Method, apparatus, device, and medium for visualizing energy efficiency of digital drive train
Patent Information
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- SIEMENS AG
- Filing Date
- 2023-09-28
- Publication Date
- 2026-06-24
Smart Images

Figure CN2023122886_03042025_PF_FP_ABST
Abstract
Description
Method, apparatus, device, and medium for visualizing energy efficiency of digital drive trainFIELD
[0001] The present invention relates to the technical field of digital drive train, in particular to a method, apparatus, device, and medium for visualizing energy efficiency of digital drive train.BACKGROUND
[0002] Energy consumption is expanding in recent years across the world. The total world energy consumption has gone through a significant growth to 580 terajoules in 2022 and is expected to keep increasing in the coming year. However, conventional energy sources are limited, and we are still experiencing the global energy crisis, with shortage in oil and gas. Efforts are being made to tackle the problem, which can be divided into pursuing two targets. One is to develop other sustainable alternatives such as wind power and nuclear power. The other lies in optimizing the way energy are used, namely increasing the efficiency.
[0003] Industry in many countries still has the feature as energy-intensive. As estimated, the industrial sector accounted for 55%total energy consumption in the world. Increasing awareness on environmental problems related to electricity production imposes a cap on energy consumption.
[0004] Integrated the crucial components and power the facilities, digital drive train converts electricity into mechanical energy, in which motor takes up about 70%of industrial electricity consumption. Therefore, improvement in energy efficiency of the drive train is clearly necessary.SUMMARY
[0005] Embodiments of the present invention propose a method, apparatus, device, and medium for visualizing energy efficiency of digital drive train.
[0006] In a first aspect, a method for visualizing energy efficiency of digital drive train is provided. Components of the digital drive train comprise a variable-frequency drive, a motor and an application device, the method comprising. The method comprising:
[0007] acquiring a model of the digital drive train;
[0008] acquiring a real-time control parameter of the variable-frequency drive;
[0009] inputting the real-time control parameter into the model;
[0010] receiving a predicted output power of at least one component of the digital drive train from the model; and
[0011] displaying a predicted energy efficiency of the at least one component based on the predicted output power in a visual interface.
[0012] In a second aspect, an apparatus for visualizing energy efficiency of digital drive train is provided. Components of the digital drive train comprise a variable-frequency drive, a motor and an application device The apparatus comprising:
[0013] a first acquiring module, configured to acquire a model of the digital drive train;
[0014] a second acquiring module, configured to acquire a real-time control parameter of the variable-frequency drive;
[0015] an inputting module, configured to input the real-time control parameter into the model; and
[0016] a receiving module, configured to receive a predicted output power of at least one component of the digital drive train from the model; and
[0017] a displaying module, configured to display a predicted energy efficiency of the at least one component based on the predicted output power in visual interface.
[0018] In a third aspect, an electronic device is provided. The electronic device comprising a processor and a memory, wherein an application program executable by the processor is stored in the memory for causing the processor to execute a method for visualizing energy efficiency of digital drive train as described in any of the above.
[0019] In a fourth aspect, a computer-readable medium comprising computer-readable instructions stored thereon is provided, wherein the computer-readable instructions, when executed by a processor, implement a method for visualizing energy efficiency of digital drive train as described in any of the above.
[0020] In a fifth aspect, a computer program product comprising a computer program, when the computer program is executed by a processor for executing a method for visualizing energy efficiency of digital drive train as described in any of the above.
[0021] According to the above technical solutions, developed visualization interface makes the data and analytics transparent, saving time and effort of the operator for checking abnormalities and providing guidance for future planning and decisions.BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to make technical solutions of examples of the present disclosure clearer, accompanying drawings to be used in description of the examples will be simply introduced hereinafter. Obviously, the accompanying drawings to be described hereinafter are only some examples of the present disclosure. Those skilled in the art may obtain other drawings according to these accompanying drawings without creative labor.
[0023] Fig. 1 is a flowchart of a method for visualizing energy efficiency of digital drive train according to an embodiment of the present invention.
