5.4.2.5 Example 5 

Claim 1: 

A method for coating a workpiece using a thermal spray coating process, the method comprising:

(a)applying, using a spray jet, a material to the workpiece by thermal spray coating; 

(b)monitoring the thermal spray coating process in real time by detecting properties of particles in the spray jet and supplying the properties as actual values; 

(c)comparing the actual values with target values; 

and, in the event that the actual values deviate from the target values,

(d)adjusting process parameters for the thermal spray coating process automatically by a controller on the basis of a neural network, said controller being a neuro-fuzzy controller which combines a neural-network and fuzzy logic rules and thereby maps statistical relationships between input variables and output variables of the neuro-fuzzy controller. 

Background: The invention relates to the control of an industrial process, i.e. thermal spray coating of a workpiece. The material used for the coating is injected with the help of a carrier gas into the high-temperature jet, where it is accelerated and/or molten. The properties of the resulting coatings are subject to great fluctuations, even with seemingly constant parameters of the coating operation. The spray jet is monitored visually with a CCD camera. The image picked up by the camera is sent to an image processing system, from which the properties of particles in the spray jet (e.g. velocity, temperature, size, etc) can be derived. A neuro-fuzzy controller is a mathematical algorithm which combines a neural network with fuzzy-logic rules.

Application of the steps of the problem-solution approach according to COMVIK:

Step (i): The method is directed at thermal spray coating, i.e. a specific technical process, comprising various concrete technical features, e.g. particles, workpiece, a spray coating device (implicit).

Step (ii): Document D1 discloses a method for the control of a thermal spray coating process by applying material to a workpiece using a spray jet, detecting deviations in the properties of the particles in said spray jet and adjusting process parameters automatically on the basis of the outcome of a neural network analysis. This document represents the closest prior art.

Step (iii): The difference between the method of claim 1 and D1 concerns the use of a neuro-fuzzy controller combining a neural network and fuzzy logic rules as specified in the second part of step (d).

Computational models and algorithms related to artificial intelligence are, on their own, of an abstract mathematical nature (G‑II, 3.3.1). The feature of combining results of a neural network analysis and fuzzy logic defines a mathematical method when taken on its own. However, together with the feature of adjusting the process parameters, it contributes to the control of the coating process. Hence, the output of the mathematical method is directly used in the control of a specific technical process.

Control of a specific technical process is a technical application, see G‑II, 3.3 (subsection "Technical applications"). In conclusion, the differentiating feature contributes to producing a technical effect serving a technical purpose and thereby contributes to the technical character of the invention. Therefore, it is taken into account in the assessment of inventive step.

Step (iii)(c): The objective technical problem must be derived from technical effects that are based on objectively established facts and that are directly and causally related to the technical features of the claim.

In the present case, the mere fact that the parameters are calculated using a combination of results of a neural network analysis and fuzzy logic – without any details on specific adaptation to the thermal spray coating process – cannot credibly ensure any technical effect beyond a different adjustment of the process parameters. In particular, no evidence can be found to acknowledge any increase in the quality of coating properties or of the thermal spraying method that would result from the combination of features of claim 1. In the absence of such evidence, the objective technical problem is to provide an alternative solution to the problem of adjusting the process parameters which control the thermal spray coating process which is already solved in D1.

Obviousness: Starting from the teaching of D1 and tasked with the above objective technical problem, the person skilled in the field of control engineering (G‑VII, 3) would look for an alternative solution to determine the control parameters of the process.

A second prior-art document D2 discloses a combination of a neural network and fuzzy logic rules providing a neuro-fuzzy controller in the technical field of control engineering. From this prior art, it has become apparent that at the date of filing of the application, neuro-fuzzy controllers were well known and applied in the field of control engineering. The present solution is therefore considered to be an obvious alternative, rendering the subject-matter of claim 1 not inventive.

Remarks: This example illustrates the case where a mathematical feature which, when taken in isolation, is non-technical but contributes to producing a technical effect serving a technical purpose in the context of the claim. The feature of using a combination of neural network results and fuzzy logic for adjusting process parameters for controlling thermal spraying contributes to the technical character of the invention and may therefore support the presence of an inventive step.

However, in the present case, claim 1 does not contain any information about the coating properties to be achieved. The availability of the general teaching of using neuro-fuzzy controllers in the field of control engineering resulted in the objection that the controller of claim 1 was an obvious alternative. This particular objection could have been avoided if the claim had recited further features of the fuzzy control method linked to some technical properties of the spray coating process. For example, if the desirable coating properties resulted from specific The input and output variables of the neuro-fuzzy controller, how the controller is trained or how the output is used in the regulation of the process parameters, these features would have had to be recited in the claim. The description and figures as filed could have provided evidence that the desirable coating properties are indeed achieved. are not defined. No features of the neuro-fuzzy controller are linked to any technical properties of the spray coating. The As currently claimed, the neuro-fuzzy controller is therefore not adapted for the specific application of thermal spray coating. There is no evidence of any particular technical effect which is credibly achieved over the whole claimed scope other than that of providing different process parameters as input to the controller.