Method, device and equipment for determining operation scheme of LNG receiving station

Abstract

The invention relates to the technical field of liquefied natural gas, in particular to a method, device and equipment for determining an operation scheme of an LNG receiving station. The operation scheme determination method of the LNG receiving station comprises the steps that historical operation big data of the LNG receiving station under each working condition is acquired; according to the historical operation big data, constructing a performance prediction model of key equipment in the LNG receiving station under each working condition; based on the performance prediction model of the key equipment in the LNG receiving station under each working condition, establishing a processing cost prediction model of the LNG receiving station under each working condition; and based on the processing cost prediction model under each working condition, optimizing an operation scheme of key equipment in the LNG receiving station under each working condition. According to the embodiment of the invention, the actual operation performance of each key device in the LNG receiving station can be determined more scientifically and systematically based on the processing cost prediction model under each working condition, the optimized operation scheme of each key device is determined, and the operation cost of the LNG receiving station is reduced.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of liquefied natural gas, and particularly to a method, device and equipment for determining the operation plan of an LNG receiving terminal. Background Art

[0002] An LNG (Liquefied Natural Gas) receiving terminal is a station for receiving (including unloading at the terminal), storing, vaporizing and exporting LNG shipped by ships. The main function of the LNG receiving terminal is to store the cryogenic liquefied natural gas transported by sea vessels in the LNG storage tank, and then pressurize it according to the needs of downstream users. After passing through a special vaporizer, the LNG is vaporized to above 0°C and enters the gas transmission main line through the gas transmission first station and is transported to downstream users.

[0003] In the existing methods for processing the operation plan of LNG receiving terminals, the start-stop sequence of equipment is mostly based on experience or randomly set. Multiple sets of similar equipment such as key equipment like LNG low-pressure pumps, high-pressure pumps, seawater pumps and BOG compressors are usually set to operate in parallel.

[0004] However, the demands of downstream users of the LNG receiving terminal fluctuate greatly. The continuous processes such as boil-off gas treatment and gaseous export are also constantly changing dynamically due to the influence of intermittent processes such as LNG unloading and liquid export. These influencing factors pose challenges to the LNG receiving terminal to achieve optimized operation costs. At the same time, in the existing methods for processing the operation plan of LNG receiving terminals, there is rarely an analysis of the actual operation performance of key equipment, and the actual efficient operation range of each equipment has not been systematically mastered. The control of some key process operation parameters such as the temperature and pressure of the reflux condenser is also mainly based on experience under the requirements of operating procedures, lacking scientific and systematic optimization methods and guidance. Therefore, how to overcome the problems existing in the existing methods for processing the operation plan of LNG receiving terminals, such as relying on manual experience, lacking analysis of the operation performance of key equipment and lacking scientific and systematic optimization methods, and provide a scientific and systematic method for determining the operation plan of the LNG receiving terminal, and then clarify the actual operation performance and actual efficient operation range of each key equipment in the LNG receiving terminal, and reduce the operation cost of the LNG receiving terminal is a key problem to be solved urgently. Summary of the Invention

[0005] The purpose of the embodiments of this specification is to provide a scientific and systematic method for determining the operation plan of an LNG receiving terminal, so as to clarify the actual operation performance and actual efficient operation range of each key equipment in the LNG receiving terminal, and then reduce the operation cost of the LNG receiving terminal.

[0006] On the one hand, an embodiment of this specification proposes a method for determining an operation plan of an LNG receiving terminal. The method includes: obtaining the historical operation big data of the LNG receiving terminal under each working condition; constructing a performance prediction model of key equipment in the LNG receiving terminal under each working condition according to the historical operation big data; establishing a processing cost prediction model of the LNG receiving terminal under each working condition based on the performance prediction model of key equipment in the LNG receiving terminal under each working condition; and optimizing the operation plan of key equipment in the LNG receiving terminal under each working condition based on the processing cost prediction model under each working condition.

[0007] On the other hand, an embodiment of this specification proposes an apparatus for determining an operation plan of an LNG receiving terminal. The apparatus includes: an obtaining module, configured to obtain the historical operation big data of the LNG receiving terminal under each working condition; a constructing module, configured to construct a performance prediction model of key equipment in the LNG receiving terminal under each working condition according to the historical operation big data; an establishing module, configured to establish a processing cost prediction model of the LNG receiving terminal under each working condition based on the performance prediction model of key equipment in the LNG receiving terminal under each working condition; and an optimizing module, configured to optimize the operation plan of key equipment in the LNG receiving terminal under each working condition based on the processing cost prediction model under each working condition.

[0008] On yet another hand, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the above method for determining an operation plan of an LNG receiving terminal.

[0009] As can be seen from the technical solutions provided by the embodiments of this specification above, the embodiments of this specification can obtain the historical operation big data of the LNG receiving terminal under each working condition; construct a performance prediction model of key equipment in the LNG receiving terminal under each working condition according to the historical operation big data; establish a processing cost prediction model of the LNG receiving terminal under each working condition based on the performance prediction model of key equipment in the LNG receiving terminal under each working condition; and optimize the operation plan of key equipment in the LNG receiving terminal under each working condition based on the processing cost prediction model under each working condition. Compared with existing methods, it is possible to more scientifically and systematically clarify the actual operation performance and actual efficient operation range of each key equipment in the LNG receiving terminal based on the processing cost prediction model under each working condition, thereby reducing the operation cost of the LNG receiving terminal. Description of the Drawings

[0010] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art.