[0024] Fig. 2 is a first schematic diagram of digital drive train model according to an embodiment of the present invention.
[0025] Fig. 3 is a second schematic diagram of digital drive train model according to an embodiment of the present invention.
[0026] Fig. 4 is a schematic diagram of visualization process and optimization process of digital drive train according to an embodiment of the present invention.
[0027] Fig. 5 is a schematic diagram of diagnosis workflow of energy consumption and efficiency according to an embodiment of the present invention.
[0028] Fig. 6 is a schematic diagram showing the power loss of digital drive train according to an embodiment of the present invention.
[0029] Fig. 7 is a structural diagram of an apparatus for visualizing energy efficiency of digital drive train according to an embodiment of the present invention.
[0030] Fig. 8 is a structural diagram of an electronic device according to an embodiment of the present invention.
[0031] List of reference numbers: DETAILED DESCRIPTION
[0032] In order to make the purpose, technical scheme, and advantages of the invention clearer, the following examples are given to further explain the invention in detail.
[0033] In order to be concise and intuitive in description, the scheme of the invention is described below by describing several representative embodiments. Many details in the embodiments are only used to help understand the scheme of the invention. However, it is obvious that the technical scheme of the invention can be realized without being limited to these details. In order to avoid unnecessarily blurring the scheme of the invention, some embodiments are not described in detail, but only the framework is given. Hereinafter, "including" refers to "including but not limited to" , "according to... " refers to "at least according to..., but not limited to... " . When the number of an element is not specifically indicated below, it means that the element can be one or more, or can be understood as at least one.
[0034] After research, it has been found that there are at least the following technical problems in the existing technology:
[0035] Technical problem 1: The prior art mainly focuses on the whole plant, and suggestions are made based on the value of the products produced or cost in the process. Few studies consider the mechanical and electrical characters of the drive train.
[0036] Technical problem 2: The prior art on the efficiency in industry is not able to establish a robust evaluation model considering the differences in end user equipment. For example, the U.S. Department of Energy’s Industrial Technologies Program offers the pumping System Assessment Tool, which can only identify the current running status of the pumping system.
[0037] Technical problems 3: Despite progresses made in finding the optimal parameters in drive train, lack of visualization tool leads to the fact that the data are not transparent to the users and cannot help them to make decisions to improve drive train energy efficiency.
[0038] Therefore, a tool that integrated analytics, diagnosis, optimization, and visualization of complete drive train is in need.
[0039] The prior art on energy efficiency of drive train usually considers the inner structure of the motor, and few of them consider the dynamic feature of the external load. Others placed the drive train in a restricted application scenario, drive train inside vehicles and trains is a preferred research field. Specific end user equipment and their key energy consumption mode is studied.
[0040] Traditional method 1: Energy efficiency of motors in drive train
[0041] Motors are the convertor in the drive train, transmitting electricity input to torque output. Traditional evaluation approaches of motor energy efficiency include nameplate method, differential rate method, current method, statistical method, equivalent circuit method and loss analysis method. However, since they rely on some technical manuals and empirical parameters, they are not accurate. These methods also interrupt operation. P. Pillay et al. created a way using genetic algorithm (GA) for online identification of some unavailable parameters. Gomaa F. Abdelnaby et al. proposed a controller for senseless speed control of Permanent Magnet Synchronous Motor (PMSM) using PI controller and fuzzy control. A motor system failure diagnosis and efficiency monitoring software are developed by Chong Liu, in which the power factor, current and torque are measured. These methods are suitable for measuring the Energy efficiency of motor alone, and do not consider the load type.
[0042] Traditional method 2: Energy efficiency of drive trains in vehicles and trains
[0043] An important topic of drive train efficiency is its performance in vehicles. Jorge O. Estima et al. studied two topology drive train traction of electrical and hybrid vehicles, which comprises Pulse Width Modulation (PWM) inverter and connects to a PMSM, with a special focus of energy efficiency and under different modes and applied variable-voltage control strategy. Similarly, Sheldon S. Williamson et al. proposed efficiency map of the invertor and traction motor in hybrid electric vehicle (HEV) and fuel cell vehicle (FCV) . Agostinho Rocha et al. proposes a simulated annealing optimization algorithm that minimizes train traction energy. These methods are limited in analyzing drive train in vehicle or train context.
