Bidirectional tidal unit full-operation operation method, device, electronic equipment and unit

Abstract

The present application discloses a method, device, electronic equipment and unit for operating a bidirectional tidal unit under all working conditions. The method includes obtaining target control data of the bidirectional tidal unit within a tidal cycle, the target control data including the tidal start and end times of the tidal cycle and the operating water level of the bidirectional tidal unit at each time within the tide; inputting the target control data into a neural network model, and determining the target operating time period of each working condition corresponding to the target control data through the correspondence between the control data and the operating time period of each working condition in the neural network model; the operating time period is the operating time period of the bidirectional tidal unit in each working condition within the tidal cycle; and controlling the bidirectional tidal unit to operate within the tidal cycle according to the target operating time period of each working condition. Based on this, the present application can determine the target operating time period for maximizing the utilization of tidal energy, and use it to control the bidirectional tidal unit.

Description

Technical Field

[0001] The present application belongs to the technical field of tidal energy development, and in particular relates to a method, device, electronic equipment and unit for operating a bidirectional tidal unit under all working conditions. Background Art

[0002] In the process of generating electricity using a bidirectional tidal turbine, multiple different operating conditions will be switched in sequence during a complete tidal cycle. That is to say, the complete tidal cycle will be divided into multiple corresponding operating time periods according to different operating conditions.

[0003] In the control technology of related bidirectional tidal turbines, the operating time periods of various working conditions, that is, the start and end times of each working condition, are often allocated based on the controller's historical experience. However, allocating operating time periods based on experience often makes it difficult to fully utilize tidal energy, that is, it is difficult to maximize the difference between the energy consumption and power generation of the bidirectional tidal turbine within a complete tidal cycle. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, electronic equipment and unit for operating a bidirectional tidal turbine under all working conditions, which can operate in a target operating period with the maximum total power generation and total energy consumption, thereby maximizing the utilization of tidal energy.

[0005] In a first aspect, an embodiment of the present application provides a method for operating a bidirectional tidal turbine in all working conditions, the method comprising:

[0006] Obtain target control data of the bidirectional tidal turbine within a tidal cycle, the target control data including the tidal start and end times of the tidal cycle and the operating water level of the bidirectional tidal turbine at each time within the tidal cycle;

[0007] The target control data is input into the neural network model, and the target operating time period of each operating condition corresponding to the target control data is determined based on the correspondence between the control data and the operating time period of each operating condition in the neural network model; the operating time period is the operating time period of the bidirectional tidal turbine under each operating condition within the tidal cycle;

[0008] The bidirectional tidal turbine is controlled to operate within the tidal cycle according to the target operating time period of each operating condition.

[0009] Before inputting the target control data into the neural network model, the method further includes:

[0010] Acquire multiple historical control data within the tidal cycle, including the start and end time of the tidal cycle, and the tidal water level and reservoir water level corresponding to each time within the tidal cycle;

[0011] Inputting historical control data into the initial neural network model;

[0012] Through the initial neural network model, the tide start and end times are divided according to each working condition, and multiple groups of operating time periods for each working condition are obtained;

[0013] For each operating period of each operating condition, the following steps are performed: the average operating water level within the corresponding operating period is calculated based on the tidal water level and reservoir water level corresponding to the start and end times of the operating period of each operating condition; the target unit flow rate at the average operating water level is determined based on the preset correspondence between the operating water level and the unit flow rate; the output power is calculated based on the average operating water level and the target unit flow rate, and the power generation and energy consumption of the operating period corresponding to each operating condition are calculated based on the output power;

[0014] Calculate the total power generation and total energy consumption of each group of working conditions, and calculate the difference between the total power generation and total energy consumption;

[0015] The corresponding relationship between the operating time period of each working condition corresponding to the maximum difference and the historical control data is obtained, and the corresponding relationship between the control data and the operating time period of each working condition is obtained, and the trained neural network model is obtained.

[0016] The operating conditions include forward power generation, reverse power generation, forward pumping and reverse pumping.

[0017] Among them, the various operating conditions also include forward water discharge conditions, reverse water discharge conditions and shutdown conditions. The power generation and energy consumption of the forward water discharge conditions, reverse water discharge conditions and shutdown conditions are all zero.

[0018] Furthermore, after determining the target unit flow rate of the average operating water level based on the preset correspondence between the operating water level and the unit flow rate, the method further includes:

[0019] Based on the preset correspondence between water level and storage capacity, determine the target storage capacity corresponding to the reservoir water level at the start and end times of the operation period of each operating condition;

[0020] Calculate the difference in target storage capacity between the start and end times of the operating period of each operating condition to obtain the corresponding difference in reservoir capacity;

[0021] When the difference between the reservoir capacity and the corresponding target unit flow is less than or equal to a preset water balance threshold, the output power is calculated based on the average operating water level and the target unit flow; or

[0022] When the difference between the reservoir capacity and the corresponding target unit flow is greater than the water balance threshold, a group of operating time periods of various working conditions corresponding to the target unit flow is deleted.

[0023] The method further includes:

[0024] Output the total power generation and total energy consumption corresponding to the maximum difference, as well as a corresponding set of target operating time periods for each operating condition.

[0025] The method further includes:

[0026] The simulation system is used to simulate the execution of the bidirectional tidal turbine within the tidal cycle according to the target operating period of each operating condition, and the simulated total power generation and simulated total energy consumption are output;

[0027] When a first difference between the total power generation and the simulated total power generation is less than a preset first verification threshold, and / or a second difference between the total energy consumption and the simulated total energy consumption is less than a preset second verification threshold, it is determined that the neural network model is valid.

[0028] In a second aspect, an embodiment of the present application provides a bidirectional tidal turbine operating device for all operating conditions, the device comprising:

[0029] An acquisition module is used to acquire target control data of the bidirectional tidal generator set within a tidal cycle, wherein the target control data includes the tidal start and end times of the tidal cycle and the operating water level of the bidirectional tidal generator set at each time within the tidal cycle;

[0030] a target operating period determination module, configured to input the target control data into a neural network model, and determine a target operating period for each operating condition corresponding to the target control data based on a correspondence between the control data and the operating period for each operating condition in the neural network model; the operating period being the operating period of the bidirectional tidal turbine in each operating condition within the tidal cycle;

[0031] The control module is used to control the bidirectional tidal generator set to operate within the tidal cycle according to the target operating time period of each working condition.

[0032] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising:

[0033] a processor and a memory storing computer program instructions;

[0034] When the processor executes the computer program instructions, it implements the full-operation method of the bidirectional tidal turbine as described in any of the above items.

