Port and shipping operation carbon emission monitoring method and system based on multi-source fusion

Abstract

The application provides a port and shipping operation carbon emission monitoring method and system based on multi-source fusion, which comprises the following steps: acquiring multi-source data such as CEMS, fuel system, AIS / RTK, equipment PLC and construction log; after pretreatment, identifying the current operation condition based on AIS / RTK, PLC and log data and generating a working condition confidence; calculating the direct emission amount by using CEMS, calculating the carbon balance emission amount by using the fuel system, and calculating the relative deviation between the two; if the deviation is greater than a second threshold, a rule update trigger signal is generated, and the feedback data package is formed by combining the working condition confidence and the deviation, which is used to update the working condition identification rule to adaptively correct the working condition identification in the next monitoring period. The method realizes the adaptive correction of working condition identification by feeding the deviation between CEMS and fuel carbon balance and the working condition confidence back to the rule update, and improves the emission attribution accuracy.

Description

Technical Field

[0001] This application pertains to the field of ship monitoring, and in particular relates to a method and system for monitoring carbon emissions from port and shipping operations based on multi-source fusion. Background Technology

[0002] Port and waterway operation involves numerous maritime activities primarily conducted by work vessels, such as dredging, reef blasting, obstacle removal, and navigation mark maintenance. These operations consume fuel and generate direct greenhouse gas emissions, primarily CO2. Current carbon emission accounting for port and waterway projects typically relies on fuel consumption ledgers and emission factor methods to determine total emissions for the project period.

[0003] Specifically, existing technologies rely solely on fuel ledgers for calculations, obtaining total fuel consumption through refueling records and fuel tank inventory checks, and then multiplying it by the corresponding emission factors to estimate total emissions. While this method can obtain the total emissions for the project period, it suffers from problems such as mismatches between refueling records and actual consumption periods, fuel tank inventory errors, difficulty in excluding non-project fuel consumption, coarse segmentation of operating conditions, and difficulty in distinguishing equipment-level contributions. Furthermore, while shipborne continuous emission monitoring systems (CEMS) can directly collect flue gas CO2 concentration and flow rate to improve real-time performance, they face engineering challenges such as vibration, salt spray, humidity variations, and large flow measurement errors. Although small CO2 sensor networks can provide background concentration information for the water area, they are greatly affected by the environment and are not suitable as a sole basis for calculating mass emissions.

[0004] Therefore, the existing technology has at least the following shortcomings: Once the operating condition identification rule is set, it becomes a fixed value. When there is a large deviation between the direct measurement results of CEMS and the fuel carbon balance results, this deviation cannot be used to reverse the operating condition identification rule, resulting in the inability to automatically correct misjudgments of the operating condition and making it difficult to guarantee the accuracy of emission attribution. Summary of the Invention

[0005] The purpose of this application is to overcome the deficiencies in the prior art and provide a method and system for monitoring carbon emissions from port and shipping operations based on multi-source fusion.

[0006] This application provides a method for monitoring carbon emissions from port and shipping operations based on multi-source fusion, including: Multi-source monitoring data is acquired from the vessel, including CEMS monitoring data, fuel system monitoring data, AIS / RTK monitoring data, equipment PLC monitoring data, and construction log data. The multi-source monitoring data is preprocessed to generate preprocessed multi-source data; Based on the AIS / RTK monitoring data, the equipment PLC monitoring data, and the construction log data from the multi-source data, the current operating condition of the vessel is identified, and an operating condition confidence score is generated. The operating condition confidence score is a measure of the consistency between the identified current operating condition and the procedures in the construction log data. Calculate the direct emissions from CEMS based on the CEMS monitoring data from the multi-source data. Calculate the fuel system monitoring data from the multi-source data to determine the fuel carbon balance emissions. The relative deviation is calculated based on the CEMS direct emissions and the fuel carbon balance emissions. If the relative deviation is greater than the first deviation threshold, a rule update trigger signal is generated; The trigger signal, the operating condition confidence level, and the relative deviation are updated according to the rules to generate a feedback data packet. Based on the feedback data packet, the operating condition identification rules are updated to generate updated operating condition identification rules, which are used to identify the current operating condition of the vessel in the next monitoring cycle.

[0007] Optionally, the preprocessing of the multi-source monitoring data to generate preprocessed multi-source data includes: Wet-based CO2 concentration and flue gas humidity were obtained from the CEMS monitoring data. The wet-based CO2 concentration is corrected to a dry-based CO2 concentration based on the flue gas humidity to generate a dry-based CO2 concentration. The dry basis CO2 concentration is used as part of the multi-source data.

[0008] Optionally, identifying the current operating condition of the vessel based on the AIS / RTK monitoring data, the equipment PLC monitoring data, and the construction log data from the multi-source data includes: Based on the vessel speed in the AIS / RTK monitoring data, the mud pump start / stop status, cutterhead start / stop status, and drilling rig start / stop status in the equipment PLC monitoring data, the preset construction face geofence, and the procedures in the construction log data, port and shipping maintenance-specific operation conditions are identified, including dredging, reef blasting, mud barge transportation, and mud dumping conditions. When the ship speed is less than the first speed threshold and the mud pump or the cutter head is in the on / off state and the ship is located within the preset construction surface geofence, it is identified as the dredging condition. When the ship speed is less than the second speed threshold, the drilling rig is in the on / off state, and the ship is located within the blasting fence, it is identified as the blasting condition. When the ship speed is greater than the third speed threshold, the mud pump is in the off state, and the ship is located within the mud dumping area fence, it is identified as the mud dumping condition. When the vessel speed is between the fourth and fifth speed thresholds, the mud pump is in the off-state, and the vessel is located in the transfer channel, it is identified as the mud barge transportation condition.

[0009] Optionally, the generated operating condition confidence level includes: The identified current working condition is compared with the corresponding time period of the work process in the construction log data, time by time. When the two are consistent, the confidence level of the operating condition is determined to meet the requirements; When the two are inconsistent, the confidence level of the operating condition is determined to be lower than the preset value, and the corresponding time period is marked as pending review.

[0010] Optionally, it also includes: Set a second deviation threshold and a first deviation threshold, wherein the first deviation threshold is greater than the second deviation threshold; After calculating the relative deviation, it is determined whether the relative deviation is greater than the second deviation threshold; If the relative deviation is greater than the second deviation threshold, then CEMS calibration or fuel data verification is triggered. Then determine whether the relative deviation is greater than the first deviation threshold; If the relative deviation is greater than the first deviation threshold, then the rule update trigger signal is generated.

