A shore power equipment control method and system based on digital twin

Abstract

The present invention discloses a shore power equipment management and control method and system based on digital twins, wherein the method includes processing the first operation monitoring data of each shore power equipment collected in real time to obtain temperature time series data, power time series data and sewage time series data respectively; processing the second operation monitoring data of the target docked ship collected in real time to obtain ship power time series data, constructing a target shore power digital twin model, obtaining a sewage monitoring key matrix and a power monitoring key matrix, calculating a power supply relative stability index and a power pollution contribution index, determining the shore power equipment to be selected, calculating the corresponding overload mitigation factor and ship-shore switching smoothness index, obtaining the target shore power equipment sequence, and displaying it in the target shore power digital twin model to perform real-time management and control of the shore power equipment. A shore power equipment management and control method and system based on digital twins provided by an embodiment of the present invention improves the management and control efficiency of shore power equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of shore power equipment control, and in particular to a shore power equipment control method and system based on digital twins. Background Art

[0002] Before a ship docks, it mainly uses the onboard auxiliary engine generators to generate electricity to meet the ship's electricity needs. The ship's auxiliary engine generators burn heavy oil or diesel. While consuming fuel to obtain power, the ship emits a large amount of polluting gases into the atmosphere, which seriously damages the ecological environment around the port area. The use of shore power equipment can provide ships with stable voltage and frequency, ensuring the safety and reliability of power supply while greatly reducing the fuel consumption of ships during docking, thereby reducing air pollutant emissions. Therefore, controlling the selection of shore power equipment after the ship docks will not only help improve the air quality of the port and its surrounding areas, reduce ship operating costs, but also promote the green transformation and sustainable development of the shipping industry.

[0003] However, since the use of shore power equipment is affected by many factors, and the shore power equipment may malfunction or experience abnormal conditions during operation, the management and control efficiency of the shore power equipment is low.

[0004] It can be seen that how to improve the control efficiency of shore power equipment has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0005] The present invention provides a shore power equipment management and control method and system based on digital twins to solve the technical problem that the use of shore power equipment is affected by various factors, and the shore power equipment may malfunction or abnormally situate during operation, resulting in low management and control efficiency of the shore power equipment, thereby improving the management and control efficiency of the shore power equipment.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a shore power equipment management and control method based on digital twins.

[0007] Based on the serialization processing technology, the first operation monitoring data of each shore power device collected in real time is processed to obtain temperature time series data, power time series data and sewage discharge time series data respectively; and, based on the serialization processing technology, the second operation monitoring data of the target berthing ship collected in real time is processed to obtain ship power time series data;

[0008] Inputting the temperature time series data, the power time series data, the sewage discharge time series data and the ship power time series data into the digital twin model to obtain a constructed target shore power digital twin model;

[0009] Processing all the pollution time series data according to the singular value decomposition technology to obtain a pollution monitoring key matrix after dimensionality reduction; and processing all the power time series data according to the singular value decomposition technology to obtain a power monitoring key matrix of each shore power equipment after dimensionality reduction;

[0010] Calculate the power supply relative stability index of each shore power device based on the volatility characteristics of all the power time series data; perform correlation analysis on the pollution monitoring key matrix and all the power monitoring key matrices to obtain the power pollution contribution index of each shore power device;

[0011] Performing a linear analysis on the power supply relative stability index and the power pollution contribution index, and determining a candidate shore power device according to the obtained continuous balanced power supply analysis results of each shore power device;

[0012] Based on the usage time of each of the selected shore power equipment and the change trend of the corresponding temperature time series data, a corresponding overload mitigation factor is calculated, wherein the overload mitigation factor reflects the impact of the usage time of the shore power equipment on the temperature;

[0013] The ship-shore switching smoothness index of each of the candidate shore power equipment is calculated based on the similarity characteristics and connectivity characteristics of the power time series data and the ship power time series data of the candidate shore power equipment, and all the candidate shore power equipment are prioritized based on the ship-shore switching smoothness index and the corresponding overload mitigation factor. The shore power equipment is controlled in real time based on the priority ranking results displayed in the target shore power digital twin model.

