Emulsification pump station flow loading and unloading control method, system, equipment and storage medium

Abstract

The present application discloses a flow loading and unloading control method, system, equipment and storage medium of an emulsified pump station. The method comprises: using sensors to obtain the action type, action duration, pressure and flow of the hydraulic support in real time; constructing an emulsified pump flow prediction model; inputting the action type of the hydraulic support, the action duration of the hydraulic support, the pressure of the emulsified pump and the flow of the emulsified pump corresponding to the current moment into the emulsified pump flow prediction model to obtain the predicted flow of the emulsified pump at the next moment; calculating and obtaining the first flow adjustment amount and generating the first emulsified pump station flow loading and unloading control instruction to pre-adjust the output flow of the emulsified pump; using a PID control algorithm, calculating the second flow adjustment amount and generating the second emulsified pump station flow loading and unloading control instruction to continue adjusting the output flow of the emulsified pump. The present application can improve the accuracy, stability and response speed of the flow control of the emulsified pump station.

Description

Technical Field

[0001] The present application relates to the technical field of emulsification pump station flow control, and in particular to an emulsification pump station flow loading and unloading control method, system, equipment and storage medium. Background Art

[0002] The emulsion pump station consists of an emulsion pump, an emulsion tank, inlet and outlet pipes, high and low pressure filters, a high pressure supply pipe, a suction circuit breaker, a return circuit breaker, a control switch, etc. It is mainly used for the supply of liquid to the hydraulic support in coal mines to meet the demand of the hydraulic support for high pressure emulsion during operation, and is the power source of the hydraulic support. As an important hydraulic equipment, the flow control of the emulsion pump station has always been one of the key technologies.

[0003] Existing emulsified pump station flow control systems mostly use traditional control methods, such as mechanical spring unloading valves and simple automatic control strategies. For example, some existing emulsified pump station flow automatic control systems detect flow through sensors and automatically adjust the output flow of the pump station according to the preset control logic. However, these systems are difficult to achieve more precise control when facing complex and changeable working conditions, and overshoot or oscillation is prone to occur during the adjustment process, affecting the stable operation of the pump station.

[0004] Therefore, the flow control system of the emulsification pump station still needs to be improved in terms of accuracy, stability and response speed to adapt to the complex and changeable working conditions, so that the flow adjustment can be made more quickly and accurately, the operating efficiency of the emulsification pump station can be improved, and safety hazards can be reduced. Summary of the invention

[0005] In order to improve the accuracy, stability and response speed of the flow control of an emulsification pump station and to adapt to complex and changeable working conditions, the present application provides an emulsification pump station flow loading and unloading control method, system, equipment and storage medium.

[0006] In a first aspect, the present application provides a method for controlling flow loading and unloading of an emulsification pump station, comprising:

[0007] Use sensors to obtain the action type, action duration, pressure and flow of the emulsion pump of the hydraulic support in real time;

[0008] Constructing an emulsion pump flow prediction model; the emulsion pump flow prediction model adopts a deep learning neural network, the input of which is the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow of the emulsion pump, and the output is the flow of the emulsion pump at the next moment;

[0009] Inputting the action type of the hydraulic support, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow rate of the emulsion pump corresponding to the current moment into the emulsion pump flow prediction model to obtain the predicted flow rate of the emulsion pump at the next moment;

[0010] A first flow adjustment amount is calculated based on the flow rate of the emulsion pump at the current moment and the predicted flow rate of the emulsion pump at the next moment, and a first emulsion pump station flow loading and unloading control instruction is generated according to the first flow adjustment amount to pre-adjust the output flow rate of the emulsion pump;

[0011] The PID control algorithm is used to calculate the second flow adjustment amount based on the predicted flow of the emulsion pump at the next moment and the flow of the emulsion pump collected at the next moment; the flow loading and unloading control instruction of the second emulsion pump station is generated according to the second flow adjustment amount to continue to adjust the output flow of the emulsion pump.

[0012] By adopting the above scheme, compared with the single emulsion pump flow time series prediction, the influence of the action of the hydraulic support and the pressure of the emulsion pump on the flow of the emulsion pump is considered, and the action of the hydraulic support, the pressure of the emulsion pump and the historical emulsion pump flow are integrated to achieve a more accurate prediction of the emulsion pump flow at the next moment using deep learning neural network technology; according to the predicted emulsion pump flow at the next moment, a feedforward flow control system is designed, and when it is predicted that the action of the hydraulic support will cause a flow change, the control parameters of the emulsion pump are adjusted in advance, thereby speeding up the response speed of the system; at the same time, a feedback control system is designed, and the control strategy is continuously adjusted using real-time feedback data to eliminate possible deviations or oscillations, so as to ensure that the pump station can operate continuously and stably.

