Coal preparation plant energy storage system and energy storage method based on digital twinning

Abstract

The invention provides a coal preparation plant energy storage system and method based on digital twinning, and the system comprises a hybrid energy storage system, a battery management system, a high-voltage DC protection system, a pre-charging / discharging loop, a high-voltage AC power distribution system, a centralized PCS cluster, and a power electronic interface of a power grid. And the battery energy storage array is connected with power consumption equipment in the coal preparation plant. Constructing a digital twinborn model of the power consumption equipment, obtaining a scheduling plan of the coal preparation plant, determining the power consumption equipment required by the technological process under the current scheduling plan, and simulating the workload of all the power consumption equipment under the current scheduling plan through the digital twinborn model; and according to the workload of the power consumption equipment, predicting the electric quantity W required by the peak value of the electricity price under the current production scheduling plan, and configuring the corresponding energy storage capacity. Through full-process efficiency management and control, production efficiency is improved, an electric energy storage system is established, and an optimal power storage and discharge planning plan is given through a digital twin technology and local peak-valley electricity prices, so that the unit power consumption cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of energy storage technology, and specifically to a coal preparation plant energy storage system and energy storage method based on digital twins. Background Art

[0002] Thermal coal preparation plants use a variety of coal preparation technologies and processes to remove impurities such as gangue and minerals with high sulfur content from the raw coal mined from coal mines. Subsequently, the raw coal is sorted and processed according to different quality requirements and market demands to produce thermal coal products that meet the corresponding standards. The purpose of setting up a coal preparation plant is to improve the quality of coal so that coal can better serve as a power fuel and is widely used in many power fields such as power generation, heating, steam locomotive coal, and industrial boiler fuel. In terms of product quality control, thermal coal preparation plants need to ensure that the calorific value of the final coal meets the specified standards, and the ash content of the clean coal must also meet the corresponding requirements.

[0003] At the production cost level, electricity consumption accounts for a relatively large proportion of production costs. How to reduce electricity costs is one of the main directions of cost control in coal preparation plants. With the development of energy storage technology, building energy storage systems and using the price differences between valley and peak periods to control electricity costs is a common method used by energy-consuming factories. Coal preparation plants correspond to different media, and their production processes are relatively large. The energy consumption of equipment in each production process link is also different, and the daily power consumption also varies greatly. Existing energy storage systems for industrial applications use valley periods for charging every day according to the total capacity of the battery array, rather than the actual electricity required the next day. Frequent charging and discharging has a significant impact on the life of the battery array. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a coal preparation plant energy storage system and energy storage method based on digital twins, so as to solve the above-mentioned problems existing in the prior art and reduce the energy consumption of the coal preparation plant.

[0005] In the first aspect, a coal preparation plant energy storage system based on digital twins includes a hybrid energy storage system, a battery management system, a high-voltage DC protection system, a pre-charge / discharge circuit, a high-voltage AC distribution system, a centralized PCS cluster, and a power grid power electronic interface. The hybrid energy storage system is connected to the power-consuming equipment in the coal preparation plant, including a lithium battery array and a supercapacitor array. A device-level digital twin model is constructed based on the dynamic data of the power-consuming equipment and coupled to generate a system-level digital twin model. According to the production schedule, the local electricity price at different time periods, and the charging and discharging cost of the hybrid energy storage system, the start-stop combination, working period, and The power of the motors of the power-consuming equipment is simulated to find the production route with the optimal total electricity price for a single working day, and the constraints include the processing volume and start-stop frequency of all the power-consuming equipment in a single working day; according to the optimal production route, the start-stop time periods of the power-consuming equipment and the power of the motors are determined; the energy storage capacity of the hybrid energy storage system is determined according to the working time periods of the power-consuming equipment and the power of the motors; the peak load time periods when the power-consuming equipment is started and stopped are predicted according to the working time periods of the power-consuming equipment, and the battery management system turns on the supercapacitor array during the peak load period to perform high-frequency power compensation for the power-consuming equipment, and the lithium battery array supplies power to the power-consuming equipment during the period other than the peak load.

[0006] In an optional implementation manner, the method for finding a production route with the best total electricity price for a single working day includes: The low-price period and peak-price period are divided into T and T' periods respectively, and the duration of each period is , j represents the jth period during the trough period, and k represents the kth period during the peak period; The power-consuming devices are numbered to form a set, where m is the total number of devices; the power of the power-consuming device numbered i in time period j is , let the power of the power consuming device numbered i in time period k be , , Indicates whether the power-consuming device numbered i works during period j. When , it means that the power-consuming device i works in the j period during the low electricity price period. When it is on, it means that the power-consuming device i is not working; , Indicates whether the power-consuming device numbered i works in time period k. When , it means that the power consuming device i works in the k period during the peak electricity price period. When it is on, it means that the power-consuming device i is not working; Assume the off-peak electricity price is C, and the power supply cost of the energy storage system is d; the total daily electricity cost during the off-peak period is C-low:

[0007] The total cost of electricity during peak hours C-high:

[0008] Establish the objective function C-total = C-low + C-high, where C-total is the total electricity cost. According to the genetic algorithm, solve , as well as The total cost of electricity is the lowest through as well as The value determines whether the power-consuming equipment is turned on or off in each time period.

[0009] In an optional implementation, a method for calculating the energy storage capacity of a hybrid energy storage system includes: According to the optimal production route, the start and stop time periods of the power-consuming equipment and the power of the motor are determined. According to the working time periods of the power-consuming equipment and the power of the motor, the total power consumption W during the peak power period of a working day is determined.

[0010] The energy storage capacity of the hybrid energy storage system is E=W×a / (η×DOD), where DOD is the depth of discharge, η is the charge and discharge efficiency, and a is the redundancy coefficient.

