19 results about "Chaos theory" patented technology

The invention relates to the technical field of graph neural networks, in particular to an ideological and political education video content compliance examination system based on a dynamic graph neural network. The module comprises three layers of progressive innovation units: a semantic space mapping unit maps text data into a semantic space of a dynamic dimension to form a semantic unit, and can adaptively adjust the dimension according to content complexity; the keyword network construction unit constructs a keyword association network containing a hierarchical subgroup structure based on a group theory principle, so that the network is kept stable and can be flexibly evolved; the network sensitivity analysis unit performs sensitivity analysis on the keyword association network based on the chaos theory and maps the network state to a predefined compliance attractor pattern library, the advanced mathematics theory is applied to the field of ideological and political content auditing, the auditing efficiency and accuracy are remarkably improved, the manual intervention requirement is reduced, and the auditing efficiency is improved. And the adaptability and sustainability of the system are enhanced.

The application discloses a QR code encryption and decryption method and system based on chaos theory and an AES algorithm, relates to the encryption and decryption technical field of QR codes, and comprises an encryption process and a decryption process; the encryption process comprises the following steps: firstly, chaotic sequences generated by improved Logistic mapping and Chebyshev mapping are subjected to XOR to obtain a composite chaotic sequence, the composite chaotic sequence is used as an initial key of AES grouping, and then ciphertext is obtained through AES encryption. Grouping initial keys are dynamically generated, a newly generated key is used for encrypting one group of plaintext data, the keys are completely independent, and therefore, one-time password is realized. Then, the AES algorithm is improved, plaintext information is first encrypted, then secondary encryption is performed on the plaintext information in a Base64 mode, final ciphertext information is subjected to QR code standard coding, and an encrypted QR code is generated. Through the mode of increasing encryption processing, the application effectively reduces information leakage or information tampering problems caused by QR codes.

The invention discloses an amplitude-frequency detection method for a weak current harmonic signal of a cable under a dynamic working condition, and relates to the technical field of cable state monitoring. A signal acquisition step; installing a high-precision current sensor at a key part of the cable, setting a proper sampling frequency according to a cable working frequency range and signal characteristics, and collecting a current signal in the cable in real time; a pretreatment step; collected current signals are preprocessed, a self-adaptive filtering algorithm is adopted to automatically adjust filtering parameters according to signal noise characteristics to remove high-frequency noise and power frequency interference, and noise reduction methods such as wavelet transformation are combined to remove random noise so as to improve the signal-to-noise ratio of the signals. The method has the advantages that the chaos characteristic in the early weak current harmonic signal of the cable is fully utilized, the chaos theory is adopted to analyze and process the signal, and different from a traditional method, weak characteristic information in the signal can be more effectively captured.

The application discloses a steel structure welding quality evaluation system and method based on distributed computing. The system includes a distributed gradient sensing unit, a physical field reconstruction unit, an entropy calculation unit, a chaotic feature extraction unit, a resource scheduling unit, a physical constraint verification unit, a chaotic synchronization analysis unit, a data aggregation processing unit, a quality comprehensive evaluation unit and a knowledge base management unit. By distributed acquisition of multi-physical field signals in the welding process and calculation of spatial gradient, the data transmission amount is significantly reduced; the complete physical field is reconstructed from the gradient information by using the multi-grid method; the potential defect area is identified and the computing resources are dynamically optimized based on information entropy analysis; the nonlinear characteristics of the sound signal are analyzed by using the chaos theory; multi-dimensional cross verification is carried out through physical constraint verification and chaotic synchronization analysis; and the federal learning is used to realize multi-site knowledge sharing. The application realizes real-time, accurate and comprehensive evaluation of the welding quality, and provides reliable technical support for steel structure welding quality control.

The invention relates to the technical field of modern application of traditional Chinese medicine theories, and aims to solve the problem of insufficient quantitative research of the five-element theory of traditional Chinese medicine and the meridian theory under modern scientific contexts. Clinical twelve-meridian bio-electricity signals are collected, the chaos theory is used as the basis, a five-element generation-restriction mechanism is fused, and a five-dimensional nonlinear kinetic equation system is constructed; by establishing an acupuncture point-meridian-five-element two-stage mapping relation, quantitative characterization of five-element characteristic values is realized; parameter identification is completed by adopting a PSO-GA integrated optimization strategy, and chaos characteristics and evolution laws of a five-element system of a human body in healthy, sub-healthy and disease states are represented by calculating a Lyapunov index, calculating fractal dimensions, drawing a chaos bifurcation diagram, a phase diagram and the like. The method can be used for human health status assessment, provides a modeling thought for modernization of traditional Chinese medicine theories, and has clinical application value.

