System and method for injecting electro-energised injection fluid into oil wells, method for training a neural network, and corresponding computer-readable memory

Abstract

The present invention relates to a system and a method for electro-energising an injection fluid (FI) injected into an oil well (210) in order to reduce the surface tension of the injection fluid (FI), wherein the electro-energisation of the injection fluid (FI) occurs by means of applying high voltage to an electron trap due to the electrical capacitive property of an assembly formed by an injection pipe (250), electro-energisation terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7,..., 135-n), and spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4,..., 110-n), wherein the electro-energisation promotes the reduction of the surface tension of the injection fluid (FI). The present invention further relates to a method for training a neural network for assessing the physicochemical properties of the petroleum fluid (PF) and the injection water (FI), and for decision-making for controlling a processing unit (170) in order to promote electro-acidulation and / or electro-alkalinisation of the injection fluid (FI). Finally, the present invention also relates to a computer-readable memory comprising information and instructions which, when executed, perform an electro-energisation method according to the invention.

Description

SYSTEM AND METHOD FOR INJECTING ELECTRO-ENERGIZED INJECTION FLUID INTO OIL WELLS, NEURAL NETWORK TRAINING METHOD AND CORRESPONDING COMPUTER-READ MEMORY Field of application

[0001] The present invention belongs to the field of methods for obtaining petroleum, oil and gas from wells or mines, notably the electrocoalescence of water-in-oil emulsions by using electron traps and improved recovery methods for obtaining hydrocarbons by increasing their mobility and / or fluid displacement. Introduction

[0002] The present invention relates to a system and a method for electro-energizing an injection fluid injected into an oil well to reduce the surface tension of the injection fluid; wherein the electro-energizing of the injection fluid occurs by applying high voltage.

[0003] The present invention also relates to a method for training a neural network to evaluate the physicochemical properties of the oil to be extracted and the injection fluid to be injected, and to make decisions for controlling a processing unit to promote the electroacidification and / or electroalkalization of the injection fluid.

[0004] Finally, the present invention also relates to a computer-readable memory comprising information and instructions which, when executed, perform an electro-energization method in accordance with the invention. Fundamentals of the invention

[0005] Oil exploration is basically carried out by pumping oil from an underground natural deposit through one or more extraction wells. There may also be, constantly or intermittently, the simultaneous injection of one or more fluids through one or more injection wells located in places distinct from the extraction wells, or even through the extraction well itself using coaxial pipelines, all with the aim of compensating for the mass displacement of the extraction and / or increasing the pressure differential.

[0006] The most commonly used petroleum treatments vary between the use of physical and chemical means for refining, purification, and removal of waste, water, and / or hydrocarbons.

[0007] Physical filters are known and used, such as classic physical barriers, sieves, gravel, activated carbon, polymers, nanoparticles, cavitation, nanocavitation, centrifuges, electrolysis systems, settling tanks, ozonizers, electromagnetic waves, among others, as well as chemical means, such as various chemicals, surfactants and polymers used to flocculate, agglomerate, polarize and purify the extracted oil.

[0008] It should be noted, however, that the state of the art does not provide solutions that utilize the properties and advantages of electron traps as agents for reducing the surface tension of the injection fluid to increase the yield of an oil well. Therefore, in oil extraction from an oil well, the state of the art does not reveal solutions that utilize the electrical capacitive property established inside an injection pipe and a high-voltage source arranged coaxially to the injection pipe, which acts as an electron trap, capable of reducing the surface tension of the injection fluid.

[0009] Furthermore, this exploration is only possible if certain specific conditions exist. For example, the oil must be present in the deposit in high concentration, and there must be sufficient permeability and even sufficient fluid connections between the chambers of the deposit to allow the flow of oil when the reservoir or basin is subjected to a pressure differential. Usually, when there is a sufficiently high level of formation energy (naturally present energy) within the well, the internal pressure, for example, of the gas dissolved in the oil, may be sufficient to eject the oil through an extraction well, which is commonly called primary extraction.

[0010] However, depending on the composition of the natural deposit and the extraction conditions, the oil may not be fully extracted, and a considerable amount of oil may be retained in porous rocks which, like a sponge, retain a significant quantity of oil, even under the effect of pressure differentials from extraction pumping and fluid injection. The same can occur if some of the oil is trapped in depressions or cavities that are difficult to access, or under any other adverse conditions. These conditions require additional extraction operations, commonly called secondary, tertiary, enhanced, or post-primary recovery operations, etc.

[0011] Because of this, a series of additional secondary, tertiary, recovery, or supplementary recovery protocols have been developed in order to improve mining yields in unfavorable mining conditions or those that require additional efforts to increase mining.

[0012] An example of a well-known and widely used state-of-the-art protocol is one that involves the injection of heated water and / or steam. Water, whose heat will aid in the liquefaction of denser oil and thus improve the efficiency of its extraction.

[0013] Water injection is one of the most widely used protocols because it is one of the least expensive. However, water presents a number of disadvantages, especially its low effectiveness in displacing oil, due to the immiscibility of water with oil and the fact that the interfacial tension between water and oil is very high.

[0014] Another protocol uses surfactants to reduce the surface tension of the injected fluid, as well as the interfacial tension between the injected fluid and the oil, providing a significant increase in water penetrability into the rock pores in question, greatly improving the yield of the proposed exploration. Although it has considerable advantages over extraction with water alone, the protocol that uses surfactants, as will be seen in greater detail later, suffers from the limitations of the surfactants themselves, which tend to precipitate and also degrade at high temperatures.

[0015] It is also important to mention that the environment and conditions of oil wells are very varied, always characterized by high temperatures and high salinity levels, and often the presence of divalent ions including calcium and magnesium, resulting in hard water with high surface tension.

[0016] Therefore, in the injection of an injection fluid into an oil well, the state of the art does not reveal solutions that utilize the electrical capacitive property established inside an injection pipe and a high-voltage source arranged coaxially to the injection pipe, which acts as an electron trap, capable of reducing the surface tension of the injection fluid, remembering that the A water-in-oil emulsion can also be an emulsion of water, salts, sand, mineral gases, solid or fluid residues, and ions in oil. State of the art

[0017] The current state of the art, which involves altering the physicochemical characteristics of elements injected into natural oil deposits to aid extraction, more specifically in the recovery of remaining oil, particularly in the more porous layers of the basin, does not yet utilize electron traps.

[0018] One example is the solution revealed by US patent document 6,499,536, which refers to a "Method for increasing the production of oil from an oil reservoir." This patent document describes a method that includes injecting a magnetic or magnetostrictive material through an oil well into an oil reservoir, vibrating this material with the aid of an alternating electric field, and removing the oil from the oil well.

[0019] Based on a reading of patent document US 6,499,536, and considering the figures in that application, it is possible to see that this method produces and injects often undesirable debris, such as sand and chemical compounds. Furthermore, the use of an electric field directly on petroleum can be undesirable, considering its conductivity properties, which can be further increased by temperature conditions. For this reason, the method in US 6,499,536 demands high installation costs, given the elements required for its safe application, including cabling, insulating materials, piping, and specific studies involving local conditions.

[0020] Another solution that utilizes magnetization techniques is that disclosed by US patent document 8,839,856, which describes a "Method and promoter for treatment by electromagnetic waves," which involves exposing a substance to a promoter made of a liquid carrier and a metallic salt, which has at least (i) a magnetic susceptibility above 1000 or (ii) an ionization potential below 500 volts, or (iii) both (i) and (ii). The application of electromagnetic wave energy to the substance is carried out while it is in the presence of the promoter, for a period of time and with sufficient frequency and amplification to promote the modification of at least one physical property of the substance. This substance is used to stimulate the oil or gas reservoir in order to increase the production of the respective well.

[0021] Again, there is the disadvantage of needing specific equipment, as well as the use of chemicals and, especially, electromagnetism, since both influence the physical-chemical characteristics and even the composition of the oil to be extracted, in addition to representing a risk to the environment.

[0022] Another solution revealed by the prior art is that of patent document US 4,438,814, which refers to a "Method of recovering oil by using alternating injections of heavy surfactant mud and fresh water". This patent document deals with a method of recovering oil suitable for recovering oil from underground formations containing water with high salinity and / or concentration of divalent ions, by using an aqueous fluid containing surfactant that is designed to effect low surface tension displacement of oil in the formation, in the presence of high salinity water. The improvement offered by US 4,438,814 comprises the injection of the desired total volume of surfactant. in the form of a plurality of relatively small surfactant fluid slurries and the alternating injection of fresh water slurries, with an equally small pore volume and salinity lower than that of the formation water. The total pore volume of the injected surfactant-containing fluid is typically 0.01 to 1.00 and preferably 0.20 to 0.50 pore volumes. Each surfactant fluid portion is followed by the injection of a quantity of fresh, low-salinity water, for example having a salinity of less than about 10,000 and preferably less than 1,000 parts per million of total dissolved solids. The volume of each low-salinity water isolation portion is less than 0.5 and preferably in the range of 0.05 to 0.20 pore volumes.