[0011] Optionally, the step of updating the trigger signal, the operating condition confidence level, and the relative deviation according to the rule to generate a feedback data packet further includes: Obtain the manual review results generated after manually reviewing the time period to be reviewed; The verification results are also included in the feedback data packet.

[0012] Optionally, updating the operating condition identification rules and generating updated operating condition identification rules based on the feedback data packet includes: Based on the manual review results, relative deviation, and working condition confidence level in the feedback data packet, adjust the ship speed threshold, equipment start / stop logic, and construction surface geofence matching parameters in the working condition identification rules.

[0013] This application also provides a carbon emission monitoring system for port and shipping operations based on multi-source fusion, including: The data acquisition module is used to acquire multi-source monitoring data from the ship, including CEMS monitoring data, fuel system monitoring data, AIS / RTK monitoring data, equipment PLC monitoring data, and construction log data. The preprocessing module is used to preprocess the multi-source monitoring data to generate preprocessed multi-source data; The working condition identification module is used to identify the current working condition of the vessel based on the AIS / RTK monitoring data, the equipment PLC monitoring data and the construction log data in the multi-source data, and generate a working condition confidence score. The working condition confidence score is a consistency measure between the identified current working condition and the process in the construction log data. The first calculation module is used to calculate the direct emissions of CEMS based on the CEMS monitoring data in the multi-source data; The second calculation module is used to calculate the fuel carbon balance emissions based on the fuel system monitoring data in the multi-source data. The deviation calculation module is used to calculate the relative deviation based on the CEMS direct emissions and the fuel carbon balance emissions. The triggering module is used to generate a rule update trigger signal if the relative deviation is greater than a first deviation threshold. The feedback generation module is used to update the trigger signal, the operating condition confidence level, and the relative deviation according to the rules to generate a feedback data packet; The rule update module is used to update the operating condition identification rules according to the feedback data packet, and generate updated operating condition identification rules for identifying the current operating condition of the vessel in the next monitoring cycle.

[0014] Optionally, the preprocessing module includes a dry basis correction submodule, comprising: Wet-based CO2 concentration and flue gas humidity were obtained from the CEMS monitoring data. The wet-based CO2 concentration is corrected to a dry-based CO2 concentration based on the flue gas humidity to generate a dry-based CO2 concentration. The dry basis CO2 concentration is used as part of the multi-source data.

[0015] Optionally, the working condition identification module includes a rule model submodule, comprising: Based on the vessel speed in the AIS / RTK monitoring data, the mud pump start / stop status, cutterhead start / stop status, and drilling rig start / stop status in the equipment PLC monitoring data, the preset construction face geofence, and the procedures in the construction log data, port and shipping maintenance-specific operation conditions are identified, including dredging, reef blasting, mud barge transportation, and mud dumping conditions. When the ship speed is less than the first speed threshold and the mud pump or the cutter head is in the on / off state and the ship is located within the preset construction surface geofence, it is identified as the dredging condition. When the ship speed is less than the second speed threshold, the drilling rig is in the on / off state, and the ship is located within the blasting fence, it is identified as the blasting condition. When the ship speed is greater than the third speed threshold, the mud pump is in the off state, and the ship is located within the mud dumping area fence, it is identified as the mud dumping condition. When the vessel speed is between the fourth and fifth speed thresholds, the mud pump is in the off-state, and the vessel is located in the transfer channel, it is identified as the mud barge transportation condition.

[0016] The beneficial effects of this application are: This application provides a multi-source fusion-based method for monitoring carbon emissions from port and shipping operations at sea, comprising: acquiring multi-source monitoring data from the vessel, wherein the multi-source monitoring data includes CEMS monitoring data, fuel system monitoring data, AIS / RTK monitoring data, equipment PLC monitoring data, and construction log data; preprocessing the multi-source monitoring data to generate preprocessed multi-source data; identifying the vessel's current operating condition based on the AIS / RTK monitoring data, the equipment PLC monitoring data, and the construction log data in the multi-source data, and generating an operating condition confidence score, wherein the operating condition confidence score is the ratio of the identified current operating condition to the carbon emissions from the construction log data. The process involves: measuring the consistency of the operation; calculating CEMS direct emissions based on the CEMS monitoring data from the multi-source data; calculating fuel carbon balance emissions based on the fuel system monitoring data from the multi-source data; calculating the relative deviation based on the CEMS direct emissions and the fuel carbon balance emissions; generating a rule update trigger signal if the relative deviation is greater than a first deviation threshold; generating a feedback data packet based on the rule update trigger signal, the operating condition confidence level, and the relative deviation; updating the operating condition identification rule based on the feedback data packet, and generating an updated operating condition identification rule for identifying the ship's current operating condition in the next monitoring cycle. This application achieves adaptive correction of operating condition identification and improves the accuracy of emission attribution by feeding back the relative deviation between CEMS and fuel carbon balance emissions and the operating condition confidence level to the update of the operating condition identification rule. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the carbon emission monitoring process for port and shipping operations based on multi-source fusion in this application; Figure 2 This is the overall architecture diagram of the carbon emission monitoring system for offshore operations of China Harbour & Shipping in this application; Figure 3 This is a list of monitored objects and a schematic diagram of the boundaries between the two ledgers in this application; Figure 4 This is a direct emission monitoring link diagram of the shipborne CEMS in this application; Figure 5 This is a schematic diagram of the coordinated deployment of navigation marks, shore-based and shipborne CO2 sensors in this application; Figure 6 This is a flowchart of the multi-source data fusion and emissions accounting process in this application; Figure 7 This is a schematic diagram of the working condition identification and spatial attribution model in this application; Figure 8 This is a structural diagram of the carbon emission monitoring system for port and shipping operations based on multi-source fusion in this application. Detailed Implementation

[0018] Exemplary embodiments of the present disclosure will now be provided in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is to be understood that various forms of implementation of the present disclosure are intended and should not be limited to the embodiments set forth herein. Rather, the embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0019] This application provides a multi-source fusion-based method and system for monitoring carbon emissions from port and shipping operations at sea. It is applicable to the monitoring, accounting, verification, spatial attribution, and ledger output of direct carbon emissions from mobile sources at sea, primarily working vessels, including port maintenance, waterway maintenance, dredging, reef blasting, obstacle removal, navigation mark maintenance, barge transportation, tugboat assistance, traffic vessel inspection, and emergency repairs. The system addresses existing technologies that lack a unified data master key and fusion mechanism among direct emission monitoring, fuel verification, sensor networks, operating condition identification, and material ledgers; lack of dynamic verification and supplementary calculation mechanisms between CEMS direct measurement results and fuel carbon balance results; insufficient use of AIS / RTK, equipment PLC, and construction logs for high-frequency operating condition identification, making it difficult to attribute emission results to specific processes and spatial units; lack of reasonable division of labor between background deduction and hotspot identification results from CO2 sensor networks and the main emission ledger; and the tendency for material consumption statistics and direct emission accounting to be confused, affecting the clarity of carbon emission results boundaries.