[0044] Traditional method 3: Energy efficiency of specific user equipment
[0045] System efficiency of drive train with user equipment has not aroused much attention yet. Xun Wang developed a portable fan efficiency online test system based on equivalent circuit model. Yan Qiu Du et al. optimizes a circulating water system of a thermal power plant by adding a variable frequency control and calculating the best frequency. These methods are applicable for specific end users.
[0046] However, there are drawbacks for the above methods, specifically. Limitation 1: A general motor efficiency analytic algorithm is not established. Limitation 2: A system integrated different speed control methods in variable frequency is in need, including the v / f control, vector control and slip control. Limitation 3: Problems of dynamic load and multi drive train system in industry application are to be solved. Limitation 4: Few studies consider the variety of end user and are only applicable to specific equipment, which makes it difficult for scale up.
[0047] Embodiments of the present invention provide a method to evaluate and optimize energy consumption for drive train with different applications (e.g., fan, water pump, compressor) . According to OEM and end user key energy consumption equipment, it makes accurate analytics and diagnosis, helping to identify energy loss saving potential and intelligently optimize the complete drive train energy efficiency. With the help of intelligent terminal (e.g., IoT 2050, edge device, IPC nano, etc. ) , transparency and optimization are realized for single and multi-drive train according to the applications. The control signal is then transmitted to the drive and the motor, helping to optimize drive train energy efficiency and performance.
[0048] Fig. 1 is a flowchart of a method for visualizing energy efficiency of digital drive train according to an embodiment of the present invention. Components of the digital drive train comprise a variable-frequency drive, a motor and an application device. As shown in Figure 1, the method comprises:
[0049] Step 101: acquiring a model of the digital drive train.
[0050] In one embodiment, acquiring a model of the digital drive train comprises: determining a mechanism model of the variable-frequency drive, a mechanism model of the motor, and a mechanism model of the application device through mechanism modeling; combining the mechanism model of the variable-frequency drive, the mechanism model of the motor, and the mechanism model of the application device to generate a mechanism model of the digital drive train.
[0051] Step 102: acquiring a real-time control parameter of the variable-frequency drive.
[0052] The control parameter comprises at least one of the following: r65: Slip frequency / f_Slip; r66: Output frequency / f_outp; r1337: Actual slip compensation / Slip comp act val; r1770: Motor model speed adaptation proportional component / MotMod n_adapt Kp; r0063_1: Actual slip compensation / Slip comp act val; r0063_2: Actual slip compensation / Slip comp act val; r21: Speed actual value, smoothed; r24: output frequency, smoothed; r25: CO: Output voltage, smoothed; r27: Absolute current actual value, smoothed; r29: current actual value Field-generating, smoothed; r30: current actual value Torque-generating, smoothed; r31: torque actual value, smoothed; r32: active power actual value, smoothed; r62: frequency setpoint after the filter; r87: power factor actual value; r39_0: Energy consumption total; r39_1: Energy received; r39_2: Energy feedback; r41: Energy consumption saved; r83: Flux setpoint; r84: Flux actual value; r1598: Total flux setpoint; r1348: U / f control Eco factor actual value; r26: DC link voltage smoothed; r1315: U / f control Eco factor actual value; r1337: U / f control Eco factor actual value; r1310: U / f control Eco factor actual value; r1311: U / f control Eco factor actual value; r1312: U / f control Eco factor actual value.
[0053] The above exemplary description provides typical examples of control parameters, and those skilled in the art may realize that this description is exemplary and not intended to limit the scope of protection of the present invention's implementation methods.
