Method for controlling the quality of industrial processes, in particular laser-welding processes

A system for controlling quality of a manufacturing process for recognizing defects in result of a production, comprising:

• means for detecting one or more process parameters;
• and
• means for processing the signals issued by said detecting means,
• wherein said processing means are means for controlling the quality of the manufacturing process such that:
• said processing means are means for acquiring, by detecting one or more quantity of the production of said manufacturing process, one or more real signals produced by a machine involved in the manufacturing process, where the one or more real signals are indicative of the quality of said manufacturing process;
• said processing means are means for providing one or more reference signals corresponding to said one or more real signals and indicative of a good-quality process for the manufacturing process;
• said processing means are means for obtaining a transformed signal from said reference signal;
• for obtaining a transformed signal from said real signal;
• for converting each of the transformed real signal and the transformed reference signal into a respective vector of energies, where the vector of energies comprises an integer number k of frequency values;
• and
• said processing means are means for comparing said one or more reference signals with said one or more real signals in order to identify the defects in the result of the production,
• wherein said comparison means are means for comparing said vector of energies of said transformed reference signal with said vector of energies of said transformed real signal and selecting frequency values among said k frequency values on the basis of said comparison, respectively, for extracting corresponding time-frequency distributions for said selected frequency values, means for calculating energies of said time-frequency distributions, and means for comparing the energies of said time-frequency distributions with threshold values in order identify energy values associated with said defects, and the corresponding time coordinates of said defects.

An apparatus which controls quality of a manufacturing process and which recognizes defects in result of a production, the apparatus comprising:

• a memory which stores process parameters detected by at least one sensor and software modules that process the detected parameters and that control the quality of the manufacturing process;
• and
• a processor which executes the software modules,
• wherein the software modules comprise:
• a module configured for acquiring, by detecting one or more quantity of the production of said manufacturing process, one or more real signals produced by a machine involved in the manufacturing process, where the one or more real signals are indicative of the quality of said manufacturing process;
• a module configured for one or more reference signals corresponding to said one or more real signals and indicative of a good-quality process for the manufacturing process;
• a module configured for obtaining a transformed signal from said reference signal;
• a module configured for obtaining a transformed signal from said real signal;
• a module configured for converting each of the transformed real signal and the transformed reference signal into a respective vector of energies, where the vector of energies comprises an integer number k of frequency values;
• and
• a module configured for comparing said one or more reference signals with said one or more real signals in order to identify the defects in the result of the production, wherein the comparing module is further configured for:
• comparing said vector of energies of said transformed reference signal with said vector of energies of said transformed real signal and for selecting frequency values among said k frequency values on the basis of said comparison, respectively, for extracting corresponding time-frequency distributions for said selected frequency values;
• calculating energies of said time-frequency distributions;
• and
• comparing the energies of said time-frequency distributions with threshold values in order identify energy values associated with said defects, and the corresponding time coordinates of said defects.

A system for controlling quality of a manufacturing process for recognizing defects in result of a production, comprising:

• sensor configured to detect one or more process parameters;
• and
• an electronic control and processing unit configured to process the signals issued by said sensor and configured to control the quality of the manufacturing process,
• wherein the processing unit is configured to acquire, by detecting one or more quantity of the production of said manufacturing process, one or more real signals produced by a machine involved in the manufacturing process, where the one or more real signals are indicative of the quality of said manufacturing process;
• wherein the processing unit is configured to provide one or more reference signals corresponding to said one or more real signals and indicative of a good-quality process for the manufacturing process;
• wherein the processing unit is configured to obtain a transformed signal from said reference signal;
• to obtain a transformed signal from said real signal;
• to convert each of the transformed real signal and the transformed reference signal into a respective vector of energies, where the vector of energies comprises an integer number k of frequency values;
• and
• wherein the processing unit is configured to compare said one or more reference signals with said one or more real signals in order to identify the defects in the result of the production, wherein the processing unit is configured to compare by:
• comparing said vector of energies of said transformed reference signal with said vector of energies of said transformed real signal and selecting frequency values among said k frequency values on the basis of said comparison, respectively, for extracting corresponding time-frequency distributions for said selected frequency values;
• calculating energies of said time-frequency distributions;
• and
• comparing the energies of said time-frequency distributions with threshold values in order identify energy values associated with said defects, and the corresponding time coordinates of said defects.