1029 results about "Field development" patented technology

The invention relates to the technical field of oil and gas field development, and discloses an oil and gas reservoir intelligent dynamic monitoring and optimized mining method based on big data. According to the method, through multi-source data real-time sensing and dynamic coupling modeling, the limitation of traditional static analysis is broken through, and minute-level accurate description of the state of the oil and gas reservoir is achieved; a machine learning prediction model based on physical constraints effectively fuses a data rule and a geomechanics principle, and the early warning reliability of water-driven dynamics and equipment faults is remarkably improved; a multi-objective optimization strategy of digital twin driving comprehensively plans the recovery ratio, the economy and the safety, and supports intelligent decision making under complex working conditions; the edge control and the block chain technology are combined to form a'sensing-optimizing-executing-auditing 'closed loop, so that the high efficiency, the self-adaptability and the data credibility of the mining process are ensured. According to the overall scheme, oil and gas exploitation is promoted to be transformed to intelligentization, refinement and transparency, and technical support is provided for cost reduction, efficiency improvement and sustainable development of an oil field.

The invention relates to the technical field of oil and gas field development, and discloses an ultra-large type true triaxial hydraulic fracturing fracture evolution path prediction method and system.The prediction method comprises the steps that a coupling geomechanical model integrating microscopic, macroscopic and wellbore flow scales is constructed; initializing the model and performing crack initial expansion simulation; collecting construction data in real time, and dynamically optimizing model parameters through a data assimilation algorithm; performing fracture evolution advanced prediction by using the updated model; and generating an optimization decision based on the prediction result and feeding back to the construction site. According to the method, fusion of a multi-scale physical mechanism and real-time dynamic prediction is realized, and accurate prediction and active control can be performed on crack expansion under the ultra-large true triaxial condition.

The invention provides an oil and gas well yield prediction method and device based on a sparrow search algorithm, and relates to the technical field of oil and gas field development, and the method comprises the steps: obtaining geological parameters and development parameters of a target oil and gas well; the geological parameters and the development parameters serve as input, and the predicted yield of the target oil and gas well in the target time period is generated through a pre-trained oil and gas well yield prediction model; the oil and gas well yield prediction model is obtained by training a BP neural network and a sparrow search algorithm through historical geological parameters and development parameters of a target oil and gas well. The BP neural network is optimized based on the sparrow search algorithm, the problems that an existing BP neural network is low in convergence speed and prone to falling into a local optimal solution are solved, automatic optimization of the neural network weight and the threshold value is achieved, the tedious parameter adjusting process of a conventional neural network is avoided, and meanwhile the prediction precision of the oil and gas well yield is improved.

The invention discloses an intelligent optimization method for a multi-type well seam joint control fine injection-production mode, and relates to the technical field of oil-gas field development. The method comprises the following steps: setting a well seam joint control fine injection-production mode, establishing an oil reservoir numerical simulation model in oil reservoir numerical simulation software, obtaining multiple groups of oil reservoir injection-production schemes based on a Latin hypercube sampling method, performing simulation according to each group of oil reservoir injection-production schemes by utilizing the oil reservoir numerical simulation model, generating multiple pieces of sample data, and establishing a sample database; a deep learning agent model is established, after the sample database is utilized to train and train the deep learning agent model, a particle swarm optimization algorithm is adopted to carry out single-target pre-search global optimization to obtain a preferred reference strategy, a reinforcement learning dynamic decision model is established, and a reinforcement learning agent is obtained through training based on a PPO near-end strategy optimization algorithm; and the optimal injection-production development scheme of the oil reservoir is obtained by utilizing the reinforcement learning agent, so that rapid optimization and decision support of the oil reservoir injection-production scheme in a new multi-type well seam joint control mode are realized.

