Energy consumption management system and method for a marine vessel

Abstract

The application discloses a kind of energy consumption management system and method of ship equipment, comprising: distributed sensing network, for real-time acquisition equipment operating parameter and environmental parameter;Edge computing module is connected with distributed sensing network, is configured to calculate working condition entropy value and environmental disturbance coefficient based on equipment operating parameter and environmental parameter, then generate uniform weight factor;Intelligent analysis module is communicatively connected with edge computing module, configured to dynamically adjust the preset energy consumption benchmark threshold based on uniform weight factor, generate optimization instruction, and according to uniform weight factor implementation early warning confidence calibration;Equipment control module is connected with intelligent analysis module, configured to execute optimization instruction based on the safety constraint condition of uniform weight factor. Through the uniform weight factor generated by working condition entropy value and environmental disturbance coefficient fusion dynamic coordination data acquisition, analysis decision and control execution, significantly reduce the energy consumption abnormal misjudgment rate of ship in complex sea state and improve the adaptability of closed-loop control.

Description

Technical Field

[0001] This invention relates to the field of energy efficiency management technology for ship equipment, and particularly to an energy consumption management system and method for ship equipment. Background Technology

[0002] Traditional ship energy consumption monitoring systems cannot effectively distinguish whether energy consumption anomalies originate from changes in the internal state of the equipment or from external marine environmental disturbances under complex sea conditions. This leads to the system using fixed thresholds for energy consumption assessment and control decisions. When encountering internal or external disturbances such as waves or sudden load changes, the misjudgment rate increases significantly, energy-saving optimization commands frequently fail or cause safety risks, and the system cannot achieve accurate energy consumption management that is adaptive to operating conditions. Existing technical solutions lack a collaborative quantification mechanism for the chaos of ship operating conditions and the intensity of environmental disturbances, making it difficult to build a dynamic closed-loop control system, which restricts the reliability and adaptability of ship energy efficiency optimization. Summary of the Invention

[0003] In view of this, the present invention proposes an energy consumption management system and method for ship equipment, which can significantly reduce the false alarm rate of energy consumption anomalies in complex sea conditions and improve the safety adaptability of closed-loop control. The present invention provides the following technical solution:

[0004] An energy management system for ship equipment includes:

[0005] A distributed sensor network, configured to cover the target ship's equipment and environmental monitoring points, is used to collect equipment operating parameters and environmental parameters in real time;

[0006] The edge computing module is connected to the distributed sensor network and is configured to calculate the operating condition entropy value and environmental disturbance coefficient based on the device operating parameters and environmental parameters, and then generate a unified weighting factor.

[0007] The intelligent analysis module is communicatively connected to the edge computing module and is configured to dynamically adjust the preset energy consumption benchmark threshold based on the unified weighting factor, generate optimization instructions, and perform early warning confidence calibration according to the unified weighting factor.

[0008] The device control module is connected to the intelligent analysis module and is configured to execute optimization instructions based on the security constraints of the unified weight factor.

[0009] Optionally, the distributed sensor network includes heterogeneous sensor nodes:

[0010] The equipment monitoring nodes are deployed on the ship's main engine crankshaft, pump valves, and power grid bus, and are configured to collect vibration spectrum, temperature, and current time series data.

[0011] An environmental monitoring node is deployed on the outside of the ship and configured to collect wave energy spectral density data.

[0012] Optionally, the sampling frequency of the equipment monitoring node and the environmental monitoring node is dynamically adjusted in real time according to the unified weighting factor: the sampling frequency is increased when the unified weighting factor increases, and the sampling frequency is decreased when the unified weighting factor decreases.

[0013] The device monitoring node and the environment monitoring node upload device operating parameters and environmental parameters to the edge computing module only when the rate of change of the unified weighting factor exceeds a preset threshold. Otherwise, they perform compression operations on the device operating parameters and environmental parameters and upload the compressed feature data after compression to the edge computing module.

