A port energy monitoring and analysis system

Abstract

This invention relates to the field of power grid monitoring technology, specifically a port energy monitoring and analysis system. The system includes an equipment electrical parameter acquisition module, a path association and partitioning module, an energy consumption trend extraction module, an energy consumption structure modeling module, and a monitoring tag output module. In this invention, by dividing the three-phase current sequence of equipment into slope segments to extract action segments, refined identification of electrical parameter behavior is achieved, enhancing data continuity and behavioral recognition. Combined with GNSS positioning, the operation trajectory is divided into specific areas and matched with corresponding electrical parameter behaviors, establishing a spatial linkage relationship between the path and the load, improving the accuracy of operation scenario identification, constructing typical energy consumption response profiles of equipment, and achieving structured modeling of energy consumption patterns under different operation scenarios. Based on the current response, load anomalies are judged and the operation segment status is marked, forming a closed-loop link from acquisition, identification, analysis to early warning, significantly improving remote monitoring accuracy and energy consumption identification capabilities.

Description

Technical Field

[0001] This invention relates to the field of power grid monitoring technology, and in particular to a port energy monitoring and analysis system. Background Technology

[0002] The field of power grid monitoring technology involves the real-time acquisition, analysis, and remote management of various parameters in power systems, such as voltage, current, power, and frequency. Core aspects include power quality monitoring, load status detection, power equipment operating status diagnosis, and power grid operation safety assessment. This is achieved by deploying multi-point sensing devices and utilizing data communication networks to perceive and centrally process the power system's status, thereby improving energy efficiency and system stability. Traditional port energy monitoring and analysis systems rely on manual meter reading or single-point data collection to record and report the power status of port equipment. The problems addressed by these systems include the common issues of disconnected information transmission due to the contact-based power supply structure in traditional port equipment, insufficient data dimensions for multiple devices, and reliance on manual reporting. Traditional methods use localized deployment of single electrical parameter sensors, combined with manual inspections, and breakpoint data entry and recording through the equipment management subsystem within the port's TOS system. This approach fails to establish a continuous data link and remote centralized management capabilities.

[0003] Current technologies rely on manual meter reading and single-point data collection to record the power status of port equipment. This fragmented approach results in coarse-grained information, failing to capture the power fluctuation trends during continuous operation. Traditional methods often employ localized deployment of single-parameter sensors, leading to delayed data collection cycles and a lack of multi-dimensional data support. This makes it difficult to reflect the load status of equipment at different operational stages in real time, posing risks of monitoring interruptions and data omissions. The information entry delays caused by manual inspections prevent the timely detection of critical energy consumption events, resulting in delays in assessing equipment operating efficiency and providing fault warnings. Furthermore, equipment management data relies on breakpoint entry through the TOS subsystem, failing to create a continuously tracked energy consumption trajectory and limiting the identification of abnormal load states. In real-world scenarios, such as when a tractor moves from a berth to a yard, the specific distribution of its energy consumption curve along different spatial paths cannot be clearly defined, leading to distorted assessments of energy utilization efficiency and ultimately impacting the port's overall energy scheduling and safety control capabilities. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a port energy monitoring and analysis system.

[0005] The equipment electrical parameter acquisition module acquires three-phase current data from the deployed current sensors on the quay crane, gantry crane, and tractor equipment. It extracts the current sequence in chronological order, divides the electrical parameter action segments based on the slope change of the current sequence, and constructs a set of electrical parameter action segments.

[0006] The path association partitioning module divides the operation trajectory into berthing section, yard section and loading and unloading section based on the set of electrical parameter action segments and the tractor GNSS positioning data. Based on time interval matching, it associates the electrical parameter action segments with the operation trajectory area to generate electrical parameter path area mapping results.

[0007] The energy consumption trend extraction module extracts the average current, maximum current, and current mutation frequency of the electrical parameter action segment in the path region from the electrical parameter path region mapping result, evaluates load fluctuations, and constructs a path region energy consumption trend feature set.

[0008] The power consumption structure modeling module generates equipment energy consumption response profiles for each work area based on the energy consumption trend feature set of the path area, and constructs a regional energy consumption response structure description group by combining the regional work labels.

[0009] The monitoring tag output module determines the load status of the electrical parameter operation segment based on the regional energy consumption response structure description group and the equipment rated current fluctuation range, marks the load status of the equipment operation segment, and generates a set of electrical parameter status tags for the equipment operation segment.

[0010] As a further embodiment of the present invention, the electrical parameter action segment set includes a three-phase current time series, slope change segments, and segment index information; the electrical parameter path region mapping result includes the electrical parameter action segment time interval, operation trajectory region label, and the correspondence between action segments and regions; the path region energy consumption trend feature set includes the average current, the maximum current, and the current mutation frequency; the region energy consumption response structure description group includes typical energy consumption response contours, region operation labels, and equipment energy consumption structure parameters; the equipment operation segment electrical parameter status label set includes load status labels, equipment action segment numbers, and abnormal load markers.

[0011] As a further aspect of the present invention, the device electrical parameter acquisition module includes:

[0012] The current sequence extraction submodule acquires the three-phase current sensor signals deployed on the quay crane, gantry crane, and tractor equipment, collects the raw three-phase current data in a continuous time period, arranges them in chronological order and marks the corresponding positions, and constructs a three-channel current change sequence by identifying the change trend between adjacent time periods, thereby obtaining the set of three-phase current sequence changes.

[0013] The electrical parameter action division submodule calls the set of changes in the three-phase current sequence, and determines whether the change slope of each phase current exceeds the set change slope threshold based on the change slope of each phase current between consecutive time points. When the condition is met, it is marked as an action point. Based on the distribution of time intervals between action points, the module identifies segments, delineates independent electrical parameter change areas, and generates a set of electrical parameter action change intervals.

[0014] The electrical parameter action segment set generation submodule extracts the change amplitude, maximum value and corresponding duration of the three-phase current within the set of electrical parameter action change intervals, obtains the difference value of electrical parameter action segments, filters action segments according to the value, and generates a set of electrical parameter action segments.

[0015] As a further aspect of the present invention, the path association partition module includes:

[0016] The action segment positioning submodule extracts the start and end times and device number of the action segment based on the electrical parameter action segment set, calls the trajectory point information within the corresponding time range in the GNSS positioning sequence, identifies the spatial location interval corresponding to the action segment, calculates the displacement trend change value between trajectory points, and generates the trajectory range value of the action segment.

[0017] The region segment identification submodule matches the spatial coordinates in the preset work area boundary division table according to the trajectory range value of the action segment, counts the coverage of trajectory points in different region boundaries, determines the region category based on the coverage ratio, and obtains the region matching label value.

[0018] The path region mapping submodule calls the region matching label value, organizes the action segments and region information under the tractor number, constructs a triplet dataset and arranges it in chronological order, obtains the trajectory segment feature mapping value, and obtains the electrical parameter path region mapping result according to the sorted path segment sequence.

