Patent Application
20190244467
Pinch valves are one of the most important assets at industrial plants as they are the devices that regulate gas or fluid in industrial equipment. Pinch valves are often subjected to performance issues based on environmental conditions (temperature, dust, or vibration), process characteristics (fluid corrosiveness, abrasiveness, or temperature), age (time in service), or usage (number of cycles).
The initial price of a pinch valve is much less compared to its maintenance costs.
The majority of pinch valves are subject to frequent, unnecessary, or costly maintenance inspections that often require the equipment to be shut down for maintenance. Reactive maintenance is the conventional and rapid approach for fixing or replacing parts of industrial equipment when it breaks down. There is a large unmet need to move away from reactive and seek predictive strategies for the maintenance of pinch valves.
Systems and methods for testing a pinch valve using pinch valve signatures were presented before, however, no description of sensors attached to the rubber component or stain-based analysis was described as the basis of the pinch valve signature. The common way to control and monitor the pinch valve is by using a pinch valve positioner, which is additional part to the valve itself, and it is limited to provide only an indirect and less accurate monitoring of the pinch valve operation.
There is a growing need to provide an accurate and cost effective methods for measuring the stage of pinch valves.
There may be provided a pinch valve monitoring method, array of flexible sensors and a kit, as illustrated in the specification and/or claims and/or drawings.
The subject matter regarded as the invention is particularly pointed out and distinctly claimed in the concluding portion of the specification. The invention, however, both as to organization and method of operation, together with objects, features, and advantages thereof, may best be understood by reference to the following detailed description when read with the accompanying drawings in which:
c illustrate examples of the response of the array of flexible sensors;
In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be understood by those skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, and components have not been described in detail so as not to obscure the present invention.
The subject matter regarded as the invention is particularly pointed out and distinctly claimed in the concluding portion of the specification. The invention, however, both as to organization and method of operation, together with objects, features, and advantages thereof, may best be understood by reference to the following detailed description when read with the accompanying drawings.
It will be appreciated that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity. Further, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements.
Any reference in the specification to a system should be applied mutatis mutandis to a method that can be executed by the system.
The following text may refer to piezoresistive nanoparticles. Piezoresistive nanoparticles are a non-limiting example of piezoresistive nanomaterials.
A new approach for monitoring valves and for providing real-time diagnostics may include directly sensing the valve part that undergoes deformation due to open close cycles.
For example, in pinch valve, the pinch tube is directly monitored by flexible sensors based on piezoresistive nanoparticles that are adhered to the tube or, printed directly on it. The advantage of this approach, in comparison with valves positioners are:
There is provided at least one flexible sensor is printed directly or adhered on the flexible tube of the pinch valve and may be configured to sense shape, movement, pressure and stress directly on the flexible tube. Accordingly, the status (condition) of the pinch valve is diagnosed directly.
The suggested method will answer the abovementioned needs:
Piston 16 may move upwards and downwards and controls the position of the pinching element 14. The position of the pinching element 14 determines the openness of the flexible tube 12. Thus, when the pinch valve 10 is open the pinching element 14 does not press against the flexible tube 12. When pinch valve 10 is closed, the pinching element 14 presses the top of the flexible tube 12 against the bottom of the flexible tube 12 to prevent a passage of fluid through the flexible tube 12.
Each flexible sensor may include piezoresistive nanoparticle such as gold nanoparticles (GNPs) that may be included in a GNP ink. The GNP ink may be printed on at least one flexible substrate to form at least one flexible sensor that is highly sensitive to strain and/or pressure. The sensitivity of the at least one flexible sensor may resemble a sensitivity of the human skin at the finger tips (tens of milligrams). The at least one flexible sensor can be printed directly on the flexible tube of the pinch valve.
The at least one flexible sensor can be printed on 3D surfaces.
The at least one flexible sensor provides accurate and fast (millisecond) pressure/strain sensing with high resolution (tens of mg) and wide dynamic range.
The at least one flexible sensor exhibits high resolution (sub-millimeter) location sensing.
The at least one flexible sensor may perform multi-parameters sensing—pressure/strain, temperature and humidity
The array of flexible sensors 30 was manufactured by the following process:
The flexible tube outer diameter was ten millimeter and the rubber thickness was one millimeter.
The size of each sensor flexible sensor was three by three millimeter.
The flexible sensors of the array of flexible sensors 30 have two sensing directionalities.
