Fracturing equipment

Abstract

The invention relates to the technical field of fracturing truck control systems, and discloses fracturing equipment which comprises a truck body, a high-pressure pump set, a mixing system, a fracturing control system and a propping agent conveying system are installed on the truck body, and the high-pressure pump set comprises a pump body, power equipment and a fluid end; the mixing system comprises a stirring tank, a conveying pump and a mixing control device; the fracturing control system comprises a controller, a display screen and a plurality of sensors. The fracturing control system is used for monitoring the pressure, flow and temperature of fracturing fluid in the fracturing process in real time. The proppant conveying system comprises a storage container, metering equipment and a conveying pipeline, the storage container is used for storing different types of proppants, and the metering equipment is used for accurately measuring and controlling the amount of the proppants added each time. And two ends of the conveying pipeline are respectively connected with the storage container and the mixing system. The fracturing truck disclosed by the invention has the advantages that the uniformity and the accuracy of component mixing in a fracturing fluid preparation process are improved, and the effect of fracturing operation is favorably improved.

Description

Technical Field

[0001] The present invention relates to the field of fracturing truck control systems, and more specifically, to a fracturing equipment. Background Art

[0002] A fracturing truck, also known as a hydraulic fracturing truck or simply a fracturing unit, is a special vehicle used in oil and gas field development. It plays an important role in the exploitation of unconventional oil and gas resources such as shale gas and tight oil. The fracturing technology injects high-pressure liquid into the ground to create or expand fractures in the rock, thereby increasing the fluidity and production of oil and gas.

[0003] Traditional fracturing trucks mix a preset amount of water, proppant, and chemical additives using a rated mixing procedure to make fracturing fluid. However, during the mixing process, existing fracturing trucks cannot efficiently monitor and control multiple variables such as temperature, viscosity, and concentration in the mixing process. This can lead to uneven mixing of the fracturing fluid in the existing fracturing truck's fracturing fluid mixing method, thus affecting subsequent fracturing operations. Summary of the Invention

[0004] The present invention provides a fracturing equipment to solve the technical problems raised in the above background art.

[0005] The present invention provides a fracturing equipment, including a vehicle body, on which a high-pressure pump group, a mixing system, a fracturing control system, and a proppant conveying system are installed. The high-pressure pump group includes a pump body, a power device, and a fluid end. The pump body is used to pump the fracturing fluid into the underground rock formation. The mixing system includes a mixing tank, a conveying pump, and a mixing control device. The mixing system is used to configure the fracturing fluid. The fracturing control system includes a controller, a display screen, and several sensors. The fracturing control system is used to monitor the pressure, flow rate, and temperature of the fracturing fluid in real time during the fracturing process. The proppant conveying system is used to provide proppant to the mixing system. The proppant conveying system includes a storage container, a metering device, and a conveying pipeline. The storage container is used to store different types of proppants. The metering device is used to accurately measure and control the amount of proppant added each time. The two ends of the conveying pipeline are respectively connected to the storage container and the mixing system.

[0006] In a preferred embodiment, the control method executed by the mixing system includes the following steps:

[0007] Step 101, before starting, ensure that the mixing tank, the conveying pump, and the mixing control device are all in good working condition; calibrate the sensors for measuring liquid flow rate, concentration, and temperature to ensure accurate data;

[0008] Step 102, according to the design requirements, preset the ideal ratios of water, proppant, and chemical additives in advance, and input the set ideal ratios, the preset mixing speed of the mixing tank, and the conveying rate of the proppant conveying system 5 into the mixing control device;

[0009] Step 103, in accordance with the set ideal ratios, first add a preset amount of water to the mixing tank, and then gradually add the proppant and chemical additives. Use an on-line monitoring instrument to monitor the state of the mixture in real time. The state of the mixture includes the liquid temperature of the mixture, the viscosity of the mixture, and the molar concentration of each component in the mixture, and output the real-time state information of the mixture;

[0010] Step 104, input the real-time state information of the mixture into the mixing control device, and the mixing control device outputs dynamic adjustment actions. The dynamic adjustment actions include increasing or decreasing the stirring speed of the mixing tank or the addition amount of the proppant until the mixture reaches the preset uniformity to obtain the fracturing fluid;

[0011] Step 105, the high-pressure pump group injects the fracturing fluid into the underground fracture.