The invention discloses a polymer-flooding reservoir yield prediction method and system based on a double attention mechanism and a storage medium, relates to the field of oilfield development, and aims to solve the problems that a bidirectional dependency relationship and local features of long-time-series data are difficult to capture at the same time and feature weight distribution and time-series information focusing effects are insufficient in an existing method. According to the technical key points, the method comprises the following steps: S1, collecting field development data of the polymer flooding reservoir and screening optimization characteristics; s2, a CNN-BiLSTM-DAM fusion model is constructed, and the function implementation process of the model comprises the steps that local features of input data are extracted based on a convolutional layer, a dynamic weight is distributed to the local features of each time step through an attention mechanism layer, forward and backward dependency relationships of weighted time sequence feature data are captured through a bidirectional loop structure of a BiLSTM layer, and a dynamic weight is distributed to the local features of each time step; performing weight adjustment on the time sequence features output by the BiLSTM layer through the attention mechanism layer, and capturing global time dependence through the BiLSTM layer; and S3, the optimized features are input into the trained CNN-BiLSTM-DAM fusion model, and the yield of the polymer flooding reservoir is predicted.

The invention discloses a shaft operation state intelligent prediction method based on a hybrid deep learning framework, and belongs to the field of petroleum engineering oil-gas field development engineering, and the method comprises the following steps: building a geological sequestration shaft transient temperature-pressure coupling mathematical model, and carrying out the numerical solution; constructing a double sequence feature database covering CO2 injection and leakage working conditions; adopting a parallel architecture to process the double sequence features to construct an improved double attention network; the method comprises the following steps: establishing a hybrid deep learning framework DT-DANet by coupling an improved double attention network and a time fusion Transform; and carrying out collaborative optimization training on the hybrid deep learning framework by adopting a composite loss function, wherein the output of the framework is a wellbore pressure profile, a temperature profile and phase state distribution under different time steps. According to the method, high-precision prediction of shaft multi-parameter dynamic evolution in the CO2 geological storage process is realized.

The invention discloses a deep learning assisted acceleration fracturing construction parameter intelligent real-time optimization method, and belongs to the field of unconventional oil and gas field development, and the method comprises the steps: constructing a structured sample database covering geological attributes, engineering parameters and fracturing effect responses, and carrying out the unified preprocessing of multi-source data; constructing a multi-modal space-time collaborative prediction model, and combining a multi-expansion time permissible convolutional network, a three-dimensional residual network and a cross attention mechanism; supervised learning training is carried out based on a database, sparse regularization and learning rate scheduling are introduced, and the model precision and generalization ability are improved; a hierarchical collaborative optimization framework of outer-layer Bayesian search-inner-layer CMA-ES refinement is provided, and reservoir transformation volume maximization and construction feasibility are achieved under complex constraints; compared with an existing method, optimization parameters of the method include the cluster distance and the section distance and further include the displacement, the sand concentration, the fracturing fluid type and other construction parameters, and real-time optimization of the fracturing construction parameters can be achieved through the machine learning agent model.

The invention discloses an oil-water well acidification continuous construction electric control system based on multi-parameter monitoring, and relates to the technical field related to acidification control in oil-gas field development, and the system comprises a multi-source data fusion monitoring module which integrates wellhead pressure, temperature, flow, pH value, H2S concentration and acid liquid conductivity, and an underground microwave imaging sensor carries out multi-physical quantity collection; a multi-objective optimization controller is designed, and the acid etching depth, the crack flow conductivity and the construction cost are balanced; the self-adaptive construction control module is based on a variable-frequency and variable-speed acid pump system controlled by a fuzzy sliding mode and is used for realizing stepless regulation of displacement; an intelligent shunting system is arranged, and acid liquor distribution is dynamically adjusted according to the suction volume of each layer section. According to the variable-frequency acid pump system based on fuzzy sliding mode control, stepless adjustment of the displacement is achieved; the intelligent flow distribution system dynamically prepares liquid according to the suction volume of each layer section; and through a three-stage safety interlocking mechanism, power can be cut off and emergency acid discharge can be started within 0.5 second when the temperature rise is greater than or the pressure suddenly changes, so that the well control risk is reduced.