[0013] Preferably, it also includes:

[0014] Obtain the priority of the current emulsion pump in the coordinated operation of multiple emulsion pumps in real time;

[0015] The input for constructing the emulsion pump flow prediction model also includes: the priority of the current emulsion pump corresponding to the current moment in the coordinated operation of multiple emulsion pumps;

[0016] At the same time, the priority of the current emulsion pump corresponding to the current moment in the coordinated operation of multiple emulsion pumps is input into the emulsion pump flow prediction model.

[0017] By adopting the above scheme, taking into account that the priority will be set for regular circulation in the coordinated operation of multiple emulsion pumps to extend the operating life of each emulsion pump, that is, during the circulation process, the priority of each emulsion pump changes periodically, and different priorities correspond to different flow loading and unloading adjustment amounts. Further considering the impact of priority on the flow between each pump, a flow prediction model for the emulsion pump is constructed to obtain a more accurate flow prediction value for the emulsion pump.

[0018] Preferably, it is determined whether the first flow adjustment amount is greater than the preset flow adjustment amount. If it is, the first flow adjustment amount is divided into multiple first flow sub-adjustments, and multiple third emulsification pump station flow loading and unloading control instructions are generated accordingly to replace the generation of the first emulsification pump station flow loading and unloading control instructions, and within a first preset time from the current moment, the multiple third emulsification pump station flow loading and unloading control instructions are sequentially executed to complete the pre-adjustment of the output flow of the emulsion pump; otherwise, within a second preset time from the current moment, the first emulsification pump station flow loading and unloading control instructions are generated according to the first flow adjustment amount to complete the pre-adjustment of the output flow of the emulsion pump, and the first preset time and the second preset time are both less than the sampling time interval, and the first preset time is greater than the second preset time.

[0019] By adopting the above solution, taking into account that during the movement of the hydraulic support, the pressure and flow required for each action are different, such as raising the column requires a large flow, and lowering the column requires a small flow, which may lead to a large change in flow when the action changes. In order to reduce the loss of rapid loading and unloading flow to the operation of the emulsion pump, the flow adjustment amount can be divided in a targeted manner to complete the pre-adjustment of the flow in a longer time.

[0020] Preferably, a first flow rate adjustment rate is calculated based on the flow rate of the emulsion pump at the current moment and the predicted flow rate of the emulsion pump at the next moment, and it is determined whether the first flow rate adjustment rate is greater than a preset first flow rate adjustment rate;

[0021] If the first flow adjustment rate is greater than the preset first flow adjustment rate, the backup emulsion pump flow prediction model is used to re-predict the flow of the emulsion pump at the next moment; determine whether the difference between the third flow adjustment value recalculated according to the re-predicted flow of the emulsion pump at the next moment and the first flow adjustment value is less than the preset difference; if so, no operation is performed; otherwise, the difference between the third flow adjustment value and the first flow adjustment value is used as the first flow adjustment correction value, and the fourth emulsification pump station flow loading and unloading control instruction is generated according to the first flow adjustment correction value to correct the pre-adjusted output flow of the emulsion pump.

[0022] By adopting the above solution, in case of large flow rate change, a backup prediction model is required to verify the predicted flow and generate the flow adjustment correction value in time to ensure a more accurate operating condition response.

[0023] Preferably, it also includes:

[0024] Real-time detection of the fluid temperature in the emulsion pump, and acquisition of compensation adjustment parameters for the flow measurement value under corresponding temperature conditions based on the relationship model between the fluid temperature and the emulsion pump flow measurement error established based on the historical fluid temperature and flow collected;

[0025] The flow rate of the emulsion pump obtained in real time by the sensor is compensated and adjusted according to the obtained temperature compensation adjustment parameters, and the flow rate of the emulsion pump obtained in real time by the sensor is replaced by the compensated and adjusted flow rate of the emulsion pump and input into the emulsion pump flow prediction model.

[0026] By adopting the above scheme, considering that the accuracy of flow measurement at the current moment affects the prediction accuracy of flow at the next moment and the calculation of flow adjustment value, as well as the influence of fluid temperature on flow measurement, the measurement data of the sensor is adjusted accordingly according to the real-time monitoring of fluid temperature to reduce the influence of temperature on the measurement result and obtain more accurate flow measurement value.

