Abstract: In a ship control system of one embodiment, a route command unit outputs a route command including a target ship position and a target bow direction of a ship. An information detector detects ship information including an actual ship position and an actual bow direction of a ship. An external force vector estimation unit estimates an external force vector received by a ship, using the ship information and a hull motion model related to a hull motion of the ship. A control command unit controls both rotational frequency of a main engine and a rudder angle of a ship, based on the route command, the ship information, and the external force vector.

Abstract: A ship monitoring system includes: a shipboard information processing apparatus and including a shipboard communication unit and an information acquisition unit; and a support information processing apparatus and including: a support side communication unit capable of communicating with the shipboard communication unit; a time lag identification unit; and a state prediction unit. The time lag identification unit identifies a time from transmission of the ship motion information from the shipboard communication unit to reception of the ship motion information by the support side communication unit as a reception time lag. The state prediction unit inputs the ship motion information and the reception time lag to a ship motion model related to the ship motion of the ship to predict a motion state of the ship ahead of a motion state of the ship indicated by the ship motion information by a period of time based on the reception time lag.

Abstract: In a ship control system of one embodiment, a main engine controller performs, when controlling the rotational frequency of a main engine based on a target ship speed of a ship, feedback control of an actual ship speed of the ship to perform ship speed control for bringing the actual ship speed closer to the target ship speed. A turning judgment unit judges whether or not the ship will turn. A control change unit performs, when the turning judgment unit has judged that the ship will turn, lowering processing for lowering the responsiveness of the ship speed control.

Abstract: A placement apparatus for placing a workpiece is provided. The placement apparatus includes a stage on which a workpiece can be placed in a processing vessel; an edge ring including a locking part which is disposed on the stage so as to surround a periphery of the workpiece; a conductive connecting member connected with the edge ring at the locking part; and a first contacting member configured to cause the edge ring to contact the stage, while the edge ring is connected with the connecting member.

Abstract: Techniques for causal modeling. Historical feature data is received, relating to a plurality of nodes in a system. A machine learning (ML) model is generated, for a node of the plurality of nodes. The ML model is trained to predict a plurality of future feature values for the node based on at least a portion of the historical feature data. A causal graph is generated, for the plurality of nodes, using a feature selection mechanism within the ML model. The feature selection mechanism includes a regularization term encouraging sparsity of nodes in selected features in the ML model.

Abstract: A combustor component of a combustor for combusting fuel to produce a combustion gas includes a combustion cylinder forming a passage for the combustion gas, a first acoustic device which internally includes a first cavity communicating with the passage via a first through hole formed in the combustion cylinder, a second acoustic device which is located on a radially outer side of the first acoustic device so as to cover the first acoustic device, and internally includes a second cavity communicating with the passage via a second through hole formed in the combustion cylinder, and a first communication passage causing the first cavity and an outer space of the combustion cylinder to communicate with each other without via the first through hole and the second cavity.

Abstract: A gas turbine combustor according to at least one embodiment is a gas turbine combustor that includes: a tubular member; a plurality of premixing tubes circumferentially arranged on an inner side of the tubular member, each of the plurality of premixing tubes forming an outlet portion of a premixing passage; and a base plate for supporting the plurality of premixing tubes. The base plate has: a plurality of through holes disposed corresponding to the plurality of premixing tubes, respectively, and allowing the premixing passage to pass through the base plate; and a plurality of oblique holes extending obliquely with respect to an axial direction of the gas turbine combustor in a region different from a region where the through holes are disposed.

Abstract: The upstream-side wall portion 54 includes, in the circumferential direction thereof, a first region 31 where air inlets 30 are formed at a lower density, and a second region 32 which is disposed at a position offset from the first region 31 in the circumferential direction, and in which the air inlets 30 are formed at a higher density than in the first region 31.

Abstract: A computer-implemented method is provided that includes learning causal relationships between two or more application micro-services, and applying the learned causal relationships to dynamically localize an application fault. First micro-service error log data corresponding to selectively injected errors is collected. A learned causal graph is generated based on the collected first micro-service error log data. Second micro-service error log data corresponding to a detected application and an ancestral matrix is built using the learned causal graph and the second micro-service error log data. The ancestral matrix is leveraged to identify the source of the error, and the micro-service associated with the identified error source is also subject to identification. A computer system and a computer program product are also provided.

Abstract: Techniques for causal modeling. Historical feature data is received, relating to a plurality of nodes in a system. A machine learning (ML) model is generated, for a node of the plurality of nodes. The ML model is trained to predict a plurality of future feature values for the node based on at least a portion of the historical feature data. A causal graph is generated, for the plurality of nodes, using a feature selection mechanism within the ML model. The feature selection mechanism includes a regularization term encouraging sparsity of nodes in selected features in the ML model.

Abstract: A computer-implemented method, a computer program product, and a computer system for stochastic event triage. A computer receives an event log including timestamps and event types. The computer determines a sparse impact matrix representing causal relationships between the event types, via a cardinality regularization. The computer determines triggering probabilities representing causal association probabilities between individual event instances, by leveraging a variational bound of a likelihood function. The computer provides a user with the triggering probabilities for event triage. The computer learns model parameters by iterating type-level causal analysis and instance-level causal analysis.

