Intelligent low-temperature steam heating system and equipment applying digital twinning cooperative regulation and control

Abstract

The invention provides an intelligent low-temperature steam heating system and equipment applying digital twinning cooperative regulation and control. The intelligent low-temperature steam heating system comprises a data acquisition module used for acquiring inlet steam temperature, pressure and environment temperature data of each steam utilization device; the data analysis module is used for analyzing inlet steam temperature, pressure and environment temperature data based on the pre-trained pipeline heat loss correction neural network model to determine steam dryness corresponding to each steam using device; the instruction generation module is used for matching the steam dryness with the real-time service requirements of the steam using devices, and performing collaborative decision-making on the matching result to determine a steam flow distribution instruction; and the collaborative regulation and control module is used for performing operation simulation on the steam flow distribution instruction based on a digital twin model constructed by the steam pipe network, predicting pipe network pressure fluctuation and water hammer risks, and sending the steam flow distribution instruction to a collaborative regulation and control center for steam flow collaborative distribution after the operation simulation is passed. And the safety and the reliability of system operation are obviously improved.

Description

Technical Field

[0001] This invention relates to the field of automation control technology, and in particular to an intelligent low-temperature steam heating system and equipment that utilizes digital twin collaborative control. Background Technology

[0002] Currently, steam heating systems are a widely used form of heat energy supply in industrial production and heating fields. Among them, low-temperature steam heating systems usually refer to steam systems with operating temperatures within a specific range, which are commonly found in processes that are highly sensitive to steam temperature, such as food processing, textiles, pharmaceuticals, and district heating. Traditional low-temperature steam heating systems often employ a single-point feedback independent control strategy. For example, temperature and pressure sensors are installed on the main pipeline to control the operation of pressure reducing valves or desuperheaters to stabilize the steam parameters in the main pipeline. Each steam-consuming branch independently adjusts the opening of its inlet valve based on feedback from its own terminal sensors to meet the heat demand of that terminal. This decentralized control method has inherent drawbacks: 1. The flow disturbances generated during the adjustment of each branch will couple with each other, affecting the stability of the main pipeline pressure, causing overall system fluctuations, and making it difficult to meet the precise temperature control requirements of all terminals at the same time; 2. When the system's operating conditions change, it lacks the ability to coordinate and optimize the status of each piece of equipment. It often sacrifices overall energy efficiency to meet local needs, resulting in low steam utilization and increased energy consumption. 3. Although existing technologies have introduced automated control units or simple PID control loops, their control logic is still limited to local and current state feedback, and cannot predict and proactively optimize the overall dynamic thermodynamic behavior of the system. 4. In addition, traditional systems often neglect the recovery and utilization of low-grade heat energy such as industrial waste heat, resulting in the direct emission of a large amount of heat energy, causing serious energy waste and increased carbon emissions, and a high dependence on primary energy sources (such as natural gas and coal). Therefore, in order to overcome the above-mentioned defects, the present invention provides an intelligent low-temperature steam heating system and equipment that applies digital twin collaborative control. Summary of the Invention

[0003] This invention provides an intelligent low-temperature steam heating system and equipment using digital twin collaborative control. By introducing soft measurement technology that integrates data and mechanisms, and replacing expensive hardware with algorithms, it achieves low-cost, high-precision real-time monitoring of steam dryness, effectively overcoming measurement deviations caused by pipeline heat dissipation in traditional ideal formulas. Secondly, through a multi-agent collaborative decision-making mechanism, it can dynamically coordinate the steam demand of multiple steam-using devices, achieving peak shaving and valley filling, and ensuring temperature stability. Finally, by constructing a digital twin model of the pipeline network as a safety verification sandbox before issuing control commands, it can simulate and predict risks such as water hammer and pressure oscillations in advance, achieving a leap from passive response to proactive safety pre-control, significantly improving the safety and reliability of system operation, and realizing an intelligent closed loop of perception, decision-making, and safety verification. This provides an economical, accurate, stable, and safe overall solution for low-temperature steam heating systems. Furthermore, by introducing a heat pump integrated heating module, it achieves efficient recovery and reuse of low-grade industrial waste heat, converting it into high-quality medium- and low-pressure steam, significantly reducing the system's dependence on primary energy and carbon emissions.

[0004] This invention provides an intelligent low-temperature steam heating system employing digital twin collaborative control, comprising: The data acquisition module is used to collect inlet steam temperature, pressure, and ambient temperature data of various steam-using equipment in the steam pipeline network; The data analysis module is used to analyze inlet steam temperature, pressure and ambient temperature data based on a pre-trained pipeline heat loss correction neural network model to determine the steam dryness corresponding to each steam-using equipment. The instruction generation module is used to match the steam dryness with the real-time business needs of each steam-consuming equipment, and to make collaborative decisions on the matching results based on a multi-agent collaborative decision-making algorithm to determine the steam flow allocation instruction. The collaborative control module is used to simulate the operation of steam flow distribution commands based on the digital twin model constructed on the steam pipeline network, predict pipeline pressure fluctuations and water hammer risks, and send the steam flow distribution commands to the collaborative control center for collaborative steam flow distribution after the operation simulation is passed.

[0005] Preferably, an intelligent low-temperature steam heating system employing digital twin collaborative control includes a data acquisition module comprising: The instruction issuing unit is used to obtain the communication addresses of the temperature and pressure sensors pre-installed on the inlet steam pipes of each steam-using equipment in the steam network and the ambient temperature sensor pre-installed in the environment where each steam-using equipment is located, and to send data acquisition instructions to the temperature sensor, pressure sensor and ambient temperature sensor at regular intervals based on the communication addresses of the management terminal. The data acquisition unit is used for: Based on the transmission results, the control temperature sensor collects the analog signal of the inlet steam temperature and the control pressure sensor collects the analog signal of the inlet steam pressure. At the same time, the control ambient temperature sensor collects the analog signal of the ambient temperature of the steam-using equipment. Based on a preset analog-to-digital converter, the temperature analog signal, pressure analog signal, and ambient temperature analog signal are converted into digital signals, and the obtained digital signals are packaged according to the time period to obtain the data frame corresponding to each period. The data backhaul unit is used to transmit the obtained data frames back to the data processing center based on a preset wireless communication network.

[0006] Preferably, an intelligent low-temperature steam heating system employing digital twin collaborative control includes a data analysis module comprising: The data retrieval unit is used to retrieve the inlet steam temperature, inlet steam pressure and ambient temperature data of each steam-consuming equipment, and input the retrieved inlet steam temperature, inlet steam pressure and ambient temperature data of each steam-consuming equipment as input parameters to the pre-trained pipeline heat loss correction neural network model. Data analysis unit, used for: Based on the pre-trained pipeline heat loss correction neural network model, the enthalpy values ​​of saturated steam and saturated water at the corresponding pressure are determined according to the inlet steam temperature and inlet steam pressure, and the total enthalpy value of wet steam is determined according to the inlet steam temperature and inlet steam pressure. Based on ambient temperature data and the preset thermal conductivity coefficient of the steam pipeline network, the heat loss per unit length during the process of steam being transported from the main pipeline network to the inlet of each steam-using equipment is determined, and the heat loss per unit length is calculated based on the pipeline length data to determine the cumulative heat loss value. Meanwhile, the total enthalpy of wet steam is corrected based on the cumulative heat loss value to obtain the total enthalpy of standard wet steam. Based on the preset dryness analysis strategy, the total enthalpy of standard wet steam is analyzed with the enthalpy of saturated steam and saturated water at the corresponding pressure to obtain the steam dryness corresponding to each steam-using equipment.