[0014] Optionally, the edge computing module includes:

[0015] The working condition entropy calculation unit is configured to receive the operating parameters of the equipment, generate a probability distribution of discrete working condition states through real-time clustering, and output the working condition entropy value that quantifies the uncertainty within the working condition.

[0016] The environmental disturbance coefficient calculation unit is configured to receive wave energy spectrum density data in the environmental parameters, perform frequency domain convolution operation in combination with the ship's motion response transfer function, and output an environmental disturbance coefficient that quantifies the intensity of external marine environmental disturbance.

[0017] The weighting factor generation unit is configured to generate a unified weighting factor by fusing the operating condition entropy value and the environmental disturbance coefficient through a nonlinear coupling relationship.

[0018] Optionally, the intelligent analysis module includes:

[0019] The dynamic benchmark adjustment unit is configured to calculate the performance degradation factor based on preset equipment maintenance data, perform nonlinear modulation in combination with the unified weight factor, and dynamically enhance the modulation depth according to the environmental disturbance coefficient to generate a real-time energy consumption benchmark threshold.

[0020] The optimization instruction generation unit is configured to compare the real-time energy consumption data in the device operating parameters with the real-time energy consumption benchmark threshold, and generate an optimization instruction when the energy consumption deviation exceeds the threshold range after nonlinear modulation.

[0021] The warning confidence calibration unit is configured to calculate the warning confidence based on the complement of the operating condition entropy value and the exponential decay function of the environmental disturbance coefficient. When the confidence is lower than the preset safety threshold, the automatic warning is suppressed and only a manual review prompt is triggered.

[0022] Optionally, the device control module includes:

[0023] The safety condition judgment unit is configured to monitor the unified weight factor and the environmental disturbance coefficient in real time. When the unified weight factor exceeds the first preset threshold or the environmental disturbance coefficient exceeds the second preset threshold, it is determined that the automatic execution condition is not met.

[0024] The optimized instruction execution unit is configured to dynamically scale the adjustment amount of the equipment parameters in the optimized instruction according to a unified weighting factor when the automatic execution conditions are met, and generate a scaled control instruction to be output to the ship equipment controller.

[0025] The emergency stop unit is configured to continuously monitor the rate of change of the uniform weight factor. When the rate of change exceeds the third preset threshold, it immediately sends a stop signal to the ship's equipment controller.

[0026] Optionally, the weight factor generation unit is specifically configured as follows:

[0027] Receive the operating condition entropy value and the environmental disturbance coefficient, input the environmental disturbance coefficient into the gain regulator to generate a dynamic gain factor, and then multiply the operating condition entropy value with the dynamic gain factor to output a uniform weighting factor.

[0028] The gain regulator adjusts the gain amplitude in real time based on a preset ship motion characteristic curve.

[0029] Optionally, in the environmental disturbance coefficient calculation unit, the ship's motion response transfer function includes the roll natural frequency and the pitch damping coefficient;

[0030] The motion response transfer function and wave energy spectral density data are convolved in the frequency domain to generate the six-degree-of-freedom motion response energy value of the ship, which is then processed by power normalization to output the environmental disturbance coefficient.

[0031] Optionally, the unified weighting factor output by the edge computing module is simultaneously input as a feedback signal to the sampling control terminal of the distributed sensor network, the benchmark adjustment terminal of the intelligent analysis module, and the safety judgment terminal of the device control module, forming a forced closed-loop data flow.

[0032] This invention further discloses a method for energy consumption management of ship equipment, comprising:

[0033] Real-time acquisition of operating parameters and environmental parameters of the target ship's equipment;

[0034] The operating condition entropy value is calculated based on the operating parameters to quantify the uncertainty of the operating conditions. The environmental disturbance coefficient is calculated based on the environmental parameters to quantify the intensity of external disturbances. The operating condition entropy value and the environmental disturbance coefficient are then fused through a nonlinear coupling relationship to generate a unified weighting factor.

