A self-cleaning and energy-saving combustion power generation system of oilfield associated gas based on heat exchange

Abstract

The present invention relates to a heat exchange-based oilfield associated gas self-cleaning energy-saving combustion power generation system, comprising a real-time acquisition module; a gas pretreatment module for pre-processing and controlling the associated gas; a gas combustion module; a heat exchange module; a generator set module for controlling the generator set; an emission treatment module for controlling emissions based on emission data; and a self-cleaning control module for performing self-cleaning control based on pollutant data in the associated gas data, calculating the self-cleaning efficiency based on heat conversion efficiency and cleanliness, adjusting the self-cleaning control scale based on the self-cleaning efficiency, and optimizing the inertia correction process of the pre-processing control based on the cost of adjusting the self-cleaning control scale. The present invention introduces a self-cleaning function, eliminating the need for frequent maintenance of the equipment, thereby improving the stability and service life of the burner while achieving energy-saving combustion and power generation.

Description

Technical Field

[0001] The present invention relates to the technical field of burner energy-saving power generation, and in particular to an oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange. Background Art

[0002] Associated gas, a mixture of natural gas and other impurities inevitably generated during oilfield production, is traditionally released directly into the atmosphere, causing environmental pollution and resource waste. Currently, the development and application of associated gas recovery and utilization technologies has become a key approach to reducing greenhouse gas emissions, minimizing environmental pollution, and improving the comprehensive utilization of oil and gas resources. Traditional oilfield water-jacketed boilers typically feed associated gas directly into burners for combustion to provide heat. However, due to the high impurity content in associated gas and increasingly stringent oilfield burner emission requirements, traditional burners operating under associated gas conditions have a short service life and are prone to safety hazards, such as deflagration caused by incomplete combustion. Furthermore, the equipment's intermediate storage requires gas storage tanks, which increases the burden of pressure vessel safety inspections and incurs additional labor and time costs. To address these issues, associated gas self-cleaning burner technology has emerged. This technology optimizes combustion methods to reduce impurities in associated gas, preventing incomplete combustion and related safety issues. Furthermore, the introduction of a self-cleaning function reduces the need for frequent maintenance, achieving energy-saving combustion and power generation while improving burner stability and service life.

[0003] Chinese Patent Publication No.: CN105090953A discloses a combustible gas combustion device that can generate electricity. This combustible gas burner that can generate electricity uses the same amount of combustible gas (fuel) to generate power (electricity generation) in addition to maintaining the original heat energy, thereby increasing the unit output of the combustible gas (fuel). The combustible gas enters the explosion chamber from the combustible gas inlet and is ignited by a timed igniter, causing its volume to explode in the absence of oxygen. The rapidly expanding gas is ejected through the air outlet and blown toward the passive wind wheel, causing it to generate concentric rotational force and transmit it to the generator through the axis. The gas after being blown toward the passive wind wheel generates power and burns when it encounters oxygen, and its flame provides heat energy to the energy-consuming equipment. However, this solution cannot solve the problem that one side of the burner is easily clogged by impurities, affecting the air intake of the burner, and the burner has low stability and short life. Summary of the Invention

[0004] To this end, the present invention provides an oilfield associated gas self-cleaning and energy-saving combustion power generation system based on heat exchange, which is used to overcome the problem in the prior art that the burner is easily clogged by impurities on one side, affecting the air intake of the burner, resulting in low stability and short life of the burner.

[0005] To achieve the above objectives, the present invention provides a self-cleaning and energy-saving combustion power generation system for oilfield associated gas based on heat exchange, comprising:

[0006] Real-time acquisition module, used to collect associated gas data in real time;

[0007] a gas preprocessing module, configured to perform preprocessing control on the associated gas based on the associated gas data to obtain preprocessed associated gas, obtain a prediction correction deviation from the associated gas data based on a simulation curve, perform real-time correction on the preprocessing control based on the prediction correction deviation, and calculate a prediction correction inertia coefficient and perform inertia correction on the preprocessing control based on the prediction correction inertia coefficient;

[0008] a gas combustion module for controlling the combustion of pretreated associated gas based on associated gas data, determining the combustion state based on the concentration of combustion products, and optimizing the combustion control process based on the combustion state; determining the difficulty of oxygen addition based on burner data in the associated gas data, analyzing the necessity of optimization, and adjusting the optimization method of the combustion control process based on the results of the optimization necessity analysis;

[0009] Heat exchange module, used to control heat exchange according to combustion data;

[0010] Generator module, used to control the generator according to heat exchange data;

[0011] Emission processing module, used to perform emission control based on emission data;

[0012] The self-cleaning control module is used to perform self-cleaning control based on the pollutant data in the associated gas data, calculate the self-cleaning efficiency based on the thermal conversion efficiency and cleanliness, adjust the self-cleaning control scale based on the self-cleaning efficiency, and optimize the inertia correction process of the pretreatment control based on the cost of adjusting the self-cleaning control scale.

[0013] Further, specifically, the gas pre-processing module calculates the pre-processing control parameter R according to the associated gas data, and sets The gas pretreatment module compares the pretreatment control parameter R with each preset pretreatment control parameter, and determines the pretreatment means of the associated gas according to the comparison result, and performs pretreatment control on the associated gas according to the pretreatment means of the associated gas to obtain the pretreated associated gas, wherein:

[0014] When R<R1, the gas preprocessing module determines that the preprocessing means of the associated gas is the first preset preprocessing means;

[0015] When R1≤R<R2, the gas pre-processing module determines that the pre-processing means of the associated gas is the second preset pre-processing means;

[0016] When R2≤R<R3, the gas pre-processing module determines that the pre-processing means of the associated gas is the third preset pre-processing means;

[0017] When R3<R, the gas preprocessing module determines that the preprocessing means for the associated gas is the fourth preset preprocessing means.

[0018] Furthermore, the gas pretreatment module calculates the correction coefficient f(T, P) of the burner temperature and the burner pressure according to the burner temperature T and the burner pressure P, and sets f(T, P) = 1 + a × [(T-T0) / T0] + b × [(P-P0) / P0], where T0 is a preset value of the burner temperature under a preset standard state, P0 is a preset value of the burner pressure under a preset standard state, a is a burner temperature influence coefficient, and b is a burner pressure influence coefficient. The burner temperature influence coefficient a and the burner pressure influence coefficient b are determined by experiments;

[0019] The gas pretreatment module calculates the solid particle influence factor φ according to the solid particle concentration CP and the average particle size DM, and sets φ = k1×CP×DM, where k1 is the solid particle calculation coefficient, which is determined by experiments;

[0020] The gas pretreatment module calculates the water vapor influence factor γ according to the relative humidity RH, dew point temperature D and standard dew point temperature D0, and sets γ = k2×RH×e (-D / D0) , k2 is the water vapor calculation coefficient, which is determined by experiment, and e is the base of the natural logarithm.

[0021] Furthermore, the gas preprocessing module constructs an oil and gas flow release physical model based on historical oil field production data, oil field characteristic data, and technical parameter data, and inputs the real-time oil field production data, oil field characteristic data, and technical parameter data into the oil and gas flow release physical model, obtains a simulation curve output by the oil and gas flow release physical model, and inputs the simulation curve into a deviation analysis model to obtain a predicted correction deviation U output by the deviation analysis model, and compares the predicted correction deviation U with a preset predicted correction deviation U0, and determines whether to perform real-time correction on the preprocessing control based on the comparison result, wherein:

[0022] When U≤U0, the gas preprocessing module determines not to perform real-time correction on the preprocessing control;

[0023] When U≤U0, the gas pretreatment module determines to perform real-time correction on the pretreatment control, and performs real-time correction on the concentration of each component, burner temperature, burner pressure, solid particle concentration, average particle size, relative humidity RH and dew point temperature in the pretreatment control according to the predicted correction deviation to obtain real-time corrected data, recalculates the pretreatment control parameter R according to the real-time corrected data, re-judges the pretreatment means of the associated gas, obtains the re-judged pretreatment means of the associated gas, and performs pretreatment control on the associated gas according to the re-judged pretreatment means of the associated gas.