[0007] Preferably, an intelligent low-temperature steam heating system employing digital twin collaborative control includes a data analysis unit comprising: The data correction subunit is used to obtain the total enthalpy and cumulative heat loss of the obtained wet steam, and adds the cumulative heat loss value to the total enthalpy of the wet steam after defining the cumulative heat loss value as a negative value, so as to obtain the standard total enthalpy of the wet steam. The steam dryness determination subunit is used for: Obtain the saturated steam enthalpy and saturated water enthalpy corresponding to the inlet steam pressure of each steam-using equipment, and determine the first difference between the total enthalpy of standard wet steam and the saturated water enthalpy. At the same time, determine the second difference between the saturated steam enthalpy and the saturated water enthalpy. Determine the ratio of the first difference to the second difference, and obtain the steam dryness corresponding to each steam-using equipment based on the ratio result.

[0008] Preferably, an intelligent low-temperature steam heating system employing digital twin collaborative control includes an instruction generation module comprising: The matching and judgment unit is used to match the steam dryness corresponding to each steam-consuming equipment with the real-time business requirements of each steam-consuming equipment, and to determine whether the current steam dryness meets the real-time business requirements of each steam-consuming equipment. Instruction determination unit, used for: If the current steam dryness does not meet the real-time business needs of the first steam-consuming equipment and the first steam-consuming equipment predicts that it needs to increase the steam flow, a steam consumption request is sent to the collaborative control center based on the multi-agent collaborative decision-making algorithm. Based on the steam demand request, the coordinated control center coordinates the second steam-consuming equipment, which is in the heat preservation stage and whose steam dryness meets the real-time business requirements, to temporarily suspend steam consumption. The steam demand request of the first steam-consuming equipment is matched with the temporary suspension response of the second steam-consuming equipment to determine the steam flow allocation instruction.

[0009] Preferably, an intelligent low-temperature steam heating system employing digital twin collaborative control includes an instruction determination unit comprising: The intelligent agent determination subunit is used to virtualize each steam-consuming device in the steam pipeline network as an intelligent agent with autonomous request and response capabilities; The data generation subunit is used to generate steam demand data or steam delay response data for each steam-consuming equipment based on the corresponding steam dryness and real-time business needs of each intelligent agent. The sending subunit is used to send the generated steam consumption request data or steam consumption postponement response data to the collaborative control center based on each intelligent agent. The negotiation and arbitration subunit is used to conduct negotiation and arbitration in the collaborative control center based on the received steam use request data and steam use suspension response data, and according to the central control logic. The instruction generation and distribution subunit is used to generate steam flow distribution instructions based on the negotiation and arbitration results from the collaborative control center, and then distribute the instructions to the actuators corresponding to each steam-consuming equipment.

[0010] Preferably, an intelligent low-temperature steam heating system employing digital twin collaborative control includes a collaborative control module comprising: The model building unit is used to access the management terminal and obtain the physical topology, pipeline geometric parameters and fluid dynamic characteristics of the steam pipeline network based on the access results. It then constructs a digital twin model of the steam pipeline network in the computer based on the physical topology, pipeline geometric parameters and fluid dynamic characteristics. Simulation unit, used for: Acquire steam flow distribution instructions and real-time operating status data of the steam pipeline network at the current moment. The real-time operating status data includes the pressure and temperature of each node and the opening status of each steam regulating valve. Real-time operating status data is loaded into the digital twin model, and steam flow distribution commands are used as control inputs to be executed into the digital twin model based on the loading results; Transient simulations are performed in the digital twin model based on the input results, and the dynamic pressure response process of the steam pipeline network within a preset time window is determined based on the transient simulation results. Prediction unit, used for: Based on the pressure dynamic response process, the pressure change sequence data of each node within a preset time window is extracted, and a pressure change curve is generated based on the pressure change sequence data over time. Extract the slope change characteristics and pressure peak value of the pressure change curve, and compare the slope change characteristics and pressure peak value with the corresponding preset thresholds. Based on the comparison results, predict whether the pipeline pressure fluctuation exceeds the limit or water hammer risk will occur, and obtain the target prediction result. The coordinated control unit is used for: The target prediction results are matched with preset safety constraints, and the simulation is deemed to have passed when the target prediction results meet the preset safety constraints. Based on the judgment result, the steam flow distribution command is sent to the collaborative control center, and the collaborative control center performs collaborative control of the opening degree of the steam regulating valve at the inlet of each steam-using equipment according to the steam flow distribution command.

[0011] Preferably, an intelligent low-temperature steam heating system employing digital twin collaborative control includes a prediction unit comprising: The prediction subunit is used to retrieve the preset pipeline resistance coefficient and thermal conductivity coefficient in the steam pipeline network based on the management terminal, and determine the pressure change rate and velocity change rate of the fluid in the pipeline during the steam flow redistribution process in combination with the steam flow distribution command. Determine the subunit, used for: The obtained pressure change rate and flow velocity change rate are compared with the corresponding preset pressure change threshold and preset flow velocity change threshold, respectively. If the rate of pressure change exceeds the preset pressure change threshold or the rate of flow rate change exceeds the preset flow rate change threshold, then a risk of water hammer is identified.

[0012] Preferably, in an intelligent low-temperature steam heating system employing digital twin collaborative control, the data analysis module includes a pre-trained pipeline heat loss correction neural network model, which is an adaptive control algorithm model based on deep reinforcement learning, used to optimize the low-temperature steam generation process in real time.

[0013] Preferably, an intelligent low-temperature steam heating system using digital twin collaborative control further includes: a heat pump integrated heating module; The integrated heat pump heating module includes: a multi-stage heat pump and a steam accumulator; The input end of the multi-stage heat pump is used to connect to industrial waste heat; The output end of the multi-stage heat pump is connected to the inlet of the steam accumulator. The outlet of the steam accumulator is connected to the inlet of the steam pipeline network; The multi-stage heat pump is used to gradually raise industrial waste heat to the temperature required to generate medium- and low-pressure steam and store the steam in the steam accumulator. The steam accumulator is used to release the stored steam when the steam network needs it.