The invention discloses an oil-water well liquid production profile identification and inversion method, system and program product, relates to the technical field of oil-gas field development, and solves the problems that in an existing liquid production profile monitoring method based on DAS and DTS technologies, DAS signals are prone to being interfered by fluid flow, the signal quality is poor, liquid point information cannot be accurately reflected, and the reliability is poor. The problems that liquid production profile information of DTS signal inversion lacks enough spatial constraint conditions, and the inversion result is large in deviation are solved. According to the method, the local liquid production characteristics in the DAS signals are extracted through blind source separation, the liquid outlet point positions are effectively recognized in combination with a statistical screening method, the recognized liquid outlet point positions serve as constraint conditions to be introduced into the DTS inversion process, and the precision and stability of the inversion result are effectively improved; the method not only overcomes the limitation of a traditional F-K spectral analysis method in an oil-water well environment, but also can introduce effective spatial constraints in DTS inversion, significantly reduces inversion errors, and improves the interpretation precision of a liquid production profile.

The invention discloses an injection-production regulation imbalance quantitative diagnosis method based on fluid potential energy, and the method comprises the steps: extracting a streamline track space coordinate sequence and corresponding point oil reservoir parameters based on a dynamic permeability field, a pressure field and an injection-production streamline field; constructing a three-dimensional fluid potential energy field model in the injection-production unit, and dividing dominant seepage, a retention zone and a transition zone based on the injection-production unit through potential energy gradient tensor; establishing a seepage potential index LS by taking the flow line penetrating pore volume as a stability weighting factor and combining the potential energy gradient intensity; on the basis of LS sorting, a potential energy-volume two-factor accumulation curve is constructed, the development non-equilibrium degree is represented through curve form parameterization, and the envelope area of the accumulation curve is calculated and used for representing the oil reservoir flow field development non-equilibrium degree and the development effect of each type of injection-production unit. According to the method, fluid potential energy and a two-factor cumulative distribution concept are introduced into computational logic, and unified and quantitative characterization of an oil reservoir flow field and an injection-production unit is realized in combination with a seepage mechanism of the injection-production unit.

The invention discloses an oil reservoir injection-production optimization method based on an improved multi-objective particle swarm algorithm, and belongs to the technical field of oil and gas field development. According to the method, an attention mechanism, a Transform and a long-short-term memory network are introduced based on a relational graph convolutional network, geological features and production system information are combined, inter-well water content prediction is taken as a target, an HSTMF model is constructed, an injection-production well production system does not need to be adjusted, the calculated amount is greatly reduced, and the prediction precision is remarkably superior to that of a traditional method; in the aspect of optimization algorithms, a Cauchy disturbance variation mechanism is introduced into a genetic algorithm and combined with a particle swarm optimization algorithm to form a new optimization strategy, a real-time closed-loop collaborative oil reservoir management framework is constructed in combination with the moisture content prediction capability of an HSTMF model, the net present value and the total oil production are effectively increased, the total moisture content is reduced, and good practical application value is shown.

The invention belongs to the technical field of oil-gas field development, and particularly relates to a method for testing the content of adsorbed gas in a coal bed gas diffusion process. The problem that the desorption degree of coal bed gas cannot be clearly known at present is solved. According to the technical scheme, high-temperature and high-pressure isothermal adsorption experiments under the condition of different gas proportions are carried out, methane adsorption-desorption capacity of mixed gas of different proportions under different partial pressures is determined, gas diffusion experiments are carried out to evaluate gas migration capacity in the diffusion process and methane gas partial pressure distribution in a sample, and different experiment results are synthesized to determine the methane gas content of the sample. The desorbed gas content in the coal bed gas diffusion process can be calculated; according to the new method, the proportion of the methane desorption gas amount in the coal bed gas development process can be calculated, and the desorption degree of the adsorbed gas of the coal bed reservoir is evaluated.

