State detection apparatus

A state detection apparatus comprising:

• a plurality of sensors;
• and
• a computation unit in which data detected by the plurality of sensors is output, wherein
• the computation unit includes a processing apparatus configured to execute data processing comprising
• transforming data of digitized time-series signals of the plurality of sensors into data relating to spectral intensity;
• generating a pseudo image based on data relating to the spectral intensity;
• analyzing the pseudo image;
• and
• outputting a classification result of the state of a facility, and
• the processing apparatus is further configured to perform the transforming by performing a discrete Fourier transform or a fast Fourier transform on the data of time-series signals, then converting values corresponding to the spectral intensity into a non-linear expression, and then performing quantization that reduces an expression word length of the spectral intensity.

A state detection apparatus comprising:

• a plurality of sensors;
• and
• a computation unit in which data detected by the plurality of sensors is output, wherein
• the computation unit includes a processing apparatus configured to execute data processing comprising
• transforming data of a digitized time-series signals of the plurality of sensors into data relating to spectral intensity;
• generating a pseudo image based on data relating to the spectral intensity;
• analyzing the pseudo image;
• and
• outputting a classification result of the state of a facility,
• the processing apparatus is configured to perform the transforming by discrete Fourier transform or fast Fourier transform,
• the processing apparatus is further configured to analyze the pseudo image by a convolutional neural network,
• the state detection apparatus comprises a camera which acquires a camera image and an input apparatus used by the user, and
• the processing apparatus is further configured to process the camera image selected by the user or the pseudo image, by the convolutional neural network.

A state detection apparatus comprising:

• a sensor;
• and
• a computation unit in which data detected by the sensor is output, wherein
• the computation unit includes a processing apparatus configured to execute data processing comprising
• transforming data of a digitized time-series signals of the plurality of sensors into data relating to spectral intensity;
• generating a pseudo image based on data relating to the spectral intensity;
• analyzing the pseudo image;
• and
• outputting a classification result of the state of a facility, and
• the processing apparatus generates the pseudo image in which a plurality of rows of data relating to the spectral intensity corresponding to the sensor are arranged.

A state detection apparatus comprising:

• a plurality of sensors;
• and
• a computation unit in which data detected by the plurality of sensors is output, wherein
• the computation unit includes a processing apparatus configured to execute data processing comprising
• transforming data of a digitized time-series signals of the plurality of sensors into data relating to spectral intensity;
• generating a pseudo image based on data relating to the spectral intensity;
• analyzing the pseudo image;
• and
• outputting a classification result of the state of a facility, and
• the processing apparatus is further configured to
• perform the transforming, by performing an orthogonal transformation on the time-series signals, then converting the values corresponding to spectral intensity into a non-linear expression, and then performing quantization that reduces an expression word length of spectral intensity, and
• perform the orthogonal transformation using at least one of a discrete cosine transform, a discrete sine transform, a discrete Fourier transform that is slower than the fast Fourier transform, and a Walsh-Hadamard transform.

A state detection apparatus comprising:

• a plurality of sensors;
• and
• a computation unit in which data detected by the plurality of sensors is output, wherein
• the computation unit includes a processing apparatus configured to execute data processing comprising
• transforming data of a digitized time-series signals of the plurality of sensors into data relating to spectral intensity;
• generating a pseudo image based on data relating to the spectral intensity;
• analyzing the pseudo image;
• and
• outputting a classification result of the state of a facility, and
• the processing apparatus is further configured to execute the transforming using a combination of at least two of a discrete cosine transform, a discrete sine transform, a discrete Fourier transform, a fast Fourier transform, and a Walsh-Hadamard transform.

A state detection apparatus comprising:

• a plurality of sensors;
• and
• a computation unit in which data detected by the plurality of sensors is output, wherein
• the computation unit includes a processing apparatus configured to execute data processing comprising
• transforming data of a digitized time-series signals of the plurality of sensors into data relating to spectral intensity;
• generating a pseudo image based on data relating to the spectral intensity;
• analyzing the pseudo image;
• and
• outputting a classification result of the state of a facility,
• the state detection apparatus includes an allocation table that stores the allocation of orthogonal transforms used for the transformation, and
• the processing apparatus is further configured to execute the transforming using at least one of a discrete cosine transform, a discrete sine transform, a discrete Fourier transform, a fast Fourier transform, and a Walsh-Hadamard transform, based on the allocation table.

A system comprising:

• a state detection apparatus that includes a plurality of sensors and a computation unit in which data detected by the plurality of sensors is output, wherein the computation unit includes a processing apparatus configured to execute data processing comprising
• transforming data of digitized time-series signals of the plurality of sensors into data relating to spectral intensity;
• generating a pseudo image based on data relating to the spectral intensity;
• analyzing the pseudo image;
• and
• outputting a classification result of the state of a facility;
• and
• a computer configured to determine a combination of an orthogonal transform used for the transformation and an image analysis processing algorithm based on a detection accuracy and resource information of the state detection apparatus, and to configure the state detection apparatus according to the result of the determination, or to send an instruction to configure the state detection apparatus according to the result of the determination.