An intelligent dynamic monitoring and optimized exploitation method for oil and gas reservoirs based on big data

Abstract

The application relates to the technical field of oil and gas field development, and discloses an intelligent dynamic monitoring and optimized mining method for oil and gas reservoirs based on big data; through real-time sensing and dynamic coupling modeling of multi-source data, the application breaks through the limitation of traditional static analysis, realizes minute-level accurate description of the state of the oil and gas reservoir, and effectively fuses data rules and geomechanical principles based on a machine learning prediction model under physical constraints, thereby significantly improving the early warning reliability of water drive dynamics and equipment failure; a multi-target optimization strategy driven by digital twinning coordinates the recovery rate, economy and safety, and supports intelligent decision-making under complex working conditions; the combination of edge control and blockchain technology forms a "sensing-optimization-execution-audit" closed loop, thereby ensuring the efficiency, adaptability and data reliability of the mining process. The overall scheme promotes the intelligent, refined and transparent transformation of oil and gas mining, and provides technical support for cost reduction and efficiency improvement and sustainable development of oil fields.

Description

Technical Field

[0001] This invention relates to the field of oil and gas field development technology, specifically to a method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data. Background Technology

[0002] Current dynamic monitoring of oil and gas reservoirs primarily relies on periodic static tests (such as pressure recovery well tests and production logging) and manual experience analysis. Conventional methods acquire key parameters by deploying discrete sensors (such as downhole pressure gauges and flow meters), combine them with numerical simulation software (such as Eclipse and CMG) to build static geological models, and formulate production plans based on historical data. Some technologies have attempted to introduce machine learning algorithms (such as random forests and support vector machines) to predict production indicators, but their model training largely depends on offline historical data, and local optimization is achieved through manual adjustment of injection and production parameters. Furthermore, existing systems typically employ centralized data storage, requiring regular manual audits to ensure data reliability.

[0003] Existing technologies still have shortcomings:

[0004] Traditional sensor networks suffer from low coverage density and insufficient sampling frequency, resulting in blind spots in the monitoring of key parameters (such as fracture propagation and fluid front). Furthermore, control decisions rely on periodic manual analysis and cannot respond to dynamic changes in real time. Geological modeling, seepage simulation, and equipment condition analysis are independent of each other, lacking a multi-physics coupling mechanism. Model updates rely on manual intervention and are difficult to adapt to complex scenarios such as dynamic degradation of reservoir properties. Machine learning models lack physical constraints, resulting in poor interpretability of prediction results. Moreover, the optimization process ignores the balance between economy and security. In addition, centralized data storage is susceptible to tampering and cannot meet the needs of multi-party collaborative auditing. To address these issues, a big data-based intelligent dynamic monitoring and optimized exploitation method for oil and gas reservoirs is proposed. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data, thereby solving the problems mentioned in the background.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data, comprising the following steps:

[0007] Step 1, Multi-source data acquisition and preprocessing: Deploy a heterogeneous sensor network in the wellbore, surface gathering and transportation pipeline and reservoir to collect multi-dimensional production data in real time, including formation pressure, temperature, fluid velocity, water cut, downhole motor vibration spectrum, and casing deformation data. Perform noise filtering, spatiotemporal alignment and normalization on the raw data.

[0008] Step 2, Dynamic Coupled Modeling: The preprocessed real-time data is fused with the 3D geological model and historical development data to construct a multi-physics field coupled analysis model that includes reservoir physical parameters, fluid migration patterns, and equipment operating status.

[0009] Step 3, Intelligent Prediction and Diagnosis: Based on the coupled model, an injection-production response prediction module is established through machine learning algorithms to output the prediction results of reservoir pressure distribution, water drive front location, fracture closure risk index and equipment failure probability in real time.

[0010] Step 4, Optimize decision generation: Based on the prediction results, simulate the production effect under different combinations of mining parameters in the digital twin system, and use a multi-objective optimization algorithm to generate injection-production adjustment schemes, optimized pumping frequency values, and chemical displacement agent injection strategies.

