Intelligent ship system based on Internet of Things

Abstract

The invention discloses an intelligent ship system based on the Internet of Things, and relates to the technical field of ship management, and the system comprises an Internet of Things equipment layer which is responsible for the collection and transmission of data, the receiving and execution of instructions, the safety and protection of equipment, and the monitoring and maintenance of states, and provides a solid foundation for the intelligent management of ships; and the data acquisition layer can efficiently and accurately acquire various data of the ship and further analyze and process the data transmission. Various data on the ship and a control system are highly integrated by using the Internet of Things technology, various data of the ship can be efficiently and accurately acquired, the acquired data are processed and analyzed, and valuable information is extracted to support intelligent management of the ship, so that the system not only improves the operation efficiency of the ship, but also improves the safety of the ship. The maintenance cost is reduced, ship management is more convenient and efficient, and powerful technical support is provided for sustainable development of the ship industry.

Description

Technical Field

[0001] The present invention relates to the technical field of ship management, and in particular to an intelligent ship system based on the Internet of Things. Background Art

[0002] Ship is a general term for various vessels, which are means of transportation that can sail or anchor in waters for transportation or operations. They are man-made means of transportation that humans use in geographical waters, with different technical performance, equipment and structural types to meet different usage requirements. The interior of a ship mainly includes accommodation space, support structure and drainage structure, and has a propulsion system that uses external or self-contained energy. There are many ways to classify ships. According to their use, they can be divided into civilian ships and military ships; according to the hull material, there are wooden ships, steel ships, cement ships and fiberglass ships; according to the navigation area, there are ocean-going ships, near-sea ships, coastal ships and inland ships; according to the power device, there are steam ships, internal combustion engine ships, steamships and nuclear-powered ships; according to the propulsion method, there are paddle steamers, propeller ships, flat-rotor propeller ships and sail-aided ships.

[0003] Safety is of vital importance during ship operation. Navigation safety requires ship drivers and crew members to strictly abide by relevant regulations, especially in areas with high water flow or narrow waterways. The speed should be controlled in advance to avoid capsizing accidents. In addition, the loading and route selection of ships also need to fully consider factors such as water level, flow rate, bridge navigation scale and ship maneuverability to ensure safe navigation.

[0004] Traditional ship management relies heavily on manual operation and management. Crew members and ship managers are responsible for monitoring ship status, performing maintenance tasks, and handling emergencies. However, with the rapid development of Internet of Things technology and the popularization of intelligent management concepts, traditional ship management methods can no longer meet the needs of the modern shipping industry. Traditional ship management systems often have problems such as information islands, low management efficiency, and high operating costs, which restrict the further development of the shipping industry. Therefore, it is necessary to propose an intelligent ship system based on the Internet of Things to solve the problems in the existing technology. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an intelligent ship system based on the Internet of Things. It can highly integrate various equipment, sensors and control systems on the ship through the Internet of Things technology to realize intelligent management of the ship. The system not only improves the operating efficiency of the ship and reduces maintenance costs, but also makes ship management more convenient and efficient, providing strong technical support for the sustainable development of the shipping industry.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent ship system based on the Internet of Things, which includes an Internet of Things device layer, which is responsible for the key tasks of data collection and transmission, command reception and execution, equipment safety and protection, and status monitoring and maintenance, providing a solid foundation for the intelligent management of ships;

[0007] The data collection layer can efficiently and accurately collect various ship data, and further analyze and process the data transmission to provide data support for the intelligent management of the intelligent ship system;

[0008] The data processing layer is responsible for receiving data from the data acquisition layer, processing and analyzing it, and extracting valuable information to support the intelligent management of ships;

[0009] The control execution layer is responsible for accurately controlling the navigation equipment and power equipment on the ship according to the control instructions generated by the data processing layer to achieve automated operation and optimized management of the ship;

[0010] The user interface layer is responsible for displaying data, receiving input, and providing a good user experience.

