The uncertainty of the source information is used to solve key tasks in an intelligent automated thermal process control system affects the calculation of control actions, the implementation of equipment optimal operating modes and, as a result, leads to degraded reliability. As a rule, this type of information can be qualitative (the use of expert knowledge) or quantitative in nature. In this regard, it is extremely important to reduce the impact of uncertainty. The aim of the study is to identify the types and origins of uncertainty in the source information used by an intelligent automated process control system and to develop approaches to reduce its impact on the reliability of power equipment operation. The approaches used to ensure the specified indicators of reliability, efficiency and environmental friendliness in modern intelligent automated process control systems are based on predictive strategies, according to which the technical condition of equipment and specific degradation processes are predicted. This means that various types of uncertainty can have a significant negative impact. To reduce the influence of uncertainty of the initial information that affects the reliability of power equipment operation, the use of artificial neural networks is proposed. Their application opens the possibility to predict the occurrence of equipment defects and failures based on retrospective data for specified forecast time intervals. A method for reducing the impact of anomalies contained in the source information used in an intelligent process control system for energy facilities is demonstrated. Data omissions and outliers are investigated, the elimination of which reduces the impact of uncertainty and improves the quality of solving key problems in intelligent automated process control systems. Experimental studies were carried out that made it possible to identify the mathematical methods for removing omissions and anomalies in the source information in the best way. Methodological aspects of eliminating various types of uncertainty that exist in managing of power facilities by means of intelligent automated process control systems at the key stages of the power equipment life cycle are described.