Marine distributed green ammonia production scheduling system and method based on intelligent management

Abstract

The invention provides a maritime distributed green ammonia production scheduling system and method based on intelligent management, and relates to the technical field of maritime renewable energy utilization, and the system comprises a distributed ammonia production platform which is used for the distributed production of maritime green ammonia. A renewable energy power generation device, water electrolysis hydrogen production equipment, a synthetic ammonia reactor, a green ammonia energy storage device and an ammonia production platform sensor network are configured; the multifunctional ship node is used for production, transportation and consumption of green ammonia and is provided with a green ammonia transportation carrier, an offshore production node expansion unit, a green ammonia fuel consumption terminal and a ship state sensor; the intelligent green ammonia management platform integrates a data transmission module, a multi-target optimization scheduling module, a fault prediction and emergency response module and a supply chain management module, and is used for communicating with an ammonia production platform and ship nodes through the Internet of Things technology, so that intelligent closed-loop management of green ammonia production, transportation and consumption can be realized; the production scheduling efficiency and the energy utilization rate are improved, and the transportation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of offshore renewable energy utilization, and in particular to an offshore distributed green ammonia production scheduling system and method based on intelligent management. Background Art

[0002] As the global carbon neutrality goal advances, renewable energy conversion technologies such as offshore wind power and green ammonia are receiving increasing attention.

[0003] Existing distributed offshore green ammonia production systems generally rely on manual scheduling or semi-automated control, failing to respond in real time to dynamic changes such as wind power fluctuations and equipment failures. This can lead to insufficient energy utilization and low production efficiency. Furthermore, in terms of production allocation mechanisms and supply chain integration, this approach lacks intelligent collaborative management of distributed offshore nodes. Furthermore, traditional terrestrial green ammonia production requires long-distance transportation, which carries high transportation costs and poor scheduling matching, easily leading to supply-demand imbalances and preventing effective closed-loop control of production, transportation, and consumption.

[0004] Therefore, it is necessary to provide an offshore distributed green ammonia production scheduling system and method based on intelligent management to solve the above technical problems. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides an offshore distributed green ammonia production scheduling system and method based on intelligent management, which is used to solve the problems that in traditional manual or semi-automatic scheduling modes, operators find it difficult to respond quickly to emergencies, which reduces the stability and safety of the system. In addition, the existing technology lacks effective intelligent decision-making support, making it difficult to achieve optimal resource allocation, which affects the overall economic benefits of green ammonia production.

[0006] The present invention provides an offshore distributed green ammonia production scheduling system based on intelligent management, the production scheduling system comprising: A distributed ammonia production platform, used for distributed production of offshore green ammonia, is equipped with renewable energy power generation equipment, water electrolysis hydrogen production equipment, ammonia synthesis reactor, green ammonia energy storage device, and an ammonia production platform sensor network; Multifunctional ship node, used for the production, transportation and consumption of offshore green ammonia, equipped with a green ammonia transport carrier, offshore production node expansion unit, green ammonia fuel consumption terminal and ship status sensor; An intelligent green ammonia management platform, integrating a data transmission module, a multi-objective optimization scheduling module, a fault prediction and emergency response module, and a supply chain management module, is used to communicate with the distributed ammonia production platform and the multifunctional ship node via Internet of Things technology; Among them, the data transmission module is used to obtain the real-time green ammonia production data of the distributed ammonia production platform and the ship transportation status data of the multi-functional ship node, and encrypt and transmit the real-time green ammonia production data and the ship transportation status data to the multi-objective optimization scheduling module, the fault prediction and emergency response module and the supply chain management module based on the blockchain network; the multi-objective optimization scheduling module is used to update the dynamic production scheduling strategy through a dynamic allocation algorithm; the fault prediction and emergency response module is used to construct a comprehensive fault prediction model based on the LSTM neural network, perform abnormality prediction on the distributed ammonia production platform, and trigger a comprehensive emergency response mechanism in advance; the supply chain management module is used to generate target replenishment instructions using an inventory optimization algorithm, adjust the dynamic production scheduling strategy in real time based on the target replenishment instructions, and send it to the distributed ammonia production platform and the multi-functional ship node.

[0007] Preferably, the ammonia production platform sensor network collects energy supply data of the renewable energy power generation device, hydrogen synthesis data of the water electrolysis hydrogen production equipment, ammonia synthesis data of the synthetic ammonia reactor, and green ammonia storage capacity data of the green ammonia energy storage device at preset collection time intervals, and summarizes the energy supply data, hydrogen synthesis data, ammonia synthesis data, and green ammonia storage capacity data to obtain the real-time green ammonia production data; The ship status sensor is used to collect the ship transportation status data of the multifunctional ship node; Based on the Internet of Things technology, the collected real-time green ammonia production data and the ship transportation status data are uploaded to the data acquisition module.

[0008] Preferably, after receiving the real-time green ammonia production data and the ship transportation status data, the multi-objective optimization scheduling module extracts the renewable energy power generation in the energy supply data; the hydrogen production and consumption power, hydrogen synthesis power and hydrogen synthesis maximum production capacity in the hydrogen synthesis data; the ammonia synthesis consumption power, ammonia synthesis power and ammonia synthesis maximum production capacity in the ammonia synthesis data; the liquid ammonia inventory in the green ammonia storage data and the total number of transport ships, ship transportation distance, ship load factor, actual ammonia load of ships, and maximum load of ships in the ship transportation status data, calculates the sum of the hydrogen production and consumption power and the ammonia synthesis consumption power to obtain the total consumption power, and obtains the preset scheduling cycle and the actual total green ammonia demand; A dynamic production scheduling model is constructed based on the dynamic allocation algorithm, and the dynamic production scheduling model includes a multi-objective optimization scheduling function and corresponding constraints. The multi-objective optimization scheduling function aims to minimize energy utilization, minimize transportation costs, and minimize inventory fluctuations. The constraints are the upper limit of equipment production capacity, ship load limit, and market demand constraint. The corresponding calculation formula is as follows: Where, represents energy utilization rate; represents the transportation cost; Indicates the inventory fluctuation amount; Indicates the total amount of electricity consumed; represents the amount of electricity generated by renewable energy; M represents the total number of transport ships; represents the shipping distance of the i-th ship; represents the ship load factor of the i-th ship; N represents the total number of distributed ammonia production platforms; represents the liquid ammonia inventory of the jth distributed ammonia production platform; Indicates the average value of the liquid ammonia inventory of all distributed ammonia production platforms; max indicates the maximum value operation; min indicates the minimum value operation; represents the hydrogen synthesis power of the jth distributed ammonia production platform; represents the maximum hydrogen synthesis capacity of the jth distributed ammonia production platform; represents the ammonia synthesis power of the jth distributed ammonia production platform; represents the maximum ammonia synthesis capacity of the jth distributed ammonia production platform; represents the actual ammonia load of the i-th ship; represents the maximum deadweight of the i-th ship; Indicates the preset scheduling period; Indicates the actual total green ammonia demand.

