Metallurgy hydraulic servo energy-saving system based on permanent magnet synchronous motor

Abstract

The invention belongs to the technical field of metallurgical hydraulic servo energy-saving systems, particularly relates to a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor, and aims to solve the problems that in the production process of an existing metallurgical industry hydraulic system, dynamic load matching is inconvenient under the complex working condition, energy is inconvenient to recycle and distribute, and the working efficiency is high. In order to solve the problems of low efficiency, slow response and waste of energy consumption, the invention provides the following scheme: the system comprises a driving module; the monitoring module is connected with the driving module, the monitoring module is connected with a data collection module, and the data collection module is connected with a data analysis module; dynamic load matching can be conveniently carried out under the complex working condition, energy can be conveniently recycled and distributed, the problems of high energy consumption, low response speed and the like of a metallurgical hydraulic system are solved, and the energy-saving effect and the operation efficiency of the system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of metallurgical hydraulic servo energy-saving systems, and in particular to a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor. Background Art

[0002] A metallurgical hydraulic servo energy-saving system uses an oil pump as the power source, drives the main transmission oil pump through a servo motor, detects the real-time pressure of the system using a pressure sensor, realizes closed-loop pressure control, and supplies oil according to the required flow rate and pressure, so as to achieve the purpose of energy conservation and consumption reduction.

[0003] In the prior art, in the production process of the hydraulic system in the metallurgical industry, it is not convenient to perform dynamic load matching under relatively complex working conditions, and it is not convenient to recycle and distribute energy, resulting in low efficiency, slow response, and energy consumption waste. Therefore, we propose a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor to solve the above problems. Summary of the Invention

[0004] The purpose of the present invention is to solve the disadvantages in the prior art that in the production process of the hydraulic system in the metallurgical industry, it is not convenient to perform dynamic load matching under relatively complex working conditions, and it is not convenient to recycle and distribute energy, resulting in low efficiency, slow response, and energy consumption waste, and to propose a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor.

[0005] The metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor provided by the present application adopts the following technical solutions: A metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor, comprising: A driving module; A monitoring module, the monitoring module is connected to the driving module, the monitoring module is connected to a data collection module, and the data collection module is connected to a data analysis module; An intelligent control module, the intelligent control module is connected to the monitoring module and the data analysis module, the intelligent control module is connected to an adjustment module and a cooling and heat dissipation module, and both the adjustment module and the cooling and heat dissipation module are connected to the driving module; A load adaptive module, the load adaptive module is connected to the intelligent control module, the load adaptive module is connected to an energy conversion module, the energy conversion module is connected to an energy recovery module, and the energy recovery module is connected to an energy distribution module; A fault diagnosis module, the fault diagnosis module is connected to the energy distribution module and the data analysis module, the fault diagnosis module is connected to a warning module and a generation module, the warning module is connected to a repair suggestion module and an intelligent interface module, and the generation module is connected to a fault simulation module.

[0006] Furthermore, the load adaptive module includes a dynamic load matching algorithm unit, a load classification unit, and a dual closed-loop control unit. The dynamic load matching algorithm unit is connected to the load classification unit, and the load classification unit is connected to the dual closed-loop control unit.

[0007] Furthermore, the energy distribution module includes a distribution strategy unit, a control unit, and a supercapacitor unit. The distribution strategy unit is connected to the control unit, and the control unit is connected to the supercapacitor unit.

[0008] Furthermore, the adjustment module adopts a vector control algorithm to achieve precise adjustment of the motor speed according to the real-time load feedback of the intelligent control module, with a response time less than 10 milliseconds.

[0009] Furthermore, the load classification unit classifies the load patterns through machine learning and optimizes the control strategy for different load patterns. The dual closed-loop control unit adopts a combination of feedforward control and feedback control to improve the system response speed and stability.