[0011] Step 5, Closed-loop execution and blockchain integration: The optimized plan is sent to the well site edge controller for execution, and production data after execution is collected synchronously. The prediction model parameters are updated through an online learning mechanism to form a closed-loop control link of "perception-decision-execution-verification".

[0012] Preferably, in step one:

[0013] The heterogeneous sensor network includes a distributed fiber optic acoustic sensor (DAS), a downhole permanent pressure gauge, a multiphase flow meter, and a high-precision temperature sensor at the wellhead.

[0014] Data preprocessing employs a sliding window dynamic calibration method to compensate for sensor drift. The compensation formula is as follows:

[0015] x corrected =x raw ·(1+α·Δt)+β·sin(2πf noise t)

[0016] Where, x raw The sensor's raw reading; α is the sensor's time drift coefficient, calibrated using daily zero-point self-test data; Δt: the time interval since the last calibration; β: the amplitude of environmental electromagnetic interference; f noise The main interference frequencies are identified using Fast Fourier Transform.

[0017] Preferably, the multiphysics coupling analysis model in step two includes a three-dimensional coupling of a geomechanical module, a seepage module, and an equipment operating condition module;

[0018] A loosely coupled iterative algorithm is used to achieve data interaction between modules, completing the following within each time step:

[0019] Update the reservoir permeability tensor based on changes in geostress.

[0020] Calculate fluid pressure distribution based on the new permeability;

[0021] By inferring the sleeve deformation through fluid pressure, the vibration constraint conditions of the equipment can be corrected.

[0022] Preferably, in step three:

[0023] The machine learning algorithm employs a Physical Information Neural Network (PINN), and its loss function includes:

[0024]

[0025] Among them, u pred The network outputs predicted pressure / saturation values; u obs λ1 and λ2 are the measured pressure / saturation data; K is the permeability tensor; p is the fluid pressure field; and λ1 and λ2 are the weighting coefficients of the data terms and physical constraint terms.

[0026] Preferably, in step four:

[0027] The digital twin system includes a full-chain simulation model of the formation, wellbore, and surface equipment;

[0028] The multi-objective optimization employs an improved NSGA-II algorithm, whose fitness function includes:

[0029] F = [ER, NPV, 1 / WC] T

[0030] Among them, ER is the predicted recovery rate, calculated through the material balance equation; NPV is the net present value, taking into account dynamic parameters such as oil price and operating cost; WC is the comprehensive water cut, assigned a weighting coefficient to different well groups.

[0031] Preferably, in step five:

[0032] The edge controller deploys an adaptive PID algorithm, and the control variables include:

[0033]

[0034] Where u(t) is the control output (mA); e(t) is the deviation between the setpoint and the actual value; K p K is a proportionality coefficient that is dynamically adjusted based on the reservoir pressure gradient. i The integral coefficient satisfies K with the injection-production response delay time τ. i =1 / (2τ); K d This is the differential coefficient, which is forcibly reset to zero when the sand discharge warning is activated.

[0035] Preferably, a risk hedging mechanism is introduced in the optimization decision-making process of step four, and a conservative mining scheme is activated when one of the following situations occurs:

[0036] International oil prices fell by more than 7% in a single day;

[0037] The downhole CO2 concentration monitoring value exceeded the critical value for H2S synergistic corrosion.

[0038] The regional power grid load rate remained above 90% for two consecutive hours.

[0039] Preferably, step five integrates a blockchain-based trusted evidence storage mechanism, specifically including:

[0040] Write the hash value of the optimized decision parameters into the smart contract:

[0041] H decision =SHA3-256(Q inj |Q prod |Timestamp)

[0042] Among them, Q inj Q is the command to adjust the water injection volume. prod Set the oil production rate; Timestamp is a UNIX timestamp.

