Full-automatic slurry mixing control system and method for oil field well cementation equipment

Abstract

The invention discloses a full-automatic slurry mixing control system and method for oil field well cementation equipment, and belongs to the technical field of oil field well cementation or ocean engineering, and the method comprises the following steps: S1, collecting slurry state data, power system operation data and external environment data through a multi-dimensional state sensing module to generate a real-time working condition data set; s2, based on the real-time working condition data set, adopting a preset slurry rheological state differential model to predict dynamic evolution of slurry viscosity so as to generate future slurry viscosity; s3, according to the future slurry viscosity and the preset slurry safety temperature upper limit, a preset lowest energy consumption trajectory planning model is adopted, and the optimal flow control trajectory of the power system is solved; s4, according to the real-time working condition data set, a preset optimal activator injection decision model is adopted, and the optimal activator dosage is worked out, and the accuracy and reliability of future slurry viscosity prediction are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of oilfield cementing or marine engineering, specifically to a fully automatic slurry mixing control system and method for oilfield cementing equipment. Background Technology

[0002] In oilfield cementing, especially in foundation reinforcement and fracture plugging operations in deep-sea hydrothermal vent areas, control systems face unprecedented challenges. The operating environment is extremely harsh, with intense alternating impacts from high hydrostatic pressure, low-temperature seawater, and the high temperatures and strong acidic fluids at local hydrothermal vents. Under these extreme conditions, seemingly contradictory performance requirements exist for the working slurry. Traditional control methods typically employ a command-execution model, the core of which is to precisely prepare a slurry with specific initial properties according to a pre-set formula. This method adheres dogmatically to a static control concept of "what is made is what is obtained," completely ignoring the dynamic chemical evolution characteristics of the active slurry during its transport from the mixer through pipelines to the nozzle outlet. When traditional equipment attempts to prepare and pump a highly reactive slurry designed to meet plugging requirements, a fatal technical contradiction emerges: to pump a high-viscosity slurry, the power system must operate at high power, generating a large amount of heat. The combined effect of the system's own heat generation and the high temperature of the external environment will drastically accelerate the chemical reaction of the slurry, causing the slurry to solidify prematurely inside the equipment before reaching the nozzle; this positive feedback loop of thermal runaway will eventually lead to pipeline blockage, operation failure, or even equipment damage.

[0003] The information disclosed in the background section above is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to provide a fully automatic slurry mixing control system and method for oilfield cementing equipment, so as to solve the problems mentioned in the background art.

[0005] The technical solution of the present invention includes the following steps: S1. Through the multi-dimensional state perception module, collect slurry state data, power system operation data and external environment data to generate a real-time working condition dataset; S2. Based on real-time working condition datasets and using a pre-defined differential model of slurry rheological state, predict the dynamic evolution of slurry viscosity to generate future slurry viscosity. S3. Based on the future slurry viscosity and the preset upper limit of the slurry safety temperature, and using the preset minimum energy consumption trajectory planning model, calculate the optimal flow control trajectory of the power system. S4. Based on the real-time operating condition dataset and using the preset optimal activator injection decision model, calculate the optimal activator dosage. S5. Combine the optimal flow control trajectory with the optimal activator dosage to generate a collaborative control command, which is then executed by the collaborative control execution module.

[0006] Preferably, in S1, the generation of the real-time operating condition dataset specifically includes: Collect slurry temperature, slurry pressure, and slurry flow velocity as slurry state data; Hydraulic oil temperature, motor speed, and system load are collected as operating data for the power system. External environmental data such as ambient temperature, ambient pressure, and distance to the target point are collected.

[0007] Preferably, in S2, the differential model of the slurry rheological state defines the viscosity change rate by combining the following two terms: Temperature-driven term characterizing viscosity increase due to chemical reaction; The shear thinning term characterizes the decrease in viscosity caused by mechanical shearing.

[0008] Preferably, in S3, the minimum energy consumption trajectory planning model establishes an objective function, which consists of a useful power term and a temperature penalty term; When the slurry temperature predicted based on future slurry viscosity exceeds the upper limit of the slurry's safe temperature, the temperature penalty term is positive to force the optimization algorithm to generate the optimal flow control trajectory that can reduce system heat generation. When the predicted slurry temperature based on future slurry viscosity does not exceed the upper limit of the slurry's safe temperature, the temperature penalty term is zero.

[0009] Preferably, in S4, the optimal activator dosage is calculated by establishing a target equation that makes the slurry setting time equal to the transit time of the slurry from the activator injection point to the nozzle outlet, and solving the target equation.

[0010] Preferably, in S5, the cooperative control instructions specifically include: Flow commands used to regulate the power coordination control unit; Dosage commands used to regulate the micro-dose precision injection unit.

[0011] A fully automatic slurry mixing control system for oilfield cementing equipment includes: The multi-dimensional state perception module is used to collect slurry state data, power system operation data and external environment data to generate real-time operating condition datasets; The digital twin and predictive decision-making module is used to generate the optimal flow control trajectory and the optimal activator dosage based on real-time operating condition datasets; The collaborative control execution module is used to execute collaborative control instructions consisting of the optimal flow control trajectory and the optimal activator dosage.