[0012] In a preferred embodiment, in Step 104, the method for the mixing control device to output dynamic adjustment actions includes the following steps:

[0013] Step 201, define the environment, where the environment includes the mixing tank, the conveying pump, and several sensors;

[0014] Step 202, define the state space, where the state space includes the liquid temperature of the mixture, the viscosity of the mixture, the molar concentration of each component in the mixture, the mixing time of the mixture, and the current stirring speed of the mixing tank;

[0015] Step 203, set the action space, where the action space includes adjusting the stirring speed of the mixing tank or changing the addition amount of the components;

[0016] Step 204, design the reward function, where the reward function gives rewards based on the analysis result of the uniformity of the mixture;

[0017] Step 205, initialize the mixing optimization strategy model. The mixing optimization strategy model includes an action network and a Critic network. The action network is initialized as a random strategy for selecting the best action according to the current state; the Critic network is initialized as a zero value estimate for evaluating the value of taking a specific action in a given state;

[0018] Step 206, collect the historical mixing system data of the fracturing vehicle. The mixing system data includes the state information of the mixture, the action information of the mixing system, and the result information of the mixture uniformity. Use the historical mixing system data of the fracturing vehicle as the initial experience library to help the intelligent agent learn effective strategies faster;

[0019] Step 207, train the hybrid optimization strategy model;

[0020] Step 208, deploy the trained hybrid optimization strategy model into the control system of the fracturing truck to take over the hybrid control task.

[0021] In a preferred embodiment, in Step 207, the method for training the hybrid optimization strategy model includes the following steps:

[0022] Step 1. Observe the state: Obtain the latest state information from the environment;

[0023] Step 2. Select an action: Output an action by the action network according to the current state;

[0024] Step 3. Execute the action: Apply the selected action to the hybrid system of the fracturing truck;

[0025] Step 4. Receive the new state and reward: Collect the new state and the corresponding new reward after executing this action;

[0026] Step 5. Update the Critic network: Update the parameters of the Critic network according to the received reward and new state to improve the prediction of future rewards;

[0027] Step 6. Update the action network: Based on the value evaluation provided by the Critic, adjust the parameters of the action network so that it can make better choices when encountering similar states in the future.

[0028] In a preferred embodiment, the calculation formula of the reward function is:

[0029] R = ω U ·U - ω C ·|C| - ω T ·T

[0030] where R represents the reward value, ω U 、ω C 、ω T respectively represent the weight of the mixing uniformity index, the weight of the concentration deviation, the weight of the agglomeration phenomenon, U represents the mixing uniformity index, C represents the comprehensive component concentration deviation, T represents whether there is an agglomeration phenomenon, T = 0 or 1, where 0 means there is no agglomeration phenomenon and 1 means there is an agglomeration.

[0031] In a preferred embodiment, the calculation formula of the mixing uniformity index is as follows:

[0032]

[0033] Among them, U represents the mixing uniformity index of the mixture, U ∈ [0, 1], where 1 represents complete uniformity and the same as the ideal uniformity degree, N represents the number of measurements taken at different positions in the mixture, and x i represents the mixture state value at the i-th position, and x p represents the average value of the mixture state of all selected positions.

[0034] In a preferred embodiment, the calculation formula for the average value of the mixture state is:

[0035]

[0036] Among them, x p represents the average value of the mixture state of all selected positions, N represents the number of measurements taken at different positions in the mixture, and x i represents the mixture state value at the i-th position.

