Model prediction control method for health perception enhancement of offshore oil underwater production system

Abstract

The invention relates to the technical field of petroleum engineering, and provides a model prediction control method for health perception enhancement of an offshore oil underwater production system, and the method comprises three core steps: multi-source sensor information fusion, health assessment and residual service life prediction, and health perception enhanced model prediction control. By fusing multi-source sensor data, building a health index and a dynamic Bayesian network model, predicting the remaining service life of a system, bringing a health state and a production target into an optimization framework, and dynamically adjusting the rotating speed of an electric submersible pump and the opening degree of an oil nozzle, balance between production efficiency and the service life of equipment is achieved; the state monitoring precision is improved through multi-source sensor data fusion, flexible and real-time health assessment is achieved through the dynamic Bayesian network, and a scientific basis is provided for maintenance decision making. The health perception enhanced model predictive control optimizes the control instruction, ensures the safety and efficiency of the production process, effectively prolongs the service life of the system, and has important practical value.

Description

Technical Field

[0001] The present invention relates to the technical field of petroleum engineering, and proposes a model predictive control method for enhancing health perception of an offshore oil underwater production system. Background Art

[0002] With the continued growth of global energy demand, the development of marine oil resources has become an important way to meet energy supply. As a core component of marine oil extraction, the stability and reliability of the underwater production system directly affect the production efficiency and economic benefits of the oil field. As key equipment in the underwater production system, electric submersible pumps and nozzles are responsible for providing downhole fluid lifting power and regulating oil well production, respectively. However, the complexity of the underwater environment, such as high pressure, low temperature, corrosive media, and performance degradation caused by long-term operation of equipment, significantly increase the risk of failure of key equipment in the underwater production system, seriously threatening the safety and continuity of the underwater production system.

[0003] Traditional model predictive control methods have been widely used in subsea production systems, primarily to achieve production targets by optimizing control commands. However, existing model predictive control methods fail to consider the health status and remaining useful life of equipment. This can lead to control commands exceeding the equipment's tolerance, accelerating equipment degradation and even causing failure. Therefore, it is particularly necessary to propose a model predictive control method with enhanced health awareness for offshore oil subsea production systems. Summary of the Invention

[0004] The purpose of the present invention is to address the deficiencies of the existing technology and propose a model predictive control method for an offshore oil underwater production system with enhanced health perception.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A model predictive control method for enhancing health perception of an offshore oil underwater production system comprises: Multi-source sensor information fusion: Preprocess and align data from pressure sensors, temperature sensors, and vibration sensors from various components of the underwater production system. A sliding window method is used to address inconsistent sampling frequencies. Linear interpolation is performed on low-frequency data to align it with the timestamps of high-frequency data, and mean calculation is performed to generate output data with a uniform frequency. Sensor data of different dimensions is normalized to the [0, 1] interval to facilitate subsequent fusion calculations. Weights are assigned to each component based on its reliability, and a weighted average method is used to fuse multi-source sensor data based on the sensor data of each component. Health assessment and remaining service life prediction: Based on the fusion of multi-source sensor data, a health index is constructed to reflect the current health status of the subsea production system. HIA dynamic Bayesian network model of the underwater production system's health status is constructed using the sensor data of each component and the reliability weights assigned to each component. As time changes, when the data of each sensor is updated, the new data is input into the underwater production system's health status dynamic Bayesian network through evidence nodes to dynamically update the model's health index. Based on the dynamic health index obtained from the underwater production system's health status dynamic Bayesian network, the remaining service life of the underwater production system is calculated. Model predictive control with enhanced health awareness: The equipment health status and production goals are simultaneously incorporated into the optimization framework, and the speed and nozzle opening of the submersible pump are dynamically adjusted to achieve a balance between maximizing production efficiency and extending equipment life. The inputs of the controller architecture are real-time sensor data, remaining service life prediction results, and expected oil and gas production targets, and the outputs are ESP speed control instructions and nozzle opening control instructions. The core module includes a state prediction model, a remaining service life constraint module, and an optimization solver. The objective function comprehensively considers oil and gas production tracking errors and equipment health losses, converting the remaining service life prediction value into upper and lower limit constraints of the control input. State variables such as pressure and flow must be within a safe range. Based on the system model, the state variables in the future time domain are predicted, the objective function and constraints are constructed, and the quadratic programming solver is called to generate the optimal control sequence. The optimal control instructions are sent to the actuator, and the system state is updated to enter the next control cycle.