[0014] As one of the preferred solutions, all the pollution discharge time series data are processed according to the singular value decomposition technology to obtain a pollution discharge monitoring key matrix after dimensionality reduction, including:

[0015] Taking each of the pollution discharge time series data as a row, a pollution discharge monitoring matrix is ​​obtained;

[0016] Performing a first singular value decomposition process on the pollution monitoring matrix according to the singular value decomposition technology to obtain a corresponding first left singular matrix, a first singular value matrix and a first right singular matrix, and performing a screening process on the first singular value matrix to obtain corresponding pollution monitoring key eigenvalues;

[0017] Reconstructing the first left singular matrix, the pollution discharge monitoring key eigenvalues ​​and the first right singular matrix to obtain a pollution discharge monitoring key matrix;

[0018] The method processes all the power time series data according to the singular value decomposition technology to obtain a power monitoring key matrix of each shore power equipment after dimension reduction, including:

[0019] For each of the power time series data of each of the shore power equipment, each of the power time series data is taken as a row to obtain a power monitoring matrix of each of the shore power equipment;

[0020] Performing a second singular value decomposition process on each of the power monitoring matrices according to the singular value decomposition technology to obtain a corresponding second left singular matrix, a second singular value matrix, and a second right singular matrix, and performing a screening process on the second singular value matrix to obtain a corresponding key eigenvalue of power monitoring;

[0021] The second left singular matrix, the power monitoring key eigenvalues ​​and the second right singular matrix are reconstructed to obtain a power monitoring key matrix for each of the shore power equipment.

[0022] As one of the preferred solutions, the correlation analysis of the pollution monitoring key matrix and all the power monitoring key matrices is performed to obtain the power pollution contribution index of each shore power equipment, including:

[0023] Each row of the power monitoring key matrix of each shore power device is used as a key power monitoring time sequence to be tested, and each row of the sewage monitoring key matrix is ​​used as a key sewage monitoring time sequence to be tested;

[0024] Taking each mutation point in the key time series of power monitoring to be tested as a power mutation point, taking each mutation point in the key time series of pollution monitoring to be tested as a pollution mutation point;

[0025] Calculate the pollution co-frequency mutation index of the key time series for power monitoring to be tested according to the time intervals between all the power mutation points in the key time series for power monitoring to be tested and all the pollution mutation points in the key time series for pollution monitoring to be tested;

[0026] The average value of all the pollution same-frequency mutation indexes of each shore power device is used as the power pollution contribution index of each shore power device.

[0027] As one of the preferred solutions, the pollution co-frequency mutation index of the key time series of power monitoring to be tested is calculated according to the time intervals between all the power mutation points in the key time series of power monitoring to be tested and all the pollution mutation points in the key time series of pollution monitoring to be tested, including:

[0028] ;

[0029] in, is the pollution frequency mutation index of the key time series of the power monitoring to be tested, is an exponential function with a natural constant as base, is the number of power mutation points in the key time series of power monitoring to be tested, To obtain the minimum function, is the number of pollution mutation points in the key time series of pollution monitoring to be tested, is the time interval between two time points, is the i-th power mutation point in the key time series of power monitoring to be tested, It is the jth pollution discharge mutation point in the key time series of pollution discharge monitoring to be tested.

[0030] As one of the preferred solutions, the calculation of the power supply relative stability index of each shore power device based on the volatility characteristics of all the power time series data includes:

[0031] Based on the curve fitting results of each of the power time series data, the corresponding goodness of fit is calculated, the coefficient of variation of each of the power time series data is calculated, and based on the linear relationship between each of the coefficients of variation and the corresponding goodness of fit, the power fluctuation stability coefficient of each of the power time series data is calculated;

[0032] Taking the average value of all the power fluctuation stability coefficients of each shore power device as the power supply stability factor of each shore power device;

[0033] The maximum value of the power supply stability factors of all the shore power devices is used as the reference maximum power supply stability factor, and the difference between the reference maximum power supply stability factor and each power supply stability factor is used as the relative power supply stability index of each shore power device.

[0034] As one of the preferred solutions, the linear analysis of the power supply relative stability index and the power pollution contribution index is performed, and the shore power equipment to be selected is determined according to the continuous balanced power supply analysis results of each shore power equipment, including:

[0035] The ratio of the relative stability index of power supply of each shore power equipment and the corresponding power pollution contribution index is used as the continuous balanced power supply index of each shore power equipment;

[0036] The average value of all the continuous balanced power supply indexes is divided by the corresponding value of the maximum value as the screening ratio;

[0037] All the shore power equipment are arranged in descending order according to the corresponding continuous balanced power supply indexes to obtain a continuous balanced power supply equipment sequence, and the continuous balanced power supply equipment sequence is screened based on the screening ratio to obtain the shore power equipment to be selected.

[0038] As one of the preferred solutions, the calculation of the corresponding overload mitigation factor based on the usage time of each of the selected shore power equipment and the change trend of the corresponding temperature time series data includes:

[0039] Performing a first-order difference on the temperature time series data of each of the selected shore power equipment to obtain a temperature difference time series of each of the selected shore power equipment;

[0040] The sum of all elements in the temperature difference time series is taken as the overload temperature rise trend of each of the selected shore power equipment;

[0041] Based on the linear relationship between the overload temperature rise trend of each of the selected shore power equipment and the corresponding usage time, the overload mitigation factor of each of the selected shore power equipment is calculated.

