Diseases control is always an issue in cotton production, the timely detection and effective control of diseases depend on, in most cases, an effective diagnosis system. Based on the distribution of cotton diseases in the main yielding areas of China in recent years, the main species and characters of cotton diseases were listed classified in the study and a database was established for this purpose. BP neural network as a decision-making system was used to establish an intelligent diagnosis model. Based on the model, a WEB-based Intelligent Diagnosis System for Cotton Diseases Control was developed. An experiment scheme was designed for the system test, in which 80 samples, including 8 main species of diseases, 10 samples in each sort were included. The result showed the rate of correctness that system could identify the symptom was 89.5% in average, and the average running time for a diagnosis was 900ms.