A first subset of flexible sensors (denoted a1 or a2) one has favorable sensing direction along the flow direction. The first subset includes first flexible sensor 31, third flexible sensor 33, fifth flexible sensor 35, and seventh flexible sensor 37.
A second subset of flexible sensors (denoted b1 or b2) one has favorable sensing direction that is perpendicular to the flow direction. The second subset includes second flexible sensor 32, fourth flexible sensor 34, sixth flexible sensor 36, and eighth flexible sensor 38.
Sensors are more sensitive to events (for example stress, strain) that occur along their favorable sensing direction. The shape and orientation of a sensor may determine its favorable sensing direction. For example—each flexible sensor may include two sets of fingers that are directed at a certain direction. Different finger directions provide different favorable sensing directions.
In addition, first flexible sensor 31, second flexible sensor 32, fifth flexible sensor 35 and sixth flexible sensor 36 are longer and are placed closer to the center of the tube in relation to the third flexible sensor 33, fourth flexible sensor 34, seventh flexible sensor 37 and eighth flexible sensor 38.
The first sensor 31, second sensor 32, fifth sensor 35 and sixth sensor 36 (denoted a1 or b1), have a higher response (in relation to the third flexible sensor 33, fourth flexible sensor 34, seventh flexible sensor 37 and eighth flexible sensor 38) to a compression of the flexible tube.
The dispersion of the flexible sensors on the flexible tube surface enables to provide pressure mapping on the tube.
The flexible sensors were used to sense the strains on the flexible tube during open/close cycles, flow changes and foreign matter propagation through the flexible tube.
A different array of flexible sensors is described in
In
This array of flexible sensors can be used as reference to other influence like flow. This array of flexible sensors was used for prediction of pinch valve rubber fatigue due to compression of actuators.
Sensitivity to Strain
In
A metallic strain gauge (from KYOWA) was adhered to the right side of the tube and
The array of flexible sensors 30 and the metallic strain gauge were located at opposite sides of the center of the flexible tube—at a distance of twenty millimeter from the center.
A glass slide 14 with one mm thickness applied force changing in a constant speed of 10 mm/min.
The load applied on the flexible tube was measured using Force Gauge Model M5-2 from Mark 10 load cell connected to the glass slide.
The change in the resistance of the array of flexible sensors and of the metallic strain gauge were measured with a digital multi-meter. The response was calculated by setting the baseline resistance as the resistance when no load is applied (Rb).
The resistance under a specific load is Ri and the response is calculated by: Ri−Rb/Rb.
In both
In
In
In both figures the sensitivity of the array of flexible sensors is much higher (about thirty times more) than the sensitivity of the metallic strain gauge.
Response to Open Close Cycles
The pinch valve was repetitively opened and closed during the text. In addition, the flow of fluid to the valve was controlled to include flow periods in which fluid was send to the pinch valve and no flow periods in which fluid was not supplied to the pinch valve.
The response of the pinch valve to open close cycles was monitored by the array of flexible sensors and is presented (graph 70) in
The first five open close cycles occurred during a first flow period. The sixth till tenth open close cycles occurred during a first no flow period.
The eleventh till fifteenth open close cycles occurred during a second flow period. The sixteenth till twentieth open close cycles occurred during a second no flow period.
Each open close cycle lasted few seconds. Other responses may be provided with different lengths of open close cycles.
The response of the pinch valve to open close cycles is characterized by:
Flow Identification
The indication of flow (through a pinch valve) may be significant in production line and is usually monitored with in-line pressure sensors.
In
Foreign Matter Identification
Foreign matter indication is highly valuable in production lines and there is no direct way to identify it. Foreign matter can cause the flow to continue during close status of the valve, cracks in the body of the tube, and in some industrie, like the pharmaceutical industry, cross contamination that can greatly damage the product.
An array of flexible sensors 30 is illustrated in
In
The third flexible sensor 33 and the fourth flexible sensor 34 are located to the left of the second flexible sensor 32—and both are closer to the center of the flexible tube. The third flexible sensor 33 is closer to the center than the fourth flexible sensor 34.
The eighth flexible sensor 38 is located to the left of the fourth flexible sensor 34 and substantially at the same line as the, first flexible sensor 31, second flexible sensor, and the seventh flexible sensor 37.
The seventh flexible sensor 37 is located to the left of the eighth flexible sensor 37.
The sixth flexible sensor 36 and the fifth flexible sensor 35 are located to the left of the seventh flexible sensor 37—and both are closer to the center of the flexible tube. The sixth flexible sensor 36 is closer to the center than the fifth flexible sensor 35.