[0011] Furthermore, the specific steps of the IoT device layer are as follows:

[0012] (1) Equipment connection and configuration: Connect various equipment, sensors and control systems on board the ship to the IoT network, including navigation equipment, power equipment and environmental monitoring equipment;

[0013] (2) Data collection and transmission: The sensors and control systems in the IoT device layer collect the ship’s operating status, environmental parameters, and equipment status data in real time. The collected data is transmitted to the data acquisition layer through the IoT network to ensure the real-time and accuracy of the data.

[0014] (3) Command reception and execution: Control commands are received from the control execution layer. According to the received commands, the relevant devices in the IoT device layer perform corresponding operations to realize the automated operation and optimized management of the ship.

[0015] Furthermore, the specific steps of the data collection layer are as follows:

[0016] Initialize the connection: The data collection layer first establishes a connection with the IoT device layer to ensure smooth communication channels and configure data collection parameters, including data collection frequency and data type;

[0017] Data collection: Receive data from the IoT device layer in real time. These data include the ship's operating status, environmental parameters, and equipment status. Use data preprocessing algorithms to clean and format the raw data, such as removing noise, processing outliers, and normalizing data to ensure data quality. The calculation formula for data normalization is: Where x is the original data point, min(x) and max(x) are the minimum and maximum values ​​in the data set respectively;

[0018] Data formatting: Convert the cleaned data into a unified format to facilitate subsequent analysis and processing.

[0019] Furthermore, the specific steps of the data collection layer also include:

[0020] Data transmission: The pre-processed data is sent to the data processing layer through an efficient data transmission protocol. During the transmission process, a data compression algorithm is used to reduce the amount of transmitted data and improve transmission efficiency;

[0021] Status monitoring and anomaly detection: Real-time monitoring of the status of data collection to ensure the continuity and stability of data collection. Use anomaly detection algorithms to detect anomalies in the collected data to promptly discover possible data anomalies or equipment failures. Use the Z-score method to identify outliers in the data set. The formula is: Where x is a single data point, μ is the mean of the data, which is the sum of all data points divided by the number of data points, and σ is the standard deviation of the data, which measures the dispersion of the data points relative to the mean.

[0022] Logging and storage: Record key information during the data collection process, such as data collection time, amount of data collected, and data transmission status, and store the collected data in a designated database or storage system for subsequent analysis and use.

[0023] Going further, the specific steps of the data processing layer are as follows:

[0024] Data reception and preprocessing: Receive data streams from the data acquisition layer and preprocess the data, including data cleaning, data standardization, and data dimension reduction;

[0025] Feature extraction: Extract features related to ship status, environmental parameters or equipment performance from the preprocessed data, and use feature selection algorithm (based on information gain) to screen out the most representative features. The formula of information gain is: Gain(D,A)=Entropy(D)-Entropy(D|A);

[0026] Pattern recognition and classification: Apply pattern recognition algorithms to classify or identify the extracted features to determine the current state of the ship or predict future trends. Use the support vector machine (SVM) algorithm to classify the ship's operating status to determine whether it is in a normal, abnormal or potential risk state. The algorithm formula for classifying the ship's operating status using the support vector machine (SVM) algorithm mainly involves the decision function, which is used to predict the ship's operating status category y based on the input feature vector x. The general form of the decision function is:

[0027] Furthermore, the specific steps of the data processing layer also include:

[0028] Anomaly detection and early warning: Anomaly detection algorithms are used to identify abnormal patterns in data. These anomalies may indicate equipment failures, safety hazards, or operational abnormalities. The anomaly detection algorithm uses the statistical-based IQR method. The mathematical formula for outlier detection using IQR (interquartile range) can be expressed as: IQR = Q3-Q1, where Q3 is the upper quartile (i.e., 75% of the values ​​in the data are less than or equal to Q3), and Q1 is the lower quartile (i.e., 25% of the values ​​in the data are less than or equal to Q1);

[0029] Trend analysis and prediction: Through time series analysis, regression analysis or machine learning model methods, trend analysis and prediction of ship operation data;

[0030] Result output and decision support: Output the processing and analysis results in the form of visual charts, reports or control instructions.