[0020] Please refer to Figure 1 As shown in the figure, the carbon emission monitoring method for port and shipping operations based on multi-source fusion described in this application includes: S101. Obtain multi-source monitoring data from the ship, including CEMS monitoring data, fuel system monitoring data, AIS / RTK monitoring data, equipment PLC monitoring data, and construction log data.

[0021] Collect multi-source monitoring data of port and shipping operations at sea, wherein the multi-source monitoring data is multi-source heterogeneous monitoring data.

[0022] The multi-source heterogeneous monitoring data includes shipborne CEMS data, CO2 sensor network data, activity intensity data, fuel data, construction logs, and material ledgers.

[0023] Please refer to Figure 5 As shown, the shipborne CEMS data includes CO2 concentration, O2 concentration, flue gas flow rate, flue gas temperature, pressure, and humidity; fuel data includes fuel flow rate, fuel tank level, fuel density, fuel type, refueling records, and fuel sample factors; activity intensity data includes AIS / RTK trajectory, speed, heading, equipment PLC status, main engine load, mud pump or drilling rig start / stop status, and construction log; sensor network data includes concentration, weather, location, and timestamps of buoys, shore-based, and shipborne CO2 sensors; and material ledger data includes material name, specifications, quantity, unit, batch, factor source, and issuance and return records.

[0024] The CEMS monitoring data refers to shipborne CEMS data, the fuel system monitoring data refers to fuel data, the AIS / RTK monitoring data and the equipment PLC monitoring data are both activity intensity data, and the construction log data refers to the construction log.

[0025] Shipborne CEMS is preferentially deployed at the exhaust stacks of main engines, auxiliary engines, or operating power equipment of dredging vessels, reef blasting vessels, and obstacle clearing vessels, to directly obtain CO2 concentration, O2 concentration, flue gas flow rate, temperature, pressure, and humidity.

[0026] The AIS / RTK interface with the PLC is used to collect data on ship trajectory, speed, heading, equipment start / stop status, and equipment load.

[0027] The CO2 sensor network includes a navigation mark or buoy background point, a downwind monitoring point, a shore base station, and shipborne small sensor nodes. The background point is used to obtain the background concentration in the upwind or clean water area, the downwind monitoring point is used to identify the concentration response of the construction water area affected by the ship plume, the shipborne node is used to record the moving profile and near-source changes, and the shore base station is used for data aggregation, calibration comparison, and meteorological parameter acquisition.

[0028] Activity intensity data also includes main engine load, pump status, generator load, and drilling rig status. Fuel data includes beginning and ending inventory and fuel type. Materials ledgers also include issuance, returns, disposal, and emission factor sources.

[0029] S102. Preprocess the multi-source monitoring data to generate preprocessed multi-source data.

[0030] Please refer to Figure 6 As shown, the edge gateway or cloud platform performs time synchronization, anomaly removal, missing data filling (not shown), and quality marking on multi-source heterogeneous monitoring data.

[0031] When synchronizing the multi-source heterogeneous monitoring data, alignment and resampling are performed based on a unified time grid. The resampling formula is as follows: in, Indicates that the i-th type of data source is in a unified time grid, the... Resampling results at different times; Indicates the local sampling time of the i-th type of data source. The original observations on; This represents the nearest neighbor, linear interpolation, hold-before sampling, or statistical resampling function corresponding to the i-th type of data source. This represents the k-th sampling time in the unified time grid, where i represents the data source number and k represents the unified time grid number.

[0032] Anomaly removal can employ physical thresholds, sliding window statistics, and data source consistency checks. For example, CO2 concentrations that clearly exceed the equipment's range, negative flow rates, impossible ship speeds, abnormal temperatures, and timestamp-back data can be marked as anomalies.

[0033] For short-term missing data, interpolation or fuel method can be used to supplement the data. For long-term missing data, the quality level should be reduced and the missing data description should be retained.

[0034] The wet-based flue gas concentration is corrected for dry basis, and the CO2 sensor concentration is corrected for temperature and humidity and background point drift.

[0035] The preprocessing includes time synchronization, anomaly removal, humidity correction, resampling, and quality labeling of the multi-source monitoring data.

[0036] In a specific embodiment, the preprocessing of the multi-source monitoring data to generate preprocessed multi-source data includes: obtaining wet-based CO2 concentration and flue gas humidity from the CEMS monitoring data; performing dry-based correction on the wet-based CO2 concentration based on the flue gas humidity to generate a dry-based CO2 concentration; and using the dry-based CO2 concentration as part of the multi-source data. Specifically, when the CO2 concentration is a wet-based concentration, dry-based correction is first performed using the following formula: in, This represents the volume fraction or mole fraction of CO2 on a dry basis at time t. This indicates the volume fraction or mole fraction of CO2 on a wet basis at time t. This represents the volume fraction of moisture in the flue gas at time t.

[0037] For CEMS and PLC data at the second level, a 1-second acquisition and 1-minute averaging method can be used; for construction logs, they can be mapped to a unified time grid by shift or event period.

[0038] Anomaly removal can also employ physical thresholds, sliding window statistics, and data source consistency checks. For example, CO2 concentrations that significantly exceed the equipment's measurement range, negative flow rates, impossible ship speeds, abnormal temperatures, and timestamp-back data can be marked as anomalies. For data gaps less than or equal to the preset missing duration, linear interpolation, recent valid value retention, or fuel replenishment methods can be used. For data gaps exceeding the preset missing duration, the data quality level should be lowered and noted in the results report.

[0039] S103. Based on the AIS / RTK monitoring data, the equipment PLC monitoring data, and the construction log data in the multi-source data, identify the current operating condition of the vessel and generate an operating condition confidence score. The operating condition confidence score is a measure of the consistency between the identified current operating condition and the procedures in the construction log data.

[0040] Identify port and shipping operation and maintenance conditions based on AIS / RTK, equipment PLC, and construction logs.

[0041] Please refer to Figure 7 As shown, the operating condition identification rules include speed threshold, equipment status, log verification, and fence matching.

[0042] The operational conditions include navigation or relocation, dredging operations, mud barge transportation, mud dumping, blasting reefs or drilling and blasting, obstacle removal, navigation mark maintenance, standby and berthing.

[0043] Operating condition identification is used not only to distinguish between project operations and non-project operations, but also to control emission allocation weights.