[0035] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, a method for operating a bidirectional tidal turbine under full working conditions as described in any of the preceding items is implemented.

[0036] In a fifth aspect, an embodiment of the present application provides a method for operating a bidirectional tidal turbine under full working conditions as described in any of the preceding items, which, when executed by a processor of an electronic device, causes the electronic device to execute instructions in a computer program product.

[0037] In a sixth aspect, an embodiment of the present application further provides a bidirectional tidal generator set, comprising an electronic device, which executes the full-operation method of the bidirectional tidal generator set as described above.

[0038] The operation method, device, electronic equipment and unit of the bidirectional tidal unit under all working conditions of the embodiments of the present application are based on a pre-trained neural network. Since the pre-trained neural network pre-constructs the correspondence between the control data and the operating time periods of each working condition, after the control data is input into the pre-trained neural network, the pre-trained neural network can predict the target operating time period corresponding to the control data, so that when the unit operates according to the target operating time period within the tidal cycle, the difference between the total power generation and total energy consumption of the unit can be minimized, thereby maximizing the utilization of tidal energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] Figure 1 This is a schematic diagram of water level and working conditions within a tidal cycle provided by an embodiment of the present application;

[0041] Figure 2 This is a flow chart of a method for operating a bidirectional tidal turbine under all working conditions provided by an embodiment of the present application;

[0042] Figure 3 This is a flowchart of obtaining and verifying a neural network model provided in an embodiment of the present application;

[0043] Figure 4 is a characteristic curve diagram of the unit provided in the embodiment of the present application;

[0044] Figure 5 This is a schematic diagram of the power generation effect provided by the embodiment of the present application; Figure 6 This is a structural diagram of a full-operation-condition operating device of a bidirectional tidal turbine provided in an embodiment of the present application;

[0045] Figure 7 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0047] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0048] As described in the background technology section, the relevant bidirectional tidal turbine operation technology under all working conditions is still difficult to meet the needs of actual work.

[0049] In the process of generating electricity using a bidirectional tidal turbine, multiple different operating conditions will be switched in sequence during a complete tidal cycle, such as Figure 1 As shown in FIG, in a complete tidal cycle, the bidirectional tidal turbine needs to sequentially undergo the forward power generation condition, the forward water discharge condition, the forward pumping condition, and the shutdown condition, and then sequentially undergo the reverse power generation condition, the reverse water discharge condition, the reverse pumping condition, and the shutdown condition.

[0050] Among them, in the above-mentioned forward power generation condition, forward water discharge condition, forward pumping condition, reverse power generation condition, reverse water discharge condition, reverse pumping condition and shutdown condition, the forward power generation condition and the reverse power generation condition are to do work to the power grid outside the bidirectional tidal unit to generate electricity for the external power grid. Therefore, the work done to the outside by the forward power generation condition and the reverse power generation condition is the power generation; and the forward pumping condition and the reverse pumping condition are to do work to the reservoir or seawater area to pump water from one side of the bidirectional tidal unit to the other side. Therefore, the work done to the outside by the forward pumping condition and the reverse pumping condition is energy consumption.

[0051] When switching between various operating conditions, it is necessary to assign a start and end time for each operating condition, that is, the operating time period of each operating condition, so that the bidirectional tidal turbine can operate in each operating condition in a set of assigned operating time periods.

[0052] The two different operating time periods will result in different total energy consumption and total power generation of the bidirectional tidal turbine within the same tidal cycle. Only when the difference between total power generation and total energy consumption is the largest can the tidal energy be fully utilized to the greatest extent.

[0053] However, in the control technology of related bidirectional tidal turbines, a corresponding set of operating time periods is often assigned to each operating condition based on the controller's historical experience. This method makes it difficult to maximize the difference between the energy consumption and power generation of the bidirectional tidal turbine within a complete tidal cycle, making it difficult to fully utilize tidal energy.

[0054] For example, if the operating period of the forward discharge condition or the reverse discharge condition is too short, the operating time of the next forward pumping condition or the reverse pumping condition will need to be extended, so that the bidirectional tidal unit will need to consume additional energy to complete the forward pumping condition or the reverse pumping condition with an extended operating period.

[0055] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, electronic equipment and unit for operating a bidirectional tidal turbine under all working conditions.

[0056] In this application, one side of the bidirectional tidal generator set is a tidal water area, such as a seawater area, and the water level on this side is the tidal water level of the water area; the other side is a reservoir water area, and the water level on this side is the reservoir water level.

[0057] The following is a detailed description of the operating method of the bidirectional tidal turbine under all working conditions provided by the embodiment of the present application in conjunction with the accompanying drawings.

[0058] Figure 2 A flow chart of a method for operating a bidirectional tidal turbine under full working conditions provided by an embodiment of the present application is shown.

[0059] refer to Figure 2 The method for operating a bidirectional tidal turbine in full working conditions according to one embodiment of the present application includes the following steps 201-203.

[0060] S201. Obtain target control data of a bidirectional tidal turbine within a tidal cycle, wherein the target control data includes the tidal start and end times of the tidal cycle and the operating water level of the bidirectional tidal turbine at each time within the tidal cycle.

[0061] In this embodiment, for a bidirectional tidal generator set that will operate within a predetermined tidal cycle, in order to determine the target operating period for the tidal cycle, the target control data of the bidirectional tidal generator set within the tidal cycle can be obtained for use in a neural network model to predict the target operating period.

[0062] The target control data may specifically include the start and end times of the tidal cycle and the operating water level within the tidal cycle.

[0063] The operating water level at each time is the difference between the tidal water level and the reservoir water level at each time.

[0064] In a specific example, when obtaining the tidal water level and the reservoir water level, the historical periodic change data of the tidal water level can be obtained, and the tidal water level change curve can be determined based on this; the historical periodic change data of the reservoir water level can be obtained, and the reservoir water level change curve can be determined based on this.

[0065] Based on this, the operating water level and tidal water level at any time, including the start and end time of the tide, can be determined through the tidal water level change curve and the reservoir water level change curve, and the difference between the tidal water level and the operating water level at that time can be determined as the operating water level at that time.

[0066] Figure 1 The tidal water level curve and reservoir water level curve are shown in Figure 1 As shown, the horizontal axis is time and the vertical axis is water level. The red curve is the tidal water level curve obtained based on the periodic changes in the tidal water level in history, which shows the changes in the tidal water level over time. The blue curve is the reservoir water level curve obtained based on the periodic changes in the reservoir water level in history, which shows the changes in the reservoir water level over time.

