14 results about "Nonlinear networks" patented technology

The invention provides a ship target detection method based on nonlinear network enhancement, a medium and equipment, and belongs to the field of artificial intelligence. The method comprises the following steps of: performing type conversion, data division and enhancement on image data in a data set by adopting the ship data set acquired in a real river channel scene; a nonlinear network enhanced YOLO ship detection model is constructed; adopting a multi-task joint loss function to train the YOLO ship detection model; and inputting a port monitoring image and a sea surface aerial image into the trained YOLO ship detection model, outputting a category number, a confidence value and bounding box coordinates of each prediction box, and forming a visual image. According to the method, a nonlinear network enhanced YOLO ship detection model is constructed, and the modeling expression capability of the network on a ship target in a complex scene is effectively improved, so that the robustness and the accuracy of target detection are enhanced, and particularly, the performance is better under the conditions of small target detection and image degradation.

The application belongs to the field of automation control, and particularly relates to a preset performance based adaptive backstepping sliding mode control method for a network control system, comprising the following steps: converting a nonlinear network control system model with uncertain time delay into a system model without uncertain time delay; defining a system tracking error index and a preset performance trajectory, and converting the constrained system tracking error index into a new unconstrained error index; defining a new system state error containing an intermediate virtual control signal, and performing coordinate conversion on the system model; designing a sliding mode function and a Lyapunov function, and estimating network disturbance by using an adaptive neural network function to obtain a system input signal control rate; the application effectively solves the time delay problem of the network control system without limiting the upper limit of the time delay or the time delay derivative by using the network disturbance concept, and completes the control of the system by designing a preset performance index, so that the dynamic and steady state performance of the system is ensured.

This invention relates to a data-driven switching gain state estimation method for connected vehicles. The method includes: collecting system data from various subsystems within the connected vehicle to construct a nonlinear network system as a state-space model; collecting process data and establishing a data-driven switching gain state observer; defining error data and constructing an error system; setting stable operating conditions for the nonlinear network system based on constant quantities and the gain matrix; and operating the nonlinear network system under stable conditions to achieve data-driven switching gain state estimation for the connected vehicle. By collecting a large amount of system data from various subsystems within the connected vehicle for extraction, insight, and prediction, the method emphasizes both data quantity and quality, enabling the connected vehicle to exhibit adaptive and flexible characteristics. Because a data-driven switching gain state observer is established, real-time monitoring and switching gain control of the network system can be performed to improve the efficiency and quality of network data transmission and ensure the stability of the connected vehicle's operation.

The invention provides a net zero energy consumption building radiation heating coil pipe spacing prediction method, and relates to the field of coil pipe spacing prediction. The process comprises the steps of constructing a net zero energy consumption building radiant heating coil spacing data set, constructing each piece of net zero energy consumption building data into a multi-dimensional input sequence, generating a high-dimensional feature sequence by adopting a double-layer nonlinear transformation network, generating a building thermal disturbance feature sequence in combination with a mean value and a standard deviation of the high-dimensional feature sequence, and calculating the distance between the building radiant heating coils according to the building thermal disturbance feature sequence. Introducing a thermal response significance weight value to carry out weighted fusion and layer normalization to obtain a fusion feature, extracting a thermal potential energy value and a thermal slope, inputting the thermal potential energy value and the thermal slope into a nonlinear gating structure together with the fusion feature to obtain a main heat flux feature and a waste heat feature, and generating a fusion response weight by utilizing an element-by-element multiplication method; and performing weighted summation on the main heat flux characteristic and the waste heat characteristic to obtain a weighted thermal response characteristic, finally inputting the weighted thermal response characteristic into a nonlinear network, and outputting a predicted value of the distance between the radiant heating coils. According to the method, intelligent prediction of coil pipe spacing regulation and control parameters can be realized.