The invention discloses an unconventional oil and gas yield prediction method based on space-time Transform, which is characterized in that geological parameters, fracturing construction parameters and production dynamic data are fused, and time sequence dependency and spatial heterogeneity of modeling parameters are synchronized by utilizing a space-time attention mechanism. Firstly, normalization and space-time alignment are carried out on multi-source data, and a joint input matrix is constructed; then, a dynamic change trend of fracturing construction parameters is extracted through a time attention module, a space contribution weight of geological parameters is quantified through a space attention module, and a space-time interaction matrix is introduced to capture a multi-dimensional coupling relation; and finally, outputting a yield prediction result through feature fusion and MLP. According to the method, the dependence of a traditional model on a single data source is broken through, the precision and interpretability of unconventional oil and gas yield prediction are remarkably improved, and reliable technical support is provided for oil and gas field development strategy optimization.

The invention relates to the field of intelligent diagnosis of oil and gas field development, in particular to a fracturing wellhead device failure analysis method and system based on a large model and a knowledge graph. The system is helpful for solving the problem that the accuracy and timeliness of failure analysis and fault diagnosis of the fracturing wellhead device in the prior art are limited. The method comprises the steps of building a knowledge graph, setting a knowledge graph dynamic updating mechanism oriented to the fault evolution process, building an open source large model and introducing a closed loop feedback mechanism. According to the method, the large model, the knowledge graph and the RAG technology are applied to fracturing wellhead failure analysis, and the intelligent level of the oil and gas industry is remarkably improved; the problem that a large model is high in generalization but insufficient in specialty is optimized, and the accuracy of answer generation is improved.

The invention discloses an EUR prediction model construction method and system of a tight gas reservoir gas well, and relates to the field of oil and gas field development technology and artificial intelligence cross technology, and the method comprises the steps: collecting multi-source data; screening the multi-source data by adopting a three-level feature screening method, and removing redundant features; constructing a heterogeneous integrated model comprising a plurality of machine learning models, inputting the screened features into the heterogeneous integrated model to carry out EUR prediction, obtaining respective prediction errors of different machine learning models, correcting each EUR prediction result based on the prediction errors in combination with a material balance equation MBE, a yield attenuation model DCA and fracture network simulation, and carrying out EUR prediction. And carrying out weight distribution on each machine learning model after the EUR prediction result is corrected by adopting an error reciprocal weighting method to generate a final combined EUR prediction model. According to the method, an optimization strategy combining data driving and physical constraint is adopted, and the precision and reliability of EUR prediction are improved.

The invention relates to the technical field of oil-gas field development and geothermal energy utilization. The invention provides an underground high-temperature composite fluid heating system, which comprises a crude oil separation device, a catalysis module, a high-temperature fluid generation module, an injection well pattern module, a target reservoir and a production well, and is characterized in that the crude oil separation device is communicated with the catalysis module through a first gas inlet pipeline and a second gas inlet pipeline; a first gas outlet pipeline and a second gas outlet pipeline are communicated with a high-temperature fluid generation module, the high-temperature fluid generation module is communicated with an injection well pattern module through a third gas outlet pipeline, the injection well pattern module is communicated with a target reservoir, and the target reservoir supplies energy to the outside through a fourth gas outlet pipeline. And the production well conveys the energy-supplied gas to the heat energy recovery device through the first recovery pipeline. In this way, efficient and uniform heating of the underground reservoir is achieved, energy consumption is reduced while the energy recovery efficiency is improved, and the problems of low heat conduction efficiency and high energy consumption in deep oil gas and hot dry rock development are solved.

The invention relates to an introduction structure of a fisher, which belongs to the field of oil-gas field development and comprises an expansion drive, a base is arranged at one end of the expansion drive, an expansion guide structure is arranged at the other end of the expansion drive, and a flow guide structure is arranged on the inner side of the expansion drive. The expansion guide structure comprises expansion connecting rods and a plurality of rigid expansion flaps, the end, away from the base, of the expansion drive is connected with the rigid expansion flaps, and the expansion connecting rods are connected between the adjacent rigid expansion flaps. The expansion guiding structure completes expansion and folding actions through expansion driving, the expansion guiding structure enlarges the guiding area through the expansion action and also enlarges the projection area, and the expansion guiding structure pushes a fish in the guiding area through the folding action, so that the fish is correctly guided into the fishing tool. The invention provides an effective guide area in a larger range, and enhances the adaptability of the introduction structure to the fish form, thereby improving the efficiency and success rate of the fishing operation.

