SYSTEM AND METHOD FOR PREDICTING AND OPTIMIZING DRILLING PARAMETERS

Abstract

A method and a system for using machine learning technologies to predict the value and timing of operational parameters. These predictions are then used to optimize the rate of penetration (ROP) of a drilling operation.

Description

TECHNICAL FIELD

The present disclosure relates generally to oil and gas well drilling and well operations. More specifically, this disclosure relates to a method and a system using machine learning models to optimize a rate of penetration (ROP) of the drilling operation.

BACKGROUND

Drilling and well operations in oil and gas wells are expensive operations. The cost is typically several tens to several hundred thousand dollars per day. Optimizing the rate of penetration reduces the time spent drilling the well, and consequently reducing the operational cost. Attempts to optimize performance include the following.

U.S. Pat. No. 10,539,001 uses drilling parameters and lithologies from offset wells to generate ROP as function of depth combined with the lithologies as a function of depth in a planning phase-rather than in real time.

U.S. Pat. No. 10,275,715 describes a methodology for using historical and real time data to generate a set of machine learning models that compares the actual ROP with predicted and optimum ROP within a ROP swimlane determined by statistical model. The method disclosed in U.S. Pat. No. 10,275,715 relies on relevant historical data, presents the output as a swimlane—rather than specific recommended values.

U.S. Pat. No. 9,995,129 provides a method for how to control the drilling rig, and not for finding the optimum operational parameters.

U.S. Pat. No. 7,730,967 provides a method to correct operational anomalies from drillstring sensors.

U.S. Pat. No. 8,121,971 describes rule-based agents using conventional physical algorithms to optimize drilling operations.

U.S. Pat. No. 9,424,667 describes using sensor values to calculate entropy and energy consumption and as a result determining whether the operation is RPM, weight on bit (WOB) or flowrate dominant, and using this to optimize the drilling parameters.

U.S. Pat. No. 6,382,331 describes storing relevant sensor data and ROP, performing a linear regression with ROP as the response variable and sensor data as explanatory variables to create a correlation between the ROP and one of the sensors to define an optimum value for the sensor and for then to try to follow the optimum sensor value.

U.S. Pat. No. 7,357,196 describes adjusting drilling parameters based on models of lithology, rock strength, shale plasticity, mechanical efficiency.

U.S. Pat. No. 10,316,653 describes a method and system for predicting drilling performance per depth based on a geology model giving a bit selection and predicted drilling mechanics such as bit wear, mechanical efficiency, and operating parameters.

U.S. Pat. No. 7,899,658 describes a method for simulating the performance of a drilling BHA in engineering and evaluating the performance post-run.

U.S. Pat. No. 7,412,331 describes using an equation based on rock properties for the formations to be drilled combined with string friction factor, mud weight and mechanical efficiency factor.

U.S. Pat. No. 9,970,266 describes using a neural network for real time lithology predictions and base drilling optimization recommendations based on the lithology prediction.

U.S. Pat. No. 9,022,140 describes methods and systems for prediction a range of drilling parameters based on Neural Network lithology predictions.

U.S. Pat. No. 9,057,245 describes calculating mechanical specific energy using published methods for a range of WOB and RPMs, optimum drilling operations are reached when standard deviation of MSE is low.

U.S. Pat. No. 10,591,625 describes automatic comparison and adjustment of drilling parameters towards a pre-defined setpoint.

U.S. Pat. No. 10,657,441 describes using a neural network to predict ROP by receiving real time drilling data and giving advice on parameters to change. Also requires use of static data indicative on the type of drilling data.

U.S. Pat. No. 10,577,914 discloses multi-variable modelling of drilling parameters to optimize drilling performance using a physics model.

U.S. Pat. No. 7,172,037 describes an integrated system of bottomhole assembly (BHA), toolstring sensors and “controller” that predict behavior of the drilling systems to give advice on parameter changes to optimize drilling performance, using neural networks.