Abstract: A combustor component of a combustor for combusting fuel to produce a combustion gas includes a combustion cylinder forming a passage for the combustion gas, a first acoustic device which internally includes a first cavity communicating with the passage via a first through hole formed in the combustion cylinder, a second acoustic device which is located on a radially outer side of the first acoustic device so as to cover the first acoustic device, and internally includes a second cavity communicating with the passage via a second through hole formed in the combustion cylinder, and a first communication passage causing the first cavity and an outer space of the combustion cylinder to communicate with each other without via the first through hole and the second cavity.

Abstract: A computer-implemented method, a computer program product, and a computer system for diagnosing anomalies detected by a black-box machine learning model. A computer determines a local variance of a test sample in a test dataset, where the local variance represents uncertainty of a prediction by the black-box machine learning model. The computer initializes optimal compensations for the test sample, where the optimal compensations are optimal perturbations to test sample values of respective components of a multivariate input variable. The computer determines local gradients for the test sample. Based on the local variance and the local gradients, the computer updates the optimal compensations until convergences of the optimal compensations are reached. Using the optimal compensations, the computer diagnoses the anomalies detected by the black-box machine learning model.

Abstract: A combustor provided with: a nozzle having formed therein an air jet section that causes air to be jetted from a nozzle section; a cylindrical part covering the nozzle from the outer peripheral side thereof and forming an air flow path between the cylindrical part and the nozzle; and a pressure loss section provided to the air flow path. The pressure loss section causes a loss of pressure in the air that flows through the air flow path. The nozzle is provided with: at least one air inlet section that takes in air from an outer peripheral surface that is an upstream side from the pressure loss section; and a flow path-forming section forming a discharge air flow path that guides air that is taken in from the at least one air inlet section to the air jet section.

Abstract: A computer-implemented method, a computer program product, and a computer system for diagnosing anomalies detected by a black-box machine learning model. A computer determines a local variance of a test sample in a test dataset, where the local variance represents uncertainty of a prediction by the black-box machine learning model. The computer initializes optimal compensations for the test sample, where the optimal compensations are optimal perturbations to test sample values of respective components of a multivariate input variable. The computer determines local gradients for the test sample. Based on the local variance and the local gradients, the computer updates the optimal compensations until convergences of the optimal compensations are reached. Using the optimal compensations, the computer diagnoses the anomalies detected by the black-box machine learning model.

Abstract: A method for anomaly alarm consolidation includes detecting a plurality of anomalies in time-series data received from an information technology infrastructure; identifying a plurality of root-cause candidates for each of the anomalies; generating, by a scenario analysis of the anomalies, a plurality of alarms, wherein the scenario analysis predicts a plurality of future expected values of the time-series data over a plurality of historical values of the time-series data using a graphical Granger causal model and generates the alarms based on a difference between the future expected values of the time-series data and actual values of the anomalies in the time-series data; and performing a belief propagation procedure between the root-cause candidates and the alarms to determine a plurality of root-causes that collectively comprise attributed root-causes for the alarms.

Abstract: A method for anomaly alarm consolidation includes detecting a plurality of anomalies in time-series data received from an information technology infrastructure; identifying a plurality of root-cause candidates for each of the anomalies; generating, by a scenario analysis of the anomalies, a plurality of alarms, wherein the scenario analysis predicts a plurality of future expected values of the time-series data over a plurality of historical values of the time-series data using a graphical Granger causal model and generates the alarms based on a difference between the future expected values of the time-series data and actual values of the anomalies in the time-series data; and performing a belief propagation procedure between the root-cause candidates and the alarms to determine a plurality of root-causes that collectively comprise attributed root-causes for the alarms.

Abstract: An image processing apparatus includes an image-data processor, an interface, a power source, and a controller. The controller selects a first mode, a second mode, or a third mode as a power supply mode. In the first mode, electric power is supplied from the power source to the image-data processor and the interface. In the second mode, supply of the electric power from the power source to the image-data processor and the interface is in a stopped state. In the third mode, the electric power is supplied from the power source to the interface, but supply of the electric power to the image-data processor is in a stopped state. The controller switches the power supply mode from the second mode to the third mode in response to receiving a power supply request from an external device via the interface in the second mode.

Abstract: To provide a gas turbine combustor that can suppress a generation amount of NOx and maintain a flame holding property, while suppressing burn damage around a pilot nozzle including the pilot nozzle. A gas turbine combustor includes a pilot nozzle that can inject fuel F and cooling air A for cooling a nozzle tip, a flow regulating valve that can adjust a flow rate of cooling air to be supplied to the pilot nozzle, a detection sensor that detects a combustion state of fuel, and a control device that controls the flow regulating valve based on a detection result of the detection sensor.

Abstract: The upstream-side wall portion 54 includes, in the circumferential direction thereof, a first region 31 where air inlets 30 are formed at a lower density, and a second region 32 which is disposed at a position offset from the first region 31 in the circumferential direction, and in which the air inlets 30 are formed at a higher density than in the first region 31.