[0009] Preferably, an improved genetic algorithm is used to solve the dynamic production scheduling model according to a preset update time interval, and the dynamic production scheduling strategy is updated based on the solution results, specifically including the ammonia production plan of the distributed ammonia production platform and the ship transportation path of the multi-functional ship node.

[0010] Preferably, the fault prediction and emergency response module is used to construct a comprehensive fault prediction model based on an LSTM neural network, perform abnormality prediction on the distributed ammonia production platform, and trigger a comprehensive emergency response mechanism in advance, specifically including: Performing feature extraction on the real-time green ammonia production data to obtain corresponding real-time green ammonia production features; The real-time green ammonia production feature is input into the forget gate of the comprehensive fault prediction model to determine the real-time green ammonia production feature that needs to be discarded from the memory unit. The corresponding calculation formula is as follows: Where, Represents the output of the forget gate at the current time t, which is used to determine the real-time green ammonia production features that need to be discarded from the memory unit; represents the activation function; Represents the weight of the forget gate; Represents the hidden state at the previous moment t-1; represents the real-time green ammonia production characteristics input at the current time t; Indicates hidden state and real-time green ammonia production characteristics The vector of components; Represents the bias of the forget gate; Based on the input gate of the comprehensive fault prediction model, the real-time green ammonia production characteristics that need to be stored in the memory unit are determined, and the corresponding calculation formula is as follows: Where, The output of the input gate at the current time t is used to determine the real-time green ammonia production characteristics that need to be stored in the memory unit; Represents the weight of the input gate; represents the bias of the input gate; The candidate memory units based on the comprehensive fault prediction model determine the candidate green ammonia production characteristics, and the corresponding calculation formula is as follows: Where, Represents the candidate memory unit at the current time t, which is used to determine the candidate green ammonia production characteristics; represents the hyperbolic tangent function; Represents the weight of the candidate memory unit; represents the bias of the candidate memory unit; The calculation formula for updating the memory unit is as follows: Where, Represents the memory unit at the current time t; Represents the memory unit at the previous moment t-1; Based on the output gate of the comprehensive fault prediction model, the candidate green ammonia production features that need to be output to the hidden state are determined, and the corresponding calculation formula is as follows: Where, Represents the output of the output gate at the current time t, which is used to determine the candidate green ammonia production features that need to be output to the hidden state; Represents the weight of the output gate; Represents the bias of the output gate; The hidden state at the current moment is determined based on the output of the memory unit and the output gate. The corresponding calculation formula is as follows: Where, represents the hidden state at the current time t.

[0011] Preferably, the hidden state at the current moment is mapped to the comprehensive failure probability through a fully connected layer, and the corresponding calculation formula is as follows: Where, represents the comprehensive failure probability at the current time t, ; represents the weight of the fully connected layer; represents the bias of the fully connected layer; A critical failure threshold is obtained, and when the comprehensive failure probability is greater than or equal to the critical failure threshold, the comprehensive emergency response mechanism is triggered in advance.

[0012] Preferably, the supply chain management module generates the target replenishment instruction using the inventory optimization algorithm, specifically including: The average demand rate, the standard deviation of the demand rate, and the safety factor of demand fluctuation are obtained, the round-trip shipping time of the ship in the ship shipping status data is extracted, and the trigger replenishment inventory quantity is calculated using the inventory optimization algorithm as follows: Where CBK represents the inventory quantity that triggers replenishment; represents the average demand rate; WFSJ represents the round-trip shipping time; represents the safety factor of demand fluctuation; represents the standard deviation of the demand rate; The corresponding target replenishment instruction is generated based on the trigger replenishment inventory.

[0013] An offshore distributed green ammonia production scheduling method based on intelligent management, the production scheduling method comprising: Acquire the real-time green ammonia production data in the distributed ammonia production platform and the ship transportation status data in the multifunctional ship node and upload them to the data transmission module; The real-time green ammonia production data and the ship transportation status data are transmitted to the multi-objective optimization scheduling module, the fault prediction and emergency response module, and the supply chain management module through the data transmission module; Based on the multi-objective optimization scheduling module, the dynamic allocation algorithm is used to update the dynamic production scheduling strategy; Based on the fault prediction and emergency response module, the comprehensive fault prediction model based on the LSTM neural network is constructed to predict abnormalities of the distributed ammonia production platform and trigger the comprehensive emergency response mechanism in advance; Based on the supply chain management module, the inventory optimization algorithm is used to generate the target replenishment instructions, and the dynamic production scheduling strategy is adjusted in real time based on the target replenishment instructions and sent to the distributed ammonia production platform and the multi-functional ship node, wherein the intelligent green ammonia management platform includes the data transmission module, the multi-objective optimization scheduling module, the fault prediction and emergency response module and the supply chain management module.

