A ship operation energy consumption data intelligent supervision platform

Abstract

The application discloses a kind of ship operation energy consumption data intelligent supervision platform, and the present application relates to energy consumption supervision technical field. Including: data acquisition module, data preprocessing module, correlation analysis module, fault identification module and closed-loop management module;Through the establishment of equipment operating state and energy consumption efficiency correlation mapping relationship, combined with basic statistical operation and correlation matching algorithm, the precise identification and early warning of energy efficiency loss caused by implicit failure are realized;The platform guarantees data quality through data preprocessing, quantifies energy consumption deviation degree through energy consumption-working condition correlation analysis, locates fault source in cooperation with trend slope analysis and multi-device correlation verification, forms the closed-loop management of "fault early warning-energy efficiency optimization-cost control", can reduce the risk of misjudgment, reduce economic loss, improve energy consumption efficiency and reduce operating cost, provides practical support for the digital transformation of ship operation.

Description

Technical Field

[0001] This invention relates to the field of energy consumption monitoring technology, specifically to an intelligent monitoring platform for ship operation energy consumption data. Background Technology

[0002] Driven by both the green and low-carbon transformation and intelligent upgrading of the global shipping industry, energy efficiency management and fault early warning in ship operations have become core industry needs. Traditional ship operation and maintenance models mainly rely on manual inspections and post-incident repairs, which not only suffer from low efficiency and high costs, but also make it difficult to identify latent equipment faults in their early stages. Although these latent faults do not directly cause equipment downtime, they can lead to abnormally high energy consumption over a long period, resulting in continuous energy efficiency losses and cost waste.

[0003] In existing technologies, ship energy consumption monitoring systems mostly focus on collecting energy consumption data from individual devices, lacking in-depth correlation analysis between equipment operating conditions and energy efficiency. These systems typically only identify obvious fault alarms and cannot capture hidden performance losses caused by equipment performance degradation, minor pipeline leaks, or operational mismatches. Furthermore, traditional fault warning and energy efficiency analysis modules are fragmented, failing to establish a quantitative mapping relationship between "fault-energy efficiency-cost," resulting in a lack of accurate data support for operational and maintenance decisions.

[0004] From a technical perspective, existing ship data acquisition systems suffer from issues such as inconsistent dimensions of multi-source data and coarse-grained rules for filtering outomas. This makes it difficult to effectively conduct energy consumption comparison and analysis across devices and time periods. In the identification of latent faults, existing methods mostly rely on threshold judgments from single devices, lacking the ability to perform multi-device correlation verification and time series trend analysis. This not only easily leads to misjudgments but also fails to pinpoint the root cause of the fault.

[0005] Furthermore, the need for closed-loop management in ship operations has not been fully met. Existing systems often only output alarm information and cannot translate the identification results into actionable energy efficiency optimization solutions, nor can they quantify the cost impact of failures. This makes it difficult for maintenance personnel to accurately assess the actual benefits of optimization measures and to form a complete management closed loop of "failure early warning - energy efficiency optimization - cost control". Summary of the Invention

[0006] (a) Technical problems to be solved

[0007] To address the shortcomings of existing technologies, this invention provides an intelligent monitoring platform for ship operation energy consumption data, which solves the problems mentioned in the background section.

[0008] (II) Technical Solution

[0009] To achieve the above objectives, the present invention provides the following technical solution: an intelligent monitoring platform for ship operation energy consumption data, comprising a data acquisition module, a data preprocessing module, a correlation analysis module, a fault identification module, and a closed-loop management module;

[0010] The data acquisition module is used to collect operating status data and energy consumption data of various ship equipment;

[0011] The data preprocessing module is used to standardize the collected data and filter out outliers;

[0012] The correlation analysis module is used to construct the correlation coefficient between the equipment energy consumption baseline value and the operating condition;

[0013] The fault identification module is used to verify the location of hidden performance loss through trend analysis and correlation with multiple devices;

[0014] The closed-loop management module is used to generate early warnings and classify them.

