An intelligent control and management system for electric permanent magnet equipment based on the Internet of Things

Abstract

An Internet of Things-based intelligent control and management system for electric permanent magnet equipment relates to the technical field of equipment control. Monitoring information and an aging coefficient of the electric permanent magnet equipment are obtained. Based on the electromagnetic density relationship and the gravity-magnetism conversion relationship of the electric permanent magnet equipment and the aging coefficient, a corresponding electric-to-weight control relationship is obtained. The electric-to-weight control relationship is used to output a corresponding real-time control current according to the real-time adsorption weight. An intelligent control model for the electric permanent magnet equipment is constructed based on different real-time adsorption weights and their corresponding real-time control currents. A corresponding digital twin model is constructed based on basic equipment information of the electric permanent magnet equipment. The electric permanent magnet equipment is simulated in the digital twin model to obtain simulation information of the electric permanent magnet equipment. The monitoring information is combined to determine whether there is an equipment abnormality. This system is beneficial for improving the pertinence and efficiency of equipment control and can reduce the total power consumption of equipment operation.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and in particular to an intelligent control and management system for electric permanent magnet equipment based on the Internet of Things. Background Art

[0002] Intelligent regulation of electro-permanent magnetic equipment aims to achieve intelligent regulation and efficient management of electro-permanent magnetic equipment using Internet of Things technology. By using data analysis and algorithms to analyze equipment operation data, intelligent control and management of equipment can be achieved, which can improve the operating efficiency, reliability and safety of the equipment.

[0003] In the prior art, when regulating and controlling electro-permanent magnetic equipment, the aging differences between different equipment are often ignored, resulting in a less-than-ideal final regulation result. In addition, in the prior art, the management and control of electro-permanent magnetic equipment is not intelligent enough, and it is impossible to provide targeted regulation solutions in a timely and effective manner, resulting in excessive power consumption of the equipment. To address the shortcomings of the prior art, the present invention provides an intelligent regulation and management system for electro-permanent magnetic equipment based on the Internet of Things. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent control and management system for electric permanent magnet equipment based on the Internet of Things.

[0005] The purpose of the present invention can be achieved through the following technical solution: an intelligent control and management system for electric permanent magnet equipment based on the Internet of Things, comprising the following modules:

[0006] The equipment monitoring module is used to set up several monitoring units on the electro-permanent magnetic equipment and use the monitoring units to obtain different monitoring information;

[0007] The equipment evaluation module is used to obtain the maximum adsorption force of the permanent magnet equipment under standard working conditions and obtain the aging coefficient of the permanent magnet equipment based on the maximum adsorption force;

[0008] The first building block is used to obtain the electromagnetic density relationship and the gravity-magnetic conversion relationship of the electro-permanent magnetic device respectively, and obtain the corresponding electric-gravity control relationship in combination with the aging coefficient of the electro-permanent magnetic device;

[0009] The second construction module is used to obtain the real-time adsorption weight of the electro-permanent magnetic device, output the corresponding real-time control current using the electric-weight control relationship, and construct an intelligent control model of the electro-permanent magnetic device based on different real-time adsorption weights and their corresponding real-time control currents;

[0010] The device twin module is used to obtain the basic device information of the electro-permanent magnetic device and build a corresponding digital twin model. It simulates the electro-permanent magnetic device in the digital twin model, obtains the simulation information of the electro-permanent magnetic device, and combines the monitoring information to determine whether there is any equipment abnormality and provide feedback.

[0011] Furthermore, a plurality of monitoring units are provided on the electro-permanent magnetic device, and a process of using the monitoring units to obtain different monitoring information includes:

[0012] A current monitoring unit is provided to obtain, in real time, current monitoring information on the coil branch circuit of the electro-permanent magnetic device during operation, and a vibration monitoring unit is provided to obtain, in real time, vibration monitoring information on the magnetic pole working surface of the electro-permanent magnetic device during operation;

[0013] A temperature monitoring unit is set up to obtain real-time temperature monitoring information inside the electro-permanent magnetic equipment during operation through the temperature monitoring unit. The monitoring unit includes a current monitoring unit, a vibration monitoring unit, and a temperature monitoring unit. The monitoring information includes current monitoring information, vibration monitoring information, and temperature monitoring information.