[0024] Furthermore, the gas preprocessing module calculates the predicted correction inertia coefficient YG according to the average predicted deviation UP within the inertia time and the number of real-time corrections NU within the inertia time, and sets YG = [c1, c2, c3, c4, c5, c6, c7] × [UP, NU, |△T|, |△P|, H, F, log (1+UP×NU)], [c1, c2, c3, c4, c5, c6, c7] is the predicted correction inertia coefficient weight parameter matrix, c1+c2+c3+c4+c5+c6+c7=1, |△T| is the temperature change rate, |△P| is the pressure change rate, H is the humidity fluctuation rate, and F is the solid particle concentration fluctuation rate, so as to capture short-term fluctuations, l og(1+UP×NU) is the logarithmic term of the predicted correction inertia coefficient. This term takes into account the interaction effect between the average predicted deviation UP within the inertia duration and the number of real-time corrections NU within the inertia duration. The predicted correction inertia coefficient YG is compared with the preset predicted correction inertia coefficient YG0, and inertia correction is performed on the preprocessing control based on the comparison result.

[0025] When YG≤YG0, the gas preprocessing module does not perform inertia correction on the preprocessing control;

[0026] When YG>YG0, the gas pretreatment module performs inertia correction on the pretreatment control, upgrades the pretreatment means of the associated gas, and uses the upgraded pretreatment means of the associated gas as the pretreatment means of the associated gas after inertia correction. The associated gas is pretreated and controlled according to the pretreatment means of the associated gas after inertia correction to obtain the pretreated associated gas.

[0027] Furthermore, the gas combustion module calculates the air demand AK according to the associated gas data, and sets AK={[∑ i (xi×ni)]×FK} / 0.21, the gas combustion module controls the air introduction according to the air demand AK;

[0028] The gas combustion module calculates the calorific value RZ according to the associated gas data and sets RZ=∑ i(xi×ri), the gas combustion module optimizes the air introduction control according to the calorific value;

[0029] The gas combustion module calculates the combustion air pressure according to the associated gas data, performs combustion pressure control according to the combustion air pressure, and adjusts the air introduction control and the optimization control according to the combustion pressure control situation.

[0030] Furthermore, the gas combustion module compares the carbon monoxide concentration C1 in the combustion product concentration with the preset carbon monoxide concentration C10, and determines the combustion state according to the comparison result, wherein:

[0031] When C1≤C10, the gas combustion module determines that the combustion state is complete combustion;

[0032] When C1>C10, the gas combustion module determines that the combustion state is incomplete combustion, and optimizes the calculation formula of the air demand AK in the combustion control process according to the combustion optimization coefficient ru, and sets the optimized air demand AKu=AK×ru, and sets 1<ru<1.21.

[0033] Furthermore, the gas combustion module generates a burner data distribution map based on the burner data in the associated gas data, and inputs the burner data distribution map into the oxygen doping difficulty analysis model, obtains the oxygen doping difficulty CA output by the oxygen doping difficulty analysis model, and compares the oxygen doping difficulty CA with the preset oxygen doping difficulty CA0, analyzes the necessity of optimization based on the comparison result, and adjusts the optimization method of the combustion control process based on the optimization necessity analysis result, wherein:

[0034] When CA≤CA0, the gas combustion module analyzes whether optimization is necessary, outputs an optimization necessity analysis result indicating that optimization is necessary, and does not adjust the optimization method of the combustion control process;

[0035] When CA>CA0, the gas combustion module analyzes that there is no necessity for optimization, outputs an optimization necessity analysis result that there is no necessity for optimization, and adjusts the optimization method of the combustion control process, adjusting the combustion optimization coefficient ru to 1.

[0036] Furthermore, the self-cleaning control module calculates the self-cleaning start parameter Z according to the pollutant data in the associated gas data, and sets Z=0.3×tz / tz0+0.7×gz / gz0, where tz is the self-cleaning time interval, tz0 is the preset self-cleaning time interval, gz is the self-cleaning pollutant weight, and gz0 is the preset self-cleaning pollutant weight. The self-cleaning control module compares the self-cleaning start parameter Z with the preset self-cleaning start parameter Z0, and judges the self-cleaning control situation according to the comparison result, wherein:

[0037] When Z≤Z0, the self-cleaning control module determines that the self-cleaning control condition is to not start the self-cleaning control;

[0038] When Z>Z0, the self-cleaning control module determines that the self-cleaning control condition is to start the self-cleaning control;

[0039] After starting the self-cleaning control, the self-cleaning control module opens the recoil valve and utilizes the gas in the gas storage device to perform recoil self-cleaning until gz≤(0.3×gz0), and then closes the recoil valve to stop recoil self-cleaning.

[0040] Furthermore, the self-cleaning control module calculates the self-cleaning efficiency zx according to the heat conversion efficiency rx and the cleanliness qx, and sets zx=rx / rx0+qx / qx0. The self-cleaning control module compares the self-cleaning efficiency zx with the preset self-cleaning efficiency zx0 and adjusts the self-cleaning control scale according to the comparison result, wherein:

[0041] When zx≥zx0, the self-cleaning control module determines that the self-cleaning efficiency is high and does not adjust the self-cleaning control scale;

[0042] When zx<zx0, the self-cleaning control module determines that the self-cleaning efficiency is low and adjusts the self-cleaning control scale by increasing the number of filter layers;

[0043] The self-cleaning control module inputs the self-cleaning control information into the cost analysis model, obtains the self-cleaning control scale adjustment cost CB output by the cost analysis model, compares the self-cleaning control scale adjustment cost CB with the preset self-cleaning control scale adjustment cost CB0, and adjusts the inertia correction process of the pre-processing control according to the comparison result, wherein:

[0044] When CB≤CB0, the self-cleaning control module determines not to adjust the inertia correction process of the pre-processing control;

[0045] When CB>CB0, the self-cleaning control module determines to adjust the inertia correction process of the pre-processing control, stops the inertia correction of the pre-processing control, and pushes a suggestion to the user.

