Tunnel energy operation scheduling method and system based on digital twinning, terminal and medium

Abstract

The invention belongs to the technical field of energy scheduling, and particularly discloses a tunnel energy operation scheduling method and system based on digital twinning, a terminal and a medium. Comprising the following steps: obtaining structure parameters of energy operation in a tunnel, energy use object distribution information and operation constraint conditions, and constructing a digital twinborn model; energy operation data and environment sensing data in the actual operation process of the tunnel are collected and mapped to corresponding state parameters in the digital twinborn model; generating at least one group of energy operation scheduling strategies based on the synchronized digital twin model state on the premise of meeting the tunnel safe operation constraint; and inputting the energy operation scheduling strategy into the digital twin model for simulation operation, predicting influence results of different scheduling strategies on the tunnel energy consumption level and the operation safety index, and determining a target energy operation scheduling strategy based on the simulation results. A digital twin model participates in an energy operation scheduling decision process, and simulation prediction and evaluation of tunnel energy operation scheduling are realized.

Description

Technical Field

[0001] This invention belongs to the field of energy dispatching technology, specifically relating to a tunnel energy operation dispatching method, system, terminal, and medium based on digital twins. Background Technology

[0002] With the rapid development of urban underground transportation infrastructure, the scale of facilities such as highway tunnels, urban tunnels, and integrated utility tunnels is constantly expanding. During long-term operation, tunnels need to continuously provide energy support for multiple energy-consuming components such as lighting, ventilation, drainage, and safety. Their energy operation status is directly related to the tunnel's operational safety, traffic efficiency, and operation and maintenance cost control.

[0003] Existing tunnel energy operation and management technologies are mostly based on rule-based control or experience-based thresholds, adjusting lighting brightness, ventilation intensity, and other parameters according to environmental parameters or operating conditions. Some technical solutions introduce simulation models or data analysis methods to predict or evaluate the tunnel's operating status.

[0004] However, the relevant models often deviate from the actual operation process, and model updates rely on human intervention, making it difficult to maintain high prediction accuracy under complex operating conditions and dynamic changes. In addition, in the process of energy operation and scheduling, existing technologies usually focus on the optimization of a single moment or a single indicator, lacking a comprehensive evaluation of the continuous evolution of scheduling strategies over time, resulting in limited adaptability of scheduling decisions to operational disturbances and emergencies. Summary of the Invention

[0005] This invention addresses the problems in the prior art by providing a method, system, terminal, and medium for tunnel energy operation scheduling based on digital twins. It solves the problem that model updates rely on manual intervention and are difficult to maintain high prediction accuracy under complex operating conditions and dynamic changes. At the same time, it solves the problem that the prior art usually focuses on the optimization of a single moment or a single indicator, lacks a comprehensive evaluation of the continuous evolution of the scheduling strategy in the time dimension, resulting in limited adaptability of scheduling decisions to operational disturbances and emergencies.

[0006] The technical solution adopted in this invention is as follows: Firstly, this application provides a tunnel energy operation scheduling method based on digital twins, which includes the following steps: Step S1: Obtain the structural parameters of energy operation in the tunnel, the distribution information of energy-consuming objects, and the operating constraints. Based on the structural parameters, the distribution information of energy-consuming objects, and the operating constraints, construct a digital twin model to characterize the energy operation status of the tunnel. Step S2: Collect energy operation data and environmental perception data of the tunnel during actual operation, and map the energy operation data and environmental perception data to the corresponding state parameters in the digital twin model; Step S3: Under the premise of meeting the tunnel safety operation constraints, generate at least one set of energy operation scheduling strategies based on the synchronized digital twin model state. The energy operation scheduling strategies are used to describe the energy allocation method, operation mode or scheduling sequence of the tunnel within a preset time range. Step S4: Input the energy operation and scheduling strategy into the digital twin model for simulation, predict the impact of the energy operation and scheduling strategy on the tunnel energy consumption level and operation safety indicators, and determine the target energy operation and scheduling strategy based on the impact results.

[0007] Furthermore, the process of mapping energy operation data and environmental sensing data to the corresponding state parameters in the digital twin model includes: The collected energy operation data and environmental sensing data are time-aligned to form a synchronous dataset on a unified time scale. Based on the pre-established state parameter mapping relationship, various types of data in the synchronous dataset are associated with the energy consumption state parameters, environmental state parameters, and operational constraint parameters in the digital twin model, thereby completing the state mapping of the actual tunnel operation state in the digital twin model.

[0008] Furthermore, the process of generating at least one set of energy operation scheduling strategies based on the synchronized digital twin model state includes: Adjustable operational variables corresponding to tunnel lighting, ventilation and drainage are set as decision variables, and safe operation constraints, equipment operation boundary constraints and energy consumption constraints are set as constraint conditions. Based on the prediction results of energy consumption and safety indicators in the preset prediction time domain by the digital twin model, a multi-objective optimization problem is constructed with the goal of minimizing energy consumption and maximizing safety satisfaction. A rolling time-domain model prediction solution mechanism is adopted to solve the multi-objective optimization problem in each scheduling cycle to generate a set of candidate energy operation scheduling strategies, and output at least one set of energy operation scheduling strategies from the set of candidate energy operation scheduling strategies.