[0014] Furthermore, the maximum adsorption force of the electro-permanent magnetic device under standard working conditions is obtained, and the process of obtaining the aging coefficient of the electro-permanent magnetic device according to the maximum adsorption force includes:

[0015] Under standard working conditions, a lateral force is applied to the adsorbed object until it slides. h Get the maximum adsorption force F of the electro-permanent magnetic device z ;

[0016] F z =μF h ;

[0017] Wherein, μ is the friction coefficient between the working surface of the magnetic pole and the adsorbed object, and the standard working condition refers to the preset current value, temperature value, contact area, and weight of the adsorbed object;

[0018] Obtain the theoretical maximum adsorption force F of the electro-permanent magnetic device under standard working conditions max , according to the maximum adsorption force and the theoretical maximum adsorption force, the aging coefficient S of the electro-permanent magnetic device is obtained. p ;

[0019]

[0020] Furthermore, the process of respectively obtaining the electromagnetic density relationship and the gravity-magnetism conversion relationship of the electro-permanent magnetic device and obtaining the corresponding electric-gravity control relationship in combination with the aging coefficient of the electro-permanent magnetic device includes:

[0021] According to the vacuum magnetic permeability μ0, effective magnetic pole area A, and magnetic circuit efficiency coefficient η of the electro-permanent magnetic device, the corresponding relationship between the adsorption force F and the magnetic flux density B of the electro-permanent magnetic device is obtained;

[0022]

[0023] According to the number of coil turns N, coil current I and equivalent magnetic circuit length l of the permanent magnet equipment e , relative magnetic permeability of the core μ r , obtain the residual magnetic flux density B of the permanent magnet contained in the magnetic flux density B of the electro-permanent magnetic device r and the coil's excitation flux density B c ;

[0024] B=B r +B c ;

[0025]

[0026] Obtain coil current I and excitation flux density B c The electromagnetic density relationship between the coil current I and the excitation flux density B c The corresponding relationship parameter is recorded as k I ;

[0027]

[0028] Obtain the gravity-magnetism conversion relationship between the weight m of the adsorbed object and its adsorption force F during the operation of the electro-permanent magnetic device, where g is the acceleration of gravity and ξ is the preset safety factor;

[0029] F = mgξ;

[0030] Combined with the aging coefficient S of the permanent magnet equipment p Obtain the electric-weight control relationship between the coil current I and the weight m of the adsorbed object;

[0031]

[0032] Furthermore, the process of obtaining the real-time adsorption weight of the electro-permanent magnetic device and outputting the corresponding real-time control current using the electric-weight control relationship includes:

[0033] A weight monitoring unit is provided to obtain the load-bearing weight of the electro-permanent magnetic device in real time during operation through the weight monitoring unit, and its no-load weight is subtracted to obtain the corresponding real-time adsorption weight;

[0034] The real-time adsorption weight is input into the electric-weight control relationship as the weight of the adsorbed object, and the corresponding real-time control current is output.

[0035] Furthermore, the process of constructing an intelligent control model of an electro-permanent magnetic device according to different real-time adsorption weights and their corresponding real-time control currents includes:

[0036] Using the electric-weight control relationship, the corresponding real-time control current is obtained according to the real-time adsorption weight of different permanent magnetic devices, and the parameter set corresponding to each real-time adsorption weight and its permanent magnetic device is obtained;

[0037] The parameter set includes aging coefficient, effective magnetic pole area, magnetic circuit efficiency coefficient, number of coil turns, safety factor, residual magnetic flux density, equivalent magnetic circuit length, and magnetic core relative permeability;

[0038] generating an intelligent control set according to different real-time adsorption weights and parameter sets and their corresponding real-time control currents, and dividing the obtained intelligent control set into a training set and a test set;

[0039] Constructing a convolutional neural network, using different real-time adsorption weights and parameter sets in the training set as input data of the convolutional neural network, using the corresponding real-time control currents in the training set as output data of the convolutional neural network, and training the convolutional neural network to obtain an initial convolutional neural network;

[0040] The initial convolutional neural network is model verified using the test set, and the initial convolutional neural network with a preset test error threshold is output as the corresponding intelligent control model.

