The U.S. Bureau of Mines is conducting research on the application of expert systems technology to mining equipment diagnostics and predictive maintenance, to increase mining productivity and efficiency. One of the greatest hindrances to mining productivity is the breakdown of equipment, causing lengthy and costly delays. A diagnostic maintenance expert system (dimes) is being developed for the hydraulic system of a continuous coal mining machine. Through the use of such a system, the frequency of equipment failures and repair time should be significantly reduced. This paper describes the application domain, the functional requirements, and the problem approach for dimes, the design andimplementation of the knowledge-based system, the sensor work involved with the project, and the future plans for the continued development of this and other expert systems.