Intelligent energy efficiency management system for geotextile laying ship based on Internet of Things

Abstract

The invention, which belongs to the technical field of ship management, discloses an intelligent energy efficiency management system for a geotextile laying ship based on the Internet of Things, comprising a data acquisition and transmission module, a data processing module, an intelligent early warning module and an abnormality diagnosis module. The method comprises the following steps: collecting multi-dimensional data of a laying ship in the sailing process of the laying ship, and transmitting the multi-dimensional data to a cloud server by adopting a wireless communication technology; the method comprises the following steps: preprocessing multi-dimensional data of a geotextile-laying ship to obtain characterization data of the geotextile-laying ship, and establishing a geotextile-laying ship energy efficiency database for storage; performing feature extraction operation on the representation data of the geotextile laying ship by using a correlation analysis method to obtain key feature variables; by constructing an energy consumption prediction model of the geotextile-laying ship, energy consumption prediction is carried out on characterization data of the geotextile-laying ship obtained in real time, and intelligent early warning of energy consumption of the geotextile-laying ship is achieved. And the system automatically identifies the early warning signal, carries out abnormity diagnosis on the early warning signal by using a preset random forest model, and arranges personnel to carry out intelligent maintenance until the energy consumption of the geotextile laying ship reaches a preset energy consumption standard range.

Description

Technical Field

[0001] The present invention relates to the technical field of ship management, and particularly to an intelligent energy efficiency management system for a laying barge based on the Internet of Things. Background Art

[0002] With the development of the global economy, the shipping industry plays a crucial role in international trade. As an important part of the shipping field, the energy consumption management of laying barges is of great significance for reducing operating costs, improving economic benefits, and reducing environmental pollution. However, there are many limitations in the traditional energy efficiency management methods of laying barges.

[0003] In terms of data collection, traditional methods mainly rely on manual records and simple sensor monitoring, and the obtained data has limited dimensions and low accuracy; In terms of data transmission, traditional wired communication methods have problems such as complex wiring, high maintenance costs, and poor flexibility; in addition, wired communication methods limit the range and speed of data transmission and cannot meet the requirements of real-time monitoring and remote management; In terms of data processing and analysis, traditional methods usually adopt simple statistical and calculation means and lack the ability to deeply mine and analyze a large amount of data.

[0004] In terms of early warning and diagnosis, traditional early warning mechanisms are mainly based on experience and fixed threshold judgments and lack intelligence and adaptability; when abnormal situations occur on the ship, the root causes of the problems often cannot be discovered and accurately diagnosed in a timely manner, resulting in delays in the maintenance time, increased maintenance costs, and safety risks. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art and provide an intelligent energy efficiency management system for a laying barge based on the Internet of Things to solve the problems raised in the above background art.

[0006] The purpose of the present invention can be achieved through the following technical solutions: An intelligent energy efficiency management system for a laying barge based on the Internet of Things, comprising: A data collection and transmission module, configured to collect equipment operation data, navigation data, environmental data, and operation status data of the laying barge during navigation, determine multi-dimensional data of the laying barge based on the Internet of Things, and transmit the multi-dimensional data of the laying barge to a cloud server by using wireless communication technology; A data processing module, configured to perform preprocessing on the multi-dimensional data of the laying barge to obtain characterization data of the laying barge, and establish an energy efficiency database of the laying barge for storage; A feature extraction module, configured to perform feature extraction operations on the characterization data of the laying barge by using a correlation analysis method to obtain key feature variables; An intelligent early warning module, which is used to build an energy consumption prediction model for the paving ship, predict the energy consumption of the paving ship based on the real-time obtained characterization data of the paving ship, and realize the intelligent early warning of the energy consumption of the paving ship; An abnormal diagnosis module, which automatically identifies warning signals of the system, uses a preset random forest model to diagnose the abnormalities, and arranges personnel for intelligent maintenance until the energy consumption of the paving ship reaches the preset energy consumption standard range.