[0031] Furthermore, the specific steps of the control execution layer are as follows:

[0032] (1) Receiving control instructions: receiving control instructions from the data processing layer;

[0033] (2) Equipment status confirmation: Before executing the control command, confirm the current status of the relevant equipment. The equipment status monitoring algorithm can be used to obtain equipment status information in real time to ensure that the equipment is in a controllable state;

[0034] (3) Control parameter calculation: Calculate the required control parameters based on the control instructions and equipment status. The specific calculation process may involve optimization algorithms and control algorithms to ensure the accurate execution of control instructions.

[0035] (4) Control instruction execution: The calculated control parameters are converted into specific control instructions and sent to the corresponding equipment for execution. The execution of the control instructions may involve direct control of the equipment, such as adjusting the engine throttle and changing the rudder angle.

[0036] (5) Real-time feedback and adjustment: During the execution of control instructions, the device’s feedback information, including execution status and execution results, is obtained in real time. Based on the feedback information, the control parameters are adjusted in real time to ensure continuous optimization of the control effect.

[0037] Furthermore, the optimization algorithm used in the control execution layer for calculating control parameters is a gradient descent algorithm, and the algorithm formula is: where θ n and θ n+1 They represent the control parameters for the nth and n+1th iterations respectively, α is the learning rate and the step size for updating the control parameters, is the performance index function J at θ n The gradient at , which indicates the slope or direction of the function at that point, is used in the control algorithm, and the algorithm formula is: Where u(t) is the control output, which is used to adjust the operating parameters of the equipment, e(t) is the error signal, which represents the difference between the current state and the target state, and K p , K i , K d They are proportional, integral, and differential coefficients, which are used to adjust the weight of the control output.

[0038] Furthermore, the specific steps of the user interface layer design are as follows:

[0039] (1) Requirements analysis: Communicate with stakeholders to understand their needs and expectations, analyze user requirements, and determine the functions and features of the user interface;

[0040] (2) User research: Through questionnaire surveys, user interviews, and user observation methods, understand the behavior and preferences of target users, collect user feedback, and provide guidance for interface design;

[0041] (3) Prototype design: Based on the results of demand analysis and user research, use design tools to create user interface prototypes. Prototype design includes layout, color, font, icon, and interaction design.

[0042] (4) Interface implementation: Convert the designed interface prototype into a real usable interface and use a cross-platform development framework to implement the interface;

[0043] (5) Interface evaluation and testing: Evaluate and test the implemented user interface to check whether it meets the design requirements and user expectations, collect user feedback, and make necessary adjustments and optimizations.

[0044] Furthermore, the system also includes a safety monitoring module for real-time monitoring of the safety status of the ship and timely issuing warning information once an abnormal situation is detected. The specific steps of the safety monitoring module are as follows:

[0045] (1) Configure monitoring parameters: Configure the parameters of the monitoring module, such as monitoring object, monitoring frequency, and alarm threshold, according to security requirements and system characteristics;

[0046] (2) Data collection: The monitoring module collects data from the target system or network, including logs, traffic, and user behavior;

[0047] (3) Data processing and analysis: Pre-process the collected data, such as cleaning and formatting, and use security analysis algorithms to conduct in-depth analysis of the processed data to identify potential security threats;

[0048] (4) Threat detection and identification: Based on the analysis results, the monitoring module detects and identifies possible threats, such as abnormal behavior and malicious attacks;

[0049] (5) Alarm and response: When a threat is detected, the monitoring module triggers the alarm mechanism to notify the administrator or automatically execute preset response measures.

[0050] Compared with the existing technology, the intelligent ship system based on the Internet of Things has the following beneficial effects:

[0051] 1. The present invention uses the Internet of Things technology to highly integrate various data and control systems on the ship, which can efficiently and accurately collect various data of the ship, process and analyze the collected data, and extract valuable information to support the intelligent management of the ship. The system not only improves the operating efficiency of the ship and reduces maintenance costs, but also makes ship management more convenient and efficient, providing strong technical support for the sustainable development of the shipping industry.

[0052] 2. The present invention connects various devices, sensors and control systems on the ship to the Internet of Things network through the Internet of Things device layer, uses the data acquisition layer to collect various data of the ship, uses the data processing layer to process and analyze the received data, and according to the control instructions generated by the data processing layer, the navigation equipment and power equipment on the ship are precisely controlled to realize the automated operation and optimized management of the ship.