[0011] In an optional implementation, the following constraints may be added to solve the objective function C-total = C-low + C-high. Lsystem Value setting threshold, L system The value calculation process includes: Based on the real-time simulation computing capability of the digital twin model's digital quality process and the screening and floating data in the real-time coal quality database, the real-time processing capacity of each device and system is obtained, the optimal raw coal processing capacity of the current system is obtained, and the production efficiency of the current coal preparation plant is calculated in combination with the real-time raw coal washing capacity (real-time raw coal washing capacity / optimal raw coal processing capacity). The load rate of each device is analyzed and calculated, and the load level (low load, optimal load, high load, overload, and the values ​​can be assigned and calculated separately, such as 1, 2, 3, 4) is divided. Further, according to the equipment in each major production system (raw coal preparation system, heavy medium separation system, coarse coal slime recovery system, product transportation system, etc.) in each interval (low load, optimal load, high load, overload), the probability distribution model that the equipment obeys is determined based on the historical load state, and the equipment failure data and load abnormality data within a certain period of time are collected, such as the number of failures, failure time, average load rate value in the abnormal load interval, abnormal load duration, etc., to calculate the reliability R of a single device, R=R0(1-F); where R0 is the basic credibility, R0=e -λt, λ=failure times / unit operation time, t is equipment life; F represents the reliability attenuation factor caused by abnormal load, F=min(△L×p×k,1), k is the adjustment coefficient, which needs to be set based on experience, △L=(average load rate-rated load rate) / rated load rate, p=abnormal load duration / average failure interval time; the R value can automatically adjust the allocation weight wi of each device, and assign weight wi to each device. The allocation weight wi is positively correlated with the reliability R, that is, the higher the R, the greater the weight. Thus, the overall load rate status L of the main production system is calculated system =∑(wi×Li) and divide the load levels, Li represents the load level of the power-consuming equipment numbered i, such as 1, 2, 3, 4.

[0012] The overall load rate state of the selected coal plant is L system When the reliability is low and there is a high-load or overloaded production system, analyze the load and reliability of the equipment inside the system. If the reliability is within a credible range (such as above 70%) and the equipment load is high, the reasons for the high load (including high load and overload) and solutions can be analyzed in combination with the upstream and downstream relationships of the process and the trained online inference model.

[0013] In an optional implementation manner, the power consuming device includes a concentration system, and the load level determination of the concentration system includes: Obtain the target data of the thickening system, including the current solid content of the thickener feed, the overflow turbidity of the thickener, the torque of the thickener rake, the height of the thickener coal slime layer, the underflow concentration of the thickener, the model and specification of the thickener, the number of filter presses currently in operation, and the discharge volume of the filter press. According to the historical data, the target data is cleaned, the feature importance analysis is performed on the cleaned data, and the system load level is given using the supervised learning algorithm.

[0014] In an optional implementation, the system-level digital twin model also includes a prediction model based on the Transformer-TCN hybrid architecture, which predicts the required power during the peak power period of the next working day based on input data; the input data includes the power of power-consuming equipment, raw coal screening floating data, sorting process time series data, power-consuming equipment working temperature and humidity, vibration signals, health assessment indicators, production shifts, production targets, and equipment start-stop plans. The Transformer-TCN hybrid architecture includes a Transformer layer and a TCN layer. The Transformer layer is used to capture the long-term dependencies of load data, and the TCN layer extracts local time series features through causal convolution and dilated convolution; the non-stationary load signal of the input data is decomposed through variational mode decomposition, and the modal components of different frequency bands are extracted to reduce noise interference and enhance feature interpretability. The time series feature matrix is ​​generated through Z-score standardization and sliding window technology. The model is trained using historical data and combined with transfer learning to improve the generalization ability in small sample scenarios. Adversarial training (GAN) is introduced to generate extreme working condition data (such as equipment failure and coal quality mutation) to enhance the robustness of the model. When the actual load deviates from the forecasted load by more than the threshold, the LSTM error correction module is triggered to adjust the forecast model parameters online. For example, when a sudden change in coal quality during the previous day’s production process causes a sudden increase in the load of the sorting machine, the digital twin instantly generates simulation data, updates the forecast results, and adjusts the amount of stored electricity for the next working day.

[0015] In an optional implementation, the hybrid energy storage system stores electric energy when electricity prices are low, and is connected to the power grid to release excess electric energy during peak times; the power grid power electronics interface also includes a virtual synchronous generator, which is used to simulate the rotor of the synchronous generator of the power grid system; the power grid operation status is acquired in real time to determine whether the power grid frequency change reaches a threshold. When the set threshold is reached, the virtual synchronous generator simulates the inertial response of the synchronous generator of the power grid system, dynamically adjusts the inertia of the virtual generator to delay the frequency change, calculates the power of the virtual generator based on the frequency deviation and the adjusted inertia, and adjusts the power distribution of the virtual synchronous generator corresponding to the battery array based on the health of the battery array in the hybrid energy storage system.

[0016] In a second aspect, a coal preparation plant energy storage method is provided, which adopts the coal preparation plant energy storage system based on digital twin described in the first aspect.

[0017] Beneficial effects: Based on digital twin technology, full-process twin calculations can be performed on thermal coal preparation plants; efficiency bottlenecks can be determined by load judgment of each system and equipment; through full-process efficiency management and control, comprehensive judgment and improvement of production efficiency can be made, and a new energy energy storage system can be established. Through digital twin technology and local peak and valley electricity prices, the best storage and discharge planning plan can be given, thereby reducing unit electricity consumption costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application; Figure 2 A schematic flow chart of a coal preparation plant energy storage method based on digital twin provided in an embodiment of the present application; Figure 3 A block diagram of a digital twin coal preparation plant energy storage system provided in an embodiment of the present application; Figure 4 A schematic diagram of a device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. Unless otherwise defined, the technical terms or scientific terms used in this application should be the common meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "including" and other similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connected", "coupled" or "connected" and other similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0021] The following is an explanation of the digital twin model. The digital twin model is a virtual model that uses digital technology to perform all-round, dynamic, and real-time mapping of physical entities (such as equipment, systems, processes, or environments). Its core is to use the Internet of Things (IoT), big data, artificial intelligence (AI), cloud computing, and simulation technology to synchronize the operating status, behavioral characteristics, and environmental conditions of the physical world to the virtual space in real time, thereby achieving real-time monitoring, simulation prediction, optimized decision-making, and closed-loop control of physical entities. The essence of the digital twin model is to build a virtual mirror that "coexists" with the physical entity through virtual-real interaction and data-driven. It can not only reproduce the current state of the physical entity, but also predict future behavior through historical data accumulation and algorithm deduction, and even reversely intervene in the operation of the physical entity, forming a complete closed loop from perception, analysis, decision-making to execution. Its technical foundation includes multi-source heterogeneous data acquisition, high-precision modeling and simulation, real-time data synchronization, machine learning and optimization algorithms, etc. The specific implementation is usually divided into three levels: geometric twin (describing physical structure), behavioral twin (simulating dynamic process), and rule twin (embedded business logic). In terms of technical architecture, the digital twin model consists of a physical entity layer, a data transmission layer, a virtual model layer, and a functional application layer. The physical entity layer collects temperature, pressure, vibration, position, energy consumption and other data in real time through sensors, actuators, cameras, RFID tags and other devices; the data transmission layer relies on 5G, industrial Ethernet, edge computing and other technologies to transmit the collected data to the cloud or local server at high speed and low latency, while ensuring data security and integrity; the virtual model layer is the core of the digital twin, and it builds dynamic virtual entities through three-dimensional modeling (such as CAD), physical equation simulation (such as finite element analysis), and data-driven models (such as neural networks); the functional application layer provides services such as condition monitoring, fault diagnosis, performance optimization, and predictive maintenance based on virtual models.

