Patent Application
20250012176
When a well's own energy is not enough to bring the produced fluids to the surface, an artificial lift system is needed to help lift the fluid from the wellbore. One of these methods is sucker rod pumps. In sucker rod pumps, the circular motion of crank at the surface is translated downhole to the pump using a polished rod and rod string.
In deep wells the long sucker rod has considerable stretch, distributed mass, etc., and motion at the pump end may be radically different from that imparted at the upper end. One method of determining pump performance involves plotting a curve of rod load versus displacement. The shape of the curve or “card” reflects the conditions which prevail downhole in the well. U.S. Pat. No. 3,343,409 describes a method for determining the downhole performance of a rod pumped well by measuring surface data, (the surface card) and computing a load versus displacement curve (a “pump card” for the sucker rod string at any selected depth in the well). These downhole cards or plots can be used to alter the operating conditions of the well, such as by slowing down the rod cycle to increase the time for the pump to fill during a rod cycle. Essential quantities can be extracted from the downhole data to diagnose, interpret, and modify control of the well and fluid extraction.
One embodiment under the present disclosure comprises a method for determining plunger velocity in a rod pumped well. The method comprises using position data from a downhole card to determine plunger velocity during a pump stroke; and plotting normalized plunger velocity over a downhole card.
Another embodiment under the present disclosure comprises an oil well. The oil well comprises a well assembly and pump assembly. The well assembly comprises a casing extending toward an oil bearing region; a tubing extending at least partially through the casing; a sucker rod extending at least partially through the tubing; and a plunger coupled to the sucker rod and configured to create an upstroke and downstroke in the oil bearing region to extract oil from the oil bearing region into the casing. The pump assembly is coupled to the well assembly and comprises: a motor configured to supply power to the pump assembly and the well assembly; and a gear box configured to direct power from the motor to the well assembly and the sucker rod. The oil well further comprises one or more sensors configured to detect one or more properties within the oil well; and a controller communicatively coupled to the one or more sensors and configured to control the pump assembly and the well assembly. The controller comprises one or more processors; and a non-transitory, computer-readable storage medium in operable communication with at least one processor of the one or more processors, wherein the computer-readable storage medium contains one or more programming instructions that, when executed, cause the processor to: create a downhole card based at least in part on the one or more properties from the one or more sensors; use position data from the downhole card to determine plunger velocity during a pump stroke; and plot normalized plunger velocity over the downhole card.
A further embodiment under the present disclosure comprises a method for determining plunger velocity in a rod pumped well. The method comprises using position data from a downhole card to determine plunger velocity during a pump stroke; plotting normalized plunger velocity over a downhole card; and controlling a pumping unit of the rod pumped well using the plunger velocity and downhole card data.
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an indication of the scope of the claimed subject matter.
While the specification concludes with claims which particularly point out and distinctly claim this technology, it is believed this technology will be better understood from the following description of certain examples taken in conjunction with the accompanying drawings, in which like reference numerals identify the same elements and in which:
There currently exist certain challenges related to wells and downhole cards. One piece of information that is missing from existing downhole cards is the plunger velocity during a pumping stroke. The plunger velocity can vary during a pump stroke because of compression and stretching of the well string during a stroke, or it may be physically altered using a variable frequency drive that can change the motor speed of the pump during the stroke. It would be helpful to be able to see and use the pump velocity in conjunction with the downhole card to diagnose and control the operation of the well.
Certain embodiments can provide solutions to these or other challenges. Certain embodiments described herein provide an accurate and robust way to determine plunger velocity, plot plunger velocity over a traditional downhole card and control well operation using plunger velocity data that is gathered every stroke in real time via the POC (pump off controller), edge device, SCADA (supervisory control and data acquisition) System, Integrated VFD (variable frequency drive), or Cloud based control system.
