Magnetic material demagnetization method and system based on artificial intelligence control system

Abstract

The invention provides a magnetic material demagnetization method and system based on an artificial intelligence control system. The method comprises an initial data acquisition step, a demagnetization judgment step, a demagnetization execution step and a multi-round optimization and data storage step. According to the initial detection data, the artificial intelligence control system uses an optimization algorithm to calculate needed degaussing parameters, the arrangement mode of permanent magnets in the degaussing equipment is judged according to the degaussing parameters, and degaussing operation is conducted on the to-be-degaussed material; and after demagnetization is completed, the residual magnetism intensity of the to-be-demagnetized material is detected again, if the residual magnetism intensity of the to-be-demagnetized material is lower than the preset threshold value, the demagnetization process is ended, and if the set standard is not met, the artificial intelligence control system adjusts the parameters and executes the demagnetization operation again. According to the method and system, the magnetic state data of the material to be demagnetized are collected in real time, whether demagnetization is needed or not is judged, demagnetization parameters are dynamically optimized, and through multiple rounds of detection and demagnetization operation, the target magnetic requirement is finally met, and the efficient, accurate and energy-saving demagnetization effect is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of magnetic material demagnetization, and particularly to a magnetic material demagnetization method and system based on an artificial intelligence control system. Background Art

[0002] The wide application of magnetic materials, such as in the fields of electronic devices, automotive industry, medical devices, etc., has put forward higher requirements for their demagnetization technology. Traditional demagnetization methods mostly adopt simple electromagnetic field technology with fixed parameters. However, this method is difficult to dynamically adjust demagnetization parameters according to the characteristics and residual magnetic intensity of the material to be demagnetized, and there are problems such as low efficiency, high energy consumption, and uneven effect, especially in complex geometric structures and multi-batch production. Traditional demagnetization methods lack intelligent control and real-time optimization capabilities, and it is difficult to meet the requirements of modern industry for high efficiency, precision, and environmental friendliness.

[0003] The rapid development of artificial intelligence and sensing technology has provided new possibilities for the optimization of demagnetization technology. Through the optimized control of demagnetization parameters by AI, an intelligent demagnetization method with real-time detection, feedback, and optimized control can be realized, which can significantly improve the demagnetization efficiency and effect, while reducing energy consumption and manual intervention, providing new possibilities for solving the above problems. Summary of the Invention

[0004] In view of the above, the present invention provides a magnetic material demagnetization method and system based on an artificial intelligence control system. By real-time collecting the magnetic state data of the material to be demagnetized, it is determined whether demagnetization is required, the demagnetization parameters are dynamically optimized, and through multiple rounds of detection and demagnetization operations, the target magnetic requirements are finally met, achieving efficient, accurate, and energy-saving demagnetization effects.

[0005] The technical solution of the present invention:

[0006] In the first aspect, the present invention provides a magnetic material demagnetization method based on an artificial intelligence control system, including the following steps:

[0007] Initial data collection step: Place the material to be demagnetized in the detection area, and use sensors to real-time collect its residual magnetic intensity, shape, material, and temperature and humidity environment parameters. The collected data is transmitted to the artificial intelligence control system after A / D conversion;

[0008] Demagnetization determination step: The artificial intelligence control system compares the collected data with the preset magnetic requirement threshold. If the magnetism of the material to be demagnetized exceeds the threshold, it enters the demagnetization stage, otherwise the material to be demagnetized directly passes through;

[0009] Demagnetization execution steps: Based on the initial detection data, the artificial intelligence control system uses an optimization algorithm to calculate the required demagnetization parameters, including magnetic field strength and / or magnetic field direction, and determines the arrangement of permanent magnets in the demagnetization device accordingly, and performs a demagnetization operation on the material to be demagnetized; after demagnetization is completed, the residual magnetic strength of the material to be demagnetized is detected again. If the residual magnetic strength of the material to be demagnetized is lower than the preset threshold, the demagnetization process ends. If the set standard is not reached, the artificial intelligence control system adjusts the parameters and re-executes the demagnetization operation;

[0010] Multi-round optimization and data storage steps: The artificial intelligence control system optimizes the subsequent demagnetization parameters based on historical demagnetization data through a reinforcement learning algorithm, and adjusts the magnetic field strength, direction and / or time according to the demagnetization effect of the previous round; for materials to be demagnetized with complex shapes, the magnetic field distribution is optimized by means of zone detection, zone processing, simulation verification and dynamic adjustment; the data acquisition and demagnetization operations are repeated until the material to be demagnetized meets the target magnetic requirements, and then the system stops the demagnetization process and records the data.