[0022] The application of digital twin models in coal preparation plants is mainly reflected in the construction of a virtual mirror system that is highly synchronized with the actual physical equipment, process flow and production environment to achieve real-time monitoring, intelligent optimization and predictive maintenance of the entire coal preparation process. In coal preparation plants, digital twin models first collect equipment operation data (such as motor speed, bearing temperature, separation density, coal slurry concentration, processing volume, energy consumption, etc.) in real time through sensors (such as vibration sensors, temperature sensors, pressure sensors, and current sensors) deployed on key equipment such as crushers, heavy medium separators, centrifugal dehydrators, vibrating screens, and belt conveyors, and combine the screening floating and sinking data of raw coal, ash content, sulfur content and other coal quality parameters, and transmit them to the cloud or local digital twin platform through the Internet of Things (IoT) technology. The platform uses three-dimensional modeling technology (such as BIM or CAD) to build a geometric model of coal preparation equipment, and dynamically simulates the operating status of equipment under different working conditions by integrating mechanism models (such as density control equations for heavy medium separation and fluid mechanics models for centrifugal dehydrators) with data-driven models (such as LSTM neural network prediction of equipment failures and random forest algorithm optimization of separation parameters). For example, in the heavy medium separation process, the digital twin model can analyze the matching relationship between the raw coal density distribution and the medium density in real time, dynamically adjust the suspension density setting value, combine historical data to predict the separation efficiency and clean coal yield, and verify the feasibility of parameter adjustment through virtual debugging, and then feed back the optimization command to the PLC control system to achieve closed-loop control of separation density, so that the clean coal recovery rate can be increased by 3%-5%. In terms of equipment health management, the digital twin model analyzes the time-frequency characteristics of the vibration signal (such as extracting high-frequency fault components by wavelet packet decomposition) and the harmonic characteristics of the current, and combines the equipment historical fault library to predict potential faults such as crusher hammer wear and centrifuge bearing aging, and generates maintenance suggestions (such as replacing the screen 2 weeks in advance), reducing unplanned downtime by 20%-30%. In addition, in response to the high energy consumption of coal preparation plants, the digital twin model can simulate the equipment start-stop combination and load distribution strategy under different production shifts, and dynamically optimize the crusher operation frequency and pump equipment power in combination with time-of-use electricity prices and the state of energy storage system (SOC), so as to reduce the power consumption per ton of coal by 8%-12%. In safety management and control, the digital twin model uses laser radar and video fusion technology to build a three-dimensional panoramic map of the coal preparation workshop, track the location of personnel and the operating status of equipment in real time, and automatically trigger the sound and light alarm and link the emergency stop system when it detects that the belt is running off track, the coal bunker level exceeds the limit, or personnel are close to the dangerous area. At the same time, the digital twin supports cross-system collaboration. For example, when the amount of raw coal entering the washing suddenly increases, the model can simulate the load matching relationship between the heavy medium separation system and the coarse coal slime recovery system, and dynamically adjust the cyclone inlet pressure and the magnetic separator excitation current to avoid system overload.Through digital twin technology, the coal preparation plant has achieved a transformation from "experience-driven" to "data-driven", with overall production efficiency increased by 15%-20% and equipment utilization increased to more than 90%. At the same time, it provides a virtual test environment for process innovation (such as intelligent dry sorting instead of wet sorting), significantly reducing the cost and risk of technological transformation.

[0023] The coal preparation plant energy storage construction method based on digital twin provided in the embodiment of the present application can be applied in the following aspects: Figure 1 The analysis and decision-making system shown in the figure includes a transmission layer, a perception layer, an algorithm layer, and an application layer. Through the real-time simulation and simulation technology of digital twins, the load status of systems and equipment, the load balancing of multi-system material distribution, and the load judgment of the concentration system, the production efficiency bottlenecks can be analyzed and solved, so as to increase the raw coal processing capacity per unit time of the coal preparation plant, improve the equipment utilization rate, and reduce the power consumption per ton of coal and the unit power consumption cost. A closed-loop and precise control of the production efficiency of the whole thermal coal preparation plant of "prediction-adjustment-verification" can be achieved.

[0024] The data layer obtains underlying real-time data through various basic sensors such as quality, water volume, flow, concentration, gate opening, and equipment motor current, builds a full-process data lake, and combines the time series database (InfluxDB) to realize real-time processing of high-frequency data. The perception layer includes distributed edge nodes and multi-device collaboration protocols. Distributed edge nodes deploy edge computing modules on key equipment (such as heavy medium shallow trough separators), run lightweight AI models locally, and achieve low-latency real-time control (such as fine-tuning of heavy medium addition); the multi-device collaboration protocol is based on the communication protocol of the Industrial Internet of Things (IIoT) to achieve autonomous collaboration between devices.

[0025] Digital twin computing model: Based on the process calculation rules of the coal preparation industry, the online and dynamic calculation of the coal preparation production process system process is carried out. According to the real-time coal quality fluctuations (such as ash content and calorific value), the raw coal screening floating and sinking data are automatically adjusted. The digital twin computing model will perform simulation operations based on the latest data. Furthermore, according to the machine learning neural network algorithm, the floating and sinking data of each sorting system obtained by the digital twin computing model are fitted with the selectivity curve, so as to predict the optimal washing parameters (such as heavy medium density and coarse coal slime sorting machine feeding pressure), and send the decision target to the corresponding execution system (such as intelligent density control and intelligent coarse coal slime sorting system). The execution system is equipped with distributed edge node technology to achieve low-latency real-time control and reduce manual intervention. The LSTM neural network and digital twin digital quality process calculation model are used to predict the quality of clean coal after washing (such as clean coal ash content and end coal calorific value) in real time, and the key influencing factors (such as raw coal particle size distribution and density distribution characteristics) are analyzed in combination with the XGBoost algorithm to adjust the process parameters in advance. When the predicted quality deviates from the target value, the system automatically triggers the compensation strategy. For example, when the ash content of clean coal exceeds the standard, the shallow trough sorting density is adjusted to achieve a closed loop of "prediction-adjustment-verification". When the predicted quality deviates from the target value, the system automatically triggers the compensation strategy. The application layer is used for load analysis of the system and power-consuming equipment, load judgment of the concentration system, and power storage distribution.