[0014] This invention provides an intelligent low-temperature steam heating equipment using digital twin collaborative control, comprising: An industrial waste heat recovery and temperature raising subsystem includes a multi-stage heat pump for receiving industrial waste heat and a steam accumulator connected to the output of the multi-stage heat pump. A steam transmission and distribution network, with its inlet connected to the outlet of a steam accumulator, is used to transport steam to multiple steam-consuming devices; Multiple steam-consuming equipment execution terminals are installed on the inlet pipes of each steam-consuming equipment, including steam regulating valves, temperature sensors, pressure sensors, and ambient temperature sensors for collecting ambient temperature. The integrated control unit communicates with multi-stage heat pumps, steam accumulators, steam regulating valves, and various sensors. It contains a digital twin model of the steam piping network and is configured to perform the following operations: Collect steam temperature, pressure, and ambient temperature data at the inlet of each steam-using equipment; The cumulative heat loss value is determined based on ambient temperature data and the preset thermal conductivity coefficient of the pipeline in the steam pipeline network. The total enthalpy of wet steam determined based on inlet steam temperature and pressure is corrected based on the cumulative heat loss value to obtain the standard total enthalpy of wet steam. Based on the standard total enthalpy of wet steam and the enthalpy of saturated steam and saturated water at the corresponding pressure, the steam dryness of each steam-using equipment is determined. The steam dryness is matched with the real-time business requirements of each steam-consuming equipment, and the matching results are used to make collaborative decisions based on a multi-agent collaborative decision-making algorithm to determine the steam flow allocation instructions. The steam flow distribution command is input into the digital twin model for operation simulation to predict pipeline pressure fluctuations and water hammer risks. After the operation simulation is passed, the opening degree of the steam regulating valve at the inlet of each steam-using equipment is coordinated and controlled according to the steam flow distribution command.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: By introducing soft measurement technology that integrates data and mechanisms, and replacing expensive hardware with algorithms, low-cost, high-precision real-time monitoring of steam dryness is achieved, effectively overcoming measurement deviations caused by pipeline heat dissipation in traditional ideal formulas. Secondly, through a multi-agent collaborative decision-making mechanism, the steam demand of multiple steam-using equipment can be dynamically coordinated to achieve peak shaving and valley filling, ensuring temperature stability. Finally, by constructing a digital twin model of the pipeline network as a safety verification sandbox before the issuance of control commands, risks such as water hammer and pressure oscillation can be simulated and predicted in advance, achieving a leap from passive response to proactive safety pre-control, significantly improving the safety and reliability of system operation, and realizing an intelligent closed loop of perception, decision-making, and safety verification. This provides an economical, accurate, stable, and safe overall solution for low-temperature steam heating systems. In addition, by introducing a heat pump integrated heating module, the efficient recovery and reuse of low-grade industrial waste heat is achieved, converting it into high-quality medium- and low-pressure steam, significantly reducing the system's dependence on primary energy and carbon emissions.

[0016] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0017] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0018] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a structural diagram of an intelligent low-temperature steam heating system using digital twin collaborative control in an embodiment of the present invention; Figure 2 This is a structural diagram of the data acquisition module in an intelligent low-temperature steam heating system that applies digital twin collaborative control, according to an embodiment of the present invention. Detailed Implementation

[0019] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0020] Example 1: This example provides an intelligent low-temperature steam heating system that utilizes digital twin collaborative control, such as... Figure 1 As shown, it includes: The data acquisition module is used to collect inlet steam temperature, pressure, and ambient temperature data of various steam-using equipment in the steam pipeline network; The data analysis module is used to analyze inlet steam temperature, pressure and ambient temperature data based on a pre-trained pipeline heat loss correction neural network model to determine the steam dryness corresponding to each steam-using equipment. The instruction generation module is used to match the steam dryness with the real-time business needs of each steam-consuming equipment, and to make collaborative decisions on the matching results based on a multi-agent collaborative decision-making algorithm to determine the steam flow allocation instruction. The collaborative control module is used to simulate the operation of steam flow distribution commands based on the digital twin model constructed on the steam pipeline network, predict pipeline pressure fluctuations and water hammer risks, and send the steam flow distribution commands to the collaborative control center for collaborative steam flow distribution after the operation simulation is passed.

[0021] In this embodiment, the pre-trained pipeline heat loss correction neural network model refers to a machine learning model trained using historical operating data, specifically designed to correct the steam enthalpy calculation error caused by heat dissipation from the pipeline wall based on the inlet temperature and pressure of the steam pipeline and the ambient temperature data, thereby outputting a steam dryness value that is closer to the real physical state.

[0022] In this embodiment, steam dryness refers to the mass fraction of actual gaseous steam in wet steam, which is a key parameter used to characterize steam quality and thermodynamic state.

[0023] In this embodiment, the multi-agent collaborative decision-making algorithm refers to a distributed decision-making method that virtualizes each steam-consuming device in the steam pipeline network as an intelligent agent with autonomous request and response capabilities, and conducts negotiation and arbitration through a central control logic (collaborative control center) to achieve dynamic load balancing and optimization at the system level.

[0024] In this embodiment, the digital twin model refers to a virtual system model constructed based on the physical topology, equipment parameters and fluid dynamics mechanism of the actual steam pipeline network, which can accurately map the real-time state of the system and simulate its future behavior. In this invention, it is specifically used for safety testing and consequence prediction before the execution of control commands.

[0025] In this embodiment, the collaborative control center refers to the central processing and control unit that receives steam usage requests and system status information from each steam-consuming device's intelligent agent, executes a multi-agent collaborative decision-making algorithm, and finally issues steam flow distribution instructions verified by a digital twin model to each device.

[0026] The beneficial effects of the above technical solution are as follows: By introducing soft measurement technology that integrates data and mechanisms, and replacing expensive hardware with algorithms, low-cost, high-precision real-time monitoring of steam dryness is achieved, effectively overcoming the measurement deviation caused by pipeline heat dissipation in traditional ideal formulas. Secondly, through a multi-agent collaborative decision-making mechanism, the steam demand of multiple steam-using equipment can be dynamically coordinated to achieve peak shaving and valley filling, ensuring temperature stability. Finally, by constructing a digital twin model of the pipeline network as a safety verification sandbox before the issuance of control commands, risks such as water hammer and pressure oscillation can be simulated and predicted in advance, realizing a leap from passive response to proactive safety pre-control, significantly improving the safety and reliability of system operation, and realizing an intelligent closed loop of perception, decision-making, and safety verification. This provides an economical, accurate, stable, and safe overall solution for low-temperature steam heating systems. In addition, by introducing a heat pump integrated heating module, efficient recovery and reuse of low-grade industrial waste heat is achieved, converting it into high-quality medium- and low-pressure steam, significantly reducing the system's dependence on primary energy and carbon emissions.

[0027] Example 2: Based on Example 1, this example provides an intelligent low-temperature steam heating system that utilizes digital twin collaborative control, such as... Figure 2 As shown, the data acquisition module includes: The instruction issuing unit is used to obtain the communication addresses of the temperature and pressure sensors pre-installed on the inlet steam pipes of each steam-using equipment in the steam network and the ambient temperature sensor pre-installed in the environment where each steam-using equipment is located, and to send data acquisition instructions to the temperature sensor, pressure sensor and ambient temperature sensor at regular intervals based on the communication addresses of the management terminal. The data acquisition unit is used for: Based on the transmission results, the control temperature sensor collects the analog signal of the inlet steam temperature and the control pressure sensor collects the analog signal of the inlet steam pressure. At the same time, the control ambient temperature sensor collects the analog signal of the ambient temperature of the steam-using equipment. Based on a preset analog-to-digital converter, the temperature analog signal, pressure analog signal, and ambient temperature analog signal are converted into digital signals, and the obtained digital signals are packaged according to the time period to obtain the data frame corresponding to each period. The data backhaul unit is used to transmit the obtained data frames back to the data processing center based on a preset wireless communication network.

[0028] In this embodiment, the instruction issuing unit refers to the functional unit responsible for storing the communication addresses of each sensor and sending data acquisition start instructions to the corresponding sensor according to the time period set by the management terminal.

[0029] In this embodiment, the data acquisition unit refers to the functional unit that receives analog signals returned by sensors, performs preprocessing operations such as analog-to-digital conversion and data packaging, and transmits the processed data frames to the next stage. The preset analog-to-digital converter is pre-configured.

[0030] In this embodiment, the data return unit refers to the functional unit that receives the packaged data frames and sends them to the remote data processing center through a preset wireless communication network.

