Apparatus and Method for Monitoring a Pump

Abstract

An apparatus for monitoring of a pump includes a control module, and an error detection unit, wherein a support vector machine based module is provided that receives an estimated output quantity data value from the control module, processes the estimated output quantity data value to provide a processed estimated output quantity data value via the support vector machine, and supplies the processed estimated output quantity data value to the error detection unit instead of the estimated output quantity data value of the control module.

Claims

1.-10. (canceled)

11. An apparatus for monitoring a pump, the apparatus comprising: a control module configured to: receive at least one signal representing an operational parameter of the pump, and estimate an estimated output quantity data value of the pump based on the signal representing the operational parameter; an error detection unit configured to: receive the estimated output quantity data value from the control module, receive a measured output quantity data value of the pump provided by a sensor, provide a difference data value by subtracting the estimated output quantity data value from the measured output quantity data value, compare the difference data value with a predetermined threshold value and provide a corresponding comparison result, and output an error status signal of the pump based on a result of the comparison; and a support vector machine based module configured to: receive the estimated output quantity data value from the control module, process the estimated output quantity data value to provide a processed estimated output quantity data value by use of the support vector machine, and supply the processed estimated output quantity data value to the error detection unit instead of the estimated output quantity data value of the control module.

12. The apparatus according to claim 11, wherein the support vector machine based module is further configured to operate machine learning support vector machine regression.

13. The apparatus according to claim 11, wherein the support vector machine based module is configured to be trained with real data of operational parameters of the pump.

14. The apparatus according to claim 12, wherein the support vector machine based module is configured to be trained with real data of operational parameters of the pump.

15. The apparatus according to claim 11, wherein the control module is further configured to receive signals for all operational parameters of the pump and configured to estimate the estimated output quantity data value based on all signals of the operational parameters.

16. The apparatus according to claim 11, wherein the control module is further configured to estimate the estimated output quantity data value based on an H-Q-model which, in turn, is based on H-Q-curves provided by a manufacturer of the pump.

17. The apparatus according to claim 11, wherein the apparatus is configured to monitor a centrifugal pump.

18. The apparatus according to claim 11, wherein the control module is further configured to detect an electric parameter of an electric machine driving the pump.

19. The apparatus according to claim 11, wherein the error detection unit is further configured to calculate the predetermined threshold value from a Root Mean Square of a predetermined number of difference data values.

20. A method for monitoring of a pump, the method comprising: receiving at least one signal representing an operational parameter of the pump (16); estimating an estimated output quantity data value of the pump based on a signal of the operational parameter, receiving the estimated output quantity data value from the control module; receiving a measured output quantity data value of the pump provided by a sensor; providing a difference data value by subtracting the estimated output quantity data value from the received measured output quantity data value; comparing the difference data value with a predetermined threshold value and providing a corresponding comparison result; outputting an error status signal of the pump based on a result of the comparison; receiving the estimated output quantity data value from the control module by a support vector machine based module, processing the received estimated output quantity data value by the support vector machine based module to provide a processed estimated output quantity data value; and supplying the processed received estimated output quantity data value instead of the estimated output quantity data value of the control module for subtraction.

21. A non-transitory computer program product including a computer program executing on a processing device to monitor a pump, said program comprising: software code portions for receiving at least one signal representing an operational parameter of the pump; software code portions for estimating an estimated output quantity data value of the pump based on a signal of the operational parameter; software code portions for receiving the estimated output quantity data value from the control module; software code portions for receiving a measured output quantity data value of the pump provided by a sensor; software code portions for providing a difference data value by subtracting the estimated output quantity data value from the received measured output quantity data value; software code portions for comparing the difference data value with a predetermined threshold value and providing a corresponding comparison result; software code portions for outputting an error status signal of the pump based on a result of the comparison; software code portions for receiving the estimated output quantity data value from the control module by a support vector machine based module; software code portions for processing the received estimated output quantity data value by the support vector machine based module to provide a processed estimated output quantity data value; and software code portions for supplying the processed received estimated output quantity data value instead of the estimated output quantity data value of the control module for subtraction.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The teachings of the present inventions can be readily understood and at least some additional specific details will appear by considering the following detailed description of at least one exemplary embodiment in conjunction with the accompanying drawings, showing schematically the invention applied to monitoring of a centrifugal pump, in which:

[0040] FIG. 1 shows schematically a scheme for a centrifugal pump in accordance with the invention;

[0041] FIG. 2 is a graphical plot of H-Q-curves for the pump of FIG. 1;

[0042] FIG. 3 is a flow chart for estimation training in a training stage of the H-Q SVM model in accordance with the invention;

[0043] FIG. 4 is a block schematic diagram of the pump of FIG. 1 connected with an apparatus in accordance with the invention;

[0044] FIG. 5 is a diagram schematically showing real data of the pump of FIG. 1;

[0045] FIG. 6 is a diagram schematically showing a model error and two threshold values;

[0046] FIG. 7 a diagram schematically showing a fault index, where an index in the range of 1 relates to normal behaviour of the pump and an index of the range of 0 relates to an abnormal behaviour of the pump; and

[0047] FIG. 8 is a schematic block diagram depicting a radial basic functions (RBF) network approach.

DETAILED DESCRIPTION OF THE EXEMPLARY EMBODIMENTS

[0048] FIG. 1 shows schematic a block diagram of a pump arrangement 52 comprising a centrifugal pump 16 having an inlet 18 for auction of water, and an outlet 20 for providing the output flow of the pump 16. The pump 16 is driven by an electric motor 14 which, in turn, is supplied with electric energy by a frequency converter 12. The frequency converter 12, in turn, is connected with a power supply network 10 to supply the frequency converter 12 with electric energy.

[0049] FIG. 2 shows a graphical plot H-Q-curves of the pump 16 that is usually provided by a manufacturer of the pump 16. This diagram shows the relationship between the volume flow of the pump 16 and a pressure difference between inlet 18 and outlet 20 at a constant speed of a pump crank of the pump 16. The pressure difference is also referred to as “head”.

[0050] FIG. 4 shows a schematic block diagram of an apparatus 100 for monitoring of the centrifugal pump 16. The apparatus 100 is an apparatus in accordance with the invention. The apparatus 100 comprises a control module 60 which is configured to receive two signals representing operational parameters 74, 76 of the centrifugal pump 16. Presently, the operational parameter 74 refers to a “head” of the centrifugal pump 16, whereas the operational parameter 76 refers to a frequency that relates to the rotation of the centrifugal pump 16. In other embodiments, different or additional operational parameters can be considered.

[0051] The control module 60 is further configured to estimate an estimated output quantity data value 72 of the pump 16, where estimation is based on the signals of the operational parameters 74, 76. For estimation purposes, the control module 60 uses for the purpose of estimation a H-Q-model estimation 34 which, in turn, is based on pump curves (FIG. 2) provided by the manufacturer of the centrifugal pump 16. The estimated output quantity data value 72 is an output value of the control module 60, which is provided for further processing of the apparatus 100.

[0052] FIG. 4 shows a pump arrangement 52 comprising the centrifugal pump 16. The operational parameter 76 impinges on the centrifugal pump 16. At the inlet 18 site, the centrifugal pump 16 comprises a first pressure sensor 54, whereas, at the outlet 20, a second pressure sensor 56 is provided. The pressure sensors 54, 56 provide signal to a head unit 58 that calculates the head of the signals supplied by the pressure sensors 54, 56. The head unit 58 provides the operational parameter 74 as an output that is supplied to the apparatus 100, i.e., to the control module 60.

[0053] The apparatus 100 further comprises an error detection unit 62. The error detection unit 62 is configured to receive a measured output quantity data value 80 of the pump 16 that is provided by a sensor 78. In the present embodiment, the measured output quantity data value refers to a volume flow at the outlet 20 of the centrifugal pump 16. In the present embodiment, the sensor 78 forms part of the pump arrangement 52.