[0035] Based on the unified weighting factor, the energy consumption benchmark threshold is dynamically adjusted to generate equipment optimization instructions, and the warning confidence level is calibrated according to the unified weighting factor.

[0036] The device optimization instructions are executed based on the safety constraints of the unified weighting factor, forming a closed-loop control process.

[0037] According to the technical solution of the present invention, the operating parameters of ship equipment and marine environmental parameters are collected in real time through a distributed sensor network. The edge computing module integrates the operating condition entropy value and the environmental disturbance coefficient to generate a unified weighting factor, which drives the intelligent analysis module to dynamically adjust the energy consumption benchmark threshold and calibrate the early warning confidence level. Based on the safety constraints of this factor, the equipment control module executes optimization instructions, thereby accurately distinguishing whether the energy consumption anomaly originates from changes in the internal state of the equipment or external environmental disturbances under complex sea conditions. This significantly reduces the misjudgment rate and improves the safety adaptability of closed-loop control, solving the problem of energy-saving command failure and navigation safety risks caused by fixed threshold evaluation in traditional systems, and realizing accurate energy consumption management with operating condition adaptation. Attached Figure Description

[0038] For illustrative and not limiting purposes, the present invention will now be described in conjunction with embodiments and accompanying drawings, wherein:

[0039] Figure 1 This is a schematic diagram of the constituent modules of the energy management system in an embodiment of the present invention;

[0040] Figure 2 This is a flowchart illustrating the energy management method in an embodiment of the present invention. Detailed Implementation

[0041] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0042] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0043] It should be noted that, where there is no conflict, the embodiments and features of the embodiments in this application can be combined with each other. The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0044] refer to Figure 1 This embodiment discloses an energy consumption management system for ship equipment, including a distributed sensor network 21, an edge computing module 22, an intelligent analysis module 23, and an equipment control module 24, which are described in detail below:

[0045] The distributed sensor network 21 is configured to cover the target ship's equipment and environmental monitoring points for real-time collection of equipment operating parameters and environmental parameters.

[0046] Specifically, the distributed sensor network 21 includes heterogeneous sensor nodes. Taking a bulk carrier as an example, equipment monitoring nodes are installed on the main engine crankshaft, boiler feedwater pump valves, and power grid bus, respectively equipped with vibration sensors, temperature sensors, and current sensors; environmental monitoring nodes are installed on the mast top, equipped with band radar. This deployment strategy stems from the need to simultaneously capture the internal state of equipment and external ocean disturbances, such as bearing vibration spectra and wave energy spectra, for abnormal ship energy consumption diagnosis. Specifically, on the one hand, the internal state of equipment, such as main engine bearing wear, changes slowly under stable operating conditions, resulting in redundant data from high-frequency sampling; on the other hand, external ocean disturbances, such as swell impacts or sudden changes in operating conditions, such as lock chamber load switching, can trigger millisecond-level energy consumption peaks, requiring high-density data capture. Traditional fixed sampling schemes suffer from a 42% loss rate of critical data under swell conditions, and high-frequency sampling leads to communication overload. This implementation balances data integrity and communication load through a dynamic sampling mechanism.

[0047] Heterogeneous sensor nodes have built-in processing units to execute adaptive sampling algorithms:

[0048] The unified weighting factor output by the edge computing module 22 is received in real time via the industrial Ethernet interface. The initial sampling frequency is For example, if the value is 100Hz, then the real-time sampling frequency is... The dynamic adjustment formula is as follows: ,in, This is the sensitivity coefficient. As the benchmark weight value, and These are the minimum and maximum boundaries of the frequency, respectively. This is the amplitude limiting function. When... As the value increases, the uncertainty in characterizing the operating conditions or environment also increases. Linear boosting to capture transient peaks; when When decreasing, Linear reduction is used to reduce the acquisition of redundant data by adjusting the sampling frequency.