U.S. Pat. No. 8,527,249 describes readings to calculate equivalent circulating density (ECD) for different drilling parameters and then propose drilling parameters to be as close to max allowable ECD as possible.

SUMMARY

In some embodiments, the disclosure provides a methodology for remote cloud-based optimization of ROP by recommending values in real-time for rotary speeds, weight-on-bit and mud flow rates that optimize ROP, solely using readily available surface measurements.

In some embodiments, the disclosure provides a methodology for on-premise optimization of ROP by recommending values in real-time for rotary speeds, weight-on-bit and mud flow rates that optimize ROP, solely using readily available surface measurements.

In some embodiments, the disclosure provides a methodology for near wellbore (e.g., rig server) optimization of ROP by recommending values in real-time for rotary speeds, weight-on-bit and mud flow rates that optimize ROP, solely using readily available surface measurements.

In one aspect, the disclosure provides a method for predicting drilling parameters for drilling operation. The method comprises: receiving time-based data from a real-time data system including a sensor; filtering the time-based data from the system; and generating, using a machine learning model, predictions based on the filtered time-based data from the sensor. The predictions include a predicted rate of penetration. The method further includes selecting drilling parameters that yield the highest predicted rate of penetration.

In some embodiments, the predictions include one or more of weight on bit, revolutions per minute and mud flow.

In some embodiments, the time-based data includes one or more of rate of penetration, weight on bit, revolutions per minute and mud flow.

In some embodiments, the time-based data is received at a processor remote from the oil well.

In some embodiments, the processor calculates the average values for one or more sensor values over a time interval or a depth interval.

In some embodiments, one or more machine learning models predict values of one or more of rate of penetration, weight on bit, revolutions per minute, and mud flow based on the measured time-based data or averaged time-based data.

In some embodiments, one or more machine learning model predicts values of one or more of rate of penetration, weight on bit, revolutions per minute, and mud flow based the logarithmic values of the time-based data.

In some embodiments, an algorithm stepwise modifies the measured sensor values and a machine learning model makes a new prediction for each modification.

In some embodiments, predictions are repeated one or more times during the operational sequence.

In some embodiments, one or more of the predicted weight on bit, revolutions per minute and mud flow yielding the highest rate of penetration is selected.

In some embodiments, the predicted weight on bit, revolutions per minute and mud flow yielding the highest rate of penetration is compared with threshold values of said parameters.

In some embodiments, a different rate of penetration and associated parameters is selected if one or more of the parameters exceeds the threshold values.

In some embodiments, the predicted data values are converted to time or depth series data and visualized in a computer user interface.

In some embodiments, the predicted data values are converted to time or depth series data is stored in a database.

In some embodiments, drilling operations are identified by filtering two or more sensors.

In some embodiments, two or more machine learning models utilize the same filtered and normalized data sets and a selection algorithm selects a single preferred prediction data series.

In one aspect, the disclosure provides a system for predicting rate of penetration in oilfield operations comprising: a real time data system associated with at least one oil well; an electronic processor; and a memory. The memory storing instructions that when executed by the electronic processor configure the electronic processor to: receive data from the real time data system; filtering the time-based data from the system; and generating, using a machine learning model, predictions based on the filtered time-based data from the sensor. The predictions include a predicted rate of penetration. The memory storing instructions configure the electronic processor to selecting drilling parameters that yield the highest predicted rate of penetration.

In some embodiments, the real time data system comprises one or more sensors associated with an oil well.

In some embodiments, the processor configured to receive data from the real time data system is remote from the oil well.

In some embodiments, the time measured, predicted drilling parameters, and rate of penetration are visualized in a user interface.

In some embodiments, the user interface is located remote from the oil well.

In some embodiments, the predicted drilling parameters and rate of penetration are converted to time or depth series data and stored in a database.

In some embodiments, receiving data from the real time data system includes data from two or more sensors.

In some embodiments, two or more machine learning models are using the same filtered and normalized data sets and a selection algorithm selects a single preferred prediction data series.

