Spectral analysis, machine learning, and frac score assignment to acoustic signatures of fracking events
System, method, and apparatus for classifying fracture quantity and quality of fracturing operation activities during hydraulic fracturing operations, the system comprising: a sensor coupled to a fracking wellhead, circulating fluid line, or standpipe of a well and configured to convert acoustic vibrations in fracking fluid in the fracking wellhead into an electrical signal; a memory configured to store the electrical signal; a converter configured to access the electrical signal from the memory and convert the electrical signal in a window of time into a current frequency domain spectrum; a machine-learning system configured to classify the current frequency domain spectrum, the machine-learning system having been trained on previous frequency domain spectra measured during previous hydraulic fracturing operations and previously classified by the machine-learning system; and a user interface configured to return a classification of the current frequency domain spectrum to an operator of the fracking wellhead.
1. A method of improving fracture quantity and quality in hydraulic fracturing operations, the method comprising:
performing a first fracking operation on a well in a subterranean formation;
providing a sensor coupled to a wellhead, circulating fluid line, or standpipe of the well and configured to convert acoustic vibrations in fluid in the well into an electrical signal in a time domain;
recording the electrical signal to a memory;
converting the electrical signal for a window of time to a current frequency domain spectrum comprising one or more amplitude spikes, the current frequency domain spectrum constituting a measured frequency signature;
analyzing the current frequency domain spectrum via a machine-learning system trained on previous frequency domain spectra measured during previous hydraulic fracturing operations and previously classified by the machine-learning system;
classifying the current frequency domain spectrum as associated with initiation of a fracture in the well; and
adjusting frac design parameters in near real-time based on the quantification and classification to optimize fracture quantity and classification.
2. The method of claim 1 , wherein the sensor samples at greater than 1 kHz or is an acoustic sensor.
3. The method of claim 1 , wherein the sensor is an acoustic sensor.
4. The method of claim 1 , wherein the converting comprises a Fast-Fourier transform.
5. The method of claim 1 , wherein the analyzing considers a number of frequency spikes, a width of the frequency spikes, and an amplitude of the frequency spikes in the current frequency domain spectrum.
6. The method of claim 1 , wherein the machine-learning system is trained on frequency domain spectra measured during previous hydraulic fracturing operations as a machine-learning input and associated well outcomes as machine-learning outputs.
7. The method of claim 6 , wherein the well outcomes comprise a well flow rate.
8. The method of claim 6 , wherein the well outcomes comprise a fracture intersection with a wellbore of a well used during the training.
9. The method of claim 8 , wherein the well outcomes comprise extension of an existing fracture.
10. The method of claim 1 , wherein the classifying is based on a grouping of frequency domain spectra measured during previous hydraulic fracturing operations that most closely match the current frequency domain spectra.
11. The method of claim 1 , wherein the sensor is configured to be in contact with the fluid in the well or with a surface of a circulating fluid line or standpipe at the wellhead.
12. The method of claim 11 , further comprising classifying the Current frequency domain spectrum as associated with geometric parameters of the fracture.
13. The method of claim 1 , further comprising analyzing the electrical signal for the window of time in the time domain and using this in addition to the analyzing the current frequency domain spectrum to perform the classifying.
14. The method of claim 1 , further comprising performing the classifying based also on analysis of pressure sensor data during the window of time.
15. The method of claim 1 , further comprising classifying the Current frequency domain spectrum as associated with intersection of the fracture and the well.
16. The method of claim 15 , further comprising classifying the Current frequency domain spectrum as associated with extension of the fracture.
17. The method of claim 16 , further comprising classifying the Current frequency domain spectrum as associated with a fracture size that is likely to support propping.
18. The method of claim 17 , further comprising classifying the Current frequency domain spectrum as associated with successful propping of the fracture.
19. The method of claim 1 , further comprising classifying the current frequency domain spectrum as associated with extension of the fracture or as associated with at least a temporary end to the extension of the fracture.
20. The method of claim 1 , further comprising classifying the current frequency domain spectrum as associated with at least a temporary end to the extension of the fracture.
21. The method of claim 1 , further comprising classifying the current frequency domain spectrum as associated with a fracture size that is likely to support propping or as associated with successful propping of the fracture.
22. The method of claim 1 , further comprising classifying the current frequency domain spectrum as associated with successful propping of the fracture.
23. The method of claim 1 , further comprising classifying the current frequency domain spectrum as associated with (1) intersection of the fracture and the well, (2) intersection of the fracture and the well, but a fracture size that is unlikely to support propping, or (3) no intersection of the fracture and the well.
24. The method of claim 1 , wherein the converting is performed on a local converter and the current frequency domain spectrum is transported via a large area network to a remote server hosting the machine-learning system.
25. The method of claim 1 , wherein the electrical signal is transported via a large area network to a remote converter for performing the converting.
26. The method of claim 1 , further comprising adjusting parameters of subsequent hydraulic fracturing operations to change how a subsequent frequency domain spectrum is classified.
27. The method of claim 1 , wherein a second fracking operation is adjusted for perforation gun pressure, fracking stage duration, a pressure of fluid forced into the formation during a fracking stage, or a pH of fluid pumped into the well.