Monitoring method using kernel regression modeling with pattern sequences

A method for monitoring the condition of an object, comprising:

• obtaining reference data that indicates the normal operational state of the object and in the form of a plurality of learned, equal-size, time sequential and multi-dimensional pattern matrices, each learned, equal-size, time sequential and multi-dimensional pattern matrix having a plurality of reference vectors, each reference vector having reference values representing a plurality of parameters, each of the plurality of learned, equal-size, time sequential and multi-dimensional pattern matrices being equal in size to a corresponding input multi-dimensional pattern array;
• obtaining input data representing a plurality of parameters indicating the current condition of the object, the input data being in the form of a plurality of input multi-dimensional pattern arrays;
• generating, by at least one processor, estimate values based on a calculation that uses the input data and the learned equal-size, time sequential and multi-dimensional pattern matrices to determine a similarity measure between the input data and reference values in the plurality of learned, equal-size, time sequential, and multi-dimensional pattern matrices;
• comparing the estimate values to corresponding input values so that resulting values from the comparison can be used to determine the condition of the object.

A method for monitoring the condition of an object, comprising:

• obtaining reference data that indicates the normal operational state of the object, the reference data being grouped in equal-sized and multi-dimensional training arrays, each of the training arrays being equal in size to a corresponding input multi-dimensional pattern array and each training array including a plurality of time-ordered reference vectors sequenced in time;
• obtaining input data representing a plurality of parameters indicating the current condition of the object, the input data being a plurality of input multi-dimensional pattern arrays;
• generating, by at least one processor, estimate values based on a calculation that uses both the input data and the reference data to determine similarity measures between the input data and the reference data, wherein the estimate values are generated in the form of an estimate matrix having a plurality of time-ordered estimate vectors, each estimate vector having estimate values representing multiple parameters;
• and
• comparing at least one estimate vector for each time period represented by the estimate matrix to the input data so that the resulting values from the comparison can be used to determine the condition of the object.