[0044] When the results of the rule model identification are inconsistent with the construction log, the time period is marked as pending review, and the data quality level of the corresponding time period is reduced when attributing emissions.

[0045] In one specific embodiment, identifying the current operating condition of the vessel based on the AIS / RTK monitoring data, the equipment PLC monitoring data, and the construction log data from the multi-source data includes: Based on the ship speed in the AIS / RTK monitoring data, the mud pump start / stop status, cutter start / stop status and drilling rig start / stop status in the equipment PLC monitoring data, the preset construction face geofence, and the procedures in the construction log data, port and shipping maintenance exclusive operation conditions, including dredging, reef blasting, mud barge transportation, and mud dumping, are identified.

[0046] Specifically: When the ship speed is less than the first speed threshold and the mud pump or the cutter head is in the on / off state and the ship is located within the preset construction surface geofence, it is identified as the dredging condition. When the ship speed is less than the second speed threshold, the drilling rig is in the on / off state, and the ship is located within the blasting fence, it is identified as the blasting condition. When the ship speed is greater than the third speed threshold, the mud pump is in the off state, and the ship is located within the mud dumping area fence, it is identified as the mud dumping condition. When the vessel speed is between the fourth and fifth speed thresholds, the mud pump is in the off-state, and the vessel is located in the transfer channel, it is identified as the mud barge transportation condition.

[0047] For example, when the ship speed is greater than 3 knots, the main engine load is high, and the operating equipment is shut down, it can be determined as navigation or relocation; when the ship speed is between 0 knots and 2 knots, the mud pump, cutter head, or grab bucket equipment is on, and the ship position is within the geographical fence of the construction surface, it can be determined as dredging operation; when the ship trajectory matches the transport route, the mud dumping area fence, and the mud unloading gate status, it can be determined as mud barge transportation or mud dumping; when the ship speed is approximately 0 knots, the main engine is under low load or shut down, and the auxiliary machinery and generator are running, it can be determined as standby or berthing.

[0048] The generated operating condition confidence level includes: The identified current work condition is compared with the corresponding work process in the construction log data time by time. When the two are consistent, the confidence level of the work condition is determined to meet the requirements. When the two are inconsistent, the confidence level of the work condition is determined to be lower than the preset value, and the corresponding time period is marked as pending review.

[0049] The operating condition can be represented by the following rule model: Where s(t) represents the ship's operating condition at time t; F represents the operating condition identification rule function; and v(t) represents the ship's speed at time t. This represents the engine or equipment load at time t; This indicates the on / off status of pumps, drilling rigs, mud unloading gates, or other operating equipment; g(t) represents the geographical fence where the ship is located at time t; l(t) represents the construction log or manual verification information.

[0050] When multiple devices are operating at the same time, if the device-level fuel flow rate is available, fuel flow rate should be prioritized for allocation; if only device load is available, allocation should be based on the device's rated power and load rate; if neither is available, allocation weights can be set according to construction logs and expert rules, and the data quality level can be reduced.

[0051] S104. Calculate the direct emissions of CEMS based on the CEMS monitoring data in the multi-source data.

[0052] Calculation of direct CO2 emissions from ship fuel combustion based on shipborne CEMS mass flow method.

[0053] When the shipborne CEMS can simultaneously obtain dry-based CO2 concentration and dry-based standard flue gas flow rate, the mass flow rate method is used as the primary accounting method.

[0054] After dry basis correction, CEMS direct emissions are calculated using the following formula: in, This represents the CO2 emissions calculated based on the CEMS mass flow method, in tCO2. This represents the dry basis CO2 concentration at time t, multiplied by [value] when the concentration is expressed in ppm. When the concentration is expressed as a volume fraction, it should be converted according to the corresponding ratio. This represents the dry-basis standard flue gas flow rate at time t, in units of... ; This indicates the molar mass of CO2, expressed in kg / kmol. This represents the molar volume of a gas under standard conditions, in units of 1. ; This indicates the calculation time step, in hours (h). Represents a set All moments Perform summation; This represents the set of valid monitoring times.

[0055] When both CEMS concentration data and dry-basis standard flue gas flow rate data are valid, the direct emissions are calculated using CO2 concentration, dry-basis standard flue gas flow rate, CO2 molar mass, standard state gas molar volume, and time step. When the CEMS concentration is valid but there is a short-term lack of flue gas flow data, the flue gas flow is supplemented by the fuel carbon balance method or the engine air volume estimation method, and the supplementation period is marked.

[0056] Please refer to Figure 4 As shown, the shipborne CEMS direct emission monitoring link includes exhaust gas sampling, sampling pretreatment, gas analysis, synchronous acquisition, emission calculation, and result output. The exhaust gas sampling unit collects flue gas from the ship's exhaust stack. The sampling pretreatment unit performs filtration, heating, and dehumidification. The gas analysis unit measures CO2 and O2 concentrations. The synchronous acquisition unit collects flue gas flow rate, temperature, pressure, humidity, and operating condition data. The emission calculation unit calculates CO2 emissions using the mass flow method.

[0057] S105. Calculate the fuel system monitoring data from the multi-source data to determine the fuel carbon balance emissions.

[0058] The direct CO2 emissions were verified and supplemented based on the fuel carbon balance method.

[0059] Fuel carbon balance emissions are calculated using the following formula: in, This represents the CO2 emissions calculated based on the fuel carbon balance method. This represents the consumption mass of the i-th type of fuel during the accounting period; This represents the CO2 conversion coefficient corresponding to the i-th type of fuel; A set of indexes representing fuel types; Represents a set All fuel types Perform summation.

[0060] The fuel consumption mass can be determined by the fuel volumetric flow rate, fuel tank level, fuel density, and temperature correction factor. The specific calculation formula is as follows: in, Indicates the mass of fuel consumed by the i-th type; This represents the volume consumption of the i-th type of fuel during the accounting period; Indicates the density of the i-th type of fuel; This represents the temperature correction coefficient for the i-th type of fuel.

[0061] S106. Calculate the relative deviation based on the CEMS direct emissions and the fuel carbon balance emissions.

[0062] The system will determine the discrepancy between the CEMS results and the fuel carbon balance results. The relative deviation between CEMS direct emissions and fuel carbon balance emissions is calculated using the following formula: in, Indicates relative deviation; This indicates the avoidance of extremely small positive numbers with a denominator of zero.

[0063] In one specific embodiment, the method further includes: setting a second deviation threshold and a first deviation threshold, wherein the first deviation threshold is greater than the second deviation threshold; after calculating the relative deviation, determining whether the relative deviation is greater than the second deviation threshold; if the relative deviation is greater than the second deviation threshold, triggering CEMS calibration or fuel data verification; then determining whether the relative deviation is greater than the first deviation threshold; if the relative deviation is greater than the first deviation threshold, generating the rule update trigger signal.