[0026] like Figure 3 As shown, the coal preparation plant energy storage system based on digital twin in the embodiment of the present application includes a hybrid energy storage system, a battery management system, a high-voltage DC protection system, a pre-charge / discharge circuit, a high-voltage AC distribution system, a centralized PCS cluster, and a power grid power electronic interface. The battery energy storage is connected to the power-consuming equipment in the coal preparation plant, and the total capacity of the hybrid energy storage system is determined by the above method. The hybrid energy storage system stores electrical energy and provides DC power. The battery management system (BMS) monitors the battery status (SOC / SOH), balancing management, thermal management, and fault protection. The high-voltage DC protection system provides overvoltage, overcurrent, and short-circuit protection to ensure the safety of the DC side; the pre-charge / discharge circuit limits the surge current when the system starts and releases residual energy when it stops; the centralized PCS cluster provides DC-AC bidirectional conversion, grid-connected / off-grid mode switching, and power regulation; the high-voltage AC distribution system distributes AC power and integrates protection devices (circuit breakers, fuses). The power grid power electronic interface needs to comply with the grid connection standards (voltage, frequency, harmonics) to achieve bidirectional flow of electrical energy.

[0027] like Figure 2 As shown, the coal preparation plant energy storage method based on digital twin includes the following steps.

[0028] Deploy sensors to obtain dynamic data of power-consuming equipment in coal preparation plants, including electrical parameters, operating parameters, and environmental parameters under various coal quality processes. Electrical parameters are collected through smart meters at intervals of 1 second to 1 minute for current and voltage waveforms. Vibration / temperature parameters are monitored through industrial-grade vibration sensors at a sampling rate of 10kHz for the mechanical state of the equipment. Edge gateways (such as Huawei Atlas500) can be deployed on the device side to filter, denoise, and compress the raw data. For example, perform FFT analysis on the current signal to extract the fundamental and harmonic components. High-frequency vibration / current waveforms can be transmitted to the cloud or local server in real time through OPCUA and MQTT communication protocols. Coal quality data can be wirelessly transmitted within the workshop through ModbusTCP and LoRaWAN communication protocols.

[0029] The deployment of sensors is shown in the following table.

[0030]

[0031] Get the production schedule of the coal preparation plant. The parameters obtained are as follows: Coal quality parameters: ash content, moisture content, sulfur content, and particle size distribution.

[0032] Process parameters: crushing particle size, sorting density, dehydration time.

[0033] Production scheduling: batch size, time window, priority.

[0034] Determine the coal quality and power-consuming equipment required for the process under the current production schedule. The coal quality-process-equipment mapping rules are shown in the following table.

[0035]

[0036] A device-level digital twin model is built based on the dynamic data of power-consuming equipment to simulate and measure the working status of the power-consuming equipment. The device-level architecture includes geometric models and physical models. The geometric model includes the 3D appearance and structural topology of the power-consuming equipment. The physical model includes the motor power mathematical equations and heat conduction equations based on the laws of physics.

[0037] Geometric modeling can use software such as SolidWorks / Blender to build a 3D appearance model of the equipment (such as a crusher, centrifugal pump), including the topological structure of key components such as bearings and gearboxes. It can also calibrate the geometric dimensions through laser scanning reverse engineering, with an error of <0.1mm. Synchronize equipment maintenance records (such as bearing replacement) to the 3D model and update the component topology.

[0038] The motor power model is the core module of the digital twin physical model. It is necessary to combine the motor's main characteristics with real-time operation data to achieve accurate energy consumption modeling. The electrical parameters collected by the motor power model include voltage U (V) and current I (A), which are collected in real time through smart meters. Mechanical parameters include speed n (rpm), which is analyzed through encoder or vibration sensor FFT, and friction coefficient k friction (N·m·s / rad²) is calibrated through no-load experiments, and the motor efficiency η is obtained through manufacturer nameplate data or IEEE112 standard testing. Electric power calculation, mechanical power correction, harmonic loss compensation, and temperature drift compensation are performed based on the collected parameters to generate the power model of the motor.

[0039] The device-level digital twin model is coupled to generate a system-level digital twin model for collaborative simulation between devices. Taking the crushing-sorting system of a coal preparation plant as an example, the crusher motor power is coupled with the centrifugal pump load torque in the energy flow, and the crushed coal block particle size distribution is coupled with the centrifugal pump processing efficiency in the material flow. In the signal flow, the vibrating screen fault signal is coupled with the feed rate of the feeder. The dynamic power balance equation of energy flow coupling is: ∑ Pinput =∑(P motor +P loss )+P conveyor +P auxiliary Among them, ∑ Pinput is the total input power of the system, is the total electrical power obtained by the entire system from the power grid or other energy sources, ∑(P motor +P loss ) is the power and loss of the main equipment, which is the sum of the energy consumption of all driving motors (such as crushers and centrifugal pumps), including effective output power and internal losses. The input power of the crusher motor = output mechanical power (driving rotor) + stator copper loss + bearing friction loss. conveyor is the conveyor system power, the total power consumed by the conveyor operation (including the energy consumption of the drive motor and mechanical loss), the input power of the belt conveyor motor + the friction loss between the belt and the roller, P auxiliary It is the power of auxiliary system, and its energy consumption of non-direct production equipment, such as control system, sensor, lighting, etc. It can be the electrical power of PLC control cabinet, dust monitor and workshop lighting system.

[0040] For the realization of collaborative simulation, time synchronization management can be achieved through hardware-level synchronization, such as using the PTP protocol to align the device model simulation clock with an error of <1ms. It can also be synchronized at the software level, defining a global simulation step (such as 10ms) in the coordinator to trigger iterative calculation of the device model. The data interaction protocol for real-time sensor data can use the MQTT protocol, and the data interaction protocol for model state parameters can be implemented through the OPCUA protocol.

[0041] According to the production schedule, local electricity prices at different times, and the charging and discharging costs of the hybrid energy storage system, the start-stop combination of power-consuming equipment, working hours, and the power of the motors of power-consuming equipment are simulated through a system-level digital twin model to find the production route with the optimal total electricity price for a single working day. The constraints include the processing volume and start-stop frequency of all power-consuming equipment in a single working day.

