Intelligent management method applied to ship waste gas denitrification system

Abstract

The invention relates to the technical field of ship exhaust gas denitrification, in particular to an intelligent management method applied to a ship exhaust gas denitrification system, and the method comprises the steps: collecting historical data related to the ship exhaust gas denitrification system, carrying out the feature extraction of the historical data, and outputting historical feature data; establishing a denitrification efficiency prediction model, predicting the denitrification efficiency of the next time node by using the denitrification efficiency prediction model, and outputting a prediction result; and sending a prediction result to an operation and maintenance platform of the waste gas denitrification system, and manually adjusting a management strategy by operation and maintenance personnel according to a test result. Optimized management is achieved, and the ship waste gas denitrification system is more economical and efficient in operation.

Description

Background Art

[0002] As an important means of water transportation, ships' exhaust emissions pose a serious threat to the environment and human health. In particular, nitrogen oxides (NOx) in ship diesel engine exhaust can cause a series of environmental problems such as acid rain, photochemical smog and ozone holes, which seriously damage the earth's ecosystem. At the same time, NOx can also irritate people's eyes, nose, throat and lungs, easily cause respiratory diseases, and cause great harm to the human body. Therefore, reducing ship exhaust emissions, especially NOx emissions, has become an urgent task in the global environmental protection field. With the development of science and technology, intelligent technology has been widely used in the industrial field. In the field of exhaust gas treatment, intelligent technology can improve the efficiency and stability of the exhaust gas treatment system through real-time monitoring, optimized operation, early warning and fault diagnosis. For ship exhaust gas denitrification systems, the introduction of intelligent management methods can achieve precise control of exhaust gas emissions, ensure stable operation of the system, and reduce operating and maintenance costs. Specifically, intelligent management methods can monitor various parameters of ship exhaust gas denitrification systems in real time, such as NOx emission concentration, reaction temperature, catalyst activity, etc. By analyzing these data, the system can automatically adjust operating parameters such as reaction time, reaction temperature, gas flow, etc. to optimize the denitrification effect. In addition, when the system fails or is abnormal, the intelligent management method can also provide early warning and fault diagnosis to help staff take timely measures to avoid accidents. Summary of the invention

[0003] The main purpose of the present invention is to provide an intelligent management method for a ship exhaust gas denitrification system, which effectively solves the above-mentioned problems mentioned in the background technology.

[0004] The technical solution of the present invention is as follows:

[0005] In the first aspect, an intelligent management method for a ship exhaust gas denitrification system is proposed, the method comprising the following steps:

[0006] S1. Collect historical data related to the ship exhaust gas denitrification system, extract features from the historical data, and output historical feature data;

[0007] S2. Establish a denitrification efficiency prediction model, and use the denitrification efficiency prediction model to predict the denitrification efficiency at the next time node, and output the prediction result;

[0008] S3. Send the prediction results to the exhaust gas denitrification system operation and maintenance platform, and the operation and maintenance personnel will manually adjust the management strategy according to the test results.

[0009] A further improvement of the present invention is that the historical data related to the ship exhaust gas denitrification system in S1 includes historical denitrification efficiency data and historical denitrification efficiency influencing factor data, and the historical denitrification efficiency influencing factor data includes historical environmental data and historical ship operation data.

[0010] A further improvement of the present invention is that the feature extraction of historical data in S1 comprises the following specific steps:

[0011] S11, obtaining historical denitrification efficiency data and historical denitrification efficiency influencing factor data, extracting historical denitrification efficiency characteristic data and historical time characteristic data from the historical denitrification efficiency data, and extracting historical temperature characteristic data, historical pressure characteristic data, and historical flow characteristic data from the historical environmental data;

[0012] S12, combining the historical temperature characteristic data, historical pressure characteristic data, and historical flow characteristic data corresponding to each set of historical time characteristic data into a characteristic vector, and taking the set of all characteristic vectors as a characteristic data set of historical denitrification efficiency influencing factors.

[0013] A further improvement of the present invention is that the establishment of the denitrification efficiency prediction model in S2 comprises the following specific steps:

[0014] S21, obtaining the characteristic vector corresponding to each set of historical time characteristic data in step S12, and simultaneously obtaining the historical denitrification efficiency characteristic data corresponding to each set of historical time characteristic data;

[0015] S22. Establish a denitrification efficiency prediction model, which takes the predicted denitrification efficiency as output, all feature vectors in the historical denitrification efficiency influencing factor feature data set as input, the actual denitrification efficiency corresponding to each set of feature vectors as the prediction target, and minimizing the loss function as the training target. The denitrification efficiency prediction model is trained until the loss function converges to the minimum value and the training is stopped.