[0009] Furthermore, the simulation and evaluation steps for scheduling strategies based on digital twins include: For each set of energy operation scheduling strategies, a corresponding scheduling execution sequence is constructed in the digital twin model. The scheduling execution sequence is simulated and deduced in multiple time steps within the preset prediction time domain to obtain the energy consumption state evolution sequence and the operation safety state evolution sequence of the energy operation scheduling strategy at different time nodes. Based on the energy consumption state evolution sequence and the operation safety state evolution sequence, the cumulative energy consumption index, energy consumption fluctuation index and safety risk accumulation index of each energy operation scheduling strategy in the prediction time domain are calculated. Based on the preset multi-indicator decision-making rules, the cumulative energy consumption index, energy consumption fluctuation index and safety risk accumulation index are normalized and weighted to form a comprehensive scheduling evaluation value corresponding to each energy operation scheduling strategy. Under the premise of meeting the constraints of safe operation, the target energy operation and scheduling strategy is determined based on the comprehensive scheduling evaluation value.

[0010] Furthermore, based on the discrepancy between historical operational data and current synchronized energy operational data, the process of assessing the consistency between the digital twin model's state and the tunnel's actual operational state includes: Within a preset time window, the predicted value sequence of the corresponding state parameters in the digital twin model and the measured value sequence corresponding to the actual operating state of the tunnel are obtained respectively. Based on the predicted and measured value sequences, the deviation metric of each state parameter within the time window is calculated. The deviation metric is determined as follows:

[0011] in, This represents the measured value of the i-th state parameter at time t. This represents the predicted value of the corresponding state parameter in the digital twin model at time t, where T represents the number of sampling points within the time window; Based on the deviation metric value corresponding to each state parameter The deviation metrics are weighted and aggregated according to preset weights to obtain the consistency evaluation value C between the digital twin model state and the actual tunnel operation state, where:

[0012] in, Let represent the consistency weight corresponding to the i-th state parameter, and satisfy . N represents the number of state parameters participating in the consensus assessment; When the consistency evaluation value C is less than the preset consistency threshold, it is determined that the consistency between the current digital twin model state and the actual tunnel operation state is insufficient, triggering the correction or reconstruction of the digital twin model state parameters.

[0013] Furthermore, after obtaining the consistency evaluation value C between the digital twin model state and the actual tunnel operating state, the following is also included: Based on the consistency evaluation value C, the weights of the state parameters involved in the generation and evaluation of energy operation scheduling strategies are dynamically corrected. Specifically, when the consistency evaluation value C is lower than the preset consistency threshold, the weight of the corresponding state parameter in the scheduling strategy evaluation process is reduced, and when the consistency evaluation value C is higher than the consistency threshold, the weight of the corresponding state parameter in the scheduling strategy evaluation process is increased. In the subsequent generation and simulation evaluation of energy operation scheduling strategies, the energy consumption and operation safety indicators of the scheduling strategy are recalculated and comprehensively evaluated based on the dynamically corrected state parameter weights.

[0014] Furthermore, based on the consistency evaluation value C, online parameter correction or partial reconstruction of the digital twin model is performed, specifically including: When the consistency evaluation value C is in the first preset range, it is determined that the overall structure of the digital twin model still meets the modeling assumptions. Online correction is performed on the model parameters related to energy consumption prediction or operation safety prediction in the digital twin model. The online correction includes incremental updates of the model parameters based on historical operation data and current synchronized energy operation data to reduce the deviation between the predicted value and the actual operation value of the digital twin model. When the consistency evaluation value C is in the second preset range below the first preset range, it is determined that the local modeling relationship of the digital twin model is inconsistent with the actual operating state of the tunnel. Local reconstruction is performed on the corresponding local state description or state evolution relationship in the digital twin model. The local reconstruction includes re-establishing the correlation between relevant state parameters or updating the corresponding state evolution rules. After completing online parameter correction or partial reconstruction, the generation and simulation evaluation process of energy operation scheduling strategy is re-executed based on the updated digital twin model.

[0015] Secondly, this application provides a tunnel energy operation scheduling system based on digital twins, used to implement the tunnel energy operation scheduling method based on digital twins as described in the first aspect. The system includes: The modeling module is configured to acquire structural parameters of energy operation within the tunnel, distribution information of energy-consuming objects, and operational constraints, and to construct a digital twin model to characterize the energy operation status of the tunnel based on the structural parameters, distribution information of energy-consuming objects, and operational constraints. The data synchronization module is configured to collect energy operation data and environmental perception data of the tunnel during actual operation, and map the energy operation data and environmental perception data to the corresponding state parameters in the digital twin model; The strategy generation module is configured to generate at least one set of energy operation scheduling strategies based on the synchronized digital twin model state, under the premise of meeting the tunnel safety operation constraints. The energy operation scheduling strategies are used to describe the energy allocation method, operation mode or scheduling sequence of the tunnel within a preset time range. The strategy evaluation module is configured to input the energy operation scheduling strategy into the digital twin model for simulation, predict the impact of the energy operation scheduling strategy on the tunnel energy consumption level and operation safety indicators, and determine the target energy operation scheduling strategy based on the impact results.

