METHOD FOR CONTROLLING A PROCESS WITHIN A SYSTEM, PARTICULARLY A COMBUSTION PROCESS IN A BOILER OR FURNACE

Abstract

The invention relates to an apparatus and a method for controlling 4 a process within a system, particularly a combustion process in a boiler or furnace, comprising the following steps: capturing 1 of state variables (s.sub.t) of the system; creating 2 an interference model, which describes the effects of interference-based system changes (v.sub.t) on the state variables (s.sub.t) of the system; creating 3 a process model, which describes the effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system; and controlling 4 the process within the system by performing setting actions (a.sub.t) by considering the process model, the interference model and predetermined controlling goals.

Claims

1. A method for controlling a process within a system, particularly a combustion process in a boiler or furnace, comprising the following steps: capturing of state variables (s.sub.t) of the system; creating an interference model, which describes the effects of interference-based system changes (v.sub.t) on the state variables (s.sub.t) of the system; creating a process model, which describes the effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system; and controlling the process within the system by performing setting actions (a.sub.t) by considering the process model, the interference model and predetermined controlling goals.

2. The method according to claim 1, wherein the state variables (s.sub.t) are captured by sensors of the system or a manual and/or automatic sample evaluation.

3. The method according to claim 1, wherein during the creation of the interference model past interference-based system changes (v.sub.t) are considered for integration in a temporal context and/or wherein during the creation of the process model past effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system are considered for integration in a temporal context.

4. The method according one of claim 1, wherein the interference model is adapted continuously by effects of interference-based system changes (v.sub.t) on the state variables (s.sub.t) of the system and/or wherein the process model is adapted continuously by effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system.

5. The method according to one of claim 1, wherein the interference model and/or the process model is created by a test run of the system and/or by expert knowledge.

6. The method according to one of claim 1, wherein the interference model and/or the process model is created, and particularly continuously adapted, by a computer-based neural network.

7. The method according to one of claim 1, wherein multiple, independently from one another, interference models are created and during the controlling of the process within the system the interference model is considered that momentarily best describes the interference-based system changes (v.sub.t).

8. The method according to one of claim 1, wherein multiple, independently from one another, process models are created and during the controlling of the process within the system the process model is considered that momentarily best describes effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system.

9. The method according to one of claim 1, wherein the interference model considers multiple assumed future effects of interference-based system changes (v.sub.t) on the state variables (s.sub.t) of the system and/or wherein the process model considers multiple assumed future effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system.

10. An apparatus for executing the method according to claim 1 comprising a system to be controlled with sensor for capturing of state variables (s.sub.t), actuators for performing setting actions (a.sub.t) and a control unit, preferably a computing device, connected to the system.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In the following the inventive method will be explained with reference to the embodiment shown in FIG. 1.

[0045] FIG. 1 shows the sequence of an inventive method for controlling a process within a system.

DETAILED DESCRIPTION

[0046] FIG. 1 shows the sequence of an inventive method for controlling a process within a system, particularly a combustion process in a boiler or furnace.

[0047] In a first step the state variables (s.sub.t) of the system are captured 1. The capturing 1 of the state variables (s.sub.t) is performed by sensors of the system or by manual and/or automatic evaluation of samples.

[0048] During the execution of the inventive method an interference model (SM) is created, which describes the effects of interference-based system changes (v.sub.t) on the state variables (s.sub.t) of the system. The interference model (SM) is for example created by a test run of the system and/or by expert knowledge. During the execution of the inventive method past interference-based system changes (v.sub.t) can be considered during creation of the interference model (SM) for integration in a temporal context. Furthermore, the interference model (SM) can be continuously adapted by effects of interference-based system changes (v.sub.t) on the state variables (s.sub.t) of the system.

[0049] The interference model (SM) is for example created 2, and particularly continuously adapted, by a computer-based neural network.

[0050] Particularly preferred multiple, independent from one another, interference models (SM) are created 2 and during controlling 4 of the process within the system the interference model (SM) is considered, which best maps the current interference-based system changes (v.sub.t).

[0051] For improving the accuracy of the inventive method, the interference model (SM) can consider future expected effects of interference-based system changes (v.sub.t) on the state variables (s.sub.t) of the system.

[0052] In a further step of the inventive method, a process model (PM) is created, which describes the effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system.

[0053] The process model (PM) is for example created 3 by a test run of the system with at least an exemplary execution of possible setting actions (a.sub.t) and/or by expert knowledge. During the creation 3 of the process model (PM) preferably past effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system are considered for an integration in a temporal context. Furthermore, the process model (PM) is preferably continuously adapted by effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system.

[0054] The process model (PM) is advantageously created 3, and particularly continuously adapted, by a computer-based neural network.

[0055] Particularly preferred multiple, independent from one another, process models (PM) are created 3 and during controlling the process within the system the process model (PM) is considered, which currently best maps the effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system.

[0056] For further improving the inventive method the process model (PM) considers future expected effects of setting actions (a.sub.t) on the state variables (s.sub.t) of the system. According to the inventive method the process within the system is controlled 4 by performing setting actions (a.sub.t) by considering the process model (PM), the interference model (SM) and predetermined controlling goals.

LIST OF NUMERALS

[0057] 1 capturing of state variables (s.sub.t) [0058] 2 creation of an interference model (SM) [0059] 3 creation of a process model (PM) [0060] 4 controlling the process within the system