A system and method for unsupervised root cause analysis of machine failures. The method includes analyzing, via at least unsupervised machine learning, a plurality of sensory inputs that are proximate to a machine failure, wherein the output of the unsupervised machine learning includes at least one anomaly; identifying, based on the output at least one anomaly, at least one pattern; generating, based on the at least one pattern and the proximate sensory inputs, an attribution dataset, the attribution dataset including a plurality of the proximate sensory inputs leading to the machine failure; and generating, based on the attribution dataset, at least one analytic, wherein the at least one analytic includes at least one root cause anomaly representing a root cause of the machine failure.

A system and method for unsupervised root cause analysis of machine failures. The method includes analyzing, via at least unsupervised machine learning, a plurality of sensory inputs that are proximate to a machine failure, wherein the output of the unsupervised machine learning includes at least one anomaly; identifying, based on the output at least one anomaly, at least one pattern; generating, based on the at least one pattern and the proximate sensory inputs, an attribution dataset, the attribution dataset including a plurality of the proximate sensory inputs leading to the machine failure; and generating, based on the attribution dataset, at least one analytic, wherein the at least one analytic includes at least one root cause anomaly representing a root cause of the machine failure.

According to an exemplary embodiment of the present disclosure, a computer program stored in a computer readable storage medium is disclosed. The computer program performs operations for processing input data when the computer program is executed by one or more processors of a computer device, the operations including: obtaining input data based on sensor data obtained during manufacturing of an article by using one or more manufacturing recipes in one or more manufacturing equipment; inputting the input data to a neural network model loaded to the computer device; generating an output by processing the input data by using the neural network model; and detecting an anomaly for the input data based on the output of the neural network model.

According to an exemplary embodiment of the present disclosure, a computer program stored in a computer readable storage medium is disclosed. The computer program performs operations for processing input data when the computer program is executed by one or more processors of a computer device, the operations including: obtaining input data based on sensor data obtained during manufacturing of an article by using one or more manufacturing recipes in one or more manufacturing equipment; inputting the input data to a neural network model loaded to the computer device; generating an output by processing the input data by using the neural network model; and detecting an anomaly for the input data based on the output of the neural network model.

A monitoring apparatus includes a sensing circuitry configured to sense a locked or released state of a door of a railway vehicle, or sense an open or closed state of the door, and a processor. The processor acquires an output of the sensing circuitry, and position information in an opening or closing direction of the door, and determines an abnormality in a configuration related to an opening or closing operation of the door, based on a match between the acquired output of the sensing circuitry and the position information.

A production line monitoring device that identifies a cause of a production defect, reduces the amount of analysis data and computation, and performs real-time processing, is provided. The production line monitoring device includes a defect indication detection unit that detects an indication of a production defect of a production line, and a defect cause identification unit that identifies a cause of the production defect. The defect indication detection unit collects measurement information measured by an inspection apparatus for each reference that identifies a position on products, and detects an indication of the production defect from the change with time of the measurement information at the references. The defect cause identification unit performs stratified analysis based on production information related to the reference when the defect indication detection unit detects an indication of a production defect, and identifies a cause of a production defect from a result of the analysis.

A visual inspection data collection and analysis system comprising: a plurality of visual inspection appliances (VTA) configured to inspect and acquire visual inspection data relating to inspected items; and a data collection and analytics server (DCAS) configured to receive information comprising the visual inspection data from the multiple VIAs and to analyze the received information to form a big data analysis. The VIAs are adapted for detecting defects or gating or counting the inspected items without the involvement of the DCAS.

A method for tracking product in an installation in which powdered product is processed into manufactured items is provided. The method comprises introducing the powdered product into the installation through at least one inlet, obtaining measurement data for the powdered product from at least one mass sensor positioned in the at least one inlet, and dividing the measurement data into mass units of equal size. The progression of the mass units is then tracked through the installation using measurement data from at least one other mass sensor in the installation.

This disclosure relates to the analysis of data generated by one or more connected systems and devices. Operational data obtained by one or more connected devices and/or systems, such as a connected thermostat and/or wind turbine system, may be used to detect and/or predict impending failures and/or suboptimal performance. By detecting and/or predicting anomalous system and device performance, various actions may be taken to improve system and device performance and mitigate failure conditions.

Systems and other embodiments described herein relate to a defects mangement system that includes a server having a database configured to store a plurality of records that respectively correspond to a plurality of products in an inspection line, a mobile computing device configured to receive user input indicating a location of a defect on a selected product among the plurality of products, and a local hub, in communication with the server, that receives the user input from the mobile computing device and updates a record among the plurality of records that corresponds to the selected product to include a defect indication in accordance with the user input.