[0027] Preferably, it also includes:

[0028] There are a plurality of emulsion pump flow prediction models constructed, and each of the emulsion pump flow prediction models constructed corresponds to predicting the flow of one emulsion pump among a plurality of emulsion pumps operating in a coordinated manner;

[0029] Based on the flow rate of each emulsion pump at the current moment and the corresponding predicted flow rate of the emulsion pump at the next moment, the first flow adjustment amount of the corresponding emulsion pump is calculated, and the first emulsion pump station flow loading and unloading control instruction is generated according to the first flow adjustment amount of the corresponding emulsion pump to pre-adjust the output flow rate of the corresponding emulsion pump.

[0030] By adopting the above scheme, taking into account the condition of coordinated operation of multiple emulsion pumps, multiple emulsion pump flow prediction models are constructed, the flow prediction of the corresponding emulsion pumps is completed respectively, the distributed adjustment of the output flow of each emulsion pump is realized, and the control response speed of the flow of the overall emulsion pump station is improved.

[0031] Preferably, the sensor for obtaining the flow rate of the emulsion pump in real time is an electromagnetic flowmeter or an ultrasonic flowmeter.

[0032] By adopting the above scheme, a non-invasive flow sensor is used to ensure real-time measurement of the emulsion flow without interfering with the fluid flow.

[0033] In a second aspect, the present application provides an emulsification pump station flow loading and unloading control system, comprising:

[0034] The emulsion pump flow-related data acquisition module is used to obtain the action type, action duration, pressure and flow of the emulsion pump of the hydraulic support in real time using sensors;

[0035] An emulsion pump flow prediction module is used to construct an emulsion pump flow prediction model; the emulsion pump flow prediction model adopts a deep learning neural network, and the input is the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow of the emulsion pump, and the output is the flow of the emulsion pump at the next moment; the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow of the emulsion pump are input into the emulsion pump flow prediction model to obtain the predicted flow of the emulsion pump at the next moment;

[0036] An emulsion pump flow feedforward loading and unloading control module is used to calculate a first flow adjustment amount based on the flow of the emulsion pump at the current moment and the predicted flow of the emulsion pump at the next moment, and generate a first emulsion pump station flow loading and unloading control instruction according to the first flow adjustment amount to pre-adjust the output flow of the emulsion pump;

[0037] The emulsion pump flow feedback loading and unloading control module adopts the PID control algorithm to calculate the second flow adjustment amount according to the predicted flow of the emulsion pump at the next moment and the flow of the emulsion pump collected at the next moment; and generates the second emulsion pump station flow loading and unloading control instruction according to the second flow adjustment amount to continue to adjust the output flow of the emulsion pump.

[0038] By adopting the above solution, the accuracy, stability and response speed of the emulsification pump station flow control can be improved to adapt to complex and changing working conditions.

[0039] In a third aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method as described above.

[0040] In a fourth aspect, the present application provides a computer device, comprising a memory, a processor, and a program stored and executable on the memory, wherein the program implements the steps of the above method when executed by the processor.

[0041] In summary, this application has the following beneficial effects:

[0042] By comprehensively considering the action of the hydraulic support, the pressure of the emulsion pump and the historical flow of the emulsion pump, a neural network technology is constructed to achieve a more accurate prediction of the flow of the emulsion pump at the next moment; based on the predicted flow of the emulsion pump at the next moment, a feedforward flow control system is designed. When it is predicted that the action of the hydraulic support will cause a flow change, the control parameters of the emulsion pump are adjusted in advance to improve the response speed of the flow control; at the same time, a feedback control system is designed to continuously adjust the control strategy using real-time feedback data to eliminate possible deviations or oscillations, thereby ensuring that the pump station can operate continuously and stably. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of the emulsification pump station flow loading and unloading control method described in a specific embodiment;

[0044] Figure 2 It is a structural schematic diagram of the emulsification pump station flow loading and unloading control system described in a specific embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] like Figure 1 As shown, the embodiment of the present application discloses a method for controlling flow loading and unloading of an emulsification pump station, which specifically includes the following steps:

[0047] S1. Use sensors to obtain the action type, action duration, pressure and flow of the hydraulic support in real time.

