The invention discloses a step-type landslide displacement prediction method based on a VMD-Mama algorithm. The step-type landslide displacement prediction method comprises the steps of constructing a data set in the same region, performing variational mode decomposition, performing variational mode decomposition, performing periodic term displacement component prediction and performing prediction component superposition and prediction precision evaluation. According to the invention, the unit prediction model and the multivariate prediction model are respectively constructed for different displacement components based on the Mama model, and the prediction precision of the accumulated displacement of the landslide is improved.
The invention provides a wire feeding self-adaptive adjusting method based on fast frequency MIG welding and a weldingsystem. The method comprises the steps that a self-adaptive adjustment model is constructed, the arc voltage is divided into three intervals with VL and VH as nodes, wire feeding speed variation function expressions of the three intervals are set, and the wire feeding speed variation function expressions have adjustable parameters; acquiring an arc voltage detection value, judging an interval in the self-adaptive adjustment model to obtain a wire feeding speed variation, and further adjusting a wire feeding speed set value; the PID regulator controls the wire feeding speed in a closed-loop manner; and when the times of the arc voltage detection value in the first interval and the third interval, the short circuit times and the arc breaking times are excessive, adjusting adjustable parameters of the adaptive adjustment model. According to the method, the wire feeding speed can be rapidly corrected to enable the arc voltage to return to a normal range, and overregulation can be prevented, so that the system has higher disturbance compensation capability and rapid responsiveness and can adapt to fast-frequency current changing at a high speed.
The present invention relates to the technical field of sleep diagnosis, and in particular to a sleep staging method based on deep learning, the method comprising: collecting a number of target physiological signals, preprocessing each target physiological signal to obtain a number of standard physiological signals; synchronously aligning and integrating each standard physiological signal in turn to obtain a standard sleep data set; determining the actual correlation between each physiological signal to be integrated in the standard sleep data set, and determining an actual signal combination strategy according to the actual correlation; generating an actual sleep data set according to the actual signal combination strategy, and extracting features from the actual sleep data set to generate actual feature parameters; inputting the actual feature parameters into a deep learning model to determine the actual sleep state; analyzing the actual sleep state, and performing corresponding sleep intervention according to the analysis results. The present invention realizes low-cost non-intrusive sleep monitoring, thereby improving people's physical health.
The invention discloses a method for generating a remote sensingimage based on a text. NLP (Natural LanguageProcessing) and CV (Computer Vision) technologies are fused. According to the method, a high-quality remote sensing image is generated by analyzing text description and carrying out hierarchical prototype learning and dynamic prototype learning by utilizing a dynamic hierarchical prototype block. Specifically, a text image pair is processed by an encoder to obtain a text image mark, a joint mark formed by splicing the text image pair and the text image mark is input into a dynamic hierarchical prototype layer to extract features, and the method enhances the memory and information retrieval capability of a model by combining a Hopfield network and a self-attention mechanism. Therefore, the richness and accuracy of remote sensing image feature representation are improved. Besides, a dynamic prototype learning strategy is adopted, so that the model can gradually learn and adapt to more prototypes, and higher robustness and accuracy are shown when complex data are processed. Finally, the method can generate a remote sensing image which is visually consistent with the text description and has high-quality details.