The array of flexible sensors 30 may be printed on or glued to a flexible tube and may be configured to detect foreign matter that passes through the pinch valve.
In the following setup, the sensors that showed significant change in the presence of foreign matter where the sensors that their main sensing direction is perpendicular to the flow direction (for example first flexible sensor 31 and eighth flexible sensor 38).
The response of the pinch valve was measured during repetitive open close cycles whereas the closed position was kept for two seconds and the open position was kept for five seconds.
In all cases, the standard deviation was an order of magnitude smaller than the response size. From these results, it can be concluded that a foreign matter can be detected with nanoparticles-based sensors. The results showed meaningful change in the response size only for sensor with sensing direction that is perpendicular to the flow, therefore, foreign matter can be differentiated from other parameters like changes in the flow, since changes in the flow affect in a similar manner on all sensors.
Prediction of Pinch Valve Rubber Fatigue Due to Compression of the Compressor.
The response of the nanoparticles-based sensors is highly depended on the health status of the flexible tube. Specifically, a change in the response size is clear towards the end of life of the flexible tube.
The graph includes five curves that represent the response of the pinch valve at five different time windows—each of ten open close cycles—wherein the different time windows start at different open close cycles—3300, 3500, 3700, 3900 and 4100 cycles. The response measured by the array of flexible sensors increases with increasing open close cycle s. This is an indication for increase elasticity and thinning of the rubber component of the flexible tube.
Sensors Sustainability
The stability and sustainability of the sensors to the flexible tube life time was tested by measuring the signal from the sensors while they are attached to the flexible tube in the valve in accelerated life test. The accelerated life test included 50 K and more open close cycles at 50° C. when the sensors were places far enough from the actuator (e.g., 1-2 cm away from the center) the sensors and the adhesion showed good stability over time.
Failure Prediction
The data set was based on 8 tubes based on FKM (fluoroelastomer materials) with 8 nanoparticles based sensors adhered to them. The adhesion of the piezoresistive nanomaterials based sensors to the FKM tube was performed with Pangofol All-Purpose Bonding Cements adhesive. The adhesion process included an overnight curing time. The tubes were placed in a pneumatic metal pinch valve in an incubator set for 50° C. as presented in
The resistance of the nanoparticles based sensor changes a result of:
The setup was equipped with an external pressure sensor that detect the pressure drop inside the flexible tube in case of a leak and stops the pneumatic actuator. That way, the specific time of failure (e.g., burst of the flexible tube) can be detected, and the related responses of the nanoparticles based sensors can be correlated.
The methodology for burst prediction was Feature based analysis, and included: Data preparation, Overview, Cycles splitting, Feature selection, Feature engineering, PCA—Principle Component Analysis, training set, Modeling of burst prediction
Feature Selection and Engineering
Some features are general and represent general changes over time. For example, the amplitude recorded from the piezoresistive nanomaterial based sensors adhered to the pinched tube.
As can be seen, there is a clear trend and the amplitude monotonously decreasing with increasing operation time. This decrease can be corollate to changes in the flexible tube elasticity.
Different features were extracted for different signal types. The type of the signal is evaluated based on its representative cycle.
By data inspection optional patterns are defined as presented in
In
The exponential growth factor change as a function of operation time is presented by curve 115 of
Using approximations (for example logarithmic approximation, exponential approximation or yet another approximation) allows to compress the measurements and save both storage resource, communication resources and the like.
Modelling
The framing of the problem may be a regression one, where the goal is to predict the time remaining until burst of the tube. The general idea is to fit a separate model for each signal type and make an ensemble of them.
A set of eight tubes was used to build the model.
Modelling was based on a subset of the features. Discriminant Analysis and Principle Component Analysis were used to learn about the diversity in the data and the ability to identify failure in the described system (see
The flow chart of the modeling process 150 is described in
The modeling process includes the following sequence of steps:
The features preparation 155 outputs a training set Xtraining 161 and a test set Xtesting 162.
Xtraining may be based on 70% of the data and used to build features with the real ttf (Ytraining 163) as reference. Xteesting 162—30% of the data is turn into features based on the training set.
From the test set features that are based on the training set, the Ŷprediction (the predicted time to failure) is received and compered to the actual Ytesting which is the real time to failure. The comparison allows to estimate the model accuracy. This model allows the prediction of burst±150 cycles.
The model inputs and outputs are summarized in Table 1 of
Features are sorted alongside the timestamp and the time to failure, creating a new data table. From this point there is no longer use in the raw data. An example of such a table is presented in Table 2 denoted 162 in
Table 2 provides examples for features list alongside with time stamp and the time to failure.