[0011] In a second aspect, the present invention provides a magnetic material demagnetization system based on an artificial intelligence control system, including:

[0012] Initial data acquisition module: configured to place the material to be demagnetized in the detection area, and use sensors to collect its residual magnetic strength, shape, material, and temperature and humidity environment parameters in real time. The collected data is transmitted to the artificial intelligence control system after A / D conversion;

[0013] Demagnetization determination module: configured to compare the data collected by the artificial intelligence control system with the preset magnetic requirement threshold. If the magnetism of the material to be demagnetized exceeds the threshold, it enters the demagnetization stage, otherwise the material to be demagnetized passes directly;

[0014] Demagnetization execution module: configured to, based on the initial detection data, the artificial intelligence control system uses an optimization algorithm to calculate the required demagnetization parameters, including magnetic field strength and / or magnetic field direction, and determines the arrangement of permanent magnets in the demagnetization device accordingly, and performs a demagnetization operation on the material to be demagnetized; after demagnetization is completed, the residual magnetic strength of the material to be demagnetized is detected again. If the residual magnetic strength of the material to be demagnetized is lower than the preset threshold, the demagnetization process ends. If the set standard is not reached, the artificial intelligence control system adjusts the parameters and re-executes the demagnetization operation;

[0015] Multi-round optimization and data storage module: configured to, the artificial intelligence control system optimizes the subsequent demagnetization parameters based on historical demagnetization data through a reinforcement learning algorithm, and adjusts the magnetic field strength, direction and / or time according to the demagnetization effect of the previous round; for materials to be demagnetized with complex shapes, the magnetic field distribution is optimized by means of zone detection, zone processing, simulation verification and dynamic adjustment; the data acquisition and demagnetization operations are repeated until the material to be demagnetized meets the target magnetic requirements, and then the system stops the demagnetization process and records the data.

[0016] The beneficial effects of the demagnetization method and system of magnetic materials based on the artificial intelligence control system of the present invention are mainly reflected in the following aspects:

[0017] I. Significantly improve the demagnetization efficiency: By using the artificial intelligence control system for intelligent parameter optimization, the present invention can dynamically adjust the demagnetization parameters such as current intensity, frequency and time according to the real-time data of the material to be demagnetized, so that the demagnetization efficiency can be increased by 30%-50% under the same conditions. This improvement not only shortens the demagnetization cycle, but also improves the overall throughput of the production line.

[0018] II. Achieve high efficiency and energy saving: The closed-loop feedback mechanism and high-precision sensors of the present invention can monitor the residual magnetic state of magnetic materials in real time and perform precise control through AI algorithms. This control method can avoid material damage or waste caused by over-demagnetization, and at the same time, by dynamically optimizing the magnetic field strength and direction, the power consumption during the demagnetization process can be significantly reduced, and the energy consumption can be reduced by about 20%-40%.

[0019] III. Ensure precise demagnetization effect: Through multiple rounds of data collection and parameter optimization, the present invention can control the residual magnetic amount of the material to be demagnetized below 0.05 mT, meeting the international standard and meeting the requirements of high-precision fields. This precise demagnetization effect improves the quality and reliability of products.

[0020] IV. Enhance the universality and automation level of the system: The present invention is applicable to the demagnetization treatment of various materials and complex geometric shapes, with wide applicability. At the same time, by realizing the automatic process of real-time data collection, transmission, detection and demagnetization operation of materials, the manual intervention is significantly reduced, and the intelligent level of the production line is improved, providing strong support for the deep integration of batch production lines.

[0021] In summary, the demagnetization method of magnetic materials based on the artificial intelligence control system provided by the present invention shows significant beneficial effects in terms of improving demagnetization efficiency, achieving high efficiency and energy saving, ensuring precise demagnetization effect, and enhancing the universality and automation level of the system, and has broad market application prospects and important economic value.

