8results about How to "Overcome dependence" patented technology

The application discloses an online identification method for fractional order parameters of a transformer based on an Adam-SGD fractional order neural network, and comprises the following steps: acquiring a fractional order state equation representing dynamic characteristics of capacitors and inductors of a DC-DC transformer; establishing a fractional order discrete recursive model based on GL fractional order calculus definition; constructing a neural network structure according to a recursive relationship of capacitor voltage and inductor current in the discrete model, taking actually collected voltage and current values as reference values, taking neural network output as estimated values, and constructing a mean square error loss function; performing gradient calculation and weight updating on the loss function by using an Adam-SGD optimization algorithm, and online adjusting neural network weights; and calculating and outputting parameters of the capacitors and the inductors in real time according to the established fractional order discrete model and the obtained weights. When the weights are updated, the application adopts an adaptive switching mechanism of Adam-SGD, and has the rapid convergence ability of Adam and the stable and fine optimization ability of SGD, so that the efficiency and reliability of online training of the fractional order neural network are significantly improved.

This invention discloses a method for diagnosing self-discharge anomalies in energy storage battery packs based on short-term charging data, belonging to the field of battery safety monitoring technology. Addressing the shortcomings of existing methods that rely on complete charge-discharge cycles and are difficult to adapt to multi-stage varying operating conditions, this invention extracts features from multi-stage charging data, combines an autoencoder to achieve adaptive extraction of features under multiple operating conditions, and constructs a data-driven model fused with GCN-BiLSTM (Graph Convolutional Network-Bidirectional Long Short-Term Memory) to accurately estimate the RCC (Remaining Charging Capacity) of individual battery cells. Finally, based on the size, distribution, and changes of the RCC of each individual cell in the battery pack, we can diagnose overall battery pack inconsistencies, individual cell SOC inconsistencies, and self-discharge faults. This provides a guarantee for the safe operation of energy storage systems.

The application provides a machine-generated text detection method, system, device and medium, and belongs to the field of natural language processing. The method comprises the following steps: performing sentence segmentation on an original text; generating a perturbed text through a four-layer structure perception perturbator, wherein the perturbator dynamically selects a perturbation type and intensity through a learnable strategy; reorganizing the text through a pre-trained encoding-decoding model and extracting a feature vector; fusing the multi-source semantic and structural features of the original text, the perturbed text and the reorganized text; and inputting a classifier to output a text detection result in combination with a comprehensive loss function. The problem of low detection accuracy of the text after machine polishing is solved.

The invention relates to the technical field of power system monitoring, and discloses an icing torsion inversion method, system and device based on a physical constraint neural network, and a medium, and the method comprises the steps: collecting the torsion angle data, environmental parameter data and historical icing thickness data of a transmission conductor; establishing a physical constraint model between the torsion angle and the icing thickness based on a wire mechanics principle; constructing a first neural network based on the physical constraint model, and defining a composite loss function including a data driving loss function and a physical constraint loss function; training a first neural network by using historical icing thickness data, and optimizing network parameters through a back propagation algorithm to minimize a composite loss function; and inputting the torsion angle data and the environmental parameter data into a trained first neural network for prediction to obtain an icing thickness prediction value of the current wire. According to the method, the mechanical physical model is embedded into the neural network training process, so that accurate inversion from the wire torsion angle to the icing thickness is realized.

This invention relates to an artificial intelligence-based data inspection quality control method, system, device, and medium. The method includes: cleaning and determining the distribution of raw inspection data to generate a qualified dataset; adaptively learning key model parameters such as the effective data range and optimal smoothing coefficient through iterative calculation and simulation optimization based on the dataset and its distribution type; training a long short-term memory neural network time-series prediction model using the qualified dataset, and setting quality control limits by combining the learned benchmark dispersion to construct a real-time quality monitoring model; inputting real-time inspection samples into the model, generating alarm signals by calculating an exponentially weighted moving average monitoring statistic and comparing it with the control limits; iteratively optimizing the model and parameters based on historical alarm signals and new data to achieve continuous self-updating of quality control, enabling automatic learning of quality control parameters and intelligent optimization of the model, and improving the real-time monitoring capability of minor system deviations during the inspection process.

The application discloses a sputum suction pressure optimization method and system combining multi-parameter cooperative feedback, and relates to the technical field of intelligent control of medical equipment. The method comprises the following steps: predicting and obtaining a physiological state parameter sequence and a sputum viscosity sequence of a wounded person in a preset time zone; based on the body parameters of the wounded person and the transfer scene parameters, a predicted body position feature sequence is constructed through simulation; a body position fluctuation coefficient is obtained according to the body position feature sequence, and an adaptive adjustment time window is dynamically set; taking the maximization of sputum removal efficiency and the minimization of airway mucosa injury risk as double objectives, an adaptive sputum suction negative pressure control scheme is optimized and generated in the time window by combining a generative adversarial network and a genetic algorithm; and finally, the sputum suction operation is performed according to the scheme. Through multi-parameter cooperative prediction and intelligent optimization, the application solves the poor adaptability problem of traditional sputum suction pressure control in a dynamic transfer environment, and significantly improves the accuracy, safety and reliability of sputum suction operation.

The present application relates to a kind of full-band beat vibration identification methods of rotating equipment, the method comprises: using vibration velocity sensor to collect the vibration velocity signal of rotor;Using variable mode decomposition VMD to decompose vibration velocity signal, obtain multiple intrinsic mode function;The FFT transform of all intrinsic mode functions is obtained, and corresponding frequency spectrum is obtained;While the analytic signal of all intrinsic mode functions is obtained after Hilbert transform, the corresponding amplitude envelope is obtained, and the FFT transform of each amplitude envelope is carried out, and corresponding envelope spectrum is obtained;Envelope spectrum is analyzed, and whether intrinsic mode function can be beat vibration signal is judged, and whether it is beat vibration signal is further determined after analyzing frequency spectrum, and excitation component is obtained.Compared with prior art, the present application can effectively avoid the uncertainty caused by subjective judgment, improve the robustness when tracing analysis, and realize full-band beat vibration detection under the condition of no rotation frequency prior.

This application relates to the field of groundwater monitoring, and in particular to a multi-parameter groundwater depth determination device. The device includes an integrated template on which a water level gauge, a thermometer, a conductivity meter, a pH meter, and a GPS positioning device are respectively installed. These components are modularly integrated into the template. A main control unit is mounted on the template, and the main control unit is connected to the water level gauge, thermometer, conductivity meter, pH meter, and GPS positioning device via a corresponding data transmission bus. A cable encoder and a depth-determining float are also installed on the template, and the float is lowered via a guide rod. The purpose of this application is to provide effective support for practical production work such as groundwater pollution prevention and control and ecological restoration.