[0007] As a further solution of the present invention, the data acquisition module includes: Sensors, which are used to collect the equipment operation data of the paving ship during navigation; GPS, which is used to collect the navigation data of the paving ship during navigation; Anemometers, wind vanes, current meters, and current direction meters: which are used to collect the environmental data of the paving ship during navigation; Monitoring equipment, which is used to collect the operation status data of the paving ship during navigation.

[0008] As a further solution of the present invention, preprocessing the multi-dimensional data of the paving ship includes: Cleaning the multi-dimensional data of the paving ship to remove invalid data, duplicate data, and error data; Converting the format of the cleaned data, and uniformly converting the collected data into a standard time series data format to meet the requirements of data storage.

[0009] As a further solution of the present invention, the feature extraction operation is as follows: By calculating the correlation coefficient between each data variable in the paving ship characterization data and the energy consumption of the paving ship, select the data variables with a correlation coefficient greater than or equal to the preset standard, and mark them as key feature variables; among them, the preset standard is set to 0.6; The calculation formula is as follows: ; In the formula, r is the correlation coefficient; x i is the i-th data variable, i = 1, 2,..., n, and n is the total number of data variables; y i is the energy consumption of the paving ship corresponding to the i-th data variable; is the average value of this data variable; is the average value of the corresponding energy consumption of the paving ship.

[0010] As a further solution of the present invention, building an energy consumption prediction model for the paving ship includes: Using a multiple regression model to build an energy consumption prediction model; Among them, the expression of the multiple regression model is: ; In the formula, is the predicted energy consumption of the mattress-laying vessel, β 0, β 1, …, β m are the regression coefficients to be estimated; w 1, w 2, …, w m are the key characteristic variables affecting the energy consumption of the mattress-laying vessel; ε is the error term.

[0011] As a further solution of the present invention, it further includes: Taking the extracted key characteristic variables as the input of the model to train the multi-source linear regression model, and determining the regression coefficients based on the least squares method to minimize the error between the actual energy consumption and the model-predicted energy consumption; Among them, the least squares method is used to solve the regression coefficients; ; In the formula, β represents the regression coefficient; X = ( w 1, w 2, …, w m ), represents the matrix composed of the key characteristic variables; X T is the transpose of the matrix X; E is the actual energy consumption; By minimizing the sum of squared errors calculate the error between the actual energy consumption and the model-predicted energy consumption; among them, L is the sum of squared errors to be minimized; E u is the actual energy consumption of the u-th input sample; is the predicted energy consumption of the u-th input sample; u = 1, 2, …, N, and N is the total number of input samples; Based on the determined regression coefficients, obtain the energy consumption prediction model of the mattress-laying vessel.

[0012] As a further solution of the present invention, for the energy consumption prediction of the real-time acquired characterization data of the mattress-laying vessel, it includes: Real-time acquire the characterization data of the mattress-laying vessel and extract the real-time key characteristic variables, input the real-time key characteristic variables into the energy consumption prediction model, and obtain the real-time predicted energy consumption of the mattress-laying vessel at this time; Compare the real-time predicted energy consumption with the preset energy efficiency standard range; among them, the preset energy efficiency standard range includes the maximum energy consumption limit and the minimum energy consumption limit; If the real-time predicted energy consumption > the maximum energy consumption limit, it indicates that the energy consumption of the mattress-laying vessel is extremely high, promptly send out a warning signal, and mark the operating state of the mattress-laying vessel as an abnormal state; If the real-time predicted energy consumption < the minimum energy consumption limit, it indicates that the paving barge is overly energy-saving, and the system automatically issues a warning signal in a timely manner, marking the operating state of the paving barge as an abnormal state; If the minimum energy consumption limit ≤ the real-time predicted energy consumption ≤ the maximum energy consumption limit, it indicates that the energy consumption of the paving barge is normal, and the operating state of the paving barge is marked as a normal state.