There are numerous advantages to various embodiments under the present disclosure. Certain embodiments described herein can provide an accurate and robust way to determine plunger velocity, plot plunger velocity over a traditional downhole card, and control well operation using plunger velocity data that is gathered every stroke in real time via the pump off controller/edge device/SCADA System/Integrated VFD or Cloud based control system. Furthermore, certain embodiments can use plunger velocity as an input for control, something that has been unavailable in the prior art.
Referring now to
Well bore 11 includes casing 23 and tubing 24 extending inside casing 23. Sucker rod 25 extends through the interior of tubing 24 to plunger 19. At the bottom of well bore 11 in oil bearing region 26, casing 23 includes perforations 27 that allow hydrocarbons and other material to enter annulus 28 between casing 23 and tubing 24. Gas is permitted to separate from the liquid products and travel up the annulus where it is captured. Liquid well products collect around pump barrel 29, which contains standing valve 30. Plunger 19 includes traveling valve 31. During the down stroke of the plunger, traveling valve is opened and product in the pump barrel is forced into the interior of tubing 24. When the pump begins its upstroke, traveling valve 31 is closed and the material in the tubing is formed forced up the tubing by the motion of plunger 19.
Controller 40 can control the one or more functionalities or processes of well 10 and/or pump assembly 12. Controller 40 may be powered by motor 13 or another power supply. Controller 40 may be communicatively coupled (wireless or wired) with e.g., sensors 45 within well 10, which may measure properties such as e.g., depth, temperature, pressure, flow rates, plunger speed, wear on parts/components, or other parameters. Controller 40 can collect data on well 10 or pump assembly 12 and may be communicatively coupled with computing devices 90 via network 80. Network 80 can comprise Wi-fi, cellular, GPS (global positioning system), satellite, other networks, or combinations of the foregoing. Computing devices 90 can be remote or local to well 10, and can be used to control well 10 or pump assembly 12, collect and/or analyze data, and/or perform other tasks. Controller 40 and/or computing devices 90 can create downhole cards or utilize them in various processes as described further herein. In some embodiments, the functionalities of controller 40 may be implemented in computing device(s) 90 and be cloud-based. In some embodiments, controller 40 and/or computing device(s) 90 may be able to control multiple oil well systems 5, and may be able to implement methods further described herein across multiple oil well systems 5.
Creating a downhole card can take into account a variety of parameters. In certain embodiments three forces used with rod pumping include elasticity, viscous friction, and mechanical friction. Elasticity takes the form of stress waves traveling up and down the rod string at the speed of sound as the rod string material stretches and compresses with the cyclic motion of the pumping unit. Produced fluid being lifted to the surface creates a viscous force on the outer diameter of the rod string opposing its movement. Finally, either due to well deviation, paraffin or other external factors, the rod string and couplings cause mechanical friction with its contact with the inner diameter of the tubing.
In order to effectively control rod pumps, one should calculate not only the work done at the surface but also anticipate the energy losses to the system due to the above three conditions. Once the position of the plunger and the load on the plunger have been measured at the surface, the downhole data can be calculated and represented as a downhole card, examples of downhole cards under the present disclosure are shown in
One data point missing from a downhole card, however, is plunger velocity as it travels through a complete pump stroke. Fortunately, the downhole card data already collected can be used to calculate the plunger velocity through the pump stroke.
Once the plunger velocity has been determined, the data can be plotted with the plunger velocity (y-axis) plotted against plunger position (x-axis) to show the plunger velocity through an entire pump stroke. Such a plot is shown in
The plunger velocity plot of
Additionally, other examples of pump diagnosis and control can include, e.g.:
Controller 40 and/or computing device(s) 90 of
Yet another application of the additional of plunger velocity to the downhole card involves utilizing the supplied plunger velocity plot from e.g., controller 40 that is calculated each stroke, and allowing a user to setup intra-stroke speed control to prevent rod buckling.