[0049] Furthermore, the collected data is uploaded, according to... rate of change ,when When the data exceeds a preset threshold, the original time-series data, such as vibration acceleration sequences and wave spectrum sampling points, is uploaded. Otherwise, compression is performed to extract the temporal characteristics of the collected data and generate compressed feature data, such as vibration RMS values ​​and wave dominant frequency energy proportions. This allows for data uploads using less bandwidth, significantly reducing packet loss rates in specific environments compared to traditional full data uploads, thereby greatly improving the capture rate of critical events.

[0050] The edge computing module 22 is connected to the distributed sensor network 21 and is configured to calculate the operating condition entropy value and environmental disturbance coefficient based on the device operating parameters and environmental parameters, and then generate a unified weighting factor.

[0051] The edge computing module 22 is deployed in a dual-redundant hardware platform within the ship's engine room control cabinet, receiving compressed feature data from a distributed sensor network in real time via an Ethernet interface. Due to the stringent constraints of the ship's edge environment—satellite communication latency as high as 5 seconds, making it impossible to rely on the cloud for handling sudden changes in operating conditions; and traditional local computing, which only performs simple threshold judgments, failing to quantify the coupling effect between the chaos of operating conditions and environmental disturbances—the edge computing module 22 achieves millisecond-level dynamic decision-making through a three-layer cascaded unit. Specifically, it includes an operating condition entropy calculation unit 221, an environmental disturbance coefficient calculation unit 222, and a weight factor generation unit 223.

[0052] The operating condition entropy calculation unit 221 is configured to collect the operating parameter vector of the acquisition device. ,in The vibration RMS value, For temperature, For current, a lightweight K-means algorithm is used to generate discrete operating condition state sets. ; Calculate the probability of each state ,in For state Number of occurrences Calculate the original entropy value for the number of samples in the sliding window. ,in, This represents the total number of discrete operating conditions. Indicates the first The probability of each operating condition is then normalized by the total number of historical conditions M, and the operating condition entropy value is output: Therefore, it can be seen that due to the strong time-varying nature of ship operating conditions, such as OEI≈0 when anchored and stationary, and OEI>0.8 during storm maneuvers, normalization eliminates the influence of historical data scale, making OEI∈[0,1]. Experimental results show that this algorithm accurately captures the entropy jump caused by load switching when ships enter and exit locks, improving the operating condition identification accuracy by 31.5% compared to the unnormalized entropy value.

[0053] Environmental disturbance coefficient calculation unit 222 is configured to receive wave energy spectrum density. ,in The angular frequency is used in conjunction with the pre-stored ship motion response transfer function. Perform frequency domain convolution: ,in, Generated from the ship's hydrodynamic model, including the natural frequency of rolling. and pitch damping coefficient , This characterizes the energy value of a ship's six degrees of freedom motion response. Then, it is based on the main engine's rated power. Normalized to 10% of the baseline, the output environmental disturbance coefficient is: .

[0054] Weighting factor generation unit 223 is configured to input environmental disturbance coefficient EDC into a lookup table-type gain regulator to generate dynamic gain factor G: Then, the operating condition entropy value OEI is integrated to generate a unified weighting factor: ,in, For the preset ship motion characteristic curve, The gain coefficient, determined through optimization using historical ship navigation data, reflects the amplification effect of environmental disturbances on the system's decision weights. This nonlinear coupling mechanism solves the decoupling of internal and external disturbances; for example, when a ship encounters a sudden surge (EDC spike) but the equipment status is stable (OEI low), Appropriately increase the threshold to relax control and avoid false intervention; when equipment failure (high OEI) is combined with calm sea state (low EDC), Maintain high values ​​and strengthen monitoring to reduce the false positive rate.

[0055] The intelligent analysis module 23 is communicatively connected to the edge computing module and is configured to dynamically adjust the preset energy consumption benchmark threshold based on the unified weight factor, generate optimization instructions, and perform early warning confidence calibration according to the unified weight factor.