The invention relates to the field of industrial aluminum alloy, and discloses a method for improving homogeneous cooling uniformity, which comprises the following steps of: determining the water quantity of homogeneous cooling water and the initial opening degree of a water valve of a homogeneous cooling chamber according to the temperature of a bar; chaos state characteristics of homogeneous cooling water are extracted based on the chaos theory, multi-step prediction and risk judgment are carried out, and a neural network model of the homogeneous cooling water temperature and the opening degree adjustment amount of a homogeneous cooling chamber water valve is trained under the constraint of a stable operation interval; the opening degree adjustment amount is output through a neural network model, the water valve opening degree adjustment amount is optimized and decomposed into temperature deviation, energy consumption, chaotic stability and response smoothness target sub-population independent evolution through a co-evolution mechanism, and the global optimal opening degree adjustment amount is obtained through dynamic weighted combination; and based on the global optimal opening degree adjustment amount corresponding to the current homogeneous cooling water temperature and the initial opening degree of the homogeneous cooling chamber water valve, the final opening degree of the homogeneous cooling chamber water valve is determined. And precise, stable and efficient control of homogeneous cooling is realized.

The application discloses a kind of based on improved ascidian algorithm's workflow optimization scheduling method.This method considers the time delay and reliability problem existing in workflow scheduling, utilizes reliability model to define the scheduling failure factor of workflow, and the weighted sum of time delay and failure factor is used as fitness function to evaluate workflow scheduling scheme, and the ascidian algorithm is improved, in population initialization, the standard deviation of population is used in the optimal population selected in multiple populations generated.In the updating of individual in population, chaos theory and updating algorithm are combined, the different method of using chaos mapping to replace pseudo-random sequence, and the leader and follower are updated using chaos mechanism, the global search speed in potential search area is improved, the speed of searching the optimal workflow scheduling scheme is improved, the edge server time delay is minimized, and the task scheduling reliability is improved, and finally the optimal workflow scheduling scheme is obtained.

The application discloses a micro-grid load distribution control method, device and equipment based on entropy increase disturbance, which analyzes the micro-grid operation state through chaos measurement, constructs an entropy increase disturbance incentive mechanism to actively stimulate system vitality, extracts inherent frequency characteristics of each power supply after random disturbance is applied, establishes a frequency synchronization coordination mechanism to realize multi-source collaboration, actively identifies distribution scheme loopholes by adopting counterexample search, generates a reinforced distribution strategy to improve robustness, evaluates load bearing capacity of each power supply, constructs a load conduction topology and analyzes stress distribution, acquires each power supply bearing limit parameter through boundary active detection, and fully excavates equipment potential, generates a final control instruction based on a multi-layer time sequence synchronization mechanism, and realizes multi-power supply coordinated output. The chaos theory is introduced into the micro-grid control, local optimum is avoided through active disturbance, a multi-layer coordination mechanism is adopted to adapt to new energy volatility, and an adaptive load distribution control scheme is provided for the micro-grid with high proportion of renewable energy access.

This invention discloses a novel design paradigm for phase-locked loops (PLLs) based on chaos theory, relating to the field of millimeter-wave radar integrated circuit technology. This design breaks away from the traditional approach of suppressing chaos in PLLs by actively introducing a controllable chaotic operating point. Through dynamic adjustment of loop bandwidth and modulation depth, it utilizes the characteristics of singular attractors to accelerate phase acquisition and stabilization. During the startup phase, the system enhances nonlinearity to enter a chaotic state for rapid locking, while suppressing nonlinearity in the steady-state phase to improve linearity and noise performance. This invention also integrates lock detection and feedback control mechanisms to optimize loop parameters in real time, significantly improving the tracking capability and robustness of the PLL in scenarios such as frequency-modulated continuous wave (FMCW), exhibiting both universality and scalability.

The present application relates to the technical field of magnetic encoder, especially to a causal inference compensation system and method for residual magnetism effect of magnetic encoder, comprising three anisotropic magnetoresistive sensors arranged uniformly along the circumference of the gear, a signal processing module, a topological dynamics model unit, a multi-step delay processing unit, a reverse factor reasoning unit and a compensation output unit, the present application maps the magnetic sensing data to a three-dimensional Riemann manifold, constructs a tangent space dynamics representation, and establishes a G-VAR model based on the topological structure of the manifold; a conditional probability measure space is constructed by multi-step delay coordinate embedding to identify the invariant measure and attractor structure of the system; reverse trajectory tracking analysis is performed based on chaos theory to separate the residual magnetism effect component; compensation data is generated to modify the output signal of the magnetic encoder, the present application can effectively capture the nonlinear dynamic characteristics of the residual magnetism effect, accurately model and compensate, and greatly improve the angle measurement accuracy.