[0054] In one embodiment, acquiring a model of the digital drive train comprises: determining a training sample, which comprises a historical value of the control parameter of the variable-frequency drive, wherein a label set of the training sample includes a historical output power of the variable-frequency drive corresponding to the historical value, a historical output power of the motor corresponding to the historical value, and a historical output power of the application device corresponding to the historical value; inputting the training sample into a neural network model to receive a predicted output power set from the neural network model, which includes a predicted output power of the variable-frequency drive, a predicted output power of the motor, and a predicted output power of the application device; determining a loss function value based on a difference between the predicted output power set and the label set; configuring model parameters of the neural network model to make the loss function value lower than a preset threshold; determining the configured neural network model as an artificial intelligence model of the digital drive train.
[0055] Fig. 2 is a first schematic diagram of digital drive train model according to an embodiment of the present invention.
[0056] In Figure 2, training sample 11 is inputted into a neural network model 20. The training sample 11 includes a value of a historical control parameter of the variable-frequency drive and label set. The label set includes: (1) output power of variable-frequency drive corresponding to the value of historical control parameter; (2) output power of motor corresponding to the value of historical control parameter; (3) output power of application device corresponding to the value of historical control parameter. Neural network model 20 outputs a predicted output power set which includes predicted output power of the variable-frequency drive, predicted output power of the motor, and predicted output power of the application device. Determining a loss function value based on a difference between the predicted output power set and the label set, configuring model parameters of the neural network model 20 to make the loss function value lower than a preset threshold, and determining the configured neural network model 20 as an artificial intelligence model of the digital drive train.
[0057] In one embodiment, acquiring a model of the digital drive train comprises: determining a first training sample, which comprises a first historical value of the control parameter of the variable-frequency drive, wherein a label of the first training sample comprises a historical output power of the variable-frequency drive corresponding to the first historical value; inputting the first training sample into a first neural network model to receive a predicted output power of the variable-frequency drive from the first neural network model; determining a first loss function value based on a first difference between the predicted output power of the variable-frequency drive and the label of the first training sample; configuring model parameters of the first neural network model to make the first loss function value lower than a preset first threshold; determining the configured first neural network model as an artificial intelligence model of the variable-frequency drive.
[0058] In one embodiment, acquiring a model of the digital drive train comprises: determining a second training sample, which comprises a second historical value of the control parameter of the variable-frequency drive, wherein a label of the second training sample comprises a historical output power of the motor corresponding to the second historical value; inputting the second training sample into a second neural network model to receive a predicted output power of the motor from the second neural network model; determining a second loss function value based on a second difference between the predicted output power of the motor and the label of the second training sample; configuring model parameters of the second neural network model to make the second loss function value lower than a preset second threshold; determining the configured second neural network model as an artificial intelligence model of the motor.
[0059] In one embodiment, acquiring a model of the digital drive train comprises: determining a third training sample, which comprises a third historical value of the control parameter of the variable-frequency drive, wherein a label of the third training sample comprises a historical output power of the application device corresponding to the third historical value; inputting the third training sample into a third neural network model to receive a predicted output power of the application device from the third neural network model; determining a third loss function value based on a third difference between the predicted output power of the application device and the label of the third training sample; configuring model parameters of the third neural network model to make the third loss function value lower than a preset third threshold; determining the configured third neural network model as an artificial intelligence model of the application device.
[0060] Fig. 3 is a second schematic diagram of digital drive train model according to an embodiment of the present invention.
[0061] In Figure 3, artificial intelligence model 30 of the digital drive chain includes first neural network model 37 of the variable-frequency drive, second neural network model 38 of the motor, and third neural network model 39 of the application device.
[0062] First training sample 31 is inputted into first neural network model 37. First training sample 31 includes a value of historical control parameter of the variable-frequency drive and a label. The label comprises historical output power of the variable-frequency drive corresponding to the value of historical control parameter. Receiving predicted output power 32 of variable-frequency drive from the first neural network model 37, determining a first loss function value based on a first difference between the predicted output power 32 and the label of the first training sample 31, configuring model parameters of the first neural network model 37 to make the first loss function value lower than a preset first threshold, and determining the configured first neural network model 37 as an artificial intelligence model of the variable-frequency drive.
