7results about How to "Improve correction ability" patented technology

The invention relates to a tower air temperature correction method and device based on weather station forecast and computer equipment. The method comprises the following steps: acquiring monitored air temperature data and air temperature forecast data of a target power grid in a set historical time period, and acquiring a to-be-trained air temperature prediction model related to a power grid tower at the same time; using the monitored air temperature data and the forecast data as a training set input model, training the model, and generating a trained air temperature prediction model; and evaluating the model in the aspects of a low-temperature interval, a whole-section temperature interval and low-temperature forecasting performance so as to obtain a low-temperature interval index, a whole-section temperature index and a low-temperature forecasting performance index. Based on the evaluation results, different indexes of the model are endowed with combination weights, and various adjusted air temperature prediction models are generated. And selecting the adjustment model with the maximum weight index total amount in all the weight combinations as a final target air temperature prediction model applied to the power grid tower. By adopting the method, the accuracy of predicting the icing of the power grid can be effectively improved.

A horizontal line auxiliary jig for circuit board processing comprises a base, a bearing plate and two sets of electromagnetic strips, the bearing plate is arranged on the base, and the two sets of electromagnetic strips are located on the two sides of the bearing plate respectively; a movable rotating shaft is arranged at the upper end of the base, a clamping rotating groove is formed in the bottom of the bearing plate, and the clamping rotating groove is arranged above the movable rotating shaft in a clamping and penetrating mode and can horizontally rotate around the axis of the movable rotating shaft; the side face of the bearing plate is further provided with a plurality of installation grooves and magnetic blocks, and the magnetic blocks are installed in the installation grooves in a clamped mode respectively and arranged opposite to the two sets of electromagnetic strips. According to the utility model, the circuit board is borne by designing a matching structure of the base, the bearing plate and the electromagnetic strip, and the circuit board is rectified and straightened by utilizing the principle of electromagnetic force, so that not only is the rectifying effect strong, but also the processing efficiency and the processing quality are greatly improved; the utility model has the advantages of strong practicability and strong popularization significance.

This invention discloses a motor control method based on Hall effect elliptic correction and sector linear models, comprising: installing orthogonal Hall sensor pairs and determining elliptic correction compensation parameters through offline correction; dividing mechanical sectors and establishing a linear model representing the correspondence between electrical angles and mechanical angles for each mechanical sector; performing elliptic correction on the original output signals of the orthogonal Hall sensor pairs according to the elliptic correction compensation parameters, and calculating the real-time mechanical angles based on the elliptic-corrected output signals; querying the mechanical sector where the real-time mechanical angles are located, and calculating the corresponding real-time electrical angles according to the linear model; and generating corresponding motor control signals based on the real-time electrical angles. This invention replaces hardware precision with algorithms, resulting in extremely low hardware costs, low computational load, low processor requirements, and the ability to correct traditionally defective motors to a usable or even high-performance level, significantly improving supply chain utilization and product cost-effectiveness.

The application relates to a medical care voice structured input method and system based on self-supervised learning, and belongs to the medical service field. The method comprises the following steps: collecting medical care voice, outputting an audio feature sequence and a context high-dimensional vector based on the medical care voice; pre-training an MS-CCP model through self-supervised learning, outputting a medical voice encoder through the MS-CCP model; inputting the audio feature sequence into the medical voice encoder to obtain a high-level semantic feature sequence, performing dynamic memory and reasoning decoding based on the high-level semantic feature sequence and the context high-dimensional vector, outputting a word sequence and a label sequence, and merging to form a structured voice record; and performing structured confidence verification and writing based on the structured voice record. The application realizes medical voice structured input which overcomes dependence on labeled data, fuses patient context information, realizes end-to-end structured output, and has intelligent confidence evaluation.

The invention discloses a large-dynamic-range high-precision pupil and optical axis stable compound control system which comprises a front-stage optical path system, a coarse-stage pupil correction assembly, a coarse-stage pupil error detection assembly, a fine-stage pupil and optical axis correction assembly, a spectroscope, a fine-stage pupil and optical axis error detection assembly, a processing controller and a rear-stage optical path system. Reasonable spatial arrangement is utilized to complete large-dynamic-range and high-precision correction of pupil optical axis stability errors. According to the system, coarse-level and fine-level pupil correction assemblies and an optical axis correction assembly are used as execution devices, coarse-level and fine-level error detection assemblies are used as detection feedback devices, a closed-loop system is formed through a control algorithm, and precise alignment of pupils and optical axes of front and rear optical systems is achieved.

The present invention relates to a double-sided gluing device. The double-sided gluing device of the present invention comprises: a transmission mechanism, a gluing mechanism and a correction mechanism; the transmission mechanism drives the transmission of the pole piece and the tape; the gluing mechanism comprises an unwinding module, a rewinding module and a gluing module, the unwinding module provides the tape, the rewinding module recycles the tape waste, and the gluing module bonds the pole piece and the tape; the correction mechanism comprises a gluing correction module, an unwinding correction module, a rewinding correction module and an overall correction module, the gluing correction module detects and corrects the gluing of the pole piece, the unwinding correction module detects and corrects the release of the tape, the rewinding correction module detects and corrects the recovery of the tape waste, and the overall correction module detects and corrects the incoming material of the pole piece. The double-sided gluing device of the present invention improves the correction accuracy of the device by setting a plurality of correction modules to work together, and thereby realizes that one device completes the gluing of the front and back sides of the pole piece, effectively improving the production efficiency.

The application discloses a kind of multi-mode wind energy resource month scale prediction revision method and system based on U-Net, belong to wind energy resource evaluation and climate numerical prediction cross technical field, for the month scale wind speed of climate mode output is revised.The method constructs climatic wind speed field using ERA5 reanalysis, calculates month scale 10m wind speed anomaly as revision benchmark;Obtain the month scale historical return data of multiple dynamic climate models, extract 10m wind speed and multiple layers meteorological elements, uniform interpolation and standardization, form sample set.Based on sample set, the U-Net revision model with encoding and decoding structure is constructed, and the feature combination and hyperparameter are optimized through cross-validation, to learn the nonlinear mapping from multi-mode prediction field to ERA5 anomaly field.The optimal model is used to revise the future month scale prediction, to generate wind speed products with more similar spatial structure and amplitude distribution to observations, to provide high credible wind energy climate information for wind power planning, power generation planning and power grid dispatching.