Ship waste gas denitrification remote monitoring method based on cloud computing

Abstract

The invention relates to the technical field of ship waste gas denitrification, in particular to a ship waste gas denitrification remote monitoring method based on cloud computing, which comprises the following steps: arranging sensors, and monitoring and collecting key parameters of a ship denitrification system in real time; synchronously mixing the obtained key parameters with timestamps, and carrying out data preprocessing by utilizing edge computing equipment; historical key parameters of the ship denitrification system are obtained, feature extraction is carried out, the historical key parameters are imported into an abnormal data detection model construction strategy, and an abnormal data detection model with the input being the historical key parameters and the output being abnormal scores of the historical key parameters is constructed; and carrying out feature extraction on the preprocessed data, inputting an abnormal data detection model, outputting an abnormal score of each piece of data, judging whether the data is abnormal or not, and carrying out visual display on operation and maintenance personnel. The problems that in the prior art, real-time performance, threshold inadaptability and big data analysis capacity are lacked, and dependence on manual operation is too much are solved.

Description

Background Art

[0002] Denitrification of ship exhaust gas is one of the core contents of ship pollution control by the International Maritime Organization and governments of various countries. With the implementation of IMO MARPOL Annex VI and Tier III, reducing nitrogen oxide emissions has become one of the important tasks of major ship owners and ship operators. Traditional denitrification monitoring methods are difficult to achieve efficient monitoring and emission compliance due to the limitations of system complexity, real-time nature and remote geographical location. Therefore, a cloud computing-based ship exhaust gas denitrification remote monitoring method came into being, aiming to provide a more reliable and intelligent monitoring solution.

[0003] The exhaust gas denitrification process is dynamic and affected by many factors, such as fuel type, load changes, engine operating conditions, etc. Therefore, only by monitoring the changes in each parameter in real time can we fully understand the health status of the system. Traditional monitoring systems are usually limited to local data collection and storage, and data cannot be transmitted to the cloud in real time for remote access and analysis. This limitation requires operators to directly access the equipment on board to read data, which is not only inefficient, but also lacks the ability to respond quickly in emergencies; and traditional systems lack linkage with the cloud, and cannot use big data analysis, machine learning and other technologies to conduct in-depth analysis of historical data of ships. Summary of the invention

[0004] The main purpose of the present invention is to provide a remote monitoring method for ship exhaust gas denitrification based on cloud computing, which effectively solves the above-mentioned problems mentioned in the background technology.

[0005] The technical solution of the present invention is as follows:

[0006] A remote monitoring method for ship exhaust gas denitrification based on cloud computing is proposed, which includes the following steps:

[0007] S1. Deploy sensors to monitor and collect key parameters of the ship's denitrification system in real time;

[0008] S2, synchronously mix the obtained key parameters with the timestamp, and use the edge computing device to perform data preprocessing;

[0009] S3, obtaining historical key parameters of the ship denitrification system and performing feature extraction, and importing them into the abnormal data detection model construction strategy to construct an abnormal data detection model with the input as the historical key parameters and the output as the abnormal score of the historical key parameters;

[0010] S4: Extract features from the preprocessed data in S2 and input them into the abnormal data detection model, output the abnormal score of each data, determine whether the data has abnormalities, and present a visual display to the operation and maintenance personnel.

[0011] A further improvement of the present invention is that the specific contents of the key parameters in S1 are: using chemiluminescence detection technology to collect the nitrogen-containing gas concentration at the inlet and outlet of the denitrification system; using an oxygen concentration sensor to collect the oxygen concentration of the exhaust gas before it enters the denitrification system; using a temperature sensor to measure the exhaust gas temperature in the exhaust gas pipe; using a pressure sensor to measure the exhaust gas pressure in the exhaust gas pipe; using an ultrasonic flowmeter to measure the exhaust gas volume flow rate; and using a particulate matter sensor to monitor the particulate matter concentration in the exhaust gas.

[0012] A further improvement of the present invention is that the specific content of the data preprocessing in S2 is: after the key parameters acquired are synchronously mixed with the timestamp, a discrete wavelet transform is used for denoising, a Kalman filter is used for real-time filtering of the data, and a discrete cosine transform is used for data compression.

[0013] A further improvement of the present invention is that S3 includes the following specific steps: obtaining key parameters in the historical operation process of the ship denitrification system and performing feature extraction, outputting the curve of the change of historical feature data over time, and obtaining the curve of the change of historical key parameter abnormal score over time, and dividing these data into a 70% coefficient training set and a 30% coefficient test set; performing parameter training on the abnormal data detection model, constructing an abnormal data detection model whose input is the curve of the change of historical feature data over time and output is the curve of the change of historical key parameter abnormal score over time, inputting 70% of the coefficient training set into the abnormal data detection model for training to obtain an initial abnormal data detection model, testing the initial abnormal data detection model with 30% of the coefficient test set, and outputting the optimal initial abnormal data detection model that meets the data accuracy of the nitrogen-containing gas concentration change curve as the abnormal data detection model.