[0042] As one of the preferred solutions, the ship-to-shore switching smoothness index of each of the candidate shore power equipment is calculated based on the similarity characteristics and connectivity characteristics of the power time series data and the ship power time series data of the candidate shore power equipment, including:

[0043] Calculate the average value and the corresponding standard deviation of each of the power time series data, and calculate the average value and the corresponding standard deviation of each of the ship power time series data;

[0044] The ship-shore power similarity index of each of the selected shore power equipment is calculated according to the similarity characteristics of the power time series data and the ship power time series data:

[0045] ;

[0046] in, is the ship-shore power similarity index of the kth candidate shore power equipment, is an exponential function with a natural constant as base, is the number of power monitoring data, is the average value of the mth power time series data of the kth shore power equipment to be selected, is the standard deviation of the mth power time series data of the kth selected shore power equipment, is the average value of the mth ship electrical time series data, is the standard deviation of the mth ship electrical time series data;

[0047] Predicting each of the ship power time series data to obtain a corresponding ship power prediction time series; splicing each of the power time series data with the corresponding ship power prediction time series to obtain a ship-to-shore switching prediction sequence for each of the power time series data;

[0048] Taking the average value of the Hurst exponents of all the ship-to-shore switching prediction sequences of each of the candidate shore power equipment as the ship-to-shore associated switching coefficient of each of the candidate shore power equipment;

[0049] Based on the linear relationship between each of the ship-shore power similarity indexes and the corresponding ship-shore associated switching coefficients, a ship-shore switching smoothness index of each of the selected shore power equipment is calculated.

[0050] As one of the preferred solutions, the priority sorting of all the selected shore power equipment based on the ship-shore switching smoothness index and the corresponding overload mitigation factor includes:

[0051] The ratio of the ship-to-shore switching smoothness index of each of the candidate shore power equipment and the corresponding overload mitigation factor is used as the shore power low-load smooth switching factor of each of the candidate shore power equipment;

[0052] All the candidate shore power equipment are prioritized according to the corresponding shore power low-load smooth switching factors.

[0053] Another embodiment of the present invention provides a shore power equipment management and control system based on digital twins, the system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements a shore power equipment management and control method based on digital twins as described above.

[0054] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0055] (1) Based on the serialization processing technology, the first operation monitoring data of each shore power device collected in real time is processed to obtain temperature time series data, power time series data and sewage time series data respectively; and, based on the serialization processing technology, the second operation monitoring data of the target docked ship collected in real time is processed to obtain ship power time series data, and the temperature time series data, power time series data, sewage time series data and ship power time series data are input into the digital twin model to obtain the constructed target shore power digital twin model, and the real-time monitoring data of each shore power device and the target docked ship are mapped into the virtual model, and then each shore power device and the target docked ship are analyzed in real time based on the target shore power digital twin model;

[0056] (2) Considering that the use of shore power equipment is affected by many factors, in order to eliminate the interference of non-critical factors and improve the efficiency of analysis, all sewage time series data are processed according to the singular value decomposition technology to obtain the key matrix of sewage monitoring after dimensionality reduction; and, all power time series data are processed according to the singular value decomposition technology to obtain the key matrix of power monitoring of each shore power equipment after dimensionality reduction, which improves the real-time performance of subsequent analysis of shore power equipment;

[0057] (3) The relative stability index of power supply for each shore power device is calculated based on the volatility characteristics of all power time series data; correlation analysis is performed on the key matrix of pollution monitoring and all key matrices of power monitoring to obtain the power pollution contribution index of each shore power device, and a linear analysis is performed on the relative stability index of power supply and the power pollution contribution index. Based on the analysis results of the continuous balanced power supply of each shore power device, the shore power device to be selected is determined. The stability and pollution of the power supply of the shore power device are comprehensively considered to preliminarily obtain the alternative plans for the shore power device. Subsequently, only the shore power device to be selected is analyzed, which improves the management and control efficiency of the shore power device.