[0041] Furthermore, basic device information of the electro-permanent magnetic device is obtained and a corresponding digital twin model is constructed. The process of simulating the electro-permanent magnetic device in the digital twin model includes:

[0042] The basic equipment information includes structural parameters, material parameters, electrical parameters, mechanical parameters, and environmental parameters of the electro-permanent magnetic equipment;

[0043] Digital twin technology is used to construct a digital twin model of the electro-permanent magnetic device based on the acquired basic equipment information, and simulation software is used to simulate the constructed digital twin model.

[0044] Furthermore, the process of obtaining analog information of the electro-permanent magnetic device, combining it with the monitoring information to determine whether there is any device abnormality and providing feedback includes:

[0045] In actual application scenarios, the real-time adsorption weight and parameter set of the electro-permanent magnetic device are input into the intelligent control model to output the corresponding real-time control current, and the electro-permanent magnetic device is operated according to the obtained real-time control current;

[0046] The real-time adsorption weight and real-time control current of the electro-permanent magnetic device are synchronized to the corresponding digital twin model, and the analog information of each monitoring unit of the electro-permanent magnetic device is obtained using the digital twin model, including current simulation information, vibration simulation information, and temperature simulation information.

[0047] Obtain the deviation coefficient P of the monitoring information based on the simulation information Wa at the same monitoring unit and the monitoring information Wb at the corresponding moment;

[0048]

[0049] Set a deviation threshold P0 and compare the obtained deviation coefficient with the deviation threshold. If P>P0, it is determined that the electro-permanent magnetic device has an abnormality, generate a corresponding abnormality signal and feed it back to the relevant personnel.

[0050] Equipment abnormal conditions include abnormal temperature conditions, abnormal vibration conditions, and abnormal current conditions. Equipment abnormal signals include abnormal temperature signals, abnormal vibration signals, and abnormal current signals.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] By obtaining the aging coefficients of different electro-permanent magnetic devices, the present invention can include the aging conditions of different devices in the evaluation range. By respectively obtaining the electromagnetic density relationship and the gravity-magnetism conversion relationship of the electro-permanent magnetic devices, and then combining the aging coefficients of the electro-permanent magnetic devices to obtain the corresponding electric-weight control relationship, the present invention can output the corresponding real-time control current according to the real-time adsorption weight of the electro-permanent magnetic devices, which is conducive to improving the targeted management and control of the equipment and reducing the total power consumption of the equipment operation.

[0053] By obtaining the real-time adsorption weight of different electro-permanent magnetic devices and their corresponding real-time control current, and combining the corresponding parameter sets to build an intelligent control model, it is possible to directly output the corresponding real-time control current for different electro-permanent magnetic devices, thereby improving the efficiency of equipment management and control. By using the digital twin model to obtain various simulation information of the electro-permanent magnetic devices in real time and compare it with the various monitoring information at the corresponding time, it is possible to determine whether there is any equipment abnormality, which helps relevant personnel to carry out equipment maintenance in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0055] like Figure 1 As shown in the figure, an intelligent control and management system for electric permanent magnet equipment based on the Internet of Things includes the following modules:

[0056] The equipment monitoring module is used to set up several monitoring units on the electro-permanent magnetic equipment and use the monitoring units to obtain different monitoring information;

[0057] The equipment evaluation module is used to obtain the maximum adsorption force of the permanent magnet equipment under standard working conditions and obtain the aging coefficient of the permanent magnet equipment based on the maximum adsorption force;

[0058] The first building block is used to obtain the electromagnetic density relationship and the gravity-magnetic conversion relationship of the electro-permanent magnetic device respectively, and obtain the corresponding electric-gravity control relationship in combination with the aging coefficient of the electro-permanent magnetic device;

[0059] The second construction module is used to obtain the real-time adsorption weight of the electro-permanent magnetic device, output the corresponding real-time control current using the electric-weight control relationship, and construct an intelligent control model of the electro-permanent magnetic device based on different real-time adsorption weights and their corresponding real-time control currents;

[0060] The device twin module is used to obtain the basic device information of the electro-permanent magnetic device and build a corresponding digital twin model. It simulates the electro-permanent magnetic device in the digital twin model, obtains the simulation information of the electro-permanent magnetic device, and combines the monitoring information to determine whether there is any equipment abnormality and provide feedback.