[0015] As a further aspect of the present invention, the operating status data includes the equipment rotation speed N. i Import and export pressure P r Runtime T p Where i = 1, 2, ..., n, i is the equipment number, n is the total number of equipment; r = 1, 2, ..., m, r is the monitoring point number, m is the total number of monitoring points; p = 1, 2, ..., u, p is the data collection cycle number, u is the total number of cycles;

[0016] Energy consumption data includes fuel consumption F q Electricity consumption E k Where q = 1, 2, ..., v, q is the energy consumption record number, v is the total number of energy consumption records; k = 1, 2, ..., w, k is the power monitoring point number, w is the total number of power monitoring points;

[0017] As a further aspect of the present invention, the data preprocessing module employs the formula... The collected operational status data and energy consumption data are standardized.

[0018] Among them, X x The original collected basic data, where x is the index of the corresponding basic data, X min and X max These represent the minimum and maximum values ​​of the relevant basic data during the historical data collection period. The relevant basic data includes equipment speed, inlet and outlet pressure, operating time, and fuel or electricity consumption. x ′ represents the standardized data.

[0019] As a further aspect of the present invention, the outlier filtering rule of the data preprocessing module is as follows:

[0020] When the original data X x <X min −0.1×(X max -X min ) or X x >X max +0.1×(X max -X min If the value is ), it is considered invalid data.

[0021] As a further aspect of the present invention, the correlation analysis module employs a formula. Calculate the baseline energy consumption value for a single device:

[0022] Among them, F i Let F be the baseline value of energy consumption per unit time for the i-th device. i,p Let T be the fuel consumption of the i-th device during the p-th data collection cycle. i,p Let be the runtime of the i-th device during the p-th data acquisition cycle;

[0023] Simultaneously using the formula: Calculate the energy consumption correlation coefficient under multiple operating conditions:

[0024] Among them, F i,j Let K be the real-time energy consumption per unit time of the i-th device under the j-th operating condition. i,j This is the energy consumption correlation coefficient.

[0025] As a further aspect of the present invention, when the correlation coefficient K of the device for three consecutive data acquisition cycles... i,j >K i,th At that time, it was determined that there was a hidden fault causing energy efficiency loss;

[0026] When K i,j When the efficiency is less than -3%, the equipment is determined to be in a low-load or abnormal energy-saving state.

[0027] Among them, K i,th Let be the personalized identification threshold for the i-th device.

[0028] As a further aspect of the present invention, the personalized identification threshold K i,th The determination method is as follows:

[0029] First, for all correlation coefficients K of the i-th device under historical normal operating conditions... i,j Statistical analysis was performed, and the upper limit of its 95% confidence interval was calculated, which was then used as the basic threshold; subsequently, K was used... i,th =α×K i,base Among them, K i,base Let α be the base threshold for the i-th device, and α be a preset correction coefficient.

[0030] As a further aspect of the present invention, the fault identification module adopts the following formula: Calculate the trend slope of the correlation coefficient;

[0031] In the formula, This is the average index for the collection period; S is the average correlation coefficient of the i-th device; i The slope represents the trend.

[0032] Simultaneously using formulas Calculate the cumulative energy efficiency loss L of the i-th device during u data collection cycles. i ;

[0033] In the formula, F i,p F represents the actual fuel consumption of the i-th device in the p-th cycle; i ×T i,p This represents the theoretical fuel consumption under baseline operating conditions.

[0034] As a further aspect of the present invention, the closed-loop management module adopts the formula Calculate the cost corresponding to the energy efficiency loss:

[0035] Among them, C i C represents the cost corresponding to the energy efficiency loss of the i-th device. f This refers to the unit price of fuel.

[0036] As a further aspect of this invention, the fault warning is divided into three levels:

[0037] When K i,j If the percentage is greater than 10%, it is considered a Level 1 warning and the information is sent to the ship's maintenance supervisor.

[0038] When 5% < K i,j If the rate is ≤10%, it is considered a Level II warning and the information is sent to the chief engineer.