[0014] Compared with related technologies, the offshore distributed green ammonia production scheduling system and method based on intelligent management provided by the present invention has the following beneficial effects: The present invention can obtain real-time green ammonia production data in the distributed ammonia production platform and ship transportation status data in the multi-functional ship node and upload them to the data transmission module; the real-time green ammonia production data and ship transportation status data are transmitted to the multi-objective optimization scheduling module, the fault prediction and emergency response module and the supply chain management module through the data transmission module; based on the multi-objective optimization scheduling module, a dynamic allocation algorithm is used to update the dynamic production scheduling strategy; based on the fault prediction and emergency response module, a comprehensive fault prediction model based on the LSTM neural network is constructed to predict abnormalities of the distributed ammonia production platform and trigger the comprehensive emergency response mechanism in advance; based on the supply chain management module, an inventory optimization algorithm is used to generate target replenishment instructions, and the dynamic production scheduling strategy is adjusted in real time based on the target replenishment instructions and sent to the distributed ammonia production platform and the multi-functional ship node; wherein, the intelligent green ammonia management platform includes the data transmission module, the multi-objective optimization scheduling module, the fault prediction and emergency response module and the supply chain management module, thereby realizing intelligent closed-loop management of the entire process of green ammonia production, transportation and consumption, significantly improving production scheduling efficiency and energy utilization, and reducing transportation costs.

[0015] The present invention improves the utilization rate of renewable energy and significantly reduces the loss of wind and power curtailment through a multi-objective optimization scheduling algorithm and real-time data drive, and shortens the green ammonia production cycle, reduces the unit production cost, improves the inventory turnover rate, and effectively alleviates the resource waste problem caused by the imbalance between supply and demand under the traditional model through the dynamic coordination of distributed ammonia production platforms and ship nodes. The present invention accurately predicts the abnormal conditions of the ammonia production platform through a comprehensive fault prediction model based on LSTM neural network, and combines the minute-level emergency response mechanism to reduce system downtime, significantly reduce the risk of production interruption caused by emergencies, further improve the robustness of the system in extreme weather or equipment failure scenarios, and ensure the continuity and safety of offshore operations. The multifunctional ship node of the present invention overcomes the defects of the long-distance transportation mode of traditional land production through the three-in-one design of production, transportation, and consumption, and reduces transportation costs. The present invention realizes the full-chain traceability and dynamic balance of green ammonia from production to consumption through blockchain smart contracts and inventory optimization algorithms, forming an offshore energy closed-loop network, which significantly reduces the environmental load of green ammonia production throughout its life cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a system block diagram of the offshore distributed green ammonia production scheduling system based on intelligent management of the present invention; Figure 2 This is a flow chart of the offshore distributed green ammonia production scheduling method based on intelligent management of the present invention. DETAILED DESCRIPTION

[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0018] Example 1

[0019] like Figure 1 As shown, an offshore distributed green ammonia production scheduling system based on intelligent management includes: A distributed ammonia production platform, used for distributed production of offshore green ammonia, is equipped with renewable energy power generation equipment, water electrolysis hydrogen production equipment, ammonia synthesis reactor, green ammonia energy storage device, and an ammonia production platform sensor network; Among them, the distributed ammonia production platform is the basic production node of the system, which is deployed in areas rich in offshore wind power or photovoltaic resources. Through modular design, it realizes on-site production and energy conversion of green ammonia.

[0020] Specifically, renewable energy generation devices utilize offshore wind turbines or photovoltaic arrays to convert renewable energy sources such as wind and solar power into electricity, providing zero-carbon electricity for water electrolysis hydrogen production. These devices feature maximum power point tracking (MPPT), dynamically adjusting power generation efficiency based on environmental parameters to maximize energy capture. Water electrolysis hydrogen production equipment typically utilizes a proton exchange membrane electrolyzer, which uses renewable electricity to decompose water into high-purity hydrogen and oxygen. Proton exchange membrane electrolyzers offer fast response times and high energy efficiency, adapting to the fluctuating nature of offshore wind power. Ammonia synthesis reactors, based on the Haber-Bosch process, synthesize ammonia from hydrogen and nitrogen at high temperatures (300-500°C), high pressures (15-30 MPa), and catalysts (such as iron-based catalysts). The nitrogen is typically separated from air. Green ammonia energy storage devices utilize cryogenic, atmospheric-pressure tanks or pressure vessels to store liquid ammonia. The energy storage device is equipped with a thermal insulation system to reduce evaporation losses and support rapid loading and unloading operations at ship nodes. The ammonia production platform's sensor network consists of multiple types of sensors, such as anemometers, photovoltaic irradiance meters, pressure transmitters, and liquid level gauges. These sensors collect real-time energy supply status, equipment operating parameters, and inventory data through an IoT gateway.

[0021] In practical applications, the distributed ammonia production platform uses renewable energy generation to power water electrolysis hydrogen production equipment, achieving zero-carbon energy supply for offshore green ammonia production, reducing reliance on terrestrial fossil energy, and lowering the environmental impact of production at the source. The coordinated operation of the ammonia synthesis reactor and green ammonia energy storage device allows for dynamic adjustment of production capacity based on fluctuations in renewable energy, avoiding resource waste caused by curtailment of wind and power, and improving energy utilization stability. The ammonia production platform's sensor network collects real-time data on equipment status, energy supply, and inventory, providing a high-precision decision-making basis for the intelligent management platform, significantly enhancing the production scheduling system's adaptability to complex offshore environments.

[0022] Multifunctional ship node, used for the production, transportation and consumption of offshore green ammonia, equipped with a green ammonia transport carrier, offshore production node expansion unit, green ammonia fuel consumption terminal and ship status sensor; Among them, the multifunctional ship node overcomes the single transportation defect of traditional ships and can produce, transport and consume green ammonia at sea. Among them, the green ammonia transport carrier is equipped with a low-temperature ammonia storage tank and an intelligent loading and unloading system. It can be transported according to the path instructions of the intelligent management platform. During the transportation process, the ship status sensors such as GPS, inertial navigation system, cargo hold monitoring sensors, etc. can be used to monitor the ship's position, ship load and liquid ammonia status in real time. The offshore production node expansion unit can be equipped with modular ammonia production equipment to start auxiliary production on site during periods of excess wind power to temporarily increase the system's production capacity. The unit is plug-and-play and can be linked to the ship's energy system through a quick interface. The green ammonia fuel consumption terminal can provide the ship with appropriate power supply. The ship status sensor can monitor and collect the transportation status data of the multifunctional ship node in real time.