[0056] The intelligent analysis module 23 is deployed on the ship's cloud server and receives the unified weighting factor output by the edge computing module via the shipbuilding industry Ethernet. Operating Entropy Indicator (OEI) and Environmental Disturbance Factor (EDC). Due to the fundamental flaw of traditional ship energy management systems—high misjudgment rate under sudden operating conditions—namely, the inability of fixed threshold schemes to distinguish between energy efficiency degradation caused by equipment aging and instantaneous fluctuations caused by environmental disturbances, the false trigger rate of optimization commands reaches 61% during operation. This implementation achieves precise decision-making through a three-layer dynamic control unit, including a dynamic benchmark adjustment unit 231, an optimization command generation unit 232, and a warning confidence calibration unit 233.

[0057] Specifically, the dynamic benchmark adjustment unit 231 is configured to read the inherent energy efficiency parameters of the equipment from the ship maintenance database. and historical decay factor Calculate the baseline threshold Combined with Perform nonlinear modulation: ,in, As the reference modulation coefficient, This is the environmental enhancement coefficient.

[0058] The instruction generation unit 232 is configured to receive real-time energy consumption values ​​sent by the distributed sensor network 21. Calculate the relative deviation .when , The modulated threshold, and When the value is less than the preset safety execution threshold, generate optimization instructions: ,in Indicates the first Adjustable controllable quantities of equipment for similar ships This represents the total number of controlled equipment types. The adjustable controllable quantities include, but are not limited to, main engine speed, pump frequency, power grid allocation ratio, or air conditioning air volume, and their specific physical forms are dynamically mapped by the interface protocol of the ship's equipment controller.

[0059] The early warning confidence calibration unit 233 is configured to calculate the early warning confidence level. : ,in, The attenuation coefficient is... Characterizing the stability weights of the operating conditions Suppress false early warnings under high-disturbance operating conditions. When The system suppresses automatic warnings and only sends manual review prompts to the HMI (Hardware Management Interface). A preset safety threshold is set. This mechanism reduces the false alarm rate of the equipment while maintaining a high true fault detection rate.

[0060] The device control module 24 is connected to the intelligent analysis module and is configured to execute optimization instructions based on the security constraints of the unified weight factor.

[0061] Equipment control module 24 is deployed in the ship's engine room control cabinet and is hardwired to the ship's PLC system via a bus, receiving optimization instructions output by intelligent analysis module 23 in real time. Unified weighting factor And the Environmental Disturbance Factor (EDC). When a ship's energy management system directly executes full-amplitude optimization commands under sudden operating conditions (such as encountering a 3-meter swell), it can easily lead to an engine overload shutdown rate as high as 32%. This equipment's control module 24 employs a triple safety protection mechanism—a safety condition judgment unit 241, an optimization command execution unit 242, and an emergency abort unit 243—to ensure dynamic matching between control actions and system uncertainties, while simultaneously guaranteeing that command execution delays meet requirements.

[0062] Specifically, the safety condition judgment unit 241 implements the dual locking logic of the ship safety regulations, including setting a safety execution threshold. With environmental disturbance threshold ,when or At that time, it was determined that the automatic execution conditions were not met. This was because the ship's roll resonance zone (EDC high) coincided with the equipment's critical fault state ( All scenarios (high) are considered high-risk; exceeding any one condition requires manual intervention. Therefore, a unified weighting factor is used... The OR operation with the environmental disturbance coefficient EDC can effectively enable execution control for any high-risk scenario.