[0006] Furthermore, the multi-source sensor information fusion includes: In the multi-source sensor information fusion step, the time length of the sliding window is T. For each window, data from all sensors in that time period are collected. For high-frequency sensors, there are Nh = fh × T data points in window T. For low-frequency sensors, there are Nl = fl × T data points in window T. Linear interpolation is performed on the low-frequency data to align it with the timestamp of the high-frequency data. For the i-th data point yl(ti) of the low-frequency sensor, the interpolation value at time t (ti≤t≤ti+1) is: ; Calculate the mean of the data in each window to generate output data of uniform frequency; suppose the data bit of the high-frequency sensor in window T is { y h ( t 1), y h ( t 2), y h ( t Nh )}, the interpolation data of the low-frequency sensor is { y l ( t 1), yl ( t 2), y l ( t Nh )}, the mean value within the window is: ; ; Sliding window with step size ∆t Move forward, update the data in the window and repeat the above calculation.

[0007] Furthermore, in the multi-source sensor information fusion step, the sensor data of different dimensions are normalized to the [0,1] interval to facilitate subsequent fusion calculations. For sensor data y, the normalized data yn is: .

[0008] Furthermore, in the multi-source sensor information fusion step, the reliability of each component is used to assign weights, and based on the sensor data of each component, the multi-source sensor data is fused using the weighted average method: ; in, y f is the fused data, w i The weights are calibrated based on historical data.

[0009] Furthermore, in the health assessment and remaining service life prediction steps, a health index HI reflecting the current health status of the underwater production system is constructed based on the fused multi-source sensor data: ; in, y m It is the benchmark value under normal conditions of the underwater production system.

[0010] Furthermore, in the health assessment and remaining service life prediction steps, the sensor data of each component and the reliability distribution weight of each component are used to construct a dynamic Bayesian network model of the health status of the underwater production system; in this model, E 1— E n Nodes are components of the underwater production system n The evidence node of the sensor data is used to update the data of each sensor; Y 1— Y n Nodes are components of the underwater production system n Sensor data; W Nodes are weighted nodes for reliability assignment;Y f The node is a multi-source sensor data fusion node; HI It is the underwater production system health index node; Y m The node is the baseline value node under the normal state of the underwater production system; as time changes, when the data of each sensor is updated, the new data is input into the dynamic Bayesian network of the underwater production system health status through the evidence node to complete the dynamic update of the health index of the model.

[0011] Furthermore, in the health assessment and remaining service life prediction steps, the remaining service life of the underwater production system is the time period from the current monitoring time to the time when the health index first reaches the fault threshold. Based on the dynamic health index obtained by the dynamic Bayesian network of the underwater production system health status, the remaining service life of the underwater production system can be calculated as: ; in, RUL sys is the remaining useful life of the subsea production system, G is the failure threshold.

[0012] Furthermore, in the health-aware enhanced model predictive control step, the objective function comprehensively considers oil and gas production tracking error and equipment health loss, and can be expressed as: ; in, q ( k ) is the system output, r ( k ) is the expected output target, u ( k ) is the control input, Q and R are weight matrices, representing the cost of output tracking error and control input respectively, HI ( k ) is the health index, reflecting the current degradation state of the system, λ is the health weight factor, which is dynamically adjusted as the remaining service life decreases: ; in, λ 0 is the initial weight, β is the attenuation coefficient of the health weight factor; Furthermore, in the health-aware enhanced model predictive control step, the remaining service life prediction value is converted into the upper and lower limit constraints of the control input: ; in, u max (k ) gradually decreases as the remaining service life shortens to avoid equipment overload: ; in, u design is the maximum design input, α is the control input upper limit attenuation coefficient; State variables such as pressure and flow must be within a safe range: .

