公开(公告)号：US20240280474A1

公开(公告)日：2024-08-22

申请号：US18565310

申请日：2022-06-06

Applicant: RENISHAW plc

Inventor： Ian Mac BELL

IPC: G01N21/27

CPC classification number: G01N21/274 ,  G01N2201/127 ,  G01N2201/1296

Abstract: A method for removing noise from spectral data recorded using a spectrometer. The method includes normalising spectral data to generate normalised spectral data and applying a machine learning model to the normalised spectral data. The machine learning model is trained to remove noise from spectral data using normalised training data, wherein the spectral data is normalised based on a different scaling to the normalisation of the training data.

公开(公告)号：US20220252516A1

公开(公告)日：2022-08-11

申请号：US17630599

申请日：2020-09-01

Applicant: RENISHAW PLC

Inventor： Brian John Edward SMITH ,  Ian Mac BELL

IPC: G01N21/65

Abstract: A method of determining components present in a sample from spectral data obtained from the sample including resolving each of a plurality of models of the spectral data, the plurality of models including models having a different number of component reference spectra selected from a set of predetermined component reference spectra; selecting a one of the plurality of models based upon a model selection criterion and determining one or more components present in the sample based upon the selected model. The model selection criterion includes a measure for each model, which balances improvements in fit quality of the model to the spectral data against a complexity penalty determined from the number of component reference spectrum used in the model.

公开(公告)号：US20170227467A1

公开(公告)日：2017-08-10

申请号：US15501167

申请日：2015-08-26

Applicant: RENISHAW PLC

Inventor： Brian John Edward SMITH ,  Ian Mac BELL ,  Ian Paul HAYWARD

IPC: G01N21/65 ,  G01N21/31

CPC classification number: G01N21/65 ,  G01J3/0208 ,  G01J3/021 ,  G01J3/0291 ,  G01J3/18 ,  G01J3/2803 ,  G01J3/2823 ,  G01J3/36 ,  G01J3/44 ,  G01J2003/1828 ,  G01J2003/2813 ,  G01N21/31

Abstract: Spectroscopy including a source generating light profile on the sample. The light profile is movable relative to the sample. An optical input for receiving light from sample interaction with light from the source, a detector including two-dimensional array of photodetector elements, a dispersive device between the optical input and detector to spectrally disperse light from the optical input in spectral direction across the detector, an optical splitter in optical path between the optical input and detector to split light based upon wavenumber so, for a spectrum generated by a point on the sample, the spectrum first and second portions are dispersed across photodetector elements of different array row/column. Controller shifting data between photodetector elements in spatial direction, perpendicular to spectral direction, synchronously with relative movement between light profile and sample so data is accumulated on the spectrum first and second portions across different sets of photodetector elements during relative movement.