[0058] (4) Based on the usage time of each candidate shore power equipment and the changing trend of the corresponding temperature time series data, the corresponding overload mitigation factor is calculated to evaluate the impact of the usage time of the shore power equipment on the temperature. The ship-to-shore switching smoothness index of each candidate shore power equipment is calculated based on the similarity characteristics and connectivity characteristics of the power time series data and the ship power time series data of the candidate shore power equipment. All candidate shore power equipment are prioritized based on the ship-to-shore switching smoothness index and the corresponding overload mitigation factor. The shore power equipment is controlled in real time based on the priority ranking results displayed in the shore power digital twin model. When further screening and sorting the candidate shore power equipment, the overload working risk and recovery ability of each shore power equipment after long-term operation are accurately evaluated to ensure that the shore power equipment operates in the best condition and improves its utilization efficiency. At the same time, by ensuring that the ship obtains a stable and reliable power supply during the berthing period, the ship can avoid equipment damage or power supply interruption caused by unstable power switching, thereby further improving the management and control efficiency of the shore power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic diagram of a shore power equipment control process based on digital twin in one embodiment of the present invention;

[0060] Figure 2 It is a schematic diagram of obtaining shore power equipment to be selected in one embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. 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.

[0062] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0063] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0064] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0065] An embodiment of the present invention provides a shore power equipment management and control method based on digital twins. For details, please refer to Figure 1 , Figure 1 The figure shows a schematic diagram of a shore power equipment control process based on digital twin in one embodiment of the present invention.

[0066] Step S1: Based on the serialization processing technology, the first operation monitoring data of each shore power equipment collected in real time is processed to obtain temperature time series data, power time series data and sewage time series data respectively; and, based on the serialization processing technology, the second operation monitoring data of the target docked ship collected in real time is processed to obtain ship power time series data, and a target shore power digital twin model is constructed.

[0067] Specifically, the use time of each shore power device is recorded, and the first operation monitoring data of each shore power device and the second operation monitoring data of the target docked ship are collected in real time.

[0068] It should be noted that the first operation monitoring data includes temperature, various power monitoring data and various pollution monitoring data, and the second operation monitoring data is various ship power monitoring data of the target berthed ship.

[0069] Arrange the same pollution monitoring data at all collection times in ascending order according to the collection time to obtain each pollution discharge time series data; arrange the same power monitoring data of each shore power equipment at all collection times in ascending order according to the collection time to obtain each power time series data; arrange the temperature of each shore power equipment at all collection times in ascending order according to the collection time to obtain the temperature time series data of each shore power equipment; arrange the same ship power monitoring data at all collection times in ascending order according to the collection time to obtain the ship power time series data.

[0070] It should be noted that digital twin technology can reflect the status of shore power equipment in real time. In order to ensure the safety and reliability of shore power equipment, protect the safety of personnel and property, and improve the utilization efficiency of shore power equipment, the use of shore power equipment is controlled through digital twin technology to avoid equipment overload or sudden shutdown causing impact on the power grid.

[0071] Furthermore, the temperature time series data, power time series data, sewage discharge time series data and ship power time series data are input into the digital twin model to obtain a constructed target shore power digital twin model.

[0072] Step S2: Process all pollution time series data according to the singular value decomposition technology to obtain the pollution monitoring key matrix after dimensionality reduction; and, process all power time series data according to the singular value decomposition technology to obtain the power monitoring key matrix of each shore power equipment after dimensionality reduction.

[0073] It should be noted that, considering that the use of shore power equipment is affected by many factors, in order to eliminate the interference of non-critical factors and improve the efficiency of analysis, it is necessary to first perform dimensionality reduction processing on the collected data.

[0074] Specifically, each pollution discharge time series data is taken as a row to obtain a pollution discharge monitoring matrix; the pollution discharge monitoring matrix is ​​subjected to a first singular value decomposition process according to the singular value decomposition technology to obtain the corresponding first left singular matrix, first singular value matrix and first right singular matrix; the first singular value matrix is ​​screened to obtain the corresponding pollution discharge monitoring key eigenvalues; the first left singular matrix, pollution discharge monitoring key eigenvalues ​​and the first right singular matrix are reconstructed to obtain the pollution discharge monitoring key matrix.

[0075] For each power time series data of each shore power device, each power time series data is taken as a row to obtain the power monitoring matrix of each shore power device; a second singular value decomposition process is performed on each power monitoring matrix according to the singular value decomposition technology to obtain the corresponding second left singular matrix, second singular value matrix and second right singular matrix, and the second singular value matrix is ​​screened to obtain the corresponding power monitoring key eigenvalues; the second left singular matrix, the power monitoring key eigenvalues ​​and the second right singular matrix are reconstructed to obtain the power monitoring key matrix of each shore power device.

[0076] It should be noted that the singular value decomposition technology is a well-known technology and will not be described in detail in this application.

[0077] Step S3: Calculate the relative stability index of power supply of each shore power device based on the volatility characteristics of all power time series data; perform correlation analysis on the key matrix of pollution monitoring and all key matrices of power monitoring to obtain the power pollution contribution index of each shore power device.