[0037] In a preferred embodiment, the calculation formula for the comprehensive component concentration deviation is:

[0038]

[0039] Among them, C represents the comprehensive component concentration deviation, M represents the total number of component types, and C j represents the concentration deviation percentage of the j-th component.

[0040] In a preferred embodiment, the calculation formula for the component concentration deviation is:

[0041]

[0042] Among them, C j represents the concentration deviation percentage of the j-th component, c j represents the actual concentration of the j-th component in the current state, represents the ideal concentration of the j-th component.

[0043] In a preferred embodiment, in step 206, the state information of the mixture includes: the liquid temperature of the mixture, the viscosity of the mixture, the concentrations of the components in the mixture, the mixing time that has been mixed in the mixing process, the stirring speed of the stirring tank, and the amount of substances added of each component in the mixture; the action information of the mixing system includes: the adjustment of the stirring speed of the stirring tank and the change in the amount of components added to the mixture; the result information of the mixture uniformity includes: the mixing uniformity index, the component concentration deviation, the detection of agglomeration phenomena, and the evaluation of the final mixing effect.

[0044] The beneficial effects of the present invention are as follows:

[0045] 1. The fracturing equipment of the present invention improves the uniformity and accuracy of ingredient mixing during the fracturing fluid preparation process, which helps to enhance the effect of the fracturing operation.

[0046] 2. The fracturing equipment of the present invention realizes the intelligent management and automatic adjustment of the mixing process, reduces the need for manual intervention, and improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a schematic structural view of the fracturing equipment of the present invention from the first perspective.

[0048] Figure 2 is a schematic structural view of the fracturing equipment of the present invention from the second perspective.

[0049] Figure 3 is a flowchart of the control method executed by the mixing system of the fracturing equipment of the present invention.

[0050] Figure 4 is a flowchart of the method for the mixing control device of the fracturing equipment of the present invention to output dynamic adjustment actions.

[0051] In the figures: 1, vehicle body; 2, high-pressure pump group; 3, mixing system; 4, fracturing control system; 5, proppant conveying system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] Now, the subject matter described herein will be discussed with reference to exemplary embodiments. It should be understood that discussing these embodiments is only to enable those skilled in the art to better understand and thus implement the subject matter described herein. Without departing from the scope of protection of the content of this specification, changes can be made to the functions and arrangements of the elements discussed. Each example can omit, substitute, or add various processes or components as needed. Additionally, the features described relative to some examples can also be combined in other examples.

[0053] Such as Figure 1 and Figure 2As shown in the figure, a fracturing equipment includes a vehicle body 1, on which a high-pressure pump unit 2, a mixing system 3, a fracturing control system 4, and a proppant conveying system 5 are installed. The high-pressure pump unit 2 includes a pump body, a power device, and a fluid end. The pump body is used to pump fracturing fluid into the underground rock formation. The mixing system 3 includes a mixing tank, a conveying pump, and a mixing control device. The mixing system 3 is used to configure fracturing fluid. The fracturing control system 4 includes a controller, a display screen, and several sensors. The fracturing control system 4 is used to monitor the pressure, flow rate, and temperature of the fracturing fluid during the fracturing process in real time. The proppant conveying system 5 is used to provide proppant to the mixing system 3. The proppant conveying system 5 includes a storage container, a metering device, and a conveying pipeline. The storage container is used to store different types of proppants. The metering device is used to accurately measure and control the amount of proppant added each time. The two ends of the conveying pipeline are respectively connected to the storage container and the mixing system.

[0054] It should be noted that the pressure, flow rate, and temperature of the fracturing fluid during the fracturing process can be monitored in real time and the operation parameters can be automatically adjusted according to the preset program; the proppant is sand and gravel.

