*Probabilistic Methods for Cognitive Solving of Some Problems in Artificial Intelligence Systems DOI: http://dx.doi.org/10.5772/intechopen.89168*

capabilities of AIS used for a security service of floating oil and gas platform on its operation stage. The difference from previous example is in more degree of uncertainties (because of high complexity) that allows to transform all system components to the level which is proper to medium-level workers of floating oil and gas platform. The same approach, structure, and formulas for probabilistic modeling are used.

Let a floating oil and gas platform is also decomposed on nine subsystems. Every subsystem is enumerated on **Figure 14**, and operates as parallel elements with hot reservation.

Components are: 1—a construction of platform; 2—an AIS on platform for robotics monitoring and control; 3—an underwater communication modem; 4—a remote controlled unmanned underwater robotic vehicle; 5—a sonar beacon; 6—an autonomous unmanned underwater robotic vehicle; 7—non-boarding robotic boat, a spray of the sorbent; 8—non-boarding robotic boat, a pollution collector; and 9 an unmanned aerial vehicle.

And let input for modeling is the same as in Example 6.3. Only one difference is because of complexity characteristics are proper to medium-level workers of floating oil and gas platform. For this example, it means workers and AIS can commit errors more often in comparison with skilled workers, for one element it is equal to 1 time a month instead of once a year.

For planning possibilities of functions performance by AIS in this example, the probabilistic modeling is being to answer the 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 medium-level workers (realistic view on dangerous oil and gas intelligent manufacturing)?

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 structure on **Figure 13**. Here, risks to lose the system integrity mean risks of "failure" for every subsystem. The fragments of built PDF on **Figure 14** show: from 0.0009 for a year to 0.0844 for 10 years and 0.25 for 20 years. Thus, MTBLI equals to 24 years. It is 11.4 times less often against the results of Example 6.3.

These are some estimations for example assumptions.

Thus, the answer on question is: risks to lose system integrity may be 0.0009 for a year, 0.0844 for 10 years and 0.25 for 20 years; herewith, mean time between neighboring losses of integrity is equal to 24 years. These are the realistic estimations for dangerous oil and gas intelligent manufacturing.

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


3.Expected term in average 283 years and more is admissible systemic aim for

4.Analyzed project of AISs operation effectiveness (that transform all system components to the level which is proper to skilled workers of coal company)

**6.4 Example of system planning the possibilities of functions performance by**

This subsection continues an explanation on 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 the

*An example of a floating oil and gas platform with AISs that transform all system components to the level which*

can be added to K-base history as a precedent of "success."

**AIS used for a security service of floating oil and gas platform**

providing safe company operation.

*Probability, Combinatorics and Control*

**Figure 14.**

**24**

*is proper to medium-level workers.*

4.Analyzed project of AISs operation effectiveness (that transform all system components to the level which is proper to medium-level workers of floating oil and gas platform) can be added to K-base history as precedent.