[0054] In accordance with the invention, the apparatus 100 further includes a support vector machine based module 64 that is configured to receive the estimated output quantity data value 72 from the control module 60. The support vector machine 64 processes the estimated output quantity data value 72 to provide a processed estimated output quantity data value 82 as an output. The processed estimated output quantity data value 82 is supplied to the error detection unit 62 instead of the estimated output quantity data value 72 of the control module.

[0055] The error detection unit 62 is further configured to provide a difference data value by subtracting 66 the processed estimated output quantity data value 82 from the measured output quantity data value 80. The difference data value is compared 68 with a predetermined threshold value. In response hereto, the error detection unit 62 outputs an error status signal 70 of the centrifugal pump 16 based on the result of comparing.

[0056] FIG. 3 shows schematically, in an exemplary embodiment, a flow chart of the operation of the training stage of the apparatus 100 in accordance with the invention. The method starts at 30. At 32, pump normalized characteristics from a pump specification provided by the manufacturer (FIG. 2) is input. At 34, a H-Q-model estimation is provided by the control module 60. Next, at step 36, estimation by the support vector machine based module is executed. As an output at 38, H-Q support vector machine model is provided. The method terminates at 40. FIG. 3 thus shows estimation training of the apparatus 100 in accordance with the invention.

[0057] The quality of the estimation with the apparatus in accordance with the invention can be measured by a loss function, as detailed below.

[0058] The quality of estimation is measured by the loss function L(y,f(x,ω)). SVM regression uses a new type of loss function, i.e., ε-insensitive loss function:

[00001]$\begin{array}{cc}{L}_c=\left(\gamma ,f\left(x,\stackrel{\_}{\omega }\right)\right)=\left\{\frac{0}{\left|y-f\left(x,\stackrel{\_}{\omega }\right)\right|-\mathrm{.Math.}}.Math.\frac{\mathrm{if}.Math.|y-f\left(x,\stackrel{\_}{\omega }\right)\le \mathrm{.Math.}}{\mathrm{otherwise}}\right\}& \mathrm{Eq}..Math.3\end{array}$

[0059] The empirical risk is:

[00002]$\begin{array}{cc}{R}_{\exp }\left(\stackrel{\_}{\omega }\right)=\frac{1}{n}.Math.{\Sigma }_{i=1}^n.Math.L_g\left(y_i,f\left(x,\stackrel{\_}{\omega }\right)\right)& \mathrm{Eq}..Math.4\end{array}$

[0060] It should be noted that ε-insensitive loss coincides with least-modulus loss and with a special case of Huber's robust loss function when ε=0. Hence, it can compare prediction performance of SVM, with proposed chosen ε, with regression estimates obtained using least-modulus loss (ε=0) for various noise densities.

[0061] In the following, the algorithm is described which is used by the disclosed embodiments of the invention.

[0062] The algorithm comprises a training stage as a first stage and a test stage as a second stage. The training stage is shown in accordance with FIG. 3, where the test stage is depicted by FIG. 4.

[0063] In the training stage, an H-Q-model is estimated in accordance with step 34 by using pump characteristics from a pump specification of the manufacturer. Input parameters are presently a pump current frequency that is derivable from current to be measured at the electric motor 14, as well as a pump head provided by the head unit 58. As an output, the pump flow is used, which is provided by the sensor 78.

[0064] Second, the support vector machine model is estimated that describes dependencies between real demand and output. For estimation purposes, the output of the pump flow of the H-Q-model is used as an input. The output is an estimated output flow of the pump 16.

[0065] In the test stage, the combined H-Q-SVM-model is used for output flow estimation of the pump 16. Next, an error calculation of the H-Q-SVM-model is provided. In a following step, the H-Q-SVM-model error output is compared with thresholds which, in the present embodiment, are an upper and a lower threshold. Both of these thresholds together provide a band, where the signal outside the band represents a failure or error, respectively of the pump 16. This is shown with regard to FIGS. 5 to 7.