[0016] Thirdly, this application provides a terminal, including: A memory for storing tunnel energy operation scheduling programs based on digital twins; A processor is configured to implement the steps of the digital twin-based tunnel energy operation scheduling method as described in the first aspect when executing the digital twin-based tunnel energy operation scheduling device.

[0017] Fourthly, this application provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the tunnel energy operation scheduling method based on digital twins as described in the first aspect.

[0018] As can be seen from the above technical solutions, the advantages of the present invention are: By acquiring the structural parameters of tunnel energy operation, the distribution information of energy users, and the operational constraints, a digital twin model is constructed to characterize the tunnel energy operation status. The energy operation data and environmental perception data during the actual tunnel operation are mapped to the state parameters in the digital twin model, realizing the synchronous expression of the actual tunnel operation status and the virtual model status, so that subsequent energy operation scheduling decisions have a unified and computable state basis.

[0019] Based on the digital twin model, an energy operation scheduling strategy is generated. Under the premise of meeting the constraints of tunnel safety operation, the scheduling strategy is simulated and evaluated. This allows for the prediction of the impact of different scheduling strategies on tunnel energy consumption levels and operational safety indicators before scheduling is executed, avoiding reliance on empirical rules or single-moment data for scheduling decisions and improving the rationality of energy operation scheduling.

[0020] By performing multi-time-step simulations of the scheduling execution sequence in a digital twin model, and calculating multi-dimensional evaluation indicators such as cumulative energy consumption, energy consumption fluctuations, and safety risks based on the energy consumption state evolution sequence and the safety state evolution sequence, this application can systematically evaluate the comprehensive performance of energy operation scheduling strategies in the time dimension, enabling scheduling decisions to take into account the balance between energy consumption levels and operational safety.

[0021] By quantifying the deviation between the predicted state of the digital twin model and the actual operating state of the tunnel, a consistency evaluation value is constructed to objectively assess the consistency between the digital twin model state and the actual operating state. This avoids directly relying on the prediction results of the digital twin model for scheduling decisions when the prediction deviation is large, thereby improving the reliability of the scheduling process.

[0022] Based on the consistency evaluation value, this application dynamically corrects the weights of the state parameters involved in the generation and evaluation of energy operation scheduling strategies, so that the influence of the digital twin model prediction results on scheduling decisions can be adaptively adjusted according to the model's credibility, thereby reducing the scheduling risks caused by model uncertainty.

[0023] When the consistency evaluation value indicates that there is a significant deviation between the digital twin model and the actual operating state, this application enables the digital twin model to self-correct based on the latest operating data by performing online correction or partial reconstruction of the parameters of the digital twin model, thereby maintaining its effective representation of the tunnel energy operating state and supporting the stability and adaptability of the energy operation scheduling strategy in the long-term operation process. Attached Figure Description

[0024] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of the tunnel energy operation scheduling method based on digital twins according to the present invention; Figure 2 This is a structural diagram of the tunnel energy operation and scheduling system based on digital twins according to the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] Please see Figure 1 As shown, this application provides a tunnel energy operation scheduling method based on digital twins, including the following steps: Step S1: Obtain the structural parameters of energy operation in the tunnel, the distribution information of energy-consuming objects, and the operating constraints. Based on the structural parameters, the distribution information of energy-consuming objects, and the operating constraints, construct a digital twin model to characterize the energy operation status of the tunnel. In a specific implementation, the structural parameters include the spatial dimensions of the tunnel, the zoning method, and the spatial relationships of various energy-consuming devices within the tunnel. The energy-consuming object distribution information indicates the spatial distribution of different energy-consuming objects such as lighting, ventilation, and drainage within the tunnel. The operational constraints describe the operational limitations imposed on various energy-consuming objects under safe operation requirements. In this embodiment, the structural parameters and operational constraints are extracted by analyzing the tunnel design drawings and existing operational data. Based on this, a digital twin model corresponding one-to-one with the actual operating objects of the tunnel is constructed, enabling the digital twin model to reflect the overall structural characteristics and constraints of the tunnel's energy operation in a virtual environment.

[0028] The process of acquiring structural parameters of energy operation within a tunnel, information on the distribution of energy-consuming objects, and operational constraints, and constructing a digital twin model to characterize the tunnel's energy operation status, includes: First, extracting the tunnel's spatial structural parameters based on the tunnel's as-built drawings, BIM model, or maintenance log. These spatial structural parameters include at least the tunnel length L, cross-sectional dimensions S, and zoning information. and the connectivity matrix between each partition ,in Used to represent partitions With partitions Does a connectivity relationship exist?

[0029] The above parameters are used to establish a spatial topology for tunnel partitioning, which is used to describe the overall spatial structural characteristics of the tunnel.

[0030] At the same time, the distribution information of energy-consuming objects is extracted, and the energy-consuming objects include at least lighting equipment, ventilation equipment and drainage equipment; The distribution information of energy-consuming objects can be represented as a set of energy-consuming objects as follows:

[0031] Each energy-consuming object Associate its installation location Partition Coverage and equipment number Record the corresponding rated operating parameters. With adjustable operating range This establishes a mapping relationship between energy-consuming objects and tunnel space partitions.