[0055] It should be further noted that the fracturing vehicle of the present invention further includes a fluid end system, a fracturing pump system, a drive shaft system, a chassis vehicle system, an engine system, a transmission system, and a hydraulic component system;

[0056] Specifically, the fluid end system: the fluid end CS—GYT05 system of the HJS2500 type fracturing vehicle, which is one of the core components of the fracturing vehicle and is responsible for generating high pressure to pump liquid;

[0057] The fracturing pump system: the fracturing pump GD C2800Q system of the 2500 type fracturing vehicle, which closely cooperates with the fluid end and is used for actual liquid pumping operations;

[0058] The drive shaft system: the drive shaft HJS-390.70-1550 system of the 2500 type fracturing vehicle, which is responsible for transmitting the power of the engine to the fracturing pump;

[0059] The chassis vehicle system: the chassis vehicle TAZ5466TYT system of the 2500 type fracturing vehicle, which provides the basic support and mobility of the vehicle;

[0060] The engine system: the engine CHD620V16CR system of the 2500 type fracturing vehicle, which is the heart of the whole system and provides the necessary power;

[0061] The hydraulic component system: the hydraulic components and fixed-displacement motor HMA210 / variable pump and HPV02-A2-135L-E1P1 system of the 2500 type fracturing vehicle, which is used to control various actions and auxiliary functions, such as steering and lifting;

[0062] Transmission system: The SE23800B transmission system of the 2500-type fracturing truck is used to ensure that the engine can efficiently transmit power to each working unit.

[0063] In one embodiment of the present invention, as Figure 3 shown, the control method executed by the mixing system includes the following steps:

[0064] Step 101, before starting, ensure that the mixing tank, delivery pump, and mixing control device are all in good working condition; calibrate the sensors for measuring liquid flow rate, concentration, and temperature to ensure accurate data;

[0065] Step 102, according to the design requirements, preset the ideal proportions of water, proppant, and chemical additives in advance, and input the preset ideal proportions, the preset mixing speed of the mixing tank, and the delivery rate of the proppant delivery system 5 into the mixing control device;

[0066] Step 103, according to the preset ideal proportions, first add a preset amount of water to the mixing tank, and then gradually add the proppant and chemical additives. Use an on-line monitoring instrument to monitor the state of the mixture in real time. The state of the mixture includes the liquid temperature of the mixture, the viscosity of the mixture, and the molar concentration of each component in the mixture, and output the real-time state information of the mixture;

[0067] It should be noted that the mixture is a mixed liquid of water, proppant, and chemical additives, and the real-time state information of the mixture is in the one-hot encoding format, and various information represented by the state of the above mixture is concatenated in sequence;

[0068] Step 104, input the real-time state information of the mixture into the mixing control device, and the mixing control device outputs dynamic adjustment actions. The dynamic adjustment actions include adjusting the mixing speed of the mixing tank or adjusting the addition amount of the proppant until the mixture reaches the preset uniformity to obtain the fracturing fluid;

[0069] It should be noted that adjusting the addition amount of the proppant includes the increase amount of the proppant, the increase amount of the chemical additive, and the increase amount of water. It can be understood that the proppant, chemical additive, and water can be output as a whole set of the model, or the proppant, chemical additive, and water can be output as three results. If output as three results, it means that each result corresponds to the increase amount of the proppant, chemical additive, and water respectively. If output as a set, the set contains three parameters, and these three parameters correspond to the increase amount of the proppant, chemical additive, and water respectively;

[0070] Step 105, the high-pressure pump group injects the fracturing fluid into the underground fracture.