[0011] Figure 1It is a flowchart of the method for determining the operation plan of the LNG receiving terminal provided in the embodiments of this specification;

[0012] Figure 2 It is the overall logic flowchart of the method for determining the operation plan of the LNG receiving terminal provided in the embodiments of this specification;

[0013] Figure 3 It is a schematic diagram of the typical process flow of the LNG receiving terminal provided in the embodiments of this specification;

[0014] Figure 4 It is a comparison schematic diagram of the predicted value and the actual value of the unit energy consumption of the LNG low-pressure pump B provided in the embodiments of this specification;

[0015] Figure 5 It is a schematic diagram of the relative error distribution of the unit energy consumption prediction model of the LNG low-pressure pump B provided in the embodiments of this specification;

[0016] Figure 6 It is a schematic diagram of the structural composition of the device for determining the operation plan of the LNG receiving terminal provided in the embodiments of this specification;

[0017] Figure 7 It is a schematic diagram of the structural composition of the computer device provided in the embodiments of this specification. Specific embodiments

[0018] Next, the technical solutions in the embodiments of this specification will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this specification without creative efforts shall fall within the protection scope of this specification.

[0019] Figure 1 It is a flowchart of the method for determining the operation plan of the LNG receiving terminal, Figure 2 It is the overall logic flowchart of the method for determining the operation plan of the LNG receiving terminal. Specifically, the method includes the following steps:

[0020] S101: Obtain the historical operation big data of the LNG receiving terminal under each working condition.

[0021] In some embodiments, the historical operation big data includes key parameters and energy and material consumption data. The key parameters include controllable key parameters and uncontrollable key parameters. The controllable key parameters at least include one of the start-stop state of key equipment, unloading speed, cold insulation circulation volume, inlet pressure of BOG compressor, temperature of BOG compressor, outlet pressure of BOG compressor, spray volume of the recondenser, pressure of the recondenser, liquid level of the recondenser, flow rate of LNG low-pressure pump, flow rate of LNG high-pressure pump, flow rate of seawater pump, LNG flow rate of vaporizer, and seawater flow rate of vaporizer. The uncontrollable key parameters at least include one of whether the ship has been unloaded, season, pressure of incoming LNG, temperature of incoming LNG, composition of incoming LNG, LNG liquid level in the storage tank, LNG density in the storage tank, LNG pressure in the storage tank, liquid external output volume, gaseous external output volume, external output pressure, tidal difference of seawater pump, seawater inlet pressure, and seawater inlet temperature. The energy and material consumption data at least includes one of fuel gas consumption, nitrogen consumption, electric power, current, voltage, operation time, electricity charge, capacity charge, gas charge, and maintenance cost.

[0022] By obtaining the key parameters and energy and material consumption data in the historical operation big data, it lays a data foundation for subsequently clarifying the actual operation performance and actual efficient operation range of each key equipment in the LNG receiving terminal.

[0023] In some embodiments, the key equipment of the LNG receiving terminal at least includes one of a loading / unloading arm, a storage tank, a BOG compressor, a recondenser, an LNG low-pressure pump, an LNG high-pressure pump, a seawater pump, a vaporizer, and a cold insulation circulation pipeline. Refer to Figure 3 , Figure 3 shows the typical process flow of the LNG receiving terminal. The process flow mainly consists of unloading, storage, BOG treatment, low-pressure external output, and high-pressure external output processes. During unloading, the unloading pump on the LNG carrier transports LNG to the storage tank through the loading / unloading arm and the unloading pipeline. The BOG generated in the storage tank is returned to the cabin through the gas-phase arm after pressure regulation to balance the pressure in the cabin. The remaining BOG is compressed by the BOG compressor and then enters the recondenser, where it will be condensed and liquefied by the LNG pressurized by the LNG low-pressure pump from the storage tank. Then, it is mixed with another stream of LNG pressurized by the LNG low-pressure pump from the storage tank and enters the LNG high-pressure pump to be pressurized to the pipeline transportation pressure. Then, it enters the vaporizer to absorb heat and vaporize, and finally is externally output through the pipeline network.

[0024] By determining the key equipment of the LNG receiving terminal, it lays a foundation for subsequently clarifying the actual operation performance and actual efficient operation range of each key equipment in the LNG receiving terminal.

[0025] In some embodiments, based on the uncontrollable key parameters in the historical operation big data, the operation scenarios of the LNG receiving terminal can be divided.

[0026] By dividing the operating scenarios of the LNG receiving terminal based on uncontrollable key parameters in the historical operation big data, it lays a foundation for optimizing the operating scenarios of each key equipment in the LNG receiving terminal under different scenarios.

[0027] Whether the ship has been unloaded, season, the pressure of the incoming LNG, the temperature of the incoming LNG, the composition of the incoming LNG, the LNG liquid level in the storage tank, the LNG density in the storage tank, the LNG pressure in the storage tank, the liquid outbound volume, the gaseous outbound volume, the outbound pressure, the tidal difference of the seawater pump, the seawater inlet pressure, the seawater inlet temperature, etc., the change of any one or more uncontrollable key parameters will have a huge impact on the operation of the LNG receiving terminal. Therefore, the operating modes of the LNG receiving terminal can be divided into scenarios according to different values or states of the uncontrollable key parameters, and then different operating scenarios can be set for the LNG receiving terminal according to different scenarios.

