A method and system for predicting the impact of meteorological data on ship locks

Abstract

The present invention discloses a method and system for predicting the influence of meteorological data on a ship lock. The method comprises: obtaining training samples of the meteorological data, wherein the training samples include the types and number of types of the meteorological data, and taking values ​​for each type of the meteorological data to generate meteorological data values; obtaining the true value of the influence of the ship lock, and setting an influence prediction model, inputting the training samples into the influence prediction model for training, and comparing the predicted value of the influence of the ship lock generated by the influence prediction model with the true value of the influence of the ship lock through a loss function, and continuously iterating until the number of iterations is reached to complete the training of the influence prediction model; obtaining real-time meteorological data, and inputting it into the trained influence prediction model to complete the prediction of the influence of meteorological data on the ship lock.

Description

Technical Field

[0001] The present invention belongs to the technical field of predicting the influence of meteorological data on ship locks, and more specifically, relates to a method and system for predicting the influence of meteorological data on ship locks. Background Art

[0002] Weather conditions may affect the operation of ship locks in many ways. The following are some common influencing factors:

[0003] 1. Water levels: Increased rainfall may cause the water level in the locks to rise, while drier weather may cause the water level to drop. This may affect the capacity and safety of the locks.

[0004] 2. Flow rate: Increased wind speed and rainfall may lead to increased water flow rate, which makes it challenging for ship maneuvering and navigation.

[0005] 3. Visibility: Weather conditions such as rain and fog may reduce visibility for vessels and operators, increasing the risk of lock operations.

[0006] 4. Wind: Strong winds may affect the maneuvering of vessels and the stability of locks.

[0007] 5. Temperature: Extreme temperature changes may cause the lock gate to twist, expand or contract, thus affecting the opening and operation of the gate.

[0008] In the prior art, there is no technical solution that can predict the impact of meteorological data on the operating status of the ship lock. Summary of the invention

[0009] In order to solve the above technical problems, the present invention proposes a method for predicting the influence of meteorological data on ship locks, comprising:

[0010] Acquire training samples of the meteorological data, wherein the training samples include the types and number of types of the meteorological data, and take values ​​for each type of the meteorological data to generate meteorological data values;

[0011] Obtaining the true value of the ship lock influence, and setting an influence prediction model, inputting the training sample into the influence prediction model, performing training, and comparing the ship lock influence prediction value generated by the influence prediction model with the true value of the ship lock influence through a loss function, and continuously iterating until the number of iterations is reached, thereby completing the training of the influence prediction model;

[0012] Real-time meteorological data is obtained and input into the trained impact prediction model to complete the prediction of the impact of meteorological data on the ship lock.

[0013] Furthermore, the types of meteorological data include: wind, rain, hail, snow;

[0014] The value of the meteorological data includes: the value range of each type of the meteorological data is 1 to 10, wherein the higher the severity, the greater the value of the meteorological data.

[0015] Furthermore, the influence prediction model is:

[0016]

[0017] Among them, f(t) is the predicted value of the ship lock impact at time t, n is the number of types of meteorological data, and w i is the i-th weight, x i (t) is the value of the ith meteorological data at time t, m is the highest order of the derivative, v j is the jth derivative coefficient, and p is the internal summation term x k (t) the number of jk is the weight of the j-th derivative term on the k-th meteorological data, x k (t) The value of the k-th meteorological data at time t, is the jth derivative with respect to time t.

[0018] Furthermore, the loss function is:

[0019]

[0020] Where q is the number of training samples, F(t) i is the true value of the lock influence of the i-th training sample at time t.

[0021] Furthermore, it also includes:

[0022] When j is fixed, u jk It means that different derivatives give different weights to different meteorological data to capture their different effects on the operation status of the ship lock;

[0023] When k is fixed, u jk Indicates the degree of influence of each derivative on specific meteorological data. Different derivatives are calculated according to their weight u jk To adjust the importance of the corresponding meteorological data.

[0024] Furthermore, it also includes: minimizing the difference between the actual value of the ship lock influence and the predicted value of the ship lock influence by minimizing the loss function Loss.