[0010] Furthermore, the distribution strategy unit dynamically allocates the proportion of energy recovery and release based on load prediction to optimize the system energy efficiency. The supercapacitor unit is used to quickly store and release energy.

[0011] Furthermore, the dynamic load matching algorithm unit adopts a hybrid algorithm of sliding mode control and fuzzy control to adjust the pressure and flow rate of the hydraulic system in real time, ensuring that the system pressure fluctuation is less than ±0.3 bar.

[0012] Furthermore, the cooling and heat dissipation module adopts liquid cooling and air cooling technologies. The liquid cooling system uses a microchannel design, and the air cooling system uses a centrifugal fan to ensure the heat dissipation efficiency of the motor in the metallurgical high-temperature environment.

[0013] Furthermore, the intelligent control module includes a deep learning algorithm unit, a collection unit, and a control strategy unit. The deep learning algorithm unit is connected to the collection unit, and the collection unit is connected to the control strategy unit. The deep learning algorithm unit adopts LSTM (Long Short-Term Memory Network) and GAN (Generative Adversarial Network); LSTM (Long Short-Term Memory Network) LSTM is a special recurrent neural network (RNN) used to process sequential data. Formula: Input Gate The input gate determines which new information should be stored in the cell state:

[0014] where: i tis the output of the input gate; σ is the sigmoid activation function; W xi and W hi are the weight matrices; x t is the input data; h t−1 is the hidden state at the previous time step; b i is the bias term; Forget Gate The forget gate determines which information should be discarded from the cell state:

[0015] Candidate Cell State The candidate cell state is a temporary storage for new information:

[0016] where: C t is the cell state at the current time step; ⊙ represents element-wise multiplication; Output Gate The output gate determines which information should be output:

[0017] Hidden State Update The hidden state is a filtered version of the cell state:

[0018] GAN (Generative Adversarial Network) GAN consists of a generator and a discriminator, and generates high-quality samples through adversarial training; Generator Loss Function The goal of the generator is to generate samples as close as possible to the real data distribution:

[0019] where: G(z) is the sample generated by the generator; D(G(z)) is the discriminator's discrimination result for the generated sample; E represents expectation; Discriminator Loss Function The goal of the discriminator is to distinguish real samples from generated samples:

[0020] Where: x is the real sample; pdata(x) is the distribution of the real data; pz(z) is the noise distribution of the generator input. Optimization objective The optimization objective of GAN is the game between the generator and the discriminator:

[0021] In the metallurgical hydraulic servo energy-saving system, deep learning algorithms are used for load prediction: LSTM is used to predict the load changes of the hydraulic system to optimize the control strategy; for fault diagnosis: GAN is used to generate fault samples to improve the accuracy and robustness of fault diagnosis.

[0022] Furthermore, the monitoring module includes a motor current and voltage monitoring unit, a hydraulic pressure monitoring unit, and a temperature monitoring unit. The motor current and voltage monitoring unit is connected to the hydraulic pressure monitoring unit, and the hydraulic pressure monitoring unit is connected to the temperature monitoring unit.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. Through the dynamic load matching and energy recovery distribution technology, the system can accurately adjust the motor speed and the output flow of the hydraulic pump according to the actual load demand, avoiding energy waste in traditional hydraulic systems under conditions such as pressure holding and standby. 2. Through the multi-sensor monitoring system and the fault diagnosis algorithm, the system can monitor the operating state in real time, provide fault warnings and repair suggestions, and reduce downtime. 3. Under low-load or pressure-holding conditions, the energy recovery module stores the excess energy in the super capacitor, and the distribution strategy unit dynamically distributes the ratio of energy recovery and release according to the load prediction to optimize the system energy efficiency.