[0023] It should be noted that the integrated design of the green ammonia transport carrier and the offshore production node expansion unit can achieve dynamic optimal planning of the green ammonia transport route through intelligent scheduling, reducing ineffective navigation and energy consumption; at the same time, it can utilize excess offshore wind power to achieve temporary production increases and improve the overall capacity utilization of the system.

[0024] Furthermore, green ammonia fuel consumption terminals can directly convert green ammonia into ship propulsion, establishing a closed-loop mechanism of self-production and self-consumption, eliminating the long-distance carbon footprint and scheduling delays associated with land transportation. Furthermore, ship status sensors can collect and provide real-time data support for dynamic optimization of the supply chain through the collection and feedback of transportation and consumption data.

[0025] An intelligent green ammonia management platform, integrating a data transmission module, a multi-objective optimization scheduling module, a fault prediction and emergency response module, and a supply chain management module, is used to communicate with the distributed ammonia production platform and the multifunctional ship node via Internet of Things technology; Among them, the data transmission module is used to obtain the real-time green ammonia production data of the distributed ammonia production platform and the ship transportation status data of the multi-functional ship node, and encrypt and transmit the real-time green ammonia production data and the ship transportation status data to the multi-objective optimization scheduling module, the fault prediction and emergency response module and the supply chain management module based on the blockchain network; the multi-objective optimization scheduling module is used to update the dynamic production scheduling strategy through a dynamic allocation algorithm; the fault prediction and emergency response module is used to construct a comprehensive fault prediction model based on the LSTM neural network, perform abnormality prediction on the distributed ammonia production platform, and trigger a comprehensive emergency response mechanism in advance; the supply chain management module is used to generate target replenishment instructions using an inventory optimization algorithm, adjust the dynamic production scheduling strategy in real time based on the target replenishment instructions, and send it to the distributed ammonia production platform and the multi-functional ship node.

[0026] In the intelligent green ammonia management platform, the data transmission module can obtain the production data of the distributed ammonia production platform and the transportation data of the ship nodes in real time through the Internet of Things protocol, and use alliance chain technology to hash and encrypt and distribute these data to ensure the data's immutability and security, solving the information leakage risks that may exist in traditional Internet of Things transmission. In addition, real-time data can be pre-processed through edge computing nodes, such as outlier filtering and normalization processing, to improve data quality.

[0027] The multi-objective optimization scheduling module adopts a dynamic allocation algorithm, integrating multi-dimensional objectives such as energy utilization, transportation costs, and inventory balance. It realizes global collaborative optimization of distributed nodes through an improved genetic algorithm, and updates the production scheduling strategy in real time to generate production plans and ship transportation routes for each ammonia production platform, achieving optimal resource allocation under multi-variable constraints, avoiding the lag and local defects of manual or semi-automatic scheduling, and improving resource allocation efficiency and production flexibility.

[0028] The fault prediction and emergency response module builds an equipment fault prediction model based on the long short-term memory network (LSTM), predicts potential faults in the ammonia production platform, and automatically triggers a comprehensive emergency response mechanism when an anomaly is detected, such as switching to a backup node and adjusting the transportation route. This can shorten the anomaly processing time, reduce the risk of equipment damage and production interruption losses, ensure the continuous operation of the production scheduling system, and enhance the system robustness and safety.

[0029] The supply chain management module uses an inventory optimization algorithm, combines real-time demand and transportation status, calculates the optimal replenishment quantity and order point, generates corresponding replenishment instructions, and dynamically adjusts production plans and ship scheduling, thereby reducing inventory backlogs and shortage risks, improving the response speed and operational efficiency of the entire chain, and at the same time, can trace the flow of green ammonia through smart contract technology to ensure the transparency and reliability of the supply chain.

[0030] During the specific implementation process, the ammonia production platform sensor network collects the energy supply data of the renewable energy power generation device, the hydrogen synthesis data of the water electrolysis hydrogen production equipment, the ammonia synthesis data of the synthetic ammonia reactor, and the green ammonia storage capacity data of the green ammonia energy storage device according to the preset collection time interval, and summarizes the energy supply data, the hydrogen synthesis data, the ammonia synthesis data, and the green ammonia storage capacity data to obtain the real-time green ammonia production data; The ship status sensor is used to collect the ship transportation status data of the multifunctional ship node; Based on the Internet of Things technology, the collected real-time green ammonia production data and the ship transportation status data are uploaded to the data acquisition module.

[0031] Among them, the ammonia production platform sensor network synchronously collects energy supply, hydrogen synthesis, ammonia synthesis and inventory data at preset intervals, such as minutes, to achieve digital mapping of all elements of the production process.

[0032] For example, real-time power data from renewable energy generation devices can directly reflect fluctuations in wind and solar energy, helping the system dynamically adjust the workload of hydrogen production and ammonia synthesis, avoiding equipment startup and shutdown losses or waste of production capacity due to unstable energy supply. The refined collection of hydrogen and ammonia synthesis data, such as output and reaction efficiency, provides real-time capacity boundary conditions for multi-objective optimization scheduling algorithms, ensuring that production plans match actual equipment capabilities and improving the rationality of resource utilization.

[0033] Ship status sensors can capture transportation status in real time, such as location, load, speed, etc., and combined with the inventory data of the ammonia production platform, enable the intelligent management platform to calculate transportation demand and route feasibility in real time.

[0034] For example, when the inventory of a platform approaches a safety threshold, the system can quickly dispatch nearby ships to perform transportation tasks based on ship location data, shortening the decision-making delay of traditional manual scheduling, improving the system's response speed to environmental changes, and significantly enhancing the coordination of production and transportation.