[0012] Preferably, the digital twin and predictive decision-making module specifically includes: The slurry viscosity prediction unit is used to generate the future slurry viscosity based on a pre-defined differential model of slurry rheological state and a real-time working condition dataset. The energy consumption trajectory planning unit is used to generate the optimal flow control trajectory based on the future slurry viscosity using a preset minimum energy consumption trajectory planning model. The activator decision unit is used to generate the optimal activator dosage based on a pre-defined optimal activator injection decision model and a real-time operating condition dataset.

[0013] This invention provides an improved fully automatic slurry mixing control system and method for oilfield cementing equipment, which has the following improvements and advantages compared with the prior art: 1. The system employs a pre-defined differential model of slurry rheological state to predict the dynamic evolution of slurry viscosity. This model creatively combines a temperature-driven term, which characterizes viscosity growth driven by chemical reactions, with a shear-thinning term, which characterizes viscosity reduction caused by mechanical shearing. This dialectical and unified model structure can accurately capture the dual physicochemical effects of slurry thickening due to heat and thinning due to shearing under stress within the pipeline, thereby greatly improving the accuracy and reliability of predicting future slurry viscosity. 2. Based on the predicted future slurry viscosity and the preset upper limit of slurry safety temperature, the system uses a minimum energy consumption trajectory planning model to calculate the optimal flow control trajectory of the power system. The objective function of this model consists of a useful power term and a temperature penalty term. When the predicted slurry temperature does not exceed the safety limit, the temperature penalty term is zero, and the system aims to minimize energy consumption. When there is a risk of the predicted temperature exceeding the limit, the positive temperature penalty term will force the optimization algorithm to generate an optimal flow control trajectory that can reduce the heat generated by the system. This design realizes an adaptive energy management strategy that balances efficiency and safety, effectively avoiding the occurrence of thermal runaway. 3. The system calculates the optimal activator dosage based on real-time operating data and an optimal activator injection decision model. The core of its calculation logic is to establish a target equation that makes the slurry setting time equal to the transit time of the slurry from the activator injection point to the nozzle outlet. By solving this equation, it ensures that the slurry maintains a low reactivity inside the equipment to facilitate safe transport, while being activated to the optimal performance state at the moment of leaving the nozzle, thus achieving precise spatiotemporal control of the slurry chemical evolution process. 4. The final generated collaborative control command is specifically decomposed into a flow command for regulating the power collaborative control unit and a dose command for regulating the micro-dose precision injection unit. This decoupled yet collaborative command mode enables the system to independently and in a related and precise manner regulate the energy efficiency of the physical transport process and the final effect of chemical activation, thereby improving the response accuracy and execution efficiency of the entire closed-loop control system. Attached Figure Description