[0023] The method in US patent 4,438,814 represents a fairly common solution in the oil and gas field; however, it is again noticeable that this method opts for the use of chemical compounds and even some polymers. These compounds result in additional expenses in the refining and treatment stages of the oil. It is also noted that the alternating sequences allow for the emergence of residual debris that can remain in the well. Another problem with this solution is that surfactants, in addition to being toxic and harmful to the environment, precipitate and also undergo a degradation process at high temperatures, remembering that the temperatures of oil wells and their surroundings easily exceed 140°C. 9 C, and can reach levels close to 200 9 C or higher.

[0024] In addition to the solutions above, another solution revealed by the prior art is that of patent document US 9,689,244, which refers to a "Process for wetting petroleum wettable surfaces with water". This process is achieved by applying an aqueous formulation. comprising at least one wettability modifier, which is a water-soluble ester of an alkoxylated saccharide, at the oil-wettable surface. Oil-wettable surfaces can be any hydrophobic surfaces such as rocks of underground oil formations.

[0025] Again, it is noted that the above solution results in additional expenses in the refining and treatment stages of petroleum, since, in addition to having polymeric compounds, the esters that make up the core of the process are poorly soluble. Furthermore, the physical state of the esters changes easily with ambient temperature. Therefore, the US 9,689,244 solution requires the technician to make several modifications in order to implement it, given the varied circumstances of oil extraction, hindering effective results and potentially resulting in additional costs due to the time involved in the operations.

[0026] Several other state-of-the-art solutions, such as those presented in patent documents US 4,018,278 and US 8,839,856, continue to exhibit problems common to all state-of-the-art technologies. Many of the devices and methods presented require complex installations, demanding the presence of a variety of equipment, and consequently generating greater risks of damage, accidents, and maintenance costs. Other solutions, even those that exhibit effective solutions from the point of view of safety and economy in terms of personnel and facilities, do not provide clean solutions that consider both extraction that requires less from refining and post-processing petroleum, and the environmental impacts involved.

[0027] Taking into account the aforementioned teachings of the state of the art, there is a clear need for a separation solution. emulsions that solve problems not overcome by the relevant state of the art.

[0028] This deficiency is detected in the case of injecting injection fluids into oil wells. Therefore, there is room for an improved oil extraction system and method using the properties of electron traps, which improves the efficiency and effectiveness of oil recovery from the nature discussed here and under the conditions described, using at least one fluid that is easy to obtain, does not harm the environment, has reduced surface tension to the point of penetrating even micropores and most of the porous rock formations of the prospecting, has increased fluidity, increases the fluidity of the oil to be extracted, and has polarity capable of adhering to the oil it will transport. Objectives of the invention

[0029] One of the objectives of the present invention is, therefore, to provide a system for injecting electro-energized injection fluid into oil wells, according to the characteristics of claim 1 of the attached claims.

[0030] Another objective of the present invention is to provide a method for injecting electro-energized injection fluid into oil wells, according to the characteristics of claim 13 of the attached claims.

[0031] Yet another objective of the invention is to provide a method for training a trained convolutional neural network, according to the characteristics of claim 14 of the appended claims.

[0032] Another objective of the present invention is to provide a computer-readable memory, according to the characteristics of claim 15 of the attached claims.

[0033] Other features and details of the features are represented by the dependent claims. Brief description of the figures

[0034] For a better understanding and visualization of the object of the present invention, it will now be described with reference to the attached figures, representing the technical effect obtained through an exemplary embodiment that is not limiting the scope of the present invention, in which, schematically: Figure 1: Presents a front view of an extraction platform comprising the system for injecting electro-energized injection fluid into oil wells, according to a preferred embodiment of the invention; and Figure 2: Shows an enlarged view of detail A from Figure 1. Detailed description of the invention

[0035] The following detailed description refers to the accompanying drawings in which embodiments of the present invention are represented, by way of non-limiting illustration. These embodiments are described in such a way as to allow a person skilled in the art to reproduce their results. Other embodiments resulting from structural, mechanical, logical, electrical and electronic changes are possible and can be carried out without departing from the spirit and scope of the present invention. The following detailed description should therefore not be understood in a restrictive or limiting manner.

[0036] The present invention relates to a system (100) and a method for injecting electro-energized injection fluid (Fl) into oil wells. (210), to a method of training a neural network and to a corresponding computer-readable memory. System, according to a preferred embodiment of the invention.

[0037] The system (100), according to a preferred embodiment of the invention, comprises: i. At least one extraction platform (200), offshore or onshore, for oil exploration from an oil well (210); U. At least one extraction pipeline (220) for extracting fluid petroleum (PF) from the oil well (210); ui. At least one injection pipe (250) for injecting an injection fluid (Fl) into the oil well (210); iv. At least one positive electrical power source (110) and at least one negative electrical power source (111); V. At least one grounding means (250-1) electrically connected to the injection pipe (220) by means of a plurality of connecting cables (112), a plurality of spark gaps and / or diodes (110-2) and a plurality of connectors (113); vi. At least one high-voltage cable (150) arranged coaxially to the injection pipe (250) inside the injection pipe (250) and electrically connected to the power source (110, 111); vii. A plurality of power terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) electrically connected to the high-voltage cable (150) and arranged coaxially to the injection pipe (250) and spaced along the entire length of the high voltage cable (150); VÜi. A plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and at least one oil condition detector (166) immersed in the oil well (210); and ix. At least one processing unit (170) for system control (100); wherein the injection fluid (Fl) to be injected into the oil well (210), at a location distinct from the extraction pipeline (220), is subjected to electromagnetic pulses generated by the electrical power source (110, 111) and controlled by the processing unit (170) comprising a computer-readable memory and a trained convolutional neural network, based on signals from fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and at least one oil condition detector (166) immersed in the oil well (210), the electromagnetic pulses being transmitted to the injection fluid (Fl) by means of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) along the entire path of the injection fluid (Fl) through the injection pipe (250), from an injection fluid injection system (240) on the extraction platform (200) to the oil well (210), wherein the electromagnetic pulses generated by the power source (110, 111) are alternated with switching of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) controlled by the processing unit (170), in which the injection piping (250), together with the power supply terminals (135-1, 135-2, 135-3, 135-4,. 135-5, 135-6, 135-7, ..., 135-n) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n), forms an electron trap due to the electrical capacitive property of the assembly formed by the injection tubing (250), the electro-energization terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n); where the electro-energization of the injection fluid (Fl) promotes the reduction of the surface tension of the injection fluid (Fl).

[0038] The term extraction platform (200) refers to any and all extraction platforms (200), whether offshore - in the high seas or far from the coast - or onshore - on land -, for the exploration of oil from an oil well (210).

[0039] The term "petroleum", according to the invention, refers to petroleum in pumpable fluid form extracted from the oil well (210), this fluid petroleum (FP) being essentially a water-in-oil emulsion, this emulsion may also comprise, in addition to water and oil, but without limiting the invention, salts, sand, gases, ores, solid or fluid residues, ions and all kinds of impurities from the oil well (210) and usual in oil extraction processes, the fluid petroleum (FP) thus also being an emulsion of water, salts, sand, gases, ores, solid or fluid residues, ions and impurities in oil.

[0040] It is worth noting that fluid petroleum (FP) is an emulsion comprising water, salts, sand, gases, ores, solid or fluid residues, ions, and impurities in oil, and thus, the components of this emulsion have different electrical conductivities. Saltwater, ores, and ions, for example, have higher electrical conductivity than gases and the oil itself, where gases and oil, depending on their composition, can even be considered electrical insulators. It is precisely this difference in electrical conductivity that aids in the formation of electrical potential differences between the phases that make up fluid petroleum (FP) which, when electro-energized, according to the invention, begins to separate especially from water and gases.