[0013] Furthermore, in the health-aware enhanced model predictive control step, the state variables in the future time domain are predicted based on the system model: ; in, f (∙) is the system state equation; Construct the objective function and constraints, and call the quadratic programming solver to generate the optimal control sequence: ; The optimal control instructions, namely the electric submersible pump speed and nozzle opening, are sent to the actuator, and the system status is updated to enter the next control cycle.

[0014] The beneficial effects of the present invention are as follows: By effectively integrating information from multiple sensors, the status of underwater production systems can be more accurately monitored, thereby enhancing the accuracy of health assessments. Furthermore, the application of dynamic Bayesian networks makes health status assessments more flexible and real-time, while remaining useful life predictions provide a scientific basis for maintenance decisions. Model predictive control with enhanced health awareness not only optimizes control instructions but also ensures the safety and efficiency of the production process, which has important practical value in addressing potential failures and extending system life. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a dynamic Bayesian network model of the health status of the underwater production system; Figure 2 is a schematic diagram of the underwater production system; Figure 3 This is a schematic diagram of a model predictive control system for enhanced health perception of an offshore oil underwater production system.

[0016] In the figure, 101, subsea distribution unit, 102, hydraulic distribution module, 103, electronic distribution module, 104, subsea control module, 105, control pilot valve, 106, first solenoid valve, 107, second solenoid valve, 108, third solenoid valve, 109, subsea electronic module, 110, fourth solenoid valve, 111, fifth solenoid valve, 112, sixth solenoid valve, 113, subsea valve group, 114, chemical injection valve, 115, conversion valve, 116, annular wing valve, 117, production wing valve, 118, production main valve, 119, annular main valve, 120, wellhead mechanical module, 121, nozzle module, 122, downhole electric submersible pump module, 123, master control station 124. , 201. Multi-source sensor information fusion subsystem, 202. Underwater production system monitoring data preprocessing and alignment module, 203. Underwater production system sensor data normalization module, 204. Underwater production system sensor data fusion module, 205. Health assessment and remaining service life prediction subsystem, 206. Underwater production system health index calculation module, 207. Underwater production system health status dynamic Bayesian network establishment module, 208. Underwater production system remaining service life prediction module, 209. Health perception enhanced model predictive control subsystem, 210. Controller architecture establishment module, 211. Objective function and constraint design module, 212. Control instruction optimization module. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0018] Example 1: like Figure 1 As shown in the figure, a model predictive control method with enhanced health perception of offshore oil underwater production system mainly includes three steps: multi-source sensor information fusion, health assessment and remaining service life prediction, and model predictive control with enhanced health perception.

[0019] The specific steps of multi-source sensor information fusion are: S101: Preprocessing and alignment of underwater production system monitoring data. Align the timestamps of the pressure sensors, temperature sensors, and vibration sensors from various components of the underwater production system, and use the sliding window method to solve the problem of inconsistent sampling frequencies. Assume that the time length of the sliding window is T ,For each window, collect the data of all sensors in that time period. For high-frequency sensors (sampling frequency f h ), in the window T Inside N h =f h × T data points; for low-frequency sensors (sampling frequency f l ), in the window T Inside N l = f l × T Data points. Linearly interpolate the low-frequency data to align it with the timestamp of the high-frequency data. i data points y l ( t i ), at time t ( t i ≤ t ≤ t i+1 ) is the interpolated value at: ; The data in each window is averaged to generate output data of uniform frequency. Assume that the data bits of the high-frequency sensor in window T are { y h ( t 1), y h ( t 2), y h ( t Nh )}, the interpolation data of the low-frequency sensor is { y l ( t 1), y l ( t 2), y l ( t Nh )}, the mean value within the window is: ; ; Sliding window with step size ∆t Move forward, update the data in the window and repeat the above calculation.

[0020] S102: Normalize sensor data of underwater production system. Normalize sensor data of different dimensions to the range of [0,1] to facilitate subsequent fusion calculation. y , the normalized data y n for: ; S103: Subsea production system sensor data fusion. Using the reliability of each component to assign weights, based on the sensor data of each component, a weighted average method is used to fuse multi-source sensor data: ; in, y f is the fused data, w i The weights are calibrated based on historical data.