[0014] A further improvement of the present invention is that the abnormal data detection model in S3 is an isolation forest model.

[0015] A further improvement of the present invention is that the output strategy formula of the abnormal data detection model in S3 is:

[0016]

[0017] Among them, S(x,n) is the anomaly score of data x, E(h(x)) is the average path length of the average path length of data x on all isolated trees in the isolation forest model, and c(n) is the expected path length of the binary tree when the number of samples is n.

[0018] A further improvement of the present invention is that the specific content of S4 is: extracting features from the preprocessed data in S2 and inputting them into an abnormal data detection model, outputting an abnormal score for each data; treating data with an abnormal score greater than or equal to a preset abnormal score threshold as abnormal data and feeding it back to the operation and maintenance personnel.

[0019] The technical effects of the present invention are as follows:

[0020] A remote monitoring method for ship exhaust gas denitrification based on cloud computing was constructed. By deploying sensors, the key parameters of the ship denitrification system were monitored and collected in real time; the key parameters obtained were synchronously mixed with the timestamp, and the edge computing device was used for data preprocessing; the historical key parameters of the ship denitrification system were obtained and feature extracted, and imported into the abnormal data detection model construction strategy to construct an abnormal data detection model with historical key parameters as input and historical key parameter abnormal scores as output; the preprocessed data was feature extracted and input into the abnormal data detection model, the abnormal scores of each data were output and the data was judged whether there were abnormalities, and the data was visualized for operation and maintenance personnel. The problem of lack of real-time performance, threshold inadaptability, lack of big data analysis capabilities, and excessive reliance on manual operations in existing technologies was solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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:

[0022] Figure 1 It is a schematic flow chart of the remote monitoring method of ship exhaust gas denitrification based on cloud computing of the present invention. DETAILED DESCRIPTION

[0023] The present invention aims to propose a remote monitoring method for ship exhaust gas denitrification based on cloud computing. By deploying sensors, the key parameters of the ship denitrification system are monitored and collected in real time; the key parameters obtained are synchronously mixed with the timestamp, and the edge computing device is used for data preprocessing; the historical key parameters of the ship denitrification system are obtained and feature extraction is performed, and the abnormal data detection model is imported into the abnormal data detection model construction strategy to construct an abnormal data detection model with input as historical key parameters and output as abnormal scores of historical key parameters; the preprocessed data is feature extracted and input into the abnormal data detection model, the abnormal score of each data is output and it is judged whether the data is abnormal, and a visual display is performed to the operation and maintenance personnel. The problem of lack of real-time performance, threshold inadaptability, lack of big data analysis capabilities and excessive reliance on manual operations in the existing technology is solved.

[0024] Embodiment 1:

[0025] This embodiment proposes a remote monitoring method for ship exhaust gas denitrification based on cloud computing, such as Figure 1 The following specific steps are shown:

[0026] S1. Deploy sensors to monitor and collect key parameters of the ship's denitrification system in real time;

[0027] S2, synchronously mix the obtained key parameters with the timestamp, and use the edge computing device to perform data preprocessing;

[0028] S3, obtaining historical key parameters of the ship denitrification system and performing feature extraction, and importing them into the abnormal data detection model construction strategy to construct an abnormal data detection model with the input as the historical key parameters and the output as the abnormal score of the historical key parameters;

[0029] S4: Extract features from the preprocessed data in S2 and input them into the abnormal data detection model, output the abnormal score of each data, determine whether the data has abnormalities, and present a visual display to the operation and maintenance personnel.

[0030] In this embodiment, the specific contents of the key parameters in S1 are: using chemiluminescence detection technology to collect the nitrogen-containing gas concentration at the inlet and outlet of the denitrification system; using an oxygen concentration sensor to collect the oxygen concentration of the exhaust gas before it enters the denitrification system; using a temperature sensor to measure the exhaust gas temperature in the exhaust gas pipe; using a pressure sensor to measure the exhaust gas pressure in the exhaust gas pipe; using an ultrasonic flowmeter to measure the exhaust gas volume flow rate; using a particulate matter sensor to monitor the particulate matter concentration in the exhaust gas.

[0031] In this embodiment, the specific content of the data preprocessing in S2 is: after the key parameters acquired are synchronously mixed with the timestamp, a discrete wavelet transform is used for denoising, a Kalman filter is used for real-time filtering of the data, and a discrete cosine transform is used for data compression.