[0025] The present invention also proposes a prediction system for the impact of meteorological data on ship locks, comprising:

[0026] A data acquisition module is used to acquire training samples of the meteorological data, wherein the training samples include the types and number of types of the meteorological data, and to take values ​​for each type of the meteorological data to generate meteorological data values;

[0027] A training module is used to obtain the real value of the ship lock influence, set the influence prediction model, input the training sample into the influence prediction model, perform training, and compare the ship lock influence prediction value generated by the influence prediction model with the real value of the ship lock influence through a loss function, and continuously iterate until the number of iterations is reached to complete the training of the influence prediction model;

[0028] The prediction module is used to obtain real-time meteorological data and input it into the trained impact prediction model to complete the prediction of the impact of meteorological data on the ship lock.

[0029] Furthermore, the types of meteorological data include: wind, rain, hail, snow;

[0030] The value of the meteorological data includes: the value range of each type of the meteorological data is 1 to 10, wherein the higher the severity, the greater the value of the meteorological data.

[0031] Furthermore, the influence prediction model is:

[0032]

[0033] Among them, f(t) is the predicted value of the ship lock impact at time t, n is the number of types of meteorological data, and w i is the u-th weight, x i (t) is the value of the ith meteorological data at time t, m is the highest order of the derivative, v j is the jth derivative coefficient, and p is the internal summation term x k (t) the number of jk is the weight of the j-th derivative term on the k-th meteorological data, x k (t) The value of the k-th meteorological data at time t, is the jth derivative with respect to time t.

[0034] Furthermore, the loss function is:

[0035]

[0036] Where q is the number of training samples, F(t) i is the true value of the lock influence of the i-th training sample at time t.

[0037] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:

[0038] The present invention obtains training samples of the meteorological data, wherein the training samples include the types and number of types of the meteorological data, and takes values ​​for each type of the meteorological data to generate meteorological data values; obtains the true value of the ship lock influence, and sets an influence prediction model, inputs the training samples into the influence prediction model, performs training, and compares the ship lock influence prediction value generated by the influence prediction model with the true value of the ship lock influence through a loss function, and continuously iterates until the number of iterations is reached to complete the training of the influence prediction model; obtains real-time meteorological data, and inputs it into the trained influence prediction model to complete the prediction of the influence of meteorological data on the ship lock. Through the above technical scheme, the present invention can predict the influence of meteorological data on the operating status of the ship lock, thereby better ensuring the operating safety of the ship lock. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;

[0040] Figure 2 It is a structural diagram of the system of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0041] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0042] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.

[0043] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0044] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.

[0045] The display screen is used to display the user interface of each application.

[0046] All subscripts in the formulas of the present invention are only used to distinguish parameters and have no actual meaning.

[0047] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.

[0048] Example 1

[0049] like Figure 1 As shown, an embodiment of the present invention provides a method for predicting the impact of meteorological data on a ship lock, comprising:

[0050] Step 101, obtaining training samples of the meteorological data, wherein the training samples include the types and number of types of the meteorological data, and taking values ​​for each type of the meteorological data to generate meteorological data values;

[0051] Specifically, the types of meteorological data include: wind, rain, hail, and snow;

[0052] The value of the meteorological data includes: the value range of each type of the meteorological data is 1 to 10, wherein the higher the severity, the greater the value of the meteorological data.

[0053] Step 102, obtaining the real value of the ship lock influence, and setting the influence prediction model, inputting the training sample into the influence prediction model, performing training, and comparing the ship lock influence prediction value generated by the influence prediction model with the real value of the ship lock influence through a loss function, and continuously iterating until the number of iterations is reached, thereby completing the training of the influence prediction model;

[0054] Specifically, the influence prediction model is:

[0055]

[0056] Among them, f(t) is the predicted value of the ship lock impact at time t, n is the number of types of meteorological data, and w i is the i-th weight, x i (t) is the value of the ith meteorological data at time t, m is the highest order of the derivative, v j is the jth derivative coefficient, and p is the internal summation term x k (t) the number of jk is the weight of the j-th derivative term on the k-th meteorological data, x k (t) The value of the k-th meteorological data at time t, is the jth derivative with respect to time t.

