Asset maintenance prediction using infrared and regular images

A computer program product for predicting a time to a failure condition of an asset, the computer program product comprising:

• one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
• program instructions to receive a plurality of historical image pairs of an asset, including image pairs of a failure condition of the asset, wherein respective image pairs include an infrared image and a corresponding regular image;
• program instructions to receive a first model trained to reconstruct respective images of an image pair of the asset to a healthy condition status of the asset;
• program instructions to generate a similarity coefficient between a historical image pair and a reconstruction of the historical image pair by the first model, for the plurality of historical image pairs, respectively, wherein the historical image pair includes a timestamp of a capture of the historical image pair;
• program instructions to receive a second model trained to predict a time duration until a failure condition of the asset occurs, based on the similarity coefficients and a timestamp of a capture of the plurality of historical image pairs, respectively;
• in response to receiving a real-time image pair of the asset, program instructions to generate real-time similarity coefficients between the real-time image pair and the real-time image pair reconstructed by the first model, wherein the real-time image pair includes a timestamp of a capture of the real-time image pair;
• and
• program instructions to compute a predicted time to the failure condition of the asset, based on a correlation between the similarity coefficients of the real-time image pair and the timestamp of the capture of the real-time image pair, and a historical image pair of the plurality of historical image pairs with corresponding similarity coefficients, and a time delta determined from the timestamp of the capture of the real-time image pair and a timestamp of the failure condition of the asset subsequent to the historical image pair with the corresponding similarity coefficients.

A computer system for predicting a time to a failure condition of an asset, the computer system comprising:

• one or more computer processors;
• one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
• program instructions to receive a plurality of historical image pairs of an asset, including image pairs of a failure condition of the asset, wherein respective image pairs include an infrared image and a corresponding regular image;
• program instructions to receive a first model trained to reconstruct respective images of an image pair of the asset to a healthy condition status of the asset;
• program instructions to generate a similarity coefficient between a historical image pair and a reconstruction of the historical image pair by the first model, for the plurality of historical image pairs of the asset, respectively, wherein the historical image pair includes a timestamp of a capture of the historical image pair;
• program instructions to receive a second model trained to predict a time duration until a failure condition of the asset occurs, based on the similarity coefficients and a timestamp of a capture of the plurality of historical image pairs, respectively;
• in response to receiving a real-time image pair of the asset, program instructions to generate real-time similarity coefficients between the real-time image pair and the real-time image pair reconstructed by the first model, wherein the real-time image pair includes a timestamp of the capture of the real-time image pair;
• and
• program instructions to compute a predicted time to the failure condition of the asset, based on a correlation between the similarity coefficients of the real-time image pair and the timestamp of the capture of the real-time image pair, and a historical image pair of the plurality of historical image pairs of the asset with corresponding similarity coefficients, and a time delta determined from the timestamp of the capture of the real-time image pair and a timestamp of the failure condition of the asset subsequent to the historical image pair with the corresponding similarity coefficients.