[0028] S102: According to the historical operation big data, construct a performance prediction model for the key equipment in the LNG receiving terminal under each scenario.

[0029] In some embodiments, the corresponding key parameters and energy consumption and material consumption data of the key equipment in the historical operation big data under each scenario can be obtained. Based on the corresponding key parameters and energy consumption and material consumption data of the key equipment, construct a performance prediction model for the key equipment under each scenario. For each scenario, machine / deep learning algorithms can be used to construct a performance prediction model for each key equipment in the LNG receiving terminal. The corresponding key parameters of each key equipment can be used as the input data of the performance prediction model, and the performance prediction model outputs the corresponding energy consumption and material consumption data of each key equipment. The performance prediction model is trained to fit by minimizing the difference between the predicted energy consumption and material consumption data of each key equipment and the actual energy consumption and material consumption data of each key equipment.

[0030] Applying machine learning / deep learning algorithms to the optimization scenario of the operating scenarios of the key equipment in the LNG receiving terminal can more accurately extract and learn the features in the historical operation big data, avoid the cumbersome process of relying on experience or manually designing features in traditional algorithms, improve the accuracy and efficiency of feature selection, and thus can improve the accuracy and efficiency of optimizing the operating scenarios of the key equipment in the LNG receiving terminal.

[0031] During the training process, gradient descent is adopted, and the parameters of the performance prediction model are updated according to the gradient descent algorithm of Newton-Leibniz formula. The calculation formula is:

[0032]

[0033] In the formula, ωj represents the j-th parameter of the performance prediction model, and ωj' is the corresponding updated parameter; λ represents the learning rate of the performance prediction model, which is used to determine the convergence rate of the performance prediction model. It represents the partial derivative of the loss function F(ωj) with respect to ωj when indicating the deviation between the predicted result and the actual result of the known performance prediction model, and the deviation between the predicted result and the actual result can be calculated through the loss function. The loss function is usually defined based on methods such as the sum of squared errors, absolute value of errors, logarithmic loss, etc. between the predicted result and the actual result. The performance prediction model adjusts the values of each parameter in the model by the deviation between the predicted energy consumption and material consumption data of each key device and the actual energy consumption and material consumption data of each key device, so that the deviation becomes smaller and smaller. The machine / deep learning model used in the performance prediction model of key devices in the LNG receiving station can specifically adopt models such as logistic regression, KNN, decision tree, DNN, support vector machine, XGBoost, random forest, etc.

[0034] In some embodiments, the basic energy consumption and material consumption data of the LNG receiving station under each working condition can be obtained; based on the basic energy consumption and material consumption data of the LNG receiving station under each working condition, the energy consumption and material consumption data of the key devices in the LNG receiving station, and the law of conservation of energy and mass, the actual processing cost model of the LNG receiving station under each working condition can be constructed.

[0035] By constructing the actual processing cost model of the LNG receiving station under each working condition based on the basic energy consumption and material consumption data of the LNG receiving station under each working condition, the energy consumption and material consumption data of the key devices in the LNG receiving station, and the law of conservation of energy and mass, it lays a foundation for constructing the processing cost prediction model of the LNG receiving station under each working condition based on the actual processing cost model of the LNG receiving station under each working condition.

[0036] The basic energy consumption and material consumption data of the LNG receiving station under each working condition and the energy consumption and material consumption data of the key devices in the historical operation big data under each working condition can be obtained. Based on the basic energy consumption and material consumption data of the LNG receiving station under each working condition and the energy consumption and material consumption data of all key devices in the LNG receiving station, the actual LNG processing cost model of the LNG receiving station under each working condition is constructed. The basic energy consumption and material consumption data include the energy consumption and material consumption for equipment maintenance in the LNG receiving station and the energy consumption and material consumption of other non-key devices in the LNG receiving station. The input data of the actual LNG processing cost model can be the energy consumption and material consumption data of all key devices in the LNG receiving station within any time period, the basic energy consumption and material consumption data of the LNG receiving station, the unit price of each energy consumption and material consumption, and the amount of LNG processed by the LNG receiving station. The actual LNG processing cost model can calculate the cost consumed by all key devices in the LNG receiving station and the basic cost, and superimpose the calculated cost consumed by all key devices in the LNG receiving station and the basic cost. The actual LNG processing cost model can divide the superimposed result by the amount of LNG processed by the LNG receiving station and output the actual processing cost per unit of LNG processed by the LNG receiving station.

[0037] S103: Based on the performance prediction models of key equipment in the LNG receiving terminal under each working condition, establish a processing cost prediction model for the LNG receiving terminal under each working condition.

[0038] In some embodiments, based on the actual LNG processing cost model of the LNG receiving terminal under each working condition, the performance prediction models of key equipment in the LNG receiving terminal, and the basic energy consumption and material consumption data of the LNG receiving terminal, establish a processing cost prediction model for the LNG receiving terminal under each working condition.

[0039] Based on the actual LNG processing cost model of the LNG receiving terminal under each working condition, the performance prediction models of key equipment in the LNG receiving terminal, and the basic energy consumption and material consumption data of the LNG receiving terminal, a processing cost prediction model for the LNG receiving terminal under each working condition can be established, laying a foundation for clarifying the actual operating performance and actual efficient operating range of each key equipment in the LNG receiving terminal.