[0048] Specifically, a displacement sensor and a speed sensor may be used to obtain the movement process of the hydraulic support, and the action type and action duration of the hydraulic support may be determined based on the movement process of the hydraulic support; the action types include: raising the column, lowering the column, and pulling the frame, etc.;

[0049] A high-precision pressure sensor can be used to measure the pressure of the emulsion pump;

[0050] A high-precision flow sensor (such as an electromagnetic flowmeter or an ultrasonic flowmeter) can be selected to measure the flow of the emulsion pump. In particular, it is considered that the flow measurement of the emulsion pump will be affected by the temperature of the fluid in the emulsion pump, resulting in the flow measurement error of the emulsion pump. In order to further ensure the accuracy of the measured flow, a relationship model between the fluid temperature and the emulsion pump flow measurement error is established based on the historically measured fluid temperature data, the emulsion pump flow data and the actual emulsion pump flow. According to the relationship model, the compensation adjustment parameters of the flow measurement value under the corresponding temperature conditions are determined, and the obtained temperature compensation adjustment parameters are used to compensate and adjust the flow of the emulsion pump obtained in real time by the sensor, so that the flow of the emulsion pump obtained in real time by the sensor is replaced by the compensated and adjusted flow of the emulsion pump as the real-time flow of the emulsion pump.

[0051] In addition, in addition to considering temperature compensation to measure the flow rate of the emulsion pump, multiple sensors can be used to perform average measurement to compensate for errors, that is, the pressure and flow rate of the emulsion pump obtained in real time by multiple pressure sensors and flow sensors are averaged, and the average of the pressure and flow rate of the emulsion pump corresponds to the real-time obtained pressure and flow rate of the emulsion pump.

[0052] S2. Input the action type, action duration, pressure and flow rate of the emulsion pump of the hydraulic support corresponding to the current moment into the constructed emulsion pump flow rate prediction model to obtain the predicted emulsion pump flow rate at the next moment.

[0053] Specifically, considering that different action types of hydraulic supports require different pressures and flows, such as: raising the column requires low pressure and large flow, lowering the column requires high pressure and small flow, and pulling the support requires medium pressure and large flow, that is, corresponding to different working conditions, there is an impact on the flow control of the emulsification pump station, and thus an emulsion pump flow prediction model is constructed; the constructed emulsion pump flow prediction model adopts a deep learning neural network, such as: an LSTM network with a fully connected layer; the input of the prediction model is: the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support corresponding to the current moment, and the pressure and flow of the emulsion pump corresponding to the current moment; wherein, the prediction model performs feature extraction on the input content to obtain the feature data sequence of the corresponding content; the output of the model is the emulsion pump flow at the next moment;

[0054] Among them, the fully connected layer integrates different types of feature data content, and the weight parameters corresponding to different types of feature data can be set manually; the training of the prediction model uses the action type, action duration, pressure and flow of the hydraulic support corresponding to multiple historical moments for iterative training, and uses the cross entropy error as the loss function. When the loss function reaches the preset loss value, the model training is terminated to obtain the constructed emulsion pump flow prediction model.

[0055] The action type, action duration, pressure and flow rate of the emulsion pump of the hydraulic support corresponding to the current moment are input into the constructed emulsion pump flow rate prediction model to obtain the predicted emulsion pump flow rate at the next moment.

[0056] S3. Calculate and obtain a first flow adjustment amount and correspondingly generate a first emulsification pump station flow loading and unloading control instruction to pre-adjust the output flow of the emulsion pump.

[0057] Specifically, a feedforward flow control is designed to adjust the flow in advance to improve the response speed of the emulsification pump station flow control; a difference calculation is performed based on the flow of the emulsion pump at the current moment and the predicted flow of the emulsion pump at the next moment to obtain a first flow adjustment amount;

[0058] A high-performance PLC controller is selected, and the PLC controller is used to generate a flow loading and unloading control instruction of the first emulsification pump station according to the first flow adjustment amount;

[0059] An actuator is selected and used (such as a frequency converter) to adjust the output flow of the emulsion pump according to the generated flow loading and unloading control instruction of the first emulsification pump station.

[0060] S4. Using the PID control algorithm, calculate and obtain the second flow adjustment amount and correspondingly generate a second emulsification pump station flow loading and unloading control instruction to continue adjusting the output flow of the emulsion pump.

