Topic
Process variable
About: Process variable is a research topic. Over the lifetime, 3983 publications have been published within this topic receiving 43130 citations. The topic is also known as: process parameter.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this paper, an adaptive laser cladding methodology for obtaining the optimal process parameters taking into account the real geometry of the part, providing a unique solution to solve the part-to-part variation repair problem in blades.
Abstract: Worn-out blade geometries differ from the nominal geometry Studies about numerical control tool path recalculation or control processes at constant melt pool are the most used approaches to generate a good repair process, but they use the same parameters for all parts, in spite of the different thermal behavior due to the difference in thickness This paper presents an innovative based adaptive laser cladding methodology for obtaining the optimal process parameters taking into account the real geometry of the part, providing a unique solution to solve the part-to-part variation repair problem in blades This solution can be implemented on its own or combined with monitoring and control process techniques Laser power was identified as the most effective process parameter that permitted to modify and adapt the obtained width to the presented in a blade different from the nominal The study of the obtained width when varying laser power on machined thin wall of different widths showed that MetcoClad718 and Ti6Al4V clad width behavior exhibited three phases From the comparison of experimental data with programmed overwidths, it was possible to determine equations that related the required power for variable widths Results show that it is not necessary to know the nominal input power to repair blade tips with variable geometries The required power is directly obtained from the methodology equations The performance of the proposed methodology was validated by laser cladding on machined MetcoClad718 mock-up blades and by means of the repair of Ti6Al4V compressor blades Good agreement between experimental and programmed widths was obtained
38 citations
••
TL;DR: An opportunity to fully automate the approach to process optimisation by applying labels to the data is indicated, an approach that could also potentially be suited for on-the-fly process Optimisation.
Abstract: Metal-based additive manufacturing is a relatively new technology used to fabricate metal objects within an entirely digital workflow. However, only a small number of different metals are proven for this process. This is partly due to the need to find a new set of parameters which can be used to successfully build an object for every new alloy investigated. There are dozens of variables which contribute to a successful set of parameters and process parameter optimisation is currently a manual process which relies on human judgement.,Here, the authors demonstrate the application of machine learning as an alternative method to determine this set of process parameters, the subject of this test is the processing of pure copper in a laser powder bed fusion printer. Data in the form of optical images were collected over the course of traditional parameter optimisation. These images were segmented and fed into a convolutional autoencoder and then clustered to find the clusters which best represented a high-quality result. The clusters were manually scored according to their quality and the results applied to the original set of parameters.,It was found that the machine-learned clustering and subsequent scoring reflected many of the observations which were found in the traditional parameter optimisation process.,This exercise, as well as demonstrating the effectiveness of the ML approach, indicates an opportunity to fully automate the approach to process optimisation by applying labels to the data, hence, an approach that could also potentially be suited for on-the-fly process optimisation.,Opens in a new window.
38 citations
••
TL;DR: In this paper, an approach using quality loss functions and multicriteria optimization procedure to determine appropriate process parameter values for producing quality products in a continuous casting system is proposed, where the objective function is formulated as a loss function, which establishes a functional relationship between the input variables or process parameters and the quality criteria.
38 citations
••
TL;DR: In this paper, a computationally fast technique accurately estimates process variables when conditions are dynamic due to changes in steady states, and confidence intervals for true values of process variables are provided.
Abstract: A computationally fast technique accurately estimates process variables when conditions are dynamic due to changes in steady states. The process variable estimators are unbiased and have known distributions. Thus, confidence intervals for true values of process variables are provided. The formulation of this technique was motivated by a recursive, dynamic data reconciliation technique that obtains very accurate estimators. These two techniques are compared in terms of computational speed and accuracy of estimators. The proposed technique is computationally faster, but not as accurate when variances of process measurements are large. However, the accuracy of the proposed estimators is shown to approach that of the recursive technique by iteratively recalculating estimates and when measurement variances decrease.
38 citations
•
IBM1
TL;DR: In this paper, a real-time in-situ supervision of a step performed in a processing tool during semiconductor wafer fabrication is presented, where an appropriate process parameter is selected as being the most representative of normal operating conditions.
Abstract: Method and system for real-time in-situ supervision of a step
performed in a processing tool during semiconductor wafer
fabrication. For this step, an appropriate process parameter
has been selected as being the most representative of normal
operating conditions. The evolutions of said selected process
parameter in normal operating conditions and in all its known
deviations identified by process engineers are coded and
stored in a database. Analysis rules including rejection
criteria adapted to recognize any such identified deviation
are defined by process engineers and coded in the form of
algorithms and likewise stored in the database. Finally, an
alert code and the right action to be taken are also
established by process engineers for each identified deviation
and coded in the database. During wafer processing, this
process parameter is continuously monitored, for instance by
an Etch End Point (EPD) controller. The signal is coded then
analyzed by a supervisor to be compared with corresponding
data stored in the database in real-time. If an anomaly, i.e.
a deviation to the normal process, is detected, the
corresponding alert code is flagged and the recommended
action immediately taken. As a result, only "good" wafers
will be completely processed. This technique allows total
clusterized wafer fabrication processes.
37 citations