In some embodiments, filtering results from one sensor data series are used as input to the filtering of another sensor data series.

In some embodiments, the instructions executed by the electronic processor is containerized and deployed to a virtual machine in a data center.

In some embodiments, the containerized instructions are deployed on a physical server.

Other aspects of the disclosure will become apparent by consideration of the detailed description and accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of a drilling rig being monitored by sensors.

FIG. 2 is schematic diagram showing a drillbit in a well.

FIG. 3 is a block diagram of steps of a method of the instant invention.

FIG. 4A is an example of user interfaces of the instant invention.

FIG. 4B is an example of user interfaces of the instant invention.

FIG. 5 is a block diagram demonstrating use of sensor data.

FIG. 6 is an example of a display in a data viewer.

FIG. 7 is a block diagram depicting preferred systems of the present invention.

Before any embodiments are explained in detail, it is to be understood that the invention is not limited in its application to the details of construction and the arrangement of components set forth in the following description or illustrated in the following drawings. The invention is capable of other embodiments and of being practices or of being carried out in various ways.

DETAILED DESCRIPTION

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. In case of conflict, the present document, including definitions, will control. Preferred methods and materials are described below, although methods and materials similar or equivalent to those described herein can be used in practice or testing of the present disclosure. All publications, patent applications, patents and other references mentioned herein are incorporated by reference in their entirety. The materials, methods, and examples disclosed herein are illustrative only and not intended to be limiting.

The terms “comprise(s),” “include(s),” “having,” “has,” “can,” “contain(s),” and variants thereof, as used herein, are intended to be open-ended transitional phrases, terms, or words that do not preclude the possibility of additional acts or structures. The singular forms “a,” “an” and “the” include plural references unless the context clearly dictates otherwise. The present disclosure also contemplates other embodiments “comprising,” “consisting of” and “consisting essentially of,” the embodiments or elements presented herein, whether explicitly set forth or not.

For the recitation of numeric ranges herein, each intervening number there between with the same degree of precision is explicitly contemplated. For example, for the range of 6-9, the numbers 7 and 8 are contemplated in addition to 6 and 9, and for the range 6.0-7.0, the number 6.0, 6.1, 6.2, 6.3, 6.4, 6.5, 6.6, 6.7, 6.8, 6.9, and 7.0 are explicitly contemplated.

In addition, it should be understood that embodiments may include hardware, software, and electronic components or modules that, for purposes of discussion may be illustrated and described as if the majority of the components were implemented solely in hardware. However, one of ordinary skill in the art, and based on a reading of this detailed description, would recognize that, in at least one embodiment, the electronic-based aspects may be implemented in software (e.g., stored on non-transitory computer-readable medium) executable by one or more processing units, such as a microprocessor and/or application specific integrated circuits (“ASICs”). As such, it should be noted that a plurality of hardware and software-based devices, as well as a plurality of different structural components, may be utilized to implement the embodiments. For example, “servers” and “computing devices” described in the specification can include one or more processing units, one or more computer-readable medium modules, one or more input/output interface, and various connections (e.g., a system bus) connecting the components. In one embodiment, the software-based components can be containerized and deployed on Virtual Machines (Windows, Linux or similar) in a Data Center that are either cloud based (provided by Azure, AWS or similar) or by the user organization itself. In another embodiment, the software-based components can be deployed on a physical server.

The invention provides a method and system for capturing sensor data in real time from a drilling rig in the oil and gas field. The method and system filters and normalizes the real time data and feed them into to several predictive machine learning models to predict the drilling parameters based on the current drilling performance. The ROP is then calculated for each of the predicted parameters, and an algorithm selects the optimum ROP based on these predictions. The recommended drilling parameters and expected ROP from these parameters are stored in a database and displayed in a computer user interface.