[0040] The performance prediction models of all key equipment in the LNG receiving terminal can be integrated or fused, and a processing cost prediction model can be constructed by comprehensively considering the unit price of each energy consumption and material consumption, the basic energy consumption and material consumption data of the LNG receiving terminal, and the LNG volume processed by the LNG receiving terminal. The corresponding key parameters of the key equipment in the LNG receiving terminal, the basic energy consumption and material consumption data of the LNG receiving terminal, and the LNG volume processed by the LNG receiving terminal can be used as input data and input into the processing cost prediction model, and the processing cost prediction model outputs the predicted processing cost per unit of LNG processed by the LNG receiving terminal. The energy consumption and material consumption data corresponding to all key equipment in the LNG receiving terminal, the basic energy consumption and material consumption data of the LNG receiving terminal, the unit price of each energy consumption and material consumption, and the LNG volume processed by the LNG receiving terminal can be input into the actual LNG processing cost model, and the actual LNG processing cost model outputs the actual processing cost per unit of LNG processed by the LNG receiving terminal. By minimizing the difference between the actual processing cost per unit of LNG processed by the LNG receiving terminal and the predicted processing cost per unit of LNG processed by the LNG receiving terminal, the parameters of the processing cost prediction model can be adjusted.

[0041] S104: Based on the processing cost prediction model under each working condition, optimize the operation schemes of key equipment in the LNG receiving terminal under each working condition.

[0042] In some embodiments, based on the processing cost prediction model under each working condition, an LNG processing cost optimization model under each working condition can be constructed; based on the LNG processing cost optimization model under each working condition, the operation schemes of key equipment in the LNG receiving terminal can be optimized.

[0043] Through the LNG processing cost optimization model under each working condition, the operation plan of key equipment in the LNG receiving terminal is scientifically and systematically optimized, reducing the operation cost of the LNG receiving terminal.

[0044] For the processing cost prediction model under each working condition, an optimization algorithm can be used to construct the LNG processing cost optimization model under each working condition. The optimization algorithm can be algorithms such as genetic algorithm, simulated annealing algorithm, random search, etc. For example, based on the processing cost prediction model under a certain working condition, a genetic algorithm can be used to construct the LNG processing cost optimization model. The LNG processing cost optimization model can encode the parameters of the operation plan, and the encoding method can be binary encoding method, floating-point encoding method, symbolic encoding method, etc. Then, the LNG processing cost optimization model randomly initializes a population, and the individuals in the population represent an operation plan under the current working condition. Then, the LNG processing cost optimization model establishes a fitness function to judge the quality of the individuals in the population. The LNG processing cost optimization model can select several individuals with large fitness function values from the population with a certain probability and continuously generate new operation plans through crossover and mutation operations. Through multiple iterations, the LNG processing cost optimization model can obtain a better operation plan.

[0045] In some embodiments, based on the controllable key parameters corresponding to the key equipment in the LNG receiving terminal under each working condition, the operation space of the LNG receiving terminal under each working condition can be determined; the operation space represents the set of all possible operation plans of the key equipment in the LNG receiving terminal under each working condition; based on the LNG processing cost optimization model under each working condition, an optimization objective function under each working condition can be constructed; based on the optimization objective function under each working condition, the optimal operation plan of the key equipment in the LNG receiving terminal under each working condition in the operation space can be obtained.

[0046] Through the optimization objective function under each working condition, the optimal operation plan of the key equipment in the LNG receiving terminal under each working condition in the operation space is obtained, scientifically and systematically clarifying the actual operation performance and the actual efficient operation interval of each key equipment in the LNG receiving terminal, and reducing the operation cost of the LNG receiving terminal.

[0047] For the key equipment in the LNG receiving station under each working condition, the controllable key parameters corresponding to each key equipment can be determined. According to the historical operation values of each controllable key parameter in the historical operation big data, the value range of each controllable key parameter can be determined. According to all possible numerical combinations of all relevant controllable key parameters in the LNG receiving station under each working condition, all possible operation schemes of the LNG receiving station under each working condition can be determined, that is, the operation space of the LNG receiving station under each working condition. The optimization objective function under each working condition can be constructed using the LNG processing cost optimization model. The purpose of constructing the optimization objective function under each working condition is to minimize the processing cost of the LNG receiving station. Specifically, a genetic algorithm can be used to construct the LNG processing cost optimization model. The LNG processing cost optimization model can encode the parameters of the operation scheme, and the encoding methods can be binary encoding method, floating-point encoding method, symbolic encoding method, etc. Then, the LNG processing cost optimization model randomly initializes a population, and the individuals in the population represent an operation scheme under each working condition. Then, the LNG processing cost optimization model establishes an optimization objective function to judge the processing cost of each operation scheme in the operation space. The LNG processing cost optimization model can select several operation schemes with low processing costs from the operation space with a certain probability and continuously generate new operation schemes through crossover and mutation operations. By minimizing the optimization objective function under each working condition and through multiple iterations, the LNG processing cost optimization model can obtain the optimal operation scheme.