[0071] In one embodiment of the present invention, asFigure 4 As shown, in step 104, a method for a control system to dynamically adjust a hybrid system to ensure uniform distribution of proppants and other additives in a liquid includes the following steps:

[0072] Step 201, define the environment, which includes physical devices such as a mixing tank, a transfer pump, sensors, etc.;

[0073] Step 202, define the state space, which includes the liquid temperature of the mixture, the viscosity of the mixture, the molar concentration of each component in the mixture (water, proppant, and chemical additive), the mixing time of the mixture, and the current stirring speed of the mixing tank;

[0074] Step 203, set the action space, which includes adjusting the stirring speed of the mixing tank or changing the amount of components added;

[0075] Step 204, design a reward function, which gives rewards based on the analysis results of the uniformity of the mixture;

[0076] In an embodiment of the present invention, a reward mechanism that gives positive rewards for a more uniform mixture and negative rewards for agglomeration or other non-uniform phenomena is used to design the reward function;

[0077] The design goal of the reward function is to maximize the mixing uniformity and minimize non-uniform phenomena;

[0078] Maximize the mixing uniformity: Encourage the mixing control device to take actions that contribute to improving the mixing uniformity by giving positive rewards;

[0079] Minimize non-uniform phenomena: For any phenomenon that causes agglomeration or other forms of non-uniformity in the mixture, apply negative rewards to punish these bad behaviors.

[0080] The calculation formula of the reward function is:

[0081] R = ω U ·U - ω C ·|C| - ω T ·T

[0082] Wherein, R represents the reward value, ω U 、ω C 、ω T respectively represent the weight of the mixing uniformity index, the weight of the concentration deviation, and the weight of the agglomeration phenomenon, U represents the mixing uniformity index, C represents the comprehensive component concentration deviation, T represents whether there is an agglomeration phenomenon, T = 0 or 1, where 0 means no agglomeration phenomenon and 1 means there is an agglomeration;

[0083] In an embodiment of the present invention, the calculation formula of the mixing uniformity index is as follows:

[0084]

[0085] Among them, U represents the mixing uniformity index of the mixture, U ∈ [0, 1], where 1 represents complete uniformity, which is the same as the ideal uniformity, N represents the number of measurements taken at different positions in the mixture, and x i represents the mixture state value at the i-th position, and x p represents the average value of the mixture state at all selected positions;

[0086] The calculation formula for the average value of the mixture state is:

[0087]

[0088] Among them, x p represents the average value of the mixture state at all selected positions, N represents the number of measurements taken at different positions in the mixture, and x i represents the mixture state value at the i-th position;

[0089] In an embodiment of the present invention, the calculation formula for the component concentration deviation is:

[0090]

[0091] Among them, C j represents the concentration deviation percentage of the j-th component, and c j represents the actual concentration of the j-th component in the current state, represents the ideal concentration of the j-th component.

[0092] In an embodiment of the present invention, the calculation formula for the comprehensive component concentration deviation is:

[0093]

[0094] Among them, C represents the comprehensive component concentration deviation, M represents the total number of component types, and C j represents the concentration deviation percentage of the j-th component.

[0095] It should be noted that the uniformity of the mixture is evaluated in real time by an on-line monitoring instrument or analyzed in a laboratory by regular sampling;

[0096] It should be noted that in the present invention, the uniform distribution and the uniformity of the mixture are quantified by detecting the particle size distribution parameters, concentration gradient parameters, mixing index, viscosity, and temperature, pH value, and conductivity parameters during the mixing process in the mixture;

[0097] For example, the particle size distribution refers to the proportion of particles of different sizes in a mixture, and the corresponding parameter values can be obtained using techniques such as laser scattering, sieving, or microscopic image analysis; the concentration gradient represents the change in the quantity of a specific component per unit volume of the mixture, which can be determined by sampling and analyzing the concentrations at different positions (laboratory analysis or installing relevant sensors at different positions to detect the concentration of the mixture at the corresponding positions) and calculating their differences (ideally, the concentrations of all components in the entire mixture should be uniform, without obvious local high or low concentration phenomena); the mixing index is a comprehensive indicator for measuring the mixing effect of the mixture. Color marking, fluorescent tracers, or other visualization techniques can be used, and then quantitative analysis can be performed using image processing software. A higher mixing index indicates better uniformity; viscosity refers to the ability of the mixture liquid to resist flow and is related to internal friction. Equipment such as a rotational viscometer or a capillary viscometer can be used to measure it. Appropriate viscosity helps maintain the suspension state of the components in the mixture, prevent sedimentation, and also helps control the injection speed and pressure; the temperature, pH value, and conductivity parameters of the mixture during the mixing process can be directly embedded into the mixing system by installing dedicated sensors to continuously collect data and feedback it to the control system.