[0021] The specific steps for health assessment and remaining service life prediction are: S201: Calculation of underwater production system health index. Based on the fused multi-source sensor data, a health index is constructed to reflect the current health status of the underwater production system. HI : ; in, y m It is the benchmark value under normal conditions of the underwater production system.

[0022] S202: Establishment of a dynamic Bayesian network for the health status of the underwater production system. Utilizing the sensor data of each component and the reliability weights of each component, a dynamic Bayesian network model for the health status of the underwater production system is constructed, such as Figure 1 In this model, E 1— E n Nodes are components of the underwater production system n The evidence node of the sensor data is used to update the data of each sensor; Y 1— Y n Nodes are components of the underwater production system n Sensor data; W Nodes are weighted nodes for reliability assignment; Y f The node is a multi-source sensor data fusion node; HI It is the underwater production system health index node; Y m The nodes are the baseline value nodes for the underwater production system under normal conditions. As time changes, when the data from each sensor is updated, the new data is input into the underwater production system health status dynamic Bayesian network through the evidence nodes, completing the dynamic update of the health index of the model.

[0023] S203: Prediction of the remaining service life of the underwater production system. The remaining service life of the underwater production system is the period from the current monitoring time to the first time the health index reaches the fault threshold. Based on the dynamic health index obtained by the dynamic Bayesian network of the underwater production system health status, the remaining service life of the underwater production system can be calculated as: ; in, RUL sys is the remaining useful life of the subsea production system, G is the failure threshold.

[0024] The specific steps of health-aware enhanced model predictive control are: S301: Controller Architecture Establishment. The core concept of model predictive control with enhanced health awareness for subsea production systems is to incorporate both equipment health and production targets into the optimization framework, dynamically adjusting the speed and nozzle opening of the ESP to achieve a balance between maximizing production efficiency and extending equipment life. The controller architecture's inputs are real-time sensor data, remaining useful life predictions, and expected oil and gas production targets; its outputs are control commands for the ESP speed and nozzle opening. The core modules include a state prediction model, a remaining useful life constraint module, and an optimization solver.

[0025] S302: Design of objective function and constraints. The objective function comprehensively considers oil and gas production tracking error and equipment health loss, and can be expressed as: ; in, q ( k ) is the system output, r ( k ) is the expected output target, u ( k ) is the control input, Q and R are weight matrices, representing the cost of output tracking error and control input respectively, HI ( k ) is the health index, reflecting the current degradation state of the system, λ is the health weight factor, which is dynamically adjusted as the remaining service life decreases: ; in, λ 0 is the initial weight, β is the attenuation coefficient of the health weight factor.

[0026] Convert the remaining useful life prediction value into upper and lower limit constraints of the control input: ; in, umax ( k ) gradually decreases as the remaining service life shortens to avoid equipment overload: ; in, u design is the maximum design input, α It is the upper limit attenuation coefficient of the control input.

[0027] State variables such as pressure and flow must be within a safe range: ; S303: Control instruction optimization. Predict state variables in the future time domain based on the system model: ; in, f (∙) is the system state equation.

[0028] Construct the objective function and constraints, and call the quadratic programming solver to generate the optimal control sequence: ; The optimal control instructions, namely the electric submersible pump speed and nozzle opening, are sent to the actuator, and the system status is updated to enter the next control cycle.