[0067] Based on this, for Figure 1 For the complete tidal cycle from abscissa 0 to abscissa 12, based on the tidal water level curve and the reservoir water level curve within the tidal cycle, the difference between the tidal water level and the reservoir water level at each time in the tidal cycle from abscissa 0 to abscissa 12 can be determined, that is, the operating water level.

[0068] In some examples, the target control data may include, in addition to the tidal start and end times and the operating water level of the tidal cycle, for example, the rated flow and rated power of the bidirectional tidal generator set.

[0069] S202. Input the target control data into a neural network model, and determine the target operating time period of each operating condition corresponding to the target control data through the correspondence between the control data and the operating time period of each operating condition in the neural network model; the operating time period is the operating time period of the bidirectional tidal unit in each operating condition within the tidal cycle.

[0070] In this embodiment, when the bidirectional tidal turbine operates within a tidal cycle, the operating time periods of each operating condition are taken as a group of operating time periods. Two different groups of operating time periods will result in different total power generation and total energy consumption of the bidirectional tidal turbine within the tidal cycle.

[0071] In order to fully utilize tidal energy within a tidal cycle, a set of target operating time periods can be adopted to maximize the difference between the total power generation and total energy consumption of the bidirectional tidal turbine within the tidal cycle, thereby maximizing the utilization of tidal energy.

[0072] In this step, in order to determine the target operating period corresponding to the target control data, based on the control data obtained in the previous step, the target control data can be input into the pre-trained neural network model for prediction, thereby obtaining the target operating period that maximizes the difference between total power generation and total energy consumption.

[0073] Among them, the pre-trained neural network model pre-constructs a correspondence between control data and a set of operating time periods. The correspondence can be specifically that the control data points to a set of operating time periods that can maximize the difference between the total power generation and total energy consumption of the bidirectional tidal unit within the tidal cycle, and it is used as a set of target operating time periods corresponding to the control data.

[0074] Based on this, after the control data is input into the pre-trained neural network model, the pre-trained neural network model can predict a set of target operating time periods corresponding to the control data according to the pre-constructed correspondence relationship therein.

[0075] S203: Control the bidirectional tidal turbine to operate within the tidal cycle according to the target operating time period of each operating condition.

[0076] Among them, each set of target operating time periods specifically represents the start and end time, or duration, of each operating condition.

[0077] In this step, based on a set of target operating time periods determined in the previous steps, the operation of the bidirectional tidal turbine under various working conditions can be scheduled using the set of target operating time periods within the corresponding tidal cycle.

[0078] exist Figure 1 In the example, when the bidirectional tidal turbine dispatches various operating conditions according to the target operating time period within the tidal cycle, the bidirectional tidal turbine can be controlled in the order of forward power generation condition, forward water discharge condition, forward water discharge condition, shutdown condition, reverse power generation condition, reverse water discharge condition, reverse pumping condition and shutdown condition, and the duration of each operating condition can be adjusted according to the target operating time period corresponding to each operating condition in a set of target operating time periods.

[0079] Based on this, the difference between the total power generation and the total energy consumption can be maximized when the bidirectional tidal turbine is operating within the tidal cycle.

[0080] Based on this, in this embodiment, since the pre-trained neural network model pre-constructs a correspondence between the control data and the operating time periods of each working condition, and the correspondence can be for the control data to point to a set of target operating time periods that maximize the difference between the total power generation and total energy consumption of the bidirectional tidal unit, the pre-trained neural network model can use the input control data to predict the corresponding target operating time periods, and then when the unit operates according to the target operating time periods within the tidal cycle, the difference between the total power generation and total energy consumption of the unit can be minimized.

[0081] In another embodiment of the present application, before using a pre-trained neural network model to predict each operating period of a bidirectional tidal turbine, in order to obtain a trained neural network model containing a corresponding relationship, multiple historical control data can be obtained, and multiple groups of operating periods can be determined for each historical control data through a preset initial neural network model. The total power generation and total energy consumption corresponding to each group of operating periods are calculated using each group of operating periods and the corresponding historical control data, thereby determining a group of operating periods with the largest difference between total power generation and total energy consumption among each group of operating periods corresponding to the historical control data, and constructing a corresponding relationship between the group of operating periods and the historical control data, thereby obtaining a trained neural network model.

[0082] Among them, each set of historical control data can specifically include: the tidal start and end time of a tidal cycle, the tidal water level and reservoir water level at each time within the tidal cycle. In some examples, each set of historical control data can also include the rated flow and rated power of the bidirectional tidal unit.

[0083] In this embodiment, Figure 3 It shows the specific process of obtaining the trained neural network model.

[0084] like Figure 3 As shown, when obtaining the tidal water level and reservoir water level in the historical control data, you can execute Figure 3 S301, determining the tidal water level and S302, determining the reservoir water level.

[0085] Specifically, the tidal water level at each time in the tidal cycle can be represented by a tidal water level curve, and the reservoir water level at each time can be represented by a reservoir water level curve.

[0086] In S301, the tidal water level at each time may be determined by querying a preset tidal water level curve; in S302, the reservoir water level at each time may be determined by querying a preset reservoir water level curve.

[0087] In this embodiment, based on the reservoir water level and tidal water level determined in the above steps, in order to construct the above correspondence in the initial neural network model, each set of the above historical control data can be input into the initial neural network, and the tidal cycle in each set of historical control data can be divided into multiple groups of operating time periods, that is, executing Figure 3 S303 in the above step divides the operation time periods.

[0088] Specifically, for each tidal cycle, the order of forward power generation condition, forward water discharge condition, forward pumping condition, shutdown condition, reverse power generation condition, reverse water discharge condition, reverse pumping condition and shutdown condition can be used to divide each operating condition into its own corresponding operating time period, that is, the start and end time of each operating condition, and use it as a group of divided operating time periods.

[0089] Based on this, each tidal cycle can be divided into multiple operating time periods, thereby obtaining multiple groups of operating time periods corresponding to the tidal cycle.

[0090] Furthermore, based on the divided groups of operating time periods, a calculation relationship between the operating time periods, control data, total power generation and total energy consumption can be constructed in the initial neural network, thereby constructing a corresponding relationship between the target operating time periods and the target control data.

[0091] In this embodiment, since the operating period of each operating condition in each set of operating periods is a period of time within the tidal cycle rather than a moment, in order to establish the calculation relationship between the operating period, control data, total power generation and total energy consumption, it is necessary to first calculate the average operating water level within the operating period of each operating condition in each set of historical control data, that is, to perform Figure 3 In S304, the average operating water level is determined.