[0014] The present invention will be further explained below with reference to the accompanying drawings and embodiments: Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0016] Example 1 Please see Figure 1 This invention provides a fully automatic slurry mixing control method for oilfield cementing equipment, comprising the following steps: S1. Through the multi-dimensional state perception module, collect slurry state data, power system operation data and external environment data to generate a real-time working condition dataset; S2. Based on real-time working condition datasets and using a pre-defined differential model of slurry rheological state, predict the dynamic evolution of slurry viscosity to generate future slurry viscosity. S3. Based on the future slurry viscosity and the preset upper limit of the slurry safety temperature, and using the preset minimum energy consumption trajectory planning model, calculate the optimal flow control trajectory of the power system. S4. Based on the real-time operating condition dataset and using the preset optimal activator injection decision model, calculate the optimal activator dosage. S5. Combining the optimal flow control trajectory and the optimal activator dosage, generate a collaborative control command, which is then executed by the collaborative control execution module. This embodiment provides a fully automatic slurry mixing control method for oilfield cementing equipment. The core of the control concept of this method is to change the control target from the initial state of the slurry to the final state of the slurry at the target point, and to introduce the principle of slurry spatiotemporal state prediction control and energy-reaction synergistic regulation based on digital twins to form an adaptive closed-loop control process. By establishing a multi-dimensional state perception module, comprehensive data on slurry state, power system operation, and external environment are collected to form a real-time operating condition dataset. This provides the entire control system with high-fidelity real-time information on the slurry itself, equipment operating conditions, and boundary conditions of the operating environment, forming a solid data foundation for subsequent accurate prediction and optimization decisions. Compared with the traditional open-loop control method that relies on a fixed formula, it has environmental self-adaptation capabilities. The steps of this method are as follows: Step S1: The multi-dimensional state perception module collects slurry state data, power system operation data, and external environment data to generate a real-time operating condition dataset. The multi-dimensional state perception module is an integrated unit composed of a series of industrial standard sensors, designed to monitor physical parameters related to slurry mixing operations in real time and comprehensively. In this embodiment, the module continuously collects data to form a dynamically updated real-time operating condition dataset. This dataset serves as the basis for all subsequent predictions and decision calculations, providing high-fidelity real-time boundary conditions for the digital twin system, thereby ensuring the accuracy of predictions. Step S2, based on real-time operating data and using a pre-defined slurry rheological state differential model, predicts the dynamic evolution of slurry viscosity to generate future slurry viscosity. This step aims to predict the viscosity change over time as the slurry is transported from the mixer to the nozzle. The pre-defined slurry rheological state differential model is a mathematical model calibrated in the laboratory, used to describe the viscosity change of a specific slurry formulation. Before operation, the model is precisely calibrated by performing standardized rheological tests on slurry samples and using a numerical fitting algorithm. These parameters constitute the inherent characteristic parameter set of a specific slurry formulation and are pre-set in the system. The system receives the real-time data generated in step S1 as input and calculates the predicted future slurry viscosity from the current time to any future time by performing real-time numerical integration on the differential equation. Step S3: Based on the future slurry viscosity and the preset upper limit of the slurry's safe temperature, and using a preset minimum energy consumption trajectory planning model, the optimal flow control trajectory of the power system is calculated. This step aims to minimize energy consumption while ensuring operational safety. The preset upper limit of the slurry's safe temperature is a critical value determined based on experimental data of the slurry's thermal stability and includes a safety margin. Its function is to prevent the slurry from undergoing irreversible rapid solidification due to excessively high temperatures, i.e., thermal runaway. The preset minimum energy consumption trajectory planning model is an optimal control model, which aims to find the flow control scheme that minimizes total energy consumption. This model uses the future slurry viscosity predicted in step S2 as a key input, establishes the correlation between the slurry state and pumping energy consumption, and includes a temperature penalty mechanism. By solving this model in real time, the system can generate a dynamically changing optimal flow control trajectory, rather than using the traditional constant flow or constant pressure mode. Step S4: Based on the real-time operating condition dataset and using the preset optimal activator injection decision model, calculate the optimal activator dosage. This step is used to achieve stepwise and final activation of the slurry performance. The preset optimal activator injection decision model is another mathematical model established based on laboratory calibration data. Its function is to accurately calculate the amount of activator required to achieve the best activation effect based on the real-time operating conditions. This model receives the real-time operating condition parameters from step S1 and solves them in reverse through the objective equation to calculate the optimal activator dosage. Step S5: Combining the optimal flow control trajectory and the optimal activator dosage, a coordinated control command is generated and executed by the coordinated control execution module; this step is the closing point of the control loop; the system integrates the optimal flow control trajectory calculated in step S3 and the optimal activator dosage calculated in step S4 into a set of synchronized coordinated control commands; this command is sent to the coordinated control execution module, which acts as a physical execution unit to precisely regulate the operating power of the power system to achieve the optimal flow rate and control the injection amount of the micro-dose injection unit; This embodiment transforms the control target from a static initial formulation to a dynamic final state through the aforementioned method. By employing real-time sensing, dynamic prediction, and collaborative control, it aims to address the potential thermal runaway problem caused by the superposition of system heat generation and environmental heat transfer during the pumping process of highly active slurries. This method effectively suppresses the risk of premature solidification of the slurry inside the equipment. Simultaneously, through precise terminal activation, it ensures that the slurry reaches its optimal performance state precisely when it arrives at the target operation point, significantly improving the autonomy, safety, and energy utilization efficiency of cementing operations in extreme environments.

[0017] In S1, the generation of the real-time operating condition dataset specifically includes: Collect slurry temperature, slurry pressure, and slurry flow velocity as slurry state data; Hydraulic oil temperature, motor speed, and system load are collected as operating data for the power system. External environmental data such as temperature, pressure, and distance to the target point are collected. In this embodiment, the generation of the real-time working condition dataset in step S1 is limited; In the specific implementation of step S1, the multi-dimensional state perception module completes data acquisition through its integrated specific sensors. To further clarify, the purpose of acquiring slurry state data is to directly grasp the physical state of the slurry itself. In this embodiment, temperature sensors, pressure sensors, and flow meters installed in the pipeline are used to collect slurry temperature data in real time. slurry pressure and slurry flow rate The purpose of collecting power system operating data is to monitor the equipment's own working status and load conditions. In this embodiment, the hydraulic oil temperature is collected in real time by monitoring the hydraulic system's oil temperature sensor, the motor or engine speed sensor driving the pump, and the load sensor reflecting the overall system resistance. Motor speed and system load The purpose of collecting external environmental data is to understand the boundary conditions of the work area. In this embodiment, environmental sensors mounted on a remotely operated underwater vehicle (ROV) are used to collect the external ambient temperature at the work site in real time. Environmental pressure and the distance from the nozzle of the equipment to the target point ; The above three sets of data are collected in real time and together constitute a comprehensive and highly relevant real-time operating condition dataset. By accurately collecting these three types of specific data, this embodiment provides comprehensive and high-fidelity input for subsequent prediction and decision-making models; slurry state data is the core basis for viscosity prediction; power system data reflects energy input and heat generation; and external environment data provides key boundary conditions for heat exchange calculation and activator decision-making. This specific data acquisition scheme ensures that the entire closed-loop control system can accurately perceive internal and external changes, thereby significantly improving the accuracy of the prediction model and the effectiveness of control commands, providing a necessary prerequisite for achieving robust adaptive control.