[0013] As a further solution of the present invention, the abnormal diagnosis module specifically includes: Automatically identify the warning signal, and perform abnormal diagnosis on the paving barge in the abnormal state to obtain the characterization data of the paving barge collected at this time; Use the preset random forest model to predict it, obtain the labels corresponding to different abnormal reasons or the normal label, and arrange personnel for intelligent maintenance until the energy consumption of the paving barge reaches the preset energy consumption standard range.

[0014] Compared with the existing solutions, the beneficial effects achieved by the present invention are: The present invention collects multi-dimensional data of the paving barge, covering data in multiple aspects. Compared with the traditional methods of manual recording and simple sensor monitoring, it can timely reflect the operating state and environmental changes of the paving barge, which is of great significance for timely discovering potential problems and optimizing the operation of the ship; The present invention helps to improve the data quality, reduce the influence of data deviation on the subsequent analysis results, and make the processed data more accurate and reliable by cleaning and integrating the collected data; use the correlation analysis method to extract features from the multi-dimensional data of the paving barge, and the extracted characterization data of the paving barge can more accurately reflect the performance and operating state of the paving barge; The present invention constructs an energy consumption prediction model for the paving barge, uses historical data and real-time characterization data to predict the energy consumption of the paving barge and issue a warning signal, and discovers potential energy consumption problems in advance according to the prediction results, which helps to take corresponding measures for adjustment and optimization, reduce operating costs, and improve energy utilization efficiency; The present invention helps to improve the maintenance efficiency, reduce the maintenance cost, ensure the normal operation of the paving barge, and realize the intelligent management function by using the preset random forest model to perform abnormal diagnosis on the warning signal; among them, the random forest model has a high classification accuracy and generalization ability, can handle complex non-linear problems, and effectively improves the accuracy and efficiency of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The following further describes the present invention with reference to the drawings.

[0016] Figure 1 It is a module structure diagram of the intelligent energy efficiency management system for a paving barge based on the Internet of Things proposed by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0018] Embodiment 1, as Figure 1 As shown, the present invention is an intelligent energy efficiency management system for laying ships based on the Internet of Things, including: a data acquisition and transmission module, a data processing module, a feature extraction module, and an intelligent early warning module; The data collection and transmission module is used to collect the equipment operation data, navigation data, environmental data and operation status data of the laying ship during the navigation process, determine the multi-dimensional data of the laying ship based on the Internet of Things, and transmit the multi-dimensional data of the laying ship to the cloud server using wireless communication technology; In this embodiment, as a preferred technical solution of the present invention, the data acquisition module includes: Sensors used to collect equipment operation data of the laying vessel during navigation, including but not limited to main engine speed, power, fuel consumption, temperature, and pressure; GPS, used to collect navigation data of the laying vessel during navigation, including but not limited to position, speed, and heading; Anemometer, wind vane, current meter, and current direction meter: used to collect environmental data of the laying ship during navigation, including but not limited to wind speed and direction at sea, and flow speed and direction of seawater; Monitoring equipment used to collect operating status data of the laying vessel during navigation, including but not limited to laying speed, laying area, and load weight; In the embodiment of the present invention, multi-dimensional data of the laying ship is determined by collecting equipment operation data, navigation data, environmental data and operation status data, which solves the limitations of traditional single data and is conducive to providing a data basis for subsequent analysis and optimization of the energy efficiency status of the laying ship.

[0019] The data processing module is used to pre-process the multi-dimensional data of the laying ship, obtain the laying ship characterization data, and establish a laying ship energy efficiency database for storage; Specifically, preprocessing of the multi-dimensional data of the laying ship is carried out, including: Clean the multi-dimensional data of the laying ship to remove invalid data, duplicate data and erroneous data; for example, remove sensor data that is obviously beyond the normal range; Convert the cleaned data into a standard time series data format to meet the data storage requirements; In the embodiments of the present invention, by collecting the equipment operation data, navigation data, environmental data, and operation status data of the laying vessel, the multi-dimensional data of the laying vessel is determined, which solves the limitations of traditional single data and more comprehensively reflects the actual operation status of the laying vessel, providing a rich and detailed data basis for subsequent accurate energy efficiency analysis.