The invention discloses a shale oil reservoir flow simulation method based on a limited fluid state equation, which belongs to the technical field of oil-gas field development and comprises the following steps of: establishing a limited fluid generalized state equation by considering a nano confinement effect; oil / gas phase balance is calculated based on the limited fluid generalized state equation; oil / gas two-phase physical property parameters are calculated; and establishing a multi-component multi-phase flow shale oil flow simulation formula. By adopting the method, the P-R state equation is corrected based on the nano confinement effect, phase equilibrium calculation is performed based on the corrected P-R state equation, the oil / gas two-phase physical property parameters are calculated, the parameters are substituted into the shale oil reservoir flow equation, the flow characteristics of the shale oil reservoir are defined, and the simulation efficiency is improved.

The present invention belongs to the field of gas field development, and particularly relates to a method for determining the TPC curve of a gas well under the influence of wellbore liquid accumulation. In the present invention, in order to eliminate the influence of liquid accumulation on flowing pressure calculation, the wellbore is divided into a liquid accumulation section and a non-liquid accumulation section, a wellbore pressure drop model considering the influence of liquid accumulation is established, and a method for determining the TPC curve of a gas well under the influence of wellbore liquid accumulation is proposed. This method has theoretical rationality and practical production application value in the actual application of gas reservoir production increase.

The invention relates to the technical field of oil and gas field development, in particular to a fracture parameter inversion method based on a Bayesian neural network, which comprises the following steps: establishing a bottom hole net pressure conversion model based on an actual construction curve, and drawing a bottom hole net pressure curve; calculating a bottom hole net pressure index sequence and a corresponding time sequence; establishing a shaft bottom crack extension mode judgment criterion on the basis of a classic double logarithmic curve analysis method; taking the net pressure index sequence and the time sequence obtained in the previous step as input data, combining actual physical parameter constraints, and establishing an inversion fracture parameter model based on a Bayesian neural network; and inputting the pressure index sequence to be inverted into the Bayesian neural network model to obtain a specific fracture parameter inversion result. According to the technical scheme, the confidence interval of the prediction result can be given, the prediction result and uncertainty quantification capability can be synchronously provided, and the reliability and decision support value of the inversion result are greatly improved.

The present application relates to the technical field of shale oil and gas field development, and is a test system for simulating fault activation and induced earthquake under the action of horizontal well hydraulic fracturing, which comprises a horizontal well geological model, a distributed optical fiber monitoring system, a perforating system, a fracturing system, a formation temperature simulation system and a stress applying system. The present application has a reasonable and compact structure and is convenient to use. It can realize the application of true triaxial formation pressure, simulate the real formation temperature of the formation where the horizontal well is located, and continuously and real-timely monitor the multi-physical field of the fault-containing geological reservoir under the conditions of formation pressure, temperature, the whole process of horizontal well hydraulic fracturing and multi-step conditions. Therefore, the mechanism of hydraulic fracturing activating faults, the feature difference of multi-stage fracturing fracture network, the deformation of casing and the risk of induced earthquake can be quantitatively characterized and regularly analyzed, so as to study the formation and expansion of rock mass fracturing fracture network, the activation of faults and the deformation and damage process of wellbore casing during the whole process of fracturing at different stages of horizontal well.