[0057] Specifically, the loss function is:

[0058]

[0059] Where q is the number of training samples, F(t) i is the true value of the lock influence of the i-th training sample at time t.

[0060] Specifically, it also includes:

[0061] When j is fixed, u jk It means that different derivatives give different weights to different meteorological data to capture their different effects on the operation status of the ship lock;

[0062] When k is fixed, u jk Indicates the degree of influence of each derivative on specific meteorological data. Different derivatives are calculated according to their weight u jk To adjust the importance of the corresponding meteorological data.

[0063] Step 103, obtaining real-time meteorological data and inputting it into the trained impact prediction model to complete the prediction of the impact of meteorological data on the ship lock.

[0064] Specifically, it also includes: minimizing the difference between the actual value of the ship lock influence and the predicted value of the ship lock influence by minimizing the loss function Loss.

[0065] Example 2

[0066] like Figure 2 As shown, an embodiment of the present invention further provides a prediction system for the impact of meteorological data on ship locks, comprising:

[0067] A data acquisition module is used to acquire training samples of the meteorological data, wherein the training samples include the types and number of types of the meteorological data, and to take values ​​for each type of the meteorological data to generate meteorological data values;

[0068] Specifically, the types of meteorological data include: wind, rain, hail, and snow;

[0069] The value of the meteorological data includes: the value range of each type of the meteorological data is 1 to 10, wherein the higher the severity, the greater the value of the meteorological data.

[0070] A training module is used to obtain the real value of the ship lock influence, set the influence prediction model, input the training sample into the influence prediction model, perform training, and compare the ship lock influence prediction value generated by the influence prediction model with the real value of the ship lock influence through a loss function, and continuously iterate until the number of iterations is reached to complete the training of the influence prediction model;

[0071] Specifically, the influence prediction model is:

[0072]

[0073] Among them, f(t) is the predicted value of the ship lock impact at time t, n is the number of types of meteorological data, and w i is the i-th weight, x i (t) is the value of the ith meteorological data at time t, m is the highest order of the derivative, v j is the jth derivative coefficient, and p is the internal summation term x k (t) the number of jk is the weight of the j-th derivative term on the k-th meteorological data, x k (t) The value of the k-th meteorological data at time t, is the jth derivative with respect to time t.

[0074] Specifically, the loss function is:

[0075]

[0076] Where q is the number of training samples, F(t) i is the true value of the lock influence of the i-th training sample at time t.

[0077] Specifically, it also includes:

[0078] When j is fixed, u jk It means that different derivatives give different weights to different meteorological data to capture their different effects on the operation status of the ship lock;

[0079] When k is fixed, u jk Indicates the degree of influence of each derivative on specific meteorological data. Different derivatives are calculated according to their weight u jk To adjust the importance of the corresponding meteorological data.

[0080] The prediction module is used to obtain real-time meteorological data and input it into the trained impact prediction model to complete the prediction of the impact of meteorological data on the ship lock.

[0081] Specifically, it also includes: minimizing the difference between the actual value of the ship lock influence and the predicted value of the ship lock influence by minimizing the loss function Loss.

[0082] Example 3

[0083] The embodiment of the present invention further provides a storage medium storing a plurality of instructions, wherein the instructions are used to implement the method for predicting the influence of meteorological data on a ship lock.

[0084] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0085] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, obtaining training samples of the meteorological data, wherein the training samples include types and number of types of the meteorological data, and taking values ​​for each type of the meteorological data to generate meteorological data values;

[0086] Specifically, the types of meteorological data include: wind, rain, hail, and snow;

[0087] The value of the meteorological data includes: the value range of each type of the meteorological data is 1 to 10, wherein the higher the severity, the greater the value of the meteorological data.