[0032] In this embodiment, S3 includes the following specific steps: obtaining key parameters in the historical operation process of the ship denitrification system and performing feature extraction, outputting the change curve of historical feature data over time, and obtaining the change curve of the abnormal score of the historical key parameters over time, and dividing these data into a 70% coefficient training set and a 30% coefficient test set; performing parameter training on the abnormal data detection model, constructing an abnormal data detection model whose input is the change curve of the historical feature data over time and output is the change curve of the abnormal score of the historical key parameters over time, inputting 70% of the coefficient training set into the abnormal data detection model for training to obtain an initial abnormal data detection model, testing the initial abnormal data detection model with 30% of the coefficient test set, and outputting the optimal initial abnormal data detection model that meets the data accuracy of the nitrogen-containing gas concentration change curve as the abnormal data detection model.

[0033] In this embodiment, the abnormal data detection model in S3 is an isolation forest model.

[0034] In this embodiment, the output strategy formula of the abnormal data detection model in S3 is:

[0035]

[0036] Among them, S(x,n) is the anomaly score of data x, E(h(x)) is the average path length of the average path length of data x on all isolated trees in the isolation forest model, and c(n) is the expected path length of the binary tree when the number of samples is n.

[0037] Embodiment 2:

[0038] 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 cloud computing-based ship exhaust gas denitrification remote monitoring method by calling the computer program stored in the memory.

[0039] 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 the cloud computing-based ship exhaust gas denitrification remote monitoring method 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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 The steps for the functions specified in one or more boxes.

[0044] 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. A remote monitoring method for ship exhaust gas denitrification based on cloud computing, characterized in that: The specific steps include: S1. Deploy sensors to monitor and collect key parameters of the ship's denitrification system in real time; S2, synchronously mix the obtained key parameters with the timestamp, and use the edge computing device to perform data preprocessing; S3, obtaining historical key parameters of the ship denitrification system and performing feature extraction, and importing them into the abnormal data detection model construction strategy to construct an abnormal data detection model with the input as the historical key parameters and the output as the abnormal score of the historical key parameters; S4: Extract features from the preprocessed data in S2 and input them into the abnormal data detection model, output the abnormal score of each data, determine whether the data has abnormalities, and present a visual display to the operation and maintenance personnel.

2. The method for remote monitoring of ship exhaust gas denitrification based on cloud computing according to claim 1 is characterized in that: The specific contents of the key parameters in S1 are: using chemiluminescence detection technology to collect the nitrogen-containing gas concentration at the inlet and outlet of the denitrification system; using an oxygen concentration sensor to collect the oxygen concentration of the exhaust gas before it enters the denitrification system; using a temperature sensor to measure the exhaust gas temperature in the exhaust gas pipe; using a pressure sensor to measure the exhaust gas pressure in the exhaust gas pipe; using an ultrasonic flowmeter to measure the exhaust gas volume flow rate; using a particulate matter sensor to monitor the particulate matter concentration in the exhaust gas.

3. The method for remote monitoring of ship exhaust gas denitrification based on cloud computing according to claim 2 is characterized in that: The specific content of the data preprocessing in S2 is: after synchronously mixing the collected key parameters with the timestamp, using discrete wavelet transform to perform denoising, using Kalman filter to perform real-time filtering on the data, and using discrete cosine transform to perform data compression.

4. The method for remote monitoring of ship exhaust gas denitrification based on cloud computing according to claim 3 is characterized in that: The S3 includes the following specific steps: obtaining key parameters in the historical operation process of the ship denitrification system and performing feature extraction, outputting the curve of the change of historical feature data over time, and obtaining the curve of the change of historical key parameter abnormality score over time, and dividing these data into a 70% coefficient training set and a 30% coefficient test set; performing parameter training on the abnormal data detection model, constructing an abnormal data detection model whose input is the curve of the change of historical feature data over time and whose output is the curve of the change of historical key parameter abnormality score over time, inputting 70% of the coefficient training set into the abnormal data detection model for training to obtain an initial abnormal data detection model, testing the initial abnormal data detection model with 30% of the coefficient test set, and outputting the optimal initial abnormal data detection model that meets the data accuracy of the nitrogen-containing gas concentration change curve as the abnormal data detection model.

5. The method for remote monitoring of ship exhaust gas denitrification based on cloud computing according to claim 4 is characterized in that: The abnormal data detection model in S3 is an isolation forest model.

6. The method for remote monitoring of ship exhaust gas denitrification based on cloud computing according to claim 5 is characterized in that: The output strategy formula of the abnormal data detection model in S3 is: Among them, S(x,n) is the anomaly score of data x, E(h(x)) is the average path length of the average path length of data x on all isolated trees in the isolation forest model, and c(n) is the expected path length of the binary tree when the number of samples is n.

7. The method for remote monitoring of ship exhaust gas denitrification based on cloud computing according to claim 6 is characterized in that: The specific content of S4 is: extracting features from the data preprocessed in S2 and inputting them into an abnormal data detection model, outputting an abnormal score for each data; treating data with an abnormal score greater than or equal to a preset abnormal score threshold as abnormal data and feeding it back to the operation and maintenance personnel.

Images