Diagnostic device for use in process control system
View Patent ↗A method and diagnostic device are disclosed which can receive process variable values (x(t)) of a process variable of a process medium of a process, and extract and record measurement statistics data from such process variable values, which are measured during a measuring phase. Training statistics data can be extracted and recorded from such process variable values, which are measured during a training phase. The measurement statistics data can be compared with training statistics data recorded before the measurement statistics data. The training statistics data can include a training empirical statistical distribution, which can be a distribution of a function of process variable values, which are measured during a training phase, or a distribution of a function of coefficients X t (k), which are coefficients of a function of a transform of process variable values (x(t)), which are measured during a training phase.
1. A diagnostic device comprising:
a receiving means for receiving process variable values of a process variable of a process medium of a process,
a measurement processing means for extracting and recording measurement statistics data from such process variable values, which are measured during a measuring phase,
a training processing means for extracting and recording training statistics data from such process variable values which are measured during a training phase, for calculating a training empirical statistical distribution whereby the distribution is a distribution of a function of process variable values which are measured during a training phase, and for calculating a training analytical distribution function approximating the training empirical statistical distribution, and
a comparison means for comparing the measurement statistics data with training statistics data recorded before the measurement statistics data,
wherein the measurement statistics data comprise a measurement empirical statistical distribution, which is a distribution of a function of such process variable values, which are measured during a measuring phase, and wherein the training statistics data comprise the training analytical distribution function, and wherein the comparison means outputs a failure indication when a confidence level derived from a statistical test of a consistency of the measurement empirical statistical distribution with the training analytical distribution function is below a prescribable threshold value.
2. The diagnostic device according to claim 1 , comprising a sensing means for measurement of the process variable and for generating the process variable values.
3. The diagnostic device according to claim 1 , wherein the comparison means has a condition output related to a condition of the process, wherein the condition of the process is different from a measure for the process variable.
4. The diagnostic device according to claim 3 , wherein the condition output is related to a condition of a sensing means.
5. The diagnostic device according to claim 1 , wherein the measurement statistics data and the training statistics data relate to noise carried in the process medium.
6. The diagnostic device according to claim 5 , wherein the measurement processing means calculates a transform using one of the group of Fourier transform and wavelet transform.
7. The diagnostic device according to claim 6 , wherein the training analytical distribution function is a Gamma distribution function.
8. The diagnostic device according to claim 1 , wherein the statistical test is one of the group of Chi 2 -test and Kolmogorov-Smirnov-test.
9. A diagnostic device according to claim 1 , in combination with a process control system.
10. A diagnostic device comprising:
a receiving means for receiving process variable values of a process variable of a process medium of a process,
a measurement processing means for extracting and recording measurement statistics data from such process variable values, which are measured during a measuring phase and for calculating a transform of process variable values, which are measured during a measuring phase, into coefficients X m (k) of a set of orthogonal functions,
a training processing means for extracting and recording training statistics data from such process variable values which are measured during a training phase for calculating a training empirical statistical distribution, for calculating the transform of process variable values, which are measured during the measuring phase, into the coefficients X m (k) of a set of orthogonal functions, whereby the training empirical statistical distribution is a distribution of functions of the coefficients X t (k), and for calculating a training analytical distribution function approximating the training empirical statistical distribution, and
a comparison means for comparing the measurement statistics data with training statistics data recorded before the measurement statistics data,
wherein the measurement statistics data comprise a measurement empirical statistical distribution, which is a distribution of the functions of the coefficients X m (k), and
wherein the training statistics data comprise the training analytical distribution function, and
wherein the comparison means outputs a failure indication when a confidence level of a statistical test of a consistency of the measurement empirical statistical distribution with the training analytical distribution function is below a prescribable threshold value.
11. The diagnostic device according to claim 10 , comprising a sensing means for measurement of the process variable and for generating the process variable values.
12. The diagnostic device according to claim 11 , wherein the comparison means has a condition output related to a condition of the process, wherein the condition of the process is different from a measure for the process variable.
13. The diagnostic device according to claim 12 , wherein the condition output is related to the condition of the sensing means.
14. The diagnostic device according to claim 10 , wherein the measurement statistics data and the training statistics data relate to noise carried in the process medium.
15. The diagnostic device according to claim 10 , wherein the statistical test is one of the group of Chi 2 -test and Kolmogorov-Smirnov-test.
16. A diagnostic device according to claim 10 , in combination with a process control system.
17. A diagnostic method that is performed by a diagnostic device, the methods comprising:
Obtaining, in a receiving unit of the diagnostic device, process variable values, which are derived from measuring a process variable of a process medium of a process,
transforming and recording, in a measurement unit of the diagnostic device, measurement statistics data relating to noise carried in the process medium from such process variable values, which are measured during a measuring phase,
transforming and recording, in a training unit of the diagnostic device, training statistics data relating to noise carried in the process medium from such process variable values, which are measured during a training phase,
calculating, in the training unit of the diagnostic device, a training empirical statistical distribution whereby the distribution is a distribution of a function of process variable values which are measured during a training phase,
calculating, in the training unit of the diagnostic device, a training analytical distribution function approximating the training empirical statistical distribution,
comparing, in a comparison unit of the diagnostic device, the measurement statistics data with training statistics data recorded before the measurement statistics data, wherein the measurement statistics data comprise a measurement empirical statistical distribution, which is a distribution of a function of such process variable values, which are measured during a measuring phase, and wherein the training statistics data comprise the training analytical distribution function, and
outputting, from the comparison unit of the diagnostic device, a failure indication when a confidence level derived from a statistical test of the consistency of the measurement empirical statistical distribution with the training analytical distribution function is below a prescribable threshold value.
18. A diagnostic method that is performed by a diagnostic device, the methods comprising:
Obtaining, in a receiving unit of the diagnostic device, process variable values, which are derived from measuring a process variable of a process medium of a process,
extracting and recording, in a measurement unit of the diagnostic device, measurement statistics data relating to noise carried in the process medium from such process variable values, which are measured during a measuring phase,
calculating, in a training unit of the diagnostic device a transform of process variable values, which are measured during a measuring phase, into coefficients Xm(k) of a set of orthogonal functions,
extracting and recording in the training unit of the diagnostic device, training statistics data relating to noise carried in the process medium from such process variable values, which are measured during a training phase,
calculating, in the training unit of the diagnostic device, a training empirical statistical distribution,
calculating, in the training unit of the diagnostic device, a transform of process variable values, which are measured during a measuring phase, into the coefficients Xm(k) of a set of orthogonal functions, whereby the training empirical statistical distribution is a distribution of a function of the coefficients Xt(k),
calculating, in the training unit of the diagnostic device, a training analytical distribution function approximating the training empirical statistical distribution,
comparing, in a comparison unit of the diagnostic device, the measurement statistics data with training statistics data recorded before the measurement statistics data, wherein the measurement statistics data comprise a measurement empirical statistical distribution, which is a distribution of the function of the coefficients Xm(k), and wherein the training statistics data comprise the training analytical distribution function, and
outputting, from the comparison unit of the diagnostic device, a failure indication when a confidence level of a statistical test of the consistency of the a measurement empirical statistical distribution with the training analytical distribution function is below a prescribable threshold value.