[0041] The term "injection fluid (Fl)", according to the invention, refers to any and all pumpable fluid to be injected from the injection fluid injection system (240) into the oil well (210) through the injection piping (250), preferably, but without limiting the invention, at a location other than the extraction piping (220). The injection fluid (Fl) may be, for example, but without limiting the invention, an initial aqueous formulation having an initial surface tension consistent with its initial condition (composition, temperature, pressure), comprising at least water, this water being derived directly from a water source and / or a water processing unit and / or from the sea in the form of seawater.It should be noted that the water may be conventional treated water, conventional untreated water, water from artesian wells, mineral water, hard water, brackish water, desalinated water, ionized water, carbonated water, carbonated water, and other known and appropriate forms, this water being, when possible, the water available at or near the oil extraction site.

[0042] An injection fluid system (240) is preferably, but not limited to, a system known in the prior art capable of injecting a pumpable injection fluid (Fl) into an oil well (210), possibly comprising fluid pumping equipment, piping, pressure gauges and other elements, the injection fluid system (240) possibly also comprising a source capable of supplying water, continuously and / or intermittently and / or in batches, in sufficient volume for use in A system according to the invention. This water source may be a well, an external reservoir, a cistern, the ocean and / or sea, a lake, a river, and any other suitable source, this water being, whenever possible, the water available at or near the oil extraction site. Furthermore, an injection fluid system (240) may also comprise a water processing unit or any device, equipment, or installation necessary for preparing the injection fluid (Fl) to make it suitable for use according to the invention, including, but not limited to, filters, centrifuges, presses, desalination plants, water or effluent treatment stations, and other similar suitable devices.

[0043] An oil well (210), in the context of the invention, refers to any and all oil wells (210) drilled in a permeable underground (onshore) or seabed (offshore) formation containing hydrocarbons, including units and installations known in the prior art and necessary for the extraction and / or production and / or processing of hydrocarbons.

[0044] The extraction pipeline (220) is any and all extraction pipeline (220) used to draw and / or receive the upward flow of oil extracted from the oil well (210) on an extraction platform (200).

[0045] Injection piping (250) is any and all injection piping (250) used to inject and / or pump the downward flow of injection fluid (Fl) into an oil well (210) on an extraction platform (200), wherein this injection piping (250) preferably comprises, but without limitation to the invention, an electrically insulated inner surface. It should be noted that this insulation may be insulation applied to the inside of the injection piping (250) and / or insulation resulting from the formation of an oxidation layer on the inner surface of the injection pipe (250), usual in the operation on extraction platforms (200).

[0046] Still within the context of the present invention, the term "electrical energy source" refers to an electrical energy source, with adjustable voltage and pulsed current, which may be direct current and / or alternating current, comprising at least one positive electrical energy source (110) for electron sequestration (electroacidulation) and at least one negative electrical energy source (111) for electron accumulation (electroalkalization).

[0047] The power sources (110, 111) are switchable and electrically connected to the high-voltage cable (250) by means of a set of switches or commutators. This connection also includes a set of diodes to ensure the correct direction of current flow according to the switched / selected source (110, 111) to energize the high-voltage cable (250), thus preventing reverse currents during the electro-energization process and enabling complete ionization as per parameterization. It should be noted that one or more of the diodes may eventually be replaced by contactless spark gap devices.

[0048] It should be noted that, regardless of whether a direct current or alternating current power source is used, practical tests complementary to the studies of the present invention make it clear that the higher the applied voltage, the better and more intense the harmonization of the resulting electron flow within the fluid. The choice of current intensity follows the same reasoning, that is, the higher the applied current, the more uniform the electron flow.

[0049] These considerations, however, should not be understood as limiting the applications of the present invention, since the choice of voltage and current levels will depend on the type of fluid, the conditions and characteristics of the injection fluid (Fl), the injection piping (250) through which it is transferred, any salts and / or gases and / or ions and / or water and / or sand and / or ores and / or impurities and other elements present in the fluids and other conditions that may influence the dielectric characteristics of the assembly.

[0050] That being said, the use of both low and high voltages and currents must be considered, with pulsed direct current being preferable, but without discarding the option of pulsed alternating current. For high-voltage generating sources, we have Van de Graaff sources or trivial sources, capable of generating pulsed or non-pulsed unilateral currents. The electrical voltages can vary within a range of 0.1 V to 1 GV, preferably following the range between 10 and 300 kV, more preferably a range around 15 kV. The frequency of the electrical pulses can be from 60 Hz to 1 x 10 15 Hz, preferably between 60 and 1 kHz.

[0051] Power sources (110, 111) are suitable electrical power sources according to the invention, being direct and / or pulsed alternating current sources that should enable electrical potential differences between 1 kV and 100 GV, preferably, but not limited to, a range between 0.1 V and 10 GV. The choice of voltage will depend essentially on the type of fluid to be energized, the intended energization time, and the presence or absence of any salts and / or gases and / or ions and / or water and / or sand and / or ores and / or impurities and other elements present in the fluids, as well as, of course, the dielectric properties of the equipment and its components and, eventually, from the injection piping (250). The values ​​cited here should not be understood as limiting the scope of the invention, and may be higher or lower than indicated, according to the necessary electrical power conditions.

[0052] Suitable electrical power sources (110, 111) according to the invention are direct current or pulsed alternating current sources that should enable electrical currents between 1 pA and 1 kA, preferably, but not limited to, a range between 1 mA and 100 A. The choice of electrical current intensity will depend essentially on the type of fluid to be energized, the intended energization time, and the presence or absence of any salts and / or gases and / or ions and / or water and / or sand and / or ores and / or impurities and other elements present in the fluids. The electrical power sources (110, 111) can be powered by the existing power grid or by alternative sources such as solar panels, wind turbines, etc. The values ​​and quotations should not be understood as limiting the scope of the invention and may be higher or lower than indicated, according to the necessary electro-energization conditions.

[0053] A grounding means (250-1) is a grounding means electrically connected to the injection piping (250) and which may be from the extraction platform itself (200), interconnecting all elements, parts, components and equipment that contain components or are conductors of electrical energy and which, for the safety of the extraction platform (200), must all be at the same electrical potential, to avoid potential differences that allow the undesirable formation of leakage currents and / or sparks and / or flashes, which are highly dangerous in oil extraction.

[0054] The grounding medium (250-1) is electrically connected to at least one spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110- n) by means of at least one connecting cable (112), which may be any cable or busbar commonly used for interconnecting elements, parts, components and equipment to the grounding. The grounding means (250-1) may be a grounding means already existing on the extraction platform (200) or also a grounding means added subsequently.

[0055] A spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110-n), according to the invention, is any spark gap or similar device known in the prior art and capable of acting as a device for transmitting electrical energy without permanent physical electrical contact, while a diode is any semiconductor component known in the prior art that allows the passage of electric current in only one direction. Such a spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110-n) must exist in order to obtain the necessary conditions for the creation of the electron trap, wherein the spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110-n) is disposed between the connecting cable (112) and the conductor (113) and the electrical contact between the connecting cable (112) and, consequently, the grounding medium (250-1), and the conductor (113) only occurs by the activation of the spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110-n) and, as already described, without mechanical contact between the connecting cable (112) and the conductor (113). The switching of the second spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) is done by means of the processing unit (170).

[0056] The connector (113), in turn, is any electrically conductive element connected to the spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110-n) and to the inside of the injection pipe (250), establishing electrical contact between the fluid oil (PF), the injection pipe (250) and the spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110-n), the connector (113) being a cable or a bus or a pin.

[0057] The spark gap and / or diode (110-2) is connected between the connecting cable (112) and the connector (113), wherein the electrical contact between the connecting cable (112) and the connector (113) occurs by switching the spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110-n) controlled by the processing unit (170) based on signals received from the plurality of condition detectors (165).

[0058] A high-voltage cable (150), according to the invention, is any electrically insulated cable capable of transmitting electrical energy with high voltages and / or currents, the high-voltage cable (150) being arranged coaxially to the injection pipe (250) inside the injection pipe (250) and electrically connected to the electrical energy source (110, 111), the high-voltage cable (150) comprising a plurality of electro-energization terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) electrically connected to the high-voltage cable (150) and arranged coaxially to the injection pipe (250) and spaced along the entire length of the high-voltage cable (150).

[0059] The power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) are any terminals capable of transmitting electrical energy in a controlled manner to the injection fluid (Fl) within the injection piping (250). The second power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n), therefore, are uninsulated terminals so that they can subject the injection fluid (Fl) to pulses of electrical voltages and currents coming from the power source (110, 111) and transmitted by the high-voltage cable (150).