[0019] As a further aspect of the present invention, the energy consumption trend extraction module includes:

[0020] Based on the electrical parameter path region mapping result, the current data extraction submodule extracts the time range and number information of the corresponding action segment in the path region, obtains the current sampling sequence in the action segment, detects the data continuity, and uses an interpolation algorithm to complete the discontinuous data. After collecting the current data of the action segment, it calculates the average and maximum values ​​to generate a set of current segment statistical values.

[0021] The load fluctuation calculation submodule identifies the change amplitude between consecutive points in the current sampling sequence based on the current segment statistical value set, determines whether it exceeds the preset mutation threshold, extracts the number of mutation points and constructs a mutation frequency index, collects the mutation frequency of all action segments in the path area, and generates a regional mutation frequency value set.

[0022] The trend feature construction submodule calls the current segment statistical value set and the regional change frequency value set to organize the current intensity and load fluctuation feature information in the path area, construct the feature expression structure, form the energy consumption trend performance between different areas, and generate the path area energy consumption trend feature set.

[0023] As a further aspect of the present invention, the power consumption structure modeling module includes:

[0024] The energy consumption profile construction submodule extracts the energy consumption sequence of the equipment in the working area based on the energy consumption trend feature set of the path area, identifies the energy consumption characteristics corresponding to the equipment operation stage, analyzes the change characteristics of energy consumption performance over time, calculates the energy consumption profile value of the equipment in the area, and generates a set of equipment energy consumption profile values.

[0025] The job tag fusion submodule calls the equipment energy consumption profile value group and the job tag information in the area, extracts the tag factor corresponding to the equipment, identifies the energy consumption distribution under different tags, analyzes the impact of tag attributes on energy consumption performance, calculates the energy consumption feature value under the tag category, and generates an energy consumption tag mapping relationship group.

[0026] The response structure generation submodule extracts the energy consumption feature information of devices in the region based on the energy consumption label mapping relationship group, collects the energy consumption performance of devices under the same label, analyzes the changing trend in different regions, calculates the response feature value under the region label combination, and generates a region energy consumption response structure description group.

[0027] As a further aspect of the present invention, the monitoring tag output module includes:

[0028] The load threshold judgment submodule extracts the current change sequence within the equipment operating section based on the regional energy consumption response structure description group, calculates the current offset value in combination with the rated current parameter, judges the load fluctuation of the operating section, and generates a load offset judgment value set.

[0029] The work segment status marking submodule calls the load offset judgment value set, combines the work segment current data and fluctuation threshold to judge the load status, marks it according to the status type, and obtains the work segment load status marking group.

[0030] The electrical parameter tag generation submodule integrates the equipment identifier and the work segment status according to the work segment load status tag group, extracts the electrical parameter information of the corresponding segment, assigns the corresponding status tag, and generates the equipment work segment electrical parameter status tag set.

[0031] As a further aspect of the present invention, the three-phase current data is time series data of three independent current channels collected by the current sensors of the quay crane, gantry crane, and tractor equipment, and its source is Hall current sensor or shunt resistor current detection device commonly used in industry.

[0032] The slope of the current sequence change is a numerical value representing the rate of change of current between adjacent moments, derived from the change analysis between adjacent sampling points in the current sequence.

[0033] The electrical parameter action segment is a continuous time interval divided based on the consistency of the direction of change of the current sequence. Each interval corresponds to a relatively independent equipment operation response process, which is derived from the slope characteristic analysis of the current sequence.

[0034] The GNSS positioning data is a sequence of location information collected by the global satellite navigation system equipment carried by the tractor, and its source is GPS, GLONASS or BeiDou positioning system;

[0035] The operation trajectory is a line segment of the equipment running path formed by connecting GNSS positioning data in chronological order.

[0036] The time interval matching is based on comparing the start and end times of the electrical parameter action segment with the timestamps of the operation trajectory records, and the time intervals that overlap are calibrated accordingly.

[0037] As a further aspect of the present invention, the current value feature refers to the statistical quantity extracted from the electrical parameter action segment that describes the current change law, including the average current, the maximum current, and the number of current abrupt changes.

[0038] The load fluctuation is a stability index value calculated based on the degree of change in current value characteristics.

[0039] The energy consumption response profile refers to the typical current change pattern curve of the equipment in a single operating area, which is formed based on the statistical characteristics of multiple electrical parameter action segments.

[0040] The energy consumption response structure description is a structured description entry composed of an energy consumption response outline and a work area label.

[0041] As a further aspect of the present invention, the rated current fluctuation range of the equipment is an allowable fluctuation range for operation set according to the rated current value on the equipment nameplate, which is used to distinguish between normal and abnormal load conditions.

[0042] The load status is a classification result based on whether the equipment operating current is within the range of rated current fluctuation;

[0043] The electrical parameter status label set is a set of labels formed by the load status identifiers corresponding to multiple equipment operating segments.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0045] In this invention, by dividing the three-phase current sequence of the equipment into slope segments to extract action segments, a refined identification of electrical parameter behavior is achieved, enhancing data continuity and behavior recognition. Combined with GNSS positioning, the operation trajectory is divided into specific areas and matched with corresponding electrical parameter behaviors, establishing a spatial linkage relationship between the path and the load, improving the accuracy of operation scenario identification, constructing a typical energy consumption response profile of the equipment, realizing structured modeling of energy consumption modes under different operation scenarios, judging load anomalies based on current response and marking the status of operation segments, forming a closed-loop link from collection, identification, analysis to early warning, significantly improving the accuracy of remote monitoring and energy consumption identification capabilities. Attached Figure Description

[0046] Figure 1 This is a system flowchart of the present invention;

[0047] Figure 2 This is a flowchart illustrating the acquisition process of the electrical parameter acquisition module of the device of the present invention;

[0048] Figure 3 This is a flowchart illustrating the acquisition process of the path association partition module in this invention.

[0049] Figure 4 This is a flowchart illustrating the acquisition process of the energy consumption trend extraction module of the present invention.

[0050] Figure 5 This is a flowchart illustrating the acquisition process of the power consumption structure modeling module of the present invention.

[0051] Figure 6 This is a flowchart illustrating the acquisition process of the monitoring tag output module of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0053] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0054] Port energy includes electrical energy: the power consumption of port equipment such as quay cranes, gantry cranes, and tractor equipment, including three-phase current data, voltage, and power parameters;

[0055] Fuel energy: fuel consumption for port equipment (such as generators, tractors, etc.), such as diesel and natural gas;

[0056] Renewable energy: such as the production and consumption of renewable energy sources like solar and wind power within the port;

[0057] Other forms of energy, such as cooling water and heat energy, involve other energy consumption during port operations.

[0058] Please see Figure 1 A port energy monitoring and analysis system includes:

[0059] The equipment electrical parameter acquisition module acquires three-phase current data recorded by current sensors deployed on quay cranes, gantry cranes, and tractor equipment, extracts current signals in chronological order, divides them into multiple electrical parameter action segments based on the slope of the current sequence change, and generates a set of electrical parameter action segments.