[0061] It should be further explained that, in a specific implementation process, a plurality of monitoring units are provided on the electro-permanent magnetic device, and the process of using the monitoring units to obtain different monitoring information includes:

[0062] A corresponding current monitoring unit is provided on the coil branch circuit of the electro-permanent magnetic device, and the coil current on the coil branch circuit of the electro-permanent magnetic device during operation is obtained in real time by the current monitoring unit, and marked as current monitoring information;

[0063] A corresponding vibration monitoring unit is provided on the magnetic pole working surface of the electro-permanent magnet device, and the vibration frequency of the magnetic pole working surface of the electro-permanent magnet device is obtained in real time by the vibration monitoring unit during operation, and marked as vibration monitoring information;

[0064] A corresponding temperature monitoring unit is set inside the electro-permanent magnet device. The temperature value inside the electro-permanent magnet device during operation is obtained in real time through the temperature monitoring unit and marked as temperature monitoring information. The monitoring unit includes a current monitoring unit, a vibration monitoring unit, and a temperature monitoring unit. The monitoring information includes current monitoring information, vibration monitoring information, and temperature monitoring information.

[0065] It should be further explained that, in a specific implementation process, the process of obtaining the maximum adsorption force of the electric permanent magnet device under standard working conditions and obtaining the aging coefficient of the electric permanent magnet device based on the maximum adsorption force includes:

[0066] Taking any electro-permanent magnetic device as an example, the standard working condition refers to the preset current value, temperature value, contact area, adsorption object weight and other related parameters. The contact area refers to the contact area between the magnetic pole working surface of the electro-permanent magnetic device and the adsorption object;

[0067] Under standard working conditions, a lateral force is applied to the adsorbed object until it slides, and the magnitude of the lateral force at this time is obtained and recorded as F h , according to the lateral force, the maximum adsorption force of the electro-permanent magnetic device is obtained, which is recorded as F z ;

[0068] F z =μFh ;

[0069] Wherein, μ is the friction coefficient between the magnetic pole working surface and the adsorbed object, and its value range is 0.15~0.2;

[0070] Obtain the theoretical maximum adsorption force of the electro-permanent magnetic device under standard working conditions, denoted as F max , according to the maximum adsorption force and the theoretical maximum adsorption force, the aging coefficient of the electro-permanent magnetic device is obtained, which is recorded as S p ;

[0071]

[0072] The same method is used to obtain the maximum adsorption force of different electro-permanent magnetic devices and their corresponding aging coefficients.

[0073] It should be further explained that, in a specific implementation process, the process of respectively obtaining the electromagnetic density relationship and the gravity-magnetic conversion relationship of the electro-permanent magnetic device and obtaining the corresponding electric-gravity control relationship in combination with the aging coefficient of the electro-permanent magnetic device includes:

[0074] According to the Maxwell stress tensor method, the corresponding relationship between the adsorption force F and the magnetic flux density B of the electro-permanent magnetic device is:

[0075]

[0076] Wherein, μ0 is the vacuum permeability, A is the effective magnetic pole area, and η is the magnetic circuit efficiency coefficient, which ranges from 0.6 to 0.9;

[0077] The magnetic flux density B of the electro-permanent magnetic device includes the residual magnetic flux density B of the permanent magnet. r and the coil's excitation flux density B c ;

[0078] B=B r +B c ;

[0079]

[0080] Where N is the number of coil turns, I is the coil current, l e is the equivalent magnetic circuit length, μ r is the relative magnetic permeability of the core;

[0081] Based on this, the coil current I and the excitation flux density B are obtained. c The corresponding relationship between them is recorded as the electromagnetic density relationship;

[0082]

[0083] Among them, k I is the coil current I and the excitation flux density Bc The corresponding relationship parameters between them;