[0035] After receiving the real-time green ammonia production data and the ship transportation status data, the multi-objective optimization scheduling module extracts the renewable energy power generation from the energy supply data; the hydrogen production power consumption, hydrogen synthesis power, and maximum hydrogen synthesis capacity from the hydrogen synthesis data; the ammonia synthesis power consumption, ammonia synthesis power, and maximum ammonia synthesis capacity from the ammonia synthesis data; the liquid ammonia inventory from the green ammonia storage data, and the total number of transport ships, ship transportation distance, ship load factor, actual ammonia load, and maximum ship load from the ship transportation status data, calculates the sum of the hydrogen production power consumption and the ammonia synthesis power consumption to obtain the total power consumption, and obtains the preset scheduling cycle and the actual total green ammonia demand; A dynamic production scheduling model is constructed based on the dynamic allocation algorithm, and the dynamic production scheduling model includes a multi-objective optimization scheduling function and corresponding constraints. The multi-objective optimization scheduling function aims to minimize energy utilization, minimize transportation costs, and minimize inventory fluctuations. The constraints are the upper limit of equipment production capacity, ship load limit, and market demand constraint. The corresponding calculation formula is as follows: Where, represents energy utilization rate; represents the transportation cost; Indicates the inventory fluctuation amount; Indicates the total amount of electricity consumed; represents the amount of electricity generated by renewable energy; M represents the total number of transport ships; represents the shipping distance of the i-th ship; represents the ship load factor of the i-th ship; N represents the total number of distributed ammonia production platforms; represents the liquid ammonia inventory of the jth distributed ammonia production platform; Indicates the average value of the liquid ammonia inventory of all distributed ammonia production platforms; max indicates the maximum value operation; min indicates the minimum value operation; represents the hydrogen synthesis power of the jth distributed ammonia production platform; represents the maximum hydrogen synthesis capacity of the jth distributed ammonia production platform; represents the ammonia synthesis power of the jth distributed ammonia production platform; represents the maximum ammonia synthesis capacity of the jth distributed ammonia production platform; represents the actual ammonia load of the i-th ship; represents the maximum deadweight of the i-th ship; Indicates the preset scheduling period; Indicates the actual total green ammonia demand.

[0036] An improved genetic algorithm is used to solve the dynamic production scheduling model according to a preset update time interval, and the dynamic production scheduling strategy is updated according to the solution results, specifically including the ammonia production plan of the distributed ammonia production platform and the ship transportation path of the multi-functional ship node.

[0037] It is understandable that the multi-objective optimization scheduling module can first extract key information from real-time green ammonia production data and ship transportation status data, such as the total power generation of renewable energy and the actual amount of electricity used for hydrogen production and synthetic ammonia; the current operating power and maximum production capacity of hydrogen production and synthetic ammonia equipment; the liquid ammonia inventory of each production platform; the number of transport ships, sailing distance, load capacity and actual ammonia load, etc.

[0038] Then, by calculating the total electricity consumption for hydrogen production and ammonia synthesis, that is, the total electricity demand, combined with a preset scheduling cycle, such as 15 minutes, and market demand forecasts, a dynamic production scheduling model can be constructed. This model contains three core optimization objectives: maximizing energy utilization to ensure that renewable energy is used for hydrogen production and ammonia synthesis, reducing the waste of abandoned electricity; minimizing transportation costs, that is, reducing energy consumption and time costs during transportation by optimizing ship navigation routes and load distribution; and minimizing inventory fluctuations, that is, balancing the liquid ammonia inventory of each ammonia production platform to avoid inventory backlogs on some platforms and inventory shortages on others. At the same time, the model sets multiple constraints, such as equipment production capacity cannot exceed the maximum limit, ship load cannot exceed the safety threshold, and total output needs to meet market demand, to ensure the feasibility and safety of the production scheduling strategy.

[0039] Furthermore, the multi-objective optimization scheduling module adopts an improved genetic algorithm, that is, an optimization search algorithm that simulates natural selection and genetic mechanisms. It automatically solves the dynamic production scheduling model at regular intervals, such as 5 minutes, to generate the optimal production plan and transportation route.

[0040] For example, when renewable energy generation surges at a particular ammonia production platform, the improved genetic algorithm prioritizes that platform for increased production and dispatches nearby ships to transport its excess product. When market demand suddenly increases, the algorithm coordinates production capacity adjustments across multiple platforms and plans the shortest transportation routes to ensure a balance between supply and demand. This dynamic adjustment mechanism enables the entire production scheduling system to respond to environmental changes in real time, significantly improving resource utilization efficiency and production flexibility.

[0041] The fault prediction and emergency response module is used to build a comprehensive fault prediction model based on the LSTM neural network, predict abnormalities of the distributed ammonia production platform, and trigger a comprehensive emergency response mechanism in advance, specifically including: Performing feature extraction on the real-time green ammonia production data to obtain corresponding real-time green ammonia production features; The real-time green ammonia production feature is input into the forget gate of the comprehensive fault prediction model to determine the real-time green ammonia production feature that needs to be discarded from the memory unit. The corresponding calculation formula is as follows: Where, Represents the output of the forget gate at the current time t, which is used to determine the real-time green ammonia production features that need to be discarded from the memory unit; represents the activation function; Represents the weight of the forget gate; Represents the hidden state at the previous moment t-1; represents the real-time green ammonia production characteristics input at the current time t; Indicates hidden state and real-time green ammonia production characteristics The vector of components; Represents the bias of the forget gate; Based on the input gate of the comprehensive fault prediction model, the real-time green ammonia production characteristics that need to be stored in the memory unit are determined, and the corresponding calculation formula is as follows: Where, The output of the input gate at the current time t is used to determine the real-time green ammonia production characteristics that need to be stored in the memory unit; Represents the weight of the input gate; represents the bias of the input gate; The candidate memory units based on the comprehensive fault prediction model determine the candidate green ammonia production characteristics, and the corresponding calculation formula is as follows: Where, Represents the candidate memory unit at the current time t, which is used to determine the candidate green ammonia production characteristics; represents the hyperbolic tangent function; Represents the weight of the candidate memory unit; represents the bias of the candidate memory unit; The calculation formula for updating the memory unit is as follows: Where, Represents the memory unit at the current time t; Represents the memory unit at the previous moment t-1; Based on the output gate of the comprehensive fault prediction model, the candidate green ammonia production features that need to be output to the hidden state are determined, and the corresponding calculation formula is as follows: Where, Represents the output of the output gate at the current time t, which is used to determine the candidate green ammonia production features that need to be output to the hidden state; Represents the weight of the output gate; Represents the bias of the output gate; The hidden state at the current moment is determined based on the output of the memory unit and the output gate. The corresponding calculation formula is as follows: Where, represents the hidden state at the current time t.