[0022] The preferred implementation embodiments and their beneficial effects of the present invention will be further described in detail in combination with specific embodiments. Brief Description of the Drawings

[0023] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification, and are used to explain the present invention together with the following specific embodiments, but should not constitute a limitation to the present invention. In the drawings:

[0024] Figure 1It is a flowchart of the demagnetization method of magnetic materials based on the artificial intelligence control system of the present invention;

[0025] Figure 2 It is a schematic structural diagram of the demagnetization device of the present invention;

[0026] Figure 3 It is a magnetic hysteresis curve model diagram fitted with optimized parameters;

[0027] Figure 4 It is a simulation demagnetization optimization parameter model diagram;

[0028] Figure 5 It is a spatial distribution diagram of the internal magnetic field strength of the material during the demagnetization process;

[0029] Figure 6 It is a spatial distribution diagram of the internal magnetic induction intensity of the material during the demagnetization process;

[0030] Figure 7 It is a module diagram of the demagnetization system of magnetic materials based on the artificial intelligence control system of the present invention. Specific Embodiments

[0031] The following will describe in detail the specific embodiments of the present invention with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining and illustrating the present invention, and are not used to limit the present invention.

[0032] Please refer to Figure 1 , the present invention provides a demagnetization method of magnetic materials based on an artificial intelligence control system, including the following steps:

[0033] Initial data acquisition step: Place the material to be demagnetized in the detection area, and use sensors to collect its residual magnetic intensity, shape, material, and temperature and humidity environment parameters in real time. The collected data is transmitted to the artificial intelligence control system after A / D conversion;

[0034] Demagnetization determination step: The artificial intelligence control system compares the collected data with the preset magnetic requirement threshold. It can be set that the residual magnetic intensity ≤ 0.05 mT is the qualified standard. If the magnetism of the material to be demagnetized exceeds the threshold, it enters the demagnetization stage, otherwise the material to be demagnetized directly passes through;

[0035] Demagnetization execution step: According to the initial detection data, the artificial intelligence control system uses an optimization algorithm to calculate the required demagnetization parameters, including magnetic field strength (A / m) and / or magnetic field direction, and accordingly determines the arrangement method of the permanent magnets in the demagnetization device to perform demagnetization operations on the material to be demagnetized; after demagnetization is completed, the residual magnetic intensity of the material to be demagnetized is detected again. If the residual magnetic intensity of the material to be demagnetized is lower than the preset threshold, the demagnetization process ends. If the set standard is not reached, the artificial intelligence control system adjusts the parameters and re-executes the demagnetization operation;

[0036] Multi-round optimization and data storage steps: Based on historical demagnetization data, the artificial intelligence control system optimizes subsequent demagnetization parameters through reinforcement learning algorithms, and adjusts the magnetic field strength, direction, and / or time according to the demagnetization effect of the previous round; for demagnetization materials with complex shapes, the magnetic field distribution is optimized by means of zonal detection, zonal processing, simulation verification, and dynamic adjustment; the data acquisition and demagnetization operations are repeated until the demagnetization material meets the target magnetic requirements, and then the system stops the demagnetization process and records the data.

[0037] The beneficial effects of the demagnetization method of magnetic materials based on the artificial intelligence control system of the present invention are mainly reflected in the following aspects:

[0038] I. Significantly improve demagnetization efficiency: By using the artificial intelligence control system for intelligent parameter optimization, the present invention can dynamically adjust demagnetization parameters such as current intensity, frequency, and time according to the real-time data of the demagnetization material. Thus, under the same conditions, the demagnetization efficiency is increased by 30%-50%. This improvement not only shortens the demagnetization cycle but also improves the overall throughput of the production line.

[0039] II. Achieve high efficiency and energy saving: The closed-loop feedback mechanism and high-precision sensors of the present invention can monitor the residual magnetic state of the magnetic material in real time and perform precise control through AI algorithms. This control method can avoid material damage or waste caused by over-demagnetization. At the same time, by dynamically optimizing the magnetic field strength and direction, the power consumption during the demagnetization process is significantly reduced, and the energy consumption is reduced by about 20%-40%.

[0040] III. Ensure precise demagnetization effect: Through multi-round data acquisition and parameter optimization, the present invention can control the residual magnetic quantity of the demagnetization material below 0.05 mT, meeting international standards and meeting the requirements of high-precision fields. This precise demagnetization effect improves the quality and reliability of the product.

[0041] IV. Enhance system universality and automation level: The present invention is applicable to demagnetization processing of various materials and complex geometries, with wide applicability. At the same time, by realizing the automatic process of real-time data acquisition, transmission, detection, and demagnetization operation of materials, the manual intervention is significantly reduced, and the intelligent level of the production line is improved, providing strong support for the deep integration of batch production lines.

[0042] In summary, the demagnetization method of magnetic materials based on the artificial intelligence control system provided by the present invention shows significant beneficial effects in terms of improving demagnetization efficiency, achieving high efficiency and energy saving, ensuring precise demagnetization effect, and enhancing system universality and automation level, and has broad market application prospects and important economic value.