[0029] Example 2: like Figure 2As shown, the subsea production system includes a subsea distribution unit 101, a subsea control module 104, a subsea valve group 113 and a wellhead mechanical module 120; wherein the subsea distribution unit 101 is located outside the oil tree and is installed on the seabed support, and includes: a hydraulic distribution module 102 and an electronic distribution module 103; the hydraulic distribution module 102 is connected to the control pilot valve 105 through a hydraulic pipeline, and is used to provide hydraulic power to the control pilot valve 105; the electronic distribution module 103 is connected to the subsea electronic module 109 through a cable, and is used to provide electrical power to the subsea electronic module 109; the subsea control module 104 is located between the subsea distribution unit 101 and the subsea oil tree and is installed on the seabed support, and includes: the control pilot valve 105, the subsea electronic module 113 and the wellhead mechanical module 120; Module 109, the first solenoid valve 106, the second solenoid valve 107, the third solenoid valve 108, the fourth solenoid valve 110, the fifth solenoid valve 111 and the sixth solenoid valve 112; the control pilot valve 105 is connected to the first solenoid valve 106, the second solenoid valve 107, the third solenoid valve 108, the fourth solenoid valve 110, the fifth solenoid valve 111 and the sixth solenoid valve 112 through a hydraulic pipeline to provide hydraulic power for the six solenoid valves; the underwater electronic module 109 is connected to the first solenoid valve 106, the second solenoid valve 107, the third solenoid valve 108, the fourth solenoid valve 110, the fifth solenoid valve 111 and the sixth solenoid valve 112 through a cable to control the switches of the six solenoid valves; the first solenoid valve 106 is connected to the annular wing through a hydraulic pipeline The first solenoid valve 108 is connected to the annulus main valve 119 through a hydraulic pipeline to control the switch of the annulus main valve 119; the second solenoid valve 107 is connected to the chemical injection valve 114 through a hydraulic pipeline to control the switch of the chemical injection valve 114; the third solenoid valve 108 is connected to the annulus main valve 119 through a hydraulic pipeline to control the switch of the annulus main valve 119; the fourth solenoid valve 110 is connected to the conversion valve 115 through a hydraulic pipeline to control the switch of the conversion valve 115; the fifth solenoid valve 111 is connected to the production main valve 118 through a hydraulic pipeline to control the switch of the production main valve 118; the sixth solenoid valve 112 is connected to the production wing valve 117 through a hydraulic pipeline to control the switch of the production wing valve 117; the subsea valve group 113 is located on the oil production tree and is installed on the underwater production tree. The Christmas tree body includes a chemical injection valve 114, a switching valve 115, an annular wing valve 116, a production wing valve 117, a production main valve 118, and an annular main valve 119; the chemical injection valve 114, the switching valve 115, the annular wing valve 116, the production wing valve 117, the production main valve 118, and the annular main valve 119 are connected to the oil pipeline to control the transportation of oil; the wellhead mechanical module 120 is located at the underwater wellhead and installed at the bottom of the underwater Christmas tree; the wellhead mechanical module 120 is connected to the oil pipeline to provide power for underwater oil and gas transportation; the nozzle module 121 is located underground and installed at the oil outlet; the nozzle module 121 is connected to the oil pipeline to control the oil outlet pressure; the downhole electric submersible pump module 122 is located underground and installed in the oil reservoir;The downhole electric submersible pump module 122 is connected to the nozzle module 121 and is used to extract oil from the well. The main control station 123 is located above water and installed at the control station. The main control station 123 is connected to the underwater distribution unit 101 via a cable and is used to control the underwater components and collect underwater sensor information.

[0030] Example 3: like Figure 3 As shown, the model predictive control system with enhanced health perception of the marine oil underwater production system includes a multi-source sensor information fusion subsystem 201 installed at the underwater wellhead, a health assessment and remaining service life prediction subsystem 205 installed at the underwater wellhead, and a model predictive control subsystem 209 with enhanced health perception installed at the underwater wellhead.

[0031] The multi-source sensor information fusion subsystem 201 includes an underwater production system monitoring data preprocessing and alignment module 202, an underwater production system sensor data normalization module 203 and an underwater production system sensor data fusion module 204; the underwater production system monitoring data preprocessing and alignment module 202 is connected to the main control station 123 via a cable, and is used to collect and preprocess underwater production system sensor data; the underwater production system sensor data normalization module 203 is connected to the underwater production system monitoring data preprocessing and alignment module 202 via a cable, and is used to normalize the underwater production system sensor data; the underwater production system sensor data fusion module 204 is connected to the underwater production system sensor data normalization module 203 via a cable, and is used to fuse data from underwater production system sensors.