[0060] Three-phase current data is time-series data of three independent current channels collected by current sensors of quay cranes, gantry cranes, and tractor equipment. The source is Hall current sensors or shunt resistor current detection devices commonly used in industry.

[0061] A current signal refers to a continuous numerical sequence of current changes over time, output by a sensor and recorded by a data acquisition device. It can be in analog form or in digital form after analog-to-digital conversion.

[0062] The slope of the current sequence is a numerical value that represents the rate of change of current between adjacent moments. It is used to reflect the trend of equipment load change and is derived from the change analysis between adjacent sampling points in the current sequence.

[0063] The electrical parameter action segment is a continuous time interval divided based on the consistency of the direction of change of the current sequence. Each interval corresponds to a relatively independent equipment operation response process, which is derived from the slope characteristic analysis of the current sequence.

[0064] The path association partitioning module divides the operation trajectory into different operation areas, including "berthing section", "yard section" and "loading and unloading section", based on the set of electrical parameter action segments and the GNSS positioning data of the tractor. Based on time interval matching, it associates the electrical parameter action segments with the operation areas to generate electrical parameter path area mapping results.

[0065] GNSS positioning data is a sequence of location information collected by the global satellite navigation system equipment carried by the tractor, and its source is GPS, GLONASS or BeiDou positioning system;

[0066] The operation trajectory is a line segment of the equipment's operating path formed by connecting GNSS positioning data in chronological order, used to reflect the movement route of the tractor in the port area;

[0067] Time interval matching is based on comparing the start and end times of the electrical parameter action segment with the timestamps of the operation trajectory records, and the overlapping time intervals are calibrated accordingly.

[0068] The energy consumption trend extraction module extracts the current value characteristics of the electrical parameter action segment within the path region based on the electrical parameter path region mapping results, including the average value, maximum value and change frequency, evaluates the load fluctuation within the region, and generates a path region energy consumption trend feature set.

[0069] Current value characteristics refer to the statistical quantities extracted from the electrical parameter operation segment that describe the current change pattern, including the average current, the maximum current, and the number of current abrupt changes, which are used to characterize the load change characteristics.

[0070] Current surge frequency refers to the number of times an event occurs per unit time when the current change exceeds a preset threshold, and is used to reflect the severity of load changes during operation.

[0071] Load fluctuation is a stability index value calculated based on the degree of change in current value characteristics, used to distinguish between stable load segments and fluctuating load segments.

[0072] The power consumption structure modeling module utilizes the energy consumption trend feature set of the path area to generate a typical energy consumption response profile for each device in the work area. Combined with the area work label, it constructs a description of the energy consumption response structure of the device in the area and generates a group of area energy consumption response structure descriptions.

[0073] Energy consumption response profile refers to the typical current change pattern curve of equipment in a certain operating area. It is formed based on the statistical characteristics of multiple electrical parameter action segments and is used to describe the energy consumption change characteristics of equipment in the area.

[0074] The energy consumption response structure description is a structured description entry composed of an energy consumption response outline and a work area label, used to represent the energy consumption performance pattern of the equipment within the area.

[0075] The monitoring tag output module is based on the regional energy consumption response structure description group. According to the rated current fluctuation range of the equipment, it determines whether the load of each equipment operation segment is abnormal, marks the load status of the equipment operation segment, and generates a set of electrical parameter status tags for the equipment operation segment.

[0076] The rated current fluctuation range of the equipment is the permissible fluctuation range for operation set according to the rated current value on the equipment nameplate and the relevant standards of the International Electrotechnical Commission IEC60034, and is used to distinguish between normal load and over-limit conditions;

[0077] Load status is a classification result based on whether the equipment's operating current is within the range of the rated current fluctuation, used to indicate the load level of the equipment during the operating phase;

[0078] The electrical parameter status label set is a set of labels formed by the load status identifiers of multiple equipment operation segments, used to represent the distribution of electrical parameter operating status throughout the entire operation cycle.

[0079] The electrical parameter action segment set includes three-phase current time series, slope change segments, and segment index information; the electrical parameter path region mapping results include electrical parameter action segment time intervals, operation trajectory region labels, and the correspondence between action segments and regions; the path region energy consumption trend feature set includes average current, maximum current, and current mutation frequency; the region energy consumption response structure description group includes typical energy consumption response contours, region operation labels, and equipment energy consumption structure parameters; the equipment operation segment electrical parameter status label set includes load status labels, equipment action segment numbers, and abnormal load markers.

[0080] Please see Figure 2 The equipment electrical parameter acquisition module includes:

[0081] The current sequence extraction submodule acquires the three-phase current sensor signals deployed on the quay crane, gantry crane, and tractor equipment, collects the raw three-phase current data in a continuous time period, arranges them in chronological order and marks the corresponding positions, and constructs a three-channel current change sequence by identifying the change trend between adjacent time periods, thereby obtaining the set of three-phase current sequence changes.

[0082] Three-phase current sensors deployed on quay cranes, gantry cranes, and tractor units are crucial for acquiring electrical parameter data. Each piece of equipment is equipped with an independently numbered sensor, and the data acquisition process is determined through parameter configuration. Taking the CT-A01 current sensor configured on the quay crane as an example, its initial no-load current is 18.6A, the time interval is set to 0.2 seconds, and the number of data collection points is 10. The CT-B02 sensor configured on the gantry crane has an initial current of 25.4A, and the CT-C03 sensor configured on the tractor unit has an initial current of 12.8A. The data acquisition configurations are kept consistent, such as the time interval and the number of data points, to ensure a uniform sampling period for all three types of equipment, facilitating subsequent comparative analysis. After the equipment starts, the system records the A, B, and C phase current values ​​at set intervals. The acquired data is timestamped and automatically labeled with channels, forming a standard three-channel time series. The following is the data acquisition initialization setting table:

[0083] Table 1. Equipment Current Acquisition Configuration Table:

[0084] ;

[0085] As shown in Table 1, each device collects 10 data points, and each complete data collection cycle is 2 seconds. The device generates a dynamic current response signal during operation. By calculating the difference in current values ​​between each adjacent sampling point, a change segment is formed. For example, the A-phase current of the quay crane device is 18.6A to 19.3A between t=0.2s and t=0.4s, with a change value of 0.7A. However, the system does not directly use the change value, but defines the change segment as a current change sequence ΔI. The system constructs complete ΔI_a, ΔI_b, and ΔI_c sequences in chronological order. During execution, the system generates a set of change segments for each channel. For example, for the A-phase channel of the quay crane CT-A01 device, 10 sampling points form 9 ΔI segments, resulting in a set of three-phase current sequence change values ​​composed of change segments from each channel. This set will be used for subsequent identification of changes in electrical parameters and data analysis. The constructed sequence structure can be abstractly represented as a matrix I_seq, which is a three-dimensional matrix of [device × channel × time period], facilitating standardized operations among multiple devices and thus forming a unified data input standard.

[0086] The electrical parameter action division submodule calls the set of three-phase current sequence changes, and determines whether the change slope of each phase current between consecutive time points exceeds the set change slope threshold. When the condition is met, it is marked as an action point. Based on the distribution of time intervals between action points, the module identifies segments, delineates independent electrical parameter change areas, and generates a set of electrical parameter action change intervals.