[0046] Compared with the existing technology, the beneficial effects of the present invention are that the system ensures the timeliness and accuracy of data through the real-time acquisition module, providing a reliable basis for subsequent control; the system improves combustion efficiency and stability by removing impurities and correcting control through the gas pretreatment module; the system optimizes the combustion process through the gas combustion module, improves heat output and reduces pollutant emissions; the system effectively transfers heat energy through the heat exchange module, reduces losses and improves energy efficiency; the system optimizes the power generation process through the generator set module, enhances the stability and economy of the power output; the system controls emissions through the emission treatment module and reduces environmental pollution; the system improves the system's pollution resistance and lifespan through the self-cleaning control module and reduces the risk of failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a schematic structural diagram of the oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange in this embodiment;

[0048] Figure 2 This is a schematic structural diagram of the oilfield associated gas self-cleaning energy-saving combustion power generation device based on heat exchange in this embodiment. DETAILED DESCRIPTION

[0049] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0050] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0051] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0052] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0053] See also Figure 1 As shown in FIG, which is a structural diagram of the oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange in this embodiment, the system includes:

[0054] Real-time acquisition module, used to collect associated gas data in real time;

[0055] a gas preprocessing module, configured to perform preprocessing control on the associated gas based on the associated gas data to obtain preprocessed associated gas, obtain a prediction correction deviation from the associated gas data based on a simulation curve, perform real-time correction on the preprocessing control based on the prediction correction deviation, and calculate a prediction correction inertia coefficient and perform inertia correction on the preprocessing control based on the prediction correction inertia coefficient;

[0056] a gas combustion module for controlling the combustion of pretreated associated gas based on associated gas data, determining the combustion state based on the concentration of combustion products, and optimizing the combustion control process based on the combustion state; determining the difficulty of oxygen addition based on burner data in the associated gas data, analyzing the necessity of optimization, and adjusting the optimization method of the combustion control process based on the results of the optimization necessity analysis;

[0057] Heat exchange module, used to control heat exchange according to combustion data;

[0058] Generator module, used to control the generator according to heat exchange data;

[0059] Emission processing module, used to perform emission control based on emission data;

[0060] The self-cleaning control module is used to perform self-cleaning control based on the pollutant data in the associated gas data, calculate the self-cleaning efficiency based on the thermal conversion efficiency and cleanliness, adjust the self-cleaning control scale based on the self-cleaning efficiency, and optimize the inertia correction process of the pretreatment control based on the cost of adjusting the self-cleaning control scale.

[0061] Specifically, the system is arranged in the control and management terminal of the oilfield associated gas self-cleaning and energy-saving combustion power generation device. By controlling and managing the oilfield associated gas self-cleaning and energy-saving combustion power generation device, the problem of the oilfield associated gas self-cleaning and energy-saving combustion power generation device being easily blocked by impurities on one side is solved, the air intake of the oilfield associated gas self-cleaning and energy-saving combustion power generation device is avoided, the stability of the oilfield associated gas self-cleaning and energy-saving combustion power generation device is improved, and the service life of the oilfield associated gas self-cleaning and energy-saving combustion power generation device is extended. Among them, the system ensures the timeliness and accuracy of data through a real-time acquisition module, providing a reliable basis for subsequent control; the system improves combustion efficiency and stability by removing impurities and correcting control through a gas pretreatment module; the system optimizes the combustion process through a gas combustion module, improves heat output and reduces pollutant emissions; the system effectively transfers heat energy through a heat exchange module, reduces losses, and improves energy efficiency; the system optimizes the power generation process through a generator set module, enhances the stability and economy of power output; the system controls emissions through an emission treatment module to reduce environmental pollution; the system improves the system's pollution resistance and lifespan through a self-cleaning control module, and reduces the risk of failure.

[0062] Specifically, the associated gas data refers to various data related to oilfield associated gas obtained by monitoring the energy-saving combustion power generation process of oilfield associated gas. The associated gas data includes the concentration of each component in the associated gas, burner temperature, burner pressure, average particle size, relative humidity, dew point temperature, oilfield characteristic data and technical parameter data, real-time oilfield production data, mole fraction of each component in the associated gas, total amount of associated gas, burner data and pollutant data. The components in the associated gas include methane, ethane, propane, carbon dioxide, hydrogen sulfide, water vapor and solid particles. The concentration of each component in the associated gas refers to a data set including methane concentration, ethane concentration, propane concentration, carbon dioxide concentration, hydrogen sulfide concentration, water vapor concentration and solid particle concentration. The real-time acquisition module collects the concentration of each component in the associated gas by analyzing the gas samples sampled and divided in real time by a mass spectrometer. The burner temperature refers to the temperature range inside the burner. The real-time acquisition module measures the burner temperature in real time through an infrared temperature sensor. The burner pressure refers to the gas pressure in the burner. The real-time acquisition module uses a pressure sensor installed on the burner to collect the burner pressure in real time. The average particle size refers to the average diameter of the solid particles in the associated gas. The real-time acquisition module collects the average particle size by sampling and dividing the gas samples in real time through a laser particle size analyzer. The relative humidity refers to the percentage of water vapor content in the associated gas relative to the saturated water vapor content. The real-time The acquisition module uses a humidity sensor to collect the relative humidity in real time. The dew point temperature refers to the temperature at which water vapor in the associated gas begins to condense into liquid water. The real-time acquisition module uses a dew point meter to collect the dew point temperature in real time. The oil field characteristic data refers to characteristic data such as geology, geography and production process of the oil field, such as the environmental humidity of the oil field and the oil field production process. The real-time acquisition module collects the oil field characteristic data in real time through the oil field management system and the production database. The technical parameter data refers to the technical parameter data set used in the oil field acquisition process, such as acquisition depth and acquisition frequency. The real-time acquisition module collects the technical parameter data in real time through the oil field management system. The oil field management system refers to the oil field The computer system for supervising the collection process, the production database refers to the database set in the oil field management system, the real-time oil field production data refers to the real-time monitoring data generated during the oil field production process, such as the real-time collection volume, the real-time collection module collects the real-time oil field production data in real time through the oil field management system, the mole fraction of each component in the associated gas refers to the ratio of the number of moles of each component in the associated gas to the total number of moles, which can be quantitatively analyzed using a gas analyzer, the total amount of associated gas refers to the overall flow rate of the associated gas, and this embodiment uses a flow meter for measurement, the burner data refers to a data set containing the operating status of the burner, including the highest temperature in the burner, the lowest temperature in the burner, the oxygen content in the burner, etc.The pollutant data refers to a data set indicating the degree of contamination caused to the filter during the filtration process of pre-processing the associated gas, including the self-cleaning time interval and the self-cleaning pollutant weight. The self-cleaning time interval refers to the time interval from the last self-cleaning time point to the current time, and the self-cleaning pollutant weight refers to the weight of the pollutants attached to the filter. This embodiment does not limit the real-time collection method of the self-cleaning pollutant weight. Those skilled in the art can freely set it according to actual circumstances, as long as the real-time collection requirement of the self-cleaning pollutant weight is met. For example, the self-cleaning pollutant weight can be collected in real time by attaching a pressure sensor.

[0063] Specifically, the gas pretreatment module calculates the pretreatment control parameter R according to the associated gas data and sets The gas pretreatment module compares the pretreatment control parameter R with each preset pretreatment control parameter, and determines the pretreatment means of the associated gas according to the comparison result, and performs pretreatment control on the associated gas according to the pretreatment means of the associated gas to obtain the pretreated associated gas, wherein:

[0064] When R<R1, the gas preprocessing module determines that the preprocessing means of the associated gas is the first preset preprocessing means;

[0065] When R1≤R<R2, the gas pre-processing module determines that the pre-processing means of the associated gas is the second preset pre-processing means;

[0066] When R2≤R<R3, the gas pre-processing module determines that the pre-processing means of the associated gas is the third preset pre-processing means;

[0067] When R3<R, the gas pre-processing module determines that the pre-processing means of the associated gas is the fourth preset pre-processing means;

