Linfeng Jin

Title: Linfeng Jin: Innovator in Environmental Monitoring Technologies

Introduction

Linfeng Jin is a notable inventor based in Changsha, China. He has made significant contributions to the field of environmental monitoring, particularly in the areas of flue dust concentration prediction and water quality monitoring.

Latest Patents

Linfeng Jin holds two patents that showcase his innovative approaches. The first patent is titled "Method, device, and medium for predicting flue dust concentration." This invention discloses a method, a device, and a medium for predicting flue dust concentration. It calculates the flue dust emission amount of each batch of coal fed into a furnace based on hourly coal consumption. The invention generates a general rule between the data of coal fed into the furnace and the corresponding flue dust emission amount through training a prediction model. It accurately identifies the relationship between material and flue dust emission, reduces workloads of manual accounting and verification, and provides a reference for Continuous Emission Monitoring Systems (CEMS) flue dust monitoring data. Additionally, the use of an Adam algorithm to optimize a Back Propagation Neural Network (BPNN) allows for automatic adjustment of the learning rate for each parameter, enabling fast and efficient training of the prediction model. This invention addresses measurement errors and complex manual accounting, achieving precise measurement of flue dust emissions from coal-fired power plants.

The second patent is titled "Layout optimization method of water quality monitoring points based on RF-C-SOM clustering algorithm." This method includes preprocessing collected water quality data to obtain preprocessed data used as input for training a random forest model. The model determines the feature importance of water quality indicators. Important features are selected based on feature importance and model training accuracy. Dimensionality reduction is performed on the preprocessed data to obtain dimension-reduced data. A fuzzy clustering is then conducted on this data to classify water quality sections. The initial weight values of a self-organizing mapping algorithm are determined, and a self-organizing mapping network model is trained. The model provides a point clustering result, followed by a water quality index evaluation for the clustering result before and after screening.

Career Highlights

Linfeng Jin is affiliated with Hunan University of Technology and Business, where he continues to contribute to research and innovation in environmental technologies. His work has implications for improving air and water quality monitoring systems.

Collaborations

Linfeng collaborates with colleagues