[0018] In S2, the differential model of the slurry rheological state defines the viscosity change rate by combining the following two terms: Temperature-driven term characterizing viscosity increase due to chemical reaction; Shear thinning term characterizing viscosity reduction caused by mechanical shearing;

[0019] In this embodiment, the internal structure of the differential model of the slurry rheological state in step S2 is defined; In the specific implementation of step S2, the differential model of the slurry rheological state used to predict the dynamic evolution of viscosity is essentially a differential equation describing viscosity. Over time rate of change The model is based on the analysis of the physicochemical effects on the slurry within the pipeline, and the rate of change is composed of two competing terms: The temperature-driven term characterizes viscosity growth due to chemical reactions; its physical basis is the Arrhenius equation of chemical reaction kinetics, aiming to quantify the tendency of slurries to thicken naturally due to chemical reactions such as hydration; this term indicates the real-time absolute temperature of the slurry. The higher the viscosity, the more vigorous the chemical reaction, and the faster the viscosity increases. The shear thinning term characterizes the viscosity reduction caused by mechanical shearing; its physical basis is the shear thinning effect of fluids, and its purpose is to quantify the viscosity-degrading effect caused by the mechanical energy applied to the slurry by the pumping system; this term indicates the current viscosity of the slurry itself. The higher, or the shear rate it experiences. The more intense the reaction, the faster the existing internal structure is destroyed, resulting in a faster rate of viscosity decrease. The mathematical expression for this model is constructed as follows: ;

[0020] In this equation, the first term on the right-hand side is the temperature-driven term, and the second term is the shear-thinning term; the parameters are defined as follows: The viscosity of the slurry is expressed in Pa·s and is calculated by model integration or measured in real time. Time, in seconds; The viscosity growth rate factor, in Pa·s / s, is an inherent parameter characterizing the chemical properties of a specific slurry formulation. It is obtained by fitting laboratory rheological test data and pre-set in the system. Viscosity Over time The rate of change; The base of the natural logarithm; The fitting process involves measuring the viscosity of the slurry over time at different temperatures and shear rates using a rheometer in the laboratory, and then employing a nonlinear regression algorithm, such as the Levenberg-Marquardt algorithm, to... The model is identified to minimize the sum of squared residuals between the model's predicted values ​​and the experimental data, thereby solving for the optimal parameter values. , and .

[0021] J is the equivalent hydration reaction activation energy, which is an inherent parameter characterizing the chemical properties of a specific slurry formulation. It is obtained by fitting laboratory rheological test data and pre-set in the system. Boltzmann's constant; The real-time absolute temperature of the slurry, in K, is collected in real time by the multi-dimensional state sensing module. The shear failure rate coefficient is a dimensionless parameter that is an inherent parameter characterizing the physical properties of a specific slurry formulation. It is obtained by fitting laboratory rheological test data and pre-set in the system. The shear rate experienced by the slurry. It can be calculated based on the pump speed and pipeline geometry; For example, for laminar flow in a circular pipe, the shear rate Through traffic With pipe radius The relationship can be expressed as follows: Traffic here These are the control variables that need to be optimized in step S3, thereby directly linking the control of the power system with the microrheological behavior of the slurry; Pi (π) By combining the temperature-driven viscosity increase effect and the mechanical energy-driven viscosity decrease effect into a single model, this embodiment can more accurately reflect the complex rheological behavior of slurry during actual pumping. The model structure can capture the relationship of the unity of opposites and dynamic equilibrium between the two effects, thereby greatly improving the accuracy and reliability of future slurry viscosity prediction and providing a more solid foundation for subsequent energy consumption optimization and activator decision-making. Based on this real-time operating condition dataset, the system uses a pre-defined differential model of slurry rheological state to predict the dynamic evolution of slurry viscosity. This model creatively combines a temperature-driven term, which characterizes viscosity growth driven by chemical reactions, with a shear-thinning term, which characterizes viscosity reduction caused by mechanical shearing. This dialectical and unified model structure can accurately capture the dual physicochemical effects of slurry thickening due to heat and thinning due to shearing under stress in the pipeline, thereby greatly improving the accuracy and reliability of predicting future slurry viscosity. It should be noted that this model is an effective simplification of the complex rheological behavior of slurries and is suitable for describing the main trends in viscosity under specific working conditions. For scenarios that require consideration of more complex rheological properties such as yield stress, this model can be extended.