[0032] Furthermore, operational constraints are obtained, which include at least safety operation constraints, equipment operation boundary constraints, and maintenance constraints. Among these, safety operation constraints are used to limit the allowable range of tunnel operation state parameters and can be expressed as:

[0033] in, Operating parameters include illuminance, air quality, visibility, and drainage level. This represents the corresponding set of safe operating intervals; Equipment operating boundary constraints are used to limit the start-up and shutdown conditions and operating boundaries of each energy-consuming object, and can be expressed as:

[0034] Operational constraints are used to limit the switching frequency of equipment or the minimum continuous operating time, and can be abstracted as constraints on the changes in control quantities between adjacent time points:

[0035] During the digital twin model construction phase, the aforementioned spatial structure parameters are used to establish a virtual spatial structure model for tunnel partitioning, the energy-consuming object distribution information is used to construct an energy-consuming object-partition association model, and the operational constraints are written into the constraint parameter set of the digital twin model. This enables digital twin models to describe the operating status of energy-consuming objects in each section of the tunnel and their constrained operating boundaries in a virtual environment.

[0036] The digital twin model is initialized, setting the initial operating states of each energy-consuming object. and initial environment state Load these parameters as the initial state parameters of the model to form the initial state vector of the digital twin model:

[0037] This allows for the construction of a digital twin model of tunnel energy operation for subsequent operational data mapping, energy operation scheduling strategy generation, and simulation evaluation.

[0038] Step S2: Collect energy operation data and environmental perception data of the tunnel during actual operation, and map the energy operation data and environmental perception data to the corresponding state parameters in the digital twin model; In a specific implementation, the energy operation data is used to characterize the energy consumption and equipment operating status of the tunnel during operation, while the environmental perception data is used to characterize changes in environmental conditions inside the tunnel. In this embodiment, energy operation data and environmental perception data are collected during tunnel operation according to a preset sampling period. After preprocessing the collected data, the processed energy operation data and environmental perception data are updated to the corresponding state parameters in the digital twin model based on a pre-established correspondence between state parameters. This ensures that the state in the digital twin model changes synchronously with the actual tunnel operation, thereby maintaining consistency between the virtual model and the actual operating state.

[0039] Step S3: Under the premise of meeting the tunnel safety operation constraints, generate at least one set of energy operation scheduling strategies based on the synchronized digital twin model state. The energy operation scheduling strategies are used to describe the energy allocation method, operation mode or scheduling sequence of the tunnel within a preset time range. In a specific implementation, the energy operation scheduling strategy is used to arrange the energy usage patterns of various energy-consuming objects within the tunnel during different operating periods. In this embodiment, based on the current tunnel operating status reflected in the digital twin model, and under the condition of satisfying safe operation constraints, the operating modes of different energy-consuming objects are combined to generate multiple sets of candidate energy operation scheduling strategies. Each set of energy operation scheduling strategies corresponds to different energy allocation schemes or operating mode settings, thereby providing multiple optional schemes for subsequent simulation evaluation of the scheduling strategy.

[0040] Step S4: Input the energy operation and scheduling strategy into the digital twin model for simulation, predict the impact of the energy operation and scheduling strategy on the tunnel energy consumption level and operation safety indicators, and determine the target energy operation and scheduling strategy based on the impact results.

[0041] In a specific implementation, the simulation is used to simulate the execution process of energy operation scheduling strategies in a virtual environment. In this embodiment, each energy operation scheduling strategy generated in step S3 is loaded into a digital twin model, and the scheduling execution process is simulated within a preset time range. This yields the changes in energy consumption and operational safety-related states corresponding to different scheduling strategies. The simulation results of different scheduling strategies are then compared and analyzed. Under the premise of meeting the requirements for safe tunnel operation, the energy operation scheduling strategy with the best overall performance is selected as the target energy operation scheduling strategy to guide tunnel energy operation scheduling.

[0042] In some embodiments, the process of mapping energy operation data and environmental sensing data to corresponding state parameters in a digital twin model includes: The collected energy operation data and environmental sensing data are time-aligned to form a synchronous dataset on a unified time scale. Based on the pre-established state parameter mapping relationship, various types of data in the synchronous dataset are associated with the energy consumption state parameters, environmental state parameters, and operational constraint parameters in the digital twin model, thereby completing the state mapping of the actual tunnel operation state in the digital twin model.

[0043] In a specific implementation, the time alignment process is used to eliminate differences in sampling frequency and sampling time between different data sources, enabling energy operation data and environmental sensing data to be correlated on the same time scale. In an embodiment, by resampling and interpolating the collected data at preset time intervals, a synchronized dataset containing both energy operation information and environmental status information at each sampling time is obtained. Subsequently, based on the state parameter mapping relationship predetermined during the digital twin model construction phase, the corresponding data items in the synchronized dataset are updated to the energy consumption status, environmental status, and operational constraint-related parameters in the digital twin model, thereby enabling the digital twin model to reflect the actual operating status of the tunnel in real time.

[0044] The state parameter mapping relationship is used to indicate the correspondence between the energy operation data and environmental perception data that can be collected during the actual operation of the tunnel and the state parameters in the digital twin model.

[0045] Specifically, the state parameter mapping relationship includes: For energy operation data that characterizes energy consumption or operating status, the data is mapped to energy consumption status parameters in the digital twin model by direct assignment or by assignment after calculation based on preset calculation rules. For environmental perception data that characterizes the operating environment, it is mapped to environmental state parameters or safety constraint state parameters in the digital twin model according to pre-set threshold rules or interval rules.