[0078] It should be noted that the stability of shore power equipment, as the main power source for ships during berthing, is directly related to the normal operation of various equipment on board. If the stability of shore power equipment is insufficient, it may cause frequent power outages or voltage fluctuations, thus affecting the normal operation of the ship and the safe operation of the equipment. Therefore, choosing shore power equipment with high stability is the key to ensuring the continuity of power supply.

[0079] Specifically, the corresponding goodness of fit is calculated based on the curve fitting result of each power time series data, the coefficient of variation of each power time series data is calculated, and based on the linear relationship between each coefficient of variation and the corresponding goodness of fit, the power fluctuation stability coefficient of each power time series data is calculated.

[0080] It should be noted that the calculation of the coefficient of variation and goodness of fit is a well-known technology and will not be elaborated in this application. Goodness of fit is used to evaluate the degree of fit of the data. When the coefficient of variation of the power time series data is larger and the goodness of fit is lower, it means that the fluctuation range of the power time series data is wider, the prediction ability of the regression model for the power time series data is worse, the fluctuation of the power time series data is more unstable, and the power fluctuation stability coefficient value is smaller.

[0081] As an embodiment of the present application, the ratio of the goodness of fit of each power time series data and the corresponding coefficient of variation is used as the power fluctuation stability coefficient of each power time series data.

[0082] Furthermore, the average value of all power fluctuation smoothness coefficients of each shore power device is taken as the power supply smoothness factor of each shore power device, the maximum value of the power supply smoothness factors of all shore power devices is taken as the reference maximum power supply smoothness factor, and the difference between the reference maximum power supply smoothness factor and each power supply smoothness factor is taken as the relative power supply smoothness index of each shore power device.

[0083] It should be further explained that the design of port shore power projects should follow the principles of safety, reliability, flexibility, efficiency, energy conservation, environmental protection, and economy, so as to meet the power demand of ships docked at the port and achieve energy conservation and emission reduction at the port.

[0084] Furthermore, each row of the power monitoring key matrix of each shore power equipment is used as the power monitoring key time series to be tested, each row of the pollution monitoring key matrix is ​​used as the pollution monitoring key time series to be tested, each mutation point in the power monitoring key time series to be tested is used as the power mutation point, and each mutation point in the pollution monitoring key time series to be tested is used as the pollution mutation point.

[0085] The pollution co-frequency mutation index of the key time series of power monitoring to be tested is calculated according to the time intervals between all power mutation points in the key time series of power monitoring to be tested and all pollution mutation points in the key time series of pollution monitoring to be tested:

[0086] ;

[0087] in, is the pollution frequency mutation index of the key time series of the power monitoring to be tested, is an exponential function with a natural constant as base, is the number of power mutation points in the key time series of power monitoring to be tested, To obtain the minimum function, is the number of pollution mutation points in the key time series of pollution monitoring to be tested, is the time interval between two time points, is the i-th power mutation point in the key time series of power monitoring to be tested, It is the jth pollution discharge mutation point in the key time series of pollution discharge monitoring to be tested.

[0088] The average value of all pollution same-frequency mutation indices of each shore power device is taken as the power pollution contribution index of each shore power device.

[0089] It should be noted that the smaller the time interval between each power mutation point in the key time series of power monitoring to be tested and each pollution mutation point in the key time series of pollution monitoring to be tested, the more likely it is that the key time series of power monitoring to be tested will mutate at the same time as the key time series of pollution monitoring to be tested, and the greater the pollution co-frequency mutation index value. The greater the pollution co-frequency mutation index of each power monitoring key time series of shore power equipment, the more likely it is that the shore power equipment will pollute the environment while supplying power.

[0090] Step S4: Perform a linear analysis on the relative stability index of power supply and the power pollution contribution index, and determine the shore power equipment to be selected based on the continuous balanced power supply analysis results of each shore power equipment.

[0091] Specifically, the ratio of the relative stability index of power supply of each shore power device to the corresponding power pollution contribution index is used as the continuous balanced power supply index of each shore power device, and the average value of all continuous balanced power supply indices is divided by the corresponding maximum value as the screening ratio.

[0092] All shore power equipment are arranged in descending order according to the corresponding continuous balanced power supply indexes to obtain a continuous balanced power supply equipment sequence, and the continuous balanced power supply equipment sequence is screened based on the screening ratio to obtain the shore power equipment to be selected.

[0093] It should be noted that by comprehensively considering the stability and pollution of the power supply of shore power equipment, the alternative options for shore power equipment are initially obtained, and only the selected shore power equipment is subsequently analyzed, which improves the management and control efficiency of shore power equipment.

[0094] For details, see Figure 2 , Figure 2 It is a schematic diagram of obtaining shore power equipment to be selected in one embodiment of the present invention.