Additionally, any tagging that may take place on the down stroke would be less detrimental due to slower speed. This further allows for properly timed speed reductions around the transitions on long stroke pumping units. If rod buckling is shown on the plunger velocity plot in zone 3, the right vertical line could be shifted to the left of the buckling signature. This would allow user to slow the well down earlier at top of stroke and not speed back up until the compression event is passed.
While various examples of diagnosis and control scenarios have been described, these examples are not meant to be exhaustive and other use cases can be imagined or anticipated using the concepts described herein.
There are several takeaways from the examples shown in
Computing device 2500 includes processor 2501 that is operatively coupled via a bus 2502 to an input/output interface 2505, a power source 2513, a memory 2515, a RF interface 2509, network communication interface 2511, and/or any other component, or any combination thereof. The level of integration between the components may vary from one embodiment to another. Further, certain computing devices 2500 (or components thereof) may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.
The processor 2501 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in memory 2515. Processor 2501 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processor 2501 may include multiple central processing units (CPUs).
In the example, input/output interface 2505 may be configured to provide an interface or interfaces to an input/output device(s) 2506, such as a screen, keyboard, indicator light, keypad, touchscreen, or other input or output device. Other examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into system 2500. Other examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.
In some embodiments, the power source 2513 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet, or motor 13 of
Memory 2515 may be configured to include memory such as random access memory (RAM) 2517, read-only memory (ROM) 2519, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, other storage medium 2521, and so forth. In one example, the memory 2515 includes one or more application programs 2525, an operating system 2523, web browser application, a widget, gadget engine, or other application, and corresponding data 2527. Memory 2515 may store, for use by the computing device 2500, any of a variety of various operating systems or combinations of operating systems. An article of manufacture, such as one including a simulation system or communication system may be tangibly embodied as or in memory 2515, which may be or comprise a device-readable storage medium.
Processor 2501 may be configured to communicate with an access network or other network using the RF interface 2509 or network connection interface 2511. The RF interface 2509 or network connection interface 2511 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna. In the illustrated embodiment, communication functions of the RF interface 2509 or network connection interface 2511 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof.
In certain embodiments under the present disclosure, the data collected by controller 40 and/or computing devices 90 of
At 2710 in the training pipeline 2705, data ingestion 2710 occurs, which includes gathering raw (training) data from a data storage. After data ingestion 2710, there may also be a step that controls the validity of the gathered data. At 2715 data pre-processing occurs, which can include feature engineering applied to the gathered data. This may involve, e.g., data normalization or data formatting or transformation required for the input data to the AI/ML model. After the ML model's architecture is fixed, it should be trained on one or more datasets. At 2720 model training is performed in which the AI/ML model is trained with the raw training data. To achieve good performance during live operation in a system (the so-called inference phase), the training datasets should be representative of actual data the ML model will encounter during live operation. The training process often involves numerically tuning the ML model's trainable parameters (e.g., the weights and biases of the underlying neural network (NN)) to minimize a loss function on the training datasets. The loss function may be, for example, based on a maximizing student learning (possibly against a standardized test or other measure); minimizing disruptive behavior; minimizing teacher hours spent on lesson plans, or other metrics. The purpose of the loss function is to meaningfully quantify the reconstruction error for the particular use case at hand. At 2725 model evaluation can be performed where the performance is benchmarked to some baseline. Model training 2720 and evaluation 2725 can be iterated until an acceptable level of performance is achieved. At 2730 model registration occurs, in which the AI/ML model is registered with any corresponding data on how the AI/ML model was developed, and e.g., AI/ML model evaluation data. At 2735 model deployment occurs, wherein the trained/re-trained AI/ML model is implemented in the inference pipeline 2750.