[0064] when If the deviation is less than or equal to the second deviation threshold, the data is deemed to have passed the verification. when If the deviation exceeds the first deviation threshold, a review, recalibration, or reduction of the data quality level will be triggered.

[0065] As an example, it can be Determined as excellent, 10% It has been determined that a review is required. The system was flagged as abnormal and triggered checks on flow meters, density, concentration range, gas leaks, non-project oil usage, and operating condition segments.

[0066] S107. If the relative deviation is greater than the first deviation threshold, generate a rule update trigger signal.

[0067] When the relative deviation exceeds the verification threshold, a verification of the CEMS zero point, span, flow rate, humidity, fuel density, and oil tank inventory records is triggered.

[0068] If the relative deviation is greater than the first deviation threshold, the rule update trigger signal is generated, which is used to start the update process of the working condition identification rule.

[0069] S108. Update the trigger signal, the operating condition confidence level, and the relative deviation according to the rules to generate a feedback data packet.

[0070] The system collects and integrates relevant information to form a data package for subsequent optimization.

[0071] The step of updating the trigger signal, the operating condition confidence level, and the relative deviation according to the rule to generate a feedback data packet further includes: Obtain the manual review results generated after manually reviewing the time period to be reviewed; The verification results are also included in the feedback data packet.

[0072] When the rule model's identification results are inconsistent with the construction logs, that period is marked as pending review. Manual review of these pending review periods yields accurate results, which are then included in the feedback data packet, providing a more reliable basis for subsequent rule updates.

[0073] S109. Based on the feedback data packet, update the operating condition identification rules and generate updated operating condition identification rules to identify the current operating condition of the vessel in the next monitoring cycle.

[0074] The operating condition identification rules are optimized based on the feedback data packets.

[0075] The step of updating the operating condition identification rules based on the feedback data packet and generating updated operating condition identification rules includes: Based on the manual review results, relative deviation, and operating condition confidence level in the feedback data packet, the system adjusts the ship speed threshold, equipment start / stop logic, and geofence matching parameters in the operating condition identification rules. The system includes a feedback optimization mechanism that updates the operating condition identification rules, geofence parameters, data quality thresholds, and equipment maintenance recommendations based on output results, anomaly records, and manual review results.

[0076] In this way, the operating condition identification rules can continuously improve themselves, thereby increasing the identification accuracy in future monitoring cycles.

[0077] Please refer to Figure 3 As shown, in another embodiment of this application, the step of establishing a list of monitored objects and the boundaries of the dual ledgers is also included.

[0078] The list of monitored objects adopts a primary key system of "project-ship-equipment-exhaust stack-operation-time period-spatial unit".

[0079] The establishment of the monitoring object list and the boundary of the dual ledgers includes forming an associated list of "project-ship-equipment-operation-time period-space unit" using project number, ship identification, equipment number, exhaust stack number, fuel system number, operation status, time unit and spatial unit as primary keys.

[0080] The spatial units include the harbor basin, berths, channel mileage, construction surface, dumping area, anchorage and temporary operation area, while the time units include seconds, minutes, hours, shifts, days, months and project period.

[0081] In one implementation, the monitoring list for the harbor basin dredging project includes at least the project number, contract section number, vessel name, MMSI, equipment number, exhaust stack number, fuel type, work area number, waterway mileage, work shift, work log number, and data quality marker.

[0082] For waterway maintenance and dredging projects, spatial units can be divided every 0.5km to 1km according to the mileage markers; For port berth maintenance projects, spatial units can be divided into berths, port basins, turning areas, and dumping areas.

[0083] The dual ledger boundary includes the Category 1 direct emission master ledger and the construction vessel material consumption supplementary ledger. The Category 1 direct emission master ledger only includes CO2 emissions from the combustion of fuel oil in main engines, auxiliary engines, generators, boilers, and operating power equipment; the consumption of lubricating oil, hydraulic oil, filters, wire ropes, welding materials, explosives, spare parts, and other construction vessel materials is not included in the Category 1 direct emission master ledger, but is instead listed separately in the material consumption supplementary ledger.

[0084] The material consumption replenishment ledger is calculated based on material usage and material emission factors, using the following formula: in, This indicates the amount of carbon implied in the material consumption replenishment ledger; This indicates the quantity or quality of the j-th type of material consumed; This represents the unit emission factor corresponding to the j-th type of material; A set of indexes representing material categories; Represents a set All material categories Perform summation.

[0085] The supplementary materials ledger is used for comprehensive carbon management, material reduction management and connection with other platforms, and is not added to the Category 1 direct emission master ledger to form the total amount of the marine platform master ledger.

[0086] In another embodiment of this application, the method further includes steps of background concentration subtraction, emission hotspot identification, and spatial attribution assistance based on a CO2 sensor network.

[0087] Specifically, background concentration subtraction based on a CO2 sensor network includes: identifying the water area emission response using the CO2 concentration difference between the upwind background point and the downwind monitoring point, whereby the concentration difference is calculated using the following formula: in, This represents the increase in CO2 concentration at the downwind monitoring point relative to the upwind background point at time t. This represents the CO2 concentration at the downwind monitoring point at time t; This represents the background CO2 concentration at the upwind location at time t.

[0088] The concentration difference is used for emission hotspot identification and spatial attribution assistance, but does not replace the main accounting results of the CEMS mass flow method.

[0089] When the wind direction is stable and the upwind background point and downwind monitoring points are reasonably deployed, the system calculates the concentration increment of the downwind monitoring point relative to the upwind background point to determine whether there is a significant emission response in a certain construction water area.

[0090] Under the conditions of stable wind field, well-defined monitoring cross-section, and attributable ship activity, differential flux can also be used as an auxiliary estimation indicator: in, This represents the differential CO2 flux per unit cross section at time t; Indicates air density; This indicates the difference in CO2 mole fraction between the upwind and downwind sides; This represents the wind speed component perpendicular to the monitoring section.

[0091] The differential flux is used only as supplementary evidence for spatial attribution and is not the sole accounting result of the main ledger.

[0092] In another embodiment of this application, a data quality level determination step is also included.

[0093] The data quality level is comprehensively evaluated based on CEMS effectiveness, fuel data integrity rate, operating condition identification consistency rate, time synchronization deviation, CEMS and fuel carbon balance deviation, and the proportion of missing data recalculation. The results are classified into Grade A, Grade B, Grade C, or Grade D. Grade A results are used for formal accounting and performance evaluation; Grade B results are used for formal reports but the recalculation ratio must be indicated; Grade C results are used for trend analysis; and Grade D results are only used for data gap explanation or reference description.