[0092] Specifically, in one example, for each set of historical control data, the water level difference between the reservoir water level and the tidal water level at any time within the tidal cycle can be used as the operating water level at that time, thereby determining the operating water level at each time within the tidal cycle.

[0093] Based on this, for the operating period corresponding to each working condition, the operating water levels at multiple times can be selected, and the average of the selected operating water levels can be calculated and used as the average operating water level of the operating period of the working condition.

[0094] In another example, when calculating the average running water level of each running period, the running water level at the start and end time of the running period may also be used to calculate the average running water level.

[0095] Specifically, the average operating water level can be calculated according to the following formula (1):

[0096]

[0097] in, represents the average operating water level during the operation period of the nth operating condition, t2 represents the end time of the operation period, t1 represents the start time of the operation period, Z ni Indicates the reservoir water level at the start or end time of the operating period of the nth operating condition, h ni The tidal water level representing the start time or end time of the operating period of the nth operating condition, wherein when the superscript i=1, it represents the start time of the operating period of the nth operating condition, and when the superscript i=2, it represents the end time of the operating period of the nth operating condition.

[0098] Based on this, the target unit flow corresponding to the average operating water level can be determined based on the corresponding relationship between the operating water level and the unit flow.

[0099] The unit flow rate represents the amount of water passing through the bidirectional tidal unit during the corresponding operating period.

[0100] In one example, the corresponding relationship between the operating water level and the unit flow rate can be determined by a preset unit characteristic curve.

[0101] The preset unit characteristic curve may specifically represent the numerical relationship between different operating water levels and unit flow of the corresponding bidirectional tidal unit at various times.

[0102] Figure 4 It is the unit characteristic curve that shows the relationship between the operating water level and flow rate.

[0103] Figure 4 In the coordinate system, the horizontal axis is the unit flow rate and the vertical axis is the operating water level. The positive value of the unit flow rate indicates the amount of water flowing from the reservoir to the seawater side, and the negative value indicates the amount of water flowing from the seawater side to the reservoir side. The operating water level is the reservoir water level minus the tidal water level. The positive value of the operating water level indicates the difference between the reservoir water level and the tidal water level, and the negative value of the operating water level indicates the difference between the reservoir water level and the tidal water level.

[0104] like Figure 4 As shown in the figure, during the forward power generation process, the operating water level and the unit flow change in real time. The unit flow increases from 0, and the corresponding operating water level also increases. After that, the unit flow begins to decrease, and the corresponding operating water level also decreases.

[0105] Furthermore, after the forward power generation condition is completed, the bidirectional tidal unit still maintains an operating water level greater than 0 and a corresponding unit flow, and enters the forward water discharge condition.

[0106] During the forward discharge operation, due to the offline idling of the bidirectional tidal unit, the water flows continuously and automatically from the reservoir side to the seawater side. There is a linear relationship between the unit flow and the operating water level. Therefore, as the forward discharge operation continues, the operating water level continues to decrease, and the corresponding unit flow also decreases. When the operating water level decreases to 0 or close to 0, the forward discharge operation ends and the forward pumping operation begins.

[0107] During the forward pumping condition, since the forward pumping condition is used to pump water from one side of the reservoir to the seawater side, there is a linear relationship between the unit flow and the operating water level. Therefore, as the forward pumping condition continues, the operating water level continues to increase, and the corresponding unit flow also increases. At the end of the forward pumping condition, the bidirectional tidal unit enters the shutdown condition with a certain operating water level and unit flow, and after entering the shutdown condition, the unit flow becomes 0.

[0108] At the end of the shutdown condition, the bidirectional tidal unit will first perform a hot standby process before entering the reverse power generation condition. During the hot standby process, the operating water level increases, while the unit flow remains unchanged at 0.

[0109] After the hot standby process is completed, the reverse power generation condition is started with the increased operating water level.

[0110] During the reverse power generation process, the operating water level and the unit flow change in real time. The unit flow increases from 0, and the corresponding operating water level also increases. Afterwards, the unit flow begins to decrease, and the corresponding operating water level also decreases.

[0111] Furthermore, after the reverse power generation condition is completed, the bidirectional tidal unit still maintains a non-zero operating water level and a corresponding unit flow, and enters a reverse discharge condition.

[0112] During the reverse discharge operation, due to the offline idling of the bidirectional tidal unit, the water flows continuously and automatically from the seawater side to the reservoir side. There is a linear relationship between the unit flow and the operating water level. Therefore, as the reverse discharge operation continues, the operating water level continues to decrease, and the corresponding unit flow also decreases. When the operating water level decreases to 0 or close to 0, the reverse discharge operation ends and the reverse pumping operation begins.

[0113] During the reverse pumping condition, since the reverse pumping condition is used to pump water from the seawater side to the reservoir side, there is a linear relationship between the unit flow and the operating water level. Therefore, as the reverse pumping condition continues, the operating water level continues to increase, and the corresponding unit flow also increases. At the end of the reverse pumping condition, the bidirectional tidal unit enters the shutdown condition with a certain operating water level and unit flow, and after entering the shutdown condition, the unit flow becomes 0.

[0114] At the end of the shutdown condition, the bidirectional tidal unit will first perform a hot standby process before entering the forward power generation condition. During the hot standby process, the operating water level increases, while the unit flow remains unchanged at 0.

[0115] After the hot standby process is completed, the forward power generation condition is started with the increased operating water level.

[0116] In some unit characteristic curves, the numerical relationship between the average operating water level of the corresponding bidirectional tidal unit within a period of time and the unit flow rate within the period of time can also be expressed.

[0117] Furthermore, by querying the unit characteristic curve, the target unit flow corresponding to the average operating water level in each operating period of the bidirectional tidal unit can be determined.

[0118] Furthermore, based on the determined average operating water level and target unit flow rate of each operating period, the output power of each operating period can be determined for each set of historical control data.

[0119] In one example, when determining the output power, the corresponding output power can be calculated based on a preset output power function using the average operating water level and target unit flow in each operating period, wherein the output power function represents the numerical calculation relationship between the output power, the average operating water level and the unit flow.

[0120] Specifically, the output power function can be expressed as the following formula (2):

[0121]

[0122] Among them, N T represents the output power, ρ represents the density of the water area, g represents the acceleration of gravity, Q T Indicates the unit flow rate, represents the average operating water level, and η represents the preset operating efficiency of the bidirectional tidal turbine.

[0123] In another example, the output power may also be determined by querying a preset unit characteristic curve.