[0084] Obtain the corresponding relationship between the weight m of the adsorbed object and its adsorption force F during the operation of the electro-permanent magnetic device, which is recorded as the gravity-magnetism conversion relationship;

[0085] F = mgξ;

[0086] Where g is the acceleration due to gravity, ξ is the preset safety factor, and its value range is 1.5 to 2;

[0087] Combined with the aging coefficient S of the permanent magnet equipment p Obtain the corresponding relationship between the coil current I and the weight m of the adsorbed object, which is recorded as the electric-weight control relationship;

[0088]

[0089] It should be further explained that, in a specific implementation process, the process of obtaining the real-time adsorption weight of the electro-permanent magnetic device and outputting the corresponding real-time control current using the electric-weight control relationship includes:

[0090] A corresponding weight monitoring unit is provided in the bearing structure of the electro-permanent magnetic device, and the bearing weight of the electro-permanent magnetic device during operation is obtained in real time through the weight monitoring unit, and its no-load weight is subtracted to obtain the corresponding real-time adsorption weight;

[0091] The monitored real-time adsorption weight is input into the electric-weight control relationship as the weight of the adsorbed object, and the corresponding coil current is output, which is recorded as the real-time control current. The various parameters in the electric-weight control relationship are commonly used parameters in this field and can be directly obtained.

[0092] It should be further explained that, in the specific implementation process, the process of constructing the intelligent control model of the electro-permanent magnetic device according to different real-time adsorption weights and their corresponding real-time control currents includes:

[0093] Using the electric-weight control relationship to obtain the corresponding real-time control current according to the real-time adsorption weight of different electro-permanent magnetic devices, and obtaining the parameter set corresponding to each real-time adsorption weight and its electro-permanent magnetic device, the parameter set includes aging coefficient, effective magnetic pole area, magnetic circuit efficiency coefficient, number of coil turns, safety factor, residual magnetic flux density, equivalent magnetic circuit length, and relative magnetic permeability of the magnetic core;

[0094] generating an intelligent control set according to different real-time adsorption weights and parameter sets and their corresponding real-time control currents, and dividing the obtained intelligent control set into a training set and a test set;

[0095] Constructing a convolutional neural network, using different real-time adsorption weights and parameter sets in the training set as input data of the convolutional neural network, using the corresponding real-time control currents in the training set as output data of the convolutional neural network, and training the convolutional neural network to obtain an initial convolutional neural network;

[0096] The initial convolutional neural network is model verified using the test set, and the initial convolutional neural network with a preset test error threshold is output as the corresponding intelligent control model.

[0097] It should be further explained that, in the specific implementation process, the basic device information of the electro-permanent magnetic device is obtained and the corresponding digital twin model is constructed. The process of simulating the electro-permanent magnetic device in the digital twin model includes:

[0098] Taking any electro-permanent magnetic device as an example, the basic device information refers to the data required to build a digital twin model of the electro-permanent magnetic device, including structural parameters, material parameters, electrical parameters, mechanical parameters, environmental parameters, etc.

[0099] Digital twin technology is used to construct a digital twin model of the electro-permanent magnetic device based on the acquired basic device information, and simulation software is used to simulate the constructed digital twin model. The digital twin model can simulate the operation process of the electro-permanent magnetic device based on the synchronized data.

[0100] It should be further explained that, in the specific implementation process, the process of obtaining analog information of the electro-permanent magnetic device, combining it with the monitoring information to determine whether there is any equipment abnormality and providing feedback includes:

[0101] In actual application scenarios, the real-time adsorption weight of the electro-permanent magnetic device and its parameter set are input into the intelligent control model, and the corresponding real-time control current is output by the intelligent control model, and the electro-permanent magnetic device is operated according to the obtained real-time control current;

[0102] The real-time adsorption weight and real-time control current of the electro-permanent magnetic device are synchronized to the corresponding digital twin model, and the analog information of each monitoring unit of the electro-permanent magnetic device is obtained using the digital twin model, including current simulation information, vibration simulation information, and temperature simulation information.