The invention discloses a power system operation efficiency multi-dimensional quantitative analysis method, which comprises the following steps: preprocessing dynamic indexes based on an established index system; standardizing the data of the static indexes and the dynamic indexes; performing mixed weight distribution on the static indexes and the dynamic indexes; performing comprehensive scoring on the static indexes and the dynamic indexes according to a chaos dynamical model; penalty and incentive mechanism correction is carried out on the static indexes and the dynamic indexes; the invention provides a multi-dimensional and dynamic adaptive novel electric power system operation efficiency evaluation method, high-order dynamic quantitative analysis is utilized to quantify the operation efficiency of the novel electric power system, nonlinear modeling, chaos theory and policy sensitivity analysis are combined, a more scientific and more objective quantitative analysis system is provided, and the evaluation efficiency of the operation efficiency of the novel electric power system is improved. And a quantifiable decision-making reference is provided for planning and policy making of a city-level power system.

The invention discloses a fan blade fault detection method and system, electronic equipment and a storage medium, and belongs to the field of wind power generation, and the method comprises the steps: firstly obtaining a multi-frequency terahertz signal of a to-be-detected area, forming a terahertz data matrix by taking each frequency band signal value as different dimensions, then reconstructing a phase space based on a chaos theory, expanding the matrix into a one-dimensional sequence, and carrying out the reconstruction of the phase space; the method comprises the following steps: determining an optimal delay by using a mutual information method, determining an embedding dimension through dimension verification, constructing a high-dimensional phase space according to the optimal delay and the embedding dimension, finally constructing a detection model combining an attention mechanism and a bidirectional LSTM, inputting a reconstructed phase space into the model, learning importance weight of each subspace through the attention mechanism, extracting subspace time sequence correlation characteristics through a bidirectional LSTM network, and finally constructing a detection model combining the attention mechanism and the bidirectional LSTM network. And classifying by a full-connection network, and outputting the fault category of the fan blade.

This invention discloses a traffic signal control method based on the edge of a roadside, comprising: acquiring the traffic flow of each intersection at the current moment; calculating the proportion of the traffic flow of each intersection to the total traffic flow of the intersection, obtaining first data; processing the first data through a Logistic mapping to predict second data; calculating the Jacobian matrix based on the second data, and obtaining the Lyapunov exponent based on the Jacobian matrix; if the Lyapunov exponent is positive, adjusting the noise suppression intensity based on the Lyapunov exponent to obtain a noise suppression factor; processing the first data based on the noise suppression factor to obtain denoised first data; processing the denoised first data based on chaos theory to dynamically adjust the signal cycle and green light time, and then calculating pollutant emissions; and adjusting the signal cycle and green light time again based on the target pollutant emissions. This invention improves road traffic efficiency and vehicle throughput, and reduces parking time and pollutant emissions.

The invention relates to the field of medical artificial intelligence, in particular to a grassroots pulmonary nodule diagnosis and treatment federal decision support system and method, and the method comprises the steps: deploying a lightweight MobileViT model and a high-precision 3D-Res2Net model in a model layer, the lightweight MobileViT model is used for the benign and malignant identification and excision rate judgment of grassroots hospitals, and the high-precision 3D-Res2Net model is used for processing cases which cannot be accurately judged by MobileViT. The federated learning layer adopts a gradient compression-knowledge distillation joint optimization framework, and is characterized in that a probability manifold-based adaptive gradient compression mechanism, a non-uniform quantization strategy, adaptive threshold control and topological constraint knowledge distillation are adopted, a primary hospital only transmits a prediction layer gradient and retains CNN layer parameters, about 80% of communication overhead is reduced, and the probability manifold-based knowledge distillation algorithm is provided. The anomaly detection module identifies and defends hostile attacks based on the chaos theory, multi-center diagnosis experience is efficiently integrated under the condition that basic medical resources are limited, the benign and malignant identification accuracy of the MobileViT model reaches 83.5%, 'basic first diagnosis and hierarchical diagnosis and treatment 'are supported, and the method has remarkable clinical application value.