[0053] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 The figure is a flow chart of an intelligent ship system based on the Internet of Things. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Example 1

[0058] An intelligent ship system based on the Internet of Things, which includes an Internet of Things device layer, is responsible for key tasks such as data collection and transmission, command reception and execution, equipment safety and protection, and status monitoring and maintenance, providing a solid foundation for the intelligent management of ships.

[0059] The specific steps of the IoT device layer are: connect various devices, sensors and control systems on the ship to the IoT network, including navigation equipment, power equipment, and environmental monitoring equipment, and perform necessary configurations on these devices to ensure that they can communicate and transmit data normally with the IoT network. The sensors and control systems in the IoT device layer collect the ship's operating status, environmental parameters, and equipment status data in real time. The collected data is transmitted to the data acquisition layer through the IoT network to ensure the real-time and accuracy of the data. Control instructions are received from the control execution layer. These instructions may be generated based on the results of the data processing layer. According to the received instructions, the relevant equipment in the IoT device layer performs corresponding operations to realize the automated operation and optimized management of the ship.

[0060] The IoT device layer should also consider the security and protection of the equipment, including physical security and protection technologies, such as equipment reinforcement design and hardware protection modules. At the same time, the equipment should also support data encryption technology, security protocols and communication technologies to ensure the confidentiality and integrity of data during transmission. The IoT device layer needs to monitor the operating status of the equipment in real time, promptly detect possible faults or safety hazards, and perform necessary maintenance operations based on the monitoring results to ensure the normal operation of the equipment and the stability of the system.

[0061] The system also includes a data acquisition layer that can efficiently and accurately collect various data of the ship, and further analyze and process the data transmission to provide data support for the intelligent management of the smart ship system.

[0062] The specific steps of the data collection layer are as follows: the data collection layer first establishes a connection with the IoT device layer to ensure the smooth flow of communication channels, configures data collection parameters, including data collection frequency and data type, and receives data from the IoT device layer in real time. These data include the ship's operating status (such as speed, heading), environmental parameters (such as temperature, humidity, wind speed), and equipment status (such as engine temperature and oil pressure). The data preprocessing algorithm is used to clean and format the raw data, such as removing noise, processing outliers, and normalizing data to ensure data quality. The calculation formula for data normalization is: Here, x is the original data point, min(x) and max(x) are the minimum and maximum values ​​in the data set, respectively. The cleaned data is then converted into a unified format for subsequent analysis and processing.

[0063] The basic idea of ​​median filtering is to replace the gray value of a pixel with the median of its neighborhood gray value, thereby eliminating isolated noise points. Its mathematical expression is: Output value = median(x i-n ,…,x i ,…,x i+n ), where x i is the gray value of the current pixel, n is the size of the filter window, median represents the median operation, outlier processing: the threshold-based outlier processing method is used to process data that exceeds a reasonable range, and the Z-score method is used to identify outliers in the data set.

[0064] The specific steps of the data collection layer also include: sending the preprocessed data to the data processing layer through an efficient data transmission protocol (such as MQTT, CoAP). During the transmission process, a data compression algorithm (such as Huffman coding, LZ77) is used to reduce the amount of data transmitted and improve transmission efficiency. The status of data collection is monitored in real time to ensure the continuity and stability of data collection. The anomaly detection algorithm is used to detect anomalies in the collected data to promptly discover possible data anomalies or equipment failures. Key information in the data collection process, such as data collection time, collected data volume, and data transmission status, is recorded. The collected data is stored in a designated database or storage system for subsequent analysis and use.

[0065] The Z-score method is used to identify outliers in a data set. The formula is: Where x is a single data point, μ is the mean of the data, which is the sum of all data points divided by the number of data points, and σ is the standard deviation of the data, which is used to measure the dispersion of the data points relative to the mean. To identify outliers, a Z-score threshold is usually set. If the absolute value of the Z-score of a data point (|Z|) exceeds this threshold, then the data point is considered an outlier. Common thresholds are 2 or 3, which means that if |Z|>2 or |Z|>3, the data point is considered to be abnormal.