[0060] The switching of electrical pulses from the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) is controlled by the processing unit (170) based on signals received from the condition detectors (165), wherein the number of switchings or pulses per unit of time applied to the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) determines the number of switchings or pulses per unit of time of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n).

[0061] That is, for each predetermined number of switching operations of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) there will be at least one switching operation of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n).

[0062] Between each of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) there are flexible tensioning spacers (131) slidingly fixed to the high-voltage cable (150) by means of sliding fasteners (132), wherein the tensioning spacers (135-1) and the sliding fasteners (135-2) maintain both the spacing between the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the positional and coaxial stability of the high-voltage cable (150) and the power supply terminals (135-1, 135-2, ..., 135-n). 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) inside the injection pipe (250).

[0063] In the context of the present invention, the term "condition detector" refers to any and all devices, equipment or systems known in the prior art capable of detecting, from the measurement of the physicochemical characteristics of both the injection fluid (Fl) within the injection piping (250) and the fluid oil (PF) within the well. The physical quantities acquired continuously or intermittently at predetermined intervals, from one or more fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250), are acquired continuously or intermittently at predetermined intervals, from one or more fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and at least one oil condition detector (166), are transmitted to the processing unit (170), preferably comprising, but not limiting to the invention, values ​​of electrical conductivity and / or electrical resistance, pH, time values, electrical voltage, electrical current, electrical power, impedance, reactance, fluid flow rate, fluid density, fluid temperature, pressure inside the injection pipe (250), water-in-oil emulsion composition or injection fluid composition (Fl), electric field intensity and other physical quantities applicable to the invention, the physical quantities being able to be measured directly and / or indirectly by one or more of the fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and the oil condition detectors (166).

[0064] Fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and oil condition detectors (166) comprise mechanical, luminous, pneumatic, analog, digital and similar sensors known in the prior art, for measuring electrical conductivity and / or electrical resistance, pH, presence of gases, temperature, alkalinity, viscosity, fluid oil inlet flow rate. (PF) or injection fluid outlet flow rate (Fl) and other physical quantities that assist in monitoring and decision-making by the processing unit (170) regarding the switching of electrical pulses from the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and, consequently, regarding the switching of spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n). The signals generated by the plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and oil condition detectors (166), which will be received by the processing unit (170), are input signals corresponding to the physical-chemical condition and properties of the injection fluid (Fl) and the fluid oil (PF) inside the oil well (210).

[0065] A processing unit (170), in the context of the present invention, refers to a computer system or a processing circuit configured to control the system (100), comprising a central processing unit or CPU that executes the instructions of a computer program, processing and executing arithmetic and logical operations and data input and output, the computer program being stored on a computer-readable medium with memory for data storage, connection to one or more communication and data networks and to one or more remote databases and / or a local and / or centralized and / or decentralized and / or cloud-based information storage and retrieval environment, and also equipped with all the usual peripherals of the state of the art, being capable of exchanging information with the electronic and physical medium, interfaces, applications, mobile equipment, other memory devices, etc.

[0066] The processing unit (170) of the invention comprises at least one control unit and a human-machine interface (HMI) comprising information / instruction acquisition devices and information / instruction presentation devices and other devices and / or equipment connected to the system (100) operate together and may be, in groups or separately, interconnected by one or more communication and data networks.

[0067] A processing unit (170) of the invention may be part of a computer system or be divided into one or more modules of a processing circuit. The term module, according to the invention, refers to an application-specific integrated circuit (ASIC), an electronic circuit, a processor (shared, dedicated or group of processors) and a memory that executes one or more software programs or firmware. It also refers to a combinational logic circuit and / or other suitable components capable of providing the functionalities in question.

[0068] A "computer program" according to the invention is a program executable on a processor of the invention and thus on a processing unit (170) of the system (100) of the invention, for example, in the form of an application.

[0069] A "processing circuit" according to the invention is configured to determine a trained neural network according to the invention. This processing circuit may therefore include a processor, such as a central processing unit (CPU), a microcontroller, a microprocessor, a field programmable gate array (FPGA), a graphics card, or special hardware for convolutional neural networks such as the trained convolutional neural network of the invention.

[0070] A "computer-readable memory," in the context of the present invention, is any memory or storage device, remote or local, volatile or non-volatile, transient or non-transient (permanent), that stores information and instructions and, in particular, a computer-readable memory that stores instructions capable of executing an electro-energization method according to the invention.

[0071] A "trained neural network," in the context of the present invention, is a machine learning model configured to provide output instructions in response to the reception of input information, wherein the output instructions are unambiguously and in real time associated with each reading of input information provided by at least one condition detector (165) of the injection fluid (Fl) and fluid oil (PF). A trained neural network, according to the invention, may comprise interconnected groups of artificial neurons (e.g., neuron models), and may also be a computational device or be represented as a method that will be executed by a computational device.A neural network trained according to the invention is a neural network trained with an architecture such that it delivers results quickly and accurately and that it can be run on embedded processors in the system (100) and also, alternatively, on portable processors such as, for example, but not limited to, processors in cell phones, smartphones, tablets and the like, with high processing speed and concomitant accuracy, and may also comprise layers of neurons that can be configured in a receptive field arranged side by side.

[0072] In the context of the present invention, the term "train" refers to adjusting the parameters of the machine learning model so that... Starting from a number of input information associated with previously known values ​​of the physical-chemical conditions and characteristics of the injection fluid (Fl), the fluid oil (PF) and / or values ​​corresponding to predetermined ideal conditions, be able to provide, as output instructions, instructions for the processing unit (170) unequivocally and in real time associated with each reading of input information provided by at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) of the injection fluid (Fl) and oil condition detector (166) of the petroleum fluid (PF), to correct at least one condition and physicochemical characteristic of the injection fluid (Fl) from the condition and physicochemical characteristic of the petroleum fluid (PF), by selecting the electrical power source (110, 111), switching instructions of the electrical pulses of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and, consequently, switching of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n), so that the condition and physicochemical characteristics of the injection fluid (Fl) resemble at least one expected predetermined ideal condition. for the injection fluid (Fl).

[0073] A primary extraction separator (230), according to the invention, is a separator for water, oil, solids and gases known in the prior art, possibly already existing on the extraction platform (200), performing the separation of the elements described above.

[0074] The primary extraction separator (230) may preferably, but without limiting the invention, be a gravity separator for separating the components of the mixture produced in oil wells (210), which generally includes oil, water, gas and solid waste. This equipment operates based on the density difference between the components, allowing them to separate naturally under the influence of gravity, wherein the mixture of fluids (oil, gas and water) and waste enters the separator, within which the difference in density causes the gas to rise to the top, while the water and other waste, being denser, sink to the bottom, while the oil generally remains between these two layers. The gas, oil, solids and water are then extracted through separate outlets for further processing or disposal, wherein the primary extraction separator (230) comprises a primary water pipe (231), a primary oil outlet (232), a primary gas outlet (233) and a primary solids outlet (234).

[0075] The system (100), according to the invention, may further comprise a second electron trap (140) disposed downstream of the primary extraction separator (230) for additional electro-energization of both the water from a primary water pipe (231) and the oil from a primary oil pipe (232) resulting from the separation performed by the primary extraction separator (230), wherein the second electron trap (140) may further comprise a secondary water outlet (231-1), a secondary oil outlet (232-2), a secondary gas outlet (233-1) and a secondary solids outlet (233-1).

[0076] The system (100) may also comprise at least one reel (120-2) for lowering or raising the high voltage cable (150) inside the injection pipe (250). System operation

[0077] The injection fluid (Fl) to be injected into the oil well (210), preferably, but without limitation to the invention, at a location distinct from the extraction pipeline (220), is subjected to electromagnetic pulses generated by the electrical power source (110, 111) and controlled by the processing unit. (170) comprising a computer-readable memory and a neural network, from signals from fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and signals from at least one oil condition detector (166) immersed in the oil well (210), the electromagnetic pulses being transmitted to the injection fluid (FI) via the power terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) along the entire path of the injection fluid (Fl) through the injection pipe (250), from a fluid injection system (240) on the extraction platform. (200) to the oil well (210), where the electromagnetic pulses generated by the electrical power source (110, 111) are alternated with switching of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) controlled by the processing unit (170), in which the injection pipe (250), together with the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n), forms an electron trap due to the electrical capacitive property of the assembly formed by the extraction pipe (220), the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n), in which the electro-energization of the injection fluid (Fl) promotes the reduction of the surface tension of the injection fluid (Fl).