[0066] In the diagram of FIG. 5, the real output and the output of the estimation are shown. FIG. 6 shows the error of the model with regard to the upper and the lower thresholds. FIG. 7 shows failures, whereas a value of a fault flag about 0 represents a failure, whereas a fault flag with a value of about 1 represents normal operation of the pump 16.

[0067] The operation of the support vector machine based module 64 is further detailed with reference to FIG. 8. Presently, a neural cloud classification algorithm is used as a support vector machine. The estimation of a membership function preferably consists of two steps: First, clustering by the advanced K means (AKM) clustering algorithm and, second, an approximation of clusters by radial basic functions (RBF) network approach (see FIG. 8). AKM is a modification of the K means algorithm with an adaptive calculation of optimal number of clusters for given maximum number of clusters (centroids).

[0068] AKM itself preferably consists of the following steps: [0069] Set an initial number of K centroids and a maximum and minimum bound. [0070] Call k-means algorithm to position K centroids. [0071] Insert or erase centroids according to the following premises: [0072] If the distances of data are above a certain distance from the nearest centroid, then generate a new centroid. [0073] If any cluster consists of less than a certain number of data, then remove the corresponding centroid. [0074] If the distance between some centroids is smaller than a certain value, then combine those clusters to one. [0075] Loop to step 2 unless a certain number of epochs is reached, or centroids number and their coordinates have become stable.

[0076] The output of the AKM algorithm is centers of clusters that represent historical data related to normal behaviour. This is used as a training set. After all, the centers of clusters have been extracted from the input data, the data is encapsulated with a hypersurface (membership function). For this purpose, Gaussian distributions (Gaussian bell) are used.

[00003]$\begin{array}{cc}{R}_i=e^{\frac{\left|x-m_i\right|}{2.Math.{\sigma }^2}}& \mathrm{Eq}..Math.5\end{array}$

where m.sub.i are centers of the Gaussian bell, σ is a width of the Gaussian bell, x is input data.

[0077] The centers AKM clusters are allocated to centers of corresponding Gaussian bells, as can be seen from FIG. 8 with respect to L1. The sum of all Gaussian bells is calculated to obtain the membership function. The sum of the Gaussian bells shall be preferably a unit in case of these bells overlap. Next, normalization is applied to set the confidence values p.sup.c calculated by neural clouds in boundaries between 0 to 1 (see FIG. 8).

[0078] The neural clouds encapsulate all previous history of selected parameters for a given training period. After training, the neural clouds calculate a confidence value for every new status of the pump 16, describing the confidence value of normal behaviour.

[0079] In accordance with the invention, the one-dimensional neural clouds construct membership function for the model error of thermal-mechanical fatigue (TF) simulation and provides a fuzzy output of confidence values between 0 and 1.

[0080] If desired, the different functions and embodiments discussed herein may be performed in a different or a deviating order and/or currently with each other in various ways. Furthermore, if desired, one or more of the above-described functions and/or embodiments may be optional or may be combined, preferably in an arbitrary manner.

[0081] Although various aspects of the invention are set out in the independent claims, other aspects of the invention comprise other combinations of the features from the described embodiments and/or the dependent claims with the features of the independent claims, and not solely the combinations explicitly set out in the claims.

[0082] It is also observed herein that, while the above describes exemplary embodiments of the invention, this description should not be regarded as limiting the scope. Rather, there are several variations and modifications which may be made without departing from the scope of the present invention as defined in the appended claims.

[0083] Thus, while there have been shown, described and pointed out fundamental novel features of the invention as applied to a preferred embodiment thereof, it will be understood that various omissions and substitutions and changes in the form and details of the devices illustrated, and in their operation, may be made by those skilled in the art without departing from the spirit of the invention. For example, it is expressly intended that all combinations of those elements and/or method steps which perform substantially the same function in substantially the same way to achieve the same results are within the scope of the invention. Moreover, it should be recognized that structures and/or elements and/or method steps shown and/or described in connection with any disclosed form or embodiment of the invention may be incorporated in any other disclosed or described or suggested form or embodiment as a general matter of design choice. It is the intention, therefore, to be limited only as indicated by the scope of the claims appended hereto.