[0124] The preset unit characteristic curve may include not only the numerical relationship between the operating water level and the unit flow, but also the output power, and may represent the numerical relationship between the average operating water level, the unit flow and the output power.

[0125] Based on this, the unit flow and output power corresponding to the average operating water level in each operating period can also be obtained from the unit characteristic curve.

[0126] Furthermore, for the operating period of each operating condition, the power generation and energy consumption of the operating condition during the operating period can be calculated using the output power determined above.

[0127] In this embodiment, both power generation and energy consumption can be regarded as the work done to the outside of the bidirectional tidal turbine with the output power during the operation period of the corresponding working condition. The power generation and energy consumption can be regarded as the work done to different objects respectively.

[0128] Accordingly, for the operating period of each operating condition, the product of the specific duration of the operating period and the corresponding output power can be used as the power generation or energy consumption of the operating condition during the operating period.

[0129] Based on this, when calculating the power generation, the power generation of the forward power generation condition and the reverse power generation condition in their respective operating periods can be calculated according to the following formula (3):

[0130] E T =N T ×|t2-t1| (3)

[0131] Among them, E T Indicates the power generation under forward power generation condition and / or reverse power generation condition in the corresponding operating period.

[0132] When calculating energy consumption, the energy consumption of the forward pumping condition and the reverse pumping condition in their respective operating periods can be calculated according to the following formula (4):

[0133] ε T =-N T ×|t2-t1| (4)

[0134] Among them, ε T It represents the energy consumption of forward pumping condition and reverse pumping condition in the corresponding operating period.

[0135] In one example, in the forward discharge condition and the reverse discharge condition, the bidirectional tidal turbine is in an offline idling state. At this time, the water flow can automatically flow from one side of the reservoir or seawater to the other side. Therefore, during the operation period of the forward pumping condition and the reverse pumping condition, the power generation and energy consumption of the bidirectional tidal turbine are both 0.

[0136] In one example, in a shutdown condition, the bidirectional tidal turbine is in a shutdown state, and the power generation and energy consumption of the bidirectional tidal turbine are both 0.

[0137] Based on the power generation and energy consumption of the operating time periods of each working condition determined above, for each set of operating time periods, the total power generation and total energy consumption in the corresponding tidal cycle when the bidirectional tidal turbine operates in each set of operating time periods can be calculated.

[0138] Specifically, when calculating the total power generation and total energy consumption of each group of operating time periods, for the bidirectional tidal unit operating in this group of operating time periods, the power generation corresponding to each corresponding operating condition can be accumulated to obtain the total power generation of the bidirectional tidal unit when operating in this group of operating time periods within the tidal cycle; and the energy consumption corresponding to each corresponding operating condition can be accumulated to obtain the total energy consumption of the bidirectional tidal unit when operating in this group of operating time periods within the tidal cycle.

[0139] In a specific example of calculating the total power generation and total energy consumption, for each set of operating time periods corresponding to any set of historical control data, the power generation of the forward power generation conditions and the reverse power generation conditions in the set of operating time periods can be accumulated and summed to obtain the total power generation of the set of operating time periods.

[0140] The energy consumption of the forward pumping condition and the reverse pumping condition in the group of operating time periods is accumulated and summed to obtain the total energy consumption of the group of operating time periods.

[0141] Furthermore, the difference between the total power generation and the total energy consumption can be calculated.

[0142] Based on this, the difference between the total power generation and the total energy consumption in each operating period corresponding to the set of historical control data can be calculated.

[0143] Based on the calculated difference between total power generation and total energy consumption, further Figure 3 In S305, a corresponding relationship is constructed in the initial neural network model.

[0144] Specifically, when constructing the corresponding relationship, the group of operating time periods with the largest difference among the groups of operating time periods corresponding to the group of historical control data can be determined, and this group of operating time periods can be used as the target operating time periods of the group of historical control data. The corresponding relationship between the group of target operating time periods and the group of historical control data can be associated, and this corresponding relationship can be used as the corresponding relationship between the control data and the operating time periods of each working condition, thereby completing Figure 3 S306 in which the trained neural network model is obtained.

[0145] Based on this, in this embodiment, based on the multiple groups of historical control data obtained, for each group of historical control data, by dividing the tidal cycle therein into multiple groups of operating time periods, the power generation and energy consumption of the operating condition can be calculated for the operating period of each operating condition in each group of operating time periods. Based on this, the total power generation and total energy consumption corresponding to each group of operating time periods can be determined, so that a group of operating time periods with the largest difference between total power generation and total energy consumption can be determined for each group of historical control data, and the association between the operating time period with the largest association difference and the historical control data can be achieved, so as to establish a corresponding relationship between the control data and the target operating time period for the initial neural network, and obtain a trained neural network.

[0146] Figure 5 The specific effect of the trained neural network model on power generation is further shown.

[0147] exist Figure 5 In the figure, the orange column mark indicates the predicted value of power generation predicted by the trained neural network model; the green column mark indicates the actual value of power generation obtained by dividing the operating time period of each operating condition based on historical experience instead of the target operating time period output by the trained neural network model; the purple column mark indicates the optimized value of power generation in actual operation of the target operating time period predicted by the trained neural network model.

[0148] like Figure 5 As shown in the figure, in the forward power generation condition, the actual value is the smallest, which is 6129kWh, the predicted value is higher than the actual value, which is 6190kWh, and the optimized value is the highest, which is 6753kWh.

[0149] In the reverse power generation condition, the actual value is the smallest, which is 4275kWh, the predicted value is higher than the actual value, which is 4296kWh, and the optimized value is the highest, which is 4504kWh.

[0150] Based on this, after excluding the losses caused by grid losses and other reasons, the actual value of total power generation is the smallest, which is 9808kWh. The predicted value of total power generation is higher than the actual value, which is 9857kWh, and the optimized value of total power generation is the highest, which is 10752kWh.

[0151] Therefore, the total power generation is optimal when the trained neural network model is used to output the target operating time period to control the operation of the bidirectional tidal turbine.

[0152] In another embodiment of the present application, after determining the average operating water level and target unit flow of the operating period of each operating condition, it is also possible to judge whether the operating period corresponding to the target unit flow is reasonable by comparing the reservoir capacity difference with the target unit flow.

[0153] Among them, the reservoir capacity refers to the amount of water in the reservoir.

[0154] In this embodiment, there is a preset corresponding relationship between the water level of the reservoir and the reservoir capacity, and the corresponding relationship can be specifically expressed as a reservoir capacity-water level curve.

[0155] Using this reservoir capacity-water level curve, the reservoir capacity at each time within the tidal cycle can be determined based on the reservoir water level.