[0039] When 3% < K i,j If the threshold is ≤5%, it is considered a Level 3 warning and the alert is sent to the crew on duty.

[0040] (III) Beneficial Effects

[0041] This invention provides an intelligent monitoring platform for ship operation energy consumption data. Compared with existing technologies, it has the following advantages:

[0042] This invention establishes a correlation between equipment operating status and energy efficiency. By combining basic statistical calculations and correlation matching algorithms, the platform can accurately identify energy efficiency losses caused by latent faults. This mechanism changes the previous passive mode that relied on obvious fault characteristics for early warning, enabling early detection of latent faults, effectively preventing the escalation of faults, and providing core technical support for shifting ship operation and maintenance from passive response to proactive prevention.

[0043] This invention eliminates dimensional differences between different devices and data acquisition cycles through standardized processing, while outlier filtering ensures data quality. Based on this, by calculating the correlation coefficient between a single device's energy consumption baseline and energy consumption under multiple operating conditions, the degree of energy consumption deviation of a device under different operating conditions can be dynamically quantified. Combined with trend slope analysis and multi-device correlation verification, the specific sources of hidden performance losses can be located, significantly reducing the risk of misjudgment based on single-device data and providing a scientific quantitative basis for fault diagnosis.

[0044] This invention, through a three-tiered early warning mechanism, can accurately push maintenance instructions based on the degree of energy consumption anomalies, enabling rapid response from managers at different levels. Simultaneously, the platform can generate targeted energy efficiency optimization solutions and quantify the costs corresponding to energy efficiency losses, helping operators intuitively assess the optimization effects. This not only reduces economic losses caused by equipment failures but also lowers daily operating costs through continuous optimization of energy efficiency, directly improving the economic benefits of ship operations.

[0045] This invention seamlessly connects all technical aspects through fundamental mathematical formulas, forming a complete logical chain from data acquisition to closed-loop management. It requires no complex hardware modifications and can be quickly deployed into existing ship equipment monitoring systems. Its core innovation lies in the deep integration of latent fault identification and energy efficiency optimization. This not only meets the shipping industry's core needs for safe operation and maintenance but also aligns with the industry's green and low-carbon development trend, providing a practical solution for the digital transformation of ship operations. Attached Figure Description

[0046] Figure 1 This is a system block diagram of an intelligent monitoring platform for ship operation energy consumption data according to the present invention.

[0047] Figure 2 This is a flowchart illustrating an intelligent monitoring platform for ship operation energy consumption data according to the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] Please see Figure 1 and Figure 2 As shown, the embodiments of the present invention provide the following technical solutions:

[0050] As an embodiment of the present invention:

[0051] This invention is an intelligent monitoring platform for ship operation energy consumption data, comprising: a data acquisition module, a data preprocessing module, a correlation analysis module, a fault identification module, and a closed-loop management module;

[0052] The data acquisition module is used to collect basic data corresponding to the operating status data and energy consumption data of various ship equipment.

[0053] The data preprocessing module is used to standardize the collected data and filter out outliers;

[0054] The correlation analysis module is used to construct the correlation coefficient between the equipment energy consumption baseline value and the operating condition;

[0055] The fault identification module is used to verify the location of hidden performance loss through trend analysis and correlation with multiple devices;

[0056] The closed-loop management module is used to generate early warnings and classify them.

[0057] The implementation process of an intelligent monitoring platform for ship operation energy consumption data is as follows:

[0058] Step 1: Data Acquisition and Preprocessing

[0059] For various types of equipment on ships, basic data corresponding to operating status data and energy consumption data are collected, and then the collected basic data is standardized.

[0060] In this embodiment, various types of ship equipment refer to main engines, auxiliary engines, piping systems, etc.

