Method of analyzing factors affecting product quality and adjusting molding conditions for injection molding machine

A method of analyzing factors affecting product quality of an injection molding machine, comprising the steps of:

• (a) detecting data of plural conditions related to an injection molding operation for each predetermined molding cycle and storing the detected data as plural series of data for respective conditions:
• (b) obtaining correlation coefficients representing data variation correlations of said plural conditions to create a correlation matrix, based on the respective series of data stored in said step (a);
• (c) obtaining eigen vectors of two principal components for each one of said plural conditions by performing a principal component analysis on said correlation matrix created in said step (b);
• (d) plotting points representing said plural conditions with the eigen vectors of said two principal components related with each orthogonal axis;
• (e) analyzing the quality of products based on positions of the points representing said plural conditions plotted in said step (d).

A method of adjusting molding conditions for an injection molding machine, comprising the steps of:

• (a) detecting data of plural conditions related to an injection molding operation for each predetermined molding cycle and storing the detected data as plural series of data for respective conditions;
• (b) obtaining correlation coefficients representing data variation correlation of said plural conditions to create a correlation matrix, based on the respective series of data stored in said step (a);
• (c) obtaining eigen vectors of two principal components for each of said conditions by performing a principal component analysis on the correlation matrix created in said step (b), and plotting points representing said plural conditions with the eigen vectors of said two principal components related with each orthogonal axis;
• (d) grouping points located close to one another in the points plotted in said step (c);
• and
• (e) adjusting one of the plural conditions represented by the points grouped in said step (d) to stabilize the data of the one condition and to thereby stabilize the data of all other conditions in the same group.

A method of adjusting molding conditions for an injection molding machine, comprising the steps of:

• (a) detecting data of plural conditions related to an injection molding operation for each predetermined molding cycle and storing the detected data as plural series of data for respective conditions;
• (b) obtaining correlation coefficients representing data variation correlation of the plural conditions to create a correlation matrix based on the respective series of data stored in said step (a);
• (c) obtaining eigen vectors of two principal components for each of said conditions by performing a principal component analysis on the correlation matrix created in said step (b), and plotting points representing said plural conditions with the eigen vectors of said two principal components related with each orthogonal axis;
• (d) grouping points located close to one another in the points plotted in said step (c);
• and
• (e) adjusting one of the plural conditions represented by the points grouped in said step (d) to stabilize data of the conditions in a group which is located in origin symmetry with respect to a group containing one condition on said rectangular coordinate system and to thereby stabilize data of said one condition. (f) stabilizing data of one of the conditions represented by the points grouped in said step (d) by adjusting the conditions belonging to a group which is located in origin symmetry with respect to a group containing said one condition on said rectangular coordinate system.

A method of controlling molding conditions for an injection molding machine, comprising the steps of:

• (a) detecting data of plural conditions related to an injection molding operation for each predetermined molding cycle and storing the detected data as plural series of data for respective conditions, every time when a molding condition related to the injection molding operation is adjusted:
• (b) obtaining correlation coefficients representing data variation correlation of said plural conditions to create a correlation matrix based on the respective series of data stored in said step (a);
• (c) obtaining eigen vectors of two principal components for each of said conditions by performing a principal component analysis on the correlation matrix created in said step (b), and plotting points representing said plural conditions with the eigen vectors of said two principal components related with each orthogonal axis;
• (d) adjusting said molding conditions based on the points plotted in said step (c), and repeatedly executing the foregoing steps until data of all conditions or data of a particular condition converges.

A method of adjusting molding conditions for an injection molding machine, comprising the steps of:

• (a) detecting data of plural conditions related to an injection molding operation for each predetermined molding cycle to store the detected data as plural series of data, and obtaining a standard deviation and a mean value for each data column, every time when any molding condition related to the injection molding operation is adjusted;
• (d) obtaining correlation coefficients representing data variation correlation of said plural conditions to create a correlation matrix based on the respective series of data stored in said step (a);
• (c) obtaining eigen vectors of two principal components for each of said conditions by performing a principal component analysis on the correlation matrix created in said step (b), and plotting points representing said plural conditions with the eigen vectors of said two principal components related with each orthogonal axis;
• (d) adjusting the molding conditions based on the points plotted in said step (c), and repeatedly executing the foregoing steps until the standard deviation or value obtained by dividing the standard deviation by the mean value of data of all the conditions or a particular condition converge below a set value.

A method of adjusting molding conditions for an injection molding machine, comprising the steps of:

• (a) detecting data of plural conditions related to an injection molding operation for each predetermined molding cycle and storing the detected data as plural series of data for respective conditions, every time when a molding condition related to the injection molding operation is adjusted;
• (b) obtaining correlation coefficients representing data variation correlation of said plural conditions to create a correlation matrix based on the respective series of data stored in said step (a);
• (c) obtaining eigen vectors of two principal components for each of said conditions by performing a principal component analysis on the correlation matrix created in said step (b), and plotting points representing said plural conditions with the eigen vectors of said two principal components related with each orthogonal axis;
• (d) adjusting the molding conditions based on the points plotted in said step (c), and repeatedly executing the foregoing steps until the rate of contribution of all principal components or of a particular principal component converges below a set value.

A method of adjusting molding conditions for an injection molding machine, comprising the steps of:

• (a) detecting data of plural conditions related to an injection molding operation for each predetermined molding cycle and storing the detected data as plural series of data for respective conditions, every time when a molding condition related to the injection molding operation is adjusted;
• (b) obtaining correlation coefficients representing data variation correlation of said plural conditions to create a correlation matrix based on the respective series of data stored in said step (a);
• (c) obtaining eigen vectors of two principal components for each of said conditions by performing a principal component analysis on the correlation matrix created in said step (b), and plotting points representing said plural conditions with the eigen vectors of said two principal components related with each orthogonal axis;
• (d) repeatedly executing said steps (a), (b) and (c) until the individual points plotted in said step (c) are grouped in the vicinity of the origin of the rectangular coordinate system.