[0022] In S3, the minimum energy consumption trajectory planning model establishes an objective function, which consists of a useful power term and a temperature penalty term. When the slurry temperature predicted based on future slurry viscosity exceeds the upper limit of the slurry's safe temperature, the temperature penalty term is positive to force the optimization algorithm to generate the optimal flow control trajectory that can reduce system heat generation. When the predicted slurry temperature based on future slurry viscosity does not exceed the upper limit of the slurry's safe temperature, the temperature penalty term is zero; In this embodiment, the objective function of the lowest energy consumption trajectory planning model in step S3 is defined; In the specific implementation of step S3, the core of the minimum energy consumption trajectory planning model used to solve the optimal flow control trajectory is to establish and solve the minimum value problem of the objective function J; the objective function J is defined as the integral of the total system power over the task cycle, and it consists of two parts: The first part is the useful power term; this term aims to quantify the power required to drive the slurry flow; based on fluid dynamics principles, this term is related to the future slurry viscosity predicted in step S2. and flow rate as a control variable It is proportional to the square of the value; its effect is that during the optimization process, there is a natural tendency to choose control strategies that can reduce viscosity or flow rate to save energy. The second part is the temperature penalty; this part aims to introduce a safety constraint during the system optimization process to prevent the slurry temperature from exceeding the preset upper limit of the slurry safety temperature. This upper limit The determination method is based on experimental data on the thermal stability of the slurry material, taking a temperature below the point where irreversible rapid solidification would occur and setting a sufficient safety margin; the logic setting of this penalty term is as follows: when the slurry temperature is predicted based on the future slurry viscosity... Exceeding the upper limit of the safe temperature of the slurry At that time, the temperature penalty term is positive; the magnitude of this positive value is related to the excess temperature difference. The cost function is proportional to the system heat generation and amplified by a large penalty weighting factor; this cost function forces the optimization algorithm to generate an optimal flow control trajectory that reduces system heat generation, such as by reducing the pump flow rate. When the slurry temperature is predicted based on the future slurry viscosity. The upper limit of the safe temperature of the slurry was not exceeded. At this time, the temperature penalty term is zero; under this safe operating condition, this term does not affect the objective function, and the optimization process will be mainly dominated by minimizing the useful power term. The mathematical expression for the objective function is constructed as follows: ;

[0023] The parameters are defined as follows: To find the objective function that minimizes the total energy consumption; Minimum value function; : The timeframe starts from the beginning of the task cycle To the end The integral; The constant characterizing the geometric features of the pumping pipeline is determined by parameters such as pipeline length and inner diameter; The future slurry viscosity predicted by the preceding steps; The system flow rate, which is used as the control variable, is solved by this model; The overall energy efficiency coefficient of the power system is obtained through equipment calibration. The adjustable temperature penalty weighting coefficient is expressed in W / K. The real-time temperature of the slurry is to be sensed or predicted, and the data comes from the multi-dimensional state sensing module or the internal thermal model. : A function that returns the larger of a and b; The internal thermal model is based on energy conservation and comprehensively considers three main thermal effects: first, the heat generated by viscous dissipation during the pumping process, which is proportional to the useful power term. Secondly, there is heat exchange between the pipe wall and the external environment; thirdly, there is the exothermic reaction of the slurry itself, the exothermic power of which is proportional to the chemical reaction rate and can be determined by the temperature-driven term in the viscosity model. Quantification is performed; by solving the heat balance differential equation that includes these three terms, the future slurry temperature can be predicted more accurately. .

[0024] This is the preset upper limit of the safe temperature for the slurry; By constructing an objective function consisting of a useful power term and a temperature penalty term, this embodiment implements an adaptive energy management strategy that balances efficiency and safety. Within the safe temperature range, the system operates with high energy efficiency. Once an overheating risk is predicted, the system will proactively reduce power to ensure safety, thereby achieving coordinated regulation of energy consumption and slurry reactivity and effectively avoiding thermal runaway. Based on the predicted future slurry viscosity and the preset upper limit of slurry safety temperature, the system uses a minimum energy consumption trajectory planning model to calculate the optimal flow control trajectory of the power system. The objective function of this model consists of a useful power term and a temperature penalty term. When the predicted slurry temperature does not exceed the safety limit, the temperature penalty term is zero, and the system aims to minimize energy consumption. When there is a risk of the predicted temperature exceeding the limit, the positive temperature penalty term will force the optimization algorithm to generate an optimal flow control trajectory that can reduce the heat generated by the system. This design realizes an adaptive energy management strategy that balances efficiency and safety, effectively avoiding the occurrence of thermal runaway.

