A computer-implemented method for training a software infrastructure based on machine-learning techniques to analyse data obtained from a instrumental examination of objects of a predetermined type, where each of the objects has been obtained by splitting a product into smaller pieces, wherein the software infrastructure receives, for each object in a training set, training input data comprising the data obtained from the instrumental examination and training output data comprising information on the characteristics of interest of the training object, wherein the information on the characteristics of interest is, at least in part, information that has been obtained from the results of a tomographic examination of the product from which the training object was obtained, and wherein the software infrastructure processes, through its own training unit, the training input data and the training output data for each training object in order to set internal processing parameters for the software infrastructure which correlate the training input data to the training output data.

A blade storage array is detachably mountable with a tissue log cutting saw. The saw has a cutting arm with a tool holder receptacle adapted and configured to hold a circular saw blade for the saw. The array has a plurality of storage units. Each storage unit is adapted and configured to store a circular saw blade for the saw. Each storage unit has a tool holder receptacle adapted and configured to hold a circular saw blade. Each storage unit is adapted and configured to move perpendicularly to the saw blade center axis.

A blade storage array is detachably mountable with a tissue log cutting saw. The saw has a cutting arm with a tool holder receptacle adapted and configured to hold a circular saw blade for the saw. The array has a plurality of storage units. Each storage unit is adapted and configured to store a circular saw blade for the saw. Each storage unit has a tool holder receptacle adapted and configured to hold a circular saw blade. Each storage unit is adapted and configured to move perpendicularly to the saw blade center axis.

A method for establishing a posteriori a match between a piece of wood and a log from which the piece of wood has been obtained, comprising the following operating steps of performing a tomographic scan of the wooden log, of calculating or selecting a log cutting pattern, of defining, starting with the tomographic information available, one or more virtual individualising characteristics which are linked to the distribution and/or size of physical characteristics of the log inside and/or on the surface of the self-same virtual piece of wood, of saving them in a database, together with information about the identity of the log, of dividing the log into real pieces of wood according to the cutting pattern, of acquiring real information about the distribution and/or size of physical characteristics of the log inside and/or on the surface of a real piece of wood and of defining corresponding real individualising characteristics to be compared with virtual individualising characteristics saved and of identifying an origin of the real piece of wood based on the information about the identity of the log which is saved together with the virtual individualising characteristics which match the real individualising characteristics.

A method for establishing a posteriori a match between a piece of wood and a log from which the piece of wood has been obtained, comprising the following operating steps of performing a tomographic scan of the wooden log, of calculating or selecting a log cutting pattern, of defining, starting with the tomographic information available, one or more virtual individualising characteristics which are linked to the distribution and/or size of physical characteristics of the log inside and/or on the surface of the self-same virtual piece of wood, of saving them in a database, together with information about the identity of the log, of dividing the log into real pieces of wood according to the cutting pattern, of acquiring real information about the distribution and/or size of physical characteristics of the log inside and/or on the surface of a real piece of wood and of defining corresponding real individualising characteristics to be compared with virtual individualising characteristics saved and of identifying an origin of the real piece of wood based on the information about the identity of the log which is saved together with the virtual individualising characteristics which match the real individualising characteristics.

In various embodiments, a scanner optimizer system may generate a virtual model of a predicted flitch based on a 3D model of a log/cant and a cut solution for the log/cant. The scanner optimizer system may compare a virtual model of an actual flitch to virtual models of predicted flitches by comparing data points at a fixed elevation relative to one or both faces of the models. Based on the comparisons, the scanner optimizer system may identify the source log from which the actual flitch was cut. In addition, the scanner optimizer system may identify the saw used to cut the actual flitch, and/or other relevant information, and use the additional information to monitor and adjust the saws and other equipment. Embodiments of corresponding apparatuses and methods are also described.

A sawmill for tree logs includes a rocking carriage to pick up fresh logs and feed them into the path of a saw blade, as well further provisions relating to improvements to infeed systems for the fresh logs, as well as to, outflow systems for transfer of sawn-off product to a production line conveyor or the like for further processing to downline processes after the first saw cuts on the fresh logs.

Embodiments provide methods, apparatuses, and systems for cutting wood workpieces, such as logs and cants, into desired products. In various embodiments, after a log is chipped into a cant, the cant may be scanned and re-optimized based on the new scan data and information about the source log, such as simulated orientation parameters, a 3D model, and/or potential cut solutions. In other embodiments, data from multiple sensor types may be used in combination to detect splits in logs, cants, or both. Optionally, re-optimization and split detection techniques may be used in combination to improve wood volume recovery, value, and/or throughput speed.

A computer-implemented method for training a software infrastructure based on machine-learning techniques to analyse data obtained from a instrumental examination of objects of a predetermined type, where each of the objects has been obtained by splitting a product into smaller pieces, wherein the software infrastructure receives, for each object in a training set, training input data comprising the data obtained from the instrumental examination and training output data comprising information on the characteristics of interest of the training object, wherein the information on the characteristics of interest is, at least in part, information that has been obtained from the results of a tomographic examination of the product from which the training object was obtained, and wherein the software infrastructure processes, through its own training unit, the training input data and the training output data for each training object in order to set internal processing parameters for the software infrastructure which correlate the training input data to the training output data.

A blade storage array is detachably mountable with a tissue log cutting saw. The saw has a cutting arm with a tool holder receptacle adapted and configured to hold a circular saw blade for the saw. The array has a plurality of storage units. Each storage unit is adapted and configured to store a circular saw blade for the saw. Each storage unit has a tool holder receptacle adapted and configured to hold a circular saw blade. Each storage unit is adapted and configured to move perpendicularly to the saw blade center axis.