[0066] Example 2

[0067] The system also includes a data processing layer, which is responsible for receiving data from the data acquisition layer, processing and analyzing it, and extracting valuable information to support the intelligent management of ships.

[0068] The specific steps of the data processing layer are as follows: first, receive the data stream from the data acquisition layer and preprocess the data, including data cleaning (removing duplicate, erroneous or invalid data), data standardization (converting data to a uniform scale), and data dimension reduction (reducing the number of data features to simplify subsequent processing). Then, extract features related to ship status, environmental parameters or equipment performance from the preprocessed data, and use feature selection algorithm (based on information gain) to screen out the most representative features. The formula for information gain is: Gain(D,A)=Entropy(D)-Entropy(D|A).

[0069] The steps of the information gain algorithm are as follows: For a classification problem, assume that there are K categories in the data set D, and the proportion of the kth category is p k (k=1, 2, ..., K), then the information entropy of the data set D is defined as: For feature A in dataset D, it has n different values ​​{a1, a2, ..., a n}, divide the data set D into n subsets {D1, D2, ..., D n}, each subset D i Contains all the values ​​in D that are a on feature A i The empirical conditional entropy of feature A for data set D is: Among them, |D i | represents subset D i The number of samples in |D| represents the total number of samples in data set D. The information gain of feature A for data set D is defined as the difference between the total entropy of data set D and the empirical conditional entropy of feature A for data set D, that is, Gain(D,A)=Entropy(D)-Entropy(D|A);

[0070] The specific steps of the data processing layer also include: applying pattern recognition algorithms to classify or identify the extracted features to judge the current state of the ship or predict future trends, using the Support Vector Machine (SVM) algorithm to classify the operating state of the ship to determine whether it is in a normal, abnormal or potentially risky state. The algorithm formula for using the Support Vector Machine (SVM) algorithm to classify the operating state of the ship mainly involves the decision function, and the decision function is used to predict the operating state category y of the ship according to the input feature vector x. The general form of the decision function is:

[0071] The specific steps of the Support Vector Machine (SVM) algorithm are as follows: First, it is necessary to prepare a training data set, which contains the features of the ship's operating state and the corresponding labels (normal, abnormal). Then, extract the features related to the ship's state from the preprocessed data, and these features will be used as the input of the SVM classifier. Next, use the training data set to train the SVM classifier. During the training process, the SVM will find the optimal hyperplane that can separate different category samples. Once the SVM classifier is trained, it can be used to classify new unknown samples, and the new samples will be classified into the corresponding categories according to their positions on the hyperplane.

[0072] The specific steps of the data processing layer also include: using anomaly detection algorithms to identify abnormal patterns in the data, and these anomalies may indicate equipment failures, safety hazards or abnormal operations. The anomaly detection algorithm uses the statistical-based IQR method. The mathematical formula for using the IQR (Interquartile Range) for outlier detection can be expressed as: IQR = Q3 - Q1, where Q3 is the upper quartile (i.e., 75% of the values in the data are less than or equal to Q3), and Q1 is the lower quartile (i.e., 25% of the values in the data are less than or equal to Q1). Next, define the threshold for outliers. Usually, any value less than x < Q1 - 1.5×IQR or greater than Q3 + 1.5×IQR is considered an outlier. Expressed in a mathematical formula, the condition for outliers is: x < Q1 - 1.5×IQR or x > Q3 + 1.5×IQR, where x is any data point in the data set. If the data point x meets any of the above conditions, it is considered an outlier. Through time series analysis, regression analysis or machine learning model methods, perform trend analysis and prediction on the operating data of the ship. For example, use linear regression or neural network models to predict the future energy consumption, speed or course of the ship. Finally, output the results of processing and analysis in the form of visual charts, reports or control instructions to provide decision-making support for ship managers, such as optimizing the navigation route, adjusting equipment parameters, and formulating maintenance plans.

[0073] The system also includes a control execution layer, which is responsible for accurately controlling the navigation equipment and power equipment on the ship according to the control instructions generated by the data processing layer to achieve automated operation and optimized management of the ship.