[0048] The following provides a specific embodiment of this specification:

[0049] By analyzing the historical operation big data of a certain LNG receiving station, it is determined that the main factors affecting the operation cost of the LNG receiving station are the energy consumption and material consumption of key equipment, including power consumption, fuel gas consumption, etc., with power consumption being the main one. Among them, key equipment includes unloading arms, storage tanks, BOG compressors, recondensers, LNG low-pressure pumps, LNG high-pressure pumps, seawater pumps, vaporizers, and cold insulation circulation pipelines. The corresponding key parameters include uncontrollable key parameters and controllable key parameters. Controllable key parameters include the start-stop state of key equipment, unloading speed, cold insulation circulation volume, BOG compressor inlet pressure, BOG compressor temperature, BOG compressor outlet pressure, recondenser spray volume, recondenser pressure, and recondenser liquid level, LNG low-pressure pump flow rate, LNG high-pressure pump flow rate, seawater pump flow rate, vaporizer LNG flow rate, and vaporizer seawater flow rate. Uncontrollable key parameters include whether the ship has been unloaded, season, the pressure of the incoming LNG, the temperature of the incoming LNG, the composition of the incoming LNG, the LNG liquid level in the storage tank, the LNG density in the storage tank, the LNG pressure in the storage tank, the liquid external output volume, the gaseous external output volume, the external output pressure, the seawater pump tide difference, the seawater inlet pressure, and the seawater inlet temperature. Uncontrollable key parameters are usually used to divide working conditions and known input conditions, and controllable key parameters are usually the parameters that are mainly adjusted for cost reduction and efficiency improvement. The daily operation mode of the LNG receiving station is divided according to the working conditions of each day, and an energy-saving and cost-reducing operation plan is proposed for each working condition. Select the working condition when there is no ship unloading, in summer, the storage tank pressure is 16 - 17 kPaG, rich liquid, the external output pressure is 7.5 MPa, and the external output volume is 1.5×104 Nm3 / d.

[0050] 1. Obtain the historical operation big data of the LNG receiving station under the given working condition and perform preprocessing. The preprocessing includes cleaning the data, such as deactivating and abnormal points, unifying and standardizing different physical quantities, and at the same time determining the upper and lower limits of the historical data values of each key parameter in the historical operation big data under the given working condition, and combining with the on-site process operation specifications to provide a feasible change range for the operation optimization of controllable key parameters.

[0051] 2. Based on the historical operation big data of the LNG receiving station under the given working condition, establish performance prediction models for each key equipment of the LNG receiving station. Use neural network algorithms to establish energy consumption models for key equipment such as various pumps, compressors, recondensers, and vaporizers. Specifically, use the GA-BP genetic-neural network algorithm to establish a performance prediction model for the energy consumption of the LNG high-pressure pump based on the inlet and outlet pressures, inlet temperature, and flow rate of the LNG low-pressure pump.

[0052] The function expression for the relationship between the inlet and outlet pressures and flow rate of the LNG and the energy consumption of the LNG low-pressure pump established by using the BP neural network can be expressed as:

[0053] e LP,YC =f(p LP,in ,pLP,out , m LP );

[0054] Among them, e LP,YC is the predicted power consumption value for the low-pressure pump to process 10,000 m³ of natural gas, with the unit of kW·h / 10 4 Nm 3 ; p LP,in , p LP,out are the pressures at the inlet and outlet of the LNG low-pressure pump respectively, with the unit of kPa; m LP is the flow rate of the LNG low-pressure pump, with the unit of 10 4 Nm 3 / h.

[0055] Figure 4 is the comparison between the predicted value and the actual value of the unit energy consumption of LNG low-pressure pump B. Figure 5 is the distribution of the relative error of the unit energy consumption prediction model of LNG low-pressure pump B.

[0056] 3. Establish an actual processing cost model for the LNG receiving terminal to process 10,000 m³ of natural gas. Based on historical big data, according to the operating mechanism of key equipment and the law of energy and mass conservation, taking the start-stop and flow rate distribution of corresponding key equipment under different working conditions, combined with key information such as unit energy consumption cost and operation and maintenance cost as input variables, and taking the actual cost of processing 10,000 m³ of natural gas as the output variable to establish an actual processing cost model, and calculate the actual cost value of processing 10,000 m³ of natural gas.

[0057] The actual cost of the LNG receiving terminal to process 10,000 m³ of natural gas is expressed as the ratio of the actual cost of the operation of the key equipment of the LNG receiving terminal to the amount of exported natural gas, and is identified by C SJ , and the calculation expression is:

[0058]

[0059] Among them, M LNG is the amount of exported natural gas of the LNG receiving terminal per day, with the unit of 10 4 Nm 3 / h; e i,SJ is the various energy consumption and material consumption amounts actually consumed by the key equipment to process a unit of material, with the unit of kW·h / 10 4 Nm 3 , and the unit of fuel gas is t / 10 4 Nm 3 etc.; a i is the unit price of purchasing electricity and fuel gas and other energy or materials by the LNG receiving terminal; b i is the unit price evenly distributed to each day for the maintenance cost of each key equipment turned on at the LNG receiving terminal.

[0060] 4. Based on the performance prediction model of the key equipment of the LNG receiving terminal, according to the entire process operation mechanism of the LNG receiving terminal and the law of conservation of energy and mass, combined with the unit energy consumption cost and operation and maintenance cost, a processing cost prediction model for the LNG receiving terminal to process 10,000 cubic meters of natural gas is established. Under the same input conditions, the predicted value calculated by the processing cost prediction model can reproduce the actual processing cost value calculated by the actual processing cost model with high precision.