[0043] When the actual production data deviates from the predicted value by more than 15%, the blockchain evidence audit process is automatically triggered to trace the original sensor data and intermediate results of model calculations.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] This invention overcomes the limitations of traditional static analysis by combining real-time perception of multi-source data with dynamic coupling modeling, achieving minute-level accurate characterization of oil and gas reservoir conditions. A machine learning prediction model based on physical constraints effectively integrates data patterns and geomechanical principles, significantly improving the reliability of early warnings for water-driven conditions and equipment failures. A digital twin-driven multi-objective optimization strategy coordinates recovery rate, economy, and safety, supporting intelligent decision-making under complex operating conditions. The combination of edge control and blockchain technology forms a closed loop of "perception-optimization-execution-audit," ensuring the efficiency, adaptability, and data credibility of the extraction process. This overall solution promotes the transformation of oil and gas extraction towards intelligence, precision, and transparency, providing technical support for cost reduction, efficiency improvement, and sustainable development in oilfields.

[0046] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0047] Figure 1This is a flowchart of the intelligent dynamic monitoring and optimized exploitation method for oil and gas reservoirs based on big data, as described in this invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] Please see Figure 1 The present invention provides a method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data, comprising the following steps:

[0050] Step 1: Multi-source data acquisition and preprocessing

[0051] 1. Sensor Deployment:

[0052] Downhole monitoring:

[0053] Distributed fiber optic temperature / acoustic sensors (DTS / DAS), model SilixaXT-DTS, are installed every 15 meters in the horizontal well section. The temperature measurement range is -40℃ to 300℃, the accuracy is ±0.1℃, and the acoustic sampling rate is 2kHz. These sensors are used to monitor the wellbore temperature distribution and microseismic events.

[0054] A fiber optic pressure sensor (FBG) with a range of 0-100 MPa and a resolution of 0.01 MPa was deployed 5 meters above the perforation section to collect formation pressure data in real time.

[0055] Ground monitoring:

[0056] A multiphase flow meter (Roxar MFM 2600) is installed at the wellhead to measure the flow rates of oil, gas, and water, with an accuracy of ±1.5% and a data update frequency of 1 second.

[0057] Vibration sensors (Emerson CSI 9420) are installed in the gathering and transportation pipelines, with a monitoring frequency range of 10Hz-10kHz, to detect abnormal vibrations of pumps and valves.

[0058] 2. Data preprocessing:

[0059] To address the sensor time drift problem, a sliding window dynamic calibration method is adopted, and the compensation formula is as follows:

[0060] x corrected =x raw ·(1+α·Δt)+β·sin(2πf noise t)

[0061] Where, x raw The sensor's raw reading; α is the sensor's time drift coefficient, calibrated using daily zero-point self-test data; Δt: the time interval (hours) since the last calibration; β: the amplitude of environmental electromagnetic interference (mV); f noise The main interference frequency (Hz) is identified by Fast Fourier Transform;

[0062] Example: The original reading x of a pressure gauge raw =12.5mV, time drift coefficient α=0.002 / h (calibrated by daily zero-point self-test), distance from last calibration Δt=10h, interference amplitude β=0.2mV, noise frequency f noise =50Hz, then the corrected data is:

[0063] Xcorrected=12.5×(1+0.002×10)+0.1×sin(100πt)=12.75+0.1sin(100πt)mV

[0064] Noise filtering: Wavelet thresholding was performed on the DAS acoustic signal. The sym8 wavelet basis was selected, the number of layers was decomposed to 6, and soft thresholding was applied to preserve the formation fracture characteristic signal (<500Hz).

[0065] Eliminating sensor drift and electromagnetic interference improves data reliability; after compensation, the pressure data error is reduced from ±0.5MPa to ±0.1MPa, and the signal-to-noise ratio (SNR) of the acoustic signal is increased to 40dB, effectively identifying crack propagation events and meeting the requirements of high-precision modeling.

[0066] Step 2: Dynamic Coupling Modeling

[0067] 1. Construction of a multiphysics coupling model:

[0068] 1.1. Geomechanics Module: Solve the governing equations based on geostress data (via fiber optic strain inversion):

[0069]

[0070] Where σ is the geostress tensor, ρ is the rock density, and g is the gravitational acceleration;

[0071] 1.11. Microseismic event correction: based on the hypocenter location (x i ,y i ,z i ), and energy E i Update the shear modulus μ:

[0072]

[0073] Among them, A i Let ν be the fracture area and ν be Poisson's ratio.