[0087] To determine whether the current fluctuations in each channel during operation meet the action recognition criteria, the system uses the continuous current change slope μ as the action trigger. The current change slope for each time period is calculated as the ratio of the difference between adjacent currents to the time interval. Taking the CT-A01 quay crane as an example, if the first segment ΔI is 0.7A and the time interval is 0.2 seconds, the corresponding slope μ is 3.5A / s. This value represents the current rise rate within that segment. The slopes μ_1 to μ_9 are calculated by sampling the entire segment of the equipment and compared segment by segment. The system presets the slope mutation threshold μ_thr for action judgment to be 2.8A / s. This value is derived from the classification of experimental data of the quay crane, gantry crane, and tractor under typical operating conditions. The reference results are as follows: In the stable operating range, the slope distribution is concentrated within 1.5A / s. During load changes, the frequency of instantaneous slopes exceeding 3.0A / s increases significantly. Based on this, a threshold of 2.8 A / s is set as the threshold for judging action mutations. The slope sequence of each channel is traversed. Any point where the difference between the current slope and the previous slope exceeds the threshold is marked as an action point. For example, if the slope of the 4th segment in a channel is 4.1 A / s and the previous segment is 1.2 A / s, the difference is 2.9 A / s, which exceeds the set threshold. This segment is then recorded as an action point. Subsequently, all action points are classified by time, and the interval between action points is used as the clustering basis. The maximum interval threshold is set to 1.5 seconds. In the CT-C03 device for tractor vehicles, if action points occur at t=0.4s and t=1.6s, they are considered as two independent action segments because the interval exceeds the threshold. The multiple output action segments are defined as a set of electrical parameter action change intervals. Each interval has a time range, the channel it belongs to, current slope mutation information and its data index, which can be used for subsequent comprehensive difference determination and action segment extraction.

[0088] The electrical parameter action segment set generation submodule extracts the specific calculation formulas for the change amplitude, maximum value, and corresponding duration of the three-phase current in each interval based on the set of electrical parameter action change intervals:

[0089] ;

[0090] The calculation obtains the comprehensive difference value of the electrical parameter action segment, and the action segment is filtered according to the value to generate a set of electrical parameter action segments;

[0091] in, This represents the overall difference in the action segment of the electrical parameters. Representing action segments respectively Inner Changes in three-phase current at any given time. This represents the length of time corresponding to that moment. Action segments Maximum value of internal three-phase current, The number of effective time slices within an action segment. For absolute value operations, For square root operations, This indicates a cumulative summation;

[0092] Based on the identified set of electrical parameter change intervals, it is necessary to further extract effective action segments to quantify the change level of three-phase current within the action segment. The system uses three types of indicators—current change, duration, and inter-channel difference—to construct a difference measurement index S. Taking a certain action segment in the CT-C03 equipment of the tractor as an example, four time slices are selected, and the three-phase current change data are as follows: Phase A ΔI is [1.5, 1.8, 2.0, 1.6] A, Phase B ΔI is [1.2, 1.3, 1.4, 1.2] A, and Phase C ΔI is [1.7, 1.9, 2.1, 2.0] A. Each time slice is 0.2 seconds long, and the maximum values ​​of the three-phase current within the action segment are 14.8 A, 13.9 A, and 16.2 A, respectively. Substituting these values ​​into the following formula, the calculation is performed:

[0093] Molecular calculations:

[0094] ;

[0095] Denominator calculation:

[0096] ;

[0097] ;

[0098] ;

[0099] The calculation result is:

[0100] ;

[0101] This value indicates that there is a significant difference in the three-phase current of the action segment. If the system sets the judgment threshold to 2.0, the segment is judged as a characteristic action segment and written into the electrical parameter action segment set. Its difference value S will be used as one of the basic inputs for subsequent equipment behavior judgment or power utilization evaluation.

[0102] The calculation logic of this formula aims to measure the overall activity level of the three-phase current changes within the action segment and the structural differences between channels. The numerator reflects the overall energy disturbance level by accumulating the changes in the three-phase current within each time slice. Multiplying this by the corresponding time slice length reflects the contribution intensity of each current change to the total difference at different durations, giving the changes a time-weighted effect. Finally, summing over all time slices yields a comprehensive disturbance expression. The first term in the denominator is the sum of the time slice lengths, which serves as a standardization and normalization function, eliminating the influence of different action segments on duration and making different length segments comparable. The second term in the denominator calculates the difference between each pair of the maximum values ​​of the three-phase currents, sums them, and then takes the square root to form the intensity factor of current asymmetry, which is used to measure the degree of imbalance between the three-phase channels. The square root operation is used to amplify the influence weight of the current difference between channels on the result, maintaining the nonlinear response. Thus, the formula as a whole becomes the ratio of "normalized energy disturbance" to "structural difference," thereby reflecting the comprehensive differences in the electrical parameter action segments in terms of time, energy, and channel distribution.

[0103] The comprehensive difference value of electrical parameter operating segments is a quantitative indicator used to measure the relationship between the overall change amplitude and phase asymmetry of the three-phase current of the equipment within a certain time period. This value comprehensively reflects the degree of structural difference between the current fluctuation intensity and the three-phase current within the operating segment. Essentially, it is the ratio of the total current disturbance after normalization to the maximum difference of the three-phase current, thus taking into account both the absolute value of the current change and the relative relationship between the current channels. When this value is high, it indicates that there is a significant dynamic current response within the operating segment, accompanied by a certain degree of channel inconsistency. It is suitable for identifying key electrical parameter segments with sudden changes or abnormal states during operation and is an important basis for subsequent equipment condition assessment, power distribution monitoring, or load characteristic identification.

[0104] Please see Figure 3 The path association partition module includes:

[0105] The action segment positioning submodule is based on the set of electrical parameter action segments. It extracts the start and end times and device numbers of the action segments, calls the trajectory point information within the corresponding time range in the GNSS positioning sequence, identifies the spatial location interval corresponding to the action segment, calculates the displacement trend change value between trajectory points, and generates the trajectory range value of the action segment.

[0106] Based on the set of electrical parameter action segments, the start and end times of each action segment and the corresponding tractor equipment number are extracted. The time interval of each action segment is matched one-to-one with the GNSS trajectory data. Data rows whose timestamps fall within the action segment interval are selected from the trajectory point sequence to construct the trajectory segment corresponding to that action segment. For each segment, the coordinates of the first and last trajectory points are extracted as the start and end coordinates. The coverage distance of the trajectory segment on the spatial axis is identified, and the duration is determined by combining the action segment time data. A dataset of attribute values ​​for multiple trajectory segments is constructed. During this operation, the number information of each segment must be retained for subsequent construction of a multi-segment time-series data structure. The following is an example of a GNSS sampling segment with tractor number T03, where key data from its four action segments are extracted and displayed in a table:

[0107] Table 2 GNSS trajectory segment sampling table:

[0108] ;

[0109] As shown in Table 2, the trajectory segment with action segment number 1 has a starting point of 100.0m, an ending point of 115.2m, a trajectory length of 15.2m, and a duration of 10s. This represents the effective movement distance and time span of the equipment in space within this segment. Through this type of processing, complete trajectory segment information can be generated, and the trajectory range value of the action segment can be obtained.

