INTELLIGENT DIAGNOSTICS OF CLEANROOM VENTILATION AND AIR CONDITIONING SYSTEMS
Annotation
An approach to training diagnostic models of complex technical systems with multiple uncertainty of a priori information is proposed. Since it is impossible to determine the law of distribution of values of parameters of working processes, it is proposed to use methods of nonparametric statistics. The training procedure is based on the use of topology and properties of finite-dimensional Euclidean spaces. An example of a training procedure using a computational scheme according to the Robbins-Monroe algorithm is given. A graphical interpretation of the construction of a standard of parametric failure of an element when constructing diagnostic models of equipment of the ventilation and air conditioning system of a clean room of a special facility is presented.
Keywords
Постоянный URL
Articles in current issue
- FORMATION OF SETS OF SEPTENARY SEQUENCES WITH LOW CROSS-CORRELATION LEVEL FOR DIGITAL INFORMATION TRANSMISSION SYSTEMS
- COMBINATIONAL CIRCUITS TESTING BY TWO DIAGNOSTIC FEATURES ON THE BASE OF WEIGHT-TRANSITION SUM CODES
- ASSESSMENT OF INSTRUMENTAL ERRORS OF A TILT METER BASED ON A PENDULUM COMPENSATION ACCELEROMETER
- STUDY OF THE INFLUENCE OF THE CHARACTERISTICS OF A STEAM TURBINE BLADE SURFACE ON THE ERROR OF AN OPTICAL-ELECTRONIC CHORD LENGTH CONTROL SYSTEM
- EVALUATION OF THE EFFECT OF DYNAMIC INFLUENCES ON THE CHARACTERISTICS OF AN OPTICAL-ELECTRONIC DEVICE
- METHOD FOR MATCHING AN OPTICAL SYSTEM WITH A CURVED RECEIVING SURFACE
- METHODOLOGY FOR INVESTIGATING THE POSSIBILITY OF AUTOMATICALLY ENSURING THE ACCURACY OF TECHNOLOGICAL PROCESSES OF PARTS MANUFACTURING
- INCREASING THE TECHNOLOGICAL FLEXIBILITY OF THE COMPONENT ASSEMBLY MODULE BY ENTERING COMMANDS FROM A HUMAN OPERATOR