[0068] Among them, the preset pretreatment means refer to the process mode of pretreatment of associated gas according to the pretreatment control parameter, including the first preset pretreatment means, the second preset pretreatment means, the third preset pretreatment means and the fourth preset pretreatment means. The pretreatment intensity of the first preset pretreatment means, the second preset pretreatment means, the third preset pretreatment means and the fourth preset pretreatment means is enhanced in sequence. This embodiment does not limit the specific content of the preset pretreatment means. Those skilled in the art can freely set it according to the actual situation, as long as the intensity of the associated gas is distinguished. The filter mesh diameter of the first preset pretreatment means can be set to be larger than the filter mesh diameter of the second preset pretreatment means. R is the pretreatment control parameter, which refers to the quantitative parameter used to judge the pretreatment means of the associated gas. n is the total number of components, which refers to the total number of components in the associated gas. If the components in the associated gas include methane, ethane, propane, carbon dioxide, hydrogen sulfide, water vapor and solid particles, then the total number of components n=7. i is the component order, which refers to the component order in the component data set. If the components in the associated gas include methane, ethane, propane, carbon dioxide, hydrogen sulfide, water vapor and solid particles, the total number of components n=7. In the above example, the component order of methane is 1, and the component order of ethane is 2. Wi is the weight of the i-th component, which refers to the proportion coefficient reflecting the importance of the component in the pretreatment. This embodiment does not limit the setting method of the weight of each component. Those skilled in the art can freely set it according to the actual situation, as long as it meets the judgment requirements of the pretreatment means of the associated gas. For example, the weight of each component can be obtained by analyzing the neural network model, and Ci is the concentration of the i-th component, which refers to the concentration of each component in the associated gas. f(T,P) is the correction coefficient of the burner temperature and the burner pressure, and T is the burner. temperature, P is the burner pressure, α is the solid particle weight coefficient, β is the water vapor weight coefficient, α+β=1, in this embodiment, α=0.7, β=0.3, φ is the solid particle influence factor, γ is the water vapor influence factor, and each preset preprocessing control parameter refers to a preset value of the preprocessing control parameter used to judge the preprocessing means of the associated gas, including a first preset preprocessing control parameter R1, a second preset preprocessing control parameter R2 and a third preset preprocessing control parameter R3, and R1<R2<R3 is set. In this embodiment, R1=2.7, R2=3.5, and R3=4.4;

[0069] The gas pretreatment module calculates the correction coefficient f(T, P) of the burner temperature and the burner pressure according to the burner temperature T and the burner pressure P, and sets f(T, P) = 1 + a × [(T-T0) / T0] + b × [(P-P0) / P0], where T0 is a preset value of the burner temperature under a preset standard state, in this embodiment, T0 = 1500°C, P0 is a preset value of the burner pressure under a preset standard state, in this embodiment, P0 = 200 psi, a is a burner temperature influence coefficient, and b is a burner pressure influence coefficient. The burner temperature influence coefficient a and the burner pressure influence coefficient b are determined by experiments, such as solving a and b by knowing other parameters except a and b in the f(T, P) calculation formula;

[0070] The gas pretreatment module calculates the solid particle influence factor φ according to the solid particle concentration CP and the average particle size DM, and sets φ = k1×CP×DM, where k1 is the solid particle calculation coefficient, which is determined by experiments;

[0071] The gas pretreatment module calculates the water vapor influence factor γ according to the relative humidity RH, dew point temperature D and standard dew point temperature D0, and sets γ = k2×RH×e (-D / D0) , k2 is the water vapor calculation coefficient, which is determined by experiments. For example, the water vapor calculation coefficient can be determined by measuring the gas under known conditions. The known conditions refer to the known relative humidity RH, dew point temperature D, standard dew point temperature D0 and water vapor influence factor γ, and e is the base of the natural logarithm.

[0072] Specifically, the gas preprocessing module constructs an oil and gas flow release physical model based on historical oil field production data, oil field characteristic data and technical parameter data, and inputs the real-time oil field production data, oil field characteristic data and technical parameter data into the oil and gas flow release physical model, obtains a simulation curve output by the oil and gas flow release physical model, and inputs the simulation curve into a deviation analysis model to obtain a predicted correction deviation U output by the deviation analysis model, and compares the predicted correction deviation U with a preset predicted correction deviation U0, and determines whether to perform real-time correction on the preprocessing control based on the comparison result, wherein:

[0073] When U≤U0, the gas preprocessing module determines not to perform real-time correction on the preprocessing control;

[0074] When U≤U0, the gas pretreatment module determines to perform real-time correction on the pretreatment control, and performs real-time correction on the concentration of each component, burner temperature, burner pressure, solid particle concentration, average particle size, relative humidity RH and dew point temperature in the pretreatment control according to the predicted correction deviation to obtain real-time corrected data, recalculates the pretreatment control parameter R according to the real-time corrected data, re-judges the pretreatment means of the associated gas, obtains the re-judged pretreatment means of the associated gas, and performs pretreatment control on the associated gas according to the re-judged pretreatment means of the associated gas.

[0075] Specifically, the historical oilfield production data refers to the oilfield production data before the current moment, which is the historical data of the real-time oilfield production data, representing the specifications, speed and environmental parameters of the oilfield production process. The oilfield characteristic data refers to the data representing the characteristics of the oilfield being produced, such as the longitude and latitude of the oilfield. The technical parameter data refers to the data describing the various dimensions of the oilfield production technology used, such as the maximum production speed. The oil and gas flow release physical model refers to a neural network model used to analyze the simulation curve. This embodiment does not limit the construction method of the oil and gas flow release physical model. Those skilled in the art can freely set it according to actual conditions, as long as the analysis requirements of the simulation curve are met. For example, the historical oilfield production data, oilfield characteristic data and technical parameter data can be pre-processed to obtain historical oilfield production data, oilfield characteristic data and technical parameter data represented in the form of pictures, and the convolutional neural network model is trained based on the historical oilfield production data, oilfield characteristic data and technical parameter data represented in the form of pictures, and the trained convolutional neural network model is set as the oil and gas flow release physical model. The real-time oilfield production The data refers to the data representing the specifications, speed and environmental parameters of the real-time oilfield production process. The deviation analysis model refers to a neural network model that takes the simulation curve as input and predicts the correction deviation as output, such as a convolutional neural network model. The predictive correction deviation U refers to the deviation value between the real-time oilfield production data and the simulation curve obtained by analyzing the simulation curve. The preset predictive correction deviation U0 refers to the preset value of the predictive correction deviation indicating that the deviation is large and the preprocessing control needs to be corrected in real time. For example, if U0=15 is set, the output of the oil and gas flow release physical model is The simulation curve is a collection of curves of the concentration of each component in the pretreatment control, burner temperature, burner pressure, average particle size, relative humidity RH and dew point temperature, which respectively use the concentration of each component in the pretreatment control, burner temperature, burner pressure, average particle size, relative humidity RH and dew point temperature as the vertical axis and time as the horizontal axis. The real-time corrected data is the average of the vertical axis values ​​in the simulation curve output by the oil and gas flow release physical model and the concentration of each component in the pretreatment control, burner temperature, burner pressure, average particle size, relative humidity RH and dew point temperature.

[0076] Specifically, the gas preprocessing module calculates the predicted correction inertia coefficient YG according to the average predicted deviation UP within the inertia time and the number of real-time corrections NU within the inertia time, and sets YG = [c1, c2, c3, c4, c5, c6, c7] × [UP, NU, |△T|, |△P|, H, F, log (1+UP×NU)], [c1, c2, c3, c4, c5, c6, c7] is the predicted correction inertia coefficient weight parameter matrix, c1+c2+c3+c4+c5+c6+c7=1, |△T| is the temperature change rate, |△P| is the pressure change rate, H is the humidity fluctuation rate, and F is the solid particle concentration fluctuation rate, so as to capture short-term fluctuations. og(1+UP×NU) is the logarithmic term of the predicted correction inertia coefficient. This term takes into account the interaction effect between the average predicted deviation UP within the inertia duration and the number of real-time corrections NU within the inertia duration. The predicted correction inertia coefficient YG is compared with the preset predicted correction inertia coefficient YG0, and inertia correction is performed on the preprocessing control based on the comparison result.