[0031] The beneficial effects of the above technical solution are as follows: by issuing instructions on demand and at regular intervals, it achieves accurate, automatic and synchronous acquisition of data from multiple devices and multiple types of sensors, avoiding data redundancy and communication conflicts. By converting analog signals into standardized digital signals and packaging them into data frames, it ensures the integrity and consistency of the original data, providing a reliable, real-time and uniformly formatted data foundation for subsequent steam dryness soft measurement and collaborative decision-making, thereby ensuring the efficient and stable operation of the entire intelligent control system.

[0032] Example 3: Based on Example 1, this example provides an intelligent low-temperature steam heating system using digital twin collaborative control, including a data analysis module: The data retrieval unit is used to retrieve the inlet steam temperature, inlet steam pressure and ambient temperature data of each steam-consuming equipment, and input the retrieved inlet steam temperature, inlet steam pressure and ambient temperature data of each steam-consuming equipment as input parameters to the pre-trained pipeline heat loss correction neural network model. Data analysis unit, used for: Based on the pre-trained pipeline heat loss correction neural network model, the enthalpy values ​​of saturated steam and saturated water at the corresponding pressure are determined according to the inlet steam temperature and inlet steam pressure, and the total enthalpy value of wet steam is determined according to the inlet steam temperature and inlet steam pressure. Based on ambient temperature data and the preset thermal conductivity coefficient of the steam pipeline network, the heat loss per unit length during the process of steam being transported from the main pipeline network to the inlet of each steam-using equipment is determined, and the heat loss per unit length is calculated based on the pipeline length data to determine the cumulative heat loss value. Meanwhile, the total enthalpy of wet steam is corrected based on the cumulative heat loss value to obtain the total enthalpy of standard wet steam. Based on the preset dryness analysis strategy, the total enthalpy of standard wet steam is analyzed with the enthalpy of saturated steam and saturated water at the corresponding pressure to obtain the steam dryness corresponding to each steam-using equipment.

[0033] In this embodiment, the preset pipe thermal conductivity coefficient refers to a physical parameter that is pre-set based on the material of the steam pipe, the material and thickness of the insulation layer, and is used to quantify the heat dissipation capacity per unit length of pipe.

[0034] In this embodiment, the heat loss per unit length refers to the amount of heat lost per meter of pipe to the environment per unit time, calculated based on the ambient temperature and the pipe's thermal conductivity.

[0035] In this embodiment, the cumulative heat loss value refers to the total heat dissipation obtained by summing the heat loss per unit length based on the actual pipe length from the main pipeline to the inlet of the steam-using equipment.

[0036] In this embodiment, the standard total enthalpy of wet steam refers to the wet steam enthalpy value that is closer to the true physical state after the cumulative heat loss value is added to the initial total enthalpy of wet steam as a correction.

[0037] In this embodiment, the preset dryness analysis strategy refers to a standardized algorithm process that calculates and outputs the steam dryness based on the corrected total enthalpy of wet steam, the enthalpy of saturated steam, and the enthalpy of saturated water, according to the thermodynamic dryness definition formula.

[0038] The beneficial effects of the above technical solution are: by combining environmental factors and pipeline physical parameters to accurately correct the total enthalpy of wet steam, and by performing dryness analysis based on the corrected enthalpy, the accuracy of steam dryness calculation is significantly improved, providing high-precision real-time data support for subsequent coordinated control, thereby ensuring the rationality of system load distribution and the stability of process control.

[0039] Example 4: Based on Example 3, this example provides an intelligent low-temperature steam heating system using digital twin collaborative control, including a data analysis unit: The data correction subunit is used to obtain the total enthalpy and cumulative heat loss of the obtained wet steam, and adds the cumulative heat loss value to the total enthalpy of the wet steam after defining the cumulative heat loss value as a negative value, so as to obtain the standard total enthalpy of the wet steam. The steam dryness determination subunit is used for: Obtain the saturated steam enthalpy and saturated water enthalpy corresponding to the inlet steam pressure of each steam-using equipment, and determine the first difference between the total enthalpy of standard wet steam and the saturated water enthalpy. At the same time, determine the second difference between the saturated steam enthalpy and the saturated water enthalpy. Determine the ratio of the first difference to the second difference, and obtain the steam dryness corresponding to each steam-using equipment based on the ratio result.

[0040] In this embodiment, the ratio refers to the quotient obtained by dividing the first difference between the total enthalpy of standard wet steam and the enthalpy of saturated water by the second difference between the enthalpy of saturated steam and the enthalpy of saturated water.

[0041] In this embodiment, the ratio result refers to using the calculated ratio as the final value of the steam dryness of the steam-using equipment under the current operating conditions.

[0042] The beneficial effects of the above technical solution are as follows: by making clear algebraic corrections to the cumulative heat loss value and the total enthalpy value of wet steam, and by calculating the accurate ratio between the corrected enthalpy value and the enthalpy value of saturated state, the analytical accuracy of steam dryness is significantly improved, providing accurate and reliable input parameters for subsequent multi-equipment coordinated control, thereby ensuring the effectiveness of system load distribution decisions.

[0043] Example 5: Based on Example 1, this example provides an intelligent low-temperature steam heating system using digital twin collaborative control, including an instruction generation module comprising: The matching and judgment unit is used to match the steam dryness corresponding to each steam-consuming equipment with the real-time business requirements of each steam-consuming equipment, and to determine whether the current steam dryness meets the real-time business requirements of each steam-consuming equipment. Instruction determination unit, used for: If the current steam dryness does not meet the real-time business needs of the first steam-consuming equipment and the first steam-consuming equipment predicts that it needs to increase the steam flow, a steam consumption request is sent to the collaborative control center based on the multi-agent collaborative decision-making algorithm. Based on the steam demand request, the coordinated control center coordinates the second steam-consuming equipment, which is in the heat preservation stage and whose steam dryness meets the real-time business requirements, to temporarily suspend steam consumption. The steam demand request of the first steam-consuming equipment is matched with the temporary suspension response of the second steam-consuming equipment to determine the steam flow allocation instruction.

[0044] In this embodiment, the first steam-consuming equipment refers to the steam-consuming equipment whose current steam dryness does not meet the real-time business requirements and which needs to increase steam flow.

[0045] In this embodiment, the second steam-consuming equipment refers to the steam-consuming equipment that is in the heat preservation stage and whose steam dryness meets the real-time business requirements, and whose steam consumption can be temporarily suspended.

[0046] In this embodiment, the heat preservation stage refers to the stage after the steam-using equipment has completed heating, where it only needs to maintain the temperature and does not require a large supply of steam.

[0047] In this embodiment, steam dryness refers to the mass fraction of actual gaseous steam in wet steam, which is a key parameter characterizing steam quality and thermal state.

[0048] In this embodiment, real-time business demand refers to the actual demand of steam-using equipment for steam flow or heat under the current production process.

[0049] In this embodiment, a steam demand request refers to a request signal sent by a steam-consuming device to the coordinated control center to request an increase in steam allocation when the steam dryness is insufficient or the flow rate needs to be increased.

[0050] In this embodiment, the "temporary suspension of steam use response" refers to the response signal of a steam-using device in the heat preservation stage agreeing to temporarily reduce or stop steam use after receiving an inquiry from the coordinated control center.

[0051] In this embodiment, the steam flow distribution instruction refers to the specific instruction generated by the collaborative control center based on the multi-agent collaborative decision-making algorithm, which is used to control the valve opening of each steam-consuming equipment to distribute the steam flow.

