Check patentability & draft patents in minutes with Patsnap Eureka AI!

Preprocessing method for providing uniform data blocks

A data block and preprocessing technology, applied in data processing applications, electrical digital data processing, prediction, etc., can solve problems such as lack of model quality and lack of comparability

Pending Publication Date: 2021-09-07
ROBERT BOSCH GMBH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is difficult to compare these different models and decide which one should be used in the operation of the machine
[0006] In summary, inhomogeneity in datasets and the data values ​​contained therein leads to lack of quality and lack of comparability of models trained with them

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Preprocessing method for providing uniform data blocks
  • Preprocessing method for providing uniform data blocks
  • Preprocessing method for providing uniform data blocks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] exist figure 1 In a preferred embodiment, the principle sequence of the method according to the invention and the further use of the homogenized data blocks provided by the method is shown in .

[0043] The method begins by forming 110 a data block from an initially acquired data set. In this case, the data sets within a defined period of time are each aggregated into a data block. The time periods corresponding to different data blocks preferably have the same duration and likewise preferably do not overlap each other. In this case, for example, data blocks are conceivable which extend within the range of a time period of 5 minutes, 10 minutes, 15 minutes, 30 minutes, 45 minutes, 60 minutes, etc.

[0044] Then, in a further step, an adjustment 120 of the quantity of the data sets contained in the data blocks and a normalization 140 of the values ​​of the operating parameters contained in the data sets take place. Contrary to what is shown, these two steps do not hav...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a preprocessing method for providing uniform data blocks from temporally ordered, non-uniform data sets having values of acquired operating parameters of a machine in order to obtain data blocks suitable for monitoring the machine by means of a machine learning-based algorithm. The method comprises the following steps: forming data blocks from data sets, so that each data block comprises the data sets within a corresponding time period; adjusting the amount of data sets in each data block such that the data block contains a predetermined number of complete data sets; and normalizing the data sets in the data blocks in such a way that the data sets have values for a predetermined operating parameter that lie within a predetermined range of values.

Description

technical field [0001] The invention relates to a preprocessing method for providing homogeneous data blocks from temporally ordered non-uniform data sets, wherein said data sets have values ​​of acquired operating parameters of a machine in order to obtain a data suitable for obtaining data based on Machine learning algorithms to monitor machine data blocks. In particular, the invention relates to a method for preprocessing acquired machine sensor data such that the machine sensor parameters are suitable for training and use in a machine learning-based algorithm for monitoring machines. Background technique [0002] For monitoring a machine or a machine part, a model encoding the operating state of the machine can be used. These models can be obtained by training algorithms based on machine learning, training using a training data set with parameters, in particular sensor data, acquired during machine operation. The training of the algorithms and the quality of the traine...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F11/30G06K9/62G06N20/00
CPCG06F11/3058G06N20/00G06F18/214G06Q10/04
Inventor T·托里卡
Owner ROBERT BOSCH GMBH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com