With reference to FIG. 1, a drilling rig 100 or other well operating units (e.g., a workover rigs, a coiled tubing unit, a wireline unit) includes rig equipment 104 (e.g., a block), a mud pump system 108A, 108B, 108C, a drill string 112 (i.e., downhole equipment), and a drill bit 116 for drilling rock 118. As explained herein, to minimize the non-productive times, the operation of the drilling rig 100 is monitored by a sensor 120 coupled to a portion of the rig 100. In some embodiments, more than one sensor is coupled to the drilling rig 100. An output 124 of the sensor 120 is provided to a computer system 150. The output 124 of the sensor 120 includes data that can provide insights in the operations of the rig 100 and the various types of rock 118 being drilled through. In some embodiments, the sensor 120 is a hook load sensor, a torque sensor, a mud density input sensor, a mud flow input sensor, a pressure sensor, a rotations per minute (RPM) sensor, an equivalent circulating density (ECD) sensor, a rate of penetration (ROP) sensor, a drill depth sensor, or any other suitable sensor.

The output 124 from the sensor 120 (i.e., sensor output data) is captured as part of a real-time data system 128 that then stores the output 124 in a drill site computer 154. The drill site computer 154 is typically located on the premises of the drilling rig 100. In the illustrated embodiment, the drill site computer 154 includes a memory storage 158 and a display 162. In some embodiments, the output 124 from the sensor 120 is shown on the display 162 and can be monitored by qualified personnel P1 to verify the quality of operations and to identify deviations or early warnings for undesired events.

With continued reference to FIG. 1, the output 124 from the sensor 120 captured and stored in the computer storage 1158 is also distributed via a network 166. In some embodiments, the network is internet-based. The sensor data 124 is distributed by the network 166 to one or more remote locations 170 outside from the drilling rig 10 (e.g., a remote office buildings). In some embodiments, the sensor data is stored as time or depth series of data at the remote locations 170 on computer storage 174 and shown on displays 178 to other qualified personnel P2.

The network 166 is, for example, a wide area network (“WAN”) (e.g., a TCP/IP based network), a local area network (“LAN”), a neighborhood area network (“NAN”), a home area network (“HAN”), or personal area network (“PAN”) employing any of a variety of communications protocols, such as Wi-Fi, Bluetooth, ZigBee, etc. In some embodiments, the network 166 is a cellular network, such as, for example, a Global System for Mobile Communications (“GSM”) network, a General Packet Radio Service (“GPRS”) network, an Evolution-Data Optimized (“EV-DO”) network, an Enhanced Data Rates for GSM Evolution (“EDGE”) network, a 3GSM network, a 4GSM network, a 5G New Radio, a Digital Enhanced Cordless Telecommunications (“DECT”) network, a digital AMPS (“IS-136/TDMA”) network, an Integrated Digital Enhanced Network (“iDEN”) network, a satellite network, or radiolink network etc.

With reference to FIG. 2, to drill a well, a drillbit 201 is attached to a drillstring 202. During operations, the ROP is a function of the drilling resistance of the various rock formations 203 and the forces applied from the drillbit 201 to the rock formations 203 through weight 204 set down onto the drillbit 201, commonly referred to as weight on bit (WOB); the jetting and cutting removal effect created by the flow of drilling mud 205; and the grinding effect caused by rotation 206. These actions are controlled from the drilling rig 101. The optimal ROP is achieved by selecting an optimum combination of WOB 204, rotation 206 and flow 205. These three parameters: WOB, rotation and flow together are commonly referred to as drilling parameters. The optimum combination of the drilling parameters is dynamic and is a function of rock strength of the different formations 203 as together with the depth, size and path of the well. For the practitioners in the field, that ability to use only rig sensor data in real time has significant advantages.