[0110] The region segment identification submodule matches the spatial coordinates in the preset work area boundary division table according to the trajectory range value of the action segment, counts the coverage of trajectory points in different region boundaries, determines the region category based on the coverage ratio, and obtains the region matching label value.

[0111] Based on the trajectory range value of the action segment, the start and end coordinates of each trajectory segment in Table 2 are retrieved, and the GNSS trajectory point data within that interval is extracted. The spatial coordinates of each trajectory point are then matched sequentially with the work area boundary set, which includes the coordinate range of the closed boundaries of the berthing section, the yard section, and the loading and unloading section. A point attribution determination is performed on the trajectory points, based on whether the point coordinates are located within a certain polygon boundary. The attribution category of all trajectory points within the action segment is counted. If the proportion of trajectory points of a certain category exceeds a set attribution determination threshold, the action segment is classified as the corresponding work segment. This threshold is set to 55%, and this value is determined by... In the early stages, trajectory distribution experiments were conducted on typical work areas. Among the 50 actual trajectory tests, more than 70% of the trajectory points were located in the main area, accounting for more than 55%. This was used as experimental sample support. This setting meets the reproducibility requirements of the attribution determination. For example, if the action segment number is 2, its starting point is 120.5m, its ending point is 133.7m, and the trajectory length is 13.2m, and if a total of 30 trajectory points are collected in this segment, and 17 of them fall into the yard boundary, then the attribution ratio is 56.7%, which is higher than the 55% threshold. Therefore, this segment is classified as a yard segment. After all action segments are executed, the system outputs the corresponding area label for each segment in sequence to obtain the area matching label value.

[0112] The path region mapping submodule calls the region matching label value, organizes the action segments and region information under the tractor number, and constructs a triplet dataset, which is then arranged in chronological order. The specific calculation formula is as follows:

[0113] ;

[0114] The feature mapping value of the trajectory segment is obtained by calculation, and the path segment sequence is sorted according to the value to obtain the electronic parameter path region mapping result;

[0115] in, Indicates tractor Trajectory segment feature mapping values ​​under multiple action segments Indicates tractor The The length of the trajectory segment corresponding to each action segment Indicates the duration of this action segment.

[0116] , Indicates the first The maximum and minimum trajectory coordinates in the action segment, Indicates tractor Total number of action segments, absolute value sign This represents the sum of squares of the absolute values ​​of the path feature strengths. This represents the total degree of change in the path space;

[0117] The calculation steps are as follows, based on the data in Table 2:

[0118] First step, calculate the unit velocity value:

[0119] Action segment 1: 15.2 ÷ 10.0 = 1.52;

[0120] Action segment 2: 13.2 ÷ 8.0 = 1.65;

[0121] Action segment 3: 16.4 ÷ 12.0 ≈ 1.367;

[0122] Action segment 4: 13.7 ÷ 10.0 = 1.37;

[0123] Total numerators: 1.52 + 1.65 + 1.367 + 1.37 ≈ 5.907;

[0124] The second step is to calculate the squares of the coordinate differences and sum them:

[0125] Section 1: |115.2-100.0|²=231.04;

[0126] Section 2: |133.7-120.5|²=174.24;

[0127] Section 3: |157.6-141.2|²=268.96;

[0128] Section 4: |173.1-159.4|²=187.69;

[0129] The sum of the squared terms in the denominator is 861.93, which is approximately 29.36 after the square root.

[0130] The third step is to calculate the eigenvalues:

[0131] ;

[0132] The calculated feature mapping value of the trajectory segment is 0.2013. This value serves as a comprehensive feature index of the tractor T03's path performance in action segments 1 to 4. Subsequently, this value can be compared with the regional standard value. For example, if the system distinguishes the interval standard of path density as [0.15~0.25], then the current value is in the effective mapping segment. The system uses this value as the input for the electronic parameter path region mapping judgment to obtain the electronic parameter path region mapping result.

[0133] The formula's operational logic is based on the structural and dynamic characteristics of the tractor's trajectory performance in different action segments. The numerator is calculated by dividing the trajectory length of each action segment by its duration, forming the displacement per unit time, which measures the motion intensity of each segment. This value is then summed across all action segments to reflect the overall activity level of the tractor within the entire group of action segments. The denominator first calculates the difference between the coordinates of the start and end points of the trajectory in each action segment, reflecting the spatial span of each segment. Then, the squares of the coordinate differences of each segment are summed to obtain the overall spatial expansion of the path. Finally, the square root of this sum is taken to maintain consistency with the molecular dimension and weaken the extreme influence of individual large-span segments. The entire structure constitutes a normalized ratio, where the summation operation integrates the trajectory performance of each segment, the division structure normalizes the unit time, the square root operation balances spatial scale fluctuations, and the absolute value operation ensures the non-negativity of the result, thus forming a characteristic expression that can quantify the intensity of the tractor's path segments.

[0134] The trajectory segment feature mapping value is a quantitative indicator used to measure the intensity and spatial distribution characteristics of the tractor's path motion within multiple action segments. This value comprehensively reflects the proportional relationship between the cumulative displacement of the trajectory per unit time and the spatial expansion range of the trajectory. Essentially, it is a unified expression of the motion behavior of different path segments under the normalized time dimension. When the value is large, it indicates that the tractor has high motion density or continuous propulsion characteristics in each action segment, while the spatial variation span is relatively concentrated. Conversely, it indicates that the trajectory has characteristics such as slow movement or dispersed segments. This indicator can serve as an important quantitative basis for judging the continuity of the path, the stability of the segment mapping, and the accuracy of the work area attribution, and is used to support the extraction of key features in the process of path area division and scheduling planning.

[0135] Please see Figure 4 The energy consumption trend extraction module includes:

[0136] The current data extraction submodule extracts the time range and number information of the corresponding action segment based on the electrical parameter path region mapping result, obtains the current sampling sequence within the action segment, detects the data continuity, and uses an interpolation algorithm to complete the discontinuous data. After collecting the current data of the action segment, it calculates the average and maximum values ​​to generate a set of current segment statistical values.

