Diseases control is always an issue in cotton production, which will not only lower the quantity, but also degrade the products leading serious economic loss.The timely detection and effective control of diseases depend on, in most cases, an effective diagnosis system.In order to meet the cotton farmers need for domain experts, this paper presented a WEB-based Intelligent Diagnosis System for Cotton Diseases Control by using the technology of JSP and the database development tools of MySQL.BP neural network was used as the disease inference engine in the system, so that the diagnostic accuracy and intelligence as well as the ability to solve the uncertainty and ambiguity problems were enhanced.The system could realize the query, diagnosis and online consulting of the main diseases during the whole growing process.The background component of the system was to meet the functions of cotton diseases management, users management and messages management.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.The result showed this system was high-accuracy and highspeed.The system was also effective and easy to operate.