[0063] Second training sample 33 is inputted into second neural network model 38. Second training sample 33 includes a value of historical control parameter of the variable-frequency drive and a label. The label comprises historical output power of the motor corresponding to the value of historical control parameter. Receiving predicted output power 34 of motor from the second neural network model 38, determining a second loss function value based on a second difference between the predicted output power 34 and the label of the second training sample 33; configuring model parameters of the second neural network model 38 to make the second loss function value lower than a preset second threshold; determining the configured second neural network model 38 as an artificial intelligence model of the motor.
[0064] Third training sample 35 is inputted into third neural network model 39. Third training sample 35 includes a value of historical control parameter of the variable-frequency drive and a label. The label comprises historical output power of the application device corresponding to the value of historical control parameter. Receiving predicted output power 36 of application device from the third neural network model 39, determining a third loss function value based on a third difference between the predicted output power 36 and the label of the third training sample; configuring model parameters of the third neural network model 39 to make the third loss function value lower than a preset third threshold; determining the configured third neural network model 39 as an artificial intelligence model of the application device.
[0065] Combining the artificial intelligence model 37 of the variable-frequency drive, the artificial intelligence model 38 of the motor, and the artificial intelligence model 39 of the application device to generate an artificial intelligence model 30 of the digital drive train.
[0066] Step 103: inputting the real-time control parameter into the mode.
[0067] Step 104: receiving a predicted output power of at least one component of the digital drive train from the model.
[0068] Step 105: displaying a predicted energy efficiency of the at least one component based on the predicted output power in a visual interface.
[0069] For example, dividing the predicted output power by the total consumed power of the at least one component can obtain the predicted energy efficiency. The total power consumption of the at least one component can be measured using a power meter.
[0070] In one embodiment, the method comprising: issuing an alarm message when the energy efficiency falls below a predetermined threshold, wherein the threshold comprises at least one of the following: experience value; average energy efficiency of the at least one component within a predetermined time.
[0071] In one embodiment, the method comprising: determining a real-time actual energy efficiency of the at least one component; determining an energy efficiency potential of the at least one component based on the difference between the predicted energy efficiency and the real-time actual energy efficiency; adjusting the real-time control parameter of the variable-frequency drive based on the energy efficiency potential.
[0072] In one embodiment, the application device comprises a pump; the method comprises: calibrating a fluid characteristic curve of the pump based on the real-time control parameter of the variable-frequency drive, updating the mechanism model of the pump based on the calibrated fluid characteristic curve.
[0073] Fig. 4 is a schematic diagram of visualization process and optimization process of digital drive train according to an embodiment of the present invention.
[0074] In Figure 4, the digital drive chain includes IOT2050 device 54, PLC53, variable-frequency drive 50, motor 51, and application device 52. The application device 52 can be a single device or multiple devices. When the application device is a single device, a single digital drive chain 80 is formed. When the application device is multiple devices, multiple digital drive chains 81 are formed. The application device 52 can include pumps, fans, and so on.
[0075] The main functionalities can be described as following 2 parts:
[0076] Energy Efficiency Transparency 60: In the transparency stage, accurate diagnosis 63 is made, helping to inform power demand and abnormal energy detection. Firstly, the energy consumption and efficiency related data is acquired, and parameters are visualized in visualization process 61. Then, the efficiency of the whole drive train is analyzed in energy efficiency analytics 62, and finally diagnosis 63 is given.
[0077] Energy Efficiency Optimization 70: To evaluate and optimize the energy consumption for different applications include pump, fan, and compressor, the toolbox can calculate the efficiency improvement potential, get the optimal PDS parameters 73 (e.g., default value setting algorithm or model identification, PID adaptive tuning for vector control) . In multi-pump scenarios, performance curves are used to achieve optimal control 74.