[0137] Based on the electrical parameter path region mapping results, the action segment number and corresponding time range associated with each path region are extracted. Current data sequences for each action segment within the sampling time period are obtained sequentially. After acquisition, it is determined whether there are missing or inconsistent intervals in the current data corresponding to each action segment. If there are issues such as jumps in the sampling time interval or duplicate sampling values ​​in a certain data segment, interpolation is performed to fill in the missing segments, and abnormal points are removed. After processing, the valid current data are categorized and collected according to the action segment number and assigned to the corresponding path region. Based on this, the average and maximum current values ​​for each action segment are calculated sequentially for subsequent trend analysis. In the modeling process, if the number of sampling points is less than 40, or the proportion of abnormal sampling points exceeds 10%, the action segment is excluded from the current feature extraction range. For example, in path region A1, action segments D01 and D02 collected 50 and 60 sampling points respectively, both meeting the data integrity judgment criteria. However, in path region A2, action segment D03 only collected 45 points, and there were 5 abnormal points, exceeding the set 10% threshold. Therefore, it was excluded from subsequent analysis. D04 collected 55 points completely and was retained. The statistics of this part of the sampling data are shown in Table 3. The table lists the current data status of typical action segments in different path regions:

[0138] Table 3. Current sampling information for the path region:

[0139] ;

[0140] The data in Table 3 serves as a reference for judging current integrity. The rule for judging anomalies is that the current sampling value fluctuates by more than 50A / s within three consecutive points. Combined with the above processing, a set of current segment statistics is generated.

[0141] The load fluctuation calculation submodule identifies the change amplitude between consecutive points in the current sampling sequence based on the current segment statistical value set, determines whether it exceeds the preset mutation threshold, extracts the number of mutation points and constructs a mutation frequency index, collects the mutation frequency of all action segments in the path area, and generates a regional mutation frequency value set.

[0142] Based on the current segment statistical value set, the current sampling sequence of the effective action segment in each path area is retrieved sequentially. The sampling points in the same segment are sequentially numbered, and the current change amplitude between adjacent sampling points is extracted. It is determined whether the change amplitude exceeds the mutation judgment standard value. The mutation standard value is set to 10A. Based on the experimental analysis of the current fluctuation law in the previous period, the classification method is that the change amplitude is greater than 10A and is determined to be a mutation point, and less than or equal to 10A and is determined to be a normal point. The number of mutation points in each segment is converted into a mutation frequency index by the ratio of the total number of sampling points. Then, the mutation frequency of each action segment is collected according to the path area number to construct the mutation fluctuation information matrix corresponding to the path area. For example, in the A1 area, D01 has a total of 50 sampling points, 4 mutation points, and a mutation frequency of 0.08. D02 has a total of 8 mutation points detected, with a sampling point count of 60 and a mutation frequency of 0.133, which is within the judgment interval of 0.05~0.15. In the A2 area, D04 has no mutation points and a mutation frequency of 0. Combining the mutation frequency set of the effective segments in the path area, a regional mutation frequency value set is generated.

[0143] The trend feature construction submodule calls the current segment statistical value set and the regional change frequency value set, organizes the current intensity and load fluctuation feature information in the path area, constructs the feature expression structure, forms the energy consumption trend performance between different areas, and generates the path area energy consumption trend feature set.

[0144] By calling the current segment statistical value set and the regional change frequency value set, the average current, maximum current, and change frequency index of the retained action segments in each path region are extracted to construct the energy consumption feature structure at the regional level. The current intensity value and fluctuation frequency value of multiple action segments in the region are combined and calibrated, and the feature values ​​are classified according to different intensity ranges and fluctuation ranges. The current intensity range is defined as 0 to 20A as low intensity segment, 20A to 35A as medium intensity segment, and above 35A as high intensity segment. The change frequency is less than 0.05 as stable segment, 0.05 to 0.10 as fluctuating segment, and greater than 0.10 as high-variable segment. The current level and fluctuation level of each segment in each region are jointly labeled and mapped to the regional level dataset. The combined energy consumption trend index under each region is output, the feature comparison structure between path regions is completed, and the energy consumption trend feature set of path regions is generated.

[0145] Please see Figure 5 The power consumption structure modeling module includes:

[0146] The energy consumption profile construction submodule extracts the energy consumption sequence of the equipment in each working area based on the energy consumption trend feature set of the path area, identifies the energy consumption characteristics corresponding to the equipment operation stage, analyzes the changes in its energy consumption performance over time, calculates the energy consumption profile value of the equipment in the area, and generates the equipment energy consumption profile value group.

[0147] Based on the energy consumption trend feature set of the path area, the energy consumption sequence of the equipment in each working area is extracted. First, the mapping relationship between the equipment and the path area is established. According to the equipment operation record, the energy consumption trend data of the corresponding time period is extracted and organized into a multi-segment energy consumption performance sequence indexed by the equipment number. The continuous operation segment of the equipment in different working stages in a specific area is identified, and the unit time energy consumption change trend of the equipment in each segment is obtained. The duration of each segment is recorded. After the data is processed, the change amplitude of its energy consumption sequence is judged. By analyzing the degree of fluctuation between unit time energy consumption values, the output stability of the equipment operation process is identified. The equipment energy consumption performance is divided into two categories: stable and fluctuating. In this process, the volatility rate is used as the classification basis to classify the energy consumption data into different fluctuation ranges, providing a data foundation for subsequent label fusion and response modeling. The operation of sample equipment E01 and E02 in area Z1 is shown in Table 4.

[0148] Table 4. Sample Data Table of Equipment Energy Consumption Profile:

[0149] ;

[0150] According to the data shown in Table 4, the energy consumption trends of equipment E01 were similar in the three operations, and the volatility was in a stable range. Equipment E02 was classified as a volatile equipment because its volatility was higher than the set distinction threshold. After completing the above steps, the operating behavior of each equipment in the corresponding area was uniformly converted into a standardized profile structure to generate a set of equipment energy consumption profile values.

[0151] The job tag fusion submodule calls the equipment energy consumption profile value group and the job tag information in the area, extracts the tag factor corresponding to the equipment, identifies the energy consumption distribution under different tags, analyzes the impact of tag attributes on energy consumption performance, calculates the energy consumption feature value under the tag category, and generates an energy consumption tag mapping relationship group.

[0152] The system retrieves equipment energy consumption profile value groups and regional operation tag data. First, it matches the operation tag bound to the equipment number, extracting the tag number, operation attribute fields, and region information to form a bidirectional index structure between equipment and tags. This identifies sets of equipment with the same tag number, classifies and merges their energy consumption profile features, calculates the mean and fluctuation range within each group after categorizing the equipment energy consumption values, and compares them horizontally with other tag groups to determine the effectiveness of tag attributes in distinguishing energy consumption patterns. For example, equipment E01 is bound to tag A1, and its energy consumption profile value is 6.2; equipment E02 is bound to tag A1, and its energy consumption profile value is 6.2. Label B1 has an energy consumption profile value of 6.6. The device sets under the two labels show significant differences in fluctuation levels and central tendency. These device sets can be grouped according to the label number. By comparing the differences in energy consumption distribution between the devices under labels A1 and B1, if the data within a label is concentrated and the differences between labels are large, it indicates that the label attribute has a high degree of distinguishability for energy consumption behavior. After merging the energy consumption profiles under all labels, an energy consumption response set with the label number as the primary key is established. The device number and energy consumption value are associated to realize the conversion of device energy consumption data to the label dimension and generate an energy consumption label mapping relationship group.