[0046] During the actual operation of the tunnel, the synchronized energy operation data and environmental perception data are updated to the corresponding state parameters in the digital twin model according to the state parameter mapping relationship, so as to achieve consistency maintenance between the state of the digital twin model and the actual operation state of the tunnel.

[0047] In some embodiments, the process of generating at least one set of energy operation scheduling strategies based on the synchronized digital twin model state includes: Adjustable operational variables corresponding to tunnel lighting, ventilation and drainage are set as decision variables, and safe operation constraints, equipment operation boundary constraints and energy consumption constraints are set as constraint conditions. Based on the prediction results of energy consumption and safety indicators in the preset prediction time domain by the digital twin model, a multi-objective optimization problem is constructed with the goal of minimizing energy consumption and maximizing safety satisfaction. A rolling time-domain model prediction solution mechanism is adopted to solve the multi-objective optimization problem in each scheduling cycle to generate a set of candidate energy operation scheduling strategies, and output at least one set of energy operation scheduling strategies from the set of candidate energy operation scheduling strategies.

[0048] In a specific implementation, the decision variables are used to characterize the adjustable operating states of different energy-consuming objects during operation, and the constraints are used to limit the execution of the scheduling strategy within the scope of safety and equipment operation. In an embodiment, based on the prediction results of the tunnel's current and future operating states from a digital twin model, the operating modes of different energy-consuming objects are combined, and the scheduling calculation conditions are continuously updated within a rolling scheduling cycle, thereby generating multiple sets of candidate energy operation scheduling strategies, enabling the scheduling strategy to be dynamically adjusted according to changes in the tunnel's operating state.

[0049] The process of generating at least one set of energy operation scheduling strategies based on the synchronized digital twin model state includes: Discretize the scheduling period into Adjustable operational variables corresponding to tunnel lighting, ventilation, and drainage are set as decision variables. ,in Indicates the lighting power setting value. Indicates the ventilation operation control quantity. This indicates the power setting value of the drainage pump; it sets the safety operation constraints, equipment operation boundary constraints, and energy consumption constraints as constraint conditions. Based on the prediction results of energy consumption and safety indicators by the digital twin model within a preset prediction time domain, a multi-objective optimization problem is constructed with the objectives of minimizing energy consumption and maximizing safety satisfaction. The energy consumption objective function within the prediction time domain is:

[0050] in, Energy consumption weighting coefficient For time step; This is the mapping function between the power of the ventilation fan and the control variable. To reflect the engineering characteristics of ventilation energy consumption, a cubic approximation can be used:

[0051] This embodiment designs the safety satisfaction level as the comprehensive degree of satisfaction of multiple safety indicators. These include: Illuminance satisfaction CO concentration satisfaction Visibility satisfaction With drainage safety satisfaction ; Tunnel lighting power setting Mapped to predicted average road surface illuminance :

[0052] in, The equivalent conversion factor from lighting power to illuminance. Contributions to ambient light or entrance natural light, etc.; ; Ventilation control volume Determine the equivalent ventilation volume :

[0053] CO concentration inside the tunnel The discrete prediction is obtained from "generation + discharge":

[0054] Where V is the equivalent control volume. The CO emission rate from vehicle emissions and other sources can be estimated using sensor data such as traffic flow. This is the ventilation efficiency coefficient.

[0055] ; visibility With smoke / particulate matter concentration There is a monotonic relationship:

[0056]

[0057] in, For particulate matter generation rate, This is the proportionality coefficient.

[0058] Visibility satisfaction:

[0059] Let the water level be Its changes can be accounted for by volume conservation:

[0060] Where A is the equivalent catchment area / volume conversion parameter. For the inflow of rainwater, seepage, etc. This refers to the pump discharge flow rate.

[0061] Pump discharge flow rate and pump power setting The relationship can be approximated by a monotonic function:

[0062] A value of 1 can be used to represent linearity, while other values ​​can be used to represent nonlinear pump characteristics.

[0063]

[0064] Multiple satisfaction levels are aggregated into a comprehensive safety satisfaction level.

[0065] If any indicator is not met, safety will be affected; therefore, a weighted geometric average is used.

[0066] The overall security satisfaction target in the prediction time domain can be defined as:

[0067] Multi-objective optimization can be expressed as:

[0068] The multi-objective optimization problem is transformed into a single-objective solution form. A rolling time-domain model prediction solution mechanism is adopted to solve the problem within each scheduling cycle to generate a set of candidate energy operation scheduling strategies. The single objective function is:

[0069] in, , and The normalized reference value is used; and at least one set of energy operation scheduling strategies is output from the set of candidate energy operation scheduling strategies.