With reference to FIG. 7, a computer system 180 according to some embodiments is illustrated. Data 124 from the sensor 120 may be pulled via any conventional data transfer protocol from the real time data acquisition, storage and distribution computer 182 (e.g., the drill site computer 154) to a processing computer 184, where predictive methods are performed. Mapping and configuration of data series mnemonics are performed on a configuration user interface via a web interface 186. In some embodiments, the processing computer 184, may be cloud hosted. The actual predictive modelling can be done on a separate, preferably cloud hosted system 188, such as one provided by Microsoft Azure, Amazon Web Services or other commercial cloud provider.

As used herein, the term “computers” includes a plurality of electrical and electronic components that provide power, operational control, and protection to the components and modules within the computers and/or the system. For example, the processing computer 184 includes, among other things, a processing unit (e.g., a microprocessor, a microcontroller, or other suitable programmable device), and is implemented using a known computer architecture (e.g., a modified Harvard architecture, a von Neumann architecture, etc.).

The memory storage of the computers (e.g., storage 158, 174) is a non-transitory computer readable medium and includes, for example, a program storage area and the data storage area. The program storage area and the data storage area can include combinations of different types of memory, such as a ROM, a RAM (e.g., DRAM, SDRAM, etc.), EEPROM, flash memory, a hard disk, a SD card, or other suitable magnetic, optical, physical, or electronic memory devices. The processing unit is connected to the memory and executes software instructions that are capable of being stored in a RAM of the memory (e.g., during execution), a ROM of the memory (e.g., on a generally permanent bases), or another non-transitory computer readable medium such as another memory or a disc. Software included in the implementation of the methods disclosed herein can be stored in the memory. The software includes, for example, firmware, one or more applications, program data, filters, rules, one or more program modules, and other executable instructions. For example, the processing computer 184 is configured to retrieve from the memory and execute, among other things, instructions related to the processes and methods described herein.

With reference to FIGS. 1 and 3, rig equipment and downhole tools are often equipment with sensors 301 (e.g., sensor 120). These sensors describe the operation of the rig, including but not limited to hook load (e.g., the weight of the string 112), block position (the position of 104), torque (e.g., the force used to rotate 112), RPM (e.g., the number of rotations per minute applied to 112), pump pressure and flow rate (e.g., the output values from the pump 108C). The sensors may also be sensors connected to the downhole string 112, either providing measurements on the rig operations, such as load, torque, RPM, flowrate, pump pressure or sensors measuring the properties of the downhole formation 118 including Gamma Ray (GR), Neutron Density data, Sonic response data and others. The method described herein uses sensor data to optimize the ROP.

With continued reference to FIG. 3, the method of the invention utilizes sensor data 301 stored in a computer storage facility at STEP 302. The invention involves reading such data series in a data receptor module at STEP 303 that connects to the data source and retrieves the data of the relevant input data series.

Referring to FIGS. 4A and 4B, the invention contains a user interface FIG. 4A for setting up and to configure data mnemonics FIG. 4B for the relevant sensor data series. Different sources of such data can be WITSML data, WITS0 data, OPC data or other data formats. The data receptor module is an integration service that is tailored to the source, using known system integration methodologies, in the case of WITSML, the receptor module uses XML-queries via a SOAP interface, for OPC-UA a RestAPI is used. The invention allows users to set up the data receptor to retrieve data from a specific server 401, also supporting log-in security requirements 402. The invention further has a user interface that allows the users to configure the wellbore names 403, used by the receptor module to retrieve the correct data, and to select the appropriate data sources 404 for the invention. The sensor data series used by the invention is bit depth, hole depth, mud flow in (MFI), mud density in (MDI), weight-on-bit (WOB), rotary speed (RPM), torque (TRQ) and drillpipe pressure (DPP).

Referring back to FIG. 3, the sensor data handled by the data receptor module at STEP 303 is used by the activity recognition module at STEP 304 that uses known methods to recognize the drilling activity. Only when drilling activity is recognized, the data received by the data receptor module are forwarded to the Filtering and Data preparation module at STEP 305.