[0042] The hidden state at the current moment is mapped to the comprehensive failure probability through the fully connected layer. The corresponding calculation formula is as follows: Where, represents the comprehensive failure probability at the current time t, ; represents the weight of the fully connected layer; represents the bias of the fully connected layer; A critical failure threshold is obtained, and when the comprehensive failure probability is greater than or equal to the critical failure threshold, the comprehensive emergency response mechanism is triggered in advance.

[0043] It's understandable that, leveraging the time-series data processing capabilities of LSTM neural networks, comprehensive fault prediction models can automatically capture long-term dependencies and subtle fluctuation patterns in equipment operating parameters. For example, the forget gate mechanism can filter out random noise under normal operating conditions, such as short-term wind power fluctuations, while the input gate and candidate memory cells focus on persistent anomalies, such as electrolyzer voltage consistently deviating from the threshold, enabling early identification of equipment performance degradation or potential faults.

[0044] Furthermore, the model can iteratively update multiple layers of memory cells to construct a dynamic digital twin of the platform's state. This model combines historical operating patterns with real-time data to predict the platform's overall failure probability. When the overall failure probability exceeds a critical threshold, such as 0.9, the system triggers an emergency response, such as automatically switching to a backup ammonia production platform, dispatching ships to transfer inventory, or activating energy storage devices to maintain production.

[0045] This approach shifts the fault handling mechanism from a passive downtime maintenance mode to a proactive risk isolation mode, reducing production interruptions caused by sudden failures and avoiding delays and misjudgments due to manual intervention. For example, if the temperature of a platform's reactor rises abnormally, the system will issue an early warning and initiate production increases on adjacent platforms, while simultaneously dispatching the nearest vessel to transfer inventory. This entire process requires no human intervention, significantly improving the system's anti-interference capabilities and operational stability in complex offshore environments, ensuring the continuity and safety of offshore green ammonia production.

[0046] The supply chain management module generates the target replenishment instruction using the inventory optimization algorithm, specifically including: The average demand rate, the standard deviation of the demand rate, and the safety factor of demand fluctuation are obtained, the round-trip shipping time of the ship in the ship shipping status data is extracted, and the trigger replenishment inventory quantity is calculated using the inventory optimization algorithm as follows: Where CBK represents the inventory quantity that triggers replenishment; represents the average demand rate; WFSJ represents the round-trip shipping time; represents the safety factor of demand fluctuation; represents the standard deviation of the demand rate; The corresponding target replenishment instruction is generated based on the trigger replenishment inventory.

[0047] It should be noted that the supply chain management module can use inventory optimization algorithms to generate target replenishment instructions to achieve dynamic and precise control of green ammonia inventory.

[0048] This process can integrate core factors such as demand stability, fluctuation risk and transportation time, determine the basic replenishment quantity by analyzing the average demand rate, quantify the degree of demand fluctuation based on the standard deviation of the demand rate, amplify the safety redundancy using the demand fluctuation safety factor, and then incorporate the round-trip transportation time of the ship to calculate the impact of replenishment delays, ultimately forming a scientific trigger replenishment inventory.

[0049] Furthermore, target replenishment instructions generated based on the trigger replenishment inventory level can avoid inventory backlogs or shortages caused by traditional empirical replenishment, reduce storage costs and energy waste caused by excess inventory, and ensure supply continuity through preemptive replenishment when demand suddenly changes. This data-driven replenishment mechanism significantly improves inventory turnover across the entire supply chain, enhances the supply chain's adaptability to complex offshore demand scenarios, and ensures efficient coordination across all links of green ammonia production, transportation, and consumption.

[0050] Example 2

[0051] like Figure 2 As shown, a method for scheduling offshore distributed green ammonia production based on intelligent management includes: S1, obtaining the real-time green ammonia production data in the distributed ammonia production platform and the ship transportation status data in the multifunctional ship node and uploading them to the data transmission module; S2, transmitting the real-time green ammonia production data and the ship transportation status data to the multi-objective optimization scheduling module, the fault prediction and emergency response module, and the supply chain management module through the data transmission module; S3, based on the multi-objective optimization scheduling module, using the dynamic allocation algorithm to update the dynamic production scheduling strategy; S4, based on the fault prediction and emergency response module, constructing the comprehensive fault prediction model based on the LSTM neural network, performing abnormality prediction on the distributed ammonia production platform, and triggering the comprehensive emergency response mechanism in advance; S5. Based on the supply chain management module, the inventory optimization algorithm is used to generate the target replenishment instruction. Based on the target replenishment instruction, the dynamic production scheduling strategy is adjusted in real time and sent to the distributed ammonia production platform and the multi-functional ship node. The intelligent green ammonia management platform includes the data transmission module, the multi-objective optimization scheduling module, the fault prediction and emergency response module and the supply chain management module.