[0070] In some embodiments, the simulation and evaluation steps of the scheduling strategy based on digital twins include: For each set of energy operation scheduling strategies, a corresponding scheduling execution sequence is constructed in the digital twin model. The scheduling execution sequence is simulated and deduced in multiple time steps within the preset prediction time domain to obtain the energy consumption state evolution sequence and the operation safety state evolution sequence of the energy operation scheduling strategy at different time nodes. Based on the energy consumption state evolution sequence and the operation safety state evolution sequence, the cumulative energy consumption index, energy consumption fluctuation index and safety risk accumulation index of each energy operation scheduling strategy in the prediction time domain are calculated. Based on the preset multi-indicator decision-making rules, the cumulative energy consumption index, energy consumption fluctuation index and safety risk accumulation index are normalized and weighted to form a comprehensive scheduling evaluation value corresponding to each energy operation scheduling strategy. Under the premise of meeting the constraints of safe operation, the target energy operation and scheduling strategy is determined based on the comprehensive scheduling evaluation value.

[0071] In a specific implementation, the scheduling execution sequence is used to describe the execution process of the energy operation scheduling strategy in the prediction time domain. In an embodiment, by simulating the scheduling execution process in a digital twin model with continuous time steps, the evolution of energy consumption changes and safety status changes of different scheduling strategies during operation is obtained. The comprehensive performance of different scheduling strategies is compared based on multiple evaluation dimensions, thereby selecting the scheduling strategy with the better comprehensive evaluation result as the target energy operation scheduling strategy while ensuring the safe operation requirements of the tunnel.

[0072] In some embodiments, the process of assessing the consistency between the digital twin model state and the actual tunnel operating state based on the deviation relationship between historical operating data and currently synchronized energy operating data includes: Within a preset time window, the predicted value sequence of the corresponding state parameters in the digital twin model and the measured value sequence corresponding to the actual operating state of the tunnel are obtained respectively. Based on the predicted and measured value sequences, the deviation metric of each state parameter within the time window is calculated. The deviation metric is determined as follows:

[0073] in, This represents the measured value of the i-th state parameter at time t. This represents the predicted value of the corresponding state parameter in the digital twin model at time t, where T represents the number of sampling points within the time window; Based on the deviation metric value corresponding to each state parameter The deviation metrics are weighted and aggregated according to preset weights to obtain the consistency evaluation value C between the digital twin model state and the actual tunnel operation state, where:

[0074] in, Let represent the consistency weight corresponding to the i-th state parameter, and satisfy . N represents the number of state parameters participating in the consensus assessment; When the consistency evaluation value C is less than the preset consistency threshold, it is determined that the consistency between the current digital twin model state and the actual tunnel operation state is insufficient, triggering the correction or reconstruction of the digital twin model state parameters.

[0075] In a specific implementation, the consistency assessment is used to determine the accuracy of the digital twin model's representation of the tunnel's actual operating status. In this embodiment, by continuously comparing the digital twin model's prediction results with the tunnel's actual operating data within a preset time window, it is determined whether the digital twin model can effectively reflect the tunnel's operating status. When consistency is insufficient, scheduling decisions are avoided based on model results with large deviations, providing a triggering basis for subsequent model correction or reconstruction.

[0076] In some embodiments, after obtaining the consistency evaluation value C between the digital twin model state and the actual tunnel operating state, the method further includes: Based on the consistency evaluation value C, the weights of the state parameters involved in the generation and evaluation of energy operation scheduling strategies are dynamically corrected. Specifically, when the consistency evaluation value C is lower than the preset consistency threshold, the weight of the corresponding state parameter in the scheduling strategy evaluation process is reduced, and when the consistency evaluation value C is higher than the consistency threshold, the weight of the corresponding state parameter in the scheduling strategy evaluation process is increased. In the subsequent generation and simulation evaluation of energy operation scheduling strategies, the energy consumption and operation safety indicators of the scheduling strategy are recalculated and comprehensively evaluated based on the dynamically corrected state parameter weights.

[0077] In a specific implementation, by dynamically adjusting the weights of the state parameters, the influence of the digital twin model's prediction results on scheduling decisions can be adaptively changed according to the model's current credibility. In an example, when the model's prediction deviation is large, its impact on the evaluation results of the scheduling strategy is reduced, thereby reducing the risk to scheduling decisions caused by model uncertainty.

[0078] In some embodiments, online parameter correction or partial reconstruction of the digital twin model is performed based on the consistency evaluation value C, specifically including: When the consistency evaluation value C is in the first preset range, it is determined that the overall structure of the digital twin model still meets the modeling assumptions. Online correction is performed on the model parameters related to energy consumption prediction or operation safety prediction in the digital twin model. The online correction includes incremental updates of the model parameters based on historical operation data and current synchronized energy operation data to reduce the deviation between the predicted value and the actual operation value of the digital twin model. When the consistency evaluation value C is in the second preset range below the first preset range, it is determined that the local modeling relationship of the digital twin model is inconsistent with the actual operating state of the tunnel. Local reconstruction is performed on the corresponding local state description or state evolution relationship in the digital twin model. The local reconstruction includes re-establishing the correlation between relevant state parameters or updating the corresponding state evolution rules. After completing online parameter correction or partial reconstruction, the generation and simulation evaluation process of energy operation scheduling strategy is re-executed based on the updated digital twin model.

[0079] In specific implementations, the online parameter correction is used to improve prediction accuracy while maintaining the overall model structure, and the local reconstruction is used to address situations where tunnel operating conditions change significantly. In this embodiment, by performing online correction or local reconstruction on the digital twin model, it can continuously adapt to changes in the tunnel operating environment and energy consumption characteristics, thereby providing a stable and reliable model foundation for the generation and evaluation of energy operation scheduling strategies.