[0078] The electron trap formed by the injection tubing (250) together with the electro-energization terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n), works by switching the electromagnetic pulses generated by the electrical power source (110, 111) and transmitted to the injection fluid (Fl) through the terminals of Electrical energization (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) followed by the switching of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) which, when switched, connect the electron trap to the grounding of the extraction platform (200), generating an electron flow which, after the switching is complete and depending on the instruction generated by the processing unit (170) and / or the neural network from the input signals of the fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection piping. (250) and at least one oil condition detector (166) immersed in the oil well (210), and consequent selection of the positive electrical power source (110) or the negative electrical power source (111), generates an accumulation of positive charges or negative charges in the injection fluid (Fl) in the vicinity of the electro-energization terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135- n), in response to the read physical-chemical conditions and properties. In this way, the electron trap corrects the read physical-chemical conditions and properties of the injection fluid (Fl) to adapt them to the predetermined ideal values, depending on the physical-chemical conditions and properties of the fluid oil (PF) inside the oil well (210) and, thus, enable the reduction of the surface tension of the injection fluid (Fl) and, thus, the reduction of the surface tension of the injection fluid (Fl) and the subsequent increase in the extraction of fluid oil (PF).

[0079] It should be noted that the grounding switching can occur between a certain number of switching operations of the electrical power sources (110, 111) and even before the switching operations of the electrical power sources (110, 111) to promote an initial flow of electrons.

[0080] However, grounding switching is also important in situations where, according to the input signals of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and at least one oil condition detector (166) immersed in the oil well (210), if there is a need to change between an electron sequestration condition and an electron accumulation condition or vice versa, i.e., at the moment of the need for inversion between positive and negative charges or vice versa.

[0081] Furthermore, the grounding may also be switched when there is interference in the operation of the system (100), and thus the switched grounding will be a way to reset the system (100) and / or restart the execution of the method according to the invention.

[0082] The processing unit (170) and / or the neural network will decide and control the ideal moments for switching according to each situation and, therefore, the importance of switched grounding along the injection pipeline (250). The more grounding and power supply points, the more efficient and effective the reduction of the surface tension of the injection fluid (Fl) will be.

[0083] If the input signals generated by at least one oil condition detector (166) inside the oil well (210) indicate that the fluid oil (FO) to be prospected is a 50% water-in-oil emulsion (W / O 50 / 50), then there will be, for example, but without limiting the invention, the generation of two signals from the condition detector sensors (165). Since water is more conductive than oil, there will be an input signal relating to conductivity and permittivity, in addition to an input signal relating to pH values, where water is more alkaline and oil is essentially neutral. In this case of a 50% water-in-50% oil emulsion (W / O 50 / 50), the sensors will indicate that the emulsion has It has average conductivity, meaning a moderate capacity to accumulate electrical charges, and is slightly alkaline (pH of 7.5).

[0084] For situations involving emulsions with less water and more oil, such as a W / O ratio of 30 / 70, and since oil has a neutral pH and lower electrical conductivity than water, the sensors will indicate that the emulsion has low conductivity, meaning a low capacity to accumulate electrical charges, and a pH around 7.

[0085] In the case of emulsions with a higher saltwater content, for example, a 70 / 30 W / O emulsion, the sensors will indicate that the emulsion has high electrical conductivity, meaning a greater capacity to accumulate electrical charges, with a pH tending towards 8.

[0086] Based on the above examples, which are illustrative and not limiting of the invention, it is possible to determine which output instructions the processing unit (170) and / or the neural network will send to the system (100).

[0087] When the oil condition detectors (166) indicate a 50 / 50 W / O emulsion, the processing unit (170) and / or the neural network will command the selection of the positive electrical power source (110) and the alternating switching of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the 5 spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) in order to promote the sequestration of electrons from the emulsion, for example, with electromagnetic pulses with a minimum interval of 1, and which may have their frequency increased or decreased, but always in the same direction of electron sequestration. It is worth noting that the same applies to the presence of gases, where the decrease in the surface tension of water caused by electroacidulation will promote the separation of the liquid and gaseous phases.

[0088] In the case of 30 / 70 W / O emulsions, the processing unit (170) and / or the neural network will control the selection of the positive electrical power source (110) and the alternating switching of the electro-energization terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) in order to promote an even greater sequestration of electrons from the emulsion, for example, with electromagnetic pulses with a minimum interval of 1 second between them, and which may have their frequency increased or decreased, but always in the same direction of electron sequestration. In this way, there will be even greater acidification of the emulsion and, thus, the formation of positive water ions that will force repulsion between oil / fatty acids and water, where this "injection of electrons" will decrease the surface tension of the water, which will facilitate the release and detachment of fluid oil (PF) from the oil well (210), as well as the solids and gases trapped in the water.It is worth noting that the same applies to the presence of gases, where the decrease in the surface tension of water caused by electroacidulation will promote the separation of the liquid and gaseous phases.

[0089] For emulsions with a higher salt content, for example, the 70 / 30 W / O emulsion mentioned in the example above, the processing unit (170) and / or the neural network will control the selection of the negative electrical power source (111) and the alternating switching of the power supply terminals (130) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) in order to promote an accumulation of electrons (electroalkalization), for example, with electromagnetic pulses with a minimum interval of 1 second between them, and whose frequency may be increased or decreased, but always in the same direction of electron accumulation. In this way, there will be an alkalization or saponification of the Emulsion, facilitating the separation of oil from water, due to the reduction of the water's surface tension.

[0090] Regarding the pH of the different phases of a water-in-oil emulsion according to the invention, it is important to consider that there are well-defined pH values ​​for gases in general, where there is a clear difference between the pH values ​​of hydrocarbon gases versus carbon dioxide gases, the same being true for seawater versus crude oil.

[0091] That being said, measuring the pH of an emulsion is a significant way to identify four elements in particular: hydrocarbon gases (since these gases are not ionizable, pH sensors cannot identify them); carbon dioxide gases with high acidity (low pH); crude oil (neutral pH); and underwater water (high pH).

[0092] Hydrocarbon gases, such as methane (CH4) and propane (C3H8), are gases that, when liquefied, do not have a well-defined pH. This is because methane is a chemical compound that does not ionize in water, meaning it does not dissociate into hydrogen ions (H+) and methane ions (CH4) or propane ions (C3H8-). Therefore, there is no concentration of hydrogen ions to measure the pH. Furthermore, methane and propane are gases that do not chemically react with water, meaning there is no chemical reaction that could affect the pH of the solution. Therefore, it is not possible to determine a specific pH for liquefied methane or propane.

[0093] Carbon dioxide (CO2), in turn, is a weak acid that, when dissolved in water, forms carbonic acid (H2CO3). The pH of carbon dioxide dissolved in water depends on the concentration of CO2 in the solution. In general, the pH of carbonic acid is slightly acidic, with a pH between 3.5 and 5.5. Some examples of the pH of carbonic acid solutions at different concentrations are shown below. These are: 1% CO2 in water: pH 4.5; 5% CO2 in water: pH 3.8; and 10% CO2 in water: pH 3.4. It is also important to note that the pH of carbonic acid can vary depending on factors such as temperature, pressure, and the presence of other chemical compounds in the solution.

[0094] The pH of petroleum can vary depending on its chemical composition and the presence of impurities. In general, petroleum is a non-polar liquid that does not ionize in water, meaning it doesn't have a well-defined pH. However, some studies suggest that the pH of petroleum can range from 5.5 to 8.5, depending on its chemical composition and the presence of impurities. Some examples of pH values ​​for different types of petroleum are: Light petroleum: pH 6.5 - 7.5; Heavy petroleum: pH 5.5 - 6.5; and Crude oil: pH 6.0 - 8.0. It is important to note that these values ​​are only estimates and may vary depending on the source and methodology used to measure the pH.

[0095] Finally, the pH of seawater is slightly alkaline, with an average value of around 8.1. This is because seawater contains a large amount of calcium and magnesium ions, which are alkaline. However, it is important to note that the pH of seawater can vary depending on factors such as: depth, as the pH may be lower in deep waters due to the presence of dissolved carbon dioxide; temperature, as the pH may vary with temperature, with higher values ​​in warm waters; salinity, as the pH may vary with salinity, with higher values ​​in saltier waters; and the presence of living organisms, as the pH may be affected by the presence of living organisms such as algae and plankton, which can produce or consume carbon dioxide. Some examples of seawater pH under different conditions are: Surface seawater: pH 8.1-8.3; Deep seawater: pH 7.8-8.0; Warm water: pH 8.2–8.4; and Saltwater: pH 8.3–8.5. It is important to note that these values ​​are only an estimate and may vary depending on the specific location and conditions.