[0025] In S4, the optimal activator dosage is calculated by establishing a target equation that makes the slurry setting time equal to the transit time of the slurry from the activator injection point to the nozzle outlet, and then solving the target equation. In this embodiment, the calculation logic for the optimal activator dosage in step S4 is defined; In the specific implementation of step S4, the core objective of calculating the optimal activator dosage is to ensure that the peak point of the slurry performance appears precisely at the outlet of the equipment nozzle. The underlying logic is to determine this by establishing a target equation that makes the slurry setting time equal to the transit time of the slurry from the activator injection point to the nozzle outlet, and solving the target equation. The derivation logic is explained as follows: Define the slurry setting time This refers to the time required from the injection of the activator until the slurry reaches the predetermined solidification state; according to the chemical reaction rate theory, this time is related to the dosage of the activator. They are inversely proportional, and the relationship can be described by an empirical formula based on laboratory calibration data; Define transit time This refers to the physical time required for the slurry to flow from the activator injection point at the end of the pipeline to the final nozzle outlet; this time can be calculated from the distance from the injection point to the nozzle. and the real-time flow rate of the slurry The calculation shows that, Both of these parameters are provided in real time by the multi-dimensional state perception module in step S1. Establish the objective equation: ;in, Transit time refers to the physical time required for the slurry to flow from the activator injection point to the nozzle outlet. : The distance from the activator injection point to the nozzle; : The real-time flow rate of the slurry; the physical meaning of this equation is that the time required for the chemical reaction to complete is exactly equal to the time required for fluid transport; : Slurry setting time refers to the time required from the injection of the activator to the slurry reaching the predetermined setting state; : Crossing time; The inverse relationship used here is an engineering simplification of reaction kinetics and has sufficient accuracy within a specific operating range. In applications requiring higher accuracy, this relationship can be replaced by an experimentally calibrated nonlinear dose-response model that more accurately reflects the true reaction order. By solving this objective equation, the optimal activator dosage required to achieve this objective can be determined. The mathematical expression is constructed as follows: ;

[0026] The parameters are defined as follows: The optimal dose of activator to be injected, in mol / m³, is determined by this model. The amount of chemical substances required to be converted per unit volume of slurry to reach the solidification state is a constant related to the slurry formulation, obtained through laboratory calibration and pre-placed in the system; The real-time flow velocity of the slurry is collected by the multi-dimensional state sensing module; The distance from the activator injection point to the nozzle outlet is provided by the multi-dimensional state sensing module; To the target area ambient temperature The equivalent chemical reaction rate constant under the condition is itself determined by the Arrhenius relation, and the relevant parameters are also calibrated in the laboratory and pre-set as performance parameters of the activator in the system; The expression is ,in Pre-exponential factor, The activation energy of the activator reaction is defined by the formula. Both of these parameters, as inherent characteristic parameters of the activator, are experimentally calibrated and pre-set in the system. The formula clarifies the external ambient temperature. The core impact on the final chemical reaction rate; The base of the natural logarithm; Boltzmann constant; During actual system operation, the validity of input parameters will be checked. For example, when the distance d or flow rate v is lower than the preset minimum threshold, such as when the equipment stops working or the distance information is lost, the activator decision unit will pause the calculation or output a safe zero-dose command to prevent invalid or dangerous calculation results and ensure the robustness of the system. By employing this time-synchronized target equation to calculate the activator dosage, this embodiment precisely postpones the highly reactive chemical process of the slurry in time and space to the final transport stage outside the equipment; this ensures that the slurry maintains low reactivity inside the equipment and does not solidify prematurely, while exhibiting optimal performance designed for operation the moment it leaves the nozzle, thus achieving precise spatiotemporal control of the slurry's chemical evolution process. The system calculates the optimal activator dosage based on real-time operating condition datasets and an optimal activator injection decision model. The core of its calculation logic is to establish a target equation that makes the slurry setting time equal to the transit time of the slurry from the activator injection point to the nozzle outlet. By solving this equation, it ensures that the slurry maintains a low reactivity inside the equipment to facilitate safe transport, while being activated to its optimal performance state at the moment it leaves the nozzle, thus achieving precise spatiotemporal control of the slurry's chemical evolution process.

[0027] In S5, the cooperative control instructions specifically include: Flow commands used to regulate the power coordination control unit; Dosage commands used to regulate the micro-dose precision injection unit; In this embodiment, the composition of the cooperative control command in step S5 is defined; In the specific implementation of step S5, the collaborative control instructions generated by the digital twin and predictive decision module are a dataset containing two parallel instructions, corresponding to the two core execution units of the control system respectively; these two instructions are synchronously sent to the collaborative control execution module, specifically including: The flow control command used to regulate the power coordination control unit: This command is the optimal flow control trajectory calculated by the lowest energy consumption trajectory planning model in step S3. It is not a constant value, but a flow curve that changes over time. After receiving the instruction, the collaborative control execution module will convert it into a control signal for the power collaborative control unit, such as the servo valve of the hydraulic pump or the frequency converter of the motor, so as to precisely adjust the pump speed to achieve the optimal flow trajectory. Dosage command for regulating the micro-dose precision injection unit: This command is the optimal activator dose calculated by the optimal activator injection decision model in step S4. It is a precise value; after receiving the instruction, the collaborative control execution module will control one or more micro-dose precision injection units, such as precision metering pumps, located at the end of the pipeline and near the nozzle, to inject the dose of activator into the base slurry in the main pipeline at a precise moment. By specifying the coordinated control commands into flow rate commands and dosage commands, this embodiment establishes a clear and decoupled control execution architecture; the power system is responsible for the physical transport of the slurry, and the micro-dose injection unit is responsible for the chemical activation of the slurry; this separated yet coordinated command mode enables the system to independently and correlatedly and precisely regulate the energy efficiency of the transport process and the final effect of the chemical reaction, thereby improving the response accuracy and execution efficiency of the entire control system. The final generated coordinated control commands are specifically decomposed into flow commands for regulating the power coordinated control unit and dose commands for regulating the micro-dose precision injection unit. This decoupled yet coordinated command mode enables the system to independently and correlatedly and precisely regulate the energy efficiency of the physical transport process and the final effect of chemical activation, thereby improving the response accuracy and execution efficiency of the entire closed-loop control system.