[0095] Step S5: Based on the usage time of each candidate shore power equipment and the changing trend of the corresponding temperature time series data, the corresponding overload mitigation factor is calculated, and the ship-shore switching smoothness index of each candidate shore power equipment is calculated based on the similarity characteristics and connectivity characteristics of the power time series data of the candidate shore power equipment and the ship power time series data.

[0096] It should be noted that overloading shore power equipment will cause equipment overheating, damage and frequent failures, affecting the stability of the power system, increasing safety hazards and economic losses, and may also cause environmental pollution. Therefore, when selecting shore power equipment, you should try to avoid selecting overloaded shore power equipment.

[0097] Specifically, a first-order difference is made on the temperature time series data of each candidate shore power equipment to obtain a temperature difference time series of each candidate shore power equipment, and the sum of all elements in the temperature difference time series is taken as the overload temperature rise trend of each candidate shore power equipment.

[0098] Based on the linear relationship between the overload temperature rise trend of each candidate shore power equipment and the corresponding usage time, the overload mitigation factor of each candidate shore power equipment is calculated.

[0099] It should be noted that the greater the overload temperature rise trend of the selected shore power equipment and the longer the corresponding usage time, the more likely it is that the selected shore power equipment has been running for a long time and the temperature has risen sharply. If the selected shore power equipment continues to be used, a failure may occur, resulting in abnormal power supply.

[0100] As an embodiment of the present application, the product of the overload temperature rise trend of each candidate shore power equipment and the corresponding usage time is used as the corresponding overload mitigation factor.

[0101] Furthermore, the mean value and the corresponding standard deviation of each power time series data are calculated, the mean value and the corresponding standard deviation of each ship power time series data are calculated, and the ship-shore power similarity index of each candidate shore power equipment is calculated according to the similarity characteristics of the power time series data and the ship power time series data:

[0102] ;

[0103] in, is the ship-shore power similarity index of the kth candidate shore power equipment, is an exponential function with a natural constant as base, is the number of power monitoring data, is the average value of the mth power time series data of the kth shore power equipment to be selected, is the standard deviation of the mth power time series data of the kth selected shore power equipment, is the average value of the mth ship electrical time series data, is the standard deviation of the mth ship electrical time series data.

[0104] Each ship power time series data is predicted to obtain the corresponding ship power prediction time series; each power time series data and the corresponding ship power prediction time series are spliced ​​to obtain the ship-shore switching prediction sequence of each power time series data, and the average value of the Hurst exponents of all ship-shore switching prediction sequences of each candidate shore power equipment is used as the ship-shore associated switching coefficient of each candidate shore power equipment.

[0105] Based on the linear relationship between each ship-shore power similarity index and the corresponding ship-shore associated switching coefficient, the ship-shore switching smoothness index of each candidate shore power equipment is calculated.

[0106] It should be noted that the ship-shore power similarity index represents the similarity of power generation between the candidate shore power equipment and the ship power equipment of the target docked ship, and the ship-shore associated switching coefficient represents the smoothness of switching between the candidate shore power equipment and the ship power equipment of the target docked ship. The larger the ship-shore power similarity index and the larger the ship-shore associated switching coefficient, the more likely it is that when the ship power equipment of the target docked ship switches to the candidate shore power equipment for power generation, the fluctuation of power supply can be avoided, and seamless switching of ship power and shore power can be achieved, and the larger the ship-shore switching smoothness index value.

[0107] As an embodiment of the present application, the product of the ship-shore power similarity index of each candidate shore power device and the corresponding ship-shore associated switching coefficient is used as the ship-shore switching smoothness index of each candidate shore power device.

[0108] Step S6: Prioritize all candidate shore power equipment based on the ship-shore switching smoothness index and the corresponding overload mitigation factor, and manage the shore power equipment in real time based on the priority ranking results displayed in the shore power digital twin model.

[0109] Furthermore, the ratio of the ship-shore switching smoothing index of each candidate shore power equipment and the corresponding overload mitigation factor is used as the shore power low-load smooth switching factor of each candidate shore power equipment, and all candidate shore power equipment are prioritized according to the corresponding shore power low-load smooth switching factor to obtain the target shore power equipment sequence, which is displayed in the target shore power digital twin model to perform real-time management and control of the shore power equipment.

[0110] It should be noted that by accurately assessing the overload risk and recovery capacity of each shore power equipment after long-term operation, it is ensured that the shore power equipment operates in the best condition and improves its utilization efficiency. At the same time, by ensuring the calculation of the ship-to-shore switching smoothness index, the ship obtains a stable and reliable power supply during the docking period, avoiding equipment damage or power supply interruption caused by unstable power switching, and further improving the management and control efficiency of shore power equipment.