[0016] A further improvement of the present invention is that the specific rule for minimizing the loss function in S22 is: obtain a single variable in the loss function, calculate the first-order partial derivative of the single variable of the loss function, and subtract the single variable from the corresponding first-order partial derivative to obtain the value of the updated loss function, and repeat this step until the loss function converges to the minimum value.

[0017] A further improvement of the present invention is that the denitrification efficiency prediction model in S2 is a linear regression model.

[0018] A further improvement of the present invention is that the specific formula of the loss function in S22 is:

[0019]

[0020] Where P is the loss function, m is the number of feature vectors in the characteristic data set of historical denitrification efficiency influencing factors, y is the predicted denitrification efficiency, and Y is the actual denitrification efficiency.

[0021] The technical effects of the present invention are as follows:

[0022] An intelligent management method for ship exhaust gas denitrification system has been constructed. The present invention collects historical data related to the ship exhaust gas denitrification system, extracts features from the historical data, and outputs historical feature data; establishes a denitrification efficiency prediction model, and uses the denitrification efficiency prediction model to predict the denitrification efficiency at the next time node, and outputs the prediction result; the prediction result is sent to the exhaust gas denitrification system operation and maintenance platform, and the operation and maintenance personnel manually adjust the management strategy according to the test results. Optimized management is achieved, making the operation of the ship exhaust gas denitrification system more economical and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0024] Figure 1 This is a flow chart of an intelligent management method for a ship exhaust gas denitrification system according to Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0025] The present invention aims to propose an intelligent management method for ship exhaust gas denitrification system. The present invention collects historical data related to ship exhaust gas denitrification system, extracts features from historical data, and outputs historical feature data; establishes a denitrification efficiency prediction model, and uses the denitrification efficiency prediction model to predict the denitrification efficiency at the next time node, and outputs the prediction result; the prediction result is sent to the exhaust gas denitrification system operation and maintenance platform, and the operation and maintenance personnel manually adjust the management strategy according to the test results. Optimized management is achieved, making the operation of ship exhaust gas denitrification system more economical and efficient.

[0026] Embodiment 1:

[0027] This embodiment proposes an intelligent management method for ship exhaust gas denitrification system. Figure 1 As shown, the following specific steps are included:

[0028] S1. Collect historical data related to the ship exhaust gas denitrification system, extract features from the historical data, and output historical feature data;

[0029] S2. Establish a denitrification efficiency prediction model, and use the denitrification efficiency prediction model to predict the denitrification efficiency at the next time node, and output the prediction result;

[0030] S3. Send the prediction results to the exhaust gas denitrification system operation and maintenance platform, and the operation and maintenance personnel will manually adjust the management strategy according to the test results.

[0031] In this embodiment, the historical data related to the ship exhaust gas denitrification system in S1 includes historical denitrification efficiency data and historical denitrification efficiency influencing factor data, and the historical denitrification efficiency influencing factor data includes historical environmental data and historical ship operation data.

[0032] In this embodiment, the feature extraction of historical data in S1 includes the following specific steps:

[0033] S11, obtaining historical denitrification efficiency data and historical denitrification efficiency influencing factor data, extracting historical denitrification efficiency characteristic data and historical time characteristic data from the historical denitrification efficiency data, and extracting historical temperature characteristic data, historical pressure characteristic data, and historical flow characteristic data from the historical environmental data;

[0034] S12, combining the historical temperature characteristic data, historical pressure characteristic data, and historical flow characteristic data corresponding to each set of historical time characteristic data into a characteristic vector, and taking the set of all characteristic vectors as a characteristic data set of historical denitrification efficiency influencing factors.

[0035] In this embodiment, the establishment of the denitrification efficiency prediction model in S2 includes the following specific steps:

[0036] S21, obtaining the characteristic vector corresponding to each set of historical time characteristic data in step S12, and simultaneously obtaining the historical denitrification efficiency characteristic data corresponding to each set of historical time characteristic data;

[0037] S22. Establish a denitrification efficiency prediction model, which takes the predicted denitrification efficiency as output, all feature vectors in the historical denitrification efficiency influencing factor feature data set as input, the actual denitrification efficiency corresponding to each set of feature vectors as the prediction target, and minimizing the loss function as the training target. The denitrification efficiency prediction model is trained until the loss function converges to the minimum value and the training is stopped.

