Abstract: An information processing apparatus comprising processing circuitry, the processing circuitry constructs a prediction model for predicting time-series data related to a state of a device/equipment, calculates a prediction error that is a difference between a predicted value of the time-series data predicted by the prediction model and an actual value of the time-series data, divides the prediction error into a plurality of first sections in a time axis direction, calculates a state change amount of the actual value based on the prediction error divided into the plurality of first sections; and constructs a state determination model for determining the state of the device/equipment based on the state change amount.

Abstract: According to one embodiment, an information processing apparatus includes processing circuitry configured to group first variables in first data that includes the first variables and a second variable, and generate a plurality of groups that include the first variables; and determine a model architecture of a prediction model, based on the first data, the prediction model being configured to associate the first variables included in the groups with a predicted value of the second variable.

Abstract: According to one embodiment, an operation planning system includes a demand information database and a plurality of planning units. The demand information database stores demand data including an overall output required for a plurality of operation units for a planning period in an operation plan. The plurality of planning units adjusts output settings of the plurality of operation units. Any of the planning units selects a combination of operation units which provide the overall output required for the planning period, and based on operation costs depending on the outputs of the operation units, a process is repeated to generate the operation plan, the process including: selection of the operation unit belonging to the combination of operation units; and adjustment of the output setting for the selected operation unit by the planning unit paired with the selected operation unit.

Abstract: According to one embodiment, a genotype estimation device includes: an acquirer configured to acquire a clustering strength of genotype data of a plurality of specimens including an unknown specimen whose genotype is not known and known specimens whose genotypes are known; and an estimator configured to estimate the genotype of the unknown specimen on the basis of the genotype data in response to the clustering strength being larger than a first threshold, and output an estimation result.

Abstract: According to one embodiment, an information processing device includes: a divider configured to divide time series data of an objective variable into a plurality of first sections based on values of the objective variable; a model generator configured to generate, based on time series data of an explanatory variable and the time series data of the objective variable, a plurality of prediction models in which the explanatory variable and the objective variable are associated, for the plurality of first sections; a selector configured to select a first section from the plurality of first sections based on at least one of the time series data of the explanatory variable and the time series data of the objective variable; and a predictor configured to predict the value of the objective variable by using the prediction model generated for the selected first section.

Abstract: A method and system for detecting anomalies in waveforms in an industrial plant. During a learning stage, one or more training waveforms are received from sensors monitoring a plurality of equipment in the industrial plant. The one or more training waveforms are used to generate a representative waveform and deviations of the one or more training waveforms from the representative waveform are determined. Based on the deviations, groups are created. A model may be associated with each group for building an expected waveform pattern. When test waveforms are received, based on the electrical and physical properties of the test waveforms, each test waveform is classified into one of the groups. Thereafter, each waveform is compared with the expected waveform pattern associated with the group to which the respective test waveform belongs, to detect the anomaly.

Abstract: According to one embodiment, an operation planning system includes a storage and a plurality of planning devices. The storage is configured to: store information of operating devices and planning devices included in the operation planning system; store a total output required for a plurality of operating devices in a planning period of an operation plan; and store the operation plan including a combination of operating devices operating in the planning period and an output setting value for each of the operating devices in the combination. The plurality of planning devices is configured to: generate the combination satisfying the total output required in the planning period; determine the output setting value for each of the operating devices belonging to the combination; obtain combination data which is data of the combinations generated by the other planning devices; and generate the operation plan based on the combination data.

Abstract: The present disclosure relates to a method, system and device for power generation planning in a power generation system. The power generation system comprises a plurality of Power Generation Units (PGUs). The system receives a power demand data indicative of power required over a pre-defined time period, by a load. A pattern in variation of power among various patterns is identified for each of one or more intervals in the pre-defined time period. An operation technique and a repair technique are determined for each of the one or more intervals based on the pattern. A plurality of working patterns for operating the plurality of PGUs is determined in each of the one or more intervals based on determined operational technique and repair technique for corresponding one or more intervals. System determines individual power outputs to be generated by the number of PGUs determined in each of the plurality of working patterns.

Abstract: A waveform segmentation device has a state level estimation unit that estimates a state level of input waveform data, and a segmentation identification unit that segments the waveform data at a plurality of segmentation points based on the state level estimated by the state level estimation unit. The segmentation identification unit may identify the plurality of segmentation points such that a feature value of the waveform data is included between two adjacent segmentation points among the segmentation points.

Abstract: Present disclosure discloses a method and system for detecting anomalies in waveforms in an industrial plant. During a learning stage, one or more training waveforms are received from a plurality of sensors monitoring a plurality of equipment in the industrial plant. The one or more training waveforms are used to generate a representative waveform and deviations of the one or more training waveforms from the representative waveform is determined. Based on the deviations, a plurality of groups is created. A model may be associated with each group for building an expected waveform pattern (reference waveform pattern). In real-time a plurality of test waveforms is received. Based on the electrical and physical properties of the plurality of test waveforms, each test waveform is classified into one of the plurality of groups. Thereafter, each waveform is compared with the reference waveform pattern associated with the group to which the respective test waveform belongs, to detect the anomaly.