[0063] The optimized instruction execution unit 242 is configured to optimize instructions when the above-mentioned automatic execution conditions are met. Perform dynamic scaling and generate device parameter adjustment instructions. : , where ⊙ denotes element-wise multiplication of a vector; For the whole vector; This is a scaling sensitivity coefficient. The linear decay function is based on the ship's hydrodynamic characteristics: in Output full-width command at the time; When the amplitude is increased, the control amplitude is conservatively contracted to ensure smooth operation under high disturbance conditions. Actual measurements show that during navigation in cross waves in the strait ( The scaling mechanism reduces the host speed adjustment range from 10% to 4.15% to avoid exceeding the limit of power grid frequency fluctuations.

[0064] Emergency stop unit 243 is configured for continuous monitoring rate of change Set the circuit breaker threshold ;when Immediately upon activation, a stop signal (hard-wired emergency stop priority) is sent to the PLC. This fuse mechanism is designed for sudden disturbance scenarios, such as ice floe impact. The value of is optimized through ship motion simulation. For example, in At that time, i.e., uniform weighting factor When the instantaneous rate of change is greater than 0.3 per second, the risk of equipment overload increases exponentially, especially when encountering ice floes. The emergency stop unit 243 stops the auxiliary machine adjustment command within 42ms to protect the main machine from mechanical shock.

[0065] In summary, this implementation method uses a distributed sensor network to collect real-time operating parameters and environmental parameters of ship equipment, and an edge computing module fuses the operating condition entropy value and environmental disturbance coefficient to generate a unified weighting factor. and will As a forced feedback signal that runs throughout the entire process, specifically in the intelligent analysis module, The nonlinear dynamic adjustment and calibration of the driving energy consumption benchmark threshold and the early warning confidence level enable the system to accurately distinguish between equipment anomalies and environmental disturbances under sudden operating conditions. Experimental tests show that the false judgment rate is significantly reduced from 32.1% in the traditional system to 5.2%. In the equipment control module, Based on safety constraints, dynamic scaling and circuit breaker protection are implemented for optimized commands to ensure smooth and reliable control actions of the ship in high-disturbance scenarios such as cross-wave navigation, avoiding the risk of main engine overload; this method... The closed-loop architecture at its core enhances monitoring accuracy when the system is operating stably and adaptively relaxes the control threshold when the environment is severely disturbed. This solves the fundamental defects of traditional fixed threshold schemes, such as high misjudgment rate and poor control safety under complex sea conditions, and provides a technical paradigm for ship energy efficiency management that combines accuracy and robustness.

[0066] refer to Figure 2 This embodiment further discloses a method for energy consumption management of ship equipment, including the following steps:

[0067] S100: Real-time acquisition of operating and environmental parameters of target ship equipment. Specifically, it acquires equipment operating parameters and wave energy spectrum data in real time through vibration sensors deployed on the main engine crankshaft, temperature / current sensors on pump valves, and a band radar at the top of the mast; the node's built-in processing unit receives unified weighting factors fed back from the edge computing module in real time via industrial Ethernet. According to the formula Dynamically adjust the sampling frequency, and according to Data upload strategy is determined as follows: Raw time-series data is uploaded only when the rate of change exceeds a preset threshold; otherwise, only compressed feature data is transmitted, thus reducing the satellite communication load. The initial sampling frequency, This is the sensitivity coefficient. As the benchmark weight value, and These are the minimum and maximum boundaries of the frequency, respectively. This is the amplitude limiting function.

[0068] S200: Based on the operating parameters, calculate the operating condition entropy value to quantify the uncertainty of the operating conditions; based on the environmental parameters, calculate the environmental disturbance coefficient to quantify the intensity of external disturbances; and fuse the operating condition entropy value and the environmental disturbance coefficient through a nonlinear coupling relationship to generate a unified weighting factor. Specifically, the edge computing node performs K-means clustering on the equipment operating parameters to generate a discrete operating condition state probability distribution. Calculate the normalized chemical condition entropy value ,in This represents the total number of discrete operating conditions. Indicates the first The probability of each working condition, M being the total number of historical conditions; simultaneously, the wave energy spectrum density... With ship motion response transfer function Perform frequency domain convolution, and output environmental disturbance coefficients after power normalization. ,in, Further through Nonlinear fusion generates a unified weighting factor, where, ,in, For the preset ship motion characteristic curve, This is the gain coefficient.