[0052] The beneficial effects of the above technical solution are: through intelligent collaboration among multiple devices, when a certain device needs to increase steam, the device in the non-critical steam consumption stage is coordinated to temporarily suspend steam consumption, thereby achieving dynamic balance and peak shaving of the system load; effectively avoiding drastic fluctuations in pipeline pressure caused by multiple devices using steam at the same time, significantly improving the accuracy of steam distribution and the stability of system operation, ensuring the consistency of production processes and product yield, and reducing energy waste.

[0053] Example 6: Based on Example 5, this example provides an intelligent low-temperature steam heating system using digital twin collaborative control, including an instruction determination unit comprising: The intelligent agent determination subunit is used to virtualize each steam-consuming device in the steam pipeline network as an intelligent agent with autonomous request and response capabilities; The data generation subunit is used to generate steam demand data or steam delay response data for each steam-consuming equipment based on the corresponding steam dryness and real-time business needs of each intelligent agent. The sending subunit is used to send the generated steam consumption request data or steam consumption postponement response data to the collaborative control center based on each intelligent agent. The negotiation and arbitration subunit is used to conduct negotiation and arbitration in the collaborative control center based on the received steam use request data and steam use suspension response data, and according to the central control logic. The instruction generation and distribution subunit is used to generate steam flow distribution instructions based on the negotiation and arbitration results from the collaborative control center, and then distribute the instructions to the actuators corresponding to each steam-consuming equipment.

[0054] In this embodiment, an intelligent agent refers to virtualizing each steam-using device in the steam pipeline network into a logical unit with the ability to autonomously generate requests or responses and to interact with the collaborative control center.

[0055] In this embodiment, steam request data refers to standardized data containing information such as request flow rate sent by the intelligent agent to the collaborative control center when the current steam dryness of the steam application equipment does not meet the real-time business requirements.

[0056] In this embodiment, the delayed steam use response data refers to the feedback data generated by the intelligent agent corresponding to the steam-using equipment in the heat preservation stage, after receiving an inquiry from the collaborative control center, indicating whether to agree or refuse to delay steam use based on its own process constraints.

[0057] In this embodiment, the central control logic refers to the rules or algorithms pre-set within the collaborative control center for processing request and response data sent by all intelligent agents to achieve system-level coordinated decisions. For example, coordination is achieved based on a load balancing allocation algorithm, including: the collaborative control center summarizing the steam demand request data and steam postponement response data of all intelligent agents in real time, and calculating the difference between the current total steam supply capacity of the pipeline network and the total requested load. When the requested load exceeds the steam supply capacity, the central control logic identifies intelligent agents in the heat preservation stage and allowed to postpone steam use based on the operational stage data reported by each intelligent agent, and sends postponement queries to them; based on the number of returned agreed postponement responses, it recalculates the available steam supply capacity, and reallocates the available capacity to intelligent agents still in steam demand according to the principle of proportional allocation or the principle of priority on demand.

[0058] In this embodiment, the actuator refers to the terminal actuator installed on the inlet pipe of each steam-using equipment, which is used to receive steam flow distribution instructions and adjust the valve opening to control the actual steam flow.

[0059] The beneficial effects of the above technical solution are as follows: By virtualizing each steam-consuming device into an intelligent agent with autonomous interaction capabilities, a standardized request and response mechanism is established, and a central unit conducts unified negotiation and arbitration, achieving dynamic coordination and precise allocation of steam demand among multiple devices. This mechanism effectively avoids load conflicts and pipeline pressure fluctuations caused by simultaneous steam consumption by multiple devices at the system level, ensuring on-demand allocation and efficient utilization of steam resources, and significantly improving the system's adaptability and operational stability in the face of complex operating conditions.

[0060] Example 7: Based on Example 1, this example provides an intelligent low-temperature steam heating system using digital twin collaborative control. The collaborative control module includes: The model building unit is used to access the management terminal and obtain the physical topology, pipeline geometric parameters and fluid dynamic characteristics of the steam pipeline network based on the access results. It then constructs a digital twin model of the steam pipeline network in the computer based on the physical topology, pipeline geometric parameters and fluid dynamic characteristics. Simulation unit, used for: Acquire steam flow distribution instructions and real-time operating status data of the steam pipeline network at the current moment. The real-time operating status data includes the pressure and temperature of each node and the opening status of each steam regulating valve. Real-time operating status data is loaded into the digital twin model, and steam flow distribution commands are used as control inputs to be executed into the digital twin model based on the loading results; Transient simulations are performed in the digital twin model based on the input results, and the dynamic pressure response process of the steam pipeline network within a preset time window is determined based on the transient simulation results. Prediction unit, used for: Based on the pressure dynamic response process, the pressure change sequence data of each node within a preset time window is extracted, and a pressure change curve is generated based on the pressure change sequence data over time. Extract the slope change characteristics and pressure peak value of the pressure change curve, and compare the slope change characteristics and pressure peak value with the corresponding preset thresholds. Based on the comparison results, predict whether the pipeline pressure fluctuation exceeds the limit or water hammer risk will occur, and obtain the target prediction result. The coordinated control unit is used for: The target prediction results are matched with preset safety constraints, and the simulation is deemed to have passed when the target prediction results meet the preset safety constraints. Based on the judgment result, the steam flow distribution command is sent to the collaborative control center, and the collaborative control center performs collaborative control of the opening degree of the steam regulating valve at the inlet of each steam-using equipment according to the steam flow distribution command.

[0061] In this embodiment, transient simulation is performed in a digital twin model based on the input results, and the dynamic pressure response process of the steam pipeline network within a preset time window is determined based on the transient simulation results, including: In the digital twin model, the mass conservation equation, momentum conservation equation, and energy conservation equation of the compressible fluid in the steam pipeline network are defined as the governing equations for transient simulation calculations. The steam regulating valve opening adjustment amount and adjustment time corresponding to each steam-consuming equipment are parsed from the steam flow distribution command, and the steam regulating valve opening adjustment amount is converted into the flow coefficient of the corresponding valve as a function of time change, which is used as the boundary condition input of the control equation set. Set the start and end times of the preset time window for transient simulation calculation, and discretize the preset time window into multiple consecutive time steps, each time step corresponding to a simulation calculation cycle; Using real-time operating status data as initial values, within each time step, based on the control equations and boundary conditions, the pressure, flow rate, and temperature values ​​of each calculation node at the end of the current time step are solved using a numerical iteration method. The calculation result of the current time step is used as the initial value of the next time step, and the process is continued until the end of the time window. The sequence data of the pressure of each node changing with time within the entire time window is generated step by step. The pressure values ​​of each node at different times are extracted from the sequence data to obtain a dynamic pressure response dataset for subsequent prediction of pipeline pressure fluctuations and water hammer risks.

[0062] In this embodiment, the safety constraints include that the pressure at each node does not exceed the allowable upper limit, the pressure change rate does not exceed the allowable change rate threshold, and no water hammer characteristic waveform identification mark appears.

[0063] In this embodiment, the pressure dynamic response process refers to the dynamic response sequence of the pressure values ​​of each key node in the steam pipeline network changing over time within a preset time window.

[0064] In this embodiment, the slope change characteristic of the pressure change curve refers to the characteristic parameter that reflects the rate of pressure change and its abrupt change trend, obtained by differentiating the pressure change curve over time.

[0065] In this embodiment, the target prediction result refers to the judgment conclusion generated by the prediction unit based on the slope change characteristics of the pressure change curve and the comparison between the pressure peak and the preset threshold, regarding whether pressure fluctuation exceeds the limit or water hammer risk occurs.