[0094] To facilitate project implementation, a comprehensive quality score Q can be set: Wherein, Q represents the overall quality score; This indicates that CEMS is effective; Indicates the fuel data completeness rate; Indicates the consistency rate of operating condition identification; Indicates the time synchronization compliance rate; , , and This indicates the weight of each indicator, and ; This indicates the penalty for missing measurements. This indicates the penalty for deviation between CEMS and fuel carbon balance.

[0095] As an example, when Q≥85 and the CEMS efficiency meets the requirements, it is judged as Grade A; when Furthermore, if the supplementary calculation ratio is acceptable, it is judged as Grade B; when It was initially classified as Grade C; If Q < 55 or only manual logs are available, it is classified as Grade D.

[0096] The above thresholds can be adjusted according to regulatory requirements, project accuracy requirements, and equipment conditions.

[0097] In another embodiment of this application, the method further includes the step of accounting for carbon emission monitoring results based on the ship, equipment, process, route, construction space unit, and project period, and separately accounting for the material consumption of the construction vessel as a supplementary ledger.

[0098] The spatial attribution is constrained by the ship whitelist, geofencing, and operating conditions, allocating CO2 emissions to ships, equipment, processes, and spatial units. The attribution calculation formula is as follows: in, This indicates the attributable emissions of ship s in process a and spatial unit g; This represents the emissions at time t; An indicator function indicating whether ship s belongs to the project whitelist at time t; An indicator function indicating whether process a is in progress at time t; An indicator function indicating whether the object is located within spatial cell g at time t; This indicates the allocation weight when multiple devices or processes contribute during the same time period; This represents the set of all time slices within the accounting period; Represents a set All moments Perform summation.

[0099] Output indicators include direct CO2 emissions during the project period, hourly / daily / monthly emissions, ship emissions, equipment emissions, process emissions, waterway emissions, construction area emissions, emissions per unit of dredging volume, emissions per unit of transport mileage, standby emissions ratio, carbon account for material replenishment, data quality level, and the proportion of missing data supplementation.

[0100] The system can further generate emission reduction suggestions. For example, when the proportion of standby emissions is too high, it can prompt the optimization of ship scheduling or shore power substitution. When the emissions per unit dredging volume are higher than the benchmark, it can prompt the optimization of dredging process or equipment load. When the deviation between CEMS and fuel is abnormal, it can prompt the inspection of flow meters, sampling pipelines, fuel density and non-project fuel rejection rules. When the consumption of a certain type of consumables in the material replenishment ledger is abnormal, it can prompt the reduction or substitution of materials.

[0101] Please refer to Figure 8 As shown, this application also provides a carbon emission monitoring system for port and shipping operations based on multi-source fusion, the system being used to implement the method described above.

[0102] The system includes a data acquisition module for acquiring multi-source monitoring data from the ship, including CEMS monitoring data, fuel system monitoring data, AIS / RTK monitoring data, equipment PLC monitoring data, and construction log data.

[0103] The data acquisition module can be implemented through a data acquisition terminal, which includes a shipborne CEMS terminal, CO2 sensor nodes, an AIS / RTK and PLC interface, and a fuel / material ledger interface. The shipborne CEMS terminal is used to collect CO2 concentration, O2 concentration, and flue gas flow rate from the ship's exhaust stack. The CO2 sensor nodes are used to collect CO2 concentration and meteorological data at shore-based, navigational aids, buoys, and shipborne locations. The AIS / RTK and PLC interface is used to collect ship trajectory, speed, heading, equipment on / off status, and equipment load. The fuel / material ledger interface is used to access fuel flow rate, fuel tank level, refueling slips, material requisition slips, return slips, and material factor database.

[0104] The system also includes a preprocessing module for preprocessing the multi-source monitoring data to generate preprocessed multi-source data.

[0105] The preprocessing module includes a dry basis correction submodule, which is used to obtain wet basis CO2 concentration and flue gas humidity from the CEMS monitoring data, perform dry basis correction on the wet basis CO2 concentration according to the flue gas humidity to generate a dry basis CO2 concentration, and use the dry basis CO2 concentration as part of the multi-source data.

[0106] The preprocessing module's functions can be jointly performed by the edge gateway and the cloud analytics platform. The edge gateway receives data uploaded from the data acquisition terminal and performs time synchronization, initial anomaly screening, humidity correction, data caching, and preliminary quality control locally. The edge gateway can be deployed in shore base stations, ship equipment compartments, port management stations, or mobile monitoring boxes, and supports wired Ethernet, 4G / 5G, NB-IoT, BeiDou short message service, and ship-to-shore Wi-Fi communication. The data quality control module in the cloud analytics platform performs resampling, anomaly removal, missing data imputation, drift correction, and data quality level determination.

[0107] The system also includes a working condition identification module, which is used to identify the current working condition of the vessel based on the AIS / RTK monitoring data, the equipment PLC monitoring data and the construction log data in the multi-source data, and generate a working condition confidence score. The working condition confidence score is a consistency measure between the identified current working condition and the procedures in the construction log data.

[0108] The working condition identification module includes a rule model submodule, used to identify port and shipping maintenance-specific operating conditions, including dredging, blasting, mud barge transportation, and mud dumping, based on the ship speed in the AIS / RTK monitoring data, the mud pump start / stop status, cutter start / stop status, and drilling rig start / stop status in the equipment PLC monitoring data, the preset construction face geofence, and the procedures in the construction log data. When the vessel is within the designated construction area perimeter fence, it is identified as the dredging condition; when the vessel speed is less than the second speed threshold, the drilling rig is on, and the vessel is within the blasting enclosure, it is identified as the blasting condition; when the vessel speed is greater than the third speed threshold, the mud pump is off, and the vessel is within the mud dumping area enclosure, it is identified as the mud dumping condition; when the vessel speed is between the fourth and fifth speed thresholds, the mud pump is off, and the vessel is within the transfer channel, it is identified as the mud barge transportation condition.

[0109] The operating condition identification module can be integrated into the operating condition identification module of the cloud analysis platform.

[0110] The system further includes a first calculation module for calculating CEMS direct emissions based on the CEMS monitoring data in the multi-source data; a second calculation module for calculating fuel carbon balance emissions based on the fuel system monitoring data in the multi-source data; and a deviation calculation module for calculating the relative deviation based on the CEMS direct emissions and the fuel carbon balance emissions.

