**6.1 Example 1 of system planning the possibilities of functions performance in space by using robot-manipulators**

Here, problem 1 (of planning the possibilities of functions performance) is solved by the proposed approach on the base of information gathered from different similar projects, accumulated and systematized in K-base including history. Applicability of the proposed probabilistic methods and models on development stage is demonstrated to improve some of the existing capabilities of robotmanipulator. It is required to predict the possible period of robot-manipulator use in space. When planning the possibilities of performing the functions of the cosmonaut-operator, two variants were compared: first variant–without a use of AIS; second–by using some AIS for supporting decision-making and monitoring the status of the operator's console, power units, central controller, and control handle for manipulator means.

A robot-manipulator as a system is composed on subsystems: an operator's console, a power unit, a central controller with a handle of control and manipulator means. There are supposed that a frequency of anomalies is in average 1 times a year, mean activation time from anomaly occurrence to failure is about 3 days. Time between the end of diagnostics and the beginning of the next diagnostics is about 2 months, and the recovery time is about 2 days.

System decomposition is presented on **Figure 10**. We do STEPS 1–4 (**Figure 8**) and use formulas (1)–(3) for solving the problem for complex structure composed by elementary variants decompositions presented on **Figures 3** and **4**. Here, probability of "success" (*P*) covers the following:


Risks of "failure" (R) means addition to 1 for probability of "success."

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

**Figure 10.** *Results of probabilistic modeling robot-manipulator operation.*

Results of modeling the first variant of project have shown the following (**Figure 10**): for operator's console (first subsystem), power unit (second subsystem) and central controller with a handle of control (third subsystem) MTBLI = 8766 h, for manipulator means (including a hinge of roving of key, a hinge of shoulder, a hinge of roving of elbow, a hinge of elbow, a hinge of roving of brush, a hinge of brushes, a hinge of brush rotation, a device for grasping, videocamera—united as subsystem 4, which can operate if one of these means is available) MTBLI = 31,293 h, for all complex 1,…,4 MTBLI = 2672 h; probability of reliable operation of complex 1,…,4 during 8 h is equal to 0.979; probability of reliable operation of complex 1,…,4 during 48 h is equal to 0.965.

The maximum probability of "success" and minimum risk of "failure" under limitations on the successful functions performance are used as a criterion.

The results of first variant are used for estimating input for the second variant of modeling: every subsystem for second variant (for subsystems equipped by AIS) is characterized by MTBLI = 31,293 h in analogy to the subsystem 4 of first variant. Owing to AIS, the frequency of anomalies is about 0.28 year<sup>1</sup> (it is equal to 1/MTBLI), but the conditions of anomalies activation time are more strong: the mean time is 30 min. The time between the end of diagnostics and the beginning of the next diagnostics is 1 month, and the recovery time is about 1 day.

What about the risks of "failure" during period from 0.05 to 2 years?

Analysis of modeling results proves: risks are very high despite the use of AIS with the described characteristics, see **Figure 11**.

For a robot-manipulator used in space, new knowledge for accumulating and improving K-base is as follows:


the complete set of different route variants for achieving the goal is redefined (similar to step 1). The input for modeling every part of possible route for each of the variants is updated. i = i + 1. Then, Steps 2–4 are repeated until the last part of the route is overcome on the set of possible variants (i.e., it means the goal is

If the set of possible options is exhausted and the goal is not achieved, it is concluded that the goal is unattainable with the risk of "failure" less than the acceptable risk (i.e., it means an impossibility of solving problem 2 in the defined

Thus, for optimizing robot route in space (i.e., for the "successful" solution of problem 2) in real time, information gathering, probabilistic predictions for possible route variants, their comparison, the choice of the best variant, the implementation of further actions, the improvement, accumulation, systematization, and use of

Note. The proposed methods of solving problems 1 and 2 are essentially identical approaches based on the use of the same probabilistic models (Section 3). The only difference is that for the system planning the possibilities of functions performance (problem 1), the concept of "success" is used; and for the robot route optimization under limitations on risk of "failure" (problem 2), the concept of "failure," which is

**6.1 Example 1 of system planning the possibilities of functions performance in**

Here, problem 1 (of planning the possibilities of functions performance) is solved by the proposed approach on the base of information gathered from different similar projects, accumulated and systematized in K-base including history. Applicability of the proposed probabilistic methods and models on development stage is demonstrated to improve some of the existing capabilities of robot-

manipulator. It is required to predict the possible period of robot-manipulator use in

A robot-manipulator as a system is composed on subsystems: an operator's console, a power unit, a central controller with a handle of control and manipulator means. There are supposed that a frequency of anomalies is in average 1 times a year, mean activation time from anomaly occurrence to failure is about 3 days. Time between the end of diagnostics and the beginning of the next diagnostics is about

System decomposition is presented on **Figure 10**. We do STEPS 1–4 (**Figure 8**) and use formulas (1)–(3) for solving the problem for complex structure composed by elementary variants decompositions presented on **Figures 3** and **4**. Here, proba-

space. When planning the possibilities of performing the functions of the cosmonaut-operator, two variants were compared: first variant–without a use of AIS; second–by using some AIS for supporting decision-making and monitoring the status of the operator's console, power units, central controller, and control handle

• Probability of reliable operation of robot-manipulator as a system

Risks of "failure" (R) means addition to 1 for probability of "success."