[0061] Specifically, in addition to feedforward adjustment, in order to better realize flow control to meet flow requirements, feedback control is designed, such as using a PID control algorithm, for the flow of the emulsion pump collected at the next moment of real-time feedback, calculate the difference between the predicted flow of the emulsion pump at the next moment and the flow of the emulsion pump collected at the next moment, and obtain the second flow adjustment amount; select a PLC controller, and use the PLC controller to generate a second emulsification pump station flow loading and unloading control instruction according to the second flow adjustment amount; select an actuator, and use the actuator to adjust the output flow of the emulsion pump according to the generated second emulsification pump station flow loading and unloading control instruction.

[0062] Through the above scheme, by adopting closed-loop control method and advanced prediction model for flow prediction control method, it is possible to achieve accurate control of the emulsification pump station flow and improve the stability and response speed of pump station operation.

[0063] In a specific implementation, considering that the emulsified pump station may be a single emulsion pump or multiple coordinated emulsion pumps, if it is an emulsified pump station with multiple coordinated emulsion pumps, priorities are often set for each emulsion pump for coordinated operation, such as the first level, the second level and the Nth level. The higher the priority, the greater the loading and unloading pressure of the emulsion pump, and the more corresponding flow loading and unloading; in order to balance the operation of multiple emulsion pumps, the coordinated operation work sets multiple working mode cycles, such as three-mode cycle operation, in the first mode, the first emulsion pump has the highest priority, the second emulsion pump has the second priority, and the third emulsion pump has the lowest priority; in the second mode, the second emulsion pump has the highest priority, the third emulsion pump has the second priority, and the first emulsion pump has the lowest priority; in the third mode, the third emulsion pump has the highest priority, the first emulsion pump has the second priority, and the second emulsion pump has the lowest priority; it can be seen that the priority in the coordinated operation work cycle of a single emulsion pump also affects the flow control of the emulsion pump, and the method also includes:

[0064] Obtain the priority of the current emulsion pump in the coordinated operation of multiple emulsion pumps in real time; for example: first level;

[0065] The input for constructing the emulsion pump flow prediction model also includes: the priority of the current emulsion pump corresponding to the current moment in the coordinated operation of multiple emulsion pumps;

[0066] The action type of the hydraulic support, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow rate of the emulsion pump corresponding to the current moment are input into the emulsion pump flow prediction model. At the same time, the priority of the current emulsion pump corresponding to the current moment in the coordinated operation of multiple emulsion pumps is input into the emulsion pump flow prediction model to obtain a more accurate predicted flow value.

[0067] In a specific embodiment, considering that the degree of partial flow adjustment is relatively large, in order to avoid the operation loss of the emulsification pump station due to the rapid adjustment of a relatively large degree of flow, the power consumption of the emulsification pump station is effectively reduced, and the service life of the emulsion pump is extended; the method further includes:

[0068] Determining whether the first flow adjustment amount is greater than a preset flow adjustment amount; the preset flow adjustment amount is considered to be a setting;

[0069] If it is greater than, the first flow adjustment amount is divided into a plurality of first flow sub-adjustments, and a plurality of third emulsification pump station flow loading and unloading control instructions are generated accordingly to replace the generation of the first emulsification pump station flow loading and unloading control instructions; the order of the generated plurality of third emulsification pump station flow loading and unloading control instructions is randomly set;

[0070] Within a first preset time from the current moment, a plurality of third emulsification pump station flow loading and unloading control instructions are sequentially executed to complete the pre-adjustment of the output flow of the emulsion pump; the first preset time is less than the sampling time interval, such as sampling once every 1s to obtain the flow data at the corresponding moment;

[0071] Otherwise, within the second preset time from the current moment, the first emulsification pump station flow loading and unloading control instruction is generated according to the first flow adjustment amount to complete the pre-adjustment of the output flow of the emulsion pump, and the second preset time is less than the sampling time interval, and the first preset time is greater than the second preset time.

[0072] Similarly, if the second flow adjustment amount is greater than the preset flow adjustment amount, the same division method can be used to perform flow adjustment.

[0073] In a specific embodiment, in order to further ensure the accuracy of the prediction results, when a large degree of flow adjustment is required, the backup prediction model can be used to verify the prediction results and make corrections; the method also includes:

[0074] A first flow rate adjustment rate is calculated based on the flow rate of the emulsion pump at the current moment and the predicted flow rate of the emulsion pump at the next moment, that is, the difference between the flow rate of the emulsion pump at the current moment and the predicted flow rate of the emulsion pump at the next moment divided by the sampling interval;

[0075] Determine whether the first flow rate adjustment rate is greater than the preset first flow rate adjustment rate; if the first flow rate adjustment rate is greater than the preset first flow rate adjustment rate, then use the backup emulsion pump flow prediction model to re-predict the flow rate of the emulsion pump at the next moment; determine whether the difference between the third flow rate adjustment value recalculated based on the re-predicted flow rate of the emulsion pump at the next moment and the first flow rate adjustment value is less than the preset difference, if less, do not perform any operation; the preset difference is the maximum prediction error allowed;

[0076] Otherwise, the difference between the third flow adjustment value and the first flow adjustment value is used as the first flow adjustment correction value, and the fourth emulsification pump station flow loading and unloading control instruction is generated according to the first flow adjustment correction value to correct the output flow of the pre-adjusted emulsion pump.