[0096] The electro-energization conditions are essentially determined by the type of source (110, 111), the voltage and current applied by the source (110, 111) to the high-voltage cable (150), and the time of each pulse. The choice of these three parameters is made according to the type and intensity of the electro-energization which, in the case of the present invention, occurs automatically and in real time by submitting, to each reading, input information provided by at least one oil condition detector (166) of the fluid oil (PF) in the oil well (210) and by at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) of the injection fluid (Fl) within the injection pipe (250), to the machine learning model configured to provide output instructions in response to receiving this input information, wherein the output instructions are unambiguously and in real time associated with each reading of input information provided by at least one condition detector (166) of the petroleum fluid (PF) in the oil well (210) and by at least one condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) of the injection fluid (Fl) within the injection pipe (250), altering the electric field intensity of the electron trap according to predetermined ideal values, so that the electron trap promotes the electroacidulation or electroalkalinization of the injection fluid (Fl).

[0097] The selection of the source (110, 111), the command for the voltage and current values ​​of the sources (110, 111), and the control of the operating time of the sources (110, 111) are functions executed and commanded by the processing unit (170), which assigns a protocol to each operating instruction. A predetermined triple source / voltage-current / time, according to the output instructions of the processing unit (170) and / or the trained neural network. Each instruction corresponds to a suitable ionization condition, in real time, for the conditions of the fluid oil (PF) in the oil well (210) and the injection fluid (Fl) inside the injection pipeline (250), separately. It should be noted that the choice of parameters can be unique for one or more electro-energization cycles, for example, when the physical-chemical conditions and characteristics of the fluid oil (PF) and the injection fluid (Fl) are known in advance. It should also be noted that the choice of parameters can be made manually by the user through a human-machine interface (HMI).

[0098] It should also be noted that, due to the continuous real-time correction of the injection fluid (Fl) ionization conditions, there may be an intense variation in these ionization conditions, especially according to the fluid oil (FO) conditions inside the oil well (210) during extraction, due to the constant updating of fluid oil (FO) conditions sent by the oil condition detectors (166).

[0099] In the invention system, electroenergization can be used both for electron sequestration (positive direction - electroacidification) with the selection of the positive source (110) and for electron accumulation (negative direction - electroalkalization) with the selection of the negative source (111), making it possible to obtain the exact quantity of ions with the desired charges (positive or negative direction) or, also, to promote eventual adjustments and corrections of the ion levels of the injection fluid (Fl) in process (mixed or alternating direction) to obtain an injection fluid (Fl) with the desired characteristics, predetermined according to the application and intended purpose for its energization.

[0100] In the context of the present invention, the term "electron sequestration" means that, in the case of the energized fluid, negative ions migrate to the positive pole of the constant polarity electric current immersed in the fluid, causing a desired excess of hydrogen ions (H+). + ) or cations and the consequent increase in the acidity of the fluid, here called electroacidulation. The source selected in this case is the positive electrical energy source (110).

[0101] In the context of the present invention, the term "electron accumulation" means that, in the case of the energized fluid, the positive ions migrate to the negative pole of the constant polarity electric current immersed in the fluid, causing a desired excess of hydroxyl ions (OH-) or anions and the consequent increase in the alkalinity of the fluid, here called electroalkalization. The source selected in this case is the negative source (111).

[0102] According to the invention, the intensity of the electroacidulation is determined by means of the output instructions of the processing unit (170) which will instruct the selection of one or more of two or more possibilities that will be assigned by the processing unit (170) to the corresponding triple protocol(s).

[0103] It should be noted that for the injection fluid (Fl) it is possible to have electroacidification and / or electroalkalinization alternately and simultaneously in different locations of the injection piping (250), for example, in all and / or at different elevations of the injection piping (250).

[0104] The operating time of the electron trap may vary according to the output instructions of the processing unit (170) and thus depending on the instructions for performing one or more energizing switches interspersed with grounding switches according to the readings of the fluid condition detectors. (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and at least one oil condition detector (166) immersed in the oil well (210). Therefore, the time can vary from a few milliseconds to a few seconds, with the fluid flow being a direct function of the time equivalent to the triple protocol instructed by the processing unit (170) or even the triple protocol chosen by the operator via the human-machine interface (HMI).

[0105] It is especially important to emphasize that the electrical voltage applied to the injection fluid (Fl) must be consistent with the materials used in the electron trap, and such that it overcomes the dielectric strength of the insulation in the desired locations, to allow the flow and subsequent sequestration and / or accumulation of electrons, after the grounding is removed, promoting the sequestration and / or accumulation of electrons inside the fluids (PF, Fl) and, thus, the electro-energization of the fluids (PF, Fl).

[0106] In the case of positive direction or electron sequestration, a positive differential is created and the consequent acidification of the injection fluid (Fl). In this process mode, the electrostatic sensitivity of the electro-energized fluid occurs between the positive charges of the fluid and the electrons of the fluid.

[0107] In the case of negative direction or electron accumulation, a negative differential is created, resulting in the alkalization of the injection fluid (Fl). In this process mode, the electrostatic sensitivity of the electro-energized fluid occurs between the negative charges of the fluid and the electrons of the fluid.

[0108] According to the invention, electro-energization has the advantage of reducing the surface tension of the injection fluid (Fl) through an innovative system and method, and also has the advantage of functioning in a wide temperature range, including high temperature and pressure conditions, as well as operating with fluids containing high concentrations of salts, allowing the entry of the electro-energized injection fluid (Fl) into pores of very small calibers and also increasing the penetrability of the injection fluid (Fl) under the rock pores in which the fluid petroleum reserves (PF) are deposited.

[0109] In terms of molecular cohesiveness, the invention provides increased flow and greater fluidity of the injection fluid (Fl).

[0110] Regarding surfactant power, the invention allows polarizing the molecules of the injection fluid (Fl), transforming part of the molecule, for example, water as injection fluid (Fl), partially into hydrophilic and hydrophobic, providing the carrying of water from the oily parts of the petroleum fluid (PF), thus significantly increasing the yield capacity of oil exploration.

[0111] All these undeniable advantages are obtained in a simple and economical way, without generating toxic or contaminating waste, unlike what happens with the use of surfactants. The invention greatly improves the yield of oil exploration and / or recovery without creating contaminants and with care to preserve the local environment. Method

[0112] A method for a system for injecting electro-energized injection fluid into oil wells, according to the invention, is a method implemented by a system (100) comprising at least one extraction platform (200), offshore or onshore, for oil exploration from an oil well (210); at least one pipeline extraction pipe (220) for extracting fluid petroleum (FP) from the oil well (210); at least one injection pipe (250) for injecting an injection fluid (Fl) into the oil well (210); at least one positive electrical power source (110) and at least one negative electrical power source (111); at least one grounding means (250-1) electrically connected to the injection pipe (250) by means of a plurality of connecting cables (112), a plurality of spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) and a plurality of connectors (113); at least one high-voltage cable (150) arranged coaxially to the injection pipe (250) inside the injection pipe (250) and electrically connected to the electrical power source (110, 111); a plurality of electrical power terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) electrically connected to the high-voltage cable (150) and arranged coaxially to the injection pipe (250) and spaced along the entire length of the high-voltage cable (150); a plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and at least one oil condition detector (166); and at least one processing unit (170) for controlling the system (100).

