Abstract: A weight estimation apparatus 1 includes: an impulsive force calculation unit 2 calculating an impulsive force using an acceleration response indicating vibration generated in a structure by the moving object (vehicle 27) moving through the structure, and a weight estimation unit 3 estimating a weight of the moving object using the impulsive force.

Abstract: A structure diagnosis apparatus 1 for diagnosing a state of a structure in which there is a small change in the natural frequency includes: a natural vibration extraction unit 2 configured to acquire, from a plurality of sensors 21 that a structure is provided with 20, vibration information indicating vibration generated in the structure 20, and extracting natural vibration using the vibration information; a spectral shape extraction unit 3 configured to extract spectral shape information indicating a shape of a spectrum using the natural vibration; an index calculation unit 4 for calculating an index indicating a relationship between the spectral shape information and reference spectral shape information that is a preset reference; and a state estimation unit 5 for estimating the state of the structure based on the index.

Abstract: Provided are a sound model generation device and the like that make it possible to more easily generate a sound model capable of distinguishing sound events using a plurality of features. A concatenating unit concatenates a plurality of features of sound signals that are learning data and generates a concatenated feature. A learning unit learns the generated concatenated feature for generating a sound model for distinguishing a sound event from a sound signal.

Abstract: A data calculation device including a high-level posterior distribution data calculator for calculating data indicating a posterior distribution of parameter values of a high-level model that simulates a subject, based on target data for outputs from the high-level model; and a low-level posterior distribution data calculator for calculating, for a low-level model that simulates a portion of the subject and that outputs parameter values of the high-level model, data indicating a posterior distribution of parameter values of the low-level model, based on the data indicating a posterior distribution of parameter values of the high-level model.

Abstract: A state estimation apparatus 1 includes an acquisition unit 2 that acquires deterioration information indicating a deterioration state of each structural object and a learning unit 3 that learns common information that is common between pieces of the deterioration information and estimation index information that is used for estimating a deterioration state of a target structural object, using the deterioration information as input.

Abstract: A damage diagnosis device is provided with: a detection unit for detecting that, immediately after a vehicle crossing a bridge has exited from the bridge, another vehicle is not crossing the bridge; a determination unit for determining whether the weight of the vehicle satisfies a criterion; and a diagnosis unit that, when the detection unit has detected that no other vehicle is crossing the bridge and the determination unit has determined that the weight of the vehicle satisfies the criterion, diagnoses damage to the bridge on the basis of information representing free vibration generated in the bridge due to the crossing of the vehicle, thereby improving the precision of diagnosis when damage to a bridge is diagnosed on the basis of information representing free vibration generated in the bridge due to the crossing of a vehicle.

Abstract: Provided are a sound model generation device and the like that make it possible to more easily generate a sound model capable of distinguishing sound events using a plurality of features. A concatenating unit concatenates a plurality of features of sound signals that are learning data and generates a concatenated feature. A learning unit learns the generated concatenated feature for generating a sound model for distinguishing a sound event from a sound signal.

Abstract: A model generation apparatus according to the present invention includes: a data generating unit configured to generate, from actual data of acoustic data, replacement data obtained by replacing a predetermined value in the actual data with a replacement value that is a different value from the predetermined value; and a learning unit configured to learn by using the actual data of the acoustic data and the replacement data, and generate a model for removing noise from predetermined acoustic data.

Abstract: A weight estimation apparatus 1 includes: an impulsive force calculation unit 2 calculating an impulsive force using an acceleration response indicating vibration generated in a structure by the moving object (vehicle 27) moving through the structure, and a weight estimation unit 3 estimating a weight of the moving object using the impulsive force.

Abstract: A state estimation apparatus 1 includes an acquisition unit 2 that acquires deterioration information indicating a deterioration state of each structural object and a learning unit 3 that learns common information that is common between pieces of the deterioration information and estimation index information that is used for estimating a deterioration state of a target structural object, using the deterioration information as input.

Abstract: A bearing diagnosis apparatus 1 that accurately diagnoses the state of a bearing includes: an extraction unit 2 configured to extract a feature amount using first index information indicating a response of a structure 21 to an external force and second index information indicating a response, to the external force, of a bearing 23 provided to the structure 21; and an assessment unit 3 configured to assess the state of the bearing 23 based on the extracted feature amount.

Abstract: A structure diagnosis apparatus 1 for diagnosing a state of a structure in which there is a small change in the natural frequency includes: a natural vibration extraction unit 2 configured to acquire, from a plurality of sensors 21 that a structure is provided with 20, vibration information indicating vibration generated in the structure 20, and extracting natural vibration using the vibration information; a spectral shape extraction unit 3 configured to extract spectral shape information indicating a shape of a spectrum using the natural vibration; an index calculation unit 4 for calculating an index indicating a relationship between the spectral shape information and reference spectral shape information that is a preset reference; and a state estimation unit 5 for estimating the state of the structure based on the index.