[0111] The first calculation module, the second calculation module, and the deviation calculation module can be implemented by the emission accounting module in the cloud analysis platform. The emission accounting module is used to perform CEMS mass flow method, fuel carbon balance method, missing measurement supplementation calculation, and deviation judgment.

[0112] The system further includes a triggering module for generating a rule update trigger signal if the relative deviation is greater than a first deviation threshold; a feedback generation module for generating a feedback data packet based on the rule update trigger signal, the operating condition confidence level, and the relative deviation; and a rule update module for updating the operating condition identification rules based on the feedback data packet, generating updated operating condition identification rules for identifying the current operating condition of the vessel in the next monitoring cycle.

[0113] The triggering module, feedback generation module, and rule update module can be integrated into the cloud analysis platform and linked with the operating condition identification module and emission accounting module to form a feedback optimization mechanism.

[0114] The system also includes a main ledger output module for outputting Category 1 direct emission results, including CO2 emissions from ship fuel combustion, equipment-level emissions, process-level emissions, and space unit emissions; a supplementary ledger output module for outputting material consumption replenishment results, including the consumption of materials such as lubricating oil, hydraulic oil, filter elements, wire ropes, welding materials, explosive materials, and spare parts, as well as the replenishment of implicit carbon; and a system management and application layer for access control, data storage, report display, quality traceability, early warning analysis, parameter configuration, and feedback optimization.

[0115] The main ledger output module and the supplementary ledger output module can output the results of Category 1 direct emissions and the supplementary results of material consumption, respectively. The system management and application layer supports report display, early warning analysis and emission reduction suggestion generation.

[0116] like Figure 2 As shown, in one engineering implementation, the system is deployed according to the following layers: acquisition layer, transmission layer, edge computing layer, cloud analysis layer, and results application layer. The main work vessel is equipped with a CEMS and fuel flow meter, while auxiliary vessels are connected to at least fuel ledgers and AIS / RTK data. CO2 sensors are deployed at the upwind background point outside the port, the downwind point of the construction site, and the port entrance. The edge gateway performs minute-level averaging and anomaly marking. The cloud platform generates reports according to hours, days, months, and project periods, and retains original data, process data, and calculation results for subsequent auditing and review. The edge gateway is located in a shore base station, work vessel, or port management station, supports at least one communication method among 4G / 5G, NB-IoT, Beidou short message service, and ship-shore Wi-Fi, and caches original data, quality control tags, and device status when the network is interrupted, and retransmits and reconstructs timestamps after communication is restored. The cloud-based analytics platform includes a traceable computing link, which associates and stores raw data, preprocessed data, operating condition identification results, emission accounting results, missing measurement and supplementary calculation results, data quality level, and ledger output results. It also supports querying, verification, and exporting data according to project, vessel, equipment, process, voyage segment, spatial unit, and accounting cycle.

[0117] Taking a waterway maintenance and dredging project as an example, the project includes one main dredging vessel, two mud barges and one transport vessel.

[0118] The main engine and generator exhaust pipes of the main dredging vessel are equipped with shipborne CEMS, and the mud barges and transport vessels are connected to fuel flow meters and AIS / RTK data; background CO2 sensors are deployed on the upwind side of the navigation marks in the construction area, and downwind CO2 sensors are deployed on the downwind side of the navigation marks; the shore base station is equipped with a high-precision CO2 analyzer and a weather station.

[0119] The system collects CEMS, AIS / RTK and PLC data at a frequency of 1s to 10s, performs calculations based on the 1-minute average, and compares CEMS and fuel carbon balance on a daily scale.

[0120] When the main working vessel is in dredging operation, the system identifies that the vessel speed is less than 2 knots, the mud pump and cutter head equipment are turned on, and the vessel position is within the construction face enclosure, and attributes the CEMS emissions for the corresponding time period to the dredging operation and the corresponding construction face.

[0121] When mud barges enter the transport route and pass through the dumping area enclosure, the system attributes the fuel-based emissions to the mud barge transport and dumping operations.

[0122] When a transport vessel leaves the project fence to conduct non-project navigation, the system will remove or mark the emissions during that period as non-project emissions based on the vessel whitelist and operation attribution rules.

[0123] When the deviation between the CEMS mass flow rate calculation result and the fuel carbon balance result is less than 10% on a certain day, the system marks the direct emission result for that day as Grade A; when the CEMS flow meter of a certain device has been missing measurements for more than a preset time, the system calls the fuel carbon balance method to make up the difference and writes the make-up calculation ratio into the report.

[0124] If the supplementary calculation ratio exceeds the threshold, the data quality level for that period will be automatically reduced.

[0125] In the material replenishment ledger, the system reads the requisition forms, return forms, and waste records of lubricating oil, hydraulic oil, filter elements, wire ropes, and welding materials, matches the emission factors after unifying the units, and outputs the material replenishment carbon ledger separately.

[0126] This supplementary ledger is only used for material reduction management and project-wide carbon management, and is not included in the total amount of Category 1 direct emissions from offshore platforms.

[0127] The above embodiments are provided to enable those skilled in the art to understand and apply this application. Those skilled in the art will readily make various modifications to the above embodiments and apply the general principles described herein to other embodiments without inventive effort. Therefore, this application is not limited to the above embodiments, and any improvements and modifications made to this application based on the disclosure thereof should be within the scope of protection of this application.

Claims

1. A method for monitoring carbon emissions from port and shipping operations based on multi-source fusion, characterized in that, include: The data obtained from the ship includes multi-source monitoring data such as CEMS monitoring data, fuel system monitoring data, AIS / RTK monitoring data, equipment PLC monitoring data, and construction log data. The multi-source monitoring data is preprocessed to generate preprocessed multi-source data; Based on the AIS / RTK monitoring data, the equipment PLC monitoring data, and the construction log data from the multi-source data, the current operating condition of the vessel is identified, and an operating condition confidence score is generated. The operating condition confidence score is a measure of the consistency between the identified current operating condition and the procedures in the construction log data. Calculate the direct emissions from CEMS based on the CEMS monitoring data from the multi-source data. Calculate the fuel system monitoring data from the multi-source data to determine the fuel carbon balance emissions. The relative deviation is calculated based on the CEMS direct emissions and the fuel carbon balance emissions. If the relative deviation is greater than the first deviation threshold, a rule update trigger signal is generated, which is used to start the update process of the working condition identification rules; The trigger signal, the operating condition confidence level, and the relative deviation are updated according to the rules to generate a feedback data packet. Based on the feedback data packet, the operating condition identification rules are updated to generate updated operating condition identification rules, which are used to identify the current operating condition of the vessel in the next monitoring cycle. The process of updating the work condition identification rules based on the feedback data packet includes: comparing the identified current work condition with the corresponding time period in the construction log data on a time-by-time basis; when the two are consistent, determining that the work condition confidence level meets the requirements; when the two are inconsistent, determining that the work condition confidence level is lower than a preset value, and marking the corresponding time period as a period to be reviewed; obtaining the manual review result generated after manually reviewing the period to be reviewed; incorporating the manual review result into the feedback data packet; and adjusting the ship speed threshold, equipment start / stop logic, and construction surface geofence matching parameters in the work condition identification rules based on the manual review result, the relative deviation, and the work condition confidence level in the feedback data packet.