[0078] As a result, the minimum energy consumption goal is achieved with implementation of optimization approach: The inverter parameters optimization leads to desirable response of aggregates. Torque and speed oscillation is removed via continuous data identification and fuzzy control, which ensures steady operation. The drive train can tackle dynamic load because the parameters are optimized with continuous identification. Online data is used in continuous adaption in deciding the parameter of V / f control. The fluid characteristic curve can be accurately represented via continuous adaptation using online data. Moreover, several applications based on the functions are analyzed in detail, which also unveil the technical features:
[0079] Efficiency Analytics of Drive Trains:
[0080] Technical feature 1: Embodiments of the present invention make the operation efficiency of each part of the drive trains transparent under different load differences and give a quantitative tracking of the energy losses.
[0081] Under different load conditions of drive train, the operating efficiency of each component in the transmission system lacks quantitative tracking of energy loss, leading to opacity. To improve energy transparency and provide optimization directions for overall system efficiency, the variable-frequency drive, motor and pump efficiency under different load conditions can be automatically identified, and the energy loss of each component can be calculated and displayed in real time using variable-frequency drive, motor and pump efficiency models and power consumption models, as shown in Fig 6. Fig. 6 is a schematic diagram showing the power loss of digital drive train according to an embodiment of the present invention.
[0082] In Figure 6, it is shown in a visualization interface that the total power is 80, and the power after passing through variable-frequency drive 41 is 77. Therefore, the power loss of frequency converter 41 is 3. Similarly, power loss of motor 42 is 6, power loss of pump 43 is 10, power loss of throttle value 44 is 0, and power loss of other components is 27.
[0083] Diagnosis of Energy Consumption and Efficiency:
[0084] Technical feature 2: Energy efficiency potential are detected, and corresponding implementation suggestions are proposed automatically.
[0085] The detection of energy efficiency potential in conventional digital drive systems relies on operator inspection. By analyzing current and predicted data and forecasting energy consumption and efficiency with historical data, energy efficiency potential can be automatically detected, and practical suggestions based on practice can be offered to help users to reduce energy loss and save energy consumption, as shown in Fig 5.
[0086] Fig. 5 is a schematic diagram of diagnosis workflow of energy consumption and efficiency according to an embodiment of the present invention. In Figure 5, historical data 92 (such as energy consumption and efficiency) is inputted in forecast algorithm 90 to output predicted data, such as predicted energy consumption and predicted efficiency. The predicted data and current data 93 are inputted in diagnosis module 91 to output diagnosis result 94. Forecast algorithm 90 is calibrated in model calibration process 95 by comparing the difference between actual data and predicted data,
[0087] Embodiments of the present invention use a speed control mode that can improve energy efficiency and implement the process-specific flow rate. The entire plant characteristic is shifted by the speed controller to achieve the required flow rate. Traditional fluid characteristic curve control methods face challenges in accurately converting the pump's performance curve into inverter setting parameters, and the five parameters of the full scale are often insufficient to reflect the fluid. To accurately reflect the load change, the fluid characteristic curve can be corrected in combination with actual speed, torque, power unit overload I2t, current and voltage signals, and the distribution of five parameter sets can be adaptively adjusted based on process information or data analysis of the load change range over a period.
[0088] In summary, embodiments of the present invention has at least the following advantages:
[0089] Advantage 1: The invention enables an online data analysis and optimization combined with historical data and uses an adaptive algorithm to deal with dynamic load and multi-drive system, which is suitable for practice and can help the users to meet governmental requirements, ensure future operation, save running costs, and improve competitiveness.
[0090] Advantage 2: Developed visualization interface makes the data and analytics transparent, saving time and effort of the operator for checking abnormalities and providing guidance for future planning and decisions.
[0091] Advantage 3: The user could one-button click to realize energy efficiency optimization and no need to understand the domain know-how for complete drive train in advance. The method could identify the gap and potential automatically.
[0092] Advantage 4: Embodiments of the present invention mainly involves several data analytic and intelligent optimization methods based on drive train; therefore, it does not involve violation of privacy rights, environmental pollution, etc. The method could be further scale up to 3rd party drive train in future.
