3results about How to "Simple classification" patented technology

The invention discloses a flat wire motor stator winding, which comprises a wire inserting stator and a winding wound on the stator, and is characterized in that the wire inserting stator comprises a stator iron core provided with M stator slots at equal intervals, and a flat wire motor corresponding to the pole number P is provided, and the stator slots are divided into 2n slot layers along the radial direction of the stator iron core; the windings comprise three phases of phase windings, and each phase winding comprises a first winding unit and a second winding unit which are the same and formed by hairpin coils; the first winding unit comprises a plurality of different-layer hairpin coils with spans of q, q-1 and q + 2, the different-layer hairpin coils are arranged between two adjacent slot layers of the stator slot in a crossing manner, the span between two adjacent different-layer hairpin coils is q, and q is M / P; and each phase winding comprises a parallel branches. According to the invention, wire outgoing can be carried out on one side of the iron core, wire outgoing can also be carried out on two ends of the iron core, the method adapts to a winding scheme of integer hairpin coil number and non-integer hairpin coil number of a single branch, and combination of pole-to-slot ratio and parallel branch number can be flexibly carried out.

The application discloses a vehicle classification method and system, the method comprises the following steps: S1, acquiring a plurality of real-time data of an observation area, and acquiring corresponding point cloud data set D according to the real-time data; S2, matching the point cloud data in the point cloud data set D with target vehicle data predicted by an extended Kalman filtering algorithm, and adding corresponding target vehicles into a target vehicle set O; S3, using a DBSCAN algorithm to perform cluster analysis on the point cloud data that are not matched successfully in the step S2, and adding corresponding target vehicles into the target vehicle set O; S4, acquiring the distance between any two point cloud data, and taking the maximum distance as the vehicle length; S5, according to the size of the vehicle length and a threshold value, configuring a size label for the vehicle, configuring a large vehicle label for the target vehicle with the vehicle length greater than or equal to the threshold value, and configuring a small vehicle label for the target vehicle with the vehicle length less than the threshold value. The application can realize vehicle size classification, and has the characteristics of small calculation amount and simple classification.

The application provides a vehicle detection data classification method and system, a computer and a readable storage medium. The method comprises the following steps: preprocessing vehicle detection data to generate input text; inputting an input vector into an ERNIE model to convert the input vector into a first word vector, and performing sequence feature processing on the input text to generate a second word vector; performing splicing processing on the first word vector and the second word vector to generate a word vector matrix, and inputting the word vector matrix into a DPCNN model; optimizing the DPCNN model through an equal-length convolution function, performing maximum pooling processing on the equal-length convolution function through the optimized DPCNN model to generate a maximum feature value; and outputting a predicted classification label corresponding to the input text according to the maximum feature value. Through the above method, the classification of vehicle detection data can be quickly completed, thereby greatly shortening the time consumed for classifying vehicle detection data.