[0088] Step 102, obtaining the real value of the ship lock influence, and setting the influence prediction model, inputting the training sample into the influence prediction model, performing training, and comparing the ship lock influence prediction value generated by the influence prediction model with the real value of the ship lock influence through a loss function, and continuously iterating until the number of iterations is reached, thereby completing the training of the influence prediction model;

[0089] Specifically, the influence prediction model is:

[0090]

[0091] Among them, f(t) is the predicted value of the ship lock impact at time t, n is the number of types of meteorological data, and w i is the i-th weight, x i (t) is the value of the ith meteorological data at time t, m is the highest order of the derivative, v j is the jth derivative coefficient, and p is the internal summation term x k (t) the number of jk is the weight of the j-th derivative term on the k-th meteorological data, x k (t) The value of the k-th meteorological data at time t, is the jth derivative with respect to time t.

[0092] Specifically, the loss function is:

[0093]

[0094] Where q is the number of training samples, F(t) i is the true value of the lock influence of the i-th training sample at time t.

[0095] Specifically, it also includes:

[0096] When j is fixed, u jk It means that different derivatives give different weights to different meteorological data to capture their different effects on the operation status of the ship lock;

[0097] When k is fixed, u jk Indicates the degree of influence of each derivative on specific meteorological data. Different derivatives are calculated according to their weight u jk To adjust the importance of the corresponding meteorological data.

[0098] Step 103, obtaining real-time meteorological data and inputting it into the trained impact prediction model to complete the prediction of the impact of meteorological data on the ship lock.

[0099] Specifically, it also includes: minimizing the difference between the actual value of the ship lock influence and the predicted value of the ship lock influence by minimizing the loss function Loss.

[0100] Example 4

[0101] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores a plurality of instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the method for predicting the impact of meteorological data on a ship lock.

[0102] Specifically, the electronic device of this embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.

[0103] Among them, the storage medium can be used to store software programs and modules, such as a method for predicting the impact of meteorological data on a ship lock in an embodiment of the present invention, and the corresponding program instructions / modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the above-mentioned method for predicting the impact of meteorological data on a ship lock. The storage medium may include a high-speed random storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include a storage medium remotely arranged relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0104] The processor may call the information and application stored in the storage medium through the transmission system to perform the following steps: Step 101, obtaining a training sample of the meteorological data, wherein the training sample includes the type and number of types of the meteorological data, and taking values ​​for each type of the meteorological data to generate meteorological data values;

[0105] Specifically, the types of meteorological data include: wind, rain, hail, and snow;

[0106] The value of the meteorological data includes: the value range of each type of the meteorological data is 1 to 10, wherein the higher the severity, the greater the value of the meteorological data.

[0107] Step 102, obtaining the real value of the ship lock influence, and setting the influence prediction model, inputting the training sample into the influence prediction model, performing training, and comparing the ship lock influence prediction value generated by the influence prediction model with the real value of the ship lock influence through a loss function, and continuously iterating until the number of iterations is reached, thereby completing the training of the influence prediction model;

[0108] Specifically, the influence prediction model is:

[0109]

[0110] Among them, f(t) is the predicted value of the ship lock impact at time t, n is the number of types of meteorological data, and w i is the i-th weight, x i (t) is the value of the ith meteorological data at time t, m is the highest order of the derivative, v j is the jth derivative coefficient, and p is the internal summation term x k (t) the number of jk is the weight of the j-th derivative term on the k-th meteorological data, x k(t) The value of the k-th meteorological data at time t, is the jth derivative with respect to time t.

[0111] Specifically, the loss function is:

[0112]

[0113] Where q is the number of training samples, F(t) i is the true value of the lock influence of the i-th training sample at time t.

[0114] Specifically, it also includes:

[0115] When j is fixed, u jk It means that different derivatives give different weights to different meteorological data to capture their different effects on the operation status of the ship lock;

[0116] When k is fixed, u jk Indicates the degree of influence of each derivative on specific meteorological data. Different derivatives are calculated according to their weight u jk To adjust the importance of the corresponding meteorological data.

[0117] Step 103, obtaining real-time meteorological data and inputting it into the trained impact prediction model to complete the prediction of the impact of meteorological data on the ship lock.