[0042] The method for finding the production route with the best total electricity price for a single working day can be achieved by the following method: The low-price period and peak-price period are divided into T and T' periods respectively, such as T = 8 (0:00-8:00), T' = 4 (18:00-22:00), and the duration of each period is , = 1 hour, j represents the jth period of the off-peak period, k represents the kth period of the peak period; the power-consuming devices are numbered to form a set, m is the total number of devices; let the power of the power-consuming device numbered i in the jth period be , let the power of the power consuming device numbered i in time period k be .

[0043] , Indicates whether the power-consuming device numbered i works during period j. When , it means that the power-consuming device i works in the j period during the low electricity price period. When it is on, it means that the power-consuming device i is not working; , Indicates whether the power-consuming device numbered i works in time period k. When , it means that the power consuming device i works in the k period during the peak electricity price period. When it is on, it means that the power-consuming device i is not working; Assume the off-peak electricity price is C, and the power supply cost of the energy storage system is d; the total daily electricity cost during the off-peak period is C-low:

[0044] The total cost of electricity during peak hours C-high:

[0045] Establish the objective function C-total = C-low + C-high, where C-total is the total electricity cost. According to the genetic algorithm, solve , as well as The total cost of electricity is the lowest through as well as The value determines whether the power-consuming equipment is turned on or off in each time period.

[0046] Directly use the total cost C-total as the fitness value, the smaller the better. Add the constraint violation amount to the fitness function. For example, if the processing capacity of device 1 is insufficient, add a penalty term. Solve it through genetic algorithm or particle swarm optimization. The solution steps are as follows: Initialize the population: randomly generate the start and stop status and power value of the device. Calculate the fitness. Optimize step by step through selection, crossover, and mutation until the processing capacity is met and the cost is minimized.

[0047] Optimal Solution Example Low-peak period: equipment runs at full power =50kW×8 hours, processing capacity 0.1×50×8=40 tons.

[0048] Peak hours: Equipment operation =50kW×4 hours, processing capacity 0.1×50×4=20 tons, total processing capacity 60 tons.

[0049] Total cost: 0.3×50×8+0.5×50×4=120+100=220 yuan. The off-peak motor is 0.3, and the power supply cost of the energy storage system is d=0.5.

[0050] You can also add the following constraints to solve the objective function C-total = C-low + C-high. Lsystem Value setting threshold, L system The value calculation process includes: Based on the real-time simulation computing capability of the digital twin model's digital quality process and the screening and floating data in the real-time coal quality database, the real-time processing capacity of each device and system is obtained, the optimal raw coal processing capacity of the current system is obtained, and the production efficiency of the current coal preparation plant is calculated in combination with the real-time raw coal washing capacity (real-time raw coal washing capacity / optimal raw coal processing capacity). The load rate of each device is analyzed and calculated, and the load level (low load, optimal load, high load, overload, and the values ​​can be assigned and calculated separately, such as 1, 2, 3, 4) is divided. Further, according to the equipment in each major production system (raw coal preparation system, heavy medium separation system, coarse coal slime recovery system, product transportation system, etc.) in each interval (low load, optimal load, high load, overload), the probability distribution model that the equipment obeys is determined based on the historical load state, and the equipment failure data and load abnormality data within a certain period of time are collected, such as the number of failures, failure time, average load rate value in the abnormal load interval, abnormal load duration, etc., to calculate the reliability R of a single device, R=R0(1-F); where R0 is the basic credibility, R0=e -λt, λ=failure times / unit operation time, t is equipment life; F represents the reliability attenuation factor caused by abnormal load, F=min(△L×p×k,1), k is the adjustment coefficient, which needs to be set based on experience, △L=(average load rate-rated load rate) / rated load rate, p=abnormal load duration / average failure interval time; the R value can automatically adjust the allocation weight wi of each device, and assign weight wi to each device. The allocation weight wi is positively correlated with the reliability R, that is, the higher the R, the greater the weight. Thus, the overall load rate status L of the main production system is calculated system =∑(wi×Li) and divide the load levels, Li represents the load level of the power-consuming equipment numbered i, such as 1, 2, 3, 4.

[0051] The overall load rate state of the selected coal plant is L system When the reliability is low and there is a high-load or overloaded production system, analyze the load and reliability of the equipment inside the system. If the reliability is within a credible range (such as above 70%) and the equipment load is high, the reasons for the high load (including high load and overload) and solutions can be analyzed in combination with the upstream and downstream relationships of the process and the trained online inference model.

[0052] Reliability not only reflects the stability of equipment performance, but also directly affects production efficiency, operation and maintenance costs, and energy consumption optimization. Reliability converts the equipment's operating data (number of failures, load rate, abnormal time) into a probability value, which directly reflects the current health status of the equipment. High reliability (R>0.8) equipment operates stably and is suitable for full load or overload operation. Low reliability (R<0.6): The equipment has a potential failure risk and needs to be deloaded or shut down for maintenance. By calculating reliability in real time, high-risk equipment can be identified in advance. Reliability is used as a weight factor (wi=Ri / ∑Rj, i∈j) to dynamically adjust the load distribution of the equipment in the system. High-reliability equipment is assigned more tasks to improve utilization.

[0053] Equipment with low reliability reduces load or switches to standby equipment to avoid cascading failures. High load + high reliability allows short-term overload operation to increase processing capacity. High load + low reliability forces load reduction to avoid failures. Reliability measures can directly support production efficiency improvement and cost optimization by quantifying equipment health status, guiding load distribution, and warning of potential failures. In complex industrial scenarios such as coal preparation plants, reliability calculations can significantly improve system robustness by combining digital twin models and real-time data, achieving a transformation from "post-failure repair" to "predictive maintenance," ultimately reducing energy consumption and coal processing costs per ton.

[0054] In a coal preparation plant, load refers to the workload or power demand borne by a device or system within a certain period of time, which directly affects production efficiency, energy consumption and equipment life. Equipment load refers to the actual workload of a single device during operation, usually expressed in processing capacity (such as tons / hour) or power (such as kW). The load of a crusher can be defined as the number of tons of raw coal processed per hour, or the power consumption of the motor during operation. The system load is the total workload of the entire production system (such as a heavy medium separation system), which is the superposition of the loads of multiple devices.

[0055] In a coal preparation plant, loads are usually divided into four categories according to the ratio of actual workload to rated capacity, as shown in the following table:

[0056] High / overload increases mechanical wear (such as bearing overheating and belt breakage). Excessive motor power leads to insulation aging, increased failure rate (λ), and decreased reliability (R). Frequent start and stop or idling of low-load equipment increases invalid energy consumption and shortens the life cycle.