[0020] The feature extraction module performs feature extraction operations on the characterization data of the laying vessel using the correlation analysis method to obtain key feature variables. Specifically, the feature extraction operation is as follows: By calculating the correlation coefficients between each data variable in the characterization data of the laying vessel and the energy consumption of the laying vessel, select the data variables with correlation coefficients greater than or equal to the preset standard and mark them as key feature variables; where the preset standard is set to 0.6. The calculation formula is as follows: ; In the formula, r is the correlation coefficient; x i is the i-th data variable, i = 1, 2,..., n, and n is the total number of data variables; y i is the energy consumption of the laying vessel corresponding to the i-th data variable; is the average value of this data variable; is the average value of the corresponding energy consumption of the laying vessel; In the embodiments of the present invention, by performing feature extraction operations on the characterization data of the laying vessel using the correlation analysis method to obtain key feature variables, it is beneficial to construct a more accurate and reliable energy consumption prediction model for the laying vessel, which can more accurately reflect the actual performance status of the laying vessel, reduce errors and interferences caused by the introduction of irrelevant data, and thus improve the accuracy and credibility of the evaluation results.

[0021] The intelligent warning module is used to construct an energy consumption prediction model for the laying vessel and perform energy consumption prediction on the characterization data of the laying vessel obtained in real time to achieve intelligent warning of the energy consumption of the laying vessel. Specifically, constructing an energy consumption prediction model for the laying vessel includes: Using a multiple regression model to construct an energy consumption prediction model; Among them, the expression of the multiple regression model is: ; In the formula, is the predicted energy consumption of the laying vessel, β 0, β 1,..., β m are the regression coefficients to be estimated; w 1, w 2,..., w mis the key characteristic variable affecting the energy consumption of the paving barge; ε is the error term, representing the difference between the actual energy consumption and the predicted energy consumption of the model due to factors not considered in the model. It is usually assumed to follow a normal distribution with a mean of 0; Use the extracted key characteristic variables as the input of the model to train the multi-source linear regression model, and determine the regression coefficients based on the least squares method to minimize the error between the actual energy consumption and the predicted energy consumption of the model; Among them, the least squares method is used to solve the regression coefficients; ; In the formula, β represents the regression coefficient; X = ( w 1, w 2,..., w m ), represents the matrix composed of key characteristic variables; X T is the transpose of matrix X; E is the actual energy consumption; By minimizing the sum of squared errors Calculate the error between the actual energy consumption and the predicted energy consumption of the model; among them, L is the sum of squared errors to be minimized; E u is the actual energy consumption of the u-th input sample; is the predicted energy consumption of the u-th input sample; u = 1, 2,..., N, and N is the total number of input samples; Based on the determined regression coefficients, obtain the energy consumption prediction model of the paving barge; Specifically, perform energy consumption prediction on the real-time obtained characterization data of the paving barge, including: Real-time obtain the characterization data of the paving barge and extract the real-time key characteristic variables, and input the real-time key characteristic variables into the energy consumption prediction model to obtain the real-time predicted energy consumption of the paving barge at this time; Compare the real-time predicted energy consumption with the preset energy efficiency standard range; among them, the preset energy consumption standard range includes the maximum energy consumption limit and the minimum energy consumption limit; If the real-time predicted energy consumption > the maximum energy consumption limit, it indicates that the energy consumption of the paving barge is extremely high, and an early warning signal is sent in a timely manner, and the operating state of the paving barge is marked as an abnormal state; If the real-time predicted energy consumption < the minimum energy consumption limit, it indicates that the paving barge is overly energy-saving, and the system automatically sends an early warning signal in a timely manner, and the operating state of the paving barge is marked as an abnormal state; If the minimum energy consumption limit ≤ the real-time predicted energy consumption ≤ the maximum energy consumption limit, it indicates that the energy consumption of the paving barge is normal, and the operating state of the paving barge is marked as a normal state; It should be noted that the maximum energy consumption limit is the maximum energy consumption value determined under specific operating conditions of the mattress-laying vessel, taking into account various factors such as ship design, equipment performance, safety factors, and past actual operation data; once the real-time predicted energy consumption exceeds this limit, it may mean that the vessel is in a non-efficient or abnormal operating state, and it is necessary to promptly investigate the reasons and take corrective measures; The minimum energy consumption limit, on the premise of ensuring the normal operation of the mattress-laying vessel, is the most economical and environmentally friendly energy consumption level that can be achieved by optimizing various operating parameters and taking energy-saving measures; In the embodiments of the present invention, by predicting the energy consumption based on the real-time obtained characterization data of the mattress-laying vessel, and comparing the real-time predicted energy consumption with the preset energy efficiency standard range and issuing different warning signals, it is beneficial to promptly detect abnormal situations in the energy consumption of the mattress-laying vessel. Whether the energy consumption is too high or there is excessive energy conservation, the crew can be promptly reminded to take measures to ensure that the mattress-laying vessel operates in an efficient and economical state.