Method 200 may include steps 210 and 220.
Step 210 may include sensing an electrical parameter of at least one flexible sensor during a monitoring period to provide multiple values of the sensed electrical parameter. The electrical parameter may be conductance, resistance or any other electrical parameter.
The at least one flexible sensor may include piezoresistive nanoparticles.
The piezoresistive nanoparticles may be directly coupled to a flexible conduit of the pinch valve.
The sensed electrical parameter may be indicative of a flexible conduit parameter. The flexible conduit parameter may be stress applied on a part of the flexible conduit to which the flexible sensor is attached, pressure applied on a part of the flexible conduit on which the flexible sensor is attached. Thus—the electrical parameter of the at least one flexible sensor may indicate of a passage of a foreign particle through the flexible conduit, on an expected failure of the flexible conduit, on movements of the flexible conduit, and the like.
The piezoresistive nanoparticles may be imprinted on the flexible conduit of the pinch valve.
The piezoresistive nanoparticles may be printed on at least one flexible substrate that may be glued to the flexible tube of the pinch valve.
Step 210 may be followed by step 220 of estimating, based on the multiple values of the sensed electrical parameter, a state of the pinch valve.
The estimating of the state of the pinch valve may include predicting a failure of the pinch valve.
The predicting of the failure of the pinch valve may include searching for at least one failure pattern, in the multiple values of the sensed electrical parameter, that may be indicative of a future failure of the pinch valve.
The at least one failure pattern may be indicative of a future time of failure.
The predicting of the failure of the pinch valve may include determining at least one pinch valve feature from the multiple values of the sensed electrical parameter and estimating the failure of the pinch valve based on the at least one pinch valve feature.
The estimating may be responsive to changes in one or more elastic properties of the flexible conduit during open close cycles of the pinch valve.
The piezoresistive nanoparticles may be printed on at least one flexible substrate that may be glued to the flexible tube of the pinch valve. The estimating may be responsive to changes in an adhesion of the at least one flexible substrate to the flexible conduit.
The estimating may be responsive to changes in the at least one flexible sensor over time.
The estimate may perform at least one out of calculate a model of, calculate in any other method, estimate, or apply a machine learning process, in order to take into account one or more parameters such as (i) changes in one or more elastic properties of the flexible conduit during open close cycles of the pinch valve, (ii) changes in an adhesion of the at least one flexible substrate to the flexible conduit, (iii) changes in the at least one flexible sensor over time.
The at least one flexible sensor may be multiple flexible sensors.
Some flexible sensors have a favorable sensing direction along a first axis and wherein some other flexible sensors have a favorable sensing direction along a second axis that may be oriented to the first axis.
The first axis may be parallel to a longitudinal axis of the flexible conduit.
The estimating is based on an outcome of a supervised machine learning process.
Any of the numeral examples (for example dimensions, number of cycles, number of sensors, pressure values) and/or materials (rubber, GNP) are non-limiting examples.
Any of the calculations and/or processing and/or estimation may be executed by a processing circuitry. The processing circuitry may be included in each flexible sensor, may be included in an array of flexible sensors, may be located in proximity to the one or more flexible sensor, may be remotely located from the flexible sensors.
The calculations and/or processing may be executed by multiple processing circuitries—for example a compression of the raw sensing signals may be executed by a first processing circuitry while the processing of the compressed data (for example failure prediction) can be executed by another processing circuitry.
The processing circuitry may belong to a measurement device, may be an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a graphic processing unit (GPU), a central processing unit (CPU), a hardware accelerator, a customized circuit, and the like.
There may be provided a kit that may include a pinch valve; and at least one flexible sensor that comprises piezoresistive nanomaterials, wherein the piezoresistive nanomaterials may be directly coupled to a flexible conduit of the pinch valve.
The piezoresistive nanomaterials may be imprinted on the flexible conduit of the pinch valve.
The piezoresistive nanomaterials may be printed on at least one flexible substrate that may be glued to the flexible tube of the pinch valve.
The at least one flexible sensor may be multiple flexible sensors.
The kit wherein some flexible sensors have a favorable sensing direction along a first axis and wherein some other flexible sensors have a favorable sensing direction along a second axis that may be oriented to the first axis.
The first axis may be parallel to a longitudinal axis of the flexible conduit.
