A computer implemented method comprises the steps of: providing a user interface to a computer terminal; providing a welding machine interface (252) to a welding machine (22; 31) which is equipped with a set of sensors having a power supply sensor (221; 311) configured to sense a power supplied by the welding machine (22; 31) to set a connector to an object in runtime; obtaining a threshold performance metric data signal representing threshold product performance metric predefined via the user interface; obtaining a power supply data signal from the welding machine (22; 31) via the welding machine interface (252), which power supply data signal represents the sensed power supplied by the welding machine (22; 31) to set the connector to the object; applying a machine learning model to the power represented by the obtained power supply data signal such that the machine learning model calculates a model product performance metric, wherein the machine learning model is specifically pre trained with training power sensed by the power supply sensor (221; 311) of the set of sensors of the welding machine (22; 31) and measured product performance metrics; comparing the calculated model product performance metric to the threshold product performance metric represented by the threshold performance metric data signal; and generating a non-consistency data signal when the calculated product performance metric does not comply with the threshold product performance metric.

Disclosed is an automated method (54) which includes directing rays from a source (34) to a tube (38) disposed between relatively movable first and second sealing plates (20, 32), capturing an image (70) of at least a portion of the tube (38) by an image capturing device (26), and transferring the captured image (70) to a processing device (24). The method (54) also includes determining a plurality of 26 tube parameters by the processing device (24) based on the captured image (70), using an image processing technique and determining a plurality of sealing parameters from a database (44) by the processing device (24) based on the determined plurality of tube parameters. Additionally, the method (54) includes controlling the drive unit (22) and a heater (36) by the processing device (24) influenced by the determined plurality of sealing parameters, to respectively compress the tube (36)and perform heat sealing of the tube (38).

A system for controlled induction welding of at least one weld seam area (A) of at least two surfaces of at least one workpiece is provided. The system comprises an inductor configured to be arranged in conjunction with the at least one workpiece, a processing means configured to generate an electromagnetic field by applying an alternating voltage to the inductor so as to inductively heat at least one of the surfaces so that the weld seam area (A) is welded together, simultaneously measure at least one parameter (P) of the at least one workpiece at least based on the generated electromagnetic field, detect a change of the at least one parameter (P), and determine a temperature estimation of the at least one workpiece based on said detected change.

Disclosed is an automated method (54) which includes directing rays from a source (34) to a tube (38) disposed between relatively movable first and second sealing plates (20, 32), capturing an image (70) of at least a portion of the tube (38) by an image capturing device (26), and transferring the captured image (70) to a processing device (24). The method (54) also includes determining a plurality of tube parameters by the processing device (24) based on the captured image (70), using an image processing technique and determining a plurality of sealing parameters from a database (44) by the processing device (24) based on the determined plurality of tube parameters. Additionally, the method (54) includes controlling the drive unit (22) and a heater (36) by the processing device (24) influenced by the determined plurality of sealing parameters, to respectively compress the tube (36) and perform heat sealing of the tube (38).

A method and system for the ultrasonic non-destructive testing of joints in plastic pipes using A-scans. A hand-held ultrasonic transducer is used to perform an A-scan and a comparison made on a response from the interface region of the joint used to determine a quality of the joint. Levels of result can provide a binary output to give an indication of whether or not a defect is present in the joint. Comparison techniques are described. Tests for coupling efficiency and performance are described making the system useable by an unskilled technician. The system finds application in fault detection on electro-fusion welds in plastic pipe joints.

A computer implemented method comprises the steps of: providing a user interface to a computer terminal; providing a welding machine interface (252) to a welding machine (22; 31) which is equipped with a set of sensors having a power supply sensor (221; 311) configured to sense a power supplied by the welding machine (22; 31) to set a connector to an object in runtime; obtaining a threshold performance metric data signal representing threshold product performance metric predefined via the user interface; obtaining a power supply data signal from the welding machine (22; 31) via the welding machine interface (252), which power supply data signal represents the sensed power supplied by the welding machine (22; 31) to set the connector to the object; applying a machine learning model to the power represented by the obtained power supply data signal such that the machine learning model calculates a model product performance metric, wherein the machine learning model is specifically pre trained with training power sensed by the power supply sensor (221; 311) of the set of sensors of the welding machine (22; 31) and measured product performance metrics; comparing the calculated model product performance metric to the threshold product performance metric represented by the threshold performance metric data signal; and generating a non-consistency data signal when the calculated product performance metric does not comply with the threshold product performance metric.