[0022] Based on Embodiment 1, it further includes: An abnormal diagnosis module that automatically identifies warning signals and performs an abnormal diagnosis on the mattress-laying vessel in an abnormal state to obtain the characterization data of the mattress-laying vessel collected at this time; Use a preset random forest model to predict it, obtain labels corresponding to different abnormal reasons or a normal label, and arrange personnel for intelligent maintenance until the energy consumption of the mattress-laying vessel reaches the preset energy consumption standard range; among them, the abnormal reasons include but are not limited to equipment abnormalities, excessive energy conservation, and abnormal mattress laying load; In some preferred implementation schemes, the construction method of the random forest model is as follows: Obtain the characterization data of the mattress-laying vessel in the historical abnormal state and the corresponding abnormal reasons according to the historical navigation records, extract key features related to different abnormal reasons, such as the mattress laying load; use a labeled data set (including normal labels and labels for different abnormal reasons) to train the random forest model, and adjust the parameters of the random forest model through the cross-validation method until the performance of the random forest model meets the standard; the specific algorithm formulas involved in the random forest model are not elaborated here.

[0023] In several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described invention embodiments are merely illustrative. For example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0024] The modules described as separation components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0025] In addition, the functional modules in various embodiments of the present invention may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0026] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0027] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. The intelligent energy efficiency management system for laying vessels based on the Internet of Things is characterized by: include: The data collection and transmission module is used to collect the equipment operation data, navigation data, environmental data and operation status data of the laying ship during the navigation process, determine the multi-dimensional data of the laying ship based on the Internet of Things, and transmit the multi-dimensional data of the laying ship to the cloud server using wireless communication technology; The data processing module is used to pre-process the multi-dimensional data of the laying ship, obtain the laying ship characterization data, and establish a laying ship energy efficiency database for storage; The feature extraction module uses the correlation analysis method to perform feature extraction operations on the laying ship characterization data to obtain key feature variables; Intelligent early warning module, used to build a laying ship energy consumption prediction model, predict energy consumption based on the laying ship characterization data obtained in real time, and realize intelligent early warning of laying ship energy consumption; In the abnormal diagnosis module, the system automatically identifies early warning signals, uses the preset random forest model to diagnose abnormalities, and arranges personnel to perform intelligent maintenance until the energy consumption of the laying ship reaches the preset energy consumption standard range.

2. The intelligent energy efficiency management system for laying vessels based on the Internet of Things according to claim 1 is characterized in that: The data acquisition module includes: Sensors are used to collect equipment operation data of the laying vessel during navigation; GPS, used to collect navigation data of the laying vessel during navigation; Anemometer, wind vane, current meter, and current direction meter: used to collect environmental data of the laying ship during navigation; Monitoring equipment is used to collect operating status data of the laying vessel during navigation.

3. The intelligent energy efficiency management system for laying vessels based on the Internet of Things according to claim 2 is characterized in that: Pre-process the multi-dimensional data of the laying ship, including: Clean the multi-dimensional data of the laying ship to remove invalid data, duplicate data and erroneous data; The cleaned data is formatted and the collected data is uniformly converted into a standard time series data format to meet the requirements of data storage.