[0077] When YG≤YG0, the gas preprocessing module does not perform inertia correction on the preprocessing control;

[0078] When YG>YG0, the gas pretreatment module performs inertia correction on the pretreatment control, upgrades the pretreatment means of the associated gas, and uses the upgraded pretreatment means of the associated gas as the pretreatment means of the associated gas after inertia correction. The associated gas is pretreated and controlled according to the pretreatment means of the associated gas after inertia correction to obtain the pretreated associated gas.

[0079] Specifically, upgrading the pretreatment means of the associated gas refers to gradually increasing each preset pretreatment means, such as upgrading the first preset pretreatment means to the second preset pretreatment means. When upgrading the fourth preset pretreatment means, the upgrade is pushed to the user and the upgrade plan input by the user is obtained. The predicted correction inertia coefficient YG refers to a value used to indicate that within the inertia time, the concentration of each component in the pretreatment control, the burner temperature, the burner pressure, the average particle size, the relative humidity RH and the dew point temperature have regular deviations from the simulation curve output by the oil and gas flow release physical model. When there are regular deviations, the pretreatment means of the associated gas is upgraded in advance to buffer the influence of data distortion caused by other reasons such as sensor insensitivity. The predicted correction inertia coefficient weight parameter matrix refers to the degree of influence of each variable in the adjustment formula on the final result. This embodiment is usually trained and processed through historical data. An optimization algorithm, such as regression analysis or a machine learning model, is used to determine the predicted and corrected inertia coefficient. The temperature change rate refers to the real-time rate of change of temperature during the pretreatment process. In this embodiment, the temperature change rate is obtained by performing a time derivation on the data continuously recorded by the temperature sensor. The pressure change rate refers to the real-time rate of change of pressure during the pretreatment process. In this embodiment, the pressure change rate is obtained by performing a time derivation on the data continuously recorded by the pressure sensor. The humidity fluctuation rate refers to the real-time rate of change of humidity during the pretreatment process. In this embodiment, the humidity change rate is obtained by performing a time derivation on the data continuously recorded by the humidity sensor. The solid particle concentration fluctuation rate refers to the real-time rate of change of the solid particle concentration during the pretreatment process. In this embodiment, the solid particle concentration change rate is obtained by performing a time derivation on the data continuously recorded by the solid particle concentration sensor. The logarithmic term of the predicted and corrected inertia coefficient refers to the term used to process the product of two variables.

[0080] Specifically, the gas combustion module calculates the air demand AK based on the associated gas data and sets AK={[∑ i (xi×ni)]×FK} / 0.21, the gas combustion module controls the air introduction according to the air demand AK;

[0081] The gas combustion module calculates the calorific value RZ according to the associated gas data and sets RZ=∑ i (xi×ri), the gas combustion module optimizes the air introduction control according to the calorific value;

[0082] The gas combustion module calculates the combustion air pressure according to the associated gas data, performs combustion pressure control according to the combustion air pressure, and adjusts the air introduction control and the optimization control according to the combustion pressure control situation.

[0083] Specifically, the air demand refers to the amount of air required for complete combustion of the associated gas under sufficient oxygen conditions, xi is the molar fraction of the i-th component of each component in the associated gas, i is the serial number of each component in the associated gas, ni is the number of moles of oxygen required for complete combustion of the i-th component of each component in the associated gas, FK is the total amount of associated gas, and 0.21 is the volume fraction of oxygen in the air. This embodiment does not limit the air introduction control method. Those skilled in the art can freely set it according to actual conditions, and only need to meet the precise control requirements of the air introduction process. For example, the air introduction process can be precisely controlled by controlling the valve opening. The calorific value RZ refers to the energy released when the associated gas is completely burned, and ri is the standard calorific value of each component in the associated gas. The standard calorific value of each component in the associated gas can be obtained by consulting the data and preset in the system. This embodiment does not limit the method for optimizing the air introduction control. Those skilled in the art can freely set it according to actual conditions, and only need to meet the sufficient combustion requirements of the associated gas. For example, a real-time change curve of the air demand AK and the calorific value RZ can be input into the convolutional neural network. In the model, the air intake control output by the convolutional neural network is obtained for optimization control. The combustion air pressure refers to the target air pressure in the burner to be achieved through regulation. This embodiment does not limit the calculation method of the combustion air pressure. Those skilled in the art can freely set it according to actual conditions, as long as the precise control requirements for the combustion air pressure are met. For example, the combustion air pressure can be calculated based on the required air flow and pipeline characteristics using a fluid dynamics equation, such as the Bernoulli equation. This embodiment does not limit the combustion pressure control method. Those skilled in the art can freely set it according to actual conditions, as long as the control requirements for the combustion pressure are met. For example, the combustion pressure can be controlled using a PID algorithm. The combustion pressure control condition refers to whether the combustion pressure control is successful after the combustion pressure control is performed based on the combustion air pressure. When the combustion pressure control condition is successful, the air intake control and the optimization control are not adjusted. When the combustion pressure control condition is successful, the air intake control and the optimization control are adjusted to suspend the air intake control and the optimization control.

[0084] Specifically, the gas combustion module compares the carbon monoxide concentration C1 in the combustion product concentration with the preset carbon monoxide concentration C10, and determines the combustion state according to the comparison result, wherein:

[0085] When C1≤C10, the gas combustion module determines that the combustion state is complete combustion;

[0086] When C1>C10, the gas combustion module determines that the combustion state is incomplete combustion, and optimizes the calculation formula of the air demand AK in the combustion control process according to the combustion optimization coefficient ru, and sets the optimized air demand AKu=AK×ru, and sets 1<ru<1.21.

[0087] Specifically, the combustion product concentration refers to the concentration of products produced after the associated gas is burned, including carbon dioxide concentration, carbon monoxide concentration, water vapor concentration and nitrogen oxide concentration. The carbon monoxide concentration refers to the carbon monoxide concentration in the products produced after the associated gas is burned. The preset carbon monoxide concentration refers to the preset value of the carbon monoxide concentration indicating that the combustion state is incomplete combustion. In this embodiment, the preset carbon monoxide concentration is 200 ppm.

[0088] Specifically, the gas combustion module generates a burner data distribution map based on the burner data in the associated gas data, and inputs the burner data distribution map into the oxygen doping difficulty analysis model, obtains the oxygen doping difficulty CA output by the oxygen doping difficulty analysis model, and compares the oxygen doping difficulty CA with the preset oxygen doping difficulty CA0. According to the comparison result, the necessity of optimization is analyzed, and the optimization method of the combustion control process is adjusted according to the result of the optimization necessity analysis, wherein:

[0089] When CA≤CA0, the gas combustion module analyzes whether optimization is necessary, outputs an optimization necessity analysis result indicating that optimization is necessary, and does not adjust the optimization method of the combustion control process;

[0090] When CA>CA0, the gas combustion module analyzes that there is no necessity for optimization, outputs an optimization necessity analysis result that there is no necessity for optimization, and adjusts the optimization method of the combustion control process, adjusting the combustion optimization coefficient ru to 1.