[0028] Example 2 A fully automatic slurry mixing control system for oilfield cementing equipment includes: The multi-dimensional state perception module is used to collect slurry state data, power system operation data and external environment data to generate real-time operating condition datasets; The digital twin and predictive decision-making module is used to generate the optimal flow control trajectory and the optimal activator dosage based on real-time operating condition datasets; The collaborative control execution module is used to execute collaborative control instructions consisting of the optimal flow control trajectory and the optimal activator dosage; This embodiment provides a fully automatic slurry mixing control system for oilfield cementing equipment. The system is built upon the aforementioned control method, and its physical and logical structure embodies the closed-loop control concept of perception-decision-execution. The system includes: The multi-dimensional state perception module is used to collect slurry state data, power system operation data and external environment data to generate real-time operating condition datasets. As the system's perception interface, this module consists of a series of industry-standard sensors and their data acquisition interfaces, and is responsible for providing the entire system with real-time and comprehensive information about the slurry, the equipment itself and the external environment. The digital twin and predictive decision module is used to generate the optimal flow control trajectory and the optimal activator dosage based on real-time operating condition datasets. As the decision-making core of the system, this module is a processing unit that integrates multiple interrelated mathematical models. It receives real-time data streams from the multi-dimensional state perception module, runs preset slurry rheological state differential models, minimum energy consumption trajectory planning models, and optimal activator injection decision models, performs state prediction and optimization decisions, and finally outputs two sets of key control parameters: dynamic optimal flow control trajectory and precise optimal activator dosage. The collaborative control execution module is used to execute collaborative control commands consisting of the optimal flow control trajectory and the optimal activator dosage. This module is the physical execution mechanism of the system, receiving commands from the digital twin and predictive decision module and precisely controlling the physical equipment. This module mainly includes a power collaborative control unit for regulating slurry transport, and one or more micro-dose precision injection units for achieving terminal activation at the end of the pipeline. These three modules work together to form a closed-loop predictive control system that can quickly adapt to complex and ever-changing environments and emergencies by continuously comparing and correcting the model's predictions with the actual results collected by the sensing module. This embodiment provides a complete and implementable hardware and software solution through the above system architecture. The system closely integrates digital twin prediction technology with physical actuators to realize intelligent and automated closed-loop control of the preparation and transportation process of highly active slurry. Its overall effect is to effectively suppress the risk of pipeline blockage and operation failure caused by thermal runaway in the operation of high-activity slurry in traditional equipment, and significantly improve the autonomy, safety, reliability and energy efficiency of the equipment in extreme environments.

[0029] The digital twin and predictive decision-making module specifically includes: The slurry viscosity prediction unit is used to generate the future slurry viscosity based on a pre-defined differential model of slurry rheological state and a real-time working condition dataset. The energy consumption trajectory planning unit is used to generate the optimal flow control trajectory based on the future slurry viscosity using a preset minimum energy consumption trajectory planning model. An activator decision unit is used to generate the optimal activator dosage based on a real-time operating condition dataset by adopting a preset optimal activator injection decision model. In this embodiment, the internal functional unit composition of the digital twin and predictive decision module is defined; In the specific implementation of the system, the digital twin and predictive decision module, which serves as the core of the decision-making process, is internally divided into three logically independent but data-related functional units to process different computational tasks in parallel: The slurry viscosity prediction unit is used to generate the future slurry viscosity based on a pre-set slurry rheological state differential model and a real-time working condition dataset. This unit serves as the data foundation for subsequent prediction and decision-making and is specifically responsible for running the aforementioned slurry rheological state differential model. It receives real-time data such as slurry temperature and shear rate, and continuously outputs the predicted value of the slurry viscosity evolution trend over a future period by numerically integrating the model equations. The energy consumption trajectory planning unit is used to generate the optimal flow control trajectory based on the future slurry viscosity using a preset minimum energy consumption trajectory planning model. This unit is responsible for generating energy optimization-related control strategies and is specifically responsible for running the aforementioned minimum energy consumption trajectory planning model. It receives future viscosity data from the slurry viscosity prediction unit and, in conjunction with a preset upper limit for slurry safety temperature, solves the objective function to plan a power system flow control command that ensures both safety and maximum energy savings. The activator decision unit is used to generate the optimal activator dosage based on a pre-set optimal activator injection decision model and a real-time operating condition dataset. This unit is responsible for accurately calculating the control parameters required for the chemical reaction and is specifically responsible for the aforementioned optimal activator injection decision model. It receives real-time data such as slurry flow rate, distance to the target point, and external ambient temperature, and calculates the precise activator dosage required to achieve final activation by solving the time synchronization equation. These three units perform parallel operations, and after summarizing the calculation results, they are output to the collaborative control execution module. By dividing the digital twin and predictive decision-making modules into these three functional units, the system architecture of this embodiment is clearer and more efficient. This modular internal design decomposes complex computing tasks into three focused sub-tasks, which not only facilitates parallel computing and improves the real-time response speed of the system, but also allows the maintenance, updating and calibration of each core algorithm model to be carried out independently, thereby enhancing the robustness, scalability and maintainability of the entire intelligent system. The control system provided by this invention constructs a complete perception-decision-execution closed-loop control hardware architecture by setting up a multi-dimensional state perception module, a digital twin and predictive decision-making module, and a collaborative control execution module. This system tightly integrates digital twin prediction technology with physical actuators, transforming the above methods into an implementable solution. Its internal digital twin and predictive decision-making module is further divided into a slurry viscosity prediction unit, an energy consumption trajectory planning unit, and an activator decision-making unit. This modular internal design facilitates parallel computing to improve real-time response speed and enhances the robustness, scalability, and maintainability of the entire intelligent system. In summary, this invention solves the technical problem of premature solidification of highly active slurry during pumping by using real-time sensing, dynamic prediction, and collaborative control. While ensuring that the slurry has the best performance when it reaches the target point, it significantly improves the autonomy, safety, and energy efficiency of cementing operations in extreme environments.