[0074] The specific steps of the control execution layer are as follows: first, control instructions are received from the data processing layer. These instructions may be about adjusting the speed, changing the heading, starting or shutting down the equipment operation. Before executing the control instructions, the current status of the relevant equipment is confirmed, including the equipment's operating status and parameter settings. The equipment status monitoring algorithm can be used to obtain equipment status information in real time to ensure that the equipment is in a controllable state. The specific algorithm depends on the type of equipment and monitoring requirements, which may include threshold-based monitoring and pattern-based monitoring. According to the control instructions and equipment status, the required control parameters are calculated. The specific calculation process may involve optimization algorithms and control algorithms to ensure the accurate execution of control instructions. When calculating control parameters in the control execution layer, the optimization algorithm uses a gradient descent algorithm. The algorithm formula is: where θ n and θ n+1 They represent the control parameters for the nth and n+1th iterations respectively, α is the learning rate and the step size for updating the control parameters, is the performance index function J at θ n The gradient at , which indicates the slope or direction of the function at that point, is used in the control algorithm as PID control algorithm, and the algorithm formula is: Where u(t) is the control output, which is used to adjust the operating parameters of the equipment, e(t) is the error signal, which represents the difference between the current state and the target state, and K p , K i , K d They are proportional, integral, and differential coefficients, which are used to adjust the weight of the control output;

[0075] The calculated control parameters are then converted into specific control instructions and sent to the corresponding equipment for execution. The execution of the control instructions may involve direct control of the equipment, such as adjusting the engine throttle and changing the rudder angle. During the execution of the control instructions, feedback information from the equipment is obtained in real time, including the execution status and execution results. Based on the feedback information, the control parameters are adjusted in real time to ensure continuous optimization of the control effect.

[0076] Example 3

[0077] The system also includes a user interface layer, which is responsible for displaying data, receiving input, and providing a good user experience.

[0078] The specific steps of user interface layer design are: communicate with relevant stakeholders to understand their needs and expectations, analyze user needs, determine the functions and features of the user interface, understand the behavior and preferences of target users through questionnaires, user interviews and user observation methods, collect user feedback, and provide guidance for interface design. Based on the needs analysis and user research results, use design tools to create user interface prototypes. Prototype design includes layout, color, font, icon and interaction design. Convert the designed interface prototype into a real usable interface. Use cross-platform development frameworks (such as ReactNative, Flutter) to implement the interface. Evaluate and test the implemented user interface to check whether it meets the design requirements and user expectations, collect user feedback, and make necessary adjustments and optimizations.

[0079] The system also includes a security monitoring module, which is used to monitor the safety status of the ship in real time. Once an abnormal situation is detected, an early warning message is issued in a timely manner. The specific steps of the security monitoring module are: according to security requirements and system characteristics, configure the parameters of the monitoring module, such as monitoring objects, monitoring frequency, and alarm thresholds. The monitoring module collects data from the target system or network, including logs, traffic, and user behavior, and pre-processes the collected data, such as cleaning and formatting. The processed data is deeply analyzed using security analysis algorithms to identify potential security threats. Based on the analysis results, the monitoring module detects and identifies possible threats, such as abnormal behavior and malicious attacks. When a threat is detected, the monitoring module triggers the alarm mechanism to notify the administrator or automatically execute preset response measures.

[0080] To sum up: This application connects various devices, sensors and control systems on the ship to the Internet of Things network through the Internet of Things device layer, uses the data acquisition layer to collect various data of the ship, uses the data processing layer to process and analyze the received data, and controls the execution layer according to the control instructions generated by the data processing layer to accurately control the navigation equipment and power equipment on the ship according to the control instructions generated by the data processing layer, so as to realize the automated operation and optimized management of the ship.

[0081] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the same elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent ship system based on the Internet of Things, characterized in that: The system includes an IoT device layer, which is responsible for data collection and transmission, command reception and execution, equipment safety and protection, and status monitoring and maintenance key tasks, providing a solid foundation for intelligent ship management; The data collection layer can efficiently and accurately collect various ship data, and further analyze and process the data transmission to provide data support for the intelligent management of the intelligent ship system; The data processing layer is responsible for receiving data from the data acquisition layer, processing and analyzing it, and extracting valuable information to support the intelligent management of ships; The control execution layer is responsible for accurately controlling the navigation equipment and power equipment on the ship according to the control instructions generated by the data processing layer to achieve automated operation and optimized management of the ship; The user interface layer is responsible for displaying data, receiving input, and providing a good user experience.