The application discloses a preset performance synchronization control method of a nonlinear networked time-delay system based on state translation transformation, which transforms communication time delay of the system by using state translation transformation technology, designs a preset time synchronization control scheme through the system after translation transformation, analyzes the synchronization of the transformed system, indirectly obtains effectiveness of the original system under the preset time controller, and finally realizes preset time synchronization control of the nonlinear networked time-delay system. Based on the constructed Lyapunov function, sufficient conditions of preset time synchronization are obtained, under the conditions, even if the system is affected by communication time delay or preset performance index changes, the synchronization control of the nonlinear networked time-delay system can still be realized under the preset time requirement. Finally, the effectiveness of the synchronization control scheme is verified through numerical simulation.

The invention relates to an information security technology, and provides a network attack pattern recognition method based on isometric immersion kernel function learning, which comprises the following steps of: firstly constructing geometric representation for network behavior data by using an isometric immersion kernel function, and then extracting characteristics capable of quantifying a network behavior form from the constructed geometric representation of the network behavior data; the equidistant immersion kernel function model is used for explicitly maintaining an inner product structure of non-Euclidean discrete data in a manifold representation construction process by introducing a learnable tangent space kernel function into the neural network model; according to the method, the most essential geometrical relationship in complex and nonlinear network behavior data is compressed into a low-dimensional space more suitable for machine learning model processing in a lossless or low-loss manner, the essential form of the attack behavior is accurately and stably captured in the complex and confrontation-full data, the sensitivity of attack pattern recognition is improved, and the recognition efficiency is improved. Therefore, the recognition accuracy is improved.

The present invention provides a method for achieving precise and high-dynamic tracking of an aircraft's angle of attack by using an adaptive observation method. First, an angle of attack and force, and an angle of attack and angular rate observation and parallel nonlinear networks are established respectively. Then, an angle of attack observer and a pitch rate observer are established. The observation error drives the adaptive convergence of the weight parameters of the nonlinear network. Simultaneously, an advance correction network is designed based on the observation error to obtain an observation error correction signal, which is combined with the observation integral signal and the observation error nonlinear signal to form a sliding mode signal, thereby achieving sliding mode control of the observer. Simultaneously, an expected angle of attack value set according to a flight mission is compared with the angle of attack observation value to obtain an angle of attack error. Then, an inverse design method is used to calculate an aircraft rudder angle signal based on the output signal of the parallel nonlinear observation network, the error correction signal, and the error integral signal, thereby achieving high-precision and high-dynamic performance control of the aircraft's angle of attack.

The invention relates to a network traffic anomaly detection method and system based on deep feature extraction. The method comprises the following steps: collecting original network flow data; performing standardization processing on the original network traffic data to generate a primary traffic tensor sequence; performing depth feature extraction processing on the primary flow tensor sequence through a trained encoder to generate a spatial-temporal feature vector; performing data reconstruction processing on the spatial-temporal feature vector to obtain a reconstructed traffic tensor sequence; calculating a reconstruction error between the reconstructed flow tensor sequence and the primary flow tensor sequence; and based on the reconstruction error and a preset error threshold value, a flow anomaly detection result is generated. By adopting the method, the problems that a traditional method depends on expert knowledge, complex space-time dependence is difficult to capture and generalization ability is weak can be effectively solved, and automatic and high-precision anomaly detection of high-dimensional and nonlinear network flow data is realized.

The application discloses a kind of based on nonlinear network model's prediction method of heating cigarette resistance and ventilation rate, specifically includes the following steps: S1, according to heating cigarette structure, the network model of each part pressure drop or flow of cigarette is established;S2, based on the basic principle of fluid mechanics, the relationship of each part pressure drop and flow is constructed;S3, according to the equation set constructed, the expression of cigarette resistance and ventilation rate is solved;S4, the prediction value of resistance and ventilation rate is obtained by substituting cigarette parameter into expression.The prediction model provided by the application obtains the analytical expression of resistance and ventilation rate about basic structural parameters of cigarette, so that relevant field production and research and development personnel can directly calculate according to structural parameters when designing heating cigarette to accurately predict cigarette resistance and ventilation rate.