[0098] It should be further noted that in practical applications, multiple above-mentioned parameters need to be combined for comprehensive evaluation. For example, at the fracturing operation site, engineers will first focus on the particle size distribution and concentration gradient of the mixture to ensure the initial mixing quality; then, they will rely on the real-time information provided by on-line monitoring sensors to dynamically adjust the stirring speed and component ratio; finally, the long-term stability and final effect are verified through regular sampling analysis and laboratory tests.

[0099] In the present invention, the mixing uniformity of the mixture sample randomly sampled at a certain moment (which can be the data collected by on-line monitoring instruments or the data of the mixture sample sampled regularly) is used to represent the uniformity of the mixture in the mixing tank at this moment.

[0100] Step 205: Initialize the mixing optimization strategy model. The mixing optimization strategy model includes an action network and a Critic network. The action network is initialized with a random strategy and is used to select the best action according to the current state; the Critic network is initialized with a zero value estimate and is used to evaluate the value of taking a specific action in a given state.

[0101] Step 206: Collect the historical mixing system data of the fracturing truck. The mixing system data includes the state information of the mixture, the action information of the mixing system, and the result information of the mixture uniformity. The historical mixing system data of the fracturing truck is used as the initial experience library to help the intelligent agent learn effective strategies faster.

[0102] It should be noted that the state information of the mixture includes:

[0103] Liquid temperature of the mixture: Temperature records of the mixed solution recorded every 1 minute;

[0104] Viscosity of the mixture: Measured viscosity values of the mixed solution recorded every 1 minute;

[0105] Concentrations of each component in the mixture: Actual concentrations of each component of water, proppant, and chemical additive;

[0106] Mixing time of the mixing process: Duration of each mixing operation;

[0107] Mixing speed of the stirring tank: Operating rotation speed of the stirring tank at each time period;

[0108] Amount of substance added for each component in the mixture: Amount of each component added to the mixture;

[0109] Action information of the mixing system includes:

[0110] Adjustment of the mixing speed of the stirring tank: Specific values of the mixing speed adjustment each time and their corresponding timestamps;

[0111] Change in the amount of component added to the mixture: Specific values of the change in the amount of component added each time and their corresponding timestamps;

[0112] Result information of the mixture uniformity includes:

[0113] Mixing uniformity index: Evaluation result of the mixing uniformity calculated based on imaging technology or on-line monitoring equipment;

[0114] Component concentration deviation: Difference between the actual concentration and the target concentration for each component;

[0115] Detection of agglomeration phenomenon: Binary flag indicating whether agglomeration or other non-uniform phenomena are detected;

[0116] Evaluation of the final mixing effect: Overall evaluation of the mixing quality obtained through laboratory analysis.

[0117] By collecting various types of data of the above mixing system, a rich initial experience library can be provided for the mixing control device, which not only helps to accelerate the learning process, but also ensures that the learned strategies are closer to the actual operating environment, thereby improving its effectiveness and reliability in real application scenarios; in addition, with the continuous accumulation of more new data, this experience library can be continuously updated and improved, further enhancing the learning ability and adaptability of the intelligent agent.

[0118] Step 207, training the mixing optimization strategy model;

[0119] It should be noted that the method for training the hybrid optimization strategy model includes the following steps:

[0120] Step 1, Observe the state: Obtain the latest state information from the environment;

[0121] Step 2, Select an action: The action network outputs an action based on the current state;

[0122] Step 3, Execute the action: Apply the selected action to the hybrid system of the fracturing truck;

[0123] Step 4, Receive the new state and reward: Collect the immediate feedback after executing this action, that is, the new state and the corresponding reward;

[0124] Step 5, Update the Critic network: Update the parameters of the Critic network according to the received reward and the new state to improve the prediction of future rewards;

[0125] Step 6, Update the action network: Based on the value evaluation provided by the Critic, adjust the parameters of the action network so that it can make better choices when encountering similar states in the future.