The invention provides a pushing-covering structure water-rich open-air slope stability evaluation method. The method comprises the following steps: step 1, constructing a pushing-covering structure quicksand water-rich open-air slope stability database; 2, constructing a COSMA algorithm and a random forest model; 3, constructing a stability evaluation model of the drift sand water-rich open slope with the push-cover structure; and 4, evaluating the stability of the drift sand water-rich open-air slope with the pushing and covering structure. Aiming at extreme geological conditions of multi-stage imbricate fracture structure development and strong seepage weakening of the quicksand water-rich open slope of the push-cover structure, accurate quantitative evaluation of the slope stability influence factors is realized by quantitatively analyzing the sensitivity weight of geological structure-hydrological-mechanical parameters; an intelligent evaluation model fusing chaos theory-myxobacteria optimization-random forest is provided, and the problem of slope risk quantification is solved; and slope structure parameter optimization and treatment measure accurate decision making are realized.

The invention relates to the field of construction waste resource utilization, and discloses a construction waste restoration and reutilization evaluation method based on a chaos theory and operational research, and the method comprises the steps: S1, obtaining performance evaluation index data of regenerated aggregate formed after the construction waste is subjected to restoration treatment; s2, preprocessing the performance evaluation index data; s3, constructing a chaotic evolution model based on the normalized index data; s4, performing evolution analysis on the chaotic system; s5, determining an index weight corresponding to each normalized index based on an operational research method; and S6, outputting an engineering application suggestion corresponding to the repairing and reusing grade. A chaos theory is introduced into a construction waste recycled aggregate evaluation process, and a chaos evolution model is constructed and evolution analysis is performed on a system state, so that the evaluation method can describe a nonlinear coupling relationship among multiple performance indexes and potential mutation characteristics, and the comprehensive description capability of complex material performance behaviors is improved.

The invention discloses a fault prediction system and method based on a chaos theory and a hidden Markov model. According to the method, the features extracted through the chaos theory are extremely sensitive to tiny changes of the initial state of equipment, early nonlinear dynamic anomalies can be accurately recognized, maintenance personnel can find potential problems when faults are not obviously shown, and serious shutdown caused by missing report of the early faults is avoided. The chaotic features deeply excavate system nonlinear dynamic behaviors hidden in monitoring signals, even weak fault symptoms can be captured, a reliable basis is provided for extremely early fault early warning, the chaotic features serve as input of the hidden Markov model, the strong time sequence modeling capability of the hidden Markov model is utilized, and the fault early warning method can be applied to early fault early warning. The method not only can accurately judge the degradation stage of the current equipment, but also can carry out probabilistic prediction on the change trend of the future state, so that the evolution law of the nonlinear degradation process of the equipment is accurately described, and the prediction accuracy and adaptability are remarkably improved.

The application discloses a kind of powder metallurgy blank sintering temperature intelligent control system and method, belong to powder metallurgy technical field, including data acquisition unit, data processing center, data storage unit, temperature regulating execution mechanism, data display unit and data communication unit.The temperature prediction model constructed by data processing center is composed of three core modules: topological perception multi-scale feature extraction module, chaotic dynamics time series dependence identification module and multi-source information fusion dynamic attention module, topological analysis preserves the complex correlation between parameters, chaotic theory captures the nonlinear dynamic characteristics of temperature, multi-dimensional dynamic attention mechanism pays attention to key information, realizes the high-precision prediction and control of sintering temperature, the system has self-adaptive learning ability, and can automatically adjust the control strategy according to different materials and process conditions.

The invention relates to the technical field of expansive soil slope crack intelligent detection, and discloses an expansive soil slope crack detection method and system based on big data processing, and the expansive soil slope crack detection method based on big data processing establishes a unified space-time coordinate system through a multi-source data fusion technology. A deep convolutional neural network and an attention mechanism are adopted to perform intelligent feature extraction and multi-modal fusion, and an improved U-Net network is utilized to realize fracture accurate segmentation and geometric parameter extraction. Time sequence modeling is performed on fracture evolution in combination with a multi-head attention mechanism, system characteristics are calculated and judged based on a Lyapunov index of a chaos theory, and accurate prediction of a future development trend is realized. And establishing a multi-dimensional risk assessment system, and carrying out graded early warning and intelligent decision making according to the comprehensive risk index. The method is suitable for intelligent monitoring of the expansive soil slope in the polar region permafrost region, and an innovative technical solution is provided for infrastructure safety monitoring.