[0080] Please see Figure 2 As shown, in some embodiments, this application provides a tunnel energy operation scheduling system based on digital twins, used to implement a tunnel energy operation scheduling method based on digital twins. The system includes: The modeling module is configured to acquire structural parameters of energy operation within the tunnel, distribution information of energy-consuming objects, and operational constraints, and to construct a digital twin model to characterize the energy operation status of the tunnel based on the structural parameters, distribution information of energy-consuming objects, and operational constraints. The data synchronization module is configured to collect energy operation data and environmental perception data of the tunnel during actual operation, and map the energy operation data and environmental perception data to the corresponding state parameters in the digital twin model; The strategy generation module is configured to generate at least one set of energy operation scheduling strategies based on the synchronized digital twin model state, under the premise of meeting the tunnel safety operation constraints. The energy operation scheduling strategies are used to describe the energy allocation method, operation mode or scheduling sequence of the tunnel within a preset time range. The strategy evaluation module is configured to input the energy operation scheduling strategy into the digital twin model for simulation, predict the impact of the energy operation scheduling strategy on the tunnel energy consumption level and operation safety indicators, and determine the target energy operation scheduling strategy based on the impact results.

[0081] In some embodiments, this application provides a terminal, including: A memory for storing tunnel energy operation scheduling programs based on digital twins; A processor is used to implement the steps of the digital twin-based tunnel energy operation scheduling method when executing the digital twin-based tunnel energy operation scheduling system.

[0082] In some embodiments, this application provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the tunnel energy operation scheduling method based on digital twins.

[0083] The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit the scope of one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this specification should be included within the protection scope of one or more embodiments of this specification.

Claims

1. A tunnel energy operation scheduling method based on digital twins, characterized in that, Includes the following steps: Step S1: Obtain the structural parameters of energy operation in the tunnel, the distribution information of energy-consuming objects, and the operating constraints. Based on the structural parameters, the distribution information of energy-consuming objects, and the operating constraints, construct a digital twin model to characterize the energy operation status of the tunnel. Step S2: Collect energy operation data and environmental perception data of the tunnel during actual operation, and map the energy operation data and environmental perception data to the corresponding state parameters in the digital twin model; Step S3: Under the premise of meeting the tunnel safety operation constraints, generate at least one set of energy operation scheduling strategies based on the synchronized digital twin model state. The energy operation scheduling strategies are used to describe the energy allocation method, operation mode or scheduling sequence of the tunnel within a preset time range. Step S4: Input the energy operation and scheduling strategy into the digital twin model for simulation, predict the impact of the energy operation and scheduling strategy on the tunnel energy consumption level and operation safety indicators, and determine the target energy operation and scheduling strategy based on the impact results.

2. The tunnel energy operation scheduling method based on digital twins according to claim 1, characterized in that, The process of mapping energy operation data and environmental sensing data to the corresponding state parameters in a digital twin model includes: The collected energy operation data and environmental sensing data are time-aligned to form a synchronous dataset on a unified time scale. Based on the pre-established state parameter mapping relationship, various types of data in the synchronous dataset are associated with the energy consumption state parameters, environmental state parameters, and operational constraint parameters in the digital twin model, thereby completing the state mapping of the actual tunnel operation state in the digital twin model.

3. The tunnel energy operation scheduling method based on digital twins according to claim 2, characterized in that, The process of generating at least one set of energy operation scheduling strategies based on the synchronized digital twin model state includes: Adjustable operational variables corresponding to tunnel lighting, ventilation and drainage are set as decision variables, and safe operation constraints, equipment operation boundary constraints and energy consumption constraints are set as constraint conditions. Based on the prediction results of energy consumption and safety indicators in the preset prediction time domain by the digital twin model, a multi-objective optimization problem is constructed with the goal of minimizing energy consumption and maximizing safety satisfaction. A rolling time-domain model prediction solution mechanism is adopted to solve the multi-objective optimization problem in each scheduling cycle to generate a set of candidate energy operation scheduling strategies, and output at least one set of energy operation scheduling strategies from the set of candidate energy operation scheduling strategies. In a specific implementation, the decision variables are used to characterize the adjustable operating states of different energy-consuming objects during operation, and the constraints are used to limit the execution of the scheduling strategy within the scope of safety and equipment operation. In an embodiment, based on the prediction results of the tunnel's current and future operating states from a digital twin model, the operating modes of different energy-consuming objects are combined, and the scheduling calculation conditions are continuously updated within a rolling scheduling cycle, thereby generating multiple sets of candidate energy operation scheduling strategies, enabling the scheduling strategy to be dynamically adjusted according to changes in the tunnel's operating state.