[0156] That is, the target storage capacity at the start and end times of the operating period of each operating condition can be determined.

[0157] Based on this, the difference between the target storage capacity at the start time and the target storage capacity at the end time of the operation period of each working condition can be calculated and used as the difference in reservoir storage capacity.

[0158] Specifically, the difference in storage capacity can be calculated according to the following formula (5):

[0159] ΔV=|V n2 -V n1 |

[0160] Among them, ΔV represents the difference in storage capacity, V n2 Represents the reservoir capacity at the end of the operating period of the nth operating condition, V n1 Indicates the reservoir capacity at the start time of the operating period of the nth operating condition.

[0161] Among them, in an ideal situation, the target unit flow rate in the operating period of the corresponding working condition should be equal to the difference of the corresponding storage capacity. Due to factors such as errors, the difference between the target unit flow rate and the storage capacity should also be within a reasonable range.

[0162] Based on this, it can be verified whether the difference between the target unit flow and the storage capacity is within a reasonable range.

[0163] Specifically, during verification, a water balance threshold needs to be set in advance. For the operating time periods corresponding to each operating condition within each group of operating time periods, it can be determined whether the difference between its storage capacity and the corresponding target unit flow is less than or equal to the water balance threshold.

[0164] For any set of operating time periods, if the difference between the storage capacity of the operating time periods of each operating condition and the difference between the corresponding target unit flow rate is less than or equal to the water balance threshold, then the set of operating time periods is normal.

[0165] If the difference between the storage capacity of the operating period of any operating condition and the corresponding target unit flow is greater than the water balance threshold, it is considered that there is a problem with the division of the operating period group and the operating period group is deleted.

[0166] In another example of this embodiment, after verification, if in any set of operating time periods, the difference between the storage capacity of the operating time period of any operating condition and the corresponding target unit flow is greater than the water balance threshold, the reservoir water level at the start and end time of the corresponding operating condition can also be remeasured, and the storage capacity difference can be re-determined, and / or the runoff volume can be adjusted, and the target unit flow can be re-determined.

[0167] Furthermore, after redetermining the difference in storage capacity and / or adjusting the runoff volume, it is re-determined whether the difference between the storage capacity of each operating condition and the corresponding target unit flow in the group of operating periods is less than or equal to the water balance threshold.

[0168] Based on this, in this embodiment, by comparing the difference between the target unit flow and the storage capacity of each operating condition, it is possible to determine whether a corresponding set of operating time periods is reasonable, whether the measurement of the reservoir water level is accurate, or whether the storage capacity difference is accurate.

[0169] In another embodiment of the present application, for a trained neural network model, whether the neural network model is effective can be verified by simulation.

[0170] In this embodiment, if Figure 3 As shown, after obtaining the trained neural network model, S307 can be further executed to perform simulation verification.

[0171] Specifically, before conducting simulation verification, the trained neural network model is used to predict the total power generation and total energy consumption output by the bidirectional tidal turbine during the corresponding tidal cycle when the turbine operates at the target operating time.

[0172] Furthermore, when conducting simulation verification, the preset simulation software can be used to simulate the operation of the bidirectional tidal unit in the target operating period within the corresponding tidal cycle, and during the simulated operation, the simulated total energy consumption and simulated total power generation in the corresponding tidal cycle are output.

[0173] Based on this, the effectiveness of the neural network model can be verified by comparing whether the total energy consumption and total power generation match the simulated total energy consumption and simulated total power generation. Figure 3 In S308, determine whether the verification is passed.

[0174] Specifically, when determining whether the verification is passed, a first difference between the total power generation and the simulated total power generation may be calculated, and a second difference between the total energy consumption and the simulated total energy consumption may be calculated.

[0175] Furthermore, it is determined whether the first difference is less than or equal to a preset first verification threshold, and whether the second difference is less than or equal to a preset second verification threshold.

[0176] If the first difference is less than or equal to the first verification threshold, the total power generation can be considered to match the simulated total power generation; if the second difference is less than or equal to the second verification threshold, the total energy consumption can be considered to match the simulated total energy consumption. When the total energy consumption matches the simulated total energy consumption and the total power generation matches the simulated total power generation, the neural network model can be considered valid; otherwise, the neural network model is considered invalid.

[0177] When the neural network model is invalid, that is, when the verification result of S308 is negative, S309 is further executed to adjust the parameters.

[0178] Specifically, the corresponding relationship or parameters in the neural network can be adjusted and verified again until the verification result of S308 is yes, and S310 is completed to obtain a valid neural network model.

[0179] In another example of this embodiment, when executing S308 , verification may also be completed through the difference between the total power generation and the total energy consumption.

[0180] Specifically, when determining whether the verification is passed, a third difference between the total power generation and the total energy consumption is calculated, and a fourth difference between the simulated total power generation and the simulated total energy consumption is calculated.

[0181] Furthermore, it is determined whether the difference between the third difference and the fourth difference is less than or equal to a preset third verification threshold. If it is less than or equal to the third verification threshold, it can be considered that the total energy consumption and the total power generation both match the simulated total energy consumption and the simulated total power generation, and the neural network model is considered valid; if it is greater than the first verification threshold, the neural network model can be considered invalid.

[0182] When the neural network model is invalid, that is, when the verification result of S308 is negative, S309 is further executed to adjust the parameters.

[0183] Specifically, the corresponding relationship or parameters in the neural network can be adjusted and verified again until the verification result of S308 is yes, and S310 is completed to obtain a valid neural network model.

[0184] In another example of this embodiment, when executing S308 , verification may be completed by pre-setting verification of energy consumption and verification of power generation.

[0185] Specifically, when determining whether the verification is passed, the simulated total energy consumption can be compared with the verified energy consumption, and the simulated total power generation can be compared with the verified power generation.

[0186] Furthermore, if the first verification difference between the simulated total energy consumption and the verification energy consumption is less than or equal to the preset fourth verification threshold, the total energy consumption can be considered to match the simulated total energy consumption, and if the second verification difference between the simulated total power generation and the verification power generation is less than or equal to the preset fifth verification threshold, the total power generation can be considered to match the simulated total power generation.

[0187] When the total energy consumption matches the simulated total energy consumption and the total power generation matches the simulated total power generation, the neural network model can be considered valid; otherwise, the neural network model is considered invalid.

[0188] When the neural network model is invalid, that is, when the verification result of S308 is negative, S309 is further executed to adjust the parameters.

[0189] Specifically, the corresponding relationship or parameters in the neural network can be adjusted and verified again until the verification result of S308 is yes, and S310 is completed to obtain a valid neural network model.

