30 results about "Data driven algorithms" patented technology

The invention belongs to the technical field of convexity prediction, and in particular relates to a board convexity prediction method based on kernel partial least squares combined with a support vector machine, comprising the following steps: S1, using a high-precision monitoring device to collect on-site data; S2, collecting the collected Data preprocessing; S3, establishment of KPLS regression prediction model; S4, establishment of KPLS-SVM plate convexity prediction model. In the present invention, the data-driven algorithm is used as a mathematical tool, and abnormal values ​​can be removed from a large amount of collected on-site rolling process data. The present invention establishes a continuous strip rolling strip convexity prediction model based on the kernel-partial least squares method combined with the support vector machine, The prediction of the crown of the strip continuous rolling is realized, and the invention adopts the particle swarm optimization algorithm to optimize the built model, and further improves the prediction accuracy of the strip continuous rolling crown. The invention is used for the prediction of the crown of the continuous rolling strip.

The invention relates to a method for estimating passenger flow between bus stops based on IC card data. The method determines the passenger's travel route and boarding station according to the IC card data and the bus GPS station report data, and then infers the passenger's alighting station. Obtain the complete OD information of passenger travel, calculate the OD amount according to the complete OD information, redistribute the missing passenger flow at the drop-off site using the site attraction weight, and use the redistributed passenger flow to correct the OD amount of the complete OD information. , and calculate the number of people getting on and off at the station and the passenger capacity between the stations through the corrected OD amount. Compared with the prior art, the passenger flow estimation method provided by the present invention is based on pure data driving, the algorithm has wide applicability and high accuracy, and can intuitively grasp the bus passenger flow and operation and service conditions.

The invention relates to the technical field of heating and air-conditioning equipment, in particular to a method and system for controlling the variable return water temperature of an air source heat pump based on supply and demand matching. Building model; according to the measured data of air source heat pump operation, state identification parameters are introduced to distinguish the start-up stage and stable operation stage, and a unit model that can reflect the dynamic process and loss of start-up and shutdown is established through data-driven algorithms; the end model considering the dynamic thermal process is established and considered The transmission and distribution model of the waterway inertia; the dynamic coupling relationship between the unit heating capacity, the terminal heat supply and the building heat dissipation is used to form the dynamic model of the air source heat pump system; according to the indoor thermal comfort requirements of the target system, the variable return water temperature control strategy is established , and control the unit operation according to the variable return difference water temperature control strategy during operation. The invention improves the problem of frequent start and stop of the air source heat pump unit under low load state, improves the system performance, reduces the power consumption of the system, reduces the influence of noise during the start and stop process, and helps to prolong the life of the compressor.