[0118] Specifically, it also includes: minimizing the difference between the actual value of the ship lock influence and the predicted value of the ship lock influence by minimizing the loss function Loss.

[0119] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0120] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0125] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A method for predicting the impact of meteorological data on ship locks, characterized in that: include: Acquire training samples of the meteorological data, wherein the training samples include the types and number of types of the meteorological data, and take values ​​for each type of the meteorological data to generate meteorological data values; The types of meteorological data include: wind, rain, hail, and snow; The meteorological data includes: each type of the meteorological data has a value range of 1 to 10, wherein the higher the severity, the greater the value of the meteorological data; Obtaining the true value of the ship lock influence, and setting an influence prediction model, inputting the training sample into the influence prediction model, performing training, and comparing the ship lock influence prediction value generated by the influence prediction model with the true value of the ship lock influence through a loss function, and continuously iterating until the number of iterations is reached, thereby completing the training of the influence prediction model; The influence prediction model is: Among them, f(t) is the predicted value of the ship lock impact at time t, n is the number of types of meteorological data, and w i is the i-th weight, x i (t) is the value of the ith meteorological data at time t, m is the highest order of the derivative, v j is the jth derivative coefficient, and p is the internal summation term x k (t) the number of jk is the weight of the j-th derivative term on the k-th meteorological data, x k (t) The value of the k-th meteorological data at time t, To perform the j-time derivative with respect to time t; The loss function is: Where q is the number of training samples, F(t) i is the true value of the ship lock influence of the i-th training sample at time t; Also includes: When j is fixed, u jk It means that different derivatives give different weights to different meteorological data to capture their different effects on the operation status of the ship lock; When k is fixed, u jk Indicates the degree of influence of each derivative on specific meteorological data. Different derivatives are calculated according to their weight u jk To adjust the importance of the corresponding meteorological data; It also includes: minimizing the difference between the actual value of the ship lock influence and the predicted value of the ship lock influence by minimizing the loss function Loss; Real-time meteorological data is obtained and input into the trained impact prediction model to complete the prediction of the impact of meteorological data on the ship lock.

2. A prediction system for the impact of meteorological data on ship locks, characterized in that: include: A data acquisition module is used to acquire training samples of the meteorological data, wherein the training samples include the types and number of types of the meteorological data, and to take values ​​for each type of the meteorological data to generate meteorological data values; The types of meteorological data include: wind, rain, hail, and snow; The meteorological data includes: each type of the meteorological data has a value range of 1 to 10, wherein the higher the severity, the greater the value of the meteorological data; A training module is used to obtain the real value of the ship lock influence, set the influence prediction model, input the training sample into the influence prediction model, perform training, and compare the ship lock influence prediction value generated by the influence prediction model with the real value of the ship lock influence through a loss function, and continuously iterate until the number of iterations is reached to complete the training of the influence prediction model; The influence prediction model is: Among them, f(t) is the predicted value of the ship lock impact at time t, n is the number of types of meteorological data, and w i is the i-th weight, x i (t) is the value of the ith meteorological data at time t, m is the highest order of the derivative, v j is the jth derivative coefficient, and p is the internal summation term x k (t) the number of jk is the weight of the ,th derivative term on the kth meteorological data, x k (t) The value of the k-th meteorological data at time t, To perform the j-time derivative with respect to time t; The loss function is: Where q is the number of training samples, F(t) i is the true value of the ship lock influence of the i-th training sample at time t; Also includes: When j is fixed, u jk It means that different derivatives give different weights to different meteorological data to capture their different effects on the operation status of the ship lock; When k is fixed, u jk Indicates the degree of influence of each derivative on specific meteorological data. Different derivatives are calculated according to their weight u jk To adjust the importance of the corresponding meteorological data; It also includes: minimizing the difference between the actual value of the ship lock influence and the predicted value of the ship lock influence by minimizing the loss function Loss; The prediction module is used to obtain real-time meteorological data and input it into the trained impact prediction model to complete the prediction of the impact of meteorological data on the ship lock.

Images