[0069] S300: Based on the unified weighting factor, dynamically adjust the energy consumption benchmark threshold, generate equipment optimization instructions, and calibrate the early warning confidence level according to the unified weighting factor. Specifically, the intelligent analysis platform reads the inherent energy efficiency of the equipment. and attenuation factor , combined With EDC dynamically adjusted baseline threshold ,in, , As the reference modulation coefficient, For environmental enhancement factor; when real-time energy consumption and The relative deviation exceeds the threshold and When the value is less than the preset safety execution threshold, a device parameter adjustment command is generated: Simultaneously calculate the early warning confidence level. ,when Automatic early warning system for time suppression.

[0070] S400: Execute the equipment optimization instructions based on the safety constraints of the unified weighting factor to form a closed-loop control process; specifically, the equipment controller executes a triple safety mechanism, namely, setting a safety execution threshold. With environmental disturbance threshold ,when or If the conditions for automatic execution are not met, then automatic execution is disabled; for optimization instructions... Perform dynamic scaling and generate device parameter adjustment instructions. : , where ⊙ denotes element-wise multiplication of a vector; For the whole vector; This is a scaling sensitivity factor. Continuous monitoring. rate of change Set the circuit breaker threshold ;when When this happens, immediately send a stop signal to the PLC (hard-wired emergency stop priority).

[0071] This embodiment provides a non-transitory computer-readable storage medium that stores computer instructions that cause a computer to execute the methods provided in the above-described embodiments.

[0072] Those skilled in the art will understand that all or part of the steps of the above-described method implementation can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above-described method implementation. The aforementioned storage medium includes various storage media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.

[0073] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0074] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0075] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An energy consumption management system for ship equipment, characterized in that, include: A distributed sensor network, configured to cover the target ship's equipment and environmental monitoring points, is used to collect equipment operating parameters and environmental parameters in real time; The edge computing module is connected to the distributed sensor network and is configured to calculate the operating condition entropy value and environmental disturbance coefficient based on the device operating parameters and environmental parameters, and then generate a unified weighting factor. The intelligent analysis module is communicatively connected to the edge computing module and is configured to dynamically adjust the preset energy consumption benchmark threshold based on the unified weighting factor, generate optimization instructions, and perform early warning confidence calibration according to the unified weighting factor. The device control module is connected to the intelligent analysis module and is configured to execute optimization instructions based on the security constraints of the unified weight factor.

2. The energy management system according to claim 1, characterized in that, The distributed sensor network includes heterogeneous sensor nodes: The equipment monitoring nodes are deployed on the ship's main engine crankshaft, pump valves, and power grid bus, and are configured to collect vibration spectrum, temperature, and current time series data. An environmental monitoring node is deployed on the outside of the ship and configured to collect wave energy spectral density data.

3. The energy management system according to claim 2, characterized in that, The sampling frequency of the equipment monitoring node and the environmental monitoring node is dynamically adjusted in real time according to the unified weighting factor: the sampling frequency is increased when the unified weighting factor increases, and the sampling frequency is decreased when the unified weighting factor decreases. The device monitoring node and the environment monitoring node upload device operating parameters and environmental parameters to the edge computing module only when the rate of change of the unified weighting factor exceeds a preset threshold. Otherwise, they perform compression operations on the device operating parameters and environmental parameters and upload the compressed feature data after compression to the edge computing module.