Data ingestion 2755 in the inference pipeline 2750 refers to gathering raw (inference) data from a data source. Data pre-processing 2760 can be essentially identical/similar to the data pre-processing 2715 of the training pipeline 2705. At 2765, the operational model received from the training pipeline 2705 is used to process new data received during operation of e.g., well 10 of
The training process is typically based on some variant of a gradient descent algorithm, which, at its core, typically comprises three components: a feedforward step, a back propagation step, and a parameter optimization step. These steps can be described using a dense ML model (i.e., a dense NN with a bottleneck layer) as an example.
Feedforward: A batch of training data, such as a mini-batch, (e.g., several downlink-channel estimates) is pushed through the ML model, from the input to the output. The loss function is used to compute the reconstruction loss for all training samples in the batch. The reconstruction loss may be an average reconstruction loss for all training samples in the batch.
Back propagation (BP): The gradients (partial derivatives of the loss function, L, with respect to each trainable parameter in the ML model) are computed. The back propagation algorithm sequentially works backwards from the ML model output, layer-by-layer, back through the ML model to the input. The back propagation algorithm is built around the chain rule for differentiation: When computing the gradients for layer n in the ML model, it uses the gradients for layer n+1.
Parameter optimization: The gradients computed in the back propagation step are used to update the ML model's trainable parameters. An approach is to use the gradient descent method with a learning rate hyperparameter (a) that scales the gradients of the weights and biases. It is preferred to make small adjustments to each parameter with the aim of reducing the average loss over the (mini) batch. It is common to use special optimizers to update the ML model's trainable parameters using gradient information. The following optimizers are widely used to reduce training time and improve overall performance: adaptive sub-gradient methods (AdaGrad), RMSProp, and adaptive moment estimation (ADAM).
The above process (feedforward, back propagation, parameter optimization) can be repeated many times until an acceptable level of performance is achieved on the training dataset. An acceptable level of performance may refer to the ML model achieving a pre-defined average reconstruction error over the training dataset (e.g., normalized MSE of the reconstruction error over the training dataset is less than, say, 0.1). Alternatively, it may refer to the ML model achieving a pre-defined value chosen by a user.
In some implementations, a function F (·) may be generated by a ML process, such as, for example, supervised learning, reinforcement learning, and/or unsupervised learning. It should further be understood that supervised learning may be done in various ways, such as, for example, using random forests, support vector machines, neural networks, and the like. By way of non-limiting example, any of the following types of neural networks that may be utilized, including, deep neural networks (DNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs), or any other known or future neural network that satisfies the needs of the system. In an implementation using supervised learning the neural networks may be easily integrated into the hardware described in well 10 of
Referring now to
As should be understood by one of ordinary skill in the art, in order for the NN 2900 to output proper a proper analysis, it should be trained properly (e.g., with a collection of samples) to accurately extract the likelihood values. If not trained properly, overfitting (e.g., when the NN memorizes the structure of the preambles but is unable to generalize to unseen preamble characteristics) or underfitting (e.g., when the NN is unable to learn a proper function even on the data that it was trained on) may happen. Thus, implementations may exist that prevent overfitting or underfitting, involving a set of well-engineered features that must be extracted from the preamble characteristics.
Although the present invention and its advantages have been described in detail, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims. Moreover, the scope of the present application is not intended to be limited to the particular embodiments of the process, machine, manufacture, composition of matter, means, methods and steps described in the specification. As one of ordinary skill in the art will readily appreciate from the disclosure of the present invention, processes, machines, manufacture, compositions of matter, means, methods, or steps, presently existing or later to be developed that perform substantially the same function or achieve substantially the same result as the corresponding embodiments described herein may be utilized according to the present invention. Accordingly, the appended claims are intended to include within their scope such processes, machines, manufacture, compositions of matter, means, methods, or steps.
This application claims the benefit of U.S. Provisional Patent Application No. 63/525,527, entitled “System and Method for Determining Plunger Velocity Using a Downhole Card,” filed Jul. 7, 2023, the contents are which are hereby incorporated by reference.
| Number | Date | Country | |
|---|---|---|---|
| 63525527 | Jul 2023 | US |