The invention discloses an oil reservoir water content prediction method based on a graph neural network and Transform, and belongs to the technical field of oil and gas field development, and the method comprises the following steps: S1, converting an oil reservoir injection-production model at each time point into a graph structure, and constructing a connection network from a water injection well to a production well; and S2, constructing a GNT proxy model in combination with the graph neural network and Transform, training the GNT proxy model, and predicting the water content of each production well. According to the constructed GNT proxy model, an oil reservoir injection-production structure is converted into graph data through a GCN module, the information transmission strength between nodes is dynamically adjusted through an edge feature enhanced message transmission mechanism, and inter-well communication features are accurately captured; and the multi-head self-attention mechanism of the Transform encoder module is combined to process the time sequence dependence, so that the long-distance time dynamic relationship is effectively modeled, and an efficient and reliable agent model is provided for the dynamic analysis of the oil reservoir.

The invention belongs to the technical field of oil and gas field development, and particularly relates to an adaptive adjustment method and management system for perforation water control, and the method comprises the steps: obtaining oil layer geological parameters, fluid properties and water invasion condition data; constructing a dynamic model according to the oil reservoir data, performing analysis according to the dynamic model and the water invasion prediction model, and determining a water invasion risk level according to an analysis result in combination with a dynamic weight distribution algorithm; according to the water invasion risk level and the mining target, perforation parameters are optimized in combination with a genetic algorithm, optimized perforation parameters are obtained, and according to the optimized perforation parameters, a water invasion path is simulated in combination with environmental parameters and an ant colony foraging algorithm, and a corresponding water prevention and control strategy is formulated; and according to the water control strategy, monitoring the dynamic change of the oil layer and the water control effect, adjusting parameters and strategies in time, feeding back data, and updating the water control strategy knowledge base. Therefore, the problems of lagging risk assessment, extensive perforation parameters, single prevention and control strategy, lack of closed-loop feedback and the like in the prior art are solved.

The invention provides an oil-gas well connectivity evaluation method and device, and relates to the technical field of oil-gas field development. The method comprises the following steps: acquiring monthly production data of an oil-gas well, and performing feature extraction on the monthly production data of the oil-gas well to obtain multi-dimensional dynamic features of a quantifiable dynamic injection-production relationship; and performing oil-gas well connectivity evaluation on the multi-dimensional dynamic characteristics based on a preset oil-gas well connectivity evaluation model to obtain an oil-gas well connectivity evaluation result. The device executes the method. According to the oil and gas well connectivity assessment method and device, the oil and gas well connectivity can be efficiently and accurately assessed in real time.

The invention discloses a shale oil carbon dioxide huff and puff graded pressure drop mining experiment method. The method comprises the following steps that S1, the crude oil recovery degrees under different huff and puff experiment requirements are obtained through experiments; the method is suitable for the technical field of oil and gas field development, the CO2 utilization rate and the recovery percentage of each stage in the shale oil carbon dioxide huff and puff graded pressure drop exploitation process can be accurately measured, a database is established in combination with influence factors of different injection conditions, and the reliability of the shale oil carbon dioxide huff and puff graded pressure drop exploitation process is improved. And on the basis of experimental results, weight analysis of shale oil carbon dioxide huff and puff graded pressure drop mining is carried out on each factor, so that main influence factors of shale oil carbon dioxide huff and puff graded pressure drop mining can be screened out, which is of great significance to subsequent shale oil carbon dioxide huff and puff mining adjustment.

The invention relates to the technical field of oil and gas field development engineering, in particular to an unconventional oil and gas reservoir fracturing flexible material assisted sand carrying-sand control whole process numerical simulation method which comprises the following steps: 1) acquiring a basic parameter data set; 2) respectively establishing corresponding liquid phase-solid phase interaction force models for the proppant and the flexible material; and 3) establishing a numerical model according to the liquid phase-solid phase interaction force model of the proppant and the flexible material, and simulating the whole process of flexible material-proppant cluster conveying, laying and backflow. Through the numerical simulation method provided by the invention, the change conditions of the flexible material-proppant cluster laying form, such as a visual cloud picture, an effective laying area, a particle average flow velocity change curve, flow conductivity and fracture permeability, under different working condition parameters can be simulated; therefore, objective evaluation of the efficient laying effect and the flow conductivity of the fracturing propping agent assisted by the flexible material is realized, and suggestions are provided for site construction parameter optimization.