[0111] Another embodiment of the present invention provides a shore power equipment management and control system based on digital twins, the system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements a shore power equipment management and control method based on digital twins as described above.

[0112] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A shore power equipment management and control method based on digital twin, characterized in that: include: Based on the serialization processing technology, the first operation monitoring data of each shore power equipment collected in real time is processed to obtain temperature time series data, power time series data and sewage discharge time series data respectively; And, based on the serialization processing technology, the second operation monitoring data of the target berthing ship collected in real time is processed to obtain the ship electrical time series data; Inputting the temperature time series data, the power time series data, the sewage discharge time series data and the ship power time series data into the digital twin model to obtain a constructed target shore power digital twin model; Processing all the pollution discharge time series data according to the singular value decomposition technology to obtain a pollution discharge monitoring key matrix after dimensionality reduction; And, all the power time series data are processed according to the singular value decomposition technology to obtain a power monitoring key matrix of each shore power equipment after dimension reduction; Calculate the relative stability index of power supply of each shore power device based on the volatility characteristics of all the power time series data; perform correlation analysis on the pollution monitoring key matrix and all the power monitoring key matrices to obtain the power pollution contribution index of each shore power device; Performing a linear analysis on the power supply relative stability index and the power pollution contribution index, and determining a candidate shore power device according to the obtained continuous balanced power supply analysis results of each shore power device; Based on the usage time of each of the selected shore power equipment and the change trend of the corresponding temperature time series data, a corresponding overload mitigation factor is calculated, wherein the overload mitigation factor reflects the impact of the usage time of the shore power equipment on the temperature; Calculate the ship-shore switching smoothness index of each of the candidate shore power equipment based on the similarity characteristics and connectivity characteristics of the power time series data and the ship power time series data of the candidate shore power equipment, prioritize all the candidate shore power equipment based on the ship-shore switching smoothness index and the corresponding overload mitigation factor, and manage the shore power equipment in real time based on the priority ranking result displayed in the target shore power digital twin model; Among them, the correlation analysis of the pollution monitoring key matrix and all the power monitoring key matrices to obtain the power pollution contribution index of each of the shore power equipment includes: taking each row of the power monitoring key matrix of each of the shore power equipment as the power monitoring key time series to be tested, and taking each row of the pollution monitoring key matrix as the pollution monitoring key time series to be tested; taking each mutation point in the power monitoring key time series to be tested as a power mutation point, and taking each mutation point in the pollution monitoring key time series to be tested as a pollution mutation point; calculating the pollution co-frequency mutation index of the power monitoring key time series to be tested according to the time interval between all the power mutation points in the power monitoring key time series to be tested and all the pollution mutation points in the pollution monitoring key time series to be tested; taking the average value of all the pollution co-frequency mutation indices of each of the shore power equipment as the power pollution contribution index of each of the shore power equipment.

2. A shore power equipment management and control method based on digital twins according to claim 1, characterized in that: The method of processing all the pollution time series data according to the singular value decomposition technology to obtain a pollution monitoring key matrix after dimensionality reduction includes: taking each pollution time series data as a row to obtain a pollution monitoring matrix; performing a first singular value decomposition process on the pollution monitoring matrix according to the singular value decomposition technology to obtain a corresponding first left singular matrix, a first singular value matrix and a first right singular matrix; performing a screening process on the first singular value matrix to obtain a corresponding pollution monitoring key eigenvalue; performing matrix reconstruction on the first left singular matrix, the pollution monitoring key eigenvalue and the first right singular matrix to obtain a pollution monitoring key matrix; The method processes all the power time series data according to the singular value decomposition technology to obtain the power monitoring key matrix of each shore power device after dimensionality reduction, including: for each power time series data of each shore power device, each power time series data is taken as a row to obtain the power monitoring matrix of each shore power device; performs a second singular value decomposition process on each power monitoring matrix according to the singular value decomposition technology to obtain the corresponding second left singular matrix, second singular value matrix and second right singular matrix, performs screening process on the second singular value matrix to obtain the corresponding power monitoring key eigenvalue; performs matrix reconstruction on the second left singular matrix, the power monitoring key eigenvalue and the second right singular matrix to obtain the power monitoring key matrix of each shore power device.

3. A shore power equipment management and control method based on digital twins according to claim 1, characterized in that: The calculating of the pollution co-frequency mutation index of the key time series for power monitoring to be tested according to the time intervals between all the power mutation points in the key time series for power monitoring to be tested and all the pollution mutation points in the key time series for pollution monitoring to be tested comprises: ； in, is the pollution frequency mutation index of the key time series of the power monitoring to be tested, is an exponential function with a natural constant as base, is the number of power mutation points in the key time series of power monitoring to be tested, To obtain the minimum function, is the number of pollution mutation points in the key time series of pollution monitoring to be tested, is the time interval between two time points, is the i-th power mutation point in the key time series of power monitoring to be tested, It is the jth pollution discharge mutation point in the key time series of pollution discharge monitoring to be tested.