[0190] Based on this, in this embodiment, the operation of the bidirectional tidal turbine is simulated in the target operating period, so that the simulated total energy consumption and simulated total power generation obtained through simulation can be used to verify whether the neural network is effective.

[0191] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the embodiments of the present application also provide a full-operating-condition operating device for a bidirectional tidal turbine.

[0192] refer to Figure 6 The full-operational device of the bidirectional tidal turbine includes:

[0193] An acquisition module 601 is used to acquire target control data of the bidirectional tidal turbine within a tidal cycle, wherein the target control data includes the tidal start and end times of the tidal cycle and the operating water level of the bidirectional tidal turbine at each time within the tidal cycle;

[0194] The target operating period determination module 602 is configured to input the target control data into the neural network model and determine the target operating period for each operating condition corresponding to the target control data based on the correspondence between the control data and the operating period for each operating condition in the neural network model. The operating period is the operating period of the bidirectional tidal turbine under each operating condition within the tidal cycle.

[0195] The control module 603 is used to control the bidirectional tidal turbine to operate within the tidal cycle according to the target operating time period of each operating condition.

[0196] In one embodiment, the target operating period determination module 602 is specifically configured to:

[0197] Before inputting the target control data into the neural network model, the target operating period determination module 602 performs:

[0198] Acquire multiple historical control data within the tidal cycle, including the start and end time of the tidal cycle, and the tidal water level and reservoir water level corresponding to each time within the tidal cycle;

[0199] Inputting historical control data into the initial neural network model;

[0200] Through the initial neural network model, the tide start and end times are divided according to each working condition, and multiple groups of operating time periods for each working condition are obtained;

[0201] For each operating period of each operating condition, the following steps are performed: the average operating water level within the corresponding operating period is calculated based on the tidal water level and reservoir water level corresponding to the start and end times of the operating period of each operating condition; the target unit flow rate at the average operating water level is determined based on the preset correspondence between the operating water level and the unit flow rate; the output power is calculated based on the average operating water level and the target unit flow rate, and the power generation and energy consumption of the operating period corresponding to each operating condition are calculated based on the output power;

[0202] Calculate the total power generation and total energy consumption of each group of working conditions, and calculate the difference between the total power generation and total energy consumption;

[0203] The corresponding relationship between the operating time period of each working condition corresponding to the maximum difference and the historical control data is obtained, and the corresponding relationship between the control data and the operating time period of each working condition is obtained, and the trained neural network model is obtained.

[0204] In one embodiment, the operating conditions include a forward power generation condition, a reverse power generation condition, a forward pumping condition, and a reverse pumping condition.

[0205] In one embodiment, each operating condition further includes a forward water discharge condition, a reverse water discharge condition and a shutdown condition, and the power generation and energy consumption of the forward water discharge condition, the reverse water discharge condition and the shutdown condition are all zero.

[0206] In one embodiment, the target operating period determination module 602 is further configured to:

[0207] After determining the target unit flow rate of the average operating water level based on the preset correspondence between the operating water level and the unit flow rate, the target operating period determination module 602 executes:

[0208] Based on the preset correspondence between water level and storage capacity, determine the target storage capacity corresponding to the reservoir water level at the start and end times of the operation period of each operating condition;

[0209] Calculate the difference in target storage capacity between the start and end times of the operating period of each operating condition to obtain the corresponding difference in reservoir capacity;

[0210] When the difference between the reservoir capacity and the corresponding target unit flow is less than or equal to a preset water balance threshold, the output power is calculated based on the average operating water level and the target unit flow; or

[0211] When the difference between the reservoir capacity and the corresponding target unit flow is greater than the water balance threshold, a group of operating time periods of various working conditions corresponding to the target unit flow is deleted.

[0212] In one embodiment, the bidirectional tidal turbine full-operation operation device further includes a verification module 604, which is specifically used to:

[0213] Output the total power generation and total energy consumption corresponding to the maximum difference, as well as a corresponding set of target operating time periods for each operating condition.

[0214] The simulation system is used to simulate the execution of the bidirectional tidal turbine within the tidal cycle according to the target operating period of each operating condition, and the simulated total power generation and simulated total energy consumption are output;

[0215] When a first difference between the total power generation and the simulated total power generation is less than a preset first verification threshold, and / or a second difference between the total energy consumption and the simulated total energy consumption is less than a preset second verification threshold, it is determined that the neural network model is valid.

[0216] For the convenience of description, the above devices are described as being divided into various modules according to their functions. Of course, when implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0217] The device of the above embodiment is used to implement the operation method of the corresponding bidirectional tidal unit in all working conditions in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0218] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, it implements the full-working-condition operation method of the bidirectional tidal unit as in any of the above embodiments.

[0219] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0220] The electronic device may include a processor 701 and a memory 702 storing computer program instructions.

[0221] Specifically, the processor 701 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0222] Memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 702 may include removable or non-removable (or fixed) media. Where appropriate, memory 702 may be internal or external to the electronic device. In a particular embodiment, memory 702 is a non-volatile solid-state memory.

[0223] The memory 702 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0224] The processor 701 reads and executes the computer program instructions stored in the memory 702 to implement any one of the methods for operating the bidirectional tidal turbine in all working conditions in the above embodiments.

[0225] In one example, the electronic device may further include a communication interface 703 and a bus 710. Figure 7 As shown, the processor 701, the memory 702, and the communication interface 703 are connected via a bus 710 and communicate with each other.

[0226] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0227] Bus 710 includes hardware, software or both, couples the parts of electronic equipment to each other.For example, but not limitation, bus may include Accelerated Graphics Port (AGP) or other graphics buses, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industry Standard Architecture (ISA) bus, InfiniBand interconnection, Low Pin Count (LPC) bus, memory bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 710 may include one or more buses. Although the present application embodiment describes and shows specific bus, the application considers any suitable bus or interconnection.

[0228] The electronic device can execute the operation method of the bidirectional tidal unit in full working condition in the embodiment of the present application based on the corresponding relationship constructed in the neural network model, thereby realizing the combination of Figure 1 The operation method of the bidirectional tidal turbine under full working conditions is described.

[0229] In addition, in conjunction with the full-operational method for a bidirectional tidal turbine in the above-mentioned embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the full-operational method for a bidirectional tidal turbine in the above-mentioned embodiments is implemented.

[0230] An embodiment of the present application also provides a computer program product, including a computer program, which, when processed and executed, implements the full-operation method of any one of the bidirectional tidal turbine units in the above embodiments.