[0103] Mark the temperature simulation information as W a , mark the temperature monitoring information at the corresponding moment as W b , obtain the deviation coefficient of temperature monitoring information, denoted as P;

[0104]

[0105] Set a deviation threshold P0, compare the obtained deviation coefficient with the deviation threshold, and if P>P0, determine that the electro-permanent magnetic device has a temperature anomaly, generate a corresponding temperature anomaly signal, and feed the generated temperature anomaly signal back to relevant personnel;

[0106] The same method is adopted to obtain the deviation coefficients of vibration monitoring information and current monitoring information respectively, and then judge whether there are abnormal vibration and current conditions in the permanent magnet equipment respectively, and generate corresponding abnormal vibration signals and abnormal current signals for feedback.

[0107] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent control and management system for electric permanent magnet equipment based on the Internet of Things, characterized in that: Includes the following modules: The equipment monitoring module is used to set up several monitoring units on the electro-permanent magnetic equipment and use the monitoring units to obtain different monitoring information; The equipment evaluation module is used to obtain the maximum adsorption force of the permanent magnet equipment under standard working conditions and obtain the aging coefficient of the permanent magnet equipment based on the maximum adsorption force; The first building block is used to obtain the electromagnetic density relationship and the gravity-magnetic conversion relationship of the electro-permanent magnetic device respectively, and obtain the corresponding electric-gravity control relationship in combination with the aging coefficient of the electro-permanent magnetic device; The second construction module is used to obtain the real-time adsorption weight of the electro-permanent magnetic device, output the corresponding real-time control current using the electric-weight control relationship, and construct an intelligent control model of the electro-permanent magnetic device based on different real-time adsorption weights and their corresponding real-time control currents; The device twin module is used to obtain basic device information of the electro-permanent magnetic device and build a corresponding digital twin model. The digital twin model simulates the electro-permanent magnetic device to obtain the simulated information of the electro-permanent magnetic device. Combined with the monitoring information, it determines whether there is any device anomaly and provides feedback. The process of obtaining the electromagnetic density relationship and the gravity-magnetic conversion relationship and obtaining the electric-gravity control relationship in combination with the aging coefficient includes: According to the vacuum permeability of the electro-permanent magnetic device , effective magnetic pole area A, magnetic circuit efficiency coefficient , obtain the corresponding relationship between the adsorption force F and the magnetic flux density B of the electro-permanent magnetic device; According to the number of coil turns N, coil current I, and equivalent magnetic circuit length of the permanent magnet equipment , relative magnetic permeability of the core , obtain the residual magnetic flux density B of the permanent magnet contained in the magnetic flux density B of the electro-permanent magnetic device r and the coil's excitation flux density B c ; Obtain coil current I and excitation flux density B c The electromagnetic density relationship between the coil current I and the excitation flux density B c The corresponding relationship parameters are recorded as ; Obtain the gravity-magnetism conversion relationship between the weight m of the adsorbed object and its adsorption force F during the operation of the electro-permanent magnetic device, where g is the acceleration of gravity. is the preset safety factor; Combined with the aging coefficient S of the permanent magnet equipment p Obtain the electric-weight control relationship between the coil current I and the weight m of the adsorbed object; 2. The intelligent control and management system for electric permanent magnet equipment based on the Internet of Things according to claim 1 is characterized in that: The process of setting up monitoring units and obtaining different monitoring information includes: A current monitoring unit is provided to obtain, in real time, current monitoring information on the coil branch circuit of the electro-permanent magnetic device during operation, and a vibration monitoring unit is provided to obtain, in real time, vibration monitoring information on the magnetic pole working surface of the electro-permanent magnetic device during operation; A temperature monitoring unit is set up to obtain real-time temperature monitoring information inside the electro-permanent magnetic equipment during operation through the temperature monitoring unit. The monitoring unit includes a current monitoring unit, a vibration monitoring unit, and a temperature monitoring unit. The monitoring information includes current monitoring information, vibration monitoring information, and temperature monitoring information.