[0074] 1.12. Seepage Module: The flow within the fracturing fracture is described using a non-Darcy flow equation:

[0075]

[0076] Where p is the fluid pressure; K is the permeability, the initial value of which is determined by core experiments; μ is the fluid viscosity; and β is the non-Darcy coefficient.

[0077] 1.13. Equipment Operating Condition Module: Calculate the allowable vibration velocity based on the sleeve strain ∈:

[0078]

[0079] Where E is the elastic modulus of steel; ρ steel ∈ represents the density of the steel; ∈ represents the strain measurement value.

[0080] 2. Loosely Coupled Iterative Algorithm:

[0081] Execute sequentially within each time step (Δt = 1 hour):

[0082] 2.1 Permeability Update: Based on the change in geostress, if Δσ = 5MPa, according to K... new =K old ·e 0.02Δσ Correction, yielding K new =8×e 0.01 =8.84mD;

[0083] Pressure field calculation: Solving the seepage equation yields a pressure of p = 35.2 MPa at a certain grid point;

[0084] Device constraint update: Calculate v max =0.65m / s, exceeding this value triggers frequency reduction protection.

[0085] Step 3: Intelligent Prediction and Diagnosis

[0086] 1. Training of Physical Information Neural Network (PINN):

[0087] Network structure: Input layer (14 features including pressure, temperature, and flow rate), 4 hidden layers (256 neurons, activation function is Swish), output layer (water saturation S). w Crack Risk Index R f );

[0088] Loss function:

[0089]

[0090] Among them, u predThe network outputs predicted pressure / saturation values ​​(dimensionless); u obs λ1 and λ2 are the measured pressure / saturation data (dimensionless); K is the permeability tensor; p is the fluid pressure field; λ1 and λ2 are the weighting coefficients of the data terms and physical constraint terms.

[0091] Training data: 10 years of historical production data from an oil field (500,000 samples), Adam optimizer (learning rate 0.001), batch size 512, trained until loss convergence (approximately 100,000 steps).

[0092] 2. Abnormal diagnosis mechanism:

[0093] Improve the accuracy of moisture content prediction and fault diagnosis;

[0094] Early warning of sudden changes in moisture content: When predicting S w If the increase exceeds 5% within 2 hours, the injection-to-production ratio adjustment algorithm is triggered.

[0095] ΔQ inj =k p (S w,target -S w,pred )+k i ∫(S w,target -S w,pred )dt

[0096] Where, k p =0.8 is the proportionality coefficient; k i =0.2 is the integral coefficient; S w,target =70% is the target water saturation level.

[0097] Equipment fault diagnosis: Analyze the vibration spectrum of the electric pump. If the amplitude of the 63Hz component (characteristic frequency of bearing defects) is >0.4g, the probability of failure is determined to be >85%.

[0098] Example:

[0099] Predicting the S of a certain well group w The percentage increased from 65% to 72%, with actual monitoring showing 71.3%, an error of 0.7%. The automatic water injection volume was adjusted from 250m³. 3 / d increased to 280m 3 / d;

[0100] A 0.45g component at 63Hz was detected in a certain electric pump, providing a 36-hour advance warning. The bearing was replaced to avoid downtime losses.

[0101] Step 4: Optimize Decision Generation

[0102] Increase oil recovery and reduce carbon emission intensity; hedge risks to reduce losses caused by oil price fluctuations.

[0103] 1. Digital Twin System:

[0104] A full 3D geological model with 1 million grids was built in the Petrel platform, integrating real-time production data (refresh frequency 30 seconds);

[0105] The virtual wellbore model includes detailed components such as casing, packer, pumps and valves, simulating the temperature-stress coupling effect.

[0106] 2. Multi-objective optimization algorithm:

[0107] Improved NSGA-Ⅲ algorithm parameters: population size 200, crossover probability 0.9, mutation probability 0.05, number of iterations 500;

[0108] Fitness function:

[0109] F = [ER, NPV, 1 / WC, -E] carbon ] T

[0110] Wherein, ER is the predicted recovery rate, calculated using the material balance equation; NPV is the net present value, taking into account dynamic parameters such as oil price and operating costs; WC is the comprehensive water cut, assigned a weighting coefficient to different well groups; E carbon The weights of the carbon emission indicators are dynamically adjusted according to the carbon tax policy.

