The research raise the question of the need to analyse and model the processes associated with the emission of the emergency-chemical hazardous substance (ECHS) in the urban environment. Because the assessment of the environmental pollution, the early and prompt prediction of the scale of contamination in the event of releases is the potent poisonous substance (PPS) into the environment in case of accidents (destructions) at chemically hazardous facilities remains an urgent issue. We emphasize that in order to ensure the life of any settlement, there is a need for the availability of drinking water that meets sanitary standards and hygienic rules. Chlorination is traditionally used in most of the country's settlements. To take timely measures to eliminate accidents with the emission of chlorine, the most accurate results of calculating the main indicators are necessary, such as the depth of the zone of contamination of PPS, the amount of the poisonous substance in primary and secondary clouds, the area of contamination, etc. The method of calculating these indicators is based on the use of reference tables and the coefficient method, which are convenient enough for the manual method. However, in emergencies, when serious threats to the life and health of people arise, and the situation can deteriorate rapidly, there is an acute shortage of time for a general assessment of the situation, making decisions on the organization of the rescue measures. It is obvious that the staff simply will not have enough time for scrupulous calculations, and a stressful situation, in addition, with a high degree of probability will provoke serious errors and inaccuracies.

The paper proposes an automated procedure for assessing the actual state of photoelectronic separators in real time. Random process outliers over tolerance zones are proposed as the main controlled parameter. In contrast to traditional methods, several threshold levels are used to provide the flexibility of control and forecasting. Measurement of the amplitude and duration of the outliers of random processes over the tolerance zones helps to collect statistical samples, which become the basis for statistical models in the form of distribution law. The automated system makes it possible to identify the distribution law by classical methods if the samples are of sufficient statistical volume.