[0126] Step 208, Arrange the trained hybrid optimization strategy model into the control system of the fracturing truck to take over the hybrid control task.

[0127] It should be noted that after deployment, the hybrid system and the control system need to continue to collect operation data for further optimizing the algorithm performance.

[0128] It should be noted that the historical data is represented by the mixed sample data obtained by sampling, that is, the mixing uniformity of the mixed sample randomly sampled at a certain moment represents the uniformity of the mixture in the mixing tank at this moment;

[0129] The above has described the embodiments of this embodiment, but this embodiment is not limited to the above specific implementation manners. The above specific implementation manners are only illustrative and not restrictive. Under the inspiration of this embodiment, those of ordinary skill in the art can also make many forms, all of which fall within the protection scope of this embodiment.

Claims

1. A fracturing equipment, characterized in that: The vehicle comprises a vehicle body (1), on which a high-pressure pump group (2), a mixing system (3), a fracturing control system (4) and a proppant delivery system (5) are installed. The high-pressure pump group (2) comprises a pump body, a power device and a fluid end, and the pump body is used to inject fracturing fluid into underground rock formations; the mixing system (3) comprises a mixing tank, a delivery pump and a mixing control device, and the mixing system (3) is used to prepare fracturing fluid; the fracturing control system (4) comprises a controller, a display screen and a plurality of sensors, and the fracturing control system (4) is used to monitor the pressure, flow rate and temperature of the fracturing fluid in real time during the fracturing process; the proppant delivery system (5) is used to provide proppant to the mixing system (3), and the proppant delivery system (5) comprises a storage container, a metering device and a delivery pipeline, the storage container is used to store different types of proppant, the metering device is used to accurately measure and control the amount of proppant added each time, and the two ends of the delivery pipeline are respectively connected to the storage container and the mixing system.

2. A fracturing equipment according to claim 1, characterized in that: The control method implemented by the hybrid system comprises the following steps: Step 101, before starting, ensure that the mixing tank, delivery pump and mixing control device are in good working condition; calibrate the sensors used to measure liquid flow, concentration and temperature to ensure data accuracy; Step 102, according to the design requirements, the ideal ratio of water, proppant and chemical additive is pre-set, and the above-set ideal ratio, the preset mixing speed of the mixing tank and the delivery rate of the proppant delivery system 5 are input into the mixing control device; Step 103, according to the set ideal ratio, first add a preset amount of water to the stirring tank, then gradually add proppant and chemical additives, use an online monitoring instrument to monitor the state of the mixture in real time, the state of the mixture includes the liquid temperature of the mixture, the viscosity of the mixture, the substance concentration of each component in the mixture, and output the real-time state information of the mixture; Step 104, inputting the real-time state information of the mixture into the mixing control device, the mixing control device outputs a dynamic adjustment action, the dynamic adjustment action includes increasing or decreasing the stirring speed of the mixing tank or the amount of proppant added, until the mixture reaches a preset uniformity, thereby obtaining a fracturing fluid; Step 105: The high-pressure pump group injects fracturing fluid into underground fractures.