[0077] In a specific embodiment, considering that there are multiple emulsion pumps in a coordinated operation emulsion pump station, in order to further accelerate the flow control response speed of the emulsion pump, distributed control is selected to complete the generation and execution of corresponding control instructions in parallel. Specifically, the method includes:

[0078] There are multiple emulsion pump flow prediction models constructed, each of which is generated using historical training data of a specific emulsion pump, corresponding to predicting the flow of one emulsion pump among multiple emulsion pumps operating in a coordinated manner;

[0079] Obtain the flow rate of each emulsion pump predicted at the next moment, and calculate the first flow rate adjustment amount of the corresponding emulsion pump based on the flow rate of each emulsion pump at the current moment and the corresponding predicted flow rate of the emulsion pump at the next moment, that is, the difference between the flow rate of the first emulsion pump at the current moment and the predicted flow rate of the first emulsion pump at the next moment;

[0080] A first emulsification pump station flow rate loading and unloading control instruction is generated according to the first flow rate adjustment amount of the corresponding emulsion pump to pre-adjust the output flow rate of the corresponding emulsion pump.

[0081] like Figure 2 As shown, the embodiment of the present application discloses an emulsification pump station flow loading and unloading control system, which specifically includes:

[0082] The emulsion pump flow-related data acquisition module 101 is used to obtain the action type, action duration, pressure and flow of the emulsion pump of the hydraulic support in real time using sensors;

[0083] The emulsion pump flow prediction module 102 is used to construct an emulsion pump flow prediction model; the emulsion pump flow prediction model adopts a deep learning neural network, and the input is the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow of the emulsion pump, and the output is the flow of the emulsion pump at the next moment; the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow of the emulsion pump are input into the emulsion pump flow prediction model to obtain the predicted flow of the emulsion pump at the next moment;

[0084] The emulsion pump flow feedforward loading and unloading control module 103 is used to calculate a first flow adjustment amount based on the flow of the emulsion pump at the current moment and the predicted flow of the emulsion pump at the next moment, and generate a first emulsion pump station flow loading and unloading control instruction according to the first flow adjustment amount to pre-adjust the output flow of the emulsion pump;

[0085] The emulsion pump flow feedback loading and unloading control module 104 adopts a PID control algorithm to calculate a second flow adjustment amount based on the predicted flow of the emulsion pump at the next moment and the flow of the emulsion pump collected at the next moment; and generates a second emulsion pump station flow loading and unloading control instruction based on the second flow adjustment amount to continue adjusting the output flow of the emulsion pump.

[0086] In a specific embodiment, the emulsion pump flow-related data acquisition module 101 in the system is also used to detect the fluid temperature in the emulsion pump in real time, and obtain compensation adjustment parameters of the flow measurement value under corresponding temperature conditions based on the relationship model between the fluid temperature and the emulsion pump flow measurement error established according to the collected historical fluid temperature and flow; the flow of the emulsion pump obtained in real time by the sensor is compensated and adjusted according to the obtained temperature compensation adjustment parameters, and the flow of the emulsion pump obtained in real time by the sensor is replaced by the compensated emulsion pump flow prediction model.

[0087] In a specific embodiment, the emulsion pump flow prediction module 102 in the system is also used to obtain in real time the priority of the current emulsion pump in the coordinated operation of multiple emulsion pumps; the input for constructing the emulsion pump flow prediction model also includes: the priority of the current emulsion pump corresponding to the current moment in the coordinated operation of multiple emulsion pumps; at the same time, the priority of the current emulsion pump corresponding to the current moment in the coordinated operation of multiple emulsion pumps is input into the emulsion pump flow prediction model.