[0057] For load level determination, an algorithm model can also be introduced for automatic determination. For the concentration system, the load level determination of the concentration system includes: The target data of the thickening system are obtained, and the target data include the current solid content of the thickener feed, the overflow turbidity of the thickener, the torque of the thickener rake, the height of the thickener coal slime layer, the underflow concentration of the thickener, the model and specification of the thickener, the number of filter presses currently in operation, and the discharge volume of the filter press.

[0058] According to historical data, the target data is cleaned. Data cleaning steps: missing value processing, delete records with a missing rate of more than 30%, and use linear interpolation or KNN interpolation to fill the remaining missing values; outlier detection, use box plots or 3σ principle to identify outliers, and correct or eliminate abnormal data in combination with process knowledge (such as a 10-fold increase in rake torque may be a sensor failure); data standardization, perform feature importance analysis on the cleaned data, and use supervised learning algorithms to give the system load level. Z-score standardization is performed on continuous variables (such as turbidity and torque), and unique hot encoding is performed on categorical variables (thickener model).

[0059] Perform feature importance analysis, retain key features (e.g., underflow concentration, rake torque, and slime layer height), and eliminate redundant features (e.g., model specifications that may have less impact due to equipment standardization).

[0060] Build a supervised learning model. Gradient boosting tree is suitable for high-dimensional data and nonlinear relationships, and supports classification tasks. Divide the data into training set and test set in a ratio of 7:3. Use grid search to optimize hyperparameters (such as learning rate and tree depth), and use 5-fold cross validation to prevent overfitting.

[0061] The load level definitions are shown in the following table:

[0062] According to the optimal production route, the start and stop time periods of the power-consuming equipment and the power of the motor are determined. According to the working time periods of the power-consuming equipment and the power of the motor, the total power consumption W during the peak power period of a working day is determined.

[0063] The energy storage capacity of the hybrid energy storage system is E=W×a / (η×DOD), where DOD is the depth of discharge, such as DOD=0.5 for lead-acid batteries and DOD=0.8 for lithium batteries. η is the charge and discharge efficiency, which requires consideration of the charging efficiency ηc and the discharge efficiency ηd, generally η=ηc×ηd. a is the redundancy factor, usually a≥1.2, and additional capacity is reserved to cope with forecast errors or sudden demands.

[0064] The peak load period when the power-consuming equipment starts and stops is predicted based on the working period of the power-consuming equipment. The peak current when the motor starts can reach 5-7 times the rated value. The battery management system turns on the supercapacitor array during the peak load period to compensate for the high-frequency power of the power-consuming equipment. The lithium battery array supplies power to the power-consuming equipment outside the peak load period. Through the coordinated control of peak load prediction and hybrid energy storage, the peak load pressure of lithium batteries can be significantly reduced, the service life can be extended, and the dynamic response performance of the system can be improved. The use of supercapacitors to compensate for instantaneous high-frequency demands and the combination of lithium batteries to provide continuous power supply form an energy management strategy that is both economical and reliable.

[0065] In some embodiments of the present application, the motor frequency of a single device can also be optimized at the device level through a device-level digital twin model.

[0066] Establish the relationship between the processing capacity and frequency of a single power-consuming device. The processing capacity is usually linearly related to the frequency (such as conveyor belt speed). Input parameters: minimum processing capacity of the production schedule, maximum processing capacity of the equipment, rated frequency and power, inverter efficiency table. Calculate the minimum frequency based on the minimum processing capacity and determine the frequency scanning range. Establish the unit energy consumption optimization objective function and solve the optimal motor frequency.

[0067] In some embodiments of the present application, the system-level digital twin model also includes a prediction model based on a Transformer-TCN hybrid architecture, which predicts the required power during the peak power period of the next working day based on input data; the input data includes the power of power-consuming equipment, raw coal screening floating data, sorting process time series data, power-consuming equipment working temperature and humidity, vibration signals, health assessment indicators, production shifts, production targets, and equipment start-stop plans. The Transformer-TCN hybrid architecture includes a Transformer layer and a TCN layer. The Transformer layer is used to capture the long-term dependencies of load data, and the TCN layer extracts local time series features through causal convolution and hole convolution; the non-stationary load signal of the input data is decomposed by variational mode decomposition, and the modal components of different frequency bands are extracted to reduce noise interference and enhance feature interpretability. The time series feature matrix is ​​generated by Z-score standardization and sliding window technology. The model is trained using historical data and combined with transfer learning to improve the generalization ability in small sample scenarios. Adversarial training (GAN) is introduced to generate extreme working condition data (such as equipment failure and coal quality mutation) to enhance the robustness of the model. When the actual load deviates from the forecasted load by more than the threshold, the LSTM error correction module is triggered to adjust the forecast model parameters online. For example, when a sudden change in coal quality during the previous day’s production process causes a sudden increase in the load of the sorting machine, the digital twin instantly generates simulation data, updates the forecast results, and adjusts the amount of stored electricity for the next working day.

[0068] The prediction model based on the Transformer-TCN hybrid architecture achieves high-precision peak power demand prediction by integrating long-term dependencies and local time series features, combined with VMD signal decomposition and dynamic feature engineering. The model deeply integrates equipment health and process data, providing coal preparation plants with a full-chain solution from power forecasting to scheduling optimization, significantly reducing energy consumption and operating costs, and promoting intelligent upgrades.

[0069] The hybrid energy storage system stores electric energy when the electricity price is low, and releases excess electric energy by connecting to the grid at the peak. The grid power electronic interface also includes a virtual synchronous generator, which is used to simulate the rotor of the synchronous generator of the grid system. The grid operation status is acquired in real time to determine whether the grid frequency change reaches the threshold. When the set threshold is reached, the virtual synchronous generator simulates the inertial response of the synchronous generator of the grid system, dynamically adjusts the inertia of the virtual generator to delay the frequency change, calculates the power of the virtual generator based on the frequency deviation and the adjusted inertia, and adjusts the power distribution of the virtual synchronous generator corresponding to the battery array based on the health of the battery array in the hybrid energy storage system.