2. According to claim 1, the intelligent ship system based on the Internet of Things is characterized in that: The specific steps of the IoT device layer are as follows: (1) Equipment connection and configuration: Connect various equipment, sensors and control systems on board the ship to the IoT network, including navigation equipment, power equipment and environmental monitoring equipment; (2) Data collection and transmission: The sensors and control systems in the IoT device layer collect the ship’s operating status, environmental parameters, and equipment status data in real time. The collected data is transmitted to the data acquisition layer through the IoT network to ensure the real-time and accuracy of the data. (3) Command reception and execution: Control commands are received from the control execution layer. According to the received commands, the relevant devices in the IoT device layer perform corresponding operations to realize the automated operation and optimized management of the ship.

3. The intelligent ship system based on the Internet of Things according to claim 1 is characterized in that: The specific steps of the data collection layer are as follows: Initialize the connection: The data collection layer first establishes a connection with the IoT device layer to ensure smooth communication channels and configure data collection parameters, including data collection frequency and data type; Data collection: Receive data from the IoT device layer in real time. These data include the ship's operating status, environmental parameters, and equipment status. Use data preprocessing algorithms to clean and format the raw data, such as removing noise, processing outliers, and normalizing data to ensure data quality. The calculation formula for data normalization is: Where x is the original data point, min(x) and max(x) are the minimum and maximum values ​​in the data set respectively; Data formatting: Convert the cleaned data into a unified format to facilitate subsequent analysis and processing.

4. The intelligent ship system based on the Internet of Things according to claim 3 is characterized in that: The specific steps of the data collection layer also include: Data transmission: The pre-processed data is sent to the data processing layer through an efficient data transmission protocol. During the transmission process, a data compression algorithm is used to reduce the amount of transmitted data and improve transmission efficiency; Status monitoring and anomaly detection: Real-time monitoring of the status of data collection to ensure the continuity and stability of data collection. Use anomaly detection algorithms to detect anomalies in the collected data to promptly discover possible data anomalies or equipment failures. Use the Z-score method to identify outliers in the data set. The formula is: Where x is a single data point, μ is the mean of the data, which is the sum of all data points divided by the number of data points, and σ is the standard deviation of the data, which measures the dispersion of the data points relative to the mean. Logging and storage: Record key information during the data collection process, such as data collection time, amount of data collected, and data transmission status, and store the collected data in a designated database or storage system for subsequent analysis and use.

5. The intelligent ship system based on the Internet of Things according to claim 1 is characterized in that: The specific steps of the data processing layer are as follows: Data reception and preprocessing: Receive data streams from the data acquisition layer and preprocess the data, including data cleaning, data standardization, and data dimension reduction; Feature extraction: Extract features related to ship status, environmental parameters or equipment performance from the preprocessed data, and use feature selection algorithm (based on information gain) to screen out the most representative features. The formula of information gain is: Gain(D,A)=Entropy(D)-Entropy(D|A); Pattern recognition and classification: Apply pattern recognition algorithms to classify or identify the extracted features to determine the current state of the ship or predict future trends. Use the support vector machine (SVM) algorithm to classify the ship's operating status to determine whether it is in a normal, abnormal or potential risk state. The algorithm formula for classifying the ship's operating status using the support vector machine (SVM) algorithm mainly involves the decision function, which is used to predict the ship's operating status category y based on the input feature vector x. The general form of the decision function is:

6. The intelligent ship system based on the Internet of Things according to claim 5, characterized in that: The specific steps of the data processing layer also include: Anomaly detection and early warning: Anomaly detection algorithms are used to identify abnormal patterns in data. These anomalies may indicate equipment failures, safety hazards, or operational abnormalities. The anomaly detection algorithm uses the statistical-based IQR method. The mathematical formula for outlier detection using IQR (interquartile range) can be expressed as: IQR = Q3-Q1, where Q3 is the upper quartile (i.e., 75% of the values ​​in the data are less than or equal to Q3), and Q1 is the lower quartile (i.e., 25% of the values ​​in the data are less than or equal to Q1); Trend analysis and prediction: Through time series analysis, regression analysis or machine learning model methods, trend analysis and prediction of ship operation data; Result output and decision support: Output the processing and analysis results in the form of visual charts, reports or control instructions.