[0088] In a specific embodiment, the emulsion pump flow feedforward loading and unloading control module 103 in the system is also used to determine whether the first flow adjustment amount is greater than the preset flow adjustment amount. If it is, the first flow adjustment amount is divided into multiple first flow sub-adjustments, and multiple third emulsification pump station flow loading and unloading control instructions are correspondingly generated to replace the generation of the first emulsification pump station flow loading and unloading control instructions, and within a first preset time from the current moment, the multiple third emulsification pump station flow loading and unloading control instructions are sequentially executed to complete the pre-adjustment of the output flow of the emulsion pump; otherwise, within a second preset time from the current moment, the first emulsification pump station flow loading and unloading control instructions are generated according to the first flow adjustment amount to complete the pre-adjustment of the output flow of the emulsion pump, and the first preset time and the second preset time are both less than the sampling time interval, and the first preset time is greater than the second preset time.

[0089] In a specific embodiment, the emulsion pump flow feedforward loading and unloading control module 103 in the system is also used to calculate a first flow adjustment rate based on the flow of the emulsion pump at the current moment and the predicted flow of the emulsion pump at the next moment, and determine whether the first flow adjustment rate is greater than the preset first flow adjustment rate; if the first flow adjustment rate is greater than the preset first flow adjustment rate, then the backup emulsion pump flow prediction model is used to re-predict the flow of the emulsion pump at the next moment; determine whether the difference between the third flow adjustment value recalculated based on the re-predicted flow of the emulsion pump at the next moment and the first flow adjustment value is less than the preset difference, if less, no operation is performed; otherwise, the difference between the third flow adjustment value and the first flow adjustment value is used as the first flow adjustment amount correction value, and a fourth emulsification pump station flow loading and unloading control instruction is generated according to the first flow adjustment amount correction value to correct the pre-adjusted output flow of the emulsion pump.

[0090] The embodiment of the present application also discloses a computer-readable storage medium.

[0091] Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and executed such as the above-mentioned emulsification pump station flow loading and unloading control method. The computer-readable storage medium includes, for example: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0092] The embodiment of the present application also discloses a computer device.

[0093] Specifically, the computer device includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and execute the above-mentioned emulsification pump station flow loading and unloading control method.

[0094] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A method for controlling flow loading and unloading of an emulsification pump station, characterized in that: include: Use sensors to obtain the action type, action duration, pressure and flow of the emulsion pump of the hydraulic support in real time; Construct an emulsion pump flow prediction model; The emulsion pump flow prediction model adopts a deep learning neural network, the input is the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow of the emulsion pump, and the output is the flow of the emulsion pump at the next moment; Inputting the action type of the hydraulic support, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow rate of the emulsion pump corresponding to the current moment into the emulsion pump flow prediction model to obtain the predicted flow rate of the emulsion pump at the next moment; A first flow adjustment amount is calculated based on the flow rate of the emulsion pump at the current moment and the predicted flow rate of the emulsion pump at the next moment, and a first emulsion pump station flow loading and unloading control instruction is generated according to the first flow adjustment amount to pre-adjust the output flow rate of the emulsion pump; A PID control algorithm is used to calculate a second flow adjustment amount according to the predicted flow rate of the emulsion pump at the next moment and the flow rate of the emulsion pump collected at the next moment; A second emulsification pump station flow loading and unloading control instruction is generated according to the second flow adjustment amount to continue adjusting the output flow of the emulsion pump.

2. The emulsification pump station flow loading and unloading control method according to claim 1 is characterized in that: Also includes: Obtain the priority of the current emulsion pump in the coordinated operation of multiple emulsion pumps in real time; The input for constructing the emulsion pump flow prediction model also includes: the priority of the current emulsion pump corresponding to the current moment in the coordinated operation of multiple emulsion pumps; At the same time, the priority of the current emulsion pump corresponding to the current moment in the coordinated operation of multiple emulsion pumps is input into the emulsion pump flow prediction model.

3. The emulsification pump station flow loading and unloading control method according to claim 1 is characterized in that: Also includes: Determining whether the first flow adjustment amount is greater than a preset flow adjustment amount; If it is greater than, the first flow adjustment amount is divided into a plurality of first flow sub-adjustments, and a plurality of third emulsification pump station flow loading and unloading control instructions are correspondingly generated to replace the generation of the first emulsification pump station flow loading and unloading control instructions, and within the first preset time from the current moment, the plurality of third emulsification pump station flow loading and unloading control instructions are sequentially executed to complete the pre-adjustment of the output flow of the emulsion pump; Otherwise, the first emulsification pump station flow loading and unloading control instruction is generated according to the first flow adjustment amount within the second preset time from the current moment to complete the pre-adjustment of the output flow of the emulsion pump, and the first preset time and the second preset time are both less than the sampling time interval, and the first preset time is greater than the second preset time.