[0024] The present invention can facilitate dynamic load matching under relatively complex working conditions and facilitate energy recovery and distribution, thereby solving the problems of high energy consumption and low response speed in metallurgical hydraulic systems, such as low efficiency, slow response, and energy consumption waste, and significantly improving the energy-saving effect and operating efficiency of the system. Description of the drawings

[0025] Figure 1 It is a structural block diagram of a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor proposed by the present invention; Figure 2 It is a structural block diagram of the monitoring module of a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor proposed by the present invention; Figure 3 It is a structural block diagram of the load adaptive module of a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor proposed by the present invention; Figure 4Block diagram of the intelligent control module of a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor proposed by the present invention; Figure 5 Block diagram of the energy distribution module of a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor proposed by the present invention. Specific embodiments

[0026] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Embodiment 1

[0027] Refer to Figures 1 - 5 , a metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor, including: Drive module; Monitoring module, the monitoring module is connected to the drive module, the monitoring module is connected to a data collection module, and the data collection module is connected to a data analysis module; Intelligent control module, the intelligent control module is connected to the monitoring module and the data analysis module, the intelligent control module is connected to an adjustment module and a cooling and heat dissipation module, and both the adjustment module and the cooling and heat dissipation module are connected to the drive module; Load adaptive module, the load adaptive module is connected to the intelligent control module, the load adaptive module is connected to an energy conversion module, the energy conversion module is connected to an energy recovery module, and the energy recovery module is connected to an energy distribution module; Fault diagnosis module, the fault diagnosis module is connected to the energy distribution module and the data analysis module, the fault diagnosis module is connected to a warning module and a generation module, the warning module is connected to a repair suggestion module and an intelligent interface module, and the generation module is connected to a fault simulation module.

[0028] Refer to Figures 2 - 5, the load adaptive module includes a dynamic load matching algorithm unit, a load classification unit, and a double closed-loop control unit. The dynamic load matching algorithm unit is connected to the load classification unit, and the load classification unit is connected to the double closed-loop control unit. The energy distribution module includes a distribution strategy unit, a control unit, and a supercapacitor unit. The distribution strategy unit is connected to the control unit, and the control unit is connected to the supercapacitor unit. The regulation module uses a vector control algorithm to achieve precise regulation of the motor speed according to the real-time load feedback of the intelligent control module, with a response time less than 10 milliseconds. The load classification unit classifies the load patterns through machine learning and optimizes the control strategy for different load patterns. The double closed-loop control unit combines feedforward control and feedback control to improve the system response speed and stability. The distribution strategy unit dynamically allocates the proportion of energy recovery and release based on load prediction to optimize the system energy efficiency. The supercapacitor unit is used to quickly store and release energy. The dynamic load matching algorithm unit uses a hybrid algorithm of sliding mode control and fuzzy control to adjust the pressure and flow rate of the hydraulic system in real time to ensure that the system pressure fluctuation is less than ±0.3 bar. The cooling and heat dissipation module uses liquid cooling and air cooling technologies. The liquid cooling system uses a microchannel design, and the air cooling system uses a centrifugal fan to ensure the heat dissipation efficiency of the motor in the metallurgical high-temperature environment. The intelligent control module includes a deep learning algorithm unit, a collection unit, and a control strategy unit. The deep learning algorithm unit is connected to the collection unit, and the collection unit is connected to the control strategy unit. The deep learning algorithm unit uses LSTM (Long Short-Term Memory Network) and GAN (Generative Adversarial Network); LSTM (Long Short-Term Memory Network) LSTM is a special type of Recurrent Neural Network (RNN) used to process sequential data. The formula: Input Gate The input gate determines which new information should be stored in the cell state:

[0029] where: i t is the output of the input gate; σ is the sigmoid activation function; W xi and W hi are weight matrices; x t is the input data; h t−1 is the previous hidden state; b i is the bias term; Forget Gate The forget gate determines which information should be discarded from the cell state:

[0030] Candidate Cell State The candidate unit state is a temporary storage for new information:

[0031] where: C t is the unit state at the current moment; ⊙ represents element-wise multiplication; Output Gate The output gate determines which information should be output:

[0032] Hidden State Update The hidden state is a filtered version of the unit state:

[0033] GAN (Generative Adversarial Network) GAN consists of a generator and a discriminator, and generates high-quality samples through adversarial training; Generator Loss Function The goal of the generator is to generate samples as close as possible to the real data distribution:

[0034] where: G(z) is the sample generated by the generator; D(G(z)) is the discriminant result of the discriminator for the generated sample; E represents expectation; Discriminator Loss Function The goal of the discriminator is to distinguish real samples from generated samples:

[0035] where: x is the real sample; pdata(x) is the distribution of real data; pz(z) is the noise distribution of the generator input; Optimization Goal The optimization goal of GAN is the game between the generator and the discriminator:

[0036] In the metallurgical hydraulic servo energy-saving system, deep learning algorithms are used for load prediction: using LSTM to predict the load changes of the hydraulic system and optimize the control strategy; for fault diagnosis: using GAN to generate fault samples to improve the accuracy and robustness of fault diagnosis. The monitoring module includes a motor current and voltage monitoring unit, a hydraulic pressure monitoring unit, and a temperature monitoring unit. The motor current and voltage monitoring unit is connected to the hydraulic pressure monitoring unit, and the hydraulic pressure monitoring unit is connected to the temperature monitoring unit.

[0037] The implementation principle in this embodiment is as follows: During use, the monitoring module collects key parameters such as motor current, voltage, hydraulic pressure, and temperature in real time. The data collection module preliminarily processes the monitoring data, extracts characteristic values and stores them. The data analysis module deeply analyzes the collected data, extracts the load pattern and operation trend. The deep learning algorithm unit predicts the load change based on the LSTM network, generates the future load pattern. The acquisition unit obtains real-time data from the monitoring module, combines it with historical data for comprehensive analysis. The control strategy unit formulates the optimal control strategy according to the prediction result of the deep learning algorithm and real-time data. Through the vector control algorithm, according to the instructions of the intelligent control module, it precisely adjusts the motor speed, and the response time is less than 10 milliseconds. The adjustment module ensures that the pressure and flow of the hydraulic system match the load demand by adjusting the output flow of the hydraulic pump. The liquid cooling system adopts a microchannel design to quickly conduct the heat generated by the motor. The air cooling system dissipates the heat to the environment through a centrifugal fan to ensure the stable operation of the motor in a high-temperature environment. The dynamic load matching algorithm unit adopts a hybrid algorithm of sliding mode control and fuzzy control to adjust the pressure and flow of the hydraulic system in real time, ensuring that the pressure fluctuation is less than ±0.3 bar. The load classification unit classifies the load pattern through machine learning (such as rolling mill, continuous caster, etc.), and optimizes the control strategy for different patterns. The double closed-loop control unit combines feedforward control and feedback control to improve the system response speed and stability. The energy conversion module, when the hydraulic system is holding pressure or running at low load, drives the motor in reverse through the hydraulic pump and stores the excess energy in the supercapacitor unit. The distribution strategy unit dynamically distributes the proportion of energy recovery and release based on load prediction to optimize the system energy efficiency. The fault diagnosis module diagnoses faults through the data collected by the multi-sensor monitoring system and combines the fault samples generated by the GAN fault simulator. The warning module monitors the system status in real time, and when an abnormality is detected, it issues a warning to the user through the intelligent interface module. The repair suggestion module combines deep learning and an expert system to provide accurate fault repair suggestions. Embodiment Two

[0038] The difference between this embodiment and Embodiment One is that the load adaptive module is connected with a digital twin model module. The digital twin model module adopts digital twin technology to monitor and optimize the system operation status in real time through the digital twin model, improve the system intelligence level, and enhance the ability to adapt to complex working conditions. Embodiment Three

[0039] The difference between this embodiment and Embodiment One is that the monitoring module is connected with a redundancy module. The redundancy module ensures the normal operation of the system when some sensors fail by setting redundant sensors at key monitoring points, and guarantees the operation stability of the system when sensors fail. Embodiment Four

[0040] The difference between this embodiment and the first embodiment is that: the intelligent interface module is connected with a quick switching module, and the quick switching module realizes the quick switching and collaborative work between different modules through the intelligent interface module, and can quickly switch different working conditions. Embodiment Five

[0041] The difference between this embodiment and the first embodiment is that: the data collection module is connected with a data fusion module, and the data fusion module improves the accuracy and reliability of the monitoring data by combining various sensor data.