The invention discloses a reservoir fracture distribution prediction method and system based on big data, and relates to the technical field of oil and gas field development, and the method comprises the steps of multi-source data collection and fusion, multi-scale feature extraction and optimization, hybrid model construction and three-dimensional fracture probability body generation, and fracture distribution prediction and visual display. According to the method, prediction blind areas are reduced by collecting multi-source heterogeneous data, physical constraints are achieved by introducing a Griffith criterion so as to enhance geological rationality, dynamic data and static geological data of fracturing construction are subjected to combined modeling, dynamic fusion of multi-source data is achieved, timeliness of crack prediction is improved, in addition, the physical constraint hybrid model is adopted, and the prediction efficiency is improved. And spatial characteristics and dynamic response are considered through a CNN-GBDT hybrid architecture, a fracture mechanics criterion is embedded to enhance interpretability, real-time access of logging-while-drilling data in the drilling process is supported, and key technical support can be provided for unconventional oil and gas development.

The invention discloses digital intelligence powder type distribution-free variable viscosity fracturing fluid skid-mounted equipment and a control method thereof, and belongs to the technical field of oil and gas field development. The equipment comprises a stirring mechanism, a feeding mechanism, a water feeding mechanism and a discharging mechanism which are centrally controlled through a control box. The feeding mechanism adopts a first screw conveyor to convey solid materials to the stirring tank body; the water supply mechanism supplies water to the tank through a water supply pump and a water outlet pipe with an electromagnetic valve, and the water quantity is monitored by a water inlet flow sensor; the discharging mechanism outputs the mixed liquid through a discharging pump, and the viscosity of the fracturing fluid is detected in real time through a viscosity sensor. The control box is connected with all the sensors and execution components, and automatic adjustment and closed-loop control of the material proportion are achieved by collecting flow and viscosity data. According to the invention, accurate and automatic preparation of the fracturing fluid is realized, the problems of inaccurate traditional manual proportioning and poor stability are effectively solved, and the fluid preparation quality and the operation efficiency are remarkably improved.

The invention provides a polymer flooding reservoir model prediction method and device, equipment and a storage medium. Relates to the field of oil-gas field development engineering. The method comprises the steps that an injection-production system matrix is converted into a multi-channel field graph containing time codes, and a depth operator network is constructed in combination with three-dimensional physical field data output through reservoir numerical simulation; a branch network adopts a residual attention network to convert the injection-production system field graph into a parameter-dependent feature graph; the backbone network converts tensors of time coding into spatial modulation weights, and initial operators of a pressure field, an oil saturation field and a polymer concentration field are generated through dot product operation; dynamically enhancing the data density of the high-error region by using an adaptive sampling mechanism based on a Gaussian mixture model; and realizing transient multi-physics field synchronization high-precision prediction by combining geometric similarity matching multiplexing physical tags. The problems that a traditional numerical simulator is low in calculation efficiency and a conventional agent model is poor in generalization ability are solved.

The invention relates to the technical field of oil and gas field development, and discloses a horizontal well multiphase flow profile inversion method based on multisource data fusion, which comprises the following steps: S1, laying optical fibers and acquiring data; s2, data preprocessing; s3, obtaining empirical parameters and a multi-source database; s4, judging a fluid scene and constructing a solver model; s5, iterative solution and phase fraction inversion are carried out, according to the empirical parameters and the multi-source database, the solver model constructed in the step S4 is adopted, solution is carried out in different phase number scenes, and an inversion index result is obtained; and S6, visual output and abnormal flow detection are carried out, and the inversion index result obtained in the step S5 is visually presented in the depth direction of the shaft and is used for assisting in judging abnormal phenomena. According to the method, the multiphase flow thermodynamic model is constructed based on the state equation, the water-liquid ratio and the gas-oil ratio are dynamically inverted through the iterative optimization algorithm in combination with the DAS sound velocity data, and high-precision characterization of multiphase flow characteristics is achieved.