[0111] Constraints:

[0112] Bottom hole flowing pressure P wf ≥15MPa (higher than the bubble point pressure of 14.2MPa);

[0113] Injection-to-production ratio 0.9 ≤ ∑Q inj / ∑Q prod ≤1.2.

[0114] 3. Risk hedging mechanism:

[0115] When the international oil price drops by more than 8% in a single day, switch to a low-production and stable-production mode to reduce power consumption by 15%-20%.

[0116] When the downhole H2S concentration is >25ppm, an automatic corrosion inhibitor (concentration 30ppm) is injected and the pH is raised to >6.5.

[0117] Example:

[0118] After optimization, the daily output of a certain well group increased from 800 tons to 850 tons, the water cut decreased from 68% to 65%, and the annual NPV increased by $15 million; during the period of oil price crash, the automatic adjustment scheme saved $25,000 per day in electricity costs.

[0119] Step 5: Closed-Loop Execution and Blockchain Integration

[0120] Short control response time; blockchain-based evidence storage shortens data auditing time and reduces costs.

[0121] 1. Edge control execution:

[0122] Adaptive PID control rules:

[0123]

[0124] Where u(t) is the control output (mA); e(t) is the deviation between the setpoint and the actual value; K p K is a proportionality coefficient that is dynamically adjusted based on the reservoir pressure gradient. i The integral coefficient satisfies K with the injection-production response delay time τ. i =1 / (2τ); K d This is the differential coefficient, which is forcibly reset to zero when the sand discharge warning is activated.

[0125] Example: For a well with pressure deviation e(t) = 1.5 MPa and ae(t) = 1.5 MPa, calculate the control output:

[0126]

[0127] Adjusting the water pump frequency from 45Hz to 48Hz increases the water injection volume by 12m³. 3 / h.

[0128] 2. Blockchain-based evidence storage:

[0129] Hash calculation: Write the hash value of the optimized decision parameters into the smart contract.

[0130] H decision =SHA3-256(Q inj |Q prod |Timestamp)

[0131] Among them, Q inj Q is the command to adjust the water injection volume. prod Sets the oil production rate; Timestamp is a UNIX timestamp.

[0132] Example:

[0133] Hdecision=SHA3-256(300∣∣1800∣∣1659376800000)

[0134] Among them, Q inj =300m 3 / d, Q prod =1800m 3 / d, Timestamp = 2022-08-02 12:00:00 (UNIX timestamp);

[0135] Smart contract trigger: When the actual oil production deviation is greater than 12%, the DAS raw data and model intermediate parameters are automatically retrieved to locate the source of the anomaly (such as the excessive drift of a certain FBG pressure gauge).

[0136] This embodiment provides a big data-based intelligent dynamic monitoring and optimized exploitation method for oil and gas reservoirs. It utilizes a heterogeneous sensor network, including distributed fiber optic sensors and multiphase flow meters, to collect real-time data on formation pressure, temperature, and fluid velocity. A multi-physics coupled model of geomechanics, seepage, and equipment operating conditions is constructed, and a Physically Constrained Neural Network (PINN) is employed to accurately predict water cut and fracture risk. A multi-objective optimization scheme is generated based on digital twins and an improved NSGA-Ⅲ algorithm. Adaptive PID edge control is used to adjust injection and production parameters in real time, forming a closed-loop control chain. Blockchain hash storage ensures data immutability and full-process traceability. Practical applications show that this method improves recovery rate, reduces ineffective water injection, increases fault warning accuracy, and lowers carbon emission intensity, possessing the core advantages of efficient exploitation, intelligent operation and maintenance, and green low-carbon development.