[0030] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A fully automatic slurry mixing control method for oilfield cementing equipment, characterized in that, Includes the following steps: S1. Through the multi-dimensional state perception module, collect slurry state data, power system operation data and external environment data to generate a real-time working condition dataset; S2. Based on real-time working condition datasets and using a pre-defined differential model of slurry rheological state, predict the dynamic evolution of slurry viscosity to generate future slurry viscosity. S3. Based on the future slurry viscosity and the preset upper limit of the slurry safety temperature, and using the preset minimum energy consumption trajectory planning model, calculate the optimal flow control trajectory of the power system. S4. Based on the real-time operating condition dataset and using the preset optimal activator injection decision model, calculate the optimal activator dosage. S5. Combine the optimal flow control trajectory with the optimal activator dosage to generate a collaborative control command, which is then executed by the collaborative control execution module.

2. The fully automatic slurry mixing control method for oilfield cementing equipment according to claim 1, characterized in that, In S1, the generation of the real-time operating condition dataset specifically includes: Collect slurry temperature, slurry pressure, and slurry flow velocity as slurry state data; Hydraulic oil temperature, motor speed, and system load are collected as operating data for the power system. External environmental data such as ambient temperature, ambient pressure, and distance to the target point are collected.

3. The fully automatic slurry mixing control method for oilfield cementing equipment according to claim 1, characterized in that, In S2, the differential model of the slurry rheological state defines the viscosity change rate by combining the following two terms: Temperature-driven term characterizing viscosity increase due to chemical reaction; The shear thinning term characterizes the decrease in viscosity caused by mechanical shearing.

4. The fully automatic slurry mixing control method for oilfield cementing equipment according to claim 1, characterized in that, In S3, the minimum energy consumption trajectory planning model establishes an objective function, which consists of a useful power term and a temperature penalty term. When the slurry temperature predicted based on future slurry viscosity exceeds the upper limit of the slurry's safe temperature, the temperature penalty term is positive to force the optimization algorithm to generate the optimal flow control trajectory that can reduce system heat generation. When the predicted slurry temperature based on future slurry viscosity does not exceed the upper limit of the slurry's safe temperature, the temperature penalty term is zero.

5. The fully automatic slurry mixing control method for oilfield cementing equipment according to claim 1, characterized in that, In S4, the optimal activator dosage is calculated by establishing a target equation that makes the slurry setting time equal to the transit time of the slurry from the activator injection point to the nozzle outlet, and then solving the target equation.

6. The fully automatic slurry mixing control method for oilfield cementing equipment according to claim 1, characterized in that, In S5, the cooperative control instructions specifically include: Flow commands used to regulate the power coordination control unit; Dosage commands used to regulate the micro-dose precision injection unit.

7. A fully automatic slurry mixing control system for oilfield cementing equipment, based on the fully automatic slurry mixing control method for oilfield cementing equipment according to any one of claims 1-6, characterized in that, include: The multi-dimensional state perception module is used to collect slurry state data, power system operation data and external environment data to generate real-time operating condition datasets; The digital twin and predictive decision-making module is used to generate the optimal flow control trajectory and the optimal activator dosage based on real-time operating condition datasets; The collaborative control execution module is used to execute collaborative control instructions consisting of the optimal flow control trajectory and the optimal activator dosage.

8. The fully automatic slurry mixing control system for oilfield cementing equipment according to claim 7, characterized in that, The digital twin and predictive decision-making module specifically includes: The slurry viscosity prediction unit is used to generate the future slurry viscosity based on a pre-defined differential model of slurry rheological state and a real-time working condition dataset. The energy consumption trajectory planning unit is used to generate the optimal flow control trajectory based on the future slurry viscosity using a preset minimum energy consumption trajectory planning model. The activator decision unit is used to generate the optimal activator dosage based on a pre-defined optimal activator injection decision model and a real-time operating condition dataset.

Images