[0093] Fig. 7 is a structural diagram of an apparatus for visualizing energy efficiency of digital drive train according to an embodiment of the present invention. Components of the digital drive train comprise a variable-frequency drive, a motor and an application device, the apparatus 700 comprising: a first acquiring module 701, configured to acquire a model of the digital drive train; a second acquiring module 702, configured to acquire a real-time control parameter of the variable-frequency drive; an inputting module 703, configured to input the real-time control parameter into the model; and a receiving module 704, configured to receive a predicted output power of at least one component of the digital drive train from the model; and a displaying module 705, configured to display a predicted energy efficiency of the at least one component based on the predicted output power in visual interface
[0094] Embodiments of the present invention also propose an electronic device with a processor memory architecture. Fig. 8 is a structural diagram of an electronic device according to an embodiment of the present invention. As shown in Figure 8, electronic device 800 includes a processor 801, a memory 802, and a computer program stored on memory 802 that can run on processor 801. When the computer program is executed by processor 801, the method for visualizing energy efficiency of digital drive train as described in either of the above is implemented. Among them, memory 802 can be implemented as various storage media such as electrically erasable programmable read-only memory (EEPROM) , flash memory, programmable program read-only memory (PROM) , etc. Processor 801 can be implemented to include one or more central processors or one or more field programmable gate arrays, wherein the field programmable gate array integrates one or more central processor cores. Specifically, the central processing unit or core can be implemented as a CPU, MCU, DSP, and so on.
[0095] It should be noted that not all steps and modules in the above processes and structural diagrams are necessary, and some steps or modules can be ignored according to actual needs. The execution sequence of each step is not fixed and can be adjusted as needed. The division of each module is only for the convenience of describing the functional division used. In actual implementation, a module can be divided into multiple modules, and the functions of multiple modules can also be implemented by the same module. These modules can be in the same device or different devices.
[0096] The hardware modules in each implementation can be implemented mechanically or electronically. For example, a hardware module can include specially designed permanent circuits or logic devices (such as dedicated processors, such as FPGA or ASIC) to complete specific operations. Hardware modules can also include programmable logic devices or circuits temporarily configured by software (such as general-purpose processors or other programmable processors) for performing specific operations. As for the specific use of mechanical methods, either dedicated permanent circuits or temporarily configured circuits (such as software configuration) to implement hardware modules, it can be determined based on cost and time considerations.
[0097] The above is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this invention shall be included within the scope of protection of this invention.
[0098] Independent of the grammatical term usage, individuals with male, female or other gender identities are included within the term.
Claims
1.A method for visualizing energy efficiency of digital drive train, wherein components of the digital drive train comprise a variable-frequency drive, a motor and an application device, the method comprising:acquiring (101) a model of the digital drive train;acquiring (102) a real-time control parameter of the variable-frequency drive;inputting (103) the real-time control parameter into the model;receiving (104) a predicted output power of at least one component of the digital drive train from the model; anddisplaying (105) a predicted energy efficiency of the at least one component based on the predicted output power in a visual interface.2.The method of claim 1, wherein acquiring (101) a model of the digital drive train comprises:determining a mechanism model of the variable-frequency drive, a mechanism model of the motor, and a mechanism model of the application device through mechanism modeling;combining the mechanism model of the variable-frequency drive, the mechanism model of the motor, and the mechanism model of the application device to generate a mechanism model of the digital drive train.3.The method of claim 1, wherein acquiring (101) a model of the digital drive train comprises:determining a training sample, which comprises a historical value of the control parameter of the variable-frequency drive, wherein a label set of the training sample includes a historical output power of the variable-frequency drive corresponding to the historical value, a historical output power of the motor corresponding to the historical value, and a historical output power of the application device corresponding to the historical value;inputting the training sample into a neural network model to receive a predicted output power set from the neural network model, which includes a predicted output power of the variable-frequency drive, a predicted output power of the motor, and a predicted output power of the application device;determining a loss function value based on a difference between the predicted output power set and the label set;configuring model parameters of the neural network model to make the loss function value lower than a preset threshold;determining the configured neural network model as an artificial intelligence