# US 12,181,846 B2 · Systems and processes for optimizing operation of industrial equipment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,181,846 B2 - Document ID: US12181846B2 - Status: Granted - Kind: B2 - Application number: 18/197,125 - Filed: 2023-05-15 - Published: 2023-09-14 - Granted: 2024-12-31 - Earliest claimed: 2019-05-30 - Assignees: Georgia-Pacific Corporation - Applicants: Georgia-Pacific LLC - Inventors: Robert Hartwell Herring, III - Web page: https://patentgrep.com/patent/US12181846B2 ## CPC - D21G 9/0009: {Paper-making control systems} - G05B 13/042: {in which a parameter or coefficient is automatically adjusted to optimise the performance} - D21F 7/00: Other details of machines for making continuous webs of paper - G05B 13/0265: {the criterion being a learning criterion} - G06Q 50/04: Manufacturing - D21G: CALENDERS; ACCESSORIES FOR PAPER-MAKING MACHINES (winders or rewinders for finished products, means for adjustment of wrinkles or lateral extensions B65H) - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - D21F: PAPER-MAKING MACHINES; METHODS OF PRODUCING PAPER THEREON - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract A system, method, and medium for virtually real time monitoring of machine performance are described. An optimal set-point for a data source is determined. The data source corresponds to operation of a machine. Virtually real time data is received from the data source corresponding to current operation of the machine. A deviation between the virtually real time data and the optimal set-point for the data source is computed. An intensity map is rendered representing the computed deviation according to a predefined visual gradient. ## Claims ### Claim 1 A method for virtually real time monitoring of machine performance, comprising: determining an optimal set-point for a data source, the data source corresponding to operation of a machine; receiving virtually real time data from the data source corresponding to current operation of the machine; computing a deviation between the virtually real time data and the optimal set-point for the data source; and rendering an intensity map representing the computed deviation according to a predefined visual gradient, wherein the predefined visual gradient comprises a color gradient, a set of colors in the color gradient corresponds to an intensity scale derived according to a scaled normal distribution about the optimal set-point, the intensity scale comprises scaled deviation thresholds, and rendering the intensity map further comprises: generating a sampling frame for the data source; scaling the deviation of the data source to the intensity scale; and rendering the sampling frame for the data source on the intensity map, wherein a color of the sampling frame is derived from a comparison between the scaled deviation value and the scaled deviation thresholds. ### Claim 2 (depends on 1) The method of claim 1, wherein the intensity map is displayed in association with a corrective action corresponding to a pre-error state of the machine. ### Claim 3 (depends on 1) The method of claim 1, wherein the optimal set-point for the data source is determined using a machine learning model. ### Claim 4 (depends on 1) The method of claim 1, wherein computing the deviation further comprises computing a respective deviation for each of a plurality of data sources between virtually real time data from each of the plurality of data sources and a corresponding optimal set-point for each of the plurality of data sources, the plurality of data sources corresponding to operation of the machine; and the method further comprises: calculating an overall health metric for the machine based at least in part on the respective deviation for each of the plurality of data sources. ### Claim 5 (depends on 1) The method of claim 1, wherein the intensity map represents the computed deviation for a plurality of data sources. ### Claim 6 (depends on 1) The method of claim 1, wherein the deviation comprises a standard deviation. ### Claim 7 (depends on 1) The method of claim 1, wherein the data source corresponds to a physical sensor operatively connected to the machine. ### Claim 8 (depends on 1) The method of claim 1, wherein the machine is a paper-making machine. ### Claim 9 (depends on 1) The method of claim 1, wherein the virtually real time data corresponds to a particular time period, and the computed deviation varies over the particular time period. ### Claim 10 (depends on 1) The method of claim 1, wherein: the set of colors in the color gradient comprises a first subset of colors associated with lower scaled deviation thresholds and a second subset of colors associated with higher scaled deviation thresholds; the first subset of colors trends toward colors of shorter wavelengths; and the second subset of colors trends toward colors of longer wavelengths. ### Claim 11 A system for virtually real time monitoring of machine performance, comprising: at least one computing device configured to at least: determine an optimal set-point for a data source, the data source corresponding to operation of a machine; receive virtually real time data from the data source corresponding to current operation of the machine; compute a deviation between the virtually real time data and the optimal set-point for the data source; render an intensity map representing the computed deviation according to a predefined visual gradient, wherein the predefined visual gradient comprises a color gradient, a set of colors in the color gradient corresponds to an intensity scale derived according to a scaled normal distribution about the optimal set-point, and the intensity scale comprises scaled deviation thresholds; generate a sampling frame for the data source; scale the deviation of the data source to the intensity scale; and render the sampling frame for the data source on the intensity map, wherein a color of the sampling frame is derived from a comparison between the scaled deviation value and the scaled deviation thresholds. ### Claim 12 (depends on 11) The system of claim 11, wherein the optimal set-point is determined based at least in part on a principal component analysis-based multivariate model of optimal machine performance. ### Claim 13 (depends on 11) The system of claim 11, wherein: the set of colors in the color gradient comprises a first subset of colors associated with lower scaled deviation thresholds and a second subset of colors associated with higher scaled deviation thresholds; the first subset of colors trends toward colors of shorter wavelengths; and the second subset of colors trends toward colors of longer wavelengths. ### Claim 14 A non-transitory computer-readable medium embodying instructions executable in at least one computing device, wherein when executed the instructions cause the at least one computing device to at least: determine an optimal set-point for a data source, the data source corresponding to operation of a machine; receive virtually real time data from the data source corresponding to current operation of the machine; compute a deviation between the virtually real time data and the optimal set-point for the data source; render an intensity map representing the computed deviation according to a predefined visual gradient, wherein the predefined visual gradient comprises a color gradient, a set of colors in the color gradient corresponds to an intensity scale derived according to a scaled normal distribution about the optimal set-point, and the intensity scale comprises scaled deviation thresholds; generate a sampling frame for the data source; scale the deviation of the data source to the intensity scale; and render the sampling frame for the data source on the intensity map, wherein a color of the sampling frame is derived from a comparison between the scaled deviation value and the scaled deviation thresholds. ### Claim 15 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the optimal set-point is determined based at least in part on a principal component analysis-based multivariate model of optimal machine performance. ### Claim 16 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein: the set of colors in the color gradient comprises a first subset of colors associated with lower scaled deviation thresholds and a second subset of colors associated with higher scaled deviation thresholds; the first subset of colors trends toward colors of shorter wavelengths; and the second subset of colors trends toward colors of longer wavelengths. ### Claim 17 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the intensity map is displayed in association with a corrective action corresponding to a pre-error state of the machine. ### Claim 18 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the optimal set-point for the data source is determined using a machine learning model. ### Claim 19 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein computing the deviation further comprises computing a respective deviation for each of a plurality of data sources between virtually real time data from each of the plurality of data sources and a corresponding optimal set-point for each of the plurality of data sources, the plurality of data sources corresponding to operation of the machine. ### Claim 20 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the data source corresponds to a physical sensor operatively connected to the machine.