[0043] In the initial data acquisition step, the material to be demagnetized is carefully and precisely placed within a well-designed detection area. This detection area is specially laid out to ensure that the data obtained by the sensors is highly reliable and representative. In the detection area, a variety of advanced sensors are distributed, each performing its own function and working together to complete the real-time acquisition of various key parameters of the material.

[0044] As one of the core indicators for measuring the demagnetization requirements of magnetic materials, the residual magnetic intensity is measured by a high-sensitivity magnetic field sensor. This sensor uses advanced magnetoelectric conversion technology to accurately sense extremely weak magnetic field changes around the material and convert them into electrical signals. Whether it is the inherent magnetic field remaining in the material due to processing, storage, etc., or the additional magnetic field generated under the interference of the external environment, it can be accurately captured, providing a key basis for subsequent judgment on whether the material needs to be demagnetized and determining the demagnetization parameters.

[0045] For the acquisition of the material shape, a combination of non-contact optical measurement sensors and structural scanning sensors is used. The optical measurement sensor uses the principle of optical imaging to perform a full-range scan of the material surface to obtain its two-dimensional contour information; the structural scanning sensor emits electromagnetic waves with a specific frequency to penetrate a certain depth of the material surface and detect its internal structural characteristics. The data of the two complement each other, and after being processed by algorithms, an accurate three-dimensional shape model of the material can be constructed, recording in detail information such as the size, geometric shape, internal holes or defects of the material, which is of great significance for subsequent determination of the arrangement of permanent magnets in the demagnetization equipment and optimization of the magnetic field distribution.

[0046] The identification and analysis of the material are jointly completed by a spectral analyzer and a composition detection sensor. The spectral analyzer irradiates the material surface with light of a specific wavelength and analyzes the main element composition and chemical bond structure of the material according to the absorption, reflection, and scattering characteristics of the material to light; the composition detection sensor uses microelectromechanical sensing technology to accurately measure the content of various trace elements in the material. Through the data fusion and comparison of the two, not only can the material type, such as ferromagnetic materials, ferrimagnetic materials, etc., be accurately judged, but also detailed chemical composition information of the material can be obtained, providing strong support for formulating personalized demagnetization schemes according to the material characteristics.

[0047] In terms of environmental parameters, the temperature and humidity environmental parameters have an undeniable impact on the magnetic performance of magnetic materials and the demagnetization process. The temperature sensor uses high-precision thermistor technology to quickly respond to environmental temperature changes. The humidity sensor is based on the principle of capacitive sensing and can measure the environmental relative humidity in real time. The temperature and humidity data collected by these two sensors are transmitted in a timely manner for subsequent compensation and correction of relevant parameters during the demagnetization process to ensure that the demagnetization effect is not interfered by environmental factors.

[0048] All the analog signals collected by the sensors are quickly and accurately converted into digital signals by the A / D conversion module. The A / D conversion module uses high-speed and high-precision conversion chips, which can effectively reduce the errors in the data conversion process. The converted digital signals are transmitted stably and quickly to the artificial intelligence control system through high-speed data transmission buses such as SPI and USB. After receiving the data, the artificial intelligence control system integrates, stores, and preliminarily analyzes it, laying a solid data foundation for subsequent determination of whether degaussing is needed and calculation of degaussing parameters.

[0049] In the degaussing determination step, after the artificial intelligence control system receives a series of information including residual magnetic intensity, shape, material, and temperature and humidity environment parameters transmitted from the data acquisition module, it quickly starts the built-in data analysis and determination program. The system will first extract the residual magnetic intensity data and accurately compare it with the pre-set magnetic requirement threshold. In the present invention, it is clearly defined that the residual magnetic intensity ≤ 0.05 mT is used as the qualified standard, which is determined through verification of a large amount of experimental data and in combination with the usage requirements of magnetic materials in the industry, and can ensure that the processed magnetic materials meet the needs of the vast majority of application scenarios.

[0050] In the degaussing execution step, as Figure 2 shown, the degaussing device includes a degaussing coil and an alternating arrangement of multiple permanent magnets.

[0051] The arrangement direction and intensity of the permanent magnets will affect the degaussing effect. By changing the N and S poles of the permanent magnets, the magnetic field direction acting on the magnetic material by the permanent magnets can be changed. Therefore, arranging the permanent magnets reasonably can form a uniform magnetic field in the target area to achieve complete degaussing. The arrangement method of the permanent magnets is determined by analyzing the initial magnetic field direction and the residual magnetic intensity distribution of the material to be degaussed detected by the sensor.