4. The tunnel energy operation and scheduling method based on digital twins according to claim 3, characterized in that, The steps for simulating and evaluating scheduling strategies based on digital twins include: For each set of energy operation scheduling strategies, a corresponding scheduling execution sequence is constructed in the digital twin model. The scheduling execution sequence is simulated and deduced in multiple time steps within the preset prediction time domain to obtain the energy consumption state evolution sequence and the operation safety state evolution sequence of the energy operation scheduling strategy at different time nodes. Based on the energy consumption state evolution sequence and the operation safety state evolution sequence, the cumulative energy consumption index, energy consumption fluctuation index and safety risk accumulation index of each energy operation scheduling strategy in the prediction time domain are calculated. Based on the preset multi-indicator decision-making rules, the cumulative energy consumption index, energy consumption fluctuation index and safety risk accumulation index are normalized and weighted to form a comprehensive scheduling evaluation value corresponding to each energy operation scheduling strategy. Under the premise of meeting the constraints of safe operation, the target energy operation and scheduling strategy is determined based on the comprehensive scheduling evaluation value.

5. The tunnel energy operation scheduling method based on digital twins according to claim 4, characterized in that, The process of assessing the consistency between the digital twin model's state and the tunnel's actual operating state, based on the discrepancy between historical operating data and currently synchronized energy operating data, includes: Within a preset time window, the predicted value sequence of the corresponding state parameters in the digital twin model and the measured value sequence corresponding to the actual operating state of the tunnel are obtained respectively. Based on the predicted and measured value sequences, the deviation metric of each state parameter within the time window is calculated. The deviation metric is determined as follows: in, This represents the measured value of the i-th state parameter at time t. This represents the predicted value of the corresponding state parameter in the digital twin model at time t, where T represents the number of sampling points within the time window; Based on the deviation metric value corresponding to each state parameter The deviation metrics are weighted and aggregated according to preset weights to obtain the consistency evaluation value C between the digital twin model state and the actual tunnel operation state, where: in, Let represent the consistency weight corresponding to the i-th state parameter, and satisfy . N represents the number of state parameters participating in the consensus assessment; When the consistency evaluation value C is less than the preset consistency threshold, it is determined that the consistency between the current digital twin model state and the actual tunnel operation state is insufficient, triggering the correction or reconstruction of the digital twin model state parameters.

6. The tunnel energy operation scheduling method based on digital twins according to claim 5, characterized in that, After obtaining the consistency evaluation value C between the digital twin model state and the actual tunnel operating state, the following is also included: Based on the consistency evaluation value C, the weights of the state parameters involved in the generation and evaluation of energy operation scheduling strategies are dynamically corrected. Specifically, when the consistency evaluation value C is lower than the preset consistency threshold, the weight of the corresponding state parameter in the scheduling strategy evaluation process is reduced, and when the consistency evaluation value C is higher than the consistency threshold, the weight of the corresponding state parameter in the scheduling strategy evaluation process is increased. In the subsequent generation and simulation evaluation of energy operation scheduling strategies, the energy consumption and operation safety indicators of the scheduling strategy are recalculated and comprehensively evaluated based on the dynamically corrected state parameter weights.

7. The tunnel energy operation scheduling method based on digital twins according to claim 6, characterized in that, Based on the consistency evaluation value C, online parameter correction or partial reconstruction of the digital twin model is performed, specifically including: When the consistency evaluation value C is in the first preset range, it is determined that the overall structure of the digital twin model still meets the modeling assumptions. Online correction is performed on the model parameters related to energy consumption prediction or operation safety prediction in the digital twin model. The online correction includes incremental updates of the model parameters based on historical operation data and current synchronized energy operation data to reduce the deviation between the predicted value and the actual operation value of the digital twin model. When the consistency evaluation value C is in the second preset range below the first preset range, it is determined that the local modeling relationship of the digital twin model is inconsistent with the actual operating state of the tunnel. Local reconstruction is performed on the corresponding local state description or state evolution relationship in the digital twin model. The local reconstruction includes re-establishing the correlation between relevant state parameters or updating the corresponding state evolution rules. After completing online parameter correction or partial reconstruction, the generation and simulation evaluation process of energy operation scheduling strategy is re-executed based on the updated digital twin model.

8. A tunnel energy operation scheduling system based on digital twins, used to implement the tunnel energy operation scheduling method based on digital twins as described in claim 1, characterized in that, The system includes: The modeling module is configured to acquire structural parameters of energy operation within the tunnel, distribution information of energy-consuming objects, and operational constraints, and to construct a digital twin model to characterize the energy operation status of the tunnel based on the structural parameters, distribution information of energy-consuming objects, and operational constraints. The data synchronization module is configured to collect energy operation data and environmental perception data of the tunnel during actual operation, and map the energy operation data and environmental perception data to the corresponding state parameters in the digital twin model; The strategy generation module is configured to generate at least one set of energy operation scheduling strategies based on the synchronized digital twin model state, under the premise of meeting the tunnel safety operation constraints. The energy operation scheduling strategies are used to describe the energy allocation method, operation mode or scheduling sequence of the tunnel within a preset time range. The strategy evaluation module is configured to input the energy operation scheduling strategy into the digital twin model for simulation, predict the impact of the energy operation scheduling strategy on the tunnel energy consumption level and operation safety indicators, and determine the target energy operation scheduling strategy based on the impact results.

9. A terminal, characterized in that, include: A memory for storing tunnel energy operation scheduling programs based on digital twins; A processor is configured to implement the steps of the tunnel energy operation scheduling method based on digital twins as described in claim 1 when executing the tunnel energy operation scheduling device based on digital twins.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the tunnel energy operation scheduling method based on digital twins as described in claim 1.

Images