[0070] Dynamic variable inertia VSG control solves the problem that fixed inertia cannot take into account both fast response and stability by adjusting the virtual inertia J(t) in real time. According to the frequency deviation Δf(t) and its change rate dΔf / dt, the inertia is adjusted in two stages:

[0071] in, is the minimum inertia (typical value ), used to ensure the basic inertia, is the maximum inertia (typical value ), used to limit response delay, For the adjustment factor (calibrated by HIL test, it is recommended ), Example: When detected and hour, .

[0072] Dynamic variable inertia VSG control is a control strategy used to improve the stability of power grid systems. It monitors the changes in grid frequency in real time and dynamically adjusts the inertia value of the system according to the deviation of grid frequency and its rate of change. This control method can solve the problem that fixed inertia value cannot guarantee fast response and system stability at the same time. Glossary: ​​1. Dynamic variable inertia: refers to the dynamic adjustment of inertia value according to real-time data during system operation. Inertia is a physical quantity that measures the system's resistance to speed changes. In power systems, the size of inertia affects the response speed and stability of the system. 2. VSG control: The abbreviation of Virtual Synchronous Generator Control, which is a control strategy used to simulate the behavior of traditional synchronous generators to improve the stability and controllability of distributed power generation systems. 3. Grid frequency deviation: refers to the difference between the actual operating frequency of the grid and the standard frequency (such as 50Hz or 60Hz). Excessive grid frequency deviation may affect the stable operation of the power system. 4. Inertia value J(t): In dynamic variable inertia VSG control, the inertia value J(t) is calculated in real time based on the grid frequency deviation, and it changes with the change of grid operation status. 5. Adjustment coefficient : The adjustment coefficients are used to control the calculation method of the inertia value J(t). They are calibrated through experiments or simulations (HIL tests) to achieve the best control effect.

[0073] For small deviation stages (≤0.5Hz), gradually increase inertia, suppress frequency fluctuations, and improve stability. For large deviation stages (>0.5Hz), dynamically reduce inertia through the rate of change, accelerate power response, and avoid frequency collapse. It is simple and easy to implement, requiring only frequency deviation and its rate of change as input, with low computational complexity, and is suitable for real-time control.

[0074] Deep charging and discharging improves revenue but damages life. Battery SOC (State of Charge) and SOH (State of Health) are two important parameters for evaluating battery performance and life. By regularly testing the battery's SOH, the battery's SOC usage range is adjusted according to the test results to optimize the battery's life and revenue. Specifically, if the battery's SOH is lower than 80%, it is necessary to reduce the battery's discharge depth, that is, set a higher SOC minimum value to protect the battery. Glossary: ​​1. Battery SOC: SOC refers to the current state of charge of the battery, usually expressed as a percentage. It reflects the amount of remaining battery power and is one of the key parameters in the battery management system. 2. Battery SOH: SOH refers to the battery's health state, which reflects the battery's performance and aging. A decrease in SOH means a decrease in battery capacity and a shortened life. 3. Deep charging and discharging: refers to charging and discharging the battery to a state close to full charge or fully discharged. Although deep charging and discharging can improve the battery's use revenue in the short term, it will accelerate battery aging and reduce battery life in the long run.

[0075] Harmonic suppression is performed through virtual resistance. The specific steps are to measure the system resonance point offline (such as FFT analysis), design a virtual resistance transfer function with passband characteristics, and inject the virtual resistance transfer function into the VSG current loop feedforward to suppress harmonics by increasing damping, but it will reduce the efficiency of the system. It includes several key steps: first measure the resonance point of the system, then design a specific virtual resistance transfer function, and finally inject this function into the current loop of the voltage source inverter (VSG). The transfer function is as follows:

[0076] Where Rvirtual(s) represents the dynamic impedance value of the virtual resistor in the complex frequency domain. is the target resonant frequency (such as 250Hz), ζ is the damping ratio (recommended 0.7~1.0), K: gain coefficient (determined by frequency sweep test), and s is a complex frequency variable. Related keyword analysis: 1. Virtual resistance: Virtual resistance is a way to simulate the characteristics of resistance in power electronic systems to control or suppress specific electrical phenomena, such as harmonics. 2. Harmonic suppression: Harmonic suppression refers to the technology of reducing or eliminating the distortion of current or voltage waveforms caused by nonlinear loads in power systems. 3. FFT analysis: Fast Fourier Transform (FFT) is an algorithm used to convert signals from the time domain to the frequency domain to analyze the frequency components in the signal. 4. Bandpass characteristics: Bandpass characteristics refer to a system or device that has a good transmission capability for signals within a certain frequency range, while having a large attenuation for signals outside this range. 5. VSG current loop feedforward injection: VSG refers to a virtual synchronous generator, and current loop feedforward injection refers to the direct addition of control signals to the current control loop to improve the dynamic response and stability of the system.

[0077] Based on the same inventive concept, an embodiment of the present application also discloses a coal plant energy storage method, which adopts the above-mentioned digital twin-based coal preparation plant energy storage system.

[0078] Corresponding to the above method, the embodiment of the present disclosure also provides an electronic device, such as Figure 4 As shown, it is a schematic diagram of the structure of an electronic device 400 provided in an embodiment of the present disclosure, including: a processor 41, a memory 42, and a bus 43; the memory 42 is used to store execution instructions, including a memory 421 and an external memory 422; the memory 421 here is also called an internal memory, which is used to temporarily store the operation data in the processor 41, and the data exchanged with the external memory 422 such as a hard disk. The processor 41 exchanges data with the external memory 422 through the memory 421. When the electronic device 400 is running, the processor 41 communicates with the memory 42 through the bus 43, so that the processor 41 executes Figure 1 The communication interface is used for communication between the above electronic device and other devices.

[0079] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0080] The present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the energy storage method described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0081] The disclosed embodiments also provide a computer program product, which includes computer instructions. When the computer instructions are executed by a processor, the steps of the drone intelligent airport deployment method described in the above method embodiment can be executed. For details, please refer to the above method embodiment, which will not be repeated here.