[0042] As mentioned above, the above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and all should be covered within the protection scope of the present invention.

Claims

1. A metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor, characterized in that: Comprising: Drive module; Monitoring module, the monitoring module is connected to the drive module, the monitoring module is connected with a data collection module, and the data collection module is connected with a data analysis module; Intelligent control module, the intelligent control module is connected to the monitoring module and the data analysis module, the intelligent control module is connected with an adjustment module and a cooling and heat dissipation module, and both the adjustment module and the cooling and heat dissipation module are connected to the drive module; Load adaptive module, the load adaptive module is connected to the intelligent control module, the load adaptive module is connected with an energy conversion module, the energy conversion module is connected with an energy recovery module, and the energy recovery module is connected with an energy distribution module; Fault diagnosis module, the fault diagnosis module is connected to the energy distribution module and the data analysis module, the fault diagnosis module is connected with a warning module and a generation module, the warning module is connected with a repair suggestion module and an intelligent interface module, and the generation module is connected with a fault simulation module.

2. The metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 1, characterized in that: The monitoring module includes a motor current and voltage monitoring unit, a hydraulic pressure monitoring unit, and a temperature monitoring unit. The motor current and voltage monitoring unit is connected to the hydraulic pressure monitoring unit, and the hydraulic pressure monitoring unit is connected to the temperature monitoring unit.

3. The metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 2, wherein: The load adaptive module includes a dynamic load matching algorithm unit, a load classification unit, and a double closed-loop control unit. The dynamic load matching algorithm unit is connected to the load classification unit, and the load classification unit is connected to the double closed-loop control unit.

4. The metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 3, wherein: The intelligent control module includes a deep learning algorithm unit, a collection unit, and a control strategy unit. The deep learning algorithm unit is connected to the collection unit, and the collection unit is connected to the control strategy unit.

5. A metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 4, characterized in that: The energy distribution module includes a distribution strategy unit, a control unit, and a supercapacitor unit. The distribution strategy unit is connected to the control unit, and the control unit is connected to the supercapacitor unit.

6. A metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 5, characterized in that: The cooling and heat dissipation module adopts liquid cooling and air cooling technologies. The liquid cooling system uses a microchannel design, and the air cooling system uses a centrifugal fan to ensure the heat dissipation efficiency of the motor in the high-temperature metallurgical environment.

7. The metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 6, characterized in that: The adjustment module adopts a vector control algorithm and realizes precise adjustment of the motor speed according to the real-time load feedback of the intelligent control module, with a response time of less than 10 milliseconds.

8. A metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 7, characterized in that: The dynamic load matching algorithm unit adopts a hybrid algorithm of sliding mode control and fuzzy control to adjust the pressure and flow rate of the hydraulic system in real time, ensuring that the system pressure fluctuation is less than ±0.3 bar.

9. The metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 8, characterized in that: The load classification unit classifies the load patterns through machine learning and optimizes the control strategy for different load patterns. The double closed-loop control unit adopts a combination of feedforward control and feedback control to improve the system response speed and stability.

10. A metallurgical hydraulic servo energy-saving system based on a permanent magnet synchronous motor according to claim 9, characterized in that: The distribution strategy unit dynamically distributes the proportion of energy recovery and release based on load prediction to optimize the system energy efficiency. The supercapacitor unit is used for rapid energy storage and release.

Images