[0153] The response structure generation submodule extracts the energy consumption characteristic information of devices in the region based on the energy consumption label mapping relationship group, collects the energy consumption performance of devices under the same label, analyzes the changing trend of their different regions, calculates the response characteristic value under the region label combination, and generates the region energy consumption response structure description group.

[0154] Based on the energy consumption label mapping relationship group, the energy consumption characteristic data of the devices in each region are summarized. The device sets in different regions are extracted according to the label category, and the energy consumption response distribution information of the devices under each label is organized. On this basis, the combination traversal of labels and regions is performed. The average energy consumption response value and fluctuation level are calculated for each combination. The concentration and offset characteristics in the response distribution are identified. According to the set response level classification rules, the response structure of each label combination is classified into different level segments, such as: stable segment, fluctuating segment, and high-variable segment. The classification is also combined with the distribution of the number of devices. Then, the response structure expression form of all label combinations under each region is organized. The label number, device number set, region number and corresponding response index are extracted and uniformly mapped to the region response structure matrix to construct an energy consumption response data structure oriented to region classification. This forms a multi-label energy consumption response record with region number as the dimension and generates a region energy consumption response structure description group.

[0155] Please see Figure 6 The monitoring tag output module includes:

[0156] The load threshold judgment submodule extracts the current change sequence within the equipment operating section based on the regional energy consumption response structure description group, calculates the current offset value in combination with the rated current parameter, judges the load fluctuation of each operating section, and generates a load offset judgment value set.

[0157] Based on the regional energy consumption response structure description group, current variation data of equipment in each operating segment is extracted. First, the operating segments are categorized and summarized according to equipment number. The start and end times of each segment are extracted, and current signal sequences within continuous segments are divided along a time axis. Current sampling values ​​at each time point in these sequences are obtained. Then, the rated current parameter values ​​are extracted by combining the equipment's factory calibration information. The current sequence within each operating segment is structurally compared with the rated current to calculate the current offset value within each segment. The variation amplitude of the offset value within the sampling period is analyzed, and the variation range is divided into intervals. For example, if the rated current is set to 20A, the offset interval is set to ±5A. Values ​​exceeding this range are considered abnormal offsets. To ensure the repeatability of the analysis results, the current variation of each segment is further analyzed. To maintain consistency in processing methods, the offset between the peak current and the rated current within the sampling period is uniformly used as the criterion for judgment. In practical applications, the sampling period for a certain equipment's operating segment is 60 seconds. During this period, the maximum current sampling value is 28A, the minimum is 14A, and the average is 22A, corresponding to an offset of 2A. An offset threshold of 5A is set, and this segment is judged to be in a stable operating state. If the offset is 6A, it is marked as an abnormal offset. The data of all equipment and all operating segments are processed in the above manner, and the calculation results of each segment are recorded to form a basic dataset for status judgment. This dataset includes fields such as equipment number, operating segment number, current sequence within the sampling period, rated current parameter, offset calculation value, and offset level. Data samples are shown in Table 5.

[0158] Table 5 Sample Table for Judging Current Deviation in Operating Sections:

[0159] ;

[0160] As shown in Table 5, by judging the offset value, the load status of each operation segment is marked and summarized into a load offset judgment value set.

[0161] The work segment status marking submodule calls the load offset judgment value set, combines the work segment current data and fluctuation threshold to judge the load status of each segment, marks it according to the status type, and obtains the work segment load status marking group.

[0162] The load offset judgment value set is invoked to perform status identification processing on each work segment data. First, the number and corresponding offset level of each work segment are read, and the start and end time information of the work segment is extracted. Combined with the current fluctuation range data, a status labeling operation is performed. According to the rules, if the offset level is "abnormal," the status is marked as unstable; if the offset level is "normal," the status is marked as stable. In addition, it is necessary to determine whether there are periodic large fluctuations in the current sampling curve. If the difference between the peak and trough values ​​exceeds the set stability threshold range, it is also marked as an abnormal state. This stability threshold is set to 20% of the rated current; that is, when the rated current is 20A, the allowable fluctuation range is ±4. A. If the peak-to-valley difference of current in a certain work segment is 9A, the status is marked as abnormal. After completing the batch calculation of the above rules, a status field is established for each work segment. The output result fields are work segment number, equipment number, load status identifier, fluctuation level, status time period, etc. The output record format is as follows: S001-E01-Stable-Low Fluctuation-20240101T080000 to 20240101T081000. The overall data structure supports aggregation by equipment, as well as aggregation by region or work type. The status of each work segment is associated with the original sampling segment one by one, which is convenient for subsequent traceability and tag generation, and the work segment load status tag group is obtained.

[0163] The electrical parameter label generation submodule integrates equipment identification and work segment status based on the work segment load status tag group, extracts electrical parameter information of the corresponding segment, assigns corresponding status labels, and generates a set of electrical parameter status labels for the equipment work segment.

[0164] Based on the load status tag group of the work segment, integrate the equipment number, work segment number, and work time segment information to construct a multi-dimensional data table. Map the current status of each work segment to structured tag information, and classify and encode the work segment data according to the tag status type. For example, a stable state is coded as "01", and an abnormal state is coded as "02". Each record is bound to a unique work segment number and status code. When constructing the tag structure, it is necessary to additionally integrate the area number information and the work task number to support the subsequent horizontal linkage of tags in the work scheduling system. For example, equipment E03 in work segment S007 If the internal status is marked as abnormal, the area number is Z04, and the task number is T011, then the corresponding generated label is S007-E03-Z04-T011-02, which is uniformly stored in the label set field. Each label record is uniquely identified by a combination of fields. At the same time, it is possible to trace back the status and current sequence characteristics of the work segment based on the label code. After the label data generation process is completed, all label records are organized by the equipment dimension. The output fields include equipment number, work segment number, area number, label code, status type, etc., generating the equipment work segment electrical parameter status label set.