[0091] Specifically, the burner data distribution diagram refers to a statistical data diagram generated based on the burner data, with the burner data type as the horizontal axis and the various types of burner data values ​​as the vertical axis. The oxygen doping difficulty analysis model refers to an algorithm model for analyzing the difficulty of adding oxygen to the gas combustion process. This embodiment does not limit the setting method of the oxygen doping difficulty analysis model. Those skilled in the art can freely set it according to actual conditions, as long as the requirements for the oxygen doping difficulty analysis are met. For example, a convolutional neural network model trained by historical burner data distribution diagram data can be set as the oxygen doping difficulty analysis model. The oxygen doping difficulty refers to the output of the oxygen doping difficulty analysis model that represents the difficulty of adding oxygen to the gas combustion process. The preset oxygen doping difficulty refers to the preset value of the oxygen doping difficulty for judging the optimization necessity analysis result. The existence of optimization necessity means that the optimization method of the combustion control process needs to be adjusted. The non-existence of optimization necessity means that the optimization method of the combustion control process does not need to be adjusted.

[0092] Specifically, the heat exchange module preprocesses the combustion data to obtain a real-time combustion data characteristic diagram, and inputs the real-time combustion data characteristic diagram into the heat exchange control analysis model to obtain the heat exchange control instructions output by the heat exchange control analysis model. The heat exchange module performs heat exchange control according to the heat exchange control instructions.

[0093] Specifically, the combustion data refers to the real-time status data of the burner when it is burning the associated gas, including the real-time input amount of the associated gas, real-time temperature, real-time oxygen concentration, and real-time carbon dioxide production. The heat exchange control analysis model refers to a neural network model that uses the real-time combustion data characteristic map as input and the heat exchange control instruction as output. This embodiment does not limit the setting method of the heat exchange control analysis model, such as it can be set to a convolutional neural network model.

[0094] Specifically, the generator set module preprocesses the heat exchange data to obtain a real-time heat exchange data characteristic diagram, and inputs the real-time heat exchange data characteristic diagram into the generator set control analysis model to obtain the generator set control instructions output by the generator set control analysis model. The generator set module controls the generator set according to the generator set control instructions.

[0095] Specifically, the heat exchange data refers to the real-time status data of the burner when performing thermoelectric conversion on associated gas, including the received thermal energy, the output electrical energy and the surface temperature of the thermoelectric conversion component of the generator set. This embodiment does not limit the preprocessing means, and those skilled in the art can freely set it according to actual conditions, as long as the preprocessing requirements of the heat exchange data are met. For example, the heat exchange data can be set to perform missing value processing, and the heat exchange data after missing value processing is converted into the real-time heat exchange data feature graph. The real-time heat exchange data feature graph refers to a statistical graph with each category of data in the heat exchange data as the horizontal axis and the numerical value of each category of data as the vertical axis. The generator set control analysis model refers to a convolutional neural network model with the real-time heat exchange data feature graph as input and the generator set control instruction as output. The generator set control instruction refers to a computer instruction for controlling the thermoelectric conversion process of the generator set. The generator set control refers to the process of controlling the generator set according to the generator set control instruction.

[0096] Specifically, the emission processing module preprocesses the emission data to obtain an emission data characteristic diagram, and inputs the emission data characteristic diagram into the emission control analysis model to obtain the emission control instructions output by the emission control analysis model. The emission processing module performs emission control according to the emission control instructions.

[0097] Specifically, the emission data refers to the data used to determine whether the gas after combustion meets the emission standards after the burner performs thermoelectric conversion on the associated gas. This embodiment does not limit the specific content of the emission data. Those skilled in the art can freely set it according to actual conditions, as long as it meets the judgment requirements of the gas emission standards. For example, the emission data can be set to include sulfur dioxide concentration, carbon monoxide concentration and post-combustion particulate matter concentration. The means for preprocessing the emission data is the same as the means for preprocessing the heat exchange data. The emission data feature graph refers to a statistical graph with each category of data in the emission data as the horizontal axis and the numerical value of each category of data as the vertical axis. The emission control analysis model refers to a convolutional neural network model with the emission data feature graph as input and the emission control instruction as output. The emission control instruction refers to a computer instruction for controlling the emission process after the combustion of the associated gas. The emission control refers to the process of controlling the emission of the associated gas after combustion according to the emission control instruction.

[0098] Specifically, the self-cleaning control module calculates the self-cleaning start parameter Z according to the pollutant data in the associated gas data, and sets Z=0.3×tz / tz0+0.7×gz / gz0, where tz is the self-cleaning time interval, tz0 is the preset self-cleaning time interval, gz is the self-cleaning pollutant weight, and gz0 is the preset self-cleaning pollutant weight. The self-cleaning control module compares the self-cleaning start parameter Z with the preset self-cleaning start parameter Z0, and judges the self-cleaning control situation according to the comparison result, wherein:

[0099] When Z≤Z0, the self-cleaning control module determines that the self-cleaning control condition is to not start the self-cleaning control;

[0100] When Z>Z0, the self-cleaning control module determines that the self-cleaning control condition is to start the self-cleaning control;

[0101] After starting the self-cleaning control, the self-cleaning control module opens the recoil valve and utilizes the gas in the gas storage device to perform recoil self-cleaning until gz≤(0.3×gz0), and then closes the recoil valve to stop recoil self-cleaning.

[0102] Specifically, the self-cleaning time interval refers to the time interval from the current time to the last self-cleaning time, the preset self-cleaning time interval refers to the preset value of the self-cleaning time interval used to judge the self-cleaning control situation, such as being set to 63 hours, the self-cleaning pollutant weight refers to the weight of pollutants attached to the filter net, the preset self-cleaning pollutant weight refers to the preset value of the self-cleaning pollutant weight used to judge the self-cleaning control situation, such as being set to 100g, the self-cleaning start parameter refers to the parameter used to judge the self-cleaning control situation, and the preset self-cleaning start parameter refers to the preset value of the parameter used to judge the self-cleaning control situation, such as being set to 0.95.

[0103] Specifically, the self-cleaning control module calculates the self-cleaning efficiency zx based on the heat conversion efficiency rx and the cleanliness qx, and sets zx=rx / rx0+qx / qx0. The self-cleaning control module compares the self-cleaning efficiency zx with the preset self-cleaning efficiency zx0 and adjusts the self-cleaning control scale according to the comparison result, wherein:

[0104] When zx≥zx0, the self-cleaning control module determines that the self-cleaning efficiency is high and does not adjust the self-cleaning control scale;

[0105] When zx<zx0, the self-cleaning control module determines that the self-cleaning efficiency is low, and adjusts the self-cleaning control scale by increasing the number of filter layers.

[0106] Specifically, the thermal conversion efficiency rx refers to the ratio of the actually generated heat energy to the ideal thermal energy of the associated gas. The ideal thermal energy of the associated gas refers to the thermal energy that can be converted by the associated gas under ideal conditions, which can be calculated based on the total volume of the associated gas. The preset thermal conversion efficiency rx0 refers to a preset value of thermal conversion efficiency reflecting high thermal conversion efficiency, such as being set to 78%. The cleanliness qx refers to the ratio of the self-cleaning pollutant weight to the preset cleaning weight. The preset cleaning weight refers to a preset value indicating a clean weight in a clean state, such as 20g. The preset cleanliness qx0 refers to a preset value of cleanliness reflecting a clean state, such as 25%. The self-cleaning efficiency refers to a value calculated based on the thermal conversion efficiency rx and the cleanliness qx, reflecting the self-cleaning ability. The preset self-cleaning efficiency refers to a preset value of self-cleaning efficiency reflecting high self-cleaning efficiency. , such as 85%. The self-cleaning control scale refers to the control degree of self-cleaning in the associated gas treatment process. This embodiment does not limit the control method of the self-cleaning control scale. Those skilled in the art can freely set it according to actual conditions, and only need to meet the control requirements for self-cleaning. For example, the self-cleaning control scale can be controlled by increasing the number of filter layers. Increasing the number of filter layers refers to increasing the number of filters for filtering the associated gas. This embodiment does not limit the method of increasing the number of filter layers. Those skilled in the art can freely set it according to actual conditions, and only need to meet the increase in the demand for filters. For example, a preset number of filters can be built into the oilfield associated gas self-cleaning energy-saving combustion power generation device based on heat exchange. When the number of filter layers needs to be increased, the built-in preset number of filters are controlled to extend.

