Please enable JavaScript.

Coggle requires JavaScript to display documents.

Cluster VI: Team 4 - Coggle Diagram

- - - - how does the measuring equipment used affect the total variation?
  - - - how does the operator affect the total variation?
  - - - Acceptable measurement system(
        
        % Tolerance/% Study Variance <10%
        
        % Contribution <1%
        
        variation caused by parts, not equipment or people
      - Acceptable(Marginal)
        
        % Tolerance/% Study Variance between 10%-30%
        
        % Contribution between 1%-9%
        
        Cause depending on criticality of measurement(e.g cost of device, repair & others)
      - Not acceptable
        
        % Tolerance/% Study Variance >30%
        
        % Contribution >9%
        
        Gage system needs improvement
  - - - number of non-overlapping confidence interval that span he range of process variation
        
        higher value= higher chance the tool is able to distinguish one part from another
    - - Acceptable (>5)
      - Not acceptable
        
        <2
        
        measurement system unable to distinguish from one part to another
        
        =2
        
        data only divided into 2 groups (e.g. high/low, yes/no)
        
        =3
        
        data only divided into 3 groups(e.g high/middle/low, yes/maybe/no
  - - - Equipment-> lack of maintenance
      - People
        
        Environment-> lighting of work area(e.g. too dim/bright)
        ->Noisy
        
        Physical-> tired, poor eyesight, muscle cramps
    - - -> Measurement procedures not clear(e.g.how to measure?), improper training of operators in using or reading gauge, Operational definition unclear(no specific way to measure)
    - - increase precision of measurement tool
      - Analyse more distinct parts that represent the whole range of process
- - - - There is significant difference among the measurements of the nozzle (p < 0.05, 0.000 < 0.05).
        
        Possibly due to the characteristics of the nozzle that caused the operators to have different measurements.
    - - There is significant difference among the measurements taken between the two operators (p <= 0.05).
    - - The interaction between the nozzle and operator is not significantly different (p > 0.05, 0.707 > 0.05).
  - - - Acceptable (0.80 < 1)
        
        Suggests that most of the variation was caused by parts, not equipment or operator.
    - - Indicates that the measurement analysis system can be distinguished between parts.
  - - - Acceptable (4.63 < 10)
    - - Acceptable (8.97 < 10)
    - - Acceptable (15 > 5)
  - - - Operator 2 had a lower measurement average and showed more variability than Operator 1.
    - - Statistically out of control
      - Process is not stable
      - Similar mean between two operators
    - - There were low variability for all measurements.
    - - Measurements by Operator 2 were slightly lower that by Operator 1.
    - - Measurements were agreeable between the two operators.
- - - - It access the accuracy of the gauge over the expected operating range.
      - It uses the linear regression model: Y = mX + C, where X is the reference value, Y id the Bias (measured value), m is the slope coefficient and C is the constant coefficient
      - Zero or non-significant Linearity % value means gauge is having good linearity.
      - General guidelines for good bias and linearity: % Linearity < 10% and % Bias < 10%
    - - From the Gage Linearity and Bias Report,The p-values for the slope and bias determines if the linearity and/or bias is significant. Hence, determines if the MSA is acceptable
      - Analysis Steps
        
        Linearity
        
        if p-value < alpha-value (0.05), linearity is significant.
        if p value > alpha -value (0.05), linearity is insignificant.
        
        Bias
        
        if p-value < alpha -value (0.05), bias is significant.
        if p-value > alpha -value (0.05), bias is insignificant.
      - Minitab Gage Linearity & Bias Study
        
        Steps on Minitab
        
        Step 1 is to transfer the data from the excel file into the Minitab worksheet. Step 2 is to choose stat and click quality tools, and click the gage study which will show the gage linearity and bias study. Step 3 is to complete the dialog box by entering the part number, reference values, measurement data, and the process variation.
  - - - Difference between the reference value and the observed average of the measurement on the same characteristic, on the same part.
        
        Bias indicates how accurate the gage is when compared to a reference value.
        
        A positive bias indicates that the gauge overestimates. A negative bias indicates that the gauge underestimates.
        
        The %Bias value indicates the magnitude of the bias as a %age of the process variation (usually 6 sigma).
    - - Change of bias with respect to the size
        
        Linearity examines how accurate your measurements are through the expected range of the measurements.
        
        Linearity indicates whether the gage has the same accuracy across all reference values.
        
        When the slope is small, the gage linearity is good.
- - - - The observations indicate that the operators have similar measurements across all 9 Nozzle. Hence, we can say that the variance issue is not contributed by operators, as if their measurements are similar, it means that they both used the same procedure for measurement. Hence, variance could be mainly contributed by the difference in process of making Nozzles as all 9 Nozzles measured, give significantly different diameter values.
- - - - Bias
        
        Deviation between average measurement and the reference value of the part or standard.
        
        Small bias= Accurate measurement system
        
        Bias= Measurement system average - Reference value
        % of bias= bias / (Tolerance or process variation) x 100%
        
        High bias= not accurate
        
        Appraisers not following the measurement procedure
        
        An error in measuring the Reference Value
        
        Instability in the measurement. If the SPC chart shows a trend, the measurement device could be wearing or calibration could be drifting.
      - Stability
        
        Difference in the average of at least two sets of measurements obtained with a gauge as result of time
        
        Stability = consistent accuracy & precision over time
        
        Control Charts used to establish & maintain gauge stability.
        
        X bar chart (accuracy)
        
        chart indicates measurement is no longer accurate , thus need recalibration
        
        R Chart (Precision)
        
        indicates instability due to repeatability or reproducibility.
      - Definition: How close to the reference value of the part or standard. Ensured by calibration.
    - - Definition: variation of measurement attributed to the variability introduced by measurement system
      - Repeatability
        
        Variation in measurement in measuring same part by using one measuring tool + same operator in the same environment
        
        AKA Equipment Variation(EV)
      - Reproducibility
        
        Average measurement in measuring same part by using one measuring tool BUT different operators
        
        AKA Appraiser Variation(AV)/Operator effect
  - - - Equipment used
        
        Gages, fixtures, test equipment used and their associated calibration systems
      - Samples measured
        
        the part or material samples measured, the sampling plans
      - Environment
        
        Temperature, humidity
      - Personnel
        
        Operators, their skill level, training
      - Process procedure
        
        Test method, specification
- - - - p-value of Pipe & Operator Interaction = Less than 0.05. So, it is significant in contributing to variation.
      - Total Gage R&R value for % contribution = between 1%-9%. So, it is considered marginally acceptable.
        
        Part-to-part value for % contribution = more than 9%. So, it is not acceptable
      - Look at Total Gage R&R values for %Study variance & %Tolerance. Refer to GR&R Acceptability Table to check if measurement system is acceptable, marginally acceptable or not acceptable
        
        NDC = 7, which indicates that measurement system is acceptable
      - Components of Variation graph: Allows comparison between components of variations, to find out what is the main source contributing to variance.
        
        R chart: Allows to see which operator has more variability in measurements
        
        Xbar chart: Indicates if process is in control / not stable