Abstract: A diagnosis apparatus 1 including: a target vibration information generation unit 2 that generates pieces of target vibration information; a comparative relationship information generation unit 3 that generates pieces of comparative relationship information indicating relationships among the pieces of target vibration information, or the pieces of comparative relationship information indicating relationships among pieces of reference vibration information and the pieces of target vibration information, the pieces of reference vibration information indicating vibrations in the target mode among vibrations that are measured in a reference period; and a diagnosis unit 5 that diagnoses that a change has occurred in the structure 20 between the diagnosis period and the reference period based on a result of comparison between a distribution of pieces of reference relationship information and the distribution that has been calculated in relation to the pieces of comparative relationship information.

Abstract: A diagnosis apparatus 1 includes: a generation unit 2 configured to acquire vibration information indicating vibration produced in a structure 20 from a plurality of sensors 21 provided to the structure 20, and to generate, using the vibration information, natural vibration mode information indicating a natural vibration mode shape; an occurrence rate calculation unit 3 configured to calculate a rate of occurrence of a normal natural vibration mode shape based on the number of times vibration was applied to the structure 20 and the number of times the normal natural vibration mode shape was generated when the vibration was applied; and a diagnosis unit 4 configured to diagnose whether or not repair and reinforcement performed on the structure were effective based on the rate of occurrence and a reference value.

Abstract: A diagnosis apparatus 1 including: a target vibration information generation unit 2 that generates pieces of target vibration information; a comparative relationship information generation unit 3 that generates pieces of comparative relationship information indicating relationships among the pieces of target vibration information, or the pieces of comparative relationship information indicating relationships among pieces of reference vibration information and the pieces of target vibration information, the pieces of reference vibration information indicating vibrations in the target mode among vibrations that are measured in a reference period; and a diagnosis unit 5 that diagnoses that a change has occurred in the structure 20 between the diagnosis period and the reference period based on a result of comparison between a distribution of pieces of reference relationship information and the distribution that has been calculated in relation to the pieces of comparative relationship information.

Abstract: A damage diagnosis device is provided with: a detection unit for detecting that, immediately after a vehicle crossing a bridge has exited from the bridge, another vehicle is not crossing the bridge; a determination unit for determining whether the weight of the vehicle satisfies a criterion; and a diagnosis unit that, when the detection unit has detected that no other vehicle is crossing the bridge and the determination unit has determined that the weight of the vehicle satisfies the criterion, diagnoses damage to the bridge on the basis of information representing free vibration generated in the bridge due to the crossing of the vehicle, thereby improving the precision of diagnosis when damage to a bridge is diagnosed on the basis of information representing free vibration generated in the bridge due to the crossing of a vehicle.

Abstract: The present invention provides a damage detection apparatus, a damage detection method, and a damage detection program that can detect damage in a support by measuring vibration of a supported object. The damage detection apparatus that detects damage in a structure including a supported object and a support according to one example embodiment of the present invention includes a dominant frequency acquisition unit that acquires a dominant frequency from vibration information at a plurality of points on the supported object; a rigid body vibration identification unit that identifies rigid body vibration information on the structure from the acquired dominant frequency; and a damage determination unit that determines damage in the support based on the identified rigid body vibration information.

Abstract: An abnormality diagnosis apparatus including: a feature amount calculation unit 2 configured to perform, on mode vectors generated based on vibration of a structure 20 measured by sensors 21, normalization of amplitude components and normalization for removing an initial phase from phase components, and calculate amplitude feature amounts corresponding to the amplitude components and phase feature amounts corresponding to the phase components; and an abnormality detection unit 3 configured to specify an abnormality in the structure 20 based on the amplitude feature amounts and the phase feature amounts.

Abstract: A damage diagnosing device includes: a generating unit which generates second vibration characteristic information including a characteristic value of an increase characteristic opposite to an amplitude of oscillation exhibited by first vibration characteristic information, relating to a structure including a supporting portion and a supported portion supported at a support point by the supporting portion; a calculating unit which calculates a degree that values indicated by the first vibration characteristic information and the second vibration characteristic information have changed from reference values relating to the first vibration characteristic information and the second vibration characteristic information as a result of damage that has occurred in the structure; and a diagnosing unit which diagnoses the damage on the basis of the degree of change, to more accurately diagnose damage that has occurred in a structure having a supporting portion and a supported portion supported at a support point by th

Abstract: A vibration determination device according to an exemplary aspect of the present invention includes: at least one memory storing a set of instructions; and at least one processor configured to execute the set of instructions to: determine, based on a plurality of feature values representing features of a vibration of a structure, whether the vibration of the structure is a standard vibration; and detect, when it is not determined that the vibration of the structure is the standard vibration, an outlier included in the plurality of feature values; determine, based on the plurality of feature values other than the detected outlier, whether the vibration of the structure is the standard vibration; and output whether the vibration of the structure is the standard vibration.