4. The emulsification pump station flow loading and unloading control method according to claim 1 is characterized in that: Also includes: Calculating a first flow rate adjustment rate based on the flow rate of the emulsion pump at the current moment and the predicted flow rate of the emulsion pump at the next moment, and determining whether the first flow rate adjustment rate is greater than a preset first flow rate adjustment rate; If the first flow rate adjustment rate is greater than the preset first flow rate adjustment rate, the backup emulsion pump flow rate prediction model is used to re-predict the flow rate of the emulsion pump at the next moment; Determine whether the difference between the third flow rate adjustment value recalculated according to the re-predicted flow rate of the emulsion pump at the next moment and the first flow rate adjustment value is less than a preset difference, and if so, do not perform any operation; Otherwise, the difference between the third flow adjustment value and the first flow adjustment value is used as the first flow adjustment correction value, and the fourth emulsification pump station flow loading and unloading control instruction is generated according to the first flow adjustment correction value to correct the output flow of the pre-adjusted emulsion pump.

5. The emulsification pump station flow loading and unloading control method according to claim 1 is characterized in that: Also includes: Real-time detection of the fluid temperature in the emulsion pump, and acquisition of compensation adjustment parameters for the flow measurement value under corresponding temperature conditions based on the relationship model between the fluid temperature and the emulsion pump flow measurement error established based on the historical fluid temperature and flow collected; The flow rate of the emulsion pump obtained in real time by the sensor is compensated and adjusted according to the obtained temperature compensation adjustment parameters, and the flow rate of the emulsion pump obtained in real time by the sensor is replaced by the compensated and adjusted flow rate of the emulsion pump and input into the emulsion pump flow prediction model.

6. The emulsification pump station flow loading and unloading control method according to claim 1 is characterized in that: Also includes: There are a plurality of emulsion pump flow prediction models constructed, and each of the emulsion pump flow prediction models constructed corresponds to predicting the flow of one emulsion pump among a plurality of emulsion pumps operating in a coordinated manner; Based on the flow rate of each emulsion pump at the current moment and the corresponding predicted flow rate of the emulsion pump at the next moment, the first flow adjustment amount of the corresponding emulsion pump is calculated, and the first emulsion pump station flow loading and unloading control instruction is generated according to the first flow adjustment amount of the corresponding emulsion pump to pre-adjust the output flow rate of the corresponding emulsion pump.

7. The emulsification pump station flow loading and unloading control method according to claim 1 is characterized in that: The sensor for obtaining the flow rate of the emulsion pump in real time is an electromagnetic flowmeter or an ultrasonic flowmeter.

8. An emulsification pump station flow loading and unloading control system, characterized in that: include: The emulsion pump flow-related data acquisition module is used to obtain the action type, action duration, pressure and flow of the emulsion pump of the hydraulic support in real time using sensors; An emulsion pump flow prediction module is used to construct an emulsion pump flow prediction model; the emulsion pump flow prediction model adopts a deep learning neural network, and the input is the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support, the pressure sequence of the emulsion pump and the flow of the emulsion pump, and the output is the flow of the emulsion pump at the next moment; the action type of the hydraulic support corresponding to the current moment, the action duration of the hydraulic support, the pressure of the emulsion pump and the flow of the emulsion pump are input into the emulsion pump flow prediction model to obtain the predicted flow of the emulsion pump at the next moment; An emulsion pump flow feedforward loading and unloading control module is used to calculate a first flow adjustment amount based on the flow of the emulsion pump at the current moment and the predicted flow of the emulsion pump at the next moment, and generate a first emulsion pump station flow loading and unloading control instruction according to the first flow adjustment amount to pre-adjust the output flow of the emulsion pump; The emulsion pump flow feedback loading and unloading control module adopts the PID control algorithm to calculate the second flow adjustment amount according to the predicted flow of the emulsion pump at the next moment and the flow of the emulsion pump collected at the next moment; and generates the second emulsion pump station flow loading and unloading control instruction according to the second flow adjustment amount to continue to adjust the output flow of the emulsion pump.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer device, characterized in that: The computer device comprises a memory, a processor and a program stored and executable on the memory, and the program implements the steps of the method according to any one of claims 1 to 7 when executed by the processor.

Images