Claims

1. A method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data, characterized in that, Includes the following steps: Step 1, Multi-source data acquisition and preprocessing: Deploy a heterogeneous sensor network in the wellbore, surface gathering and transportation pipeline and reservoir to collect multi-dimensional production data in real time, including formation pressure, temperature, fluid velocity, water cut, downhole motor vibration spectrum, and casing deformation data. Perform noise filtering, spatiotemporal alignment and normalization on the raw data. The heterogeneous sensor network includes distributed fiber optic acoustic sensors, downhole permanent pressure gauges, multiphase flow meters, and high-precision temperature sensors at the wellhead. Data preprocessing employs a sliding window dynamic calibration method to compensate for sensor drift. The compensation formula is as follows: in, The original sensor reading; The sensor's time drift coefficient is calibrated using daily zero-point self-test data. : The time interval since the last calibration; This refers to the amplitude of environmental electromagnetic interference. The main interference frequencies were identified using Fast Fourier Transform. Step 2, Dynamic Coupled Modeling: The preprocessed real-time data is fused with the 3D geological model and historical development data to construct a multi-physics field coupled analysis model that includes reservoir physical parameters, fluid migration patterns, and equipment operating status. Step 3, Intelligent Prediction and Diagnosis: Based on the coupled model, an injection-production response prediction module is established through machine learning algorithms to output the prediction results of reservoir pressure distribution, water drive front location, fracture closure risk index and equipment failure probability in real time. Step 4, Optimize decision generation: Based on the prediction results, simulate the production effect under different combinations of mining parameters in the digital twin system, and use a multi-objective optimization algorithm to generate injection-production adjustment schemes, optimized pumping frequency values, and chemical displacement agent injection strategies. Step 5, Closed-loop execution and blockchain integration: The optimized plan is sent to the well site edge controller for execution, and production data after execution is collected synchronously. The prediction model parameters are updated through an online learning mechanism to form a closed-loop control link of "perception-decision-execution-verification".

2. The method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data as described in claim 1, characterized in that, The multiphysics coupling analysis model in step two includes a three-dimensional coupling of a geomechanics module, a seepage module, and an equipment condition module. A loosely coupled iterative algorithm is used to achieve data interaction between modules, completing the following within each time step: Update the reservoir permeability tensor based on changes in geostress. Calculate fluid pressure distribution based on the new permeability; By inferring the sleeve deformation through fluid pressure, the vibration constraint conditions of the equipment can be corrected.

3. The method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data according to claim 1, characterized in that, In step three: The machine learning algorithm employs a Physical Information Neural Network (PINN), and its loss function includes: in, The network outputs predicted pressure / saturation values; These are measured pressure / saturation data; K is the permeability tensor; p is the fluid pressure field. , These are the weighting coefficients for the data items and the physical constraint items.

4. The method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data according to claim 1, characterized in that, In step four: The digital twin system includes a full-chain simulation model of the formation, wellbore, and surface equipment; The multi-objective optimization employs an improved NSGA-II algorithm, whose fitness function includes: Among them, ER is the predicted recovery rate, calculated through the material balance equation; NPV is the net present value, taking into account dynamic parameters such as oil price and operating cost; WC is the comprehensive water cut, assigned a weighting coefficient to different well groups.

5. The method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data according to claim 1, characterized in that, In step five: The edge controller deploys an adaptive PID algorithm, and the control variables include: in, To control the output (mA); The deviation between the set value and the actual value; This is a proportionality coefficient, dynamically adjusted according to the reservoir pressure gradient; The integral coefficient satisfies the following condition with the injection-production response delay time τ: ; This is the differential coefficient, which is forcibly reset to zero when the sand discharge warning is activated.

6. The method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data according to claim 1, characterized in that, A risk hedging mechanism is introduced in the optimization decision-making process of step four, and a conservative mining scheme is activated when one of the following situations occurs: International oil prices fell by more than 7% in a single day; The downhole CO2 concentration monitoring value exceeded the critical value for H2S synergistic corrosion. The regional power grid load factor remained above 90% for two consecutive hours.

7. The method for intelligent dynamic monitoring and optimized exploitation of oil and gas reservoirs based on big data according to claim 1, characterized in that, The trusted evidence storage mechanism integrated into step five specifically includes: Write the hash value of the optimized decision parameters into the smart contract: in, This is a command to adjust the water injection volume. Set the oil production rate; Timestamp is a UNIX timestamp. When the actual production data deviates from the predicted value by more than 15%, the blockchain evidence audit process is automatically triggered to trace the original sensor data and intermediate results of model calculations.

Images