This study focuses on coalbed methane (CBM) wells in high-ranking coal seam as the research subject. Considering the influence of effective stress and matrix shrinkage, a comprehensive permeability calculation model for CBM reservoirs is established. Based on this model, the variations in pressure and permeability during well production are quantified. By integrating static geological parameters, a finely classified classification of CBM wells is achieved using self-organizing map (SOM) neural network. Subsequently, an analysis of production dynamic characteristics and productivity differences among different types of CBM wells is performed, followed by providing drainage optimization suggestions. The results of SOM analysis show that 7,000 m3/d and 1,500 m3/d can be used as the production boundaries for the wells with different productivity in Block P. The daily gas production of exceptional well exceeds 7,000 m3/d, and the permeability remains relatively stable throughout the drainage process of this well. The daily gas production of the potential well ranges from 1,500 to 7,000 m3/d, and the permeability exhibits a significant decrease during the drainage process. The daily gas production of Inefficient well is consistently below 1,500 m3/d with moderate permeability variation. In addition to well location and structural geology, production variability is also influenced by the matching of reservoir conditions and drainage systems. This is primarily manifested in discontinuous drainage systems and rapid decline in bottom hole pressure (BHP) during early production. The analysis of drainage parameters indicates that in order to achieve optimal production from CBM wells, the BHP should exhibit an initial rapid decline followed by a slowly decrease during the early production period, with an average pressure drop ranging from 0.005 to 0.02 MPa/d. The research findings can offer technical guidance for the future advancement of CBM in the P Block.