Referring to FIG. 5, in the filtering and data preparation module, the applicable sensor data 501 are gathered for two configurable times (t1 an t2) or depth intervals (d1 or d2) by the data aggregation service 502. The aggregated data is then averaged over the t1, t2, d1, and d2 intervals at data averaging service 503. In the data preparation module 504, a series of calculations are made for each calculation time (Tn) or depth (Dn) stamp. In one instance of the invention, these calculations involve EQN. 1 and EQN. 2.

$\begin{array}{cc}\mathrm{Input}1=1/\left(\mathrm{MFI}*\mathrm{MDI}\right)& \left[1\right]\end{array}$ $\begin{array}{cc}\mathrm{Input}2=\left(\mathrm{TRQ}*\mathrm{RPM}\right)/\mathrm{ROP}& \left[2\right]\end{array}$

These calculations are made for each of the aggregated time and depth intervals (t1, t2, d1, d2).

In another instance of the invention, the logarithm or natural logarithm of Input 1 and input 2 are prepared. For each Tn or Dn, a combination of one or more of the following input data are forwarded to the machine learning modules at STEP 306: INPUT=Input 1, log(Input1), ln(input1), input2, log(Input2), ln(input2), MFI, MDI, WOB, RPM. TRQ and DPP, collectively termed INPUT. Based on the input data, the machine learning models predict the drilling parameters and ROP a depth increment, D(n+1) or Time, T(n+1) ahead in time. For each time, Tn or depth Dn stamp, the predictions may be repeated a configurable number of times (N) for one or more of the INPUT parameters. For each time, the input values are variable according to EQN. 3.

$\begin{array}{cc}\mathrm{INPUT}\left(1\mathrm{to}N\right)=\mathrm{INPUT}+/-\left(1\mathrm{to}N\right)*\mathrm{Delta}\left(\mathrm{value}\right)& \left[3\right]\end{array}$

The Delta(value) as well as the N value may be configured individually for each of the parameters that are part of the INPUT. In one instance of the invention, there is a individually configurable threshold value for each of the parameters included in INPUT for one or more of the following values: N, Delta(value), INPUT(1 to N) that applies to one or more of the variables.

The output from the machine learning modules is a series of N+1 set of predicted drilling parameters (WOBN, RPMN and 12lown) with the corresponding predicted ROPN value. Such output is generated for each of the time (Tn) or Depth (Dn) stamp where data is gathered.

For each time (Tn) or Depth (Dn) stamp, in one instance of the invention, the selection algorithm identifies the maximum predicted ROP value at STEP 307 from the set of N+1 possible ROP value and select the corresponding drilling parameters from this value as the recommended drilling parameter. In another instance of the invention, the selection algorithm at STEP 307 compares the selected drilling parameters for the maximum ROP to their pre-set or calculated using known methods, maximum allowable threshold values. If one or more of the drilling parameters exceeds their maximum value, a new set of drilling parameter corresponding to a new maximum ROP are selected and checked against the threshold values. This is repeated until the maximum ROP with allowable drilling parameters are identified.

The selected maximum drilling parameters and the corresponding predicted ROP value are converted to a time-series data be the real Time data converter at STEP 308. The time series data are stored in a data storage at STEP 309 and displayed in a data viewer at STEP 310. The method of the invention may be used in both real time during a drilling operation, and by replaying historical data.

FIG. 6 shows an example of a display in a data viewer (at STEP 310), as an example of the method applied to historical data as a replay. Data sensor values 601 indicating the status of the operation is shown for reference. The drilling parameters (WOB, RPM and Flow) are displayed in separate swimlanes 602. The individual components within each swimlane are a shown with curve 603, which shows the actual drilling parameters as they were during the operation. The recommend drilling parameter is shown as curve 604, based on the prediction method detailed herein. A gap, or delta, between the recommended drilling parameters based on the predictions 604, and the gap between the actual and the recommended values 603 is shown as 605.