[0061] Operating status data includes equipment rotation speed N i Import and export pressure P r Runtime T p ;

[0062] Where i = 1, 2, ..., n, i is the equipment number, n is the total number of equipment; r = 1, 2, ..., m, r is the monitoring point number, m is the total number of monitoring points; p = 1, 2, ..., u, p is the data collection cycle number, u is the total number of cycles;

[0063] Energy consumption data includes fuel consumption F q Electricity consumption E k ;

[0064] Where q = 1, 2, ..., v, q is the energy consumption record number, v is the total number of energy consumption records; k = 1, 2, ..., w, k is the power monitoring point number, w is the total number of power monitoring points;

[0065] The standardized processing method is as follows:

[0066]

[0067] Where: X x The original collected basic data, namely N i P r F q T p E k And x is the index of the corresponding data; X x，min X is the minimum value of this type of data during the historical collection period; x，max X represents the maximum value of this type of data within the historical collection period. x ′ represents the standardized data, with a value range of [0,1].

[0068] Standardization is used to eliminate dimensional differences between different devices and different acquisition cycles;

[0069] Taking host speed as an example, if the historical minimum speed of a host is 500 rpm and the maximum speed is 1500 rpm, and the currently collected speed is 1000 rpm, then the standardized speed is: ;

[0070] Step 2: Building the energy consumption-operating condition correlation model:

[0071] By conducting basic statistical calculations, a quantitative correlation between equipment operating status and energy consumption is established to identify hidden energy efficiency losses.

[0072] The method is as follows:

[0073] Step 1.1, Calculation of baseline energy consumption for a single device:

[0074] Firstly, through: Calculate the baseline energy consumption F(G) per unit time for each device under historical normal operating conditions. i ;

[0075] Wherein: F i,p T represents the fuel consumption of the i-th device during the p-th data collection cycle, expressed in kg. i,p Let be the runtime of the i-th device during the p-th data acquisition cycle, in hours (h).

[0076] For example, if a host computer consumes 100kg, 120kg, and 90kg of fuel in three data acquisition cycles, corresponding to runtimes of 2h, 2.5h, and 1.8h respectively, then its energy consumption per unit time baseline value is:

[0077] kg / h;

[0078] Step 1.2, Calculation of energy consumption correlation coefficients under multiple operating conditions:

[0079] pass: The proportion by which the energy consumption of the i-th device deviates from the benchmark value under the j-th operating condition is determined and denoted as the operating condition energy consumption correlation coefficient K. i,j ;

[0080] Where: j is the equipment's operating condition number, j=1, 2, ..., e, e is the total number of operating conditions, F i,j Let be the real-time energy consumption per unit time of the i-th equipment under the j-th operating condition, with the unit being kg / h; the operating condition energy consumption correlation coefficient is used to reflect the impact of changes in equipment operating status on energy consumption; a positive value indicates that the energy consumption is higher than the benchmark value, and a negative value indicates that the energy consumption is lower than the benchmark value.

[0081] If the real-time energy consumption per unit time of the above host under a certain operating condition is 55 kg / h, then its operating condition correlation coefficient is: ;

[0082] Step 1.3, Setting the association threshold:

[0083] Based on the statistical results of the ship's historical operating data within a specified period, and combined with the design conditions and actual operating scenarios of different equipment, a threshold for identifying hidden performance losses is set, as follows:

[0084] First, for all correlation coefficients K of the i-th device under historical normal operating conditions... i,j Statistical analysis was conducted to calculate the upper limit of its 95% confidence interval, which was then used as the basic threshold.

[0085] To adapt to the differences in operating conditions across different flight zones and load rates, a correction coefficient α is introduced into the basic threshold, ultimately yielding the device's personalized identification threshold, which is determined by K. i,th =α×K i,base Among them, K i,th K is the personalized recognition threshold for the i-th device. i,base The base threshold for the i-th device;

[0086] In this embodiment, the correction coefficient α ranges from 0.8 to 1.2;

[0087] When the correlation coefficient K of the device for three consecutive data acquisition cycles i,j >K i,thAt that time, it was determined that there was a hidden fault causing energy efficiency loss;

[0088] When K i,j When the efficiency is less than -3%, the equipment is determined to be in a low-load or abnormal energy-saving state.