[0066] In this embodiment, the preset safety constraints refer to a number of pre-set safety indicators used to determine whether the simulation passes, including that the pressure at each node does not exceed the allowable upper limit, the pressure change rate does not exceed the allowable change rate threshold, and no water hammer risk characteristics are identified.

[0067] In this embodiment, coordinated opening control refers to the coordinated control center performing unified and on-demand opening control operations on multiple steam regulating valves at the inlet of each steam-using equipment according to the steam flow distribution command.

[0068] In this embodiment, to ensure the real-time performance of transient simulation and meet the millisecond or second-level verification requirements before the control command is issued, a reduced-order model or surrogate model is used to accelerate the digital twin model. For example, the detailed mechanism model based on three-dimensional computational fluid dynamics is converted into a low-dimensional fast solution algorithm through methods such as intrinsic orthogonal decomposition, or the input-output relationship of the transient simulation is approximated by offline training of a neural network surrogate model, thereby performing high-speed inference in online control, and thus completing the advanced simulation and verification of risks such as water hammer and pressure oscillation in a very short time.

[0069] The beneficial effects of the above technical solution are as follows: by constructing a digital twin model that is synchronously mapped with the physical pipeline network, and performing transient simulation and risk prediction before the execution of control commands, the pre-identification and proactive avoidance of pipeline pressure fluctuations and water hammer risks are realized. Secondly, by issuing commands after matching the prediction results with safety constraints, the safety and feasibility of collaborative control decisions are ensured, thereby ensuring the stability and safety of steam pipeline network operation while realizing the dynamic allocation of loads of multiple devices.

[0070] Example 8: Based on Example 7, this example provides an intelligent low-temperature steam heating system using digital twin collaborative control, including a prediction unit comprising: The prediction subunit is used to retrieve the preset pipeline resistance coefficient and thermal conductivity coefficient in the steam pipeline network based on the management terminal, and determine the pressure change rate and velocity change rate of the fluid in the pipeline during the steam flow redistribution process in combination with the steam flow distribution command. Determine the subunit, used for: The obtained pressure change rate and flow velocity change rate are compared with the corresponding preset pressure change threshold and preset flow velocity change threshold, respectively. If the rate of pressure change exceeds the preset pressure change threshold or the rate of flow rate change exceeds the preset flow rate change threshold, then a risk of water hammer is identified.

[0071] In this embodiment, the pressure change rate refers to the change in fluid pressure within the pipeline per unit time during the steam flow redistribution process.

[0072] In this embodiment, the rate of change of flow velocity refers to the change in the fluid velocity within the pipe per unit time during the steam flow redistribution process.

[0073] The beneficial effects of the above technical solution are: by introducing the pipeline resistance coefficient and thermal conductivity coefficient, and combining the flow distribution command to directly calculate the rate of change of fluid pressure and flow velocity, and comparing it with the preset threshold, the quantitative judgment of water hammer risk is realized, which significantly improves the accuracy of risk identification and response speed, and provides a precise early warning mechanism for the safe operation of the pipeline network.

[0074] Example 9: Based on Example 1, this example provides an intelligent low-temperature steam heating system using digital twin collaborative control. In the data analysis module, the pre-trained pipeline heat loss correction neural network model is an adaptive control algorithm model based on deep reinforcement learning, which is used to optimize the low-temperature steam generation process in real time.

[0075] In this embodiment, deep reinforcement learning refers to an artificial intelligence algorithm that combines deep learning with reinforcement learning. Through the interaction between the agent and the environment, it learns the mapping from a high-dimensional state space to the optimal action in order to maximize the cumulative reward. In this embodiment, it is used to dynamically learn and optimize the control strategy in the low-temperature steam generation process.

[0076] In this embodiment, the specific reinforcement learning elements of the adaptive control algorithm model based on deep reinforcement learning are further defined: To guide the agent in learning the optimal control strategy, a reward function needs to be defined to quantify the impact of each control action on system performance. The calculation of the reward function depends on the changes in the system state before and after the action is executed; therefore, it is necessary to construct a state space that comprehensively reflects the system's operating conditions and an action space that the agent can execute. Specifically: The state space S consists of key parameters acquired from the data acquisition module and derived from the data analysis module at time t, including the steam pressure P_i,t, steam temperature T_i,t, ambient temperature T_env,i,t at the inlet of each steam-consuming equipment, and the steam dryness fraction X_i,t calculated after correction for pipeline heat loss, where i represents the i-th steam-consuming equipment. In addition, to reflect the dynamic trend of the system, the state space also includes the historical value sequence of the above parameters over the past N time steps. Action space A is defined as the control instructions that the agent can execute at time t, including the opening adjustment amount ΔV_i,t of the steam regulating valve at the inlet of each steam-using equipment. This adjustment amount is either a continuous value or a discrete level, and is limited by the maximum and minimum opening range allowed by the valve's physical properties and the single-step adjustment range limit. The reward function R_t is designed as an immediate reward to evaluate the effect of the system state transition to S_{t+1} after taking action A_t in state S_t. The calculation method is based on a weighted combination of multiple objectives, including the negative values ​​of the deviation of steam dryness of all steam-using equipment from the set target value, the negative values ​​of the pressure fluctuation amplitude of the main pipeline, and the negative values ​​of the rate of change of total steam flow. At the same time, a penalty term for exceeding the safety threshold (such as pressure exceeding the limit, water hammer risk indicator) is introduced, thereby guiding the agent to achieve accurate tracking of steam dryness and stable control of pipeline pressure under the premise of meeting safety constraints.

[0077] The beneficial effects of the above technical solution are: by endowing the model with self-learning ability through deep reinforcement learning, it can dynamically adapt to fluctuations in operating conditions, optimize the steam generation control strategy online, thereby significantly improving the control accuracy of steam dryness and system energy efficiency, and ensuring stable operation under complex operating conditions.

[0078] Example 10: Based on Example 1, this example provides an intelligent low-temperature steam heating system that applies digital twin collaborative control, and also includes: a heat pump integrated heating module; The integrated heat pump heating module is connected to the collaborative control center. The integrated heat pump heating module includes a multi-stage heat pump and a steam accumulator. The input end of the multi-stage heat pump is used to connect to industrial waste heat; The output end of the multi-stage heat pump is connected to the inlet of the steam accumulator. The outlet of the steam accumulator is connected to the inlet of the steam pipeline network; The multi-stage heat pump is used to gradually raise industrial waste heat to the temperature required to generate medium- and low-pressure steam and store the steam in the steam accumulator. The steam accumulator is used to release the stored steam when the steam network needs it.

[0079] The working principle of the above technical solution is as follows: the integrated heat pump heating module serves as a supplementary heat source for the system. First, the multi-stage heat pump, driven by electricity, recovers low-grade heat energy from industrial waste heat sources (such as cooling circulating water and waste flue gas). Through multi-stage series compression or absorption heat pump circulation, the temperature of the heat energy is gradually increased until it reaches the temperature that can generate medium and low-pressure steam. Second, the generated medium and low-pressure steam is transported to a steam accumulator for storage, utilizing the sensible heat of water or phase change materials to store the heat energy. When the steam-consuming equipment in the steam pipeline enters the peak steam consumption period or the main heat source supply is insufficient, the coordination control center sends a release command to the steam accumulator, which quickly releases the stored steam to the pipeline inlet to supplement the steam required by the system. Finally, when steam consumption is at a low point or industrial waste heat is sufficient, the excess heat energy continues to be stored in the accumulator in the form of steam, achieving peak shaving and valley filling.