[0061] The predicted processing cost of the processing cost prediction model for the LNG receiving terminal to process 10,000 cubic meters of natural gas is denoted as C YC and the calculation expression is:

[0062]

[0063] where M LNG is the daily output of natural gas transported out of the LNG receiving terminal, with the unit of 10 4 Nm 3 / h; E i,YC is the various energy consumption and material consumption quantities consumed by the key equipment calculated according to the operating conditions using the performance prediction model of each key equipment; a i is the unit price of energy or materials such as electricity purchased and fuel gas purchased by the LNG receiving terminal; b i is the unit price evenly distributed to each day for the maintenance cost of each key equipment started in the LNG receiving terminal.

[0064] 5. Establish an optimization model for the processing cost of the LNG receiving terminal to process 10,000 cubic meters of natural gas. Based on the optimization model for the processing cost of the LNG receiving terminal to process 10,000 cubic meters of natural gas, the artificial intelligence algorithm particle swarm method is used for modeling. Taking the output volume, unit operation cost, maintenance cost, etc. under different operating conditions as the model input variables, and the optimized value of the processing cost of the LNG receiving terminal to process 10,000 cubic meters of natural gas as the model output variable, and at the same time determining the start-stop and flow distribution of the key equipment, providing optimization guidance for cost reduction and efficiency improvement on site in the LNG receiving terminal. The basic function of the optimization model is shown in the following formula:

[0065]

[0066] Y = 1 or Y = 0, representing the start / stop state of a certain key device. In the processing cost optimization model, the parallel devices should satisfy the mass conservation, and the key operating parameters of the devices should meet the ex-factory performance and on-site operating specifications. Table 1 shows the operating ranges of the key parameters of the low-pressure pump and high-pressure pump in the embodiments. Table 2 shows the comparison between the actual value and the optimized value of the cost of processing 10,000 cubic meters of natural gas in the LNG receiving station under the embodiment conditions, as well as the start / stop and flow distribution of the key devices. The LNG low-pressure pump originally operated with pumps B and Q, and the flow distribution is shown in Table 2. After optimization using the processing cost optimization model, it is recommended to start LNG low-pressure pumps A and M, and the flow distribution is shown in Table 2. Similarly, the optimization model provides optimization suggestions for the start / stop schemes and flow distribution of the high-pressure pump and seawater pump. After optimization, the system can reduce the cost by 5.8%.

[0067] Table 1

[0068]

[0069] Table 2

[0070]

[0071] Based on the above method for determining the operation plan of the LNG receiving station, this specification also presents an embodiment of the device for determining the operation plan of the LNG receiving station. As Figure 6 shown, the device for determining the operation plan of the LNG receiving station may specifically include the following modules:

[0072] An acquisition module 601, which can be used to acquire the historical operation big data of the LNG receiving station under each working condition.

[0073] A construction module 602, which can be used to construct a performance prediction model of the key devices in the LNG receiving station under each working condition according to the historical operation big data.

[0074] An establishment module 603, which can be used to establish a processing cost prediction model of the LNG receiving station under each working condition based on the performance prediction model of the key devices in the LNG receiving station under each working condition.

[0075] An optimization module 604, which can be used to optimize the operation plan of the key devices in the LNG receiving station under each working condition based on the processing cost prediction model under each working condition.

[0076] In some embodiments, the above historical operation big data includes key parameters and energy consumption and material consumption data; the key parameters include controllable key parameters and uncontrollable key parameters; the key equipment includes at least one of a loading arm, a storage tank, a BOG compressor, a recondenser, an LNG low-pressure pump, an LNG high-pressure pump, a seawater pump, a vaporizer, and a cold insulation circulation pipeline; the controllable key parameters include at least one of the start-stop state of the key equipment, the unloading speed, the cold insulation circulation volume, the inlet pressure of the BOG compressor, the temperature of the BOG compressor, the outlet pressure of the BOG compressor, the spray volume of the recondenser, the pressure of the recondenser, the liquid level of the recondenser, the flow rate of the LNG low-pressure pump, the flow rate of the LNG high-pressure pump, the flow rate of the seawater pump, the LNG flow rate of the vaporizer, and the seawater flow rate of the vaporizer; the uncontrollable key parameters include at least one of whether the ship has been unloaded, the season, the pressure of the incoming LNG, the temperature of the incoming LNG, the components of the incoming LNG, the LNG liquid level in the storage tank, the LNG density in the storage tank, the LNG pressure in the storage tank, the liquid external output volume, the gas external output volume, the external output pressure, the tidal difference of the seawater pump, the seawater inlet pressure, and the seawater inlet temperature; the energy consumption and material consumption data includes at least one of fuel gas consumption, nitrogen consumption, electric power, current, voltage, operation time, electricity charge, capacity charge, gas charge, and maintenance cost.

[0077] In some embodiments, the above acquisition module 601 may specifically be used to divide the operation scenarios of the LNG receiving terminal based on the uncontrollable key parameters in the historical operation big data.

[0078] In some embodiments, the above construction module 602 may specifically be used to use the corresponding key parameters of the key equipment in the historical operation big data of each scenario as input data and use the corresponding energy consumption and material consumption data of the key equipment in the historical operation big data of each scenario as output data to construct a performance prediction model of the key equipment under each scenario.

