**6.3 Example of system planning the possibilities of functions performance by AIS for a coal company**

Applicability of the proposed probabilistic methods and models is demonstrated to improve some of the existing capabilities of AIS for a coal company. This subsection contains an explanation how problem 1 (of planning the possibilities of functions performance) may be solved for intelligent manufacturing by the proposed approach on the base of data monitored. This demonstrates AIS possibilities for a coal company on its operation stage.

Let a coal company (as system) is decomposed on 9 subsystems for studying efficiency. Of course, every subsystem also may be considered as complex system, for example, see **Figure 7**. Components from 1 to 6 united by multifunctional safety system of the mine, component 7 is associated with the washing factory, component 8 is associated with transport, and component 9 with port, see **Figure 13**: 1—the control system of ventilation and local airing equipment; 2—the system of modular decontamination equipment and compressed air control; 3—the system of air and gas control; 4—the system of air dust content control; 5—the system of dynamic phenomena control and forecasting; 6—the system of fire-prevention protection; 7—the safety system of washing factory; 8—the safety system for transport; and 9 —the safety system of port. Information is monitored from different sources, accumulated in a database of dispatcher intelligence center, processed, and systematized (including systematization described in Example 2 to get input for modeling).

For planning possibilities of functions performance by AIS in this example, the probabilistic modeling is being to answer the next two questions:


see details in [27, 36]. If virtual risks are computed by formulas (1) and (3) for all points Tgiven from 0 to ∞, the calculated values form a trajectory of the PDF. The mathematical expectation of this PDF means the mean residual time to the next state "Abnormality." It defines MTBLI from this PDF. This output of probabilistic modeling can be transmitted to interested workers. Requirements to AIS operation quality are: quality measures of used information by AIS should meet admissible

*Probabilistic Methods for Cognitive Solving of Some Problems in Artificial Intelligence Systems*

Thus, the answer on the first question "How responsible worker can know a residual time before the next parameters abnormalities?" is: the calculated mean residual time to the next state "Abnormality" (MTBLI for "red" range on **Figure 12**) can be transmitted in real time to responsible worker immediately after parameter value cross the border from "Working range inside of norm," "Out of working range, but inside of norm" (from "green" to "yellow" range on **Figures 12** and **13**). It is possible as a result of implementation of the proposed approach—see example

To answer the second question, let the next input be formed from data

the average not more often once a year (it is proper to skilled workers).

to the level of every separate critical parameter of equipment.

These are some estimations for example assumptions.

take over a desired level of AIS operation effectiveness.

discovered "bottlenecks") are admissible.

functions performance by AIS for a coal company.

To answer the question we do Steps 1–4 (from **Figure 8**) and use formulas (1)– (3) for solving the problem for complex structure, see **Figure 13**. Here, risks to lose system integrity means risks of "failure" for every subsystem which can be detailed

The fragments of built PDF on **Figure 13** show: risk of "failure" increases from 0.000003 for a year to 0.0004 for 10 years and to 0.0013 for 20 years. Thus, the mean time between neighboring losses of integrity (MTBLI) equals to 283 years.

Thus, the answer on second question "What risks to lose system integrity may

be for a year, for 10 and 20 years if all subsystems are supported by AISs that transform all system components to the level which is proper to skilled workers?" is: risks to lose system integrity may be 0.000003 for a year, 0.0004 for 10 years and 0.0013 for 20 years, herewith (MTBLI) is equal to 283 years. These are the Optimistic estimations for dangerous coal intelligent manufacturing that make sense to

New knowledge for accumulating and improving K-base is as follows:

1.The input (used for modeling) characterizes admissible conditions for

2.The probability of "success" on levels 0.99997 for a year, 0.9996 for 10 years and 0.9987 for 20 years or risk of "failure" on levels 0.000003 for a year to 0.0004 for 10 years and 0.0013 for 20 years (with predicted risks levels for

Let for every system component, a frequency of occurrence of the latent or obvious threats is equal to once a month and the mean activation time of threats is about 1 day. The system diagnostics are used once for work shift 8 h, a mean duration of the system control is about 10 min, and the mean recovery time of the lost integrity of object equals to 1 day. The workers (they may be robotics, skilled mechanics, technologists, engineers, etc.) are supported by capabilities of an AIS and a remote monitoring systems allowing estimating in real time the mean residual time before the next parameters abnormalities considering the results of probabilistic modeling. Formally they operate as parallel elements with hot reservation (structure on **Figure 4**, right). Owing to AIS support workers are capable to revealing signs of a critical situation after their occurrence. Workers can commit errors on

level recommended in **Table 1**.

*DOI: http://dx.doi.org/10.5772/intechopen.89168*

of implementation in [27, 36].

monitored.

**23**

#### **Figure 13.**

*An example of a coal company with AISs that transformed all system components to the level which is proper to skilled workers.*

To answer the first question, the ranges of possible values of conditions are established: "Working range inside of norm," "Out of working range, but inside of norm," and "Abnormality" for each separate critical parameter of equipment. It is interpreted similarly by light signals—"green," "yellow," and "red," as it is reflected on **Figure 12**. Some examples of parameters may include compression, capacity, air temperature (out, in, at machinery room), voltage, etc. The information from Example 6.2 and additional time data of enterprise procedures are used by AIS as input for using formulas (1) and (3) and Steps 1–4 (from **Figure 8**) in real time of company operation activity. Here, risks to lose the system integrity during the given period Tgiven means risks to be at least once in state "Abnormality" within Tgiven. The functions of modeling is performed on special servers (centralized or mapped);