4. A shore power equipment management and control method based on digital twins according to claim 1, characterized in that: The calculating of the relative stability index of power supply of each shore power device based on the volatility characteristics of all the power time series data includes: Based on the curve fitting results of each of the power time series data, the corresponding goodness of fit is calculated, the coefficient of variation of each of the power time series data is calculated, and based on the linear relationship between each of the coefficients of variation and the corresponding goodness of fit, the power fluctuation stability coefficient of each of the power time series data is calculated; Taking the average value of all the power fluctuation stability coefficients of each shore power device as the power supply stability factor of each shore power device; The maximum value of the power supply stability factors of all the shore power devices is used as the reference maximum power supply stability factor, and the difference between the reference maximum power supply stability factor and each power supply stability factor is used as the relative power supply stability index of each shore power device.

5. The shore power equipment management and control method based on digital twin according to claim 1, characterized in that: The linear analysis of the power supply relative stability index and the power pollution contribution index is performed, and the shore power equipment to be selected is determined according to the continuous balanced power supply analysis results of each shore power equipment, including: The ratio of the relative stability index of power supply of each shore power equipment and the corresponding power pollution contribution index is used as the continuous balanced power supply index of each shore power equipment; The average value of all the continuous balanced power supply indexes is divided by the corresponding value of the maximum value as the screening ratio; All the shore power equipment are arranged in descending order according to the corresponding continuous balanced power supply indexes to obtain a continuous balanced power supply equipment sequence, and the continuous balanced power supply equipment sequence is screened based on the screening ratio to obtain the shore power equipment to be selected.

6. A shore power equipment management and control method based on digital twins according to claim 1, characterized in that: The calculating of the corresponding overload mitigation factor based on the usage time of each of the selected shore power equipment and the change trend of the corresponding temperature time series data includes: Performing a first-order difference on the temperature time series data of each of the selected shore power equipment to obtain a temperature difference time series of each of the selected shore power equipment; The sum of all elements in the temperature difference time series is taken as the overload temperature rise trend of each of the selected shore power equipment; Based on the linear relationship between the overload temperature rise trend of each of the selected shore power equipment and the corresponding usage time, the overload mitigation factor of each of the selected shore power equipment is calculated.

7. The shore power equipment management and control method based on digital twin according to claim 1, characterized in that: The calculating the ship-to-shore switching smoothness index of each of the candidate shore power equipment based on the similarity characteristics and connectivity characteristics of the power time series data and the ship power time series data of the candidate shore power equipment, respectively, includes: Calculate the average value and the corresponding standard deviation of each of the power time series data, and calculate the average value and the corresponding standard deviation of each of the ship power time series data; The ship-shore power similarity index of each of the selected shore power equipment is calculated according to the similarity characteristics of the power time series data and the ship power time series data: ； in, is the ship-shore power similarity index of the kth candidate shore power equipment, is an exponential function with a natural constant as base, is the number of power monitoring data, is the average value of the mth power time series data of the kth shore power equipment to be selected, is the standard deviation of the mth power time series data of the kth selected shore power equipment, is the average value of the mth ship electrical time series data, is the standard deviation of the mth ship electrical time series data; Predicting each of the ship power time series data to obtain a corresponding ship power prediction time series; splicing each of the power time series data with the corresponding ship power prediction time series to obtain a ship-to-shore switching prediction sequence for each of the power time series data; Taking the average value of the Hurst exponents of all the ship-to-shore switching prediction sequences of each of the candidate shore power equipment as the ship-to-shore associated switching coefficient of each of the candidate shore power equipment; Based on the linear relationship between each of the ship-shore power similarity indexes and the corresponding ship-shore associated switching coefficients, a ship-shore switching smoothness index of each of the selected shore power equipment is calculated.

8. The shore power equipment management and control method based on digital twin according to claim 1, characterized in that: The prioritizing of all the selected shore power equipment based on the ship-shore switching smoothness index and the corresponding overload mitigation factor includes: The ratio of the ship-to-shore switching smoothness index of each of the candidate shore power equipment and the corresponding overload mitigation factor is used as the shore power low-load smooth switching factor of each of the candidate shore power equipment; All the candidate shore power equipment are prioritized according to the corresponding shore power low-load smooth switching factors.

9. A shore power equipment management and control system based on digital twins, characterized in that: The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, a shore power equipment management and control method based on digital twins as described in any one of claims 1 to 8 is implemented.

Images