[0052] As described in the above embodiments, the present invention, through an intelligent management-based distributed green ammonia production scheduling system and method, can obtain real-time green ammonia production data from distributed ammonia production platforms and ship transportation status data from multi-functional ship nodes and upload them to a data transmission module; the real-time green ammonia production data and ship transportation status data are transmitted to a multi-objective optimization scheduling module, a fault prediction and emergency response module, and a supply chain management module through the data transmission module; based on the multi-objective optimization scheduling module, a dynamic allocation algorithm is used to update the dynamic production scheduling strategy; based on the fault prediction and emergency response module, a comprehensive fault prediction model based on an LSTM neural network is constructed to predict anomalies of the distributed ammonia production platform and trigger a comprehensive emergency response mechanism in advance; based on the supply chain management module, an inventory optimization algorithm is used to generate target replenishment instructions, and the dynamic production scheduling strategy is adjusted in real time based on the target replenishment instructions and sent to the distributed ammonia production platform and multi-functional ship nodes; wherein, the intelligent green ammonia management platform includes a data transmission module, a multi-objective optimization scheduling module, a fault prediction and emergency response module, and a supply chain management module, thereby realizing intelligent closed-loop management of the entire process of green ammonia production, transportation, and consumption, significantly improving production scheduling efficiency and energy utilization, and reducing transportation costs.

[0053] The present invention improves the utilization rate of renewable energy and significantly reduces the loss of wind and power curtailment through a multi-objective optimization scheduling algorithm and real-time data drive, and shortens the green ammonia production cycle, reduces the unit production cost, improves the inventory turnover rate, and effectively alleviates the resource waste problem caused by the imbalance between supply and demand under the traditional model through the dynamic coordination of distributed ammonia production platforms and ship nodes. The present invention accurately predicts the abnormal conditions of the ammonia production platform through a comprehensive fault prediction model based on LSTM neural network, and combines the minute-level emergency response mechanism to reduce system downtime, significantly reduce the risk of production interruption caused by emergencies, further improve the robustness of the system in extreme weather or equipment failure scenarios, and ensure the continuity and safety of offshore operations. The multifunctional ship node of the present invention overcomes the defects of the long-distance transportation mode of traditional land production through the three-in-one design of production, transportation, and consumption, and reduces transportation costs. The present invention realizes the full-chain traceability and dynamic balance of green ammonia from production to consumption through blockchain smart contracts and inventory optimization algorithms, forming an offshore energy closed-loop network, which significantly reduces the environmental load of green ammonia production throughout its life cycle.

[0054] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0055] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0056] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. The offshore distributed green ammonia production scheduling system based on intelligent management is characterized by: The production scheduling system includes: A distributed ammonia production platform, used for distributed production of offshore green ammonia, is equipped with renewable energy power generation equipment, water electrolysis hydrogen production equipment, ammonia synthesis reactor, green ammonia energy storage device, and an ammonia production platform sensor network; Multifunctional ship node, used for the production, transportation and consumption of offshore green ammonia, equipped with a green ammonia transport carrier, offshore production node expansion unit, green ammonia fuel consumption terminal and ship status sensor; An intelligent green ammonia management platform, integrating a data transmission module, a multi-objective optimization scheduling module, a fault prediction and emergency response module, and a supply chain management module, is used to communicate with the distributed ammonia production platform and the multifunctional ship node via Internet of Things technology; Among them, the data transmission module is used to obtain the real-time green ammonia production data of the distributed ammonia production platform and the ship transportation status data of the multi-functional ship node, and encrypt and transmit the real-time green ammonia production data and the ship transportation status data to the multi-objective optimization scheduling module, the fault prediction and emergency response module and the supply chain management module based on the blockchain network; the multi-objective optimization scheduling module is used to update the dynamic production scheduling strategy through a dynamic allocation algorithm; the fault prediction and emergency response module is used to construct a comprehensive fault prediction model based on the LSTM neural network, perform abnormality prediction on the distributed ammonia production platform, and trigger a comprehensive emergency response mechanism in advance; the supply chain management module is used to generate target replenishment instructions using an inventory optimization algorithm, adjust the dynamic production scheduling strategy in real time based on the target replenishment instructions, and send it to the distributed ammonia production platform and the multi-functional ship node.

2. The offshore distributed green ammonia production scheduling system based on intelligent management according to claim 1 is characterized in that: The ammonia production platform sensor network collects, at preset collection time intervals, energy supply data of the renewable energy power generation device, hydrogen synthesis data of the water electrolysis hydrogen production equipment, ammonia synthesis data of the synthetic ammonia reactor, and green ammonia storage capacity data of the green ammonia energy storage device, and aggregates the energy supply data, hydrogen synthesis data, ammonia synthesis data, and green ammonia storage capacity data to obtain the real-time green ammonia production data; The ship status sensor is used to collect the ship transportation status data of the multifunctional ship node; Based on the Internet of Things technology, the collected real-time green ammonia production data and the ship transportation status data are uploaded to the data acquisition module.

3. The offshore distributed green ammonia production scheduling system based on intelligent management according to claim 1 is characterized in that: After receiving the real-time green ammonia production data and the ship transportation status data, the multi-objective optimization scheduling module extracts the renewable energy power generation from the energy supply data; the hydrogen production power consumption, hydrogen synthesis power, and maximum hydrogen synthesis capacity from the hydrogen synthesis data; the ammonia synthesis power consumption, ammonia synthesis power, and maximum ammonia synthesis capacity from the ammonia synthesis data; the liquid ammonia inventory from the green ammonia storage data, and the total number of transport ships, ship transportation distance, ship load factor, actual ammonia load, and maximum ship load from the ship transportation status data, calculates the sum of the hydrogen production power consumption and the ammonia synthesis power consumption to obtain the total power consumption, and obtains the preset scheduling cycle and the actual total green ammonia demand; A dynamic production scheduling model is constructed based on the dynamic allocation algorithm, and the dynamic production scheduling model includes a multi-objective optimization scheduling function and corresponding constraints. The multi-objective optimization scheduling function aims to minimize energy utilization, minimize transportation costs, and minimize inventory fluctuations. The constraints are the upper limit of equipment production capacity, ship load limit, and market demand constraint. The corresponding calculation formula is as follows: Where, represents energy utilization rate; represents the transportation cost; Indicates the inventory fluctuation amount; Indicates the total amount of electricity consumed; represents the amount of electricity generated by renewable energy; M represents the total number of transport ships; represents the shipping distance of the i-th ship; represents the ship load factor of the i-th ship; N represents the total number of distributed ammonia production platforms; represents the liquid ammonia inventory of the jth distributed ammonia production platform; Indicates the average value of liquid ammonia inventory of all distributed ammonia production platforms; max indicates the maximum value operation; min means taking the minimum value operation; represents the hydrogen synthesis power of the jth distributed ammonia production platform; represents the maximum hydrogen synthesis capacity of the jth distributed ammonia production platform; represents the ammonia synthesis power of the jth distributed ammonia production platform; represents the maximum ammonia synthesis capacity of the jth distributed ammonia production platform; represents the actual ammonia load of the i-th ship; represents the maximum deadweight of the i-th ship; Indicates the preset scheduling period; Indicates the actual total green ammonia demand.