[0080] The beneficial effects of the above technical solution are as follows: by introducing a multi-stage heat pump, the originally waste industrial heat is converted into high-value low-pressure steam, which significantly reduces the system's dependence on primary energy sources (such as natural gas and coal), and greatly reduces carbon emissions and operating costs; at the same time, the setting of steam accumulators effectively solves the problem of discontinuous and fluctuating industrial waste heat supply, converting intermittent heat energy into a stable and controllable steam source, and improving the reliability and anti-fluctuation capability of the system's steam supply; in addition, the digital twin model and the collaborative control center can control the start-up and shutdown of the heat pump and the charging and discharging strategy of the accumulator in advance according to the pipeline load forecast, further optimizing the overall energy efficiency and realizing low-carbon and intelligent steam supply.

[0081] Example 11: This example provides an intelligent low-temperature steam heating equipment using digital twin collaborative control, comprising: An industrial waste heat recovery and temperature raising subsystem includes a multi-stage heat pump for receiving industrial waste heat and a steam accumulator connected to the output of the multi-stage heat pump. A steam transmission and distribution network, with its inlet connected to the outlet of a steam accumulator, is used to transport steam to multiple steam-consuming devices; Multiple steam-consuming equipment execution terminals are installed on the inlet pipes of each steam-consuming equipment, including steam regulating valves, temperature sensors, pressure sensors, and ambient temperature sensors for collecting ambient temperature. The integrated control unit communicates with multi-stage heat pumps, steam accumulators, steam regulating valves, and various sensors. It contains a digital twin model of the steam piping network and is configured to perform the following operations: Collect steam temperature, pressure, and ambient temperature data at the inlet of each steam-using equipment; The cumulative heat loss value is determined based on ambient temperature data and the preset thermal conductivity coefficient of the pipeline in the steam pipeline network. The total enthalpy of wet steam determined based on inlet steam temperature and pressure is corrected based on the cumulative heat loss value to obtain the standard total enthalpy of wet steam. Based on the standard total enthalpy of wet steam and the enthalpy of saturated steam and saturated water at the corresponding pressure, the steam dryness of each steam-using equipment is determined. The steam dryness is matched with the real-time business requirements of each steam-consuming equipment, and the matching results are used to make collaborative decisions based on a multi-agent collaborative decision-making algorithm to determine the steam flow allocation instructions. The steam flow distribution command is input into the digital twin model for operation simulation to predict pipeline pressure fluctuations and water hammer risks. After the operation simulation is passed, the opening degree of the steam regulating valve at the inlet of each steam-using equipment is coordinated and controlled according to the steam flow distribution command.

[0082] Example 12: Based on any one of Examples 1 to 11, this example provides a degradation control strategy for dealing with communication anomalies, including: When the coordinated control center detects that a steam-consuming equipment's intelligent agent is unable to transmit data due to a wireless network failure, the local controller of the steam-consuming equipment will activate an independent heat preservation mode based on historical data. Specifically: The local controller retrieves historical data and trends of steam dryness within a preset time period from the steam-using equipment. Combined with the equipment's own process insulation requirements, it conservatively controls the opening of the inlet steam regulating valve to maintain basic insulation requirements until communication is restored.

[0083] The above strategy ensures that the system can still maintain basic safe operation in the event of local communication failures, avoiding equipment shutdowns or process accidents caused by missing control commands.

[0084] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0085] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An intelligent low-temperature steam heating system employing digital twin collaborative control, characterized in that, include: The data acquisition module is used to collect inlet steam temperature, pressure, and ambient temperature data of various steam-using equipment in the steam pipeline network; The data analysis module is used to determine the cumulative heat loss value based on ambient temperature data and the preset thermal conductivity coefficient of the pipeline in the steam pipeline network, and to correct the total enthalpy value of wet steam determined according to the inlet steam temperature and pressure based on the cumulative heat loss value to obtain the standard total enthalpy value of wet steam. Based on the standard total enthalpy value of wet steam and the enthalpy values ​​of saturated steam and saturated water at the corresponding pressure, the steam dryness corresponding to each steam-using equipment is determined. The instruction generation module is used to match the steam dryness with the real-time business needs of each steam-consuming equipment, and to make collaborative decisions on the matching results based on a multi-agent collaborative decision-making algorithm to determine the steam flow allocation instruction. The collaborative control module is used to simulate the operation of steam flow distribution commands based on the digital twin model constructed on the steam pipeline network, predict pipeline pressure fluctuations and water hammer risks, and send the steam flow distribution commands to the collaborative control center for collaborative steam flow distribution after the operation simulation is passed.

2. The intelligent low-temperature steam heating system using digital twin collaborative control as described in claim 1, characterized in that, The data acquisition module includes: The instruction issuing unit is used to obtain the communication addresses of the temperature and pressure sensors pre-installed on the inlet steam pipes of each steam-using equipment in the steam network and the ambient temperature sensor pre-installed in the environment where each steam-using equipment is located, and to send data acquisition instructions to the temperature sensor, pressure sensor and ambient temperature sensor at regular intervals based on the communication addresses of the management terminal. The data acquisition unit is used for: Based on the transmission results, the control temperature sensor collects the analog signal of the inlet steam temperature and the control pressure sensor collects the analog signal of the inlet steam pressure. At the same time, the control ambient temperature sensor collects the analog signal of the ambient temperature of the steam-using equipment. Based on a preset analog-to-digital converter, the temperature analog signal, pressure analog signal, and ambient temperature analog signal are converted into digital signals, and the obtained digital signals are packaged according to the time period to obtain the data frame corresponding to each period. The data backhaul unit is used to transmit the obtained data frames back to the data processing center based on a preset wireless communication network.

3. The intelligent low-temperature steam heating system using digital twin collaborative control according to claim 1, characterized in that, The data analysis module includes: The data retrieval unit is used to retrieve the inlet steam temperature, inlet steam pressure and ambient temperature data of each steam-consuming equipment, and input the retrieved inlet steam temperature, inlet steam pressure and ambient temperature data of each steam-consuming equipment as input parameters to the pre-trained pipeline heat loss correction neural network model. Data analysis unit, used for: Based on the pre-trained pipeline heat loss correction neural network model, the enthalpy values ​​of saturated steam and saturated water at the corresponding pressure are determined according to the inlet steam temperature and inlet steam pressure, and the total enthalpy value of wet steam is determined according to the inlet steam temperature and inlet steam pressure. Based on ambient temperature data and the preset thermal conductivity coefficient of the steam pipeline network, the heat loss per unit length during the process of steam being transported from the main pipeline network to the inlet of each steam-using equipment is determined, and the heat loss per unit length is calculated based on the pipeline length data to determine the cumulative heat loss value. Meanwhile, the total enthalpy of wet steam is corrected based on the cumulative heat loss value to obtain the total enthalpy of standard wet steam. Based on the preset dryness analysis strategy, the total enthalpy of standard wet steam is analyzed with the enthalpy of saturated steam and saturated water at the corresponding pressure to obtain the steam dryness corresponding to each steam-using equipment.

4. The intelligent low-temperature steam heating system using digital twin collaborative control according to claim 3, characterized in that, The data analysis unit includes: The data correction subunit is used to obtain the total enthalpy and cumulative heat loss of the obtained wet steam, and adds the cumulative heat loss value to the total enthalpy of the wet steam after defining the cumulative heat loss value as a negative value, so as to obtain the standard total enthalpy of the wet steam. The steam dryness determination subunit is used for: Obtain the saturated steam enthalpy and saturated water enthalpy corresponding to the inlet steam pressure of each steam-using equipment, and determine the first difference between the total enthalpy of standard wet steam and the saturated water enthalpy. At the same time, determine the second difference between the saturated steam enthalpy and the saturated water enthalpy. Determine the ratio of the first difference to the second difference, and obtain the steam dryness corresponding to each steam-using equipment based on the ratio result.

