US 11,853,053 B2
Dynamic prediction of risk levels for manufacturing operations through leading risk indicators: dynamic exceedance probability method and system
Ankur Pariyani, Philadelphia, PA (US); Matthew Dering, Philadelphia, PA (US); Ulku G. Oktem, Philadelphia, PA (US); Brett Emaus, Philadelphia, PA (US); Daniel Shumway, Philadelphia, PA (US); and Steven DeLaurentis, Philadelphia, PA (US)
Assigned to Near-Miss Management LLC, Philadelphia, PA (US)
Filed by Near-Miss Management LLC, Philadelphia, PA (US)
Filed on Jan. 24, 2022, as Appl. No. 17/582,234.
Application 17/582,234 is a continuation in part of application No. 16/894,965, filed on Jun. 8, 2020, granted, now 11,250,366.
Application 16/894,965 is a continuation in part of application No. 16/356,580, filed on Mar. 18, 2019, granted, now 10,705,516, issued on Jul. 7, 2020.
Application 16/356,580 is a continuation in part of application No. 15/012,109, filed on Feb. 1, 2016, granted, now 10,268,962, issued on Apr. 23, 2019.
Application 15/012,109 is a continuation in part of application No. 14/511,729, filed on Oct. 10, 2014, granted, now 9,495,863, issued on Oct. 27, 2015.
Claims priority of provisional application 62/109,865, filed on Jan. 30, 2015.
Prior Publication US 2022/0214679 A1, Jul. 7, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G08B 23/00 (2006.01); G05B 23/02 (2006.01)
CPC G05B 23/0281 (2013.01) [G05B 23/027 (2013.01); G05B 23/0248 (2013.01); G05B 23/0272 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A dynamic system for analyzing risk levels for a manufacturing operation by a user, the system comprising:
a server that receives at least one variable comprising automatically measured process data from a real-time data source, a historical archive data source of the variable or a long-term process data source of the variable defining a period preceding the automatically measured process data, and a variable threshold, previously uploaded to the server by the user, or an agent or employee of the user;
a processor that uses a two-stage Bayesian inference model of parameters P and/or groups G of the parameters P of the measured process data at time interval T to determines a final dynamic exceedance probability value for the variable given the real-time data source, the historical archive data source or long-term process data source, and the variable threshold, wherein the final dynamic exceedance probability is automatically updated over time to identify operational risk and/or near-miss risk that would otherwise be unknown or concealed in parameters P; and
a display that presents the operational risk and/or near-miss risk in a graphic that visually depicts the final dynamic exceedance probability value for the variable over a future time horizon designated by the user or an agent or employee of the user;
wherein the system continuously and autonomously operates contemporaneously with the manufacturing operation.