[0079] In some embodiments, the above establishment module 603 may specifically be used to obtain the basic energy consumption and material consumption data of the LNG receiving terminal under each scenario; based on the basic energy consumption and material consumption data of the LNG receiving terminal under each scenario, the corresponding energy consumption and material consumption data of the key equipment in the LNG receiving terminal, and the law of conservation of energy and mass, construct the actual processing cost model of the LNG receiving terminal under each scenario.

[0080] In some embodiments, the above establishment module 603 may specifically further be used to establish a processing cost prediction model of the LNG receiving terminal under each scenario based on the actual processing cost model of the LNG receiving terminal under each scenario, the performance prediction model of the key equipment in the LNG receiving terminal, and the basic energy consumption and material consumption data of the LNG receiving terminal.

[0081] In some embodiments, the above optimization module 604 may specifically be configured to construct an LNG processing cost optimization model for each operating condition based on the processing cost prediction model for each operating condition; and optimize the operation plan of key equipment in the LNG receiving terminal based on the LNG processing cost optimization model for each operating condition.

[0082] In some embodiments, the above optimization module 604 may also specifically be configured to determine the operating space of the LNG receiving terminal for each operating condition based on the controllable key parameters corresponding to the key equipment in the LNG receiving terminal for each operating condition; where the operating space represents the set of all possible operation plans of the key equipment in the LNG receiving terminal for each operating condition; construct an optimization objective function for each operating condition based on the LNG processing cost optimization model for each operating condition; and obtain the optimal operation plan of the key equipment in the LNG receiving terminal for each operating condition in the operating space based on the optimization objective function for each operating condition.

[0083] It should be noted that the units, devices, or modules described in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. For the convenience of description, when describing the above devices, they are divided into various modules according to functions and described separately. Of course, when implementing this specification, the functions of each module may be implemented in one or more software and / or hardware, or the modules implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other may be through some interfaces, and the indirect couplings or communication connections of the devices or units may be in electrical, mechanical, or other forms.

[0084] As can be seen from the above, based on the device for determining the operation plan of the LNG receiving terminal provided in the embodiments of this specification, the historical operation big data of the LNG receiving terminal for each operating condition can be obtained; based on the historical operation big data, a performance prediction model of the key equipment in the LNG receiving terminal for each operating condition can be constructed; based on the performance prediction model of the key equipment in the LNG receiving terminal for each operating condition, a processing cost prediction model of the LNG receiving terminal for each operating condition can be established; and based on the processing cost prediction model for each operating condition, the operation plan of the key equipment in the LNG receiving terminal for each operating condition can be optimized. Compared with the existing methods, based on the processing cost prediction model for each operating condition, the actual operation performance and the actual efficient operation range of each key equipment in the LNG receiving terminal can be more scientifically and systematically determined, thereby reducing the operation cost of the LNG receiving terminal.

[0085] The embodiments of this specification also provide a computer device for a method of determining an operation plan for an LNG receiving terminal, including a processor and a memory for storing instructions executable by the processor. When specifically implemented, the processor may execute the following steps according to the instructions: Obtain the historical operation big data of the LNG receiving terminal under each working condition; construct a performance prediction model for key equipment in the LNG receiving terminal under each working condition based on the historical operation big data; establish a processing cost prediction model for the LNG receiving terminal under each working condition based on the performance prediction model of the key equipment in the LNG receiving terminal under each working condition; optimize the operation plan of the key equipment in the LNG receiving terminal under each working condition based on the processing cost prediction model under each working condition.

[0086] To be able to more accurately complete the above instructions, refer to Figure 7 As shown, the embodiments of this specification also provide another specific computer device 700. Among them, the computer device 700 includes a network communication port 701, a processor 702, and a memory 703. The above structures are connected by internal cables so that each structure can perform specific data interactions.

[0087] The processor 702 can specifically be used to obtain the historical operation big data of the LNG receiving terminal under each working condition; construct a performance prediction model for key equipment in the LNG receiving terminal under each working condition based on the historical operation big data; establish a processing cost prediction model for the LNG receiving terminal under each working condition based on the performance prediction model of the key equipment in the LNG receiving terminal under each working condition; optimize the operation plan of the key equipment in the LNG receiving terminal under each working condition based on the processing cost prediction model under each working condition.

[0088] The memory 703 can specifically be used to store the corresponding instruction programs.

[0089] In this embodiment, the network communication port 701 can be bound to different communication protocols, so as to send or receive different data. For example, the network communication port can be a virtual port responsible for web data communication, or a port responsible for FTP data communication, or a port responsible for email data communication. In addition, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it can also be a Bluetooth chip.

[0090] In this embodiment, the processor 702 can be implemented in any suitable manner. For example, the processor can take the form of, for example, a microprocessor or a processor, a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and a form embedded microcontroller, etc. This specification does not make a limitation.

[0091] In this embodiment, the memory 703 can include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function without a physical form is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, a TF card, etc.