3. A fracturing equipment according to claim 2, characterized in that: In step 104, the method for the hybrid control device to output a dynamic adjustment action includes the following steps: Step 201, defining an environment, the environment including a mixing tank, a delivery pump and a plurality of sensors; Step 202, defining a state space, the state space including the liquid temperature of the mixture, the viscosity of the mixture, the molar concentration of each component in the mixture, the mixing time of the mixture, and the current stirring speed of the stirring tank; Step 203, setting the action space, the action space includes adjusting the stirring speed of the stirring tank or changing the amount of ingredients added; Step 204, designing a reward function, wherein the reward function provides a reward based on the uniformity analysis result of the mixture; Step 205, initializing a hybrid optimization strategy model, which includes an action network and a critic network. The action network is initialized as a random strategy for selecting the best action according to the current state; the critic network is initialized as a zero value estimate for evaluating the value of taking a specific action under a given state; Step 206, collecting historical mixed system data of the fracturing truck, the mixed system data including state information of the mixture, action information of the mixed system and result information of the mixture uniformity, using the historical mixed system data of the fracturing truck as an initial experience library to help the intelligent agent learn effective strategies faster; Step 207, training a hybrid optimization strategy model; Step 208: deploy the trained hybrid optimization strategy model to the control system of the fracturing truck to take over the hybrid control task.

4. A fracturing equipment according to claim 3, characterized in that: In step 207, the method for training the hybrid optimization strategy model includes the following steps: Step 1: Observe the status: obtain the latest status information from the environment; Step 2: Select an action: The action network outputs an action based on the current state; Step 3: Execute the action: Apply the selected action to the mixing system of the fracturing truck; Step 4: Receive new status and reward: collect the new status and corresponding new reward after executing the action; Step 5: Update the Critic network: Update the parameters of the Critic network based on the received rewards and new states to improve the prediction of future rewards; Step 6: Update the action network: Based on the value assessment provided by the Critic, adjust the parameters of the action network so that it can make better choices when encountering similar states in the future.

5. A fracturing equipment according to claim 4, characterized in that: The reward function is calculated as: R = ω U ·U - ω C ·|C| - ω T ·T Among them, R represents the reward value, ω U ,ω C ,ω T They respectively represent the weight of the mixing uniformity index, the weight of the concentration deviation, and the weight of the agglomeration phenomenon. U represents the mixing uniformity index, C represents the comprehensive component concentration deviation, and T represents whether there is an agglomeration phenomenon. T = 0 or 1, where 0 represents no agglomeration phenomenon and 1 represents the presence of agglomeration.

6. A fracturing equipment according to claim 5, characterized in that: The calculation formula of mixing uniformity index is as follows: Where U represents the mixing uniformity index of the mixture, U∈[0,1], where 1 means that the mixture is completely uniform and has the same ideal uniformity, N represents the number of measurements taken at different locations in the mixture, and x i represents the mixture state value at the i-th position, x p Represents the average value of the mixture state at all selected positions.

7. A fracturing equipment according to claim 6, characterized in that: The formula for calculating the average value of the mixture state is: Among them, x p represents the average value of the mixture state at all positions, N represents the number of different positions selected in the mixture for measurement, x i Represents the mixture state value at the i-th position.

8. A fracturing equipment according to claim 7, characterized in that: The calculation formula for the comprehensive component concentration deviation is: Among them, C represents the comprehensive component concentration deviation, M represents the total number of component types, and C j It represents the concentration deviation percentage of the jth component.

9. A fracturing equipment according to claim 8, characterized in that: The formula for calculating the component concentration deviation is: Among them, C j represents the concentration deviation percentage of the jth component, c j represents the actual concentration of the jth component in the current state, represents the ideal concentration of the jth component.

10. A fracturing equipment according to claim 9, characterized in that: In step 206, the state information of the mixture includes: the liquid temperature of the mixture, the viscosity of the mixture, the concentration of each component in the mixture, the mixing time of the mixing process, the stirring speed of the stirring tank and the amount of each component added to the mixture; the action information of the mixing system includes: the stirring speed adjustment of the stirring tank and the change of the amount of components added to the mixture; the result information of the uniformity of the mixture includes: the mixing uniformity index, the deviation of the component concentration, the detection of agglomeration phenomenon and the evaluation of the final mixing effect.

Images