7. The intelligent ship system based on the Internet of Things according to claim 1 is characterized in that: The specific steps of the control execution layer are as follows: (1) Receiving control instructions: receiving control instructions from the data processing layer; (2) Equipment status confirmation: Before executing the control command, confirm the current status of the relevant equipment. The equipment status monitoring algorithm can be used to obtain equipment status information in real time to ensure that the equipment is in a controllable state; (3) Control parameter calculation: Calculate the required control parameters based on the control instructions and equipment status. The specific calculation process may involve optimization algorithms and control algorithms to ensure the accurate execution of control instructions. (4) Control instruction execution: The calculated control parameters are converted into specific control instructions and sent to the corresponding equipment for execution. The execution of the control instructions may involve direct control of the equipment, such as adjusting the engine throttle and changing the rudder angle. (5) Real-time feedback and adjustment: During the execution of control instructions, the device’s feedback information, including execution status and execution results, is obtained in real time. Based on the feedback information, the control parameters are adjusted in real time to ensure continuous optimization of the control effect.

8. The intelligent ship system based on the Internet of Things according to claim 7, characterized in that: When the control parameters are calculated in the control execution layer, the optimization algorithm adopts the gradient descent algorithm, and the algorithm formula is: where θ n and θ n+1 They represent the control parameters for the nth and n+1th iterations respectively, α is the learning rate and the step size for updating the control parameters, is the performance index function J at θ n The gradient at , which indicates the slope or direction of the function at that point, is used in the control algorithm as PID control algorithm, and the algorithm formula is: Where u(t) is the control output, which is used to adjust the operating parameters of the equipment, e(t) is the error signal, which represents the difference between the current state and the target state, and K p , K i , K d They are proportional, integral, and differential coefficients, respectively, which are used to adjust the weight of the control output.

9. The intelligent ship system based on the Internet of Things according to claim 1, characterized in that: The specific steps of the user interface layer design are as follows: (1) Requirements analysis: Communicate with stakeholders to understand their needs and expectations, analyze user requirements, and determine the functions and features of the user interface; (2) User research: Through questionnaire surveys, user interviews, and user observation methods, understand the behavior and preferences of target users, collect user feedback, and provide guidance for interface design; (3) Prototype design: Based on the results of demand analysis and user research, use design tools to create user interface prototypes. Prototype design includes layout, color, font, icon, and interaction design. (4) Interface implementation: Convert the designed interface prototype into a real usable interface and use a cross-platform development framework to implement the interface; (5) Interface evaluation and testing: Evaluate and test the implemented user interface to check whether it meets the design requirements and user expectations, collect user feedback, and make necessary adjustments and optimizations.

10. The intelligent ship system based on the Internet of Things according to claim 1, characterized in that: The system also includes a safety monitoring module for real-time monitoring of the safety status of the ship. Once an abnormal situation is detected, an early warning message is issued in a timely manner. The specific steps of the safety monitoring module are as follows: (1) Configure monitoring parameters: Configure the parameters of the monitoring module, such as monitoring object, monitoring frequency, and alarm threshold, according to security requirements and system characteristics; (2) Data collection: The monitoring module collects data from the target system or network, including logs, traffic, and user behavior; (3) Data processing and analysis: Pre-process the collected data, such as cleaning and formatting, and use security analysis algorithms to conduct in-depth analysis of the processed data to identify potential security threats; (4) Threat detection and identification: Based on the analysis results, the monitoring module detects and identifies possible threats, such as abnormal behavior and malicious attacks; (5) Alarm and response: When a threat is detected, the monitoring module triggers the alarm mechanism to notify the administrator or automatically execute preset response measures.

Images