4. The offshore distributed green ammonia production scheduling system based on intelligent management according to claim 3 is characterized in that: An improved genetic algorithm is used to solve the dynamic production scheduling model according to a preset update time interval, and the dynamic production scheduling strategy is updated according to the solution results, specifically including the ammonia production plan of the distributed ammonia production platform and the ship transportation path of the multi-functional ship node.

5. The offshore distributed green ammonia production scheduling system based on intelligent management according to claim 1 is characterized in that: The fault prediction and emergency response module is used to build a comprehensive fault prediction model based on the LSTM neural network, predict abnormalities of the distributed ammonia production platform, and trigger a comprehensive emergency response mechanism in advance, specifically including: Performing feature extraction on the real-time green ammonia production data to obtain corresponding real-time green ammonia production features; The real-time green ammonia production feature is input into the forget gate of the comprehensive fault prediction model to determine the real-time green ammonia production feature that needs to be discarded from the memory unit. The corresponding calculation formula is as follows: Where, Represents the output of the forget gate at the current time t, which is used to determine the real-time green ammonia production features that need to be discarded from the memory unit; represents the activation function; Represents the weight of the forget gate; Represents the hidden state at the previous moment t-1; represents the real-time green ammonia production characteristics input at the current time t; Indicates hidden state and real-time green ammonia production characteristics The vector of components; Represents the bias of the forget gate; Based on the input gate of the comprehensive fault prediction model, the real-time green ammonia production characteristics that need to be stored in the memory unit are determined, and the corresponding calculation formula is as follows: Where, The output of the input gate at the current time t is used to determine the real-time green ammonia production characteristics that need to be stored in the memory unit; Represents the weight of the input gate; represents the bias of the input gate; The candidate memory units based on the comprehensive fault prediction model determine the candidate green ammonia production characteristics, and the corresponding calculation formula is as follows: Where, Represents the candidate memory unit at the current time t, which is used to determine the candidate green ammonia production characteristics; represents the hyperbolic tangent function; Represents the weight of the candidate memory unit; represents the bias of the candidate memory unit; The calculation formula for updating the memory unit is as follows: Where, Represents the memory unit at the current time t; Represents the memory unit at the previous moment t-1; Based on the output gate of the comprehensive fault prediction model, the candidate green ammonia production features that need to be output to the hidden state are determined, and the corresponding calculation formula is as follows: Where, Represents the output of the output gate at the current time t, which is used to determine the candidate green ammonia production features that need to be output to the hidden state; Represents the weight of the output gate; Represents the bias of the output gate; The hidden state at the current moment is determined based on the output of the memory unit and the output gate. The corresponding calculation formula is as follows: Where, represents the hidden state at the current time t.

6. The offshore distributed green ammonia production scheduling system based on intelligent management according to claim 5 is characterized in that: The hidden state at the current moment is mapped to the comprehensive failure probability through the fully connected layer. The corresponding calculation formula is as follows: Where, represents the comprehensive failure probability at the current time t, ; represents the weight of the fully connected layer; represents the bias of the fully connected layer; A critical failure threshold is obtained, and when the comprehensive failure probability is greater than or equal to the critical failure threshold, the comprehensive emergency response mechanism is triggered in advance.

7. The offshore distributed green ammonia production scheduling system based on intelligent management according to claim 1 is characterized in that: The supply chain management module generates the target replenishment instruction using the inventory optimization algorithm, specifically including: The average demand rate, the standard deviation of the demand rate, and the safety factor of demand fluctuation are obtained, the round-trip shipping time of the ship in the ship shipping status data is extracted, and the trigger replenishment inventory quantity is calculated using the inventory optimization algorithm as follows: Where CBK represents the inventory quantity that triggers replenishment; represents the average demand rate; WFSJ represents the round-trip shipping time; represents the safety factor of demand fluctuation; represents the standard deviation of the demand rate; The corresponding target replenishment instruction is generated based on the trigger replenishment inventory.

8. A method for scheduling distributed green ammonia production at sea based on intelligent management, applied to a system for scheduling distributed green ammonia production at sea based on intelligent management as claimed in any one of claims 1 to 7, characterized in that: The production scheduling method comprises: Acquire the real-time green ammonia production data in the distributed ammonia production platform and the ship transportation status data in the multifunctional ship node and upload them to the data transmission module; The real-time green ammonia production data and the ship transportation status data are transmitted to the multi-objective optimization scheduling module, the fault prediction and emergency response module, and the supply chain management module through the data transmission module; Based on the multi-objective optimization scheduling module, the dynamic allocation algorithm is used to update the dynamic production scheduling strategy; Based on the fault prediction and emergency response module, the comprehensive fault prediction model based on the LSTM neural network is constructed to predict abnormalities of the distributed ammonia production platform and trigger the comprehensive emergency response mechanism in advance; Based on the supply chain management module, the inventory optimization algorithm is used to generate the target replenishment instructions, and the dynamic production scheduling strategy is adjusted in real time based on the target replenishment instructions and sent to the distributed ammonia production platform and the multi-functional ship node, wherein the intelligent green ammonia management platform includes the data transmission module, the multi-objective optimization scheduling module, the fault prediction and emergency response module and the supply chain management module.

Images