[0089] In this embodiment, the dynamic threshold mechanism can avoid misjudgment under complex working conditions by using fixed thresholds, thereby improving the accuracy of hidden fault identification.

[0090] Step 3: Identification of hidden faults and energy efficiency losses:

[0091] By analyzing the changing trends of the correlation coefficient of energy consumption under operating conditions, the specific source of hidden faults can be located, and a precise mapping between "fault and energy efficiency" can be achieved.

[0092] The method is as follows:

[0093] Step 2.1, Time Series Trend Analysis:

[0094] The correlation coefficient K of the i-th device during the continuous data acquisition period i,p Trend fitting is performed, using a linear slope to reflect the trend of energy consumption change. The formula is as follows:

[0095] in: This is the average index for the collection period; S is the average correlation coefficient of the i-th device; i The slope represents the trend; a positive value indicates an upward trend in energy consumption, while a negative value indicates a downward trend in energy consumption.

[0096] If the correlation coefficients of a host in 5 data collection periods are 2%, 3%, 5%, 7%, and 9% respectively, and the data collection period index is 1-5, then:

[0097]

[0098]

[0099]

[0100] Slope S i =1.8>0, indicating that the host's energy consumption is showing a continuous upward trend, and there is a hidden risk of failure.

[0101] Step 2.2, Multi-device association verification:

[0102] When the correlation coefficient K of the i-th device i,j When the threshold is exceeded, the correlation coefficient K of its associated devices is checked simultaneously. i′,j′ ;

[0103] In this embodiment, associated equipment refers to the main unit and its supporting pipelines, auxiliary equipment and power system, etc.

[0104] Where i′ is the number of the associated equipment, j′ is the operating condition number of the associated equipment, j′=1, 2, ..., e′, and e′ is the total number of operating conditions;

[0105] If the correlation coefficient of the associated equipment also shows abnormal fluctuations, the existence of a hidden fault can be further confirmed.

[0106] In this embodiment, a multi-device association verification mechanism is introduced to avoid misjudgment of data from a single device;

[0107] For example, when the host's K i,j When the pressure correlation coefficient K of its matching fuel pipeline is 8%, i′,j′ If the energy consumption is 6%, it can be determined that the abnormal energy consumption of the host is related to hidden faults such as pipeline leakage.

[0108] Step 2.3, Quantitative Calculation of Energy Efficiency Loss:

[0109] For identified latent faults, the following methods are used: Calculate the cumulative energy efficiency loss L of the i-th device during u data collection cycles. i Its unit is kg; F i,p F represents the actual fuel consumption of the i-th device in the p-th cycle; i ×T i,p This represents the theoretical fuel consumption under baseline operating conditions.

[0110] If the actual fuel consumption of the above-mentioned host in the three cycles is 120kg, 130kg, and 140kg respectively, corresponding to operating times of 2h, 2h, and 2h respectively, and the baseline value Fi = 49.21kg / h, then the cumulative energy efficiency loss is:

[0111] kg

[0112] Step 4: Closed-loop management support:

[0113] The identification results are transformed into actionable operation and maintenance suggestions, realizing a closed loop from fault early warning to cost control;

[0114] The method is as follows:

[0115] Based on the degree of anomaly in the correlation coefficient, the early warning is divided into three levels:

[0116] When K i,j If the rate is greater than 10%, it is considered a Level 1 warning: the message is sent to the ship's maintenance supervisor, who is advised to immediately stop the machine for inspection.

[0117] When 5% < K i,jIf the rate is ≤10%, it is considered a Level II warning: the message is sent to the chief engineer, who is advised to conduct maintenance while the ship is at port.

[0118] When 3% < K i,j If the rate is ≤5%, it is considered a Level 3 warning: the information is sent to the on-duty crew members, and the monitoring frequency is increased.