4. The intelligent energy efficiency management system for laying vessels based on the Internet of Things according to claim 3 is characterized in that: The feature extraction operation is as follows: By calculating the correlation coefficient between each data variable in the laying ship characterization data and the laying ship energy consumption, the data variables with correlation coefficients greater than or equal to the preset standard are selected and marked as key characteristic variables; wherein the preset standard is set to 0.6; The calculation formula is as follows: ； In the formula, r is the correlation coefficient; x i is the i-th data variable, i=1,2,...,n, n is the total number of data variables; y i is the energy consumption of the laying ship corresponding to the i-th data variable; is the mean value of the data variable; is the corresponding average energy consumption of the laying vessel.

5. The intelligent energy efficiency management system for laying vessels based on the Internet of Things according to claim 4 is characterized in that: Construct a model for predicting the energy consumption of laying vessels, including: Use multiple regression model to build energy consumption prediction model; The expression of the multiple regression model is: ； In the formula, To predict the energy consumption of the laying vessel, β 0, β 1, ..., β m is the regression coefficient to be estimated; w 1, w 2, ..., w m The key characteristic variables that affect the energy consumption of laying vessels; ε is the error term.

6. The intelligent energy efficiency management system for laying vessels based on the Internet of Things according to claim 5 is characterized in that: Also includes: The extracted key characteristic variables are used as the input of the model to train the multi-source linear regression model, and the regression coefficient is determined based on the least squares method to minimize the error between the actual energy consumption and the energy consumption predicted by the model; Among them, the least square method is used to solve the regression coefficient; ； In the formula, β represents the regression coefficient; X=( w 1, w 2, ..., w m ), represents the matrix composed of key feature variables; X T is the transpose of matrix X; E is the actual energy consumption; By minimizing the sum of squared errors Calculate the error between the actual energy consumption and the energy consumption predicted by the model; where L is the minimum sum of squared errors; E u is the actual energy consumption of the u-th input sample; is the predicted energy consumption of the u-th input sample; u=1,2,...,N, N is the total number of input samples; Based on the determined regression coefficients, the energy consumption prediction model of the laying ship is obtained.

7. The intelligent energy efficiency management system for laying vessels based on the Internet of Things according to claim 6 is characterized in that: Energy consumption prediction based on real-time acquired laying vessel characterization data, including: Acquire the laying ship characterization data in real time and extract the real-time key characteristic variables, input the real-time key characteristic variables into the energy consumption prediction model, and obtain the real-time predicted energy consumption of the laying ship at this time; Compare the real-time predicted energy consumption with the preset energy efficiency standard range; wherein the preset energy efficiency standard range includes a maximum energy consumption limit and a minimum energy consumption limit; If the real-time predicted energy consumption is greater than the maximum energy consumption limit, it indicates that the energy consumption of the laying ship is too high, and an early warning signal is issued in time, marking the operation status of the laying ship as abnormal; If the real-time predicted energy consumption is less than the minimum energy consumption limit, it means that the laying ship is over-saving energy, and the system will automatically send out a warning signal in time and mark the operation status of the laying ship as abnormal; If the minimum energy consumption limit ≤ real-time predicted energy consumption ≤ maximum energy consumption limit, it indicates that the energy consumption of the laying ship is normal, and the operating status of the laying ship is marked as normal.

8. The intelligent energy efficiency management system for laying vessels based on the Internet of Things according to claim 7 is characterized in that: The abnormal diagnosis module specifically includes: Automatically identify warning signals, perform abnormal diagnosis on laying vessels in abnormal states, and obtain the laying vessel characterization data collected at this time; Use the preset random forest model to predict it, obtain the corresponding labels of different abnormal causes or normal labels, and arrange personnel to perform intelligent maintenance until the energy consumption of the laying ship reaches the preset energy consumption standard range.

Images