2. The method for monitoring carbon emissions from port and shipping operations based on multi-source fusion as described in claim 1, characterized in that, The step of preprocessing the multi-source monitoring data to generate preprocessed multi-source data includes: Wet-based CO2 concentration and flue gas humidity were obtained from the CEMS monitoring data. The wet-based CO2 concentration is corrected to a dry-based CO2 concentration based on the flue gas humidity to generate a dry-based CO2 concentration. The dry basis CO2 concentration is used as part of the multi-source data.

3. The method for monitoring carbon emissions from port and shipping operations based on multi-source fusion as described in claim 1, characterized in that, The step of identifying the current operating condition of the vessel based on the AIS / RTK monitoring data, the equipment PLC monitoring data, and the construction log data from the multi-source data includes: Based on the vessel speed in the AIS / RTK monitoring data, the mud pump start / stop status, cutterhead start / stop status, and drilling rig start / stop status in the equipment PLC monitoring data, the preset construction face geofence, and the procedures in the construction log data, port and shipping maintenance-specific operation conditions are identified, including dredging, reef blasting, mud barge transportation, and mud dumping conditions. When the ship speed is less than the first speed threshold and the mud pump or the cutter head is in the on / off state and the ship is located within the preset construction surface geofence, it is identified as the dredging condition. When the ship speed is less than the second speed threshold, the drilling rig is in the on / off state, and the ship is located within the blasting fence, it is identified as the blasting condition. When the ship speed is greater than the third speed threshold, the mud pump is in the off state, and the ship is located within the mud dumping area fence, it is identified as the mud dumping condition. When the vessel speed is between the fourth and fifth speed thresholds, the mud pump is in the off-state, and the vessel is located in the transfer channel, it is identified as the mud barge transportation condition.

4. The method for monitoring carbon emissions from port and shipping operations based on multi-source fusion as described in claim 1, characterized in that, Also includes: Set a second deviation threshold and a first deviation threshold, wherein the first deviation threshold is greater than the second deviation threshold; After calculating the relative deviation, it is determined whether the relative deviation is greater than the second deviation threshold; If the relative deviation is greater than the second deviation threshold, then CEMS calibration or fuel data verification is triggered. Then determine whether the relative deviation is greater than the first deviation threshold; If the relative deviation is greater than the first deviation threshold, then the rule update trigger signal is generated.

5. A carbon emission monitoring system for port and shipping operations based on multi-source fusion, characterized in that, include: The data acquisition module is used to acquire multi-source monitoring data from the ship, including CEMS monitoring data, fuel system monitoring data, AIS / RTK monitoring data, equipment PLC monitoring data, and construction log data. The preprocessing module is used to preprocess the multi-source monitoring data to generate preprocessed multi-source data; The working condition identification module is used to identify the current working condition of the vessel based on the AIS / RTK monitoring data, the equipment PLC monitoring data and the construction log data in the multi-source data, and generate a working condition confidence score. The working condition confidence score is a consistency measure between the identified current working condition and the process in the construction log data. The first calculation module is used to calculate the direct emissions of CEMS based on the CEMS monitoring data in the multi-source data; The second calculation module is used to calculate the fuel carbon balance emissions based on the fuel system monitoring data in the multi-source data. The deviation calculation module is used to calculate the relative deviation based on the CEMS direct emissions and the fuel carbon balance emissions. The triggering module is used to generate a rule update trigger signal if the relative deviation is greater than a first deviation threshold. The rule update trigger signal is used to start the update process of the working condition identification rule. The feedback generation module is used to update the trigger signal, the operating condition confidence level, and the relative deviation according to the rules to generate a feedback data packet; The rule update module is used to update the operating condition identification rules according to the feedback data packet, and generate updated operating condition identification rules for identifying the current operating condition of the vessel in the next monitoring cycle. The process of updating the work condition identification rules based on the feedback data packet includes: comparing the identified current work condition with the corresponding time period in the construction log data on a time-by-time basis; when the two are consistent, determining that the work condition confidence level meets the requirements; when the two are inconsistent, determining that the work condition confidence level is lower than a preset value, and marking the corresponding time period as pending review; obtaining the manual review result generated after manual review of the time period to be reviewed; incorporating the manual review result into the feedback data packet; and adjusting the ship speed threshold, equipment start / stop logic, and construction surface geofence matching parameters in the work condition identification rules based on the manual review result, the relative deviation, and the work condition confidence level in the feedback data packet.

6. The carbon emission monitoring system for port and shipping operations based on multi-source fusion as described in claim 5, characterized in that, The preprocessing module includes a dry basis correction submodule, comprising: Wet-based CO2 concentration and flue gas humidity were obtained from the CEMS monitoring data. The wet-based CO2 concentration is corrected to a dry-based CO2 concentration based on the flue gas humidity to generate a dry-based CO2 concentration. The dry basis CO2 concentration is used as part of the multi-source data.

7. A carbon emission monitoring system for port and shipping operations based on multi-source fusion as described in claim 5, characterized in that, The operating condition identification module includes a rule model submodule, comprising: Based on the vessel speed in the AIS / RTK monitoring data, the mud pump start / stop status, cutterhead start / stop status, and drilling rig start / stop status in the equipment PLC monitoring data, the preset construction face geofence, and the procedures in the construction log data, port and shipping maintenance-specific operation conditions are identified, including dredging, reef blasting, mud barge transportation, and mud dumping conditions. When the ship speed is less than the first speed threshold and the mud pump or the cutter head is in the on / off state and the ship is located within the preset construction surface geofence, it is identified as the dredging condition. When the ship speed is less than the second speed threshold, the drilling rig is in the on / off state, and the ship is located within the blasting fence, it is identified as the blasting condition. When the ship speed is greater than the third speed threshold, the mud pump is in the off state, and the ship is located within the mud dumping area fence, it is identified as the mud dumping condition. When the vessel speed is between the fourth and fifth speed thresholds, the mud pump is in the off-state, and the vessel is located in the transfer channel, it is identified as the mud barge transportation condition.

Images