[0082] Those skilled in the art will appreciate that the embodiments in the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments in the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments in the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0083] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0084] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

Claims

1. A coal preparation plant energy storage system based on digital twins, including a hybrid energy storage system, a battery management system, a high-voltage DC protection system, a pre-charge / discharge circuit, a high-voltage AC power distribution system, a centralized PCS cluster, and a power grid power electronic interface. The hybrid energy storage system is connected to power-consuming equipment in the coal preparation plant, and includes a lithium battery array and a supercapacitor array, characterized in that: Also includes: Build a device-level digital twin model based on the dynamic data of power-consuming devices and couple it to generate a system-level digital twin model. According to the production schedule, local electricity prices at different times, and the charging and discharging costs of the hybrid energy storage system, the start-stop combination of power-consuming equipment, working hours, and the power of the motors of power-consuming equipment are simulated through the system-level digital twin model to find the production route with the optimal total electricity price for a single working day. The constraints include the processing volume and start-stop frequency of all power-consuming equipment in a single working day. According to the optimal production route, determine the start and stop time of power-consuming equipment and the power of the motor, Determine the energy storage capacity of the hybrid energy storage system according to the working period of the power-consuming equipment and the power of the motor; The peak load period when the power-consuming equipment starts and stops is predicted according to the working period of the power-consuming equipment. The battery management system turns on the supercapacitor array during the peak load period to perform high-frequency power compensation for the power-consuming equipment. The lithium battery array supplies power to the power-consuming equipment during periods other than the peak load period.

2. The digital twin-based coal preparation plant energy storage system according to claim 1 is characterized in that: The method for finding the production route with the best total electricity price for a single working day includes: The low-price period and peak-price period are divided into T and T' periods respectively, and the duration of each period is , j represents the jth period during the trough period, and k represents the kth period during the peak period; The power-consuming devices are numbered to form a set, where m is the total number of devices; Assume that the power consumption of the power consumption device numbered i in period j is expressed as , let the power of the power consuming device numbered i in time period k be expressed as , , Indicates whether the power-consuming device numbered i works during period j. When , it means that the power-consuming device i works in the j period during the low electricity price period. When it is on, it means that the power-consuming device i is not working; , Indicates whether the power-consuming device numbered i works in time period k. When , it means that the power consuming device i works in the k period during the peak electricity price period. When it is on, it means that the power-consuming device i is not working; Assume the off-peak electricity price is C, and the power supply cost of the energy storage system is d; the total daily electricity cost during the off-peak period is C-low: The total cost of electricity during peak hours C-high: Establish the objective function C-total = C-low + C-high, where C-total is the total electricity cost. According to the genetic algorithm, solve , as well as The total cost of electricity is the lowest through as well as The value determines whether the power-consuming device is turned on or off in each time period.

3. The digital twin-based coal preparation plant energy storage system according to claim 2 is characterized in that: The calculation method of the energy storage capacity of the hybrid energy storage system includes: According to the optimal production route, the start and stop time periods of the power-consuming equipment and the power of the motor are determined. According to the working time periods of the power-consuming equipment and the power of the motor, the total power consumption W during the peak power period of a working day is determined. The energy storage capacity of the hybrid energy storage system is E=W×a / (η×DOD), where DOD is the depth of discharge, η is the charge and discharge efficiency, and a is the redundancy coefficient.

4. The digital twin-based coal preparation plant energy storage system according to claim 1 is characterized in that: The constraint condition also includes the overall load rate state of the power consuming equipment Lsystem value reaches the set threshold, the L system The value calculation process includes: Obtain the load rate of power-consuming equipment, divide the load level, and determine the probability distribution model of the load of power-consuming equipment based on the load level of the power-consuming equipment and the historical load status of the equipment, and determine the reliability R of the power-consuming equipment. Reliability R is a measure of the probability that the power-consuming equipment can complete the expected function without failure under specific conditions and within a specified time. According to the obtained R value, adjust the load allocation weight wi of each power-consuming equipment and calculate the overall load rate status of all power-consuming equipment Lsystem =∑(wi×Li), Li represents the load level of the power-consuming equipment numbered i.

5. The digital twin-based coal preparation plant energy storage system according to claim 4 is characterized in that: The reliability R=R0(1-F), where R0 is the basic credibility, R0=e -λt , λ=failure times / unit operation time, t is the equipment life; F represents the reliability attenuation factor caused by abnormal load, F=min(△L×p×k,1), k is the adjustment coefficient, △L=(average load rate-rated load rate) / rated load rate, p=abnormal load duration / mean failure interval time.

6. The digital twin-based coal preparation plant energy storage system according to claim 5 is characterized in that: The allocation weight wi is positively correlated with the reliability R, that is, the higher the R, the greater the weight.

7. The digital twin-based coal preparation plant energy storage system according to claim 4 is characterized in that: The power consuming equipment includes a concentration system, and the load level determination of the concentration system includes: Obtain the target data of the thickening system, including the current solid content of the thickener feed, the overflow turbidity of the thickener, the torque of the thickener rake, the height of the thickener coal slime layer, the underflow concentration of the thickener, the model and specification of the thickener, the number of filter presses currently in operation, and the discharge volume of the filter press. Based on historical data, the target data is cleaned, feature importance analysis is performed on the cleaned data, and the system load level is given using a supervised learning algorithm.

8. The digital twin-based coal preparation plant energy storage system according to claim 1, characterized in that: The system-level digital twin model also includes a prediction model based on the Transformer-TCN hybrid architecture, which predicts the power required during the peak power period of the next working day based on input data; the input data includes the power of power-consuming equipment, raw coal screening floating and sinking data, sorting process time series data, power-consuming equipment working temperature and humidity, vibration signals, health assessment indicators, production shifts, production targets, and equipment start and stop plans; The Transformer-TCN hybrid architecture includes a Transformer layer and a TCN layer, wherein the Transformer layer is used to capture the long-term dependency of load data, and the TCN layer extracts local temporal features through causal convolution and dilated convolution; The non-stationary load signal of the input data is decomposed through variational modal decomposition, the modal components of different frequency bands are extracted, the noise interference is reduced and the feature interpretability is enhanced, and the time series feature matrix is ​​generated through Z-score standardization and sliding window technology.

9. The digital twin-based coal preparation plant energy storage system according to claim 1, characterized in that: The hybrid energy storage system stores electric energy when electricity prices are low, and is connected to the power grid to release excess electric energy during peak times. The power grid power electronic interface also includes a virtual synchronous generator, which is used to simulate the rotor of the synchronous generator of the power grid system. The power grid operation status is acquired in real time to determine whether the power grid frequency change reaches a threshold. When the set threshold is reached, the virtual synchronous generator simulates the inertial response of the synchronous generator of the power grid system, dynamically adjusts the inertia of the virtual generator to delay the frequency change, calculates the power of the virtual generator based on the frequency deviation and the adjusted inertia, and adjusts the power distribution of the virtual synchronous generator corresponding to the battery array based on the health status of the battery array in the hybrid energy storage system.

10. A coal preparation plant energy storage method, characterized in that: A coal preparation plant energy storage system based on digital twin as described in any one of claims 1 to 9 is adopted.

Images