3. The intelligent control and management system for electric permanent magnet equipment based on the Internet of Things according to claim 2 is characterized in that: The process of obtaining the aging coefficient of the electro-permanent magnetic device based on the maximum adsorption force includes: Under standard working conditions, a lateral force is applied to the adsorbed object until it slides. h Get the maximum adsorption force F of the electro-permanent magnetic device z ; in, is the friction coefficient between the working surface of the magnetic pole and the adsorbed object, and the standard working condition refers to the preset current value, temperature value, contact area, and weight of the adsorbed object; Obtain the theoretical maximum adsorption force F of the electro-permanent magnetic device under standard working conditions max , according to the maximum adsorption force and the theoretical maximum adsorption force, the aging coefficient S of the electro-permanent magnetic device is obtained. p ; 4. The intelligent control and management system for electric permanent magnet equipment based on the Internet of Things according to claim 3 is characterized in that: The process of obtaining the real-time adsorption weight and real-time control current of the electro-permanent magnetic device includes: A weight monitoring unit is provided to obtain the load-bearing weight of the electro-permanent magnetic device in real time during operation through the weight monitoring unit, and its no-load weight is subtracted to obtain the corresponding real-time adsorption weight; The real-time adsorption weight is input into the electric-weight control relationship as the weight of the adsorbed object, and the corresponding real-time control current is output.

5. The intelligent control and management system for electric permanent magnet equipment based on the Internet of Things according to claim 4 is characterized in that: The process of building an intelligent control model for electro-permanent magnetic equipment includes: Using the electric-weight control relationship, the corresponding real-time control current is obtained according to the real-time adsorption weight of different permanent magnetic devices, and the parameter set corresponding to each real-time adsorption weight and its permanent magnetic device is obtained; The parameter set includes aging coefficient, effective magnetic pole area, magnetic circuit efficiency coefficient, number of coil turns, safety factor, residual magnetic flux density, equivalent magnetic circuit length, and magnetic core relative permeability; generating an intelligent control set according to different real-time adsorption weights and parameter sets and their corresponding real-time control currents, and dividing the obtained intelligent control set into a training set and a test set; Constructing a convolutional neural network, using different real-time adsorption weights and parameter sets in the training set as input data of the convolutional neural network, using the corresponding real-time control currents in the training set as output data of the convolutional neural network, and training the convolutional neural network to obtain an initial convolutional neural network; The initial convolutional neural network is model verified using the test set, and the initial convolutional neural network with a preset test error threshold is output as the corresponding intelligent control model.

6. The intelligent control and management system for electric permanent magnet equipment based on the Internet of Things according to claim 5 is characterized in that: The process of simulating an electro-permanent magnetic device in a digital twin model includes: The basic equipment information includes structural parameters, material parameters, electrical parameters, mechanical parameters, and environmental parameters of the electro-permanent magnetic equipment; Digital twin technology is used to construct a digital twin model of the electro-permanent magnetic device based on the acquired basic equipment information, and simulation software is used to simulate the constructed digital twin model.

7. The intelligent control and management system for electric permanent magnet equipment based on the Internet of Things according to claim 6 is characterized in that: The process of obtaining simulation information, combining it with monitoring information to determine whether there is any equipment anomaly, and providing feedback includes: In actual application scenarios, the real-time adsorption weight and parameter set of the electro-permanent magnetic device are input into the intelligent control model to output the corresponding real-time control current, and the electro-permanent magnetic device is operated according to the obtained real-time control current; The real-time adsorption weight and real-time control current of the electro-permanent magnetic device are synchronized to the corresponding digital twin model, and the analog information of each monitoring unit of the electro-permanent magnetic device is obtained using the digital twin model, including current simulation information, vibration simulation information, and temperature simulation information. According to the simulation information W at the same monitoring unit a and the monitoring information W at the corresponding time b , obtain the deviation coefficient P of the monitoring information; Set a deviation threshold P0 and compare the obtained deviation coefficient with the deviation threshold. If P>P0, it is determined that the electro-permanent magnetic device has an abnormality, generate a corresponding abnormality signal and feed it back to the relevant personnel. Equipment abnormal conditions include abnormal temperature conditions, abnormal vibration conditions, and abnormal current conditions. Equipment abnormal signals include abnormal temperature signals, abnormal vibration signals, and abnormal current signals.

Images