[0119] Example 1 constructs a complete intelligent monitoring platform for ship operation energy consumption data. Through the collaboration of data acquisition, preprocessing, correlation analysis, fault identification, and closed-loop management modules, it achieves accurate correlation between ship equipment energy consumption and operating conditions. Its dynamic threshold mechanism and multi-device correlation verification effectively improve the accuracy of hidden fault identification and solve the problem of misjudgment under complex operating conditions caused by traditional fixed thresholds. At the same time, the three-level early warning mechanism can transform the identification results into actionable operation and maintenance suggestions, helping operation and maintenance personnel to quickly locate faults and take corresponding measures, thereby reducing energy efficiency losses in ship operation, improving energy utilization efficiency, and providing strong support for the safe and economical operation of ships.

[0120] As a second embodiment of the present invention:

[0121] In its specific implementation, compared to Embodiment 1, the technical solution of this embodiment differs only in that, in this embodiment, outlier filtering is performed on the collected basic data during data acquisition and preprocessing. The method is as follows:

[0122] For outlier data that deviates from the normal range, interval filtering is used to remove it:

[0123] When the original data X x <X x，min −0.1×(X x，max -X x，min ) or X x >X x，max +0.1×(X x，max -X x，min If the value is less than 1, it is considered invalid data and will not be included in subsequent calculations.

[0124] Example 2 adds an outlier filtering step to Example 1, using interval filtering to remove invalid data that deviates from the normal range, further ensuring data quality. This optimization avoids interference from outlier data in subsequent energy consumption correlation analysis and fault identification, making the calculation results closer to the actual operating state of the equipment, thereby improving the accuracy and reliability of hidden fault identification. At the same time, high-quality data provides a more solid foundation for calculating energy consumption benchmarks and analyzing operating condition correlation coefficients, making the platform's regulatory decisions more scientific and more effectively helping ships reduce ineffective energy consumption and lower operating costs.

[0125] As an embodiment of the present invention:

[0126] In specific implementation, compared with Embodiment 1 and Embodiment 2, the technical solution of this embodiment is to combine the solutions of Embodiment 1 and Embodiment 2. The only difference between the technical solution of this embodiment and Embodiment 1 and Embodiment 2 is that in this embodiment, in the closed-loop management support step, based on the correlation analysis results, a targeted energy efficiency optimization scheme is generated for the main engine, auxiliary engine and pipeline system of various ship equipment.

[0127] If the host correlation coefficient is abnormal, it is recommended to adjust the fuel injection pressure and check the cylinder liner wear.

[0128] If the pipeline correlation coefficient is abnormal, it is recommended to check for leaks and replace the seals.

[0129] If the number of auxiliary equipment connections is abnormal, it is recommended to optimize load distribution and clean the heat exchange equipment.

[0130] Implementation Example 3, building upon the advantages of the first two examples, adds a targeted energy efficiency optimization solution generation function. This function can provide specific optimization suggestions based on the abnormal correlation coefficients of different equipment (main engine, auxiliary engines, piping systems). For example, it suggests adjusting fuel injection pressure for main engine correlation anomalies and checking for leaks for piping anomalies. This breakthrough extends the platform from simple fault warnings to proactive energy efficiency optimization. It not only helps ships resolve existing faults promptly but also optimizes equipment operation at its source, continuously reducing energy consumption and further improving the ship's operational economy and environmental friendliness, achieving an upgrade from "problem detection" to "problem solving."

[0131] As an embodiment of the present invention:

[0132] In its specific implementation, compared to Embodiments 1, 2, and 3, the difference between this embodiment and Embodiments 1, 2, and 3 lies only in that, in this embodiment, the closed-loop management support step further includes: The effectiveness of the optimization plan should be quantitatively evaluated.

[0133] Where: C i C represents the cost corresponding to the energy efficiency loss of the i-th device, expressed in yuan. f This refers to the unit price of fuel, expressed in yuan / kg.