[0052] The arrangement methods of the permanent magnets can be divided into:

[0053] Parallel arrangement: Suitable for uniformly distributed long strip materials, providing a strong magnetic field in a single direction.

[0054] Cross arrangement: For materials with complex geometric shapes, a multi-directional magnetic field is formed through cross arrangement to enhance the degaussing effect.

[0055] Array arrangement: Used for degaussing large-area materials to ensure uniform magnetic field coverage.

[0056] Here, a polar alternating array arrangement is used. To avoid waste, three permanent magnets are selected for arrangement, specifically as follows:

[0057] When the magnetic field on the surface of the material to be measured is the N pole, an array of N-S-N composed of 3 magnets is used to eliminate it; when the surface magnetic field is the S pole, the last two magnets S-N are used to eliminate it; when the surface is not magnetized, after the first magnet magnetizes the material to be measured, the last two magnets form an array of S-N to eliminate the influence.

[0058] In the demagnetization execution step, the current intensity and frequency are dynamically optimized:

[0059] Since the remanence characteristics of magnetic materials are closely related to the intensity and frequency of the applied magnetic field. Different materials require different combinations of current intensity and frequency to achieve the best demagnetization effect. The demagnetization process can gradually reduce the magnetic induction intensity through an alternating magnetic field, so that the remanence inside the material gradually decreases below the target value.

[0060] Current intensity (A): According to Ampere's circuital law, we have N: Number of turns of the coil; l: Magnetic path length. It can be seen that the intensity H of the applied magnetic field is proportional to the current I, and dynamically adjusting the current intensity can control the magnetic field intensity.

[0061] Frequency (Hz): The frequency of the magnetic field determines the rate of magnetic domain flipping. High frequency can quickly flip magnetic domains, and low frequency is suitable for fine adjustment. The dynamic response formula between the remanence Br and the applied magnetic field frequency f is B r =B r0 .e -af ,

[0062] where, B r0 : Static remanence; f: Applied magnetic field frequency (Hz); a: Constant related to the magnetic hysteresis characteristics of the material; e is the natural constant.

[0063] A high-frequency applied magnetic field can quickly flip magnetic domains, reduce the ordered arrangement between magnetic domains, and thus reduce the remanence Br; under low-frequency conditions, the magnetic domain flipping is slower, the magnetic hysteresis effect is stronger, and the remanence Br is larger.

[0064] Therefore, it is necessary to use a sensor to continuously monitor the magnetic field intensity B value of the material to be demagnetized in real time and feed the data back to the artificial intelligence control system.

[0065] If the initial residual magnetic intensity is high, the artificial intelligence control system will select a larger current intensity and a high frequency; when the magnetic field gradually weakens, the system gradually reduces the current intensity and frequency.

[0066] The optimization process is divided into an initial stage, an intermediate stage, and an end stage.

[0067] Initial stage: In the state of high residual magnetism, an alternating magnetic field with a high current intensity and a high frequency is adopted to quickly flip the magnetic domains inside the material to be demagnetized and reduce the magnetic hysteresis phenomenon.

[0068] Intermediate stage: Monitor the remanent magnetic intensity, reduce the current intensity according to the feedback results, gradually reduce the ordered arrangement of magnetic domains, and optimize the frequency to adapt to the characteristics of different materials to be demagnetized.

[0069] Final stage: Use a magnetic field with low current intensity and low frequency to perform fine demagnetization on the material to be demagnetized, and eliminate the weak remanent magnetism.

[0070] Table 1 below shows the optimized parameters (magnetic induction intensity, magnetic field intensity) during the demagnetization process.

[0071] B (gauss) 135.1027 126.3491 117.5956 108.842 100.0885 91.3349 H (A / m) 2.6878 2.5136 2.3395 2.1653 1.9912 1.8171 B (gauss) 82.5813 73.8278 65.0742 56.3207 47.5671 38.8135 H (A / m) 1.6429 1.4688 1.3946 1.1205 0.9463 0.7722 B (gauss) 30.06 21.3064 12.5529 3.7993 / / H (A / m) 0.598 0.4239 0.2497 0.0756 / /

[0072] Refer to Figure 3 and Figure 4 . During the demagnetization process, the optimized key parameters mainly include the magnetic induction intensity B and the magnetic field intensity H. The optimized parameters are directly related to the hysteresis curve. By dynamically adjusting these parameters, the demagnetization process can be made more efficient and accurate.