5. The intelligent low-temperature steam heating system using digital twin collaborative control according to claim 1, characterized in that, The instruction generation module includes: The matching and judgment unit is used to match the steam dryness corresponding to each steam-consuming equipment with the real-time business requirements of each steam-consuming equipment, and to determine whether the current steam dryness meets the real-time business requirements of each steam-consuming equipment. Instruction determination unit, used for: If the current steam dryness does not meet the real-time business needs of the first steam-consuming equipment and the first steam-consuming equipment predicts that it needs to increase the steam flow, a steam consumption request is sent to the collaborative control center based on the multi-agent collaborative decision-making algorithm. Based on the steam demand request, the coordinated control center coordinates the second steam-consuming equipment, which is in the heat preservation stage and whose steam dryness meets the real-time business requirements, to temporarily suspend steam consumption. The steam demand request of the first steam-consuming equipment is matched with the temporary suspension response of the second steam-consuming equipment to determine the steam flow allocation instruction.

6. The intelligent low-temperature steam heating system using digital twin collaborative control according to claim 5, characterized in that, The instruction determination unit includes: The intelligent agent determination subunit is used to virtualize each steam-consuming device in the steam pipeline network as an intelligent agent with autonomous request and response capabilities; The data generation subunit is used to generate steam demand data or steam delay response data for each steam-consuming equipment based on the corresponding steam dryness and real-time business needs of each intelligent agent. The sending subunit is used to send the generated steam consumption request data or steam consumption postponement response data to the collaborative control center based on each intelligent agent. The negotiation and arbitration subunit is used to conduct negotiation and arbitration in the collaborative control center based on the received steam use request data and steam use suspension response data, and according to the central control logic. The instruction generation and distribution subunit is used to generate steam flow distribution instructions based on the negotiation and arbitration results from the collaborative control center, and then distribute the instructions to the actuators corresponding to each steam-consuming equipment.

7. The intelligent low-temperature steam heating system using digital twin collaborative control according to claim 1, characterized in that, The coordinated control module includes: The model building unit is used to access the management terminal and obtain the physical topology, pipeline geometric parameters and fluid dynamic characteristics of the steam pipeline network based on the access results. It then constructs a digital twin model of the steam pipeline network in the computer based on the physical topology, pipeline geometric parameters and fluid dynamic characteristics. Simulation unit, used for: Acquire steam flow distribution instructions and real-time operating status data of the steam pipeline network at the current moment. The real-time operating status data includes the pressure and temperature of each node and the opening status of each steam regulating valve. Real-time operating status data is loaded into the digital twin model, and steam flow distribution commands are used as control inputs to be executed into the digital twin model based on the loading results; Transient simulations are performed in the digital twin model based on the input results, and the dynamic pressure response process of the steam pipeline network within a preset time window is determined based on the transient simulation results. Prediction unit, used for: Based on the pressure dynamic response process, the pressure change sequence data of each node within a preset time window is extracted, and a pressure change curve is generated based on the pressure change sequence data over time. Extract the slope change characteristics and pressure peak value of the pressure change curve, and compare the slope change characteristics and pressure peak value with the corresponding preset thresholds. Based on the comparison results, predict whether the pipeline pressure fluctuation exceeds the limit or water hammer risk occurs, and obtain the target prediction result. The coordinated control unit is used for: The target prediction results are matched with preset safety constraints, and the simulation is deemed to have passed when the target prediction results meet the preset safety constraints. Based on the judgment result, the steam flow distribution command is sent to the collaborative control center, and the collaborative control center performs collaborative control of the opening degree of the steam regulating valve at the inlet of each steam-using equipment according to the steam flow distribution command.

8. The intelligent low-temperature steam heating system using digital twin collaborative control according to claim 7, characterized in that, Prediction unit, including: The prediction subunit is used to retrieve the preset pipeline resistance coefficient and thermal conductivity coefficient in the steam pipeline network based on the management terminal, and determine the pressure change rate and velocity change rate of the fluid in the pipeline during the steam flow redistribution process in combination with the steam flow distribution command. Determine the subunit, used for: The obtained pressure change rate and flow velocity change rate are compared with the corresponding preset pressure change threshold and preset flow velocity change threshold, respectively. If the rate of pressure change exceeds the preset pressure change threshold or the rate of flow rate change exceeds the preset flow rate change threshold, then a risk of water hammer is identified.

9. The intelligent low-temperature steam heating system using digital twin collaborative control according to claim 1, characterized in that, In the data analysis module, the pre-trained pipeline heat loss correction neural network model is an adaptive control algorithm model based on deep reinforcement learning, used to optimize the low-temperature steam generation process in real time.

10. The intelligent low-temperature steam heating system using digital twin collaborative control according to claim 1, characterized in that, Also includes: Heat pump integrated heating module; The integrated heat pump heating module includes: a multi-stage heat pump and a steam accumulator; The input end of the multi-stage heat pump is used to connect to industrial waste heat; The output end of the multi-stage heat pump is connected to the inlet of the steam accumulator. The outlet of the steam accumulator is connected to the inlet of the steam pipeline network; The multi-stage heat pump is used to gradually raise industrial waste heat to the temperature required to generate medium- and low-pressure steam and store the steam in the steam accumulator. The steam accumulator is used to release the stored steam when the steam network needs it.

11. An intelligent low-temperature steam heating equipment employing digital twin collaborative control, characterized in that, include: An industrial waste heat recovery and temperature raising subsystem includes a multi-stage heat pump for receiving industrial waste heat and a steam accumulator connected to the output of the multi-stage heat pump. A steam transmission and distribution network, with its inlet connected to the outlet of a steam accumulator, is used to transport steam to multiple steam-consuming devices; Multiple steam-consuming equipment execution terminals are installed on the inlet pipes of each steam-consuming equipment, including steam regulating valves, temperature sensors, pressure sensors, and ambient temperature sensors for collecting ambient temperature. The integrated control unit communicates with multi-stage heat pumps, steam accumulators, steam regulating valves, and various sensors. It contains a digital twin model of the steam piping network and is configured to perform the following operations: Collect steam temperature, pressure, and ambient temperature data at the inlet of each steam-using equipment; The cumulative heat loss value is determined based on ambient temperature data and the preset thermal conductivity coefficient of the pipeline in the steam pipeline network. The total enthalpy of wet steam determined based on inlet steam temperature and pressure is corrected based on the cumulative heat loss value to obtain the standard total enthalpy of wet steam. Based on the standard total enthalpy of wet steam and the enthalpy of saturated steam and saturated water at the corresponding pressure, the steam dryness of each steam-using equipment is determined. The steam dryness is matched with the real-time business requirements of each steam-consuming equipment, and the matching results are used to make collaborative decisions based on a multi-agent collaborative decision-making algorithm to determine the steam flow allocation instructions. The steam flow distribution command is input into the digital twin model for operation simulation to predict pipeline pressure fluctuations and water hammer risks. After the operation simulation is passed, the opening degree of the steam regulating valve at the inlet of each steam-using equipment is coordinated and controlled according to the steam flow distribution command.

Images