[0113] The method for a system for injecting electro-energized injection fluid into oil wells is a computer-implemented method comprising: a. Installing, on an oil extraction platform (200), at least one electrical power source (110, 111), being one positive electrical power source (110) and one negative electrical power source (111); b. Inserting, inside at least one injection pipe (250) of the extraction platform (200), at least one cable high voltage cable (150) arranged coaxially to the injection pipe (250) and electrically connected to the power source (110, 111), wherein the high voltage cable (150) comprises: a plurality of power terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) electrically connected to the high voltage cable (150) and arranged coaxially to the injection pipe (250) and spaced along the entire length of the high voltage cable (150); and a plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and at least one oil condition detector (166) immersed in the oil well (210); c. Install, on the extraction platform (200), at least one grounding means (250-1) electrically connected to the injection pipe (250) by means of a connecting cable (112), a spark gap (110-1, 110-2, 110-3, 110-4, ..., 110-n) and a connector (113); d.Start extracting oil in the form of fluid oil (FO) through the extraction pipeline (220); and. Receive in the processing unit (170), from the plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n), input signals corresponding to the condition and physical-chemical properties of the injection fluid (Fl) from an injection fluid injection system (240) of the extraction platform (200);. f. Receive in the processing unit (170), from the plurality of oil condition detectors (166) immersed in the oil well (210), input signals corresponding to the condition and physicochemical properties of the fluid oil (PF) inside the oil well (210); g. Submit the input signals from steps "d" and "e" to a trained neural network comprised by a computer-readable memory of the processing unit (170); h. Compare, by means of the trained neural network, the values ​​of the input signals to predetermined ideal condition and physicochemical characteristics for the injection fluid (Fl) depending on the values ​​of the input signals of the fluid oil (PF) inside the oil well (210); i. Generate, using a neural network, as a response to the input signals from the fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and oil condition detectors (166) that represent values ​​different from the predetermined ideal physical-chemical condition and characteristics, at least one output signal in the form of at least one output instruction to the processing unit (170), wherein the output instruction comprises instructions for selecting at least one of the electrical power sources (110, 111), switching of the electromagnetic pulses of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and instructions for switching the first spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n); j. Repeat the reading of the input signals generated by at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and at least one oil condition detector (166), until each input signal has a value similar to and / or equal to at least one predetermined ideal condition assigned to each of the input signals; and Repeat steps e , t , g , h , i and j . Method for training a neural network

[0114] A method for training a neural network, according to the invention, is a method for training a neural network for reading and evaluating the physical-chemical conditions and properties of the injection fluid (Fl) and the petroleum fluid (PF) in a system (100) for injecting an electrically powered injection fluid (Fl) into oil wells (210), and generating instructions for a processing unit (170) that controls the system (100).

[0115] The system (100) comprises at least one extraction platform (200), offshore or onshore, for oil exploration from an oil well (210); at least one extraction pipeline (220) for extracting fluid oil (PF) from the oil well (210); at least one injection pipeline (250) for injecting an injection fluid (Fl) into the oil well (210); at least one positive electrical power source (110) and at least one negative electrical power source (111); at least one grounding means (250-1) electrically connected to the injection pipeline (250) by means of a plurality of connecting cables (112), a plurality of spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) and a plurality of connectors (113); at least one high-voltage cable (150) arranged coaxially to the injection pipe (250) inside the injection pipe (250) and electrically connected to the power source (110, 111); a plurality of power supply terminals (135- 1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) electrically connected to the high-voltage cable (150) and arranged coaxially to the injection pipe (250) and spaced along the entire length of the high-voltage cable (150); a plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and at least one oil condition detector (166); and at least one processing unit (170) for system control (100).

[0116] Training the neural network involves adjusting the machine learning model parameters so that, from a number of input information comprising physical-chemical conditions and characteristics of fluid oil (PF), coming from the plurality of oil condition detectors (166) and fluid condition detectors (165-1, 165- 2, 165-3, 165-4, 165-5, 165-6, ..., 165-n), all connected to the processing unit (170), associate the input information with previously known values ​​of the physical-chemical conditions and characteristics of the fluid petroleum (PF) and / or with values ​​corresponding to predetermined ideal conditions, so that the neural network can provide, as output instructions, instructions for the processing unit (170) unequivocally and in real time associated with each reading of input information provided by at least one oil condition detector (166) of the fluid petroleum (PF) and at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) of the injection fluid (Fl), to correct at least one physical-chemical condition and characteristic of the injection fluid (Fl) by selecting the source of electrical energy (110, 111), Switching instructions for the electrical pulses of the power terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and, consequently, for the switching of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n), so that the fluid conditions (PF, Fl) resemble at least one predetermined ideal condition expected for the fluids (PF, Fl) in the vicinity of the fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and in the vicinity of at least an oil condition detector (166) immersed in the oil well (210).

[0117] The method for training a neural network, according to the invention, is a computer-implemented method comprising: A. Collect a set of input signals from at least one oil condition detector (166) in the form of physical-chemical characteristics of the oil fluid (PF), in particular, but without limiting the invention, input signals relating to the electrical conductivity and / or electrical resistance of the fluid (PF); B. Collect a set of input signals from at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) in the form of physical-chemical characteristics of the petroleum fluid (PF), in particular, but without limiting the invention, input signals relating to the electrical conductivity and / or electrical resistance of the injection fluid (Fl); C. Configure a neural network to receive, as input, a set of predetermined ideal values ​​for different Condition values ​​and physical-chemical characteristics of fluid petroleum (PF); D. Configure the neural network to receive, as input, from at least one first oil condition detector (166), a set of input signals relating to the physical-chemical characteristics of fluid oil (PF); E. Configure the neural network to receive, as input, from at least one first fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n), a set of input signals relating to the physicochemical characteristics of the injection fluid (Fl); F. Unambiguously assign to each input signal at least one predetermined ideal value for different condition values ​​and physicochemical characteristics of the fluid oil (PF) and the injection fluid (Fl) and generate a first training set comprising the collected set of input signals; G. Train the neural network in an initial training stage using the first training set; H. Create a training set for a training stage comprising the first training set and incorrectly detected input signals and input signals with values ​​diverging from the predetermined ideal values; I. Train the neural network in a training stage using the training set; J. Configure the neural network to generate, in response to an input signal from at least one first oil condition detector (166) and at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n), at least one output signal in the form of at least one output instruction to the processing unit (170), wherein the output instruction comprises instructions for selecting the electrical power source (110, 111), switching the electromagnetic pulses of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and switching instructions for the spark gaps and / or diodes (110-1, 110-2, ..., 135-n). 110-3, 110-4, ..., 110-n) for the electro-energization of the injection fluid (Fl) depending on the physical-chemical conditions and properties of the fluid petroleum (PF) and the injection fluid (Fl); K. Repeat the reading of the input signals generated by at least one first condition detector (160) until each input signal has a value similar to and / or equal to at least one predetermined ideal condition assigned to each of the input signals; and L. Produce a neural network by repeatedly training the trained neural network with each of the training datasets. Memory read by computer

[0118] A computer-readable memory, according to a preferred embodiment of the invention, is a memory comprising a a set of information and instructions which, when executed, effect a method for injecting an electrically energised injection fluid (Fl) into oil wells (210).

[0119] Separation of water-in-oil emulsions by electro-energization in oil extraction, according to the invention. Conclusion

[0120] It will be readily understood by those skilled in the art that modifications can be made to the present invention without departing from the concepts set forth in the description above. These modifications should be considered as falling within the scope of the present invention. Consequently, the particular embodiments described in detail above are merely illustrative and exemplary and not limiting as to the scope of the present invention, to which the full extent of the appended claims and all equivalents thereof should be given.

Claims

CLAIMS 1. System for injecting electro-energized injection fluid into oil wells, characterized by comprising: i. At least one extraction platform (200), offshore or onshore, for oil exploration from an oil well (210); U. At least one extraction pipeline (220) for extracting fluid petroleum (PF) from the oil well (210); ui. At least one injection pipe (250) for injecting an injection fluid (Fl) into the oil well (210); iv. At least one positive electrical power source (110) and at least one negative electrical power source (111); V. At least one grounding means (250-1) electrically connected to the injection pipe (220) by means of a plurality of connecting cables (112), a plurality of spark gaps and / or diodes (110-2) and a plurality of connectors (113); vi. At least one high voltage cable (150) arranged coaxially to the injection pipe (250) inside the injection pipe (250) and electrically connected to the power source (110, 111); vii. A plurality of electrical energizing terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) electrically connected to the high-voltage cable (150) and arranged coaxially to the injection pipe (250) and spaced along the entire length of the high-voltage cable (150); VÜi. A plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and at least one oil condition detector (166) immersed in the oil well (210); and ix. At least one processing unit (170) for system control (100).

2. System according to claim 1, characterized in that the injection fluid (Fl) to be injected into the oil well (210), at a location distinct from the extraction pipeline (220), is subjected to electromagnetic pulses generated by the electrical power source (110, 111) and controlled by the processing unit (170) comprising a computer-readable memory and a trained convolutional neural network, based on signals from fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipeline (250) and at least one oil condition detector (166) immersed in the oil well (210), the electromagnetic pulses being transmitted to the injection fluid (Fl) by means of the electro-energization terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) along the entire path of the injection fluid (Fl) through the injection piping (250), from an injection fluid injection system (240) on the extraction platform (200) to the oil well (210), wherein the electromagnetic pulses generated by the electrical power source (110, 111) are alternated with switching of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) controlled by the processing unit (170), wherein the injection piping (250), together with the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n),. forms an electron trap due to the electrical capacitive property of the assembly formed by the injection piping (250), the electro-energization terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n); where the electro-energization of the injection fluid (Fl) promotes the reduction of the surface tension of the injection fluid (Fl).

