampled time point series and the sparsely resampled stress value series to obtain a denoised sampling time point series and a denoised stress value series. A denoised stress curve can then be obtained based on the denoised sampling time point series and the denoised stress value series. After sparsely resampling using the nonlinear method, denoising is performed, thereby retaining effective information in the stress curve and improving the accuracy of the denoised stress curve.

The present application relates to the technical field of artificial pancreas, and particularly relates to an optimization method for insulin infusion rate in artificial pancreas, comprising the following steps: S1: establishing a blood glucose control mathematical model, calculating a general expression of insulin infusion rate containing an equivalent part and an equivalent linear equation of insulin concentration error; S2: improving a conventional linear insulin infusion rate method in a closed loop system of artificial pancreas, and proposing a nonlinear method capable of replacing the conventional linear insulin infusion rate, namely a non-smooth infusion rate; S3: optimizing an insulin infusion rate improvement gain parameter in the nonlinear method in step S2, so that the insulin concentration reaches an expected value more quickly, the required maximum infusion rate is smaller, and the consumed energy is also smaller. The optimization method can significantly improve the control speed of the insulin concentration, and the required maximum infusion rate is smaller and the consumed energy is also smaller.