model of the digital drive train.4.The method of claim 1, wherein acquiring (101) a model of the digital drive train comprises:determining a first training sample, which comprises a first historical value of the control parameter of the variable-frequency drive, wherein a label of the first training sample comprises a historical output power of the variable-frequency drive corresponding to the first historical value;inputting the first training sample into a first neural network model to receive a predicted output power of the variable-frequency drive from the first neural network model;determining a first loss function value based on a first difference between the predicted output power of the variable-frequency drive and the label of the first training sample;configuring model parameters of the first neural network model to make the first loss function value lower than a preset first threshold;determining the configured first neural network model as an artificial intelligence model of the variable-frequency drive.5.The method of claim 4, wherein acquiring (101) a model of the digital drive train comprises:determining a second training sample, which comprises a second historical value of the control parameter of the variable-frequency drive, wherein a label of the second training sample comprises a historical output power of the motor corresponding to the second historical value;inputting the second training sample into a second neural network model to receive a predicted output power of the motor from the second neural network model;determining a second loss function value based on a second difference between the predicted output power of the motor and the label of the second training sample;configuring model parameters of the second neural network model to make the second loss function value lower than a preset second threshold;determining the configured second neural network model as an artificial intelligence model of the motor.6.The method of claim 5, wherein acquiring (101) a model of the digital drive train comprises:determining a third training sample, which comprises a third historical value of the control parameter of the variable-frequency drive, wherein a label of the third training sample comprises a historical output power of the application device corresponding to the third historical value;inputting the third training sample into a third neural network model to receive a predicted output power of the application device from the third neural network model;determining a third loss function value based on a third difference between the predicted output power of the application device and the label of the third training sample;configuring model parameters of the third neural network model to make the third loss function value lower than a preset third threshold;determining the configured third neural network model as an artificial intelligence model of the application device.7.The method of claim 6, comprising:combining the artificial intelligence model of the variable-frequency drive, the artificial intelligence model of the motor, and the artificial intelligence model of the application device to generate an artificial intelligence model of the digital drive train.8.The method of any one of claims 1-7, comprising:issuing an alarm message when the energy efficiency falls below a predetermined threshold, wherein the threshold comprises at least one of the following:experience value;average energy efficiency of the at least one component within a predetermined time.9.The method of any one of claims 1-7, comprising:determining a real-time actual energy efficiency of the at least one component;determining an energy efficiency potential of the at least one component based on the difference between the predicted energy efficiency and the real-time actual energy efficiency;adjusting the real-time control parameter of the variable-frequency drive based on the energy efficiency potential.10.The method of claim 2, wherein the application device comprises a pump; the method comprises:calibrating a fluid characteristic curve of the pump based on the real-time control parameter of the variable-frequency drive,updating the mechanism model of the pump based on the calibrated fluid characteristic curve.11.An apparatus for visualizing energy efficiency of digital drive train, components of the digital drive train comprise a variable-frequency drive, a motor and an application device, the apparatus comprising:a first acquiring module (701) , configured to acquire a model of the digital drive train;a second acquiring module (702) , configured to acquire a real-time control parameter of the variable-frequency drive;an inputting module (703) , configured to input the real-time control parameter into the model; anda receiving module (704) , configured to receive a predicted output power of at least one component of the digital drive train from the model; anda displaying module (705) , configured to display a predicted energy efficiency of the at least one component based on the predicted output power in visual interface.12.An electronic device, comprising a processor (801) and a memory (802) , wherein an application program executable by the processor (801) is stored in the memory (802) for causing the processor (801) to execute a method for visualizing energy efficiency of digital drive train according to any one of claims 1-10.13.A computer-readable medium comprising computer-readable instructions stored thereon, wherein the computer-readable instructions for visualizing energy efficiency of digital drive train according to any one of claims 1-10.14.A computer program product comprising a computer program, upon the computer program is executed by a processor for executing a method for visualizing energy efficiency of digital drive train according to any one of claims 1-10.