This application relates to an encoder-based intelligent event-triggered control method, apparatus, device, and medium. The method includes: outputting a first control output and a second control output respectively through the controlled object and controller of a nonlinear networked control system model, and sampling them in a sensor to obtain sampling parameters; determining whether an event has been triggered based on the sampling parameters through an event triggering mechanism; if the event is triggered, outputting a trigger moment output signal through the event triggering mechanism, and encoding the trigger moment output information through an encoder to obtain encoded parameters; transmitting the encoded parameters through a network to a decoder for decoding to obtain decoded parameters, and transmitting the decoded parameters to the receiving end through a zero-order hold. This invention avoids situations where the communication network cannot transmit signals normally and the system loses control during DoS attacks, thus improving the performance and stability of the nonlinear networked control system.

This invention discloses a communication scheduling method for a nonlinear system under a denial-of-service attack based on an event-triggered mechanism. Applied to a state-constrained nonlinear network physical system, it establishes a dynamic equation model for the nonlinear system under a denial-of-service attack; models the attack timing and provides constraints on attack frequency and duration; and generates a trigger time sequence based on an event-triggered mechanism to control the updating and maintenance of the actuator input signals. The event-triggered mechanism includes: real-time monitoring of whether the current time is during a communication interruption period; if the current time is during a communication interruption period, a time-triggered mode is used to determine the update time sequence of the control signals at a fixed time interval δ0; if the current time is during a normal communication period, an event-triggered mode is used to dynamically determine the trigger time based on the relationship between control error and the current system state. By monitoring the communication status in real time, it ensures that the update rhythm remains stable even under harsh attack conditions, balancing anti-interference capability and robustness.

The application provides a state estimation method and system of a nonlinear networked system based on an asynchronous encoding and decoding mechanism and a storage medium, and belongs to the network control field. The method is used for solving the problem that the existing method ignores the quantization error of the encoding and decoding mechanism and the delay existing in the process, and influences the estimation accuracy of the state estimator. The method comprises the following processes: a dynamic model of a nonlinear networked system with variance constraint and an asynchronous encoding and decoding mechanism is established; an upper bound Θ of a state estimation value and an estimation error covariance matrix at j time is input at j+1 time j|j , 2n x +1 Sigma points are generated, wherein n x is the dimension of a state vector; a numerical Jacobian matrix of a nonlinear function is calculated according to the generated Sigma points, the nonlinear networked system is approximated as a linearized system, the statistical characteristics of the quantization error are calculated, and the error is eliminated; and an estimator gain matrix is solved, so that the state estimation of the nonlinear networked system with variance constraint and the asynchronous encoding and decoding mechanism is realized.

The application discloses a kind of multi-layer nonlinear optical neural network computing systems based on linear signal re-encoding, belong to optical neural network computing technical field, including: control circuit and optical processing chip system;The control circuit is used to realize the loading of input signal and the reading of output result;The optical processing chip system includes light source, integrated optical computing chip and detector, and the light carrier emitted by light source generates input optical signal after being modulated by input signal, and after being processed by multi-layer nonlinear activation in linear calculation area, linear re-encoding area and high-speed modulation area on integrated optical computing chip, output result is read by detector and returned to control circuit.The application utilizes pure linear device to realize all-optical nonlinear network, cooperates analog activation function by re-encoding and modulation, needs only single physical layer to construct depth architecture without photoelectric conversion, with the advantages of all-optical processing, CMOS compatible, high speed and low power consumption.

The invention provides a method for establishing a model for evaluating the influence of an offshore wind power project on biodiversity accumulation, and belongs to the technical field of the influence of offshore wind power on the environment. And establishing a pressure state response nonlinear network model containing a collaborative amplification transfer function and an antagonism offset transfer function, calculating a single-project cumulative influence index and a multi-project superposition cumulative influence index, and evaluating the degree of separation of the wind power project to the network connectivity of the habitat connectivity graph. Constructing a wind-power-free project anti-fact scene through an interruption time sequence analysis method, and carrying out causal attribution to generate a cumulative influence evaluation grade and an ecological restoration suggestion report; the method solves the technical problem that the assessment of the cumulative influence of an offshore wind power project on the biodiversity lacks a multi-scale nonlinear pressure transmission mechanism and ecological response dynamic coupling capability.