[0165] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A port energy monitoring and analysis system, characterized in that, Port energy includes electrical energy, fuel energy, and renewable energy; the system includes: The equipment electrical parameter acquisition module receives three-phase current data collected by current sensors deployed on quay cranes, gantry cranes and tractor equipment, extracts the current sequence in time sequence, divides the electrical parameter action segments based on the slope change of the current sequence, and constructs a set of electrical parameter action segments. The device electrical parameter acquisition module includes: The current sequence extraction submodule acquires the three-phase current sensor signals deployed on the quay crane, gantry crane, and tractor equipment, collects the raw three-phase current data in a continuous time period, arranges them in chronological order and marks the corresponding positions, and constructs a three-channel current change sequence by identifying the change trend between adjacent time periods, thereby obtaining the set of three-phase current sequence changes. The electrical parameter action division submodule calls the set of changes in the three-phase current sequence, and determines whether the change slope of each phase current exceeds the set change slope threshold based on the change slope of each phase current between consecutive time points. When the condition is met, it is marked as an action point. Based on the distribution of time intervals between action points, the module identifies segments, delineates independent electrical parameter change areas, and generates a set of electrical parameter action change intervals. The electrical parameter action segment set generation submodule extracts the change amplitude, maximum value and corresponding duration of the three-phase current within the set of electrical parameter action change intervals, obtains the difference value of electrical parameter action segments, filters action segments according to the value, and generates a set of electrical parameter action segments. The path association partitioning module divides the operation trajectory into berthing section, yard section and loading and unloading section based on the set of electrical parameter action segments and the tractor GNSS positioning data. Based on time interval matching, it associates the electrical parameter action segments with the operation trajectory area to generate electrical parameter path area mapping results. The energy consumption trend extraction module extracts the average current, maximum current, and current mutation frequency of the electrical parameter action segment in the path region from the electrical parameter path region mapping result, evaluates load fluctuations, and constructs a path region energy consumption trend feature set. The power consumption structure modeling module generates equipment energy consumption response profiles for each work area based on the energy consumption trend feature set of the path area, and constructs a regional energy consumption response structure description group by combining the regional work labels. The monitoring tag output module determines the load status of the electrical parameter action segment based on the regional energy consumption response structure description group and the equipment rated current fluctuation range, marks the load status of the equipment operation segment, and generates a set of electrical parameter status tags for the equipment operation segment. The load fluctuation is a stability index value calculated based on the degree of change in current value characteristics. The energy consumption response profile refers to the current change pattern curve of the equipment in a single operating area, which is formed based on the statistical characteristics of multiple electrical parameter action segments. The energy consumption response structure description is a structured description entry composed of an energy consumption response outline and a work area label.

2. The port energy monitoring and analysis system according to claim 1, characterized in that, The electrical parameter action segment set includes a three-phase current time series, slope change segments, and segment index information; The electrical parameter path region mapping result includes the electrical parameter action segment time interval, operation trajectory region label, and the correspondence between the action segment and the region; the path region energy consumption trend feature set includes the average current, the maximum current, and the current mutation frequency; the region energy consumption response structure description group includes the typical energy consumption response profile, the region operation label, and the equipment energy consumption structure parameters; the equipment operation segment electrical parameter status label set includes the load status label, the equipment action segment number, and the abnormal load mark.

3. The port energy monitoring and analysis system according to claim 1, characterized in that, The path-associated partition module includes: The action segment positioning submodule extracts the start and end times and device number of the action segment based on the electrical parameter action segment set, calls the trajectory point information within the corresponding time range in the GNSS positioning sequence, identifies the spatial location interval corresponding to the action segment, calculates the displacement trend change value between trajectory points, and generates the trajectory range value of the action segment. The region segment identification submodule matches the spatial coordinates in the preset work area boundary division table according to the trajectory range value of the action segment, counts the coverage of trajectory points in different region boundaries, determines the region category based on the coverage ratio, and obtains the region matching label value. The path region mapping submodule calls the region matching label value, organizes the action segments and region information under the tractor number, constructs a triplet dataset and arranges it in chronological order, obtains the trajectory segment feature mapping value, and obtains the electrical parameter path region mapping result according to the sorted path segment sequence.

4. The port energy monitoring and analysis system according to claim 3, characterized in that, The energy consumption trend extraction module includes: Based on the electrical parameter path region mapping result, the current data extraction submodule extracts the time range and number information of the corresponding action segment in the path region, obtains the current sampling sequence in the action segment, detects the data continuity, and uses an interpolation algorithm to complete the discontinuous data. After collecting the current data of the action segment, it calculates the average and maximum values ​​to generate a set of current segment statistical values. The load fluctuation calculation submodule identifies the change amplitude between consecutive points in the current sampling sequence based on the current segment statistical value set, determines whether it exceeds the preset mutation threshold, extracts the number of mutation points and constructs a mutation frequency index, collects the mutation frequency of all action segments in the path area, and generates a regional mutation frequency value set. The trend feature construction submodule calls the current segment statistical value set and the regional change frequency value set to organize the current intensity and load fluctuation feature information in the path area, construct the feature expression structure, form the energy consumption trend performance between different areas, and generate the path area energy consumption trend feature set.

5. The port energy monitoring and analysis system according to claim 4, characterized in that, The power consumption structure modeling module includes: The energy consumption profile construction submodule extracts the energy consumption sequence of the equipment in the working area based on the energy consumption trend feature set of the path area, identifies the energy consumption characteristics corresponding to the equipment operation stage, analyzes the change characteristics of energy consumption performance over time, calculates the energy consumption profile value of the equipment in the area, and generates a set of equipment energy consumption profile values. The job tag fusion submodule calls the equipment energy consumption profile value group and the job tag information in the area, extracts the tag factor corresponding to the equipment, identifies the energy consumption distribution under different tags, analyzes the impact of tag attributes on energy consumption performance, calculates the energy consumption feature value under the tag category, and generates an energy consumption tag mapping relationship group. The response structure generation submodule extracts the energy consumption feature information of devices in the region based on the energy consumption label mapping relationship group, collects the energy consumption performance of devices under the same label, analyzes the changing trend in different regions, calculates the response feature value under the region label combination, and generates a region energy consumption response structure description group.

6. The port energy monitoring and analysis system according to claim 5, characterized in that, The monitoring tag output module includes: The load threshold judgment submodule extracts the current change sequence within the equipment operating section based on the regional energy consumption response structure description group, calculates the current offset value in combination with the rated current parameter, judges the load fluctuation of the operating section, and generates a load offset judgment value set. The work segment status marking submodule calls the load offset judgment value set, combines the work segment current data and fluctuation threshold to judge the load status, marks it according to the status type, and obtains the work segment load status marking group. The electrical parameter tag generation submodule integrates the equipment identifier and the work segment status according to the work segment load status tag group, extracts the electrical parameter information of the corresponding segment, assigns the corresponding status tag, and generates the equipment work segment electrical parameter status tag set.

7. The port energy monitoring and analysis system according to claim 1, characterized in that, The three-phase current data is time-series data of three independent current channels collected by the current sensors of the quay crane, gantry crane, and tractor equipment. The source is Hall current sensor or shunt resistor current detection device. The slope of the current sequence change is a numerical value representing the rate of change of current between adjacent moments, derived from the change analysis between adjacent sampling points in the current sequence; The electrical parameter action segment is a continuous time interval divided based on the consistency of the direction of change of the current sequence. Each interval corresponds to a relatively independent equipment operation response process, which is derived from the slope characteristic analysis of the current sequence. The GNSS positioning data is a sequence of location information collected by the global satellite navigation system equipment carried by the tractor, and its source is GPS, GLONASS or BeiDou positioning system; The operation trajectory is a line segment of the equipment running path formed by connecting GNSS positioning data in chronological order. The time interval matching is based on comparing the start and end times of the electrical parameter action segment with the timestamps of the operation trajectory records, and the time intervals that overlap are calibrated accordingly.

8. The port energy monitoring and analysis system according to claim 1, characterized in that, The rated current fluctuation range of the equipment is the operating fluctuation range set according to the rated current value on the equipment nameplate; The load status is a classification result based on whether the equipment operating current is within the range of rated current fluctuation; The electrical parameter status label set is a set of labels formed by the load status identifiers corresponding to multiple equipment operating segments.

Images