FIG. 7 provides a depiction of preferred systems of the present invention. Sensor data may be pulled via any conventional data transfer protocol from the Real Time Data Acquisition, storage and distribution computer 182 to the computer of the invention 184, where the different modules of the invention, 303, 304, 305, 306, 307 and 308 are installed. Mapping and configuration of data series mnemonics are performed on a configuration user interface on a user interface with a web interface 186. The output of the invention are stored in a time and depth based storage and distribution computer 188, which may be the same computers from which data are pulled 182. The data are viewed on a web-based user interface 190 as shown in FIGS. 4A, 4B, and 6.

The systems and methods described herein can be implemented in hardware, software, firmware, or combinations of hardware, software and/or firmware. In some examples, the systems and methods described in this specification may be implemented using a non-transitory computer readable medium storing computer executable instructions that when executed by one or more processors of a computer cause the computer to perform operations.

Various features and advantages are set forth in the following claims.

Claims

1. A method for predicting drilling parameters for drilling operation, the method comprising: receiving time-based data from a real-time data system including a sensor;filtering the time-based data from the system;generating, using a machine learning model, predictions based on the filtered time-based data from the sensor, wherein the predictions include a predicted rate of penetration; andselecting drilling parameters that yield the highest predicted rate of penetration.

2. The method of claim 1, wherein the predictions include one or more of weight on bit, revolutions per minute and mud flow.

3. The method of claim 1, wherein the time-based data includes one or more of rate of penetration, weight on bit, revolutions per minute and mud flow.

4. The method of claim 3, wherein the time-based data is received at a processor remote from the oil well.

5. The method of claim 4, wherein the processor calculates the average values for one or more sensor values over a time interval or a depth interval.

6. The method of claim 4, wherein one or more machine learning models predict values of one or more of rate of penetration, weight on bit, revolutions per minute, and mud flow based on the measured time-based data averaged time-based data or logarithmic values of the time-based data.

7. (canceled)

8. The method of claim 4, wherein an algorithm stepwise modifies the measured sensor values and a machine learning model makes a new prediction for each modification.

9. The method of claim 6, wherein predictions are repeated one or more times during the operational sequence.

10. The method of claim 1, wherein one or more of the predicted weight on bit, revolutions per minute and mud flow yielding the highest rate of penetration is selected.

11. The method of claim 10, wherein the predicted weight on bit, revolutions per minute and mud flow yielding the highest rate of penetration is compared with threshold values of said parameters.

12. The method of claim 11, wherein a different rate of penetration and associated parameters is selected if one or more of the parameters exceeds the threshold values.

13. The method of claim 1, wherein the predicted data values are converted to time or depth series data and stored in a database and/or visualized in a computer user interface.

14. (canceled)

15. The method of claim 1, wherein drilling operations are identified by filtering two or more sensors.

16. The method of claim 1, wherein two or more machine learning models utilize the same filtered and normalized data sets and a selection algorithm selects a single preferred prediction data series.

17. A system for predicting rate of penetration in oilfield operations comprising: a real time data system associated with at least one oil well;an electronic processor and a memory, the memory storing instructions that when executed by the electronic processor configure the electronic processor to: receive data from the real time data system;filtering the time-based data from the system; generating, using a machine learning model, predictions based on the filtered time-based data from the sensor, wherein the predictions include a predicted rate of penetration; andselecting drilling parameters that yield the highest predicted rate of penetration.

18. The system of claim 17, wherein the real time data system comprises one or more sensors associated with an oil well.

19. The system of claim 17, wherein the processor configured to receive data from the real time data system is remote from the oil well.

20. The system of claim 17, wherein the time measured, predicted drilling parameters, and rate of penetration are visualized in a user interface which may be located remote from the oil well or on-site.

21. (canceled)

22. The system of claim 17, wherein the predicted drilling parameters and rate of penetration are converted to time or depth series data and stored in a database.

23. (canceled)

24. (canceled)

25. (canceled)

26. The system of claim 17, wherein the instructions executed by the electronic processor is containerized and deployed to a virtual machine in a data center or on a physical server.

27. (canceled)