[0134] If the energy efficiency loss L of the above host i =94.74kg, fuel price C f =6 yuan / kg, then the corresponding cost loss is: Yuan;

[0135] After optimization, if the correlation coefficient is reduced to 2%, this part of the cost can be saved;

[0136] Example 4, building upon the previous three examples, adds a quantitative evaluation function for the effectiveness of optimization solutions. It directly converts energy efficiency losses into intuitive economic costs through a cost calculation formula. This function allows ship operators to clearly see the economic losses caused by malfunctions and the cost savings that can be achieved after implementing optimization solutions, thus providing a more intuitive assessment of the actual value of optimization measures. Quantitative evaluation not only improves the scientific nature of operation and maintenance decisions but also enhances the importance that relevant personnel attach to energy efficiency optimization, promoting the platform's transformation from a technical tool to a value-creating tool, and helping ship operators achieve more refined cost control and energy efficiency management.

[0137] As a fifth embodiment of the present invention:

[0138] In specific implementation, compared with Embodiment 1, Embodiment 2, Embodiment 3 and Embodiment 4, the technical solution of this embodiment is to combine the solutions of Embodiment 1, Embodiment 2, Embodiment 3 and Embodiment 4.

[0139] Example 5 integrates all the functions of the previous four examples, forming a complete intelligent monitoring system for ship energy consumption, encompassing data collection, cleaning, analysis, fault identification, optimization scheme generation, and quantitative evaluation of results. This system ensures data quality and accurate fault identification while providing targeted optimization suggestions and quantitative effect assessments, achieving closed-loop optimization of ship energy consumption management. Through deep collaboration among multiple modules, the platform continuously explores the energy efficiency potential of equipment, minimizing energy loss and economic costs caused by hidden faults. It provides ship operators with an integrated energy efficiency management solution, comprehensively improving the safety, economy, and sustainability of ship operations.

[0140] It should be stated that all user data collected in this application was collected with the user's consent and authorization, and the use of user data is legal and compliant, and the use and processing of user data comply with the relevant laws, regulations and standards of the relevant regions.

[0141] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0142] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0143] The above formulas are all dimensionless calculations. Dimensionless calculation involves introducing a reference benchmark, such as the maximum, minimum, standard deviation, or theoretical extreme value of a physical quantity, to transform the original physical quantity into a dimensionless relative value. This value is usually mapped to a specific interval, such as [0,1] or [-1,1], which eliminates the influence of units while preserving the relative size relationship of the physical quantities. The formula is derived from software simulation based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0144] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0145] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. An intelligent monitoring platform for ship operation energy consumption data, characterized in that, include: The system includes a data acquisition module, a data preprocessing module, a correlation analysis module, a fault identification module, and a closed-loop management module. The data acquisition module is used to collect basic data corresponding to the operating status data and energy consumption data of various ship equipment. The data preprocessing module is used to standardize the collected data and filter out outliers; The correlation analysis module is used to construct the correlation coefficient between the equipment energy consumption baseline value and the operating condition; The fault identification module is used to verify the location of hidden performance loss through trend analysis and correlation with multiple devices; The closed-loop management module is used to generate early warnings and classify them.

2. The intelligent monitoring platform for ship operation energy consumption data according to claim 1, characterized in that: Operational status data includes the rotational speed of different equipment, the inlet and outlet pressures at different monitoring points, and the runtime of different data collection cycles; Energy consumption data includes fuel consumption at each energy consumption record and electricity consumption (E) at each power monitoring point. k .

3. The intelligent monitoring platform for ship operation energy consumption data according to claim 1, characterized in that: The data preprocessing module standardizes the collected operating status data and energy consumption data in the following way: The standardized data is obtained by subtracting the minimum value of the original basic data from the historical data collection period, and then dividing by the difference between the maximum and minimum values ​​of the original basic data in the historical data collection period. The basic data includes equipment speed, inlet and outlet pressure, running time, and fuel or electricity consumption.