[0231] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0232] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0233] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a bidirectional tidal unit, which includes electronic equipment, and the electronic equipment can be used to execute the full-condition operation method of the bidirectional tidal unit as any of the above-mentioned embodiments.

[0234] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0235] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0236] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A method for operating a bidirectional tidal turbine in full working conditions, characterized in that: include: Acquiring target control data of the bidirectional tidal generator set within a tidal cycle, the target control data including the tidal start and end times of the tidal cycle and the operating water level of the bidirectional tidal generator set at each time within the tidal cycle; Inputting the target control data into a neural network model, and determining a target operating time period for each operating condition corresponding to the target control data based on a correspondence between the control data and the operating time period for each operating condition in the neural network model; The operating period is the operating period of the bidirectional tidal turbine in various operating conditions within the tidal cycle; controlling the bidirectional tidal turbine to operate within the tidal cycle according to the target operating time period of each operating condition; Before inputting the target control data into the neural network model, the method further includes: Acquire a plurality of historical control data within the tidal cycle, the historical control data including the start and end time of the tidal cycle, and the tidal water level and reservoir water level corresponding to each time within the tidal cycle; inputting the historical control data into an initial neural network model; By using an initial neural network model, the tidal start and end times are divided according to each operating condition to obtain multiple groups of operating time periods for each operating condition; For each group of operating time periods of each operating condition, the following steps are performed respectively: the average operating water level in the corresponding operating time period of the operating condition is calculated based on the tidal water level and reservoir water level corresponding to the start and end times of the operating time period of each operating condition; the target unit flow rate for the average operating water level is determined based on a preset correspondence between the operating water level and the unit flow rate; the output power is calculated based on the average operating water level and the target unit flow rate, and the power generation and energy consumption of the operating time period corresponding to each operating condition are calculated based on the output power; Calculating the total power generation and total energy consumption for each group of operating conditions, and calculating the difference between the total power generation and the total energy consumption; The corresponding relationship between the operating time period of each operating condition corresponding to the maximum difference and the historical control data is obtained to obtain the corresponding relationship between the control data and the operating time period of each operating condition, and to obtain the trained neural network model.

2. The method for operating a bidirectional tidal turbine under full working conditions according to claim 1, characterized in that: The operating conditions include a forward power generation condition, a reverse power generation condition, a forward pumping condition and a reverse pumping condition.

3. The method for operating a bidirectional tidal turbine under full working conditions according to claim 2, characterized in that: The various operating conditions further include a forward water discharge operating condition, a reverse water discharge operating condition and a shutdown operating condition, and the power generation and energy consumption of the forward water discharge operating condition, the reverse water discharge operating condition and the shutdown operating condition are all zero.

4. The method for operating a bidirectional tidal turbine under full working conditions according to claim 1, characterized in that: After determining the target unit flow rate of the average operating water level based on the preset correspondence between the operating water level and the unit flow rate, the method further includes: Based on the preset correspondence between water level and storage capacity, determine the target storage capacity corresponding to the reservoir water level at the start and end times of the operation period of each operating condition; Calculate the difference in target storage capacity between the start and end times of the operating period of each operating condition to obtain the corresponding difference in reservoir capacity; When the difference between the reservoir capacity and the corresponding target unit flow is less than or equal to a preset water balance threshold, the output power is calculated based on the average operating water level and the target unit flow; or When the difference between the reservoir capacity and the corresponding target unit flow is greater than the water balance threshold, a group of operating time periods of various working conditions corresponding to the target unit flow is deleted.

5. The method for operating a bidirectional tidal turbine under full working conditions according to claim 1, characterized in that: The method further comprises: Output the total power generation and total energy consumption corresponding to the maximum difference, as well as a corresponding set of target operating time periods for each operating condition.

6. The method for operating a bidirectional tidal turbine in full working conditions according to claim 5, characterized in that: The method further comprises: Using a simulation system to simulate the execution of the bidirectional tidal turbine within the tidal cycle according to the target operating time period of each operating condition, and outputting a simulated total power generation and a simulated total energy consumption; When a first difference between the total power generation and the simulated total power generation is less than a preset first verification threshold, and / or a second difference between the total energy consumption and the simulated total energy consumption is less than a preset second verification threshold, it is determined that the neural network model is valid.

7. A bidirectional tidal turbine full-operation operation device, characterized in that: The device comprises: An acquisition module is used to acquire target control data of the bidirectional tidal generator set within a tidal cycle, wherein the target control data includes the tidal start and end times of the tidal cycle and the operating water level of the bidirectional tidal generator set at each time within the tidal cycle; a target operating period determination module, configured to input the target control data into a neural network model, and determine a target operating period for each operating condition corresponding to the target control data based on a correspondence between the control data and the operating period for each operating condition in the neural network model; the operating period being the operating period of the bidirectional tidal turbine in each operating condition within the tidal cycle; A control module, configured to control the bidirectional tidal turbine to operate within the tidal cycle according to a target operating time period of each operating condition; The target operation period determination module is configured to: before inputting the target control data into the neural network model, execute: Acquire a plurality of historical control data within the tidal cycle, the historical control data including the start and end time of the tidal cycle, and the tidal water level and reservoir water level corresponding to each time within the tidal cycle; inputting the historical control data into an initial neural network model; By using an initial neural network model, the tidal start and end times are divided according to each operating condition to obtain multiple groups of operating time periods for each operating condition; For each group of operating time periods of each operating condition, the following steps are performed respectively: the average operating water level in the corresponding operating time period of the operating condition is calculated based on the tidal water level and reservoir water level corresponding to the start and end times of the operating time period of each operating condition; the target unit flow rate for the average operating water level is determined based on a preset correspondence between the operating water level and the unit flow rate; the output power is calculated based on the average operating water level and the target unit flow rate, and the power generation and energy consumption of the operating time period corresponding to each operating condition are calculated based on the output power; Calculating the total power generation and total energy consumption for each group of operating conditions, and calculating the difference between the total power generation and the total energy consumption; The corresponding relationship between the operating time period of each operating condition corresponding to the maximum difference and the historical control data is obtained to obtain the corresponding relationship between the control data and the operating time period of each operating condition, and to obtain the trained neural network model.

8. An electronic device, characterized in that: The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the full-operation-condition operation method of the bidirectional tidal turbine as described in any one of claims 1 to 6 is implemented.

9. A bidirectional tidal generator set, characterized in that: It comprises the electronic device as claimed in claim 8, and the electronic device is used to execute the full-operation operation method of the bidirectional tidal turbine as claimed in any one of claims 1-6.

Images