3. System according to claim 1, characterized in that the injection fluid (Fl) is any and all pumpable fluid to be injected from the injection fluid injection system (240) into the oil well (210) through the injection piping (250), comprising at least water, this water being derived directly from a water source and / or a water processing unit and / or from the sea in the form of seawater.

4. System according to claim 1, characterized in that the fluid petroleum (FP) is a fluid and pumpable water-in-oil emulsion extracted from the oil well (210), the emulsion also possibly comprising salts, sand, gases, ores, solid or fluid residues, ions and all kinds of impurities from the oil well (210).

5. System, according to claim 1, characterized in that the electrical energy source (110,111) is of adjustable voltage with pulsed current, which may be direct current and / or alternating current, comprising at least one positive electrical energy source (110) for electron sequestration (electroacidulation) and at least one negative electrical energy source (111) for electron accumulation (electroalkalization).

6. System according to claim 1, characterized in that the grounding means (250-1) is a grounding means electrically connected to the injection pipe (250) and is electrically connected to a plurality of spark gaps and / or diodes (110-1, 110-2, 110- 3, 110-4, 110-n) by means of at least one connecting cable (112), wherein the connector (113) is an electrically conductive element connected to the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) and to the inside of the injection tubing (250).

7. System according to claim 1, characterized in that the switching of the electrical pulses of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and the switching of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n) are controlled by the processing unit (170) and / or a trained neural network, based on the signals received from the condition detectors (160), wherein the number of switchings or pulses per unit of time applied to the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, ..., 135-n) is ... 135-7, ..., 135-n) determine the number of switching operations or pulses per unit of time of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n).

8. System, according to claim 1, characterized in that for each predetermined number of switching operations of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) there is at least one switching operation of the spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n).

9. System according to claim 1, characterized in that the grounding means (250-1) is a grounding means electrically connected to the injection pipe (250) and is electrically connected to at least one spark gap and / or diode (110-1, 110-2, 110-3, 110-4, ..., 110-n) by means of at least one connecting cable (112).

10. System according to claim 1, characterized by fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and the oil condition detectors (166) immersed in the oil well (210) are sensors for measuring electrical conductivity and / or electrical resistance, pH, presence of gases, temperature, alkalinity, viscosity and flow rate of the injection fluid (Fl).

11. System according to claim 1, characterized in that the processing unit (170) is a computer system or a processing circuit configured to control the system (100), comprising a CPU, at least one control unit and a human-machine interface (HMI).

12. System according to claim 1, characterized in that it may further comprise a second electron trap (140) disposed downstream of the primary extraction separator (230) for additional electro-energization of both the water from a primary water pipe (231) and the oil from a primary oil pipe (232) resulting from the separation performed by the primary extraction separator (230), wherein the second electron trap (140) may further comprise a secondary water outlet (231-1), a secondary oil outlet (232-2), a secondary gas outlet (233-1) and a secondary solids outlet (233-1).

13. Method for injecting electro-energized injection fluid into oil wells, characterized by being a computer-implemented method executed on a system (100) as described in any one of claims 1 to 12, the method comprising: a. Installing, on an oil extraction platform (200), at least one electrical power source (110, 111), being a positive electrical power source (110) and a negative electrical power source (111); b. Insert, inside at least one injection pipe (250) of the extraction platform (200), at least one high-voltage cable (150) arranged coaxially to the injection pipe (250) and electrically connected to the electrical power source (110, 111), wherein the high-voltage cable (150) comprises: a plurality of power terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) electrically connected to the high-voltage cable (150) and arranged coaxially to the injection pipe (250) and spaced along the entire length of the high-voltage cable (150); and a plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) inside the injection pipe (250) and at least one oil condition detector (166) immersed in the oil well (210); c.Install, on the extraction platform (200), at least one grounding means (250-1) electrically connected to the injection pipe (250) by means of a connecting cable (112), a spark gap (110-1, 110-2, 110-3, 110-4, ..., 110-n) and a connector (113); d. Start the extraction of oil in the form of fluid oil (FO) through the extraction pipe (220); e. Receive in the processing unit (170), from the plurality of fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n), input signals corresponding to the condition and physical-chemical properties of the injection fluid (Fl) of an injection fluid system (240) of the extraction platform (200); f. Receive in the processing unit (170), from the plurality of oil condition detectors (166) immersed in the oil well (210), input signals corresponding to the condition and physicochemical properties of the fluid oil (PF) inside the oil well (210); g. Submit the input signals from steps "d" and "e" to a trained neural network comprised by a computer-readable memory of the processing unit (170); h. Compare, by means of the trained neural network, the values ​​of the input signals to predetermined ideal values ​​of condition and physicochemical characteristics for the injection fluid (Fl) depending on the values ​​of the input signals of the fluid oil (PF) inside the oil well (210); i. Generate, using a neural network, as a response to the input signals from the fluid condition detectors (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and oil condition detectors (166) that represent values ​​different from the predetermined ideal physical-chemical condition and characteristics, at least one output signal in the form of at least one output instruction to the processing unit (170), wherein the output instruction comprises instructions for selecting at least one of the electrical power sources (110, 111), switching of the electromagnetic pulses of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and instructions for switching the first spark gaps and / or diodes (110-1, 110-2, 110-3, 110-4, ..., 110-n); j. Repeat the reading of the input signals generated by at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) and at least one oil condition detector (166), until each input signal has a value similar to and / or equal to at least one predetermined ideal condition assigned to each of the input signals; and Repeat steps e , t , g , h , i and j .

14. Method for training a neural network, characterized by being a computer-implemented method for training a neural network for reading and evaluating the physical-chemical conditions and properties of the injection fluid (Fl) and the petroleum fluid (PF) in a system (100) as described in any one of claims 1 to 12, the method comprising: A. Collect a set of input signals from at least one oil condition detector (166) in the form of physical-chemical characteristics of the oil fluid (PF), in particular, but without limiting the invention, input signals relating to the electrical conductivity and / or electrical resistance of the fluid (PF); B. Collect a set of input signals from at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n) in the form of physical-chemical characteristics of the petroleum fluid (PF), in particular, but without limiting the invention, input signals relating to the electrical conductivity and / or electrical resistance of the injection fluid (Fl); C. Configure a neural network to receive, as input, a set of predetermined ideal values ​​for different Condition values ​​and physical-chemical characteristics of fluid petroleum (PF); D. Configure the neural network to receive, as input, from at least one first oil condition detector (166), a set of input signals relating to the physical-chemical characteristics of fluid oil (PF); E. Configure the neural network to receive, as input, from at least one first fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n), a set of input signals relating to the physicochemical characteristics of the injection fluid (Fl); F. Unambiguously assign to each input signal at least one predetermined ideal value for different condition values ​​and physicochemical characteristics of the fluid oil (PF) and the injection fluid (Fl) and generate a first training set comprising the collected set of input signals; G. Train the neural network in an initial training stage using the first training set; H. Create a training set for a training stage comprising the first training set and incorrectly detected input signals and input signals with values ​​diverging from the predetermined ideal values; I. Train the neural network in a training stage using the training set; J. Configure the neural network to generate, in response to an input signal from at least one first oil condition detector (166) and at least one fluid condition detector (165-1, 165-2, 165-3, 165-4, 165-5, 165-6, ..., 165-n), at least one output signal in the form of at least one output instruction to the processing unit (170), wherein the output instruction comprises instructions for selecting the electrical power source (110, 111), switching the electromagnetic pulses of the power supply terminals (135-1, 135-2, 135-3, 135-4, 135-5, 135-6, 135-7, ..., 135-n) and switching instructions for the spark gaps and / or diodes (110-1, 110-2, ..., 135-n). 110-3, 110-4, ..., 110-n) for the electro-energization of the injection fluid (Fl) depending on the physical-chemical conditions and properties of the fluid petroleum (PF) and the injection fluid (Fl); K. Repeat the reading of the input signals generated by at least one first condition detector (160) until each input signal has a value similar to and / or equal to at least one predetermined ideal condition assigned to each of the input signals; and L. Produce a neural network by repeatedly training the trained neural network with each of the training datasets.

15. Computer-readable memory, characterized by comprising a set of information and instructions which, when executed, perform a method for injecting electrically energized injection fluid (Fl) into oil wells, as described in claim 13.

Images