4. The energy management system according to claim 2, characterized in that, The edge computing module includes: The working condition entropy calculation unit is configured to receive the operating parameters of the equipment, generate a probability distribution of discrete working condition states through real-time clustering, and output the working condition entropy value that quantifies the uncertainty within the working condition. The environmental disturbance coefficient calculation unit is configured to receive wave energy spectrum density data in the environmental parameters, perform frequency domain convolution operation in combination with the ship's motion response transfer function, and output an environmental disturbance coefficient that quantifies the intensity of external marine environmental disturbance. The weighting factor generation unit is configured to generate a unified weighting factor by fusing the operating condition entropy value and the environmental disturbance coefficient through a nonlinear coupling relationship.

5. The energy management system according to claim 1, characterized in that, The intelligent analysis module includes: The dynamic benchmark adjustment unit is configured to calculate the performance degradation factor based on preset equipment maintenance data, perform nonlinear modulation in combination with the unified weight factor, and dynamically enhance the modulation depth according to the environmental disturbance coefficient to generate a real-time energy consumption benchmark threshold. The optimization instruction generation unit is configured to compare the real-time energy consumption data in the device operating parameters with the real-time energy consumption benchmark threshold, and generate an optimization instruction when the energy consumption deviation exceeds the threshold range after nonlinear modulation. The warning confidence calibration unit is configured to calculate the warning confidence based on the complement of the operating condition entropy value and the exponential decay function of the environmental disturbance coefficient. When the confidence is lower than the preset safety threshold, the automatic warning is suppressed and only a manual review prompt is triggered.

6. The energy management system according to claim 1, characterized in that, The device control module includes: The safety condition judgment unit is configured to monitor the unified weight factor and the environmental disturbance coefficient in real time. When the unified weight factor exceeds the first preset threshold or the environmental disturbance coefficient exceeds the second preset threshold, it is determined that the automatic execution condition is not met. The optimized instruction execution unit is configured to dynamically scale the adjustment amount of the equipment parameters in the optimized instruction according to a unified weighting factor when the automatic execution conditions are met, and generate a scaled control instruction to be output to the ship equipment controller. The emergency stop unit is configured to continuously monitor the rate of change of the uniform weight factor. When the rate of change exceeds the third preset threshold, it immediately sends a stop signal to the ship's equipment controller.

7. The energy management system according to claim 4, characterized in that, The weight factor generation unit is specifically configured as follows: Receive the operating condition entropy value and the environmental disturbance coefficient, input the environmental disturbance coefficient into the gain regulator to generate a dynamic gain factor, and then multiply the operating condition entropy value with the dynamic gain factor to output a uniform weighting factor. The gain regulator adjusts the gain amplitude in real time based on a preset ship motion characteristic curve.

8. The energy management system according to claim 4, characterized in that, In the environmental disturbance coefficient calculation unit, the ship's motion response transfer function includes the roll natural frequency and the pitch damping coefficient; The motion response transfer function and wave energy spectral density data are convolved in the frequency domain to generate the six-degree-of-freedom motion response energy value of the ship, which is then processed by power normalization to output the environmental disturbance coefficient.

9. The energy management system according to claim 1, characterized in that, The unified weighting factor output by the edge computing module is simultaneously input as a feedback signal to the sampling control terminal of the distributed sensor network, the benchmark adjustment terminal of the intelligent analysis module, and the safety judgment terminal of the device control module, forming a forced closed-loop data flow.

10. A method for energy consumption management of ship equipment, characterized in that, include: Real-time acquisition of operating parameters and environmental parameters of the target ship's equipment; The operating condition entropy value is calculated based on the operating parameters to quantify the uncertainty of the operating conditions. The environmental disturbance coefficient is calculated based on the environmental parameters to quantify the intensity of external disturbances. The operating condition entropy value and the environmental disturbance coefficient are then fused through a nonlinear coupling relationship to generate a unified weighting factor. Based on the unified weighting factor, the energy consumption benchmark threshold is dynamically adjusted to generate equipment optimization instructions, and the warning confidence level is calibrated according to the unified weighting factor. The device optimization instructions are executed based on the safety constraints of the unified weighting factor, forming a closed-loop control process.

Images