4. The intelligent monitoring platform for ship operation energy consumption data according to claim 3, characterized in that: The outlier filtering rules of the data preprocessing module are as follows: If the original collected basic data is less than the minimum value of the basic data in the historical collection period minus 0.1 times the difference between the maximum and minimum values ​​of the same type of basic data in the historical collection period, or if the original collected basic data is greater than the maximum value of the same type of basic data in the historical collection period plus 0.1 times the difference between the maximum and minimum values ​​of the same type of basic data in the historical collection period, it is determined to be invalid data.

5. The intelligent monitoring platform for ship operation energy consumption data according to claim 1, characterized in that: The correlation analysis module calculates the baseline energy consumption value for a single device in the following way: The base value of energy consumption per unit time for the i-th device is obtained by dividing the sum of fuel consumption of the i-th device in each data collection cycle by the sum of running time of the i-th device in each corresponding data collection cycle. Where i is the equipment number, i = 1, 2, ..., n, and n is the total number of equipment; The method for calculating the correlation coefficient of energy consumption under multiple operating conditions is as follows: The energy consumption correlation coefficient of the i-th device under the j-th working condition is obtained by dividing the difference between the real-time energy consumption per unit time of the i-th device and the benchmark energy consumption per unit time of the i-th device by the benchmark energy consumption per unit time of the i-th device. Where j is the equipment's operating condition number, j=1, 2, ..., e, and e is the total number of operating conditions.

6. The intelligent monitoring platform for ship operation energy consumption data according to claim 5, characterized in that: When the correlation coefficient of the device is greater than the personalized identification threshold of the i-th device for three consecutive collection cycles, it is determined that there is a hidden fault causing energy efficiency loss. When the correlation coefficient is less than -3%, the equipment is determined to be in a low-load or abnormal energy-saving state.

7. The intelligent monitoring platform for ship operation energy consumption data according to claim 6, characterized in that: The personalized recognition threshold is determined as follows: First, statistical analysis is performed on all correlation coefficients of the i-th device under historical normal operating conditions, and the upper limit of its 95% confidence interval is calculated, which is used as the basic threshold. Then, multiply the base threshold by the preset correction coefficient α to obtain the personalized identification threshold for the i-th device.

8. The intelligent monitoring platform for ship operation energy consumption data according to claim 7, characterized in that: The fault identification module calculates the trend slope of the correlation coefficient as follows: First, calculate the average of all collection period indices, then calculate the average of all correlation coefficients for the i-th device. Next, for each collection period, subtract the average of the collection period indices from the index of that collection period to obtain the index deviation value. Subtract the average of the correlation coefficients of the i-th device from the correlation coefficient corresponding to that collection period to obtain the correlation coefficient deviation value. Then, multiply the index deviation value of each collection period by the corresponding correlation coefficient deviation value, sum them up, and divide by the sum of the squares of the index deviation values ​​of all collection periods to obtain the trend slope. The method for calculating the cumulative energy efficiency loss of the i-th device over u data collection cycles is as follows: The cumulative energy efficiency loss is obtained by subtracting the product of the energy consumption benchmark value per unit time and the running time of the corresponding collection cycle from the actual fuel consumption of the i-th device in each collection cycle, and then summing the above differences for all collection cycles. Where u is the preset quantity.

9. The intelligent monitoring platform for ship operation energy consumption data according to claim 8, characterized in that: The closed-loop management module calculates the cost corresponding to energy efficiency loss by multiplying the cumulative energy efficiency loss of the i-th device by the known fuel price per unit to obtain the cost corresponding to the energy efficiency loss of that device.

10. The intelligent monitoring platform for ship operation energy consumption data according to claim 5, characterized in that: Fault warnings are divided into three levels: When the correlation coefficient is greater than 10%, it is judged as a Level 1 warning and pushed to the ship operation and maintenance supervisor; When the correlation coefficient is greater than 5% and less than or equal to 10%, it is judged as a level 2 warning and pushed to the chief engineer; If the correlation coefficient is greater than 3% and less than or equal to 5%, it is judged as a Level 3 warning and pushed to the crew on duty.

Images