• Probability of reliable operation of every subsystem

achieved and problem 2 is solved).

*Probability, Combinatorics and Control*

knowledge are being, see **Figure 9**.

defined as the lack of "success," is used.

**space by using robot-manipulators**

2 months, and the recovery time is about 2 days.

bility of "success" (*P*) covers the following:

conditions).

**6. Examples**

for manipulator means.

**18**

Mean activation time Tactiv = (τactivation 1 + τactivation 2 + τactivation 3)/3

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

This example is auxiliary to understand some sources of input for the proposed

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

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

• 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 (Optimistic view on dangerous coal

• How every responsible worker can know a residual time before the next

probabilistic modeling is being to answer the next two questions:

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

Mean recovery time for Trecovery = (τrecovery 1 + τrecovery 2)/2

models (Sections 3–5) used for the next examples.

*The universal elementary ranges for monitored parameters.*

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

**AIS for a coal company**

**Figure 12.**

for a coal company on its operation stage.

parameters abnormalities?

intelligent manufacturing)?

**21**

#### **Figure 11.**

*Risks of "failures" depending on the prognostic period of use (from 0.05 to 2 years).*


## **6.2 Example of forming input for probabilistic modeling from monitored data**

In practice, many devices proper to intelligent manufacturing are sources of data monitored. This example explains how monitored data can be tailored in AIS for probabilistic modeling to solve both problems 1 and 2.

The approach to form specific input for modeling is demonstrated on example of mean time Toccur for PDF Ωoccur(t) and mean time Tactiv for PDF Ωactiv(t) from random values τoccurrence and τactivation (**Figures 6** and **12**).

The elementary ranges for monitored parameters from quality or safety point of view should be set. For each parameter, the ranges of possible values of conditions are set: "Working range inside of norm," "Out of working range, but inside of norm," and "Abnormality," The condition "Abnormality" characterizes a threat to lose system integrity after danger influence (on the logic level this range "Abnormality" may be interpreted analytically as failure, fault, losses of quality, or safety etc.). The construction on **Figure 12** allows to extract data for probabilistic modeling: time between moments of the occurrences of dangers (potential threats), activation time of occurred dangers, and recovery time.

For example, from **Figure 12**:

Mean time between moments of the occurrences of dangers (potential threats)

Toccur = (τoccurrence 1 + τoccurrence 2)/2

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

**Figure 12.**

4.Analyzed project of robot-manipulator operation effectiveness can be added to

5.For analyzed project, new research for decreasing risks with the proof of its efficiency on the basis of modeling is strongly required after improving

**6.2 Example of forming input for probabilistic modeling from monitored data**

In practice, many devices proper to intelligent manufacturing are sources of data monitored. This example explains how monitored data can be tailored in AIS for

The approach to form specific input for modeling is demonstrated on example of

The elementary ranges for monitored parameters from quality or safety point of view should be set. For each parameter, the ranges of possible values of conditions are set: "Working range inside of norm," "Out of working range, but inside of norm," and "Abnormality," The condition "Abnormality" characterizes a threat to lose system integrity after danger influence (on the logic level this range "Abnormality" may be interpreted analytically as failure, fault, losses of quality, or safety etc.). The construction on **Figure 12** allows to extract data for probabilistic modeling: time between moments of the occurrences of dangers (potential threats), acti-

Mean time between moments of the occurrences of dangers (potential threats)

mean time Toccur for PDF Ωoccur(t) and mean time Tactiv for PDF Ωactiv(t) from

characteristics for every subsystem of robot-manipulator.

K-base history as precedent of "unsuccess."

*Probability, Combinatorics and Control*

*Risks of "failures" depending on the prognostic period of use (from 0.05 to 2 years).*

**Figure 11.**

probabilistic modeling to solve both problems 1 and 2.

vation time of occurred dangers, and recovery time.

For example, from **Figure 12**:

**20**

Toccur = (τoccurrence 1 + τoccurrence 2)/2

random values τoccurrence and τactivation (**Figures 6** and **12**).

*The universal elementary ranges for monitored parameters.*

Mean activation time Tactiv = (τactivation 1 + τactivation 2 + τactivation 3)/3 Mean recovery time for Trecovery = (τrecovery 1 + τrecovery 2)/2

This example is auxiliary to understand some sources of input for the proposed models (Sections 3–5) used for the next examples.