The kit may include a computer readable medium that stores instructions for: (a) receiving multiple values of a sensed electrical parameter of the at least one flexible sensor; wherein the sensed electrical parameter may be indicative of a flexible conduit parameter selected out of stress and pressure; and (b) estimating, based on the multiple values of the sensed electrical parameter, a state of the pinch valve.
There may be provided a non-transitory computer readable medium that stores instructions for receiving a sensed electrical parameter of at least one flexible sensor during a monitoring period to provide multiple values of the sensed electrical parameter; wherein the at least one flexible sensor comprises piezoresistive nanomaterials, wherein the piezoresistive nanomaterials are directly coupled to a flexible conduit of the pinch valve; wherein the sensed electrical parameter is indicative of a flexible conduit parameter selected out of stress and pressure; and estimating, based on the multiple values of the sensed electrical parameter, a state of the pinch valve.
The non-transitory computer readable medium may be a memory unit, an integrated circuit with storage capabilities, a compact disk, a magnetically readable media, a electrically readable media, a optically readable media, and the like.
Any reference to any of the terms “comprise”, “comprises”, “comprising” “including”, “may include” and “includes” may be applied to any of the terms “consists”, “consisting”, “and consisting essentially of”. For example—any of figures describing masks used for implementing a device may include more components that those illustrated in the figure, only the components illustrated in the figure or substantially only the components illustrate in the figure.
In the foregoing specification, the invention has been described with reference to specific examples of embodiments of the invention. It will, however, be evident that various modifications and changes may be made therein without departing from the broader spirit and scope of the invention as set forth in the appended claims.
Moreover, the terms “front,” “back,” “top,” “bottom,” “over,” “under” and the like in the description and in the claims, if any, are used for descriptive purposes and not necessarily for describing permanent relative positions. It is understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in other orientations than those illustrated or otherwise described herein.
Those skilled in the art will recognize that the boundaries between elements are merely illustrative and that alternative embodiments may merge elements or impose an alternate decomposition of functionality upon various elements. Thus, it is to be understood that the architectures depicted herein are merely exemplary, and that in fact many other architectures can be implemented which achieve the same functionality.
Any arrangement of components to achieve the same functionality is effectively “associated” such that the desired functionality is achieved. Hence, any two components herein combined to achieve a particular functionality can be seen as “associated with” each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated can also be viewed as being “operably connected,” or “operably coupled,” to each other to achieve the desired functionality.
Furthermore, those skilled in the art will recognize that boundaries between the above described operations are merely illustrative. The multiple operations may be combined into a single operation, a single operation may be distributed in additional operations and operations may be executed at least partially overlapping in time. Moreover, alternative embodiments may include multiple instances of a particular operation, and the order of operations may be altered in various other embodiments.
Also, for example, in one embodiment, the illustrated examples may be implemented as circuitry located on a single device. Alternatively, the examples may be implemented as any number of separate devices or separate devices interconnected with each other in a suitable manner. However, other modifications, variations and alternatives are also possible. The specifications and drawings are, accordingly, to be regarded in an illustrative rather than in a restrictive sense.
In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word ‘comprising’ does not exclude the presence of other elements or steps then those listed in a claim. Furthermore, the terms “a” or “an,” as used herein, are defined as one or more than one. Also, the use of introductory phrases such as “at least one” and “one or more” in the claims should not be construed to imply that the introduction of another claim element by the indefinite articles “a” or “an” limits any particular claim containing such introduced claim element to inventions containing only one such element, even when the same claim includes the introductory phrases “one or more” or “at least one” and indefinite articles such as “a” or “an.” The same holds true for the use of definite articles. Unless stated otherwise, terms such as “first” and “second” are used to arbitrarily distinguish between the elements such terms describe. Thus, these terms are not necessarily intended to indicate temporal or other prioritization of such elements.
While certain features of the invention have been illustrated and described herein, many modifications, substitutions, changes, and equivalents will now occur to those of ordinary skill in the art.
It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.
Any reference to a method may be applied mutatis mutandis to a non-transitory computer readable medium that stores instructions for executing the method. The non-transitory computer readable medium may be an integrated circuit, a part of an integrated circuit, a memory unit, a compact disk, an optical storage medium, a magnetic storage medium, a memristive storage medium, a capacitive based storage medium, and the like.
This application claims priority from U.S. provisional patent 62/663,276 filing date Apr. 27, 2018 which is incorporated herein by its entirety.
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/IL2017/051162 | 10/24/2017 | WO | 00 |
| Number | Date | Country | |
|---|---|---|---|
| 62413466 | Oct 2016 | US |