[0092] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0093] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby the instructions executed on the computer or other programmable apparatus provide steps for realizing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for realizing the functions specified in one block or a plurality of blocks

[0096] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is only for the specific embodiments of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining the operation plan of an LNG receiving terminal, characterized in that, Including: Obtain the historical operation big data of the LNG receiving terminal under each working condition; Construct a performance prediction model for key equipment in the LNG receiving terminal under each working condition according to the historical operation big data; Establish a processing cost prediction model for the LNG receiving terminal under each working condition based on the performance prediction model of key equipment in the LNG receiving terminal under each working condition; Optimize the operation plan of key equipment in the LNG receiving terminal under each working condition based on the processing cost prediction model under each working condition.

2. The method according to claim 1, wherein The historical operation big data includes key parameters and energy consumption and material consumption data; The key parameters include controllable key parameters and uncontrollable key parameters; The key equipment includes at least one of a discharge arm, a storage tank, a BOG compressor, a recondenser, an LNG low-pressure pump, an LNG high-pressure pump, a seawater pump, a vaporizer, and a cold insulation circulation pipeline; The controllable key parameters include at least one of the start-stop state of key equipment, the discharge speed, the cold insulation circulation volume, the inlet pressure of the BOG compressor, the temperature of the BOG compressor, the outlet pressure of the BOG compressor, the spray volume of the recondenser, the pressure of the recondenser, the liquid level of the recondenser, the flow rate of the LNG low-pressure pump, the flow rate of the LNG high-pressure pump, the flow rate of the seawater pump, the LNG flow rate of the vaporizer, and the seawater flow rate of the vaporizer; The uncontrollable key parameters include at least one of whether the ship has been unloaded, the season, the pressure of the incoming LNG, the temperature of the incoming LNG, the components of the incoming LNG, the LNG liquid level in the storage tank, the LNG density in the storage tank, the LNG pressure in the storage tank, the liquid external output volume, the gaseous external output volume, the external output pressure, the tidal difference of the seawater pump, the seawater inlet pressure, and the seawater inlet temperature; The energy consumption and material consumption data includes at least one of fuel gas consumption, nitrogen consumption, electric power, current, voltage, operation time, electricity charge, capacity charge, gas charge, and maintenance cost.

3. The method according to claim 1, characterized in that Before obtaining the historical operation big data of the LNG receiving terminal under each working condition, it further includes: Based on the uncontrollable key parameters in the historical operation big data, conduct a working condition division on the operation plan of the LNG receiving terminal.

4. The method according to claim 1, characterized in that The constructing a performance prediction model for key equipment in the LNG receiving terminal under each working condition according to the historical operation big data includes: Use the corresponding key parameters of key equipment in the historical operation big data of each working condition as input data and use the corresponding energy consumption and material consumption data of key equipment in the historical operation big data of each working condition as output data to construct a performance prediction model for key equipment under each working condition.

5. The method according to claim 1, wherein The method further includes: Obtain the basic energy consumption and material consumption data of the LNG receiving terminal under each working condition; Construct an actual processing cost model for the LNG receiving terminal under each working condition based on the basic energy consumption and material consumption data of the LNG receiving terminal under each working condition, the corresponding energy consumption and material consumption data of key equipment in the LNG receiving terminal, and the law of conservation of energy and mass.

6. The method according to claim 5, wherein The establishing a processing cost prediction model for the LNG receiving terminal under each working condition based on the performance prediction model of key equipment in the LNG receiving terminal under each working condition includes: Based on the actual processing cost model of the LNG receiving terminal under each working condition, the performance prediction model of key equipment in the LNG receiving terminal, and the basic energy consumption and material consumption data of the LNG receiving terminal, a processing cost prediction model of the LNG receiving terminal under each working condition is established.

7. The method according to claim 1, characterized in that Based on the processing cost prediction model under each of the above-mentioned working conditions, the operation schemes of key equipment in the LNG receiving terminal under each working condition are optimized, including: Based on the processing cost prediction model under each of the above-mentioned working conditions, an LNG processing cost optimization model under each working condition is constructed; Based on the LNG processing cost optimization model under each of the above-mentioned working conditions, the operation schemes of key equipment in the LNG receiving terminal are optimized.

8. The method according to claim 7, wherein Based on the LNG processing cost optimization model under each of the above-mentioned working conditions, the operation schemes of key equipment in the LNG receiving terminal are optimized, including: Based on the corresponding controllable key parameters of key equipment in the LNG receiving terminal under each working condition, the operation space of the LNG receiving terminal under each working condition is determined; the operation space represents the set of all possible operation schemes of key equipment in the LNG receiving terminal under each working condition; Based on the LNG processing cost optimization model under each of the above-mentioned working conditions, an optimization objective function under each working condition is constructed; Based on the optimization objective function under each of the above-mentioned working conditions, the optimal operation scheme of key equipment in the LNG receiving terminal under each working condition in the operation space is obtained.

9. An operating scheme determination device for an LNG receiving terminal, characterized in that The device includes: An acquisition module for acquiring the historical operation big data of the LNG receiving terminal under each working condition; A construction module for constructing a performance prediction model of key equipment in the LNG receiving terminal under each working condition according to the historical operation big data; An establishment module for establishing a processing cost prediction model of the LNG receiving terminal under each working condition based on the performance prediction model of key equipment in the LNG receiving terminal under each working condition; An optimization module for optimizing the operation schemes of key equipment in the LNG receiving terminal under each working condition based on the processing cost prediction model under each working condition.

10. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method described in any one of claims 1-8 is implemented.

Images