[0038] In this embodiment, the specific rule for minimizing the loss function in S22 is: obtain a single variable in the loss function, calculate the first-order partial derivative of the single variable of the loss function, and subtract the single variable from the corresponding first-order partial derivative to obtain the value of the updated loss function, and repeat this step until the loss function converges to the minimum value.

[0039] In this embodiment, the denitrification efficiency prediction model in S2 is a linear regression model.

[0040] In this embodiment, the specific formula of the loss function in S22 is:

[0041]

[0042] Where P is the loss function, m is the number of feature vectors in the characteristic data set of historical denitrification efficiency influencing factors, y is the predicted denitrification efficiency, and Y is the actual denitrification efficiency.

[0043] Embodiment 2:

[0044] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned intelligent management method applied to the ship exhaust gas denitrification system by calling the computer program stored in the memory.

[0045] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement an intelligent management method for ship exhaust gas denitrification system provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0046] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), and it can also be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0047] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0048] The present invention is described with reference to flowcharts and block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process or block in the flowchart and block diagram, as well as the combination of processes and blocks in the flowchart 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, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 Process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 Process or multiple processes and boxes Figure 1 A step that specifies a function in one or more boxes.

[0050] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. An intelligent management method for ship exhaust gas denitrification system, characterized by: The specific steps include: S1. Collect historical data related to the ship exhaust gas denitrification system, extract features from the historical data, and output historical feature data; S2. Establish a denitrification efficiency prediction model, and use the denitrification efficiency prediction model to predict the denitrification efficiency at the next time node, and output the prediction result; S3. Send the prediction results to the exhaust gas denitrification system operation and maintenance platform, and the operation and maintenance personnel will manually adjust the management strategy according to the test results.

2. The intelligent management method for ship exhaust gas denitrification system according to claim 1, characterized in that: The historical data related to the ship exhaust gas denitrification system in S1 includes historical denitrification efficiency data and historical denitrification efficiency influencing factor data, and the historical denitrification efficiency influencing factor data includes historical environmental data and historical ship operation data.

3. The intelligent management method for ship exhaust gas denitrification system according to claim 2 is characterized in that: The feature extraction of historical data in S1 includes the following specific steps: S11, obtaining historical denitrification efficiency data and historical denitrification efficiency influencing factor data, extracting historical denitrification efficiency characteristic data and historical time characteristic data from the historical denitrification efficiency data, and extracting historical temperature characteristic data, historical pressure characteristic data, and historical flow characteristic data from the historical environmental data; S12, combining the historical temperature characteristic data, historical pressure characteristic data, and historical flow characteristic data corresponding to each set of historical time characteristic data into a characteristic vector, and taking the set of all characteristic vectors as a characteristic data set of historical denitrification efficiency influencing factors.

4. The intelligent scheduling method for optimizing the operation of an energy storage system according to claim 3, characterized in that: The denitrification efficiency prediction model established in S2 includes the following specific steps: S21, obtaining the characteristic vector corresponding to each set of historical time characteristic data in step S12, and simultaneously obtaining the historical denitrification efficiency characteristic data corresponding to each set of historical time characteristic data; S22. Establish a denitrification efficiency prediction model, which takes the predicted denitrification efficiency as output, all feature vectors in the historical denitrification efficiency influencing factor feature data set as input, the actual denitrification efficiency corresponding to each set of feature vectors as the prediction target, and minimizing the loss function as the training target. The denitrification efficiency prediction model is trained until the loss function converges to the minimum value and the training is stopped.

5. The intelligent management method for ship exhaust gas denitrification system according to claim 4 is characterized in that: The specific rule for minimizing the loss function in S22 is: obtain a single variable in the loss function, calculate the first-order partial derivative of the single variable of the loss function, and subtract the single variable from the corresponding first-order partial derivative to obtain the value of the updated loss function, and repeat this step until the loss function converges to the minimum value.

6. The intelligent management method for ship exhaust gas denitrification system according to claim 5 is characterized by: The denitrification efficiency prediction model in S2 is a linear regression model.

7. The intelligent management method for ship exhaust gas denitrification system according to claim 6 is characterized by: The specific formula of the loss function in S22 is: Where P is the loss function, m is the number of feature vectors in the characteristic data set of historical denitrification efficiency influencing factors, y is the predicted denitrification efficiency, and Y is the actual denitrification efficiency.

Images