Abstract: An anomaly detection apparatus has a model creator, based on a plurality of sensor data input sequentially in time, to create a plurality of candidate models with a plurality of techniques for detection of an anomaly of the sensor data, an accuracy calculator to calculate decision accuracies of the plurality of candidate models, a model selector to select one or more candidate models from among the plurality of candidate models based on the decision accuracies of the plurality of candidate models, to create an anomaly detection model, a data classifier to determine whether new sensor data is normal or abnormal based on the anomaly detection model, and a model updater to update the plurality of candidate models based on the decision accuracies of the plurality of candidate models calculated by the accuracy calculator and on the new sensor data determined to be normal or abnormal by the data classifier.

Abstract: The present disclosure relates to a method, system and device for power generation planning in a power generation system. The power generation system comprises a plurality of Power Generation Units (PGUs). The system receives a power demand data indicative of power required over a pre-defined time period, by a load. A pattern in variation of power among various patterns is identified for each of one or more intervals in the pre-defined time period. An operation technique and a repair technique are determined for each of the one or more intervals based on the pattern. A plurality of working patterns for operating the plurality of PGUs is determined in each of the one or more intervals based on determined operational technique and repair technique for corresponding one or more intervals. System determines individual power outputs to be generated by the number of PGUs determined in each of the plurality of working patterns.

Abstract: According to one embodiment, an operation planning system includes a storage and a plurality of planning devices. The storage is configured to: store information of operating devices and planning devices included in the operation planning system; store a total output required for a plurality of operating devices in a planning period of an operation plan; and store the operation plan including a combination of operating devices operating in the planning period and an output setting value for each of the operating devices in the combination. The plurality of planning devices is configured to: generate the combination satisfying the total output required in the planning period; determine the output setting value for each of the operating devices belonging to the combination; obtain combination data which is data of the combinations generated by the other planning devices; and generate the operation plan based on the combination data.

Abstract: According to one embodiment, an operation planning system includes a demand information database and a plurality of planning units. The demand information database stores demand data including an overall output required for a plurality of operation units for a planning period in an operation plan. The plurality of planning units adjusts output settings of the plurality of operation units. Any of the planning units selects a combination of operation units which provide the overall output required for the planning period, and based on operation costs depending on the outputs of the operation units, a process is repeated to generate the operation plan, the process including: selection of the operation unit belonging to the combination of operation units; and adjustment of the output setting for the selected operation unit by the planning unit paired with the selected operation unit.

Abstract: According to one embodiment, a diagnostic device includes an anomaly diagnoser and a graph creator. The anomaly diagnoser performs anomaly diagnosis based on first measured data. The graph creator determines parameter information for graph production in accordance with a result of the anomaly diagnosis and creates a first graph from the first measured data based on the parameter information.

Abstract: A biomarker search device includes a gene variation group selector which generates combinations by combining biomolecule groups which hold interaction information, specifies gene variations associated with biomolecules included in the combinations based on mapping data calculates first evaluation values of the specified gene variations with respect to the biomolecules associated with the specified gene variations, respectively, based on influence data and specifies a typical gene variation group from the specified gene variations based on the first evaluation values, and an evaluator which calculates a second evaluation value with respect to the typical gene variation group based on gene variation data which holds genotype data of a case group afflicted with a specific disease and genotype data of a control group and selects the typical gene variation group from the typical gene variation groups based on the second evaluation values.

Abstract: According to one embodiment, a genotype estimation device includes: an acquirer configured to acquire a clustering strength of genotype data of a plurality of specimens including an unknown specimen whose genotype is not known and known specimens whose genotypes are known; and an estimator configured to estimate the genotype of the unknown specimen on the basis of the genotype data in response to the clustering strength being larger than a first threshold, and output an estimation result.

Abstract: A charging management device has a first acquisition circuitry which acquires EV information necessary to charge each EV car in a charging station, a second acquisition circuitry which acquires stationary storage battery information, a third acquisition circuitry which acquires supply power information from a system power, a fourth acquisition circuitry which acquires charger information, a preliminary charging amount calculation circuitry which calculates a preliminary charging amount representing a charging amount of each EV car, an EV charging model storage circuitry which stores an EV charging model outputting a maximum charging amount of the EV car, and a charging condition determination circuitry which determines a charging condition that the charging time of each EV car and the maximum output power of the charger are within certain ranges, respectively, and the difference between the maximum charging amount of each EV car and the preliminary charging amount is further reduced.