[0107] Specifically, the self-cleaning control module inputs the self-cleaning control information into the cost analysis model, obtains the self-cleaning control scale adjustment cost CB output by the cost analysis model, compares the self-cleaning control scale adjustment cost CB with the preset self-cleaning control scale adjustment cost CB0, and adjusts the inertia correction process of the pre-processing control according to the comparison result, wherein:

[0108] When CB≤CB0, the self-cleaning control module determines not to adjust the inertia correction process of the pre-processing control;

[0109] When CB>CB0, the self-cleaning control module determines to adjust the inertia correction process of the pre-processing control, stops the inertia correction of the pre-processing control, and pushes a suggestion to the user.

[0110] Specifically, the self-cleaning control information refers to the information related to the adjustment cost when adjusting the self-cleaning control scale, such as the power consumption cost, the single cost of adding a built-in filter and the adjustment cycle consumption cost. The cost analysis model refers to a convolutional neural network model with the self-cleaning control information as input and the self-cleaning control scale adjustment cost as output. The self-cleaning control scale adjustment cost refers to the cost required to adjust the self-cleaning control scale. The preset self-cleaning control scale adjustment cost refers to the preset value of the acceptable cost required to adjust the self-cleaning control scale, such as setting it to 100 yuan. This embodiment does not specifically limit the way of pushing suggestions to users. Those skilled in the art can freely set it according to actual conditions, and only need to meet the obvious prompt requirements of users, such as setting it to push suggestions to users through pop-up windows.

[0111] See also Figure 2 As shown, it is a structural schematic diagram of the oilfield associated gas self-cleaning energy-saving combustion power generation device based on heat exchange in this embodiment, and the device includes:

[0112] The associated gas self-cleaning device buffer gas tank 1 is used to store the associated gas after buffering and filtration, and is made of 304 stainless steel;

[0113] Pressure transmitter pipe clamp 2, used for connecting the pressure transmitter, which is made of 304 stainless steel;

[0114] The gas outlet pipe hoop 3 is used to output the associated gas from the oil field and is made of 304 stainless steel;

[0115] The filter device is used for self-cleaning filtration of associated gas, which consists of a filter device flange and blind plate 4, a filter device limit pressure ring 5, a filter screen 6, an air inlet elbow 7, a filter device housing 8, a slag discharge pipe 9, and a filter device head 10;

[0116] The filter device flange and blind plate 4 are made of 304 stainless steel;

[0117] The filter device limiting pressure ring 5 is used to limit the filter screen 6 and is made of 304 stainless steel;

[0118] Filter 6, used for filtering associated gas, which is made of 304 stainless steel;

[0119] The air inlet elbow 7 is used for the intake of associated gas and is made of 304 stainless steel;

[0120] The filter housing 8 is used to provide support for the filter screen 6 and is made of 304 stainless steel;

[0121] The slag discharge pipe 9 is used to remove the self-cleaning pollutants after the filter screen 6 is self-cleaned, and is made of 304 stainless steel;

[0122] The filter head 10 is made of 304 stainless steel;

[0123] Legs 11, used to support the device, which are made of 304 stainless steel;

[0124] The drainage elbow 12 is used for regular drainage of the buffer gas tank and is made of 304 stainless steel;

[0125] Buffer gas tank 13, which is made of 304 stainless steel;

[0126] Internal connecting pipe 14, used to connect the filtering device and the buffer gas tank 13, which is made of 304 stainless steel;

[0127] The filter screen support pad 15 is used to support the filter screen 6 and is made of 304 stainless steel.

[0128] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A self-cleaning and energy-saving combustion power generation system for oilfield associated gas based on heat exchange, characterized in that: include: Real-time acquisition module, used to collect associated gas data in real time; a gas preprocessing module, configured to perform preprocessing control on the associated gas based on the associated gas data to obtain preprocessed associated gas, obtain a prediction correction deviation from the associated gas data based on a simulation curve, perform real-time correction on the preprocessing control based on the prediction correction deviation, and calculate a prediction correction inertia coefficient and perform inertia correction on the preprocessing control based on the prediction correction inertia coefficient; a gas combustion module for controlling the combustion of pretreated associated gas based on associated gas data, determining the combustion state based on the concentration of combustion products, and optimizing the combustion control process based on the combustion state; determining the difficulty of oxygen addition based on burner data in the associated gas data, analyzing the necessity of optimization, and adjusting the optimization method of the combustion control process based on the results of the optimization necessity analysis; Heat exchange module, used to control heat exchange according to combustion data; Generator module, used to control the generator according to heat exchange data; Emission processing module, used to perform emission control based on emission data; The self-cleaning control module is used to perform self-cleaning control based on the pollutant data in the associated gas data, calculate the self-cleaning efficiency based on the thermal conversion efficiency and cleanliness, adjust the self-cleaning control scale based on the self-cleaning efficiency, and optimize the inertia correction process of the pretreatment control based on the cost of adjusting the self-cleaning control scale.

2. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 1 is characterized in that: Specifically, the gas pretreatment module calculates the pretreatment control parameter R according to the associated gas data and sets , where n is the total number of components, Wi is the weight of the i-th component, Ci is the concentration of the i-th component, T is the burner temperature, P is the burner pressure, α is the solid particle weight coefficient, β is the water vapor weight coefficient, φ is the solid particle influence factor, γ is the water vapor influence factor, f(T,P) is the correction coefficient of the burner temperature and the burner pressure, T is the burner temperature, and P is the burner pressure. The gas pretreatment module compares the pretreatment control parameter R with each preset pretreatment control parameter, and judges the pretreatment means of the associated gas based on the comparison result. The associated gas is pretreated and controlled according to the pretreatment means of the associated gas to obtain the pretreated associated gas, where: When R<R1, the gas preprocessing module determines that the preprocessing means of the associated gas is the first preset preprocessing means; When R1≤R<R2, the gas pre-processing module determines that the pre-processing means of the associated gas is the second preset pre-processing means; When R2≤R<R3, the gas pre-processing module determines that the pre-processing means of the associated gas is the third preset pre-processing means; When R3<R, the gas preprocessing module determines that the preprocessing means for the associated gas is the fourth preset preprocessing means.

3. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 1 is characterized in that: The gas pretreatment module calculates the correction coefficient f(T, P) of the burner temperature and the burner pressure according to the burner temperature T and the burner pressure P, and sets f(T, P)=1+a×[(T-T0) / T0]+b×[(P-P0) / P0], where T0 is a preset value of the burner temperature under a preset standard state, P0 is a preset value of the burner pressure under a preset standard state, a is a burner temperature influence coefficient, and b is a burner pressure influence coefficient. The burner temperature influence coefficient a and the burner pressure influence coefficient b are determined by experiments; The gas pretreatment module calculates the solid particle influence factor φ according to the solid particle concentration CP and the average particle size DM, and sets φ=k1×CP×DM, where k1 is the solid particle calculation coefficient, which is determined by experiments; The gas pretreatment module calculates the water vapor influence factor γ according to the relative humidity RH, dew point temperature D and standard dew point temperature D0, setting γ=k2×RH×e (-D / D0) , k2 is the water vapor calculation coefficient, which is determined by experiment, and e is the base of the natural logarithm.

4. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 1 is characterized in that: The gas preprocessing module constructs an oil and gas flow release physical model based on historical oilfield production data, oilfield characteristic data, and technical parameter data, and inputs the real-time oilfield production data, oilfield characteristic data, and technical parameter data into the oil and gas flow release physical model, obtains a simulation curve output by the oil and gas flow release physical model, and inputs the simulation curve into a deviation analysis model, obtains a predicted correction deviation U output by the deviation analysis model, and compares the predicted correction deviation U with a preset predicted correction deviation U0, and determines whether to perform real-time correction on the preprocessing control based on the comparison result, wherein: When U≤U0, the gas preprocessing module determines not to perform real-time correction on the preprocessing control; When U>U0, the gas pretreatment module determines to perform real-time correction on the pretreatment control, and performs real-time correction on the concentration of each component, burner temperature, burner pressure, solid particle concentration, average particle size, relative humidity RH and dew point temperature in the pretreatment control according to the predicted correction deviation to obtain real-time corrected data, recalculates the pretreatment control parameter R according to the real-time corrected data, re-judges the pretreatment means of the associated gas, obtains the re-judged pretreatment means of the associated gas, and performs pretreatment control on the associated gas according to the re-judged pretreatment means of the associated gas.

5. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 1 is characterized in that: The gas preprocessing module calculates the predicted correction inertia coefficient YG according to the average predicted deviation UP within the inertia time and the number of real-time corrections NU within the inertia time, and sets YG=[c1,c2,c3,c4,c5,c6,c7]×[UP,NU,|△T|,|△P|,H,F,log(1+UP×NU)], [c1,c2,c3,c4,c5,c6,c7] is the predicted correction inertia coefficient weight parameter matrix, c1+c2+c3+c4+c5+c6+c 7=1, |△T| is the temperature change rate, |△P| is the pressure change rate, H is the humidity fluctuation rate, F is the solid particle concentration fluctuation rate, which is used to capture short-term fluctuations, log(1+UP×NU) is the logarithmic term of the predicted correction inertia coefficient, which is used to consider the interaction effect between the average predicted deviation UP within the inertia duration and the number of real-time corrections NU within the inertia duration. The predicted correction inertia coefficient YG is compared with the preset predicted correction inertia coefficient YG0, and inertia correction is performed on the preprocessing control based on the comparison result, where: When YG≤YG0, the gas preprocessing module does not perform inertia correction on the preprocessing control; When YG>YG0, the gas pretreatment module performs inertia correction on the pretreatment control, upgrades the pretreatment means of the associated gas, and uses the upgraded pretreatment means of the associated gas as the pretreatment means of the associated gas after inertia correction. The associated gas is pretreated and controlled according to the pretreatment means of the associated gas after inertia correction to obtain the pretreated associated gas.

6. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 1 is characterized in that: The gas combustion module calculates the air demand AK based on the associated gas data, setting AK={[∑ i (xi×ni)]×FK} / 0.21, wherein xi is the mole fraction of the i-th component of each component in the associated gas, i is the sequence number of each component in the associated gas, ni is the number of moles of oxygen required for complete combustion of the i-th component of each component in the associated gas, and FK is the total amount of associated gas. The gas combustion module controls air introduction according to the air demand AK; The gas combustion module calculates the calorific value RZ according to the associated gas data, setting RZ=∑ i (xi×ri), wherein ri is the standard calorific value of each component in the associated gas, and the gas combustion module optimizes the air introduction control according to the calorific value; The gas combustion module calculates the combustion air pressure according to the associated gas data, performs combustion pressure control according to the combustion air pressure, and adjusts the air introduction control and the optimization control according to the combustion pressure control situation.

7. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 6 is characterized in that: The gas combustion module compares the carbon monoxide concentration C1 in the combustion product concentration with the preset carbon monoxide concentration C10, and determines the combustion state according to the comparison result, wherein: When C1≤C10, the gas combustion module determines that the combustion state is complete combustion; When C1>C10, the gas combustion module determines that the combustion state is incomplete combustion, and optimizes the calculation formula of the air demand AK in the combustion control process according to the combustion optimization coefficient ru, and sets the optimized air demand AKu=AK×ru, and sets 1<ru<1.

21.

8. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 1 is characterized in that: The gas combustion module generates a burner data distribution map based on the burner data in the associated gas data, and inputs the burner data distribution map into the oxygen doping difficulty analysis model, obtains the oxygen doping difficulty CA output by the oxygen doping difficulty analysis model, and compares the oxygen doping difficulty CA with the preset oxygen doping difficulty CA0, analyzes the necessity of optimization based on the comparison result, and adjusts the optimization method of the combustion control process based on the optimization necessity analysis result, wherein: When CA≤CA0, the gas combustion module analyzes whether optimization is necessary, outputs an optimization necessity analysis result indicating that optimization is necessary, and does not adjust the optimization method of the combustion control process; When CA>CA0, the gas combustion module analyzes that there is no necessity for optimization, outputs an optimization necessity analysis result that there is no necessity for optimization, and adjusts the optimization method of the combustion control process, adjusting the combustion optimization coefficient ru to 1.

9. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 1 is characterized in that: The self-cleaning control module calculates the self-cleaning start parameter Z according to the pollutant data in the associated gas data, and sets Z=0.3×tz / tz0+0.7×gz / gz0, where tz is the self-cleaning time interval, tz0 is the preset self-cleaning time interval, gz is the self-cleaning pollutant weight, and gz0 is the preset self-cleaning pollutant weight. The self-cleaning control module compares the self-cleaning start parameter Z with the preset self-cleaning start parameter Z0, and judges the self-cleaning control situation according to the comparison result, wherein: When Z≤Z0, the self-cleaning control module determines that the self-cleaning control condition is to not start the self-cleaning control; When Z>Z0, the self-cleaning control module determines that the self-cleaning control condition is to start the self-cleaning control; After starting the self-cleaning control, the self-cleaning control module opens the recoil valve and utilizes the gas in the gas storage device to perform recoil self-cleaning until gz≤(0.3×gz0), and then closes the recoil valve to stop recoil self-cleaning.

10. The oilfield associated gas self-cleaning energy-saving combustion power generation system based on heat exchange according to claim 1 is characterized in that: The self-cleaning control module calculates the self-cleaning efficiency zx based on the heat conversion efficiency rx and the cleanliness qx, and sets zx=rx / rx0+qx / qx0, where rx0 is the preset heat conversion efficiency and qx0 is the preset cleanliness. The self-cleaning control module compares the self-cleaning efficiency zx with the preset self-cleaning efficiency zx0 and adjusts the self-cleaning control scale based on the comparison result, where: When zx≥zx0, the self-cleaning control module determines that the self-cleaning efficiency is high and does not adjust the self-cleaning control scale; When zx<zx0, the self-cleaning control module determines that the self-cleaning efficiency is low and adjusts the self-cleaning control scale by increasing the number of filter layers; The self-cleaning control module inputs the self-cleaning control information into the cost analysis model, obtains the self-cleaning control scale adjustment cost CB output by the cost analysis model, compares the self-cleaning control scale adjustment cost CB with the preset self-cleaning control scale adjustment cost CB0, and adjusts the inertia correction process of the pre-processing control according to the comparison result, wherein: When CB≤CB0, the self-cleaning control module determines not to adjust the inertia correction process of the pre-processing control; When CB>CB0, the self-cleaning control module determines to adjust the inertia correction process of the pre-processing control, stops the inertia correction of the pre-processing control, and pushes a suggestion to the user.

Images