[0032] The health assessment and remaining service life prediction subsystem 205 includes an underwater production system health index calculation module 206, an underwater production system health status dynamic Bayesian network establishment module 207 and an underwater production system remaining service life prediction module 208; the underwater production system health index calculation module 206 is connected to the underwater production system sensor data fusion module 204 through a cable, and is used to calculate the health index of the underwater production system; the underwater production system health status dynamic Bayesian network establishment module 207 is connected to the underwater production system health index calculation module 206 through a cable, and is used to establish a dynamic assessment model for the health status of the underwater production system; the underwater production system remaining service life prediction module 208 is connected to the underwater production system health status dynamic Bayesian network establishment module 207 through a cable, and is used to calculate the healthy service life of the underwater production system.

[0033] The health-aware enhanced model predictive control subsystem 209 includes a controller architecture establishment module 210, an objective function and constraint design module 211, and a control instruction optimization module 212; the controller architecture establishment module 210 is connected to the underwater production system remaining service life prediction module 208 via a cable, and is used to construct a controller architecture that integrates life information; the objective function and constraint design module 211 is connected to the controller architecture establishment module 210 via a cable, and is used to construct a control optimization mathematical model; the control instruction optimization module 212 is connected to the objective function and constraint design module 211, the nozzle module 121, and the downhole submersible pump module 122 via a cable, and is used to optimize the control instructions of the nozzle module 121 and the downhole submersible pump module 122.

[0034] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A model predictive control method for enhancing health perception of an offshore oil underwater production system, characterized in that: include: First, through multi-source sensor information fusion, the pressure, temperature, and vibration sensor data are preprocessed and aligned, and the data are normalized and fused; Secondly, a health index HI is constructed based on the fused data, and a dynamic Bayesian network model is used to predict the health status and remaining service life of the underwater production system. Finally, through model predictive control, the equipment health status and production goals are incorporated into the optimization framework, and the speed and nozzle opening of the submersible pump are dynamically adjusted to achieve a balance between maximizing production efficiency and extending equipment life. The controller receives real-time sensor data, remaining service life prediction and oil and gas production targets, outputs control instructions, and generates the optimal control sequence through a quadratic programming solver.

2. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 1 is characterized in that: The specific steps include: Multi-source sensor information fusion: pre-process and align the data from the pressure sensors, temperature sensors, and vibration sensors of various components of the underwater production system, use the sliding window method to solve the problem of inconsistent sampling frequencies, perform linear interpolation on low-frequency data to align it with the timestamp of high-frequency data, and perform mean calculation to generate output data with uniform frequency; Normalize sensor data of different dimensions to the interval [0,1] to facilitate subsequent fusion calculations; use the reliability of each component to assign weights, and use the weighted average method to fuse multi-source sensor data based on the sensor data of each component; Health assessment and remaining service life prediction: Based on the fused multi-source sensor data, a health index HI that reflects the current health status of the underwater production system is constructed; a dynamic Bayesian network model of the health status of the underwater production system is constructed using the sensor data of each component and the reliability allocation weight of each component. As time changes, when the data of each sensor is updated, the new data is input into the dynamic Bayesian network of the health status of the underwater production system through the evidence node to complete the dynamic update of the health index of the model; based on the dynamic health index obtained by the dynamic Bayesian network of the health status of the underwater production system, the remaining service life of the underwater production system is calculated; Model predictive control with enhanced health perception: The equipment health status and production targets are simultaneously incorporated into the optimization framework, and the speed and nozzle opening of the submersible pump are dynamically adjusted to achieve a balance between maximizing production efficiency and extending equipment life. The inputs in the controller architecture are real-time sensor data, remaining service life prediction results, and expected oil and gas production targets, and the outputs are submersible pump speed control instructions and nozzle opening control instructions. The core module includes a state prediction model, a remaining service life constraint module, and an optimization solver. The objective function comprehensively considers oil and gas production tracking errors and equipment health losses, and converts the remaining service life prediction value into upper and lower limit constraints of the control input. State variables such as pressure and flow must be within a safe range. Based on the system model, the state variables in the future time domain are predicted, the objective function and constraints are constructed, the quadratic programming solver is called to generate the optimal control sequence, the optimal control instructions are sent to the actuator, and the system state is updated to enter the next control cycle.

3. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 2 is characterized in that: The multi-source sensor information fusion includes: In the multi-source sensor information fusion step, the time length of the sliding window is T. For each window, the data of all sensors in the time period are collected; for high-frequency sensors, there are Nh=fh×T data points in window T; for low-frequency sensors, there are Nl=fl×T data points in window T; linear interpolation is performed on the low-frequency data to align it with the timestamp of the high-frequency data; for the i-th data point yl(ti) of the low-frequency sensor, the interpolation at time t (ti≤t≤ti+1) is: ； The data in each window is averaged to generate output data with uniform frequency. Let the data bits of the high-frequency sensor in window T be { y h ( t 1), y h ( t 2), y h ( t Nh )}, the interpolation data of the low-frequency sensor is { y l ( t 1), y l ( t 2), y l ( t Nh )}, the mean value in the window is: ； ； Sliding window with step size ∆t Move forward, update the data in the window and repeat the above calculation.

4. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 3 is characterized in that: In the multi-source sensor information fusion step, the sensor data of different dimensions are normalized to the interval [0,1] to facilitate subsequent fusion calculations. For sensor data y, the normalized data yn is: 。 5. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 4 is characterized in that: In the multi-source sensor information fusion step, the reliability of each component is used to assign weights, and the multi-source sensor data is fused using the weighted average method based on the sensor data of each component: ； in, y f is the fused data, w i The weights are calibrated based on historical data.

6. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 5 is characterized in that: In the health assessment and remaining service life prediction steps, a health index HI reflecting the current health status of the underwater production system is constructed based on the fused multi-source sensor data: ； in, y m It is the benchmark value under normal conditions of the underwater production system.

7. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 6 is characterized in that: In the health assessment and remaining service life prediction steps, the sensor data of each component and the reliability allocation weight of each component are used to construct a dynamic Bayesian network model of the health status of the underwater production system; in this model, E 1— E n Nodes are components of the underwater production system n The evidence node of the sensor data is used to update the data of each sensor; Y 1— Y n Nodes are components of the underwater production system n Sensor data; W Nodes are reliability-assigned weight nodes; Y f The node is a multi-source sensor data fusion node; HI It is the health index node of the underwater production system; Y m The node is the baseline value node under the normal state of the underwater production system; as time changes, when the data of each sensor is updated, the new data is input into the dynamic Bayesian network of the health status of the underwater production system through the evidence node to complete the dynamic update of the health index of the model.

8. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 7 is characterized in that: In the health assessment and remaining service life prediction steps, the remaining service life of the underwater production system is the time period from the current monitoring time to the time when the health index first reaches the fault threshold. According to the dynamic health index obtained by the dynamic Bayesian network of the health status of the underwater production system, the remaining service life of the underwater production system can be calculated as: ； in, RUL sys The remaining useful life of the subsea production system, G is the failure threshold.

9. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 8 is characterized in that: In the health-aware enhanced model predictive control step, the objective function comprehensively considers the oil and gas production tracking error and equipment health loss, which can be expressed as: ； in, q ( k ) is the system output, r ( k ) is the expected production target, u ( k ) is the control input, Q and R are weight matrices, representing the cost of production tracking error and control input respectively, HI ( k ) is the health index, reflecting the current degradation state of the system. λ is the health weight factor, which is adjusted dynamically as the remaining service life decreases: ； in, λ 0 is the initial weight, β is the attenuation coefficient of the health weight factor.

10. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 9, characterized in that: In the health-aware enhanced model predictive control step, the remaining useful life prediction value is converted into the upper and lower limit constraints of the control input: ； in, u max ( k ) gradually decreases as the remaining service life shortens to avoid equipment overload: ； in, u design For the design maximum input, α is the upper limit attenuation coefficient of the control input; State variables such as pressure and flow must be within a safe range: 。 11. The model predictive control method for enhancing health perception of an offshore oil underwater production system according to claim 10, characterized in that: In the health-aware enhanced model predictive control step, the state variables in the future time domain are predicted based on the system model: ； in, f (∙) is the system state equation; Construct the objective function and constraints, and call the quadratic programming solver to generate the optimal control sequence: ； The optimal control instruction, namely the speed of the electric submersible pump and the nozzle opening, is sent to the actuator, and the system status is updated to enter the next control cycle.

Images