[0073] The hysteresis curve is the core graph that describes the magnetic properties of materials, reflecting the relationship between the magnetic field intensity H and the magnetic induction intensity B. The hysteresis curve mainly includes characteristic parameters such as the remanent magnetism Br and the coercive force Hc.

[0074] The relationship between B and H is expressed by the fitting equation y = 50.262x - 0.31, and the correlation coefficient R of the fitting 2 = 0.9991, indicating that the optimized parameters have a high degree of linear correlation. This linear relationship means that the material gradually tends to the soft magnetic state (the remanent magnetism Br and the coercive force Hc are significantly reduced) during the demagnetization process.

[0075] With the optimized adjustment of the magnetic field intensity H, the magnetic induction intensity B gradually decreases during multiple rounds of demagnetization. The hysteresis loop gradually approaches the center line, and finally the remanent magnetism value approaches zero, reflecting the significant demagnetization effect of the magnetic material.

[0076] From Figure 5 , the spatial distribution of the magnetic field intensity H inside the material during the demagnetization process can be seen.

[0077] The magnetic field intensity inside the material is the combined result of the applied magnetic field and the magnetic response of the material itself. It can be seen from the figure that the distribution of the magnetic field intensity H has obvious gradient regions, and the color gradually transitions from red (high intensity) to blue (low intensity). This indicates that the applied magnetic field gradually decays in space, resulting in different magnetization effects in different regions, reflecting the effect of dynamically adjusting the magnetic field intensity and direction.

[0078] The demagnetization process is a process of gradually reducing the magnetic field strength and frequency, ultimately making the magnetic domains inside the material reach a disordered distribution state, thereby eliminating the remanent magnetism. The figure shows that after multiple rounds of demagnetization, the high-intensity magnetic field (red area) inside the material is gradually replaced by the weak magnetic field (blue area), indicating that the demagnetization process has a significant magnetic field reduction effect.

[0079] From Figure 6 it can be seen the spatial distribution of the magnetic induction intensity B inside the material during the demagnetization process.

[0080] The magnetic induction intensity B is the comprehensive result of the external magnetic field and the magnetization characteristics of the material itself, directly reflecting the distribution of magnetic domains inside the material. The red area represents a relatively high magnetic induction intensity (0.8 - 0.9 T), that is, there is more remanent magnetism in these areas; the green to blue areas represent a relatively low magnetic induction intensity (<0.3 T), indicating that the magnetization in these areas is basically eliminated. It reflects the gradual disordering process of magnetic domains during the demagnetization process. The B-value distribution in different regions shows that different magnetic fields with different intensities can be more accurately applied during the demagnetization process to achieve global uniform demagnetization.

[0081] According to the magnetic field intensity distribution map during the demagnetization process, such as Figure 5 and Figure 6 , it is possible to accurately know the remanent magnetism situation of the material to be demagnetized under the current conditions. The high-remanent-magnetism regions (corresponding to the high-intensity red regions), the low-remanent-magnetism regions (blue regions). The red high-remanent-magnetism regions require a stronger external magnetic field to ensure magnetic domain flipping; the blue regions do not require excessive magnetic field input, thus avoiding unnecessary energy consumption.

[0082] In the described multiple rounds of optimization and data storage steps: the magnetic field intensity, direction, or time is adjusted as follows:

[0083] The ultimate goal of the demagnetization process is to reduce the remanent magnetism of the material to be demagnetized below the target value. Through multiple rounds of demagnetization operations, the residual magnetic field in the material to be demagnetized can be gradually reduced.

[0084] The magnetic induction intensity B of the material to be demagnetized after demagnetization is measured in real time by a sensor measured , and compared with the target value B target , and the error is calculated:

[0085] ΔB = B target - B measured

[0086] According to the error ΔB, the current intensity I of the next round of demagnetization is adjusted through the proportional gain coefficient k next :

[0087] I next = I current + k·ΔB

[0088] Among them, Icurrent : The current intensity of the current demagnetization round, where k is the gain coefficient preset by the system, used to balance the adjustment speed and stability.

[0089] The physical relationship between the magnetic field strength H and the current I is:

[0090]

[0091] N: The number of turns of the coil; L: The length of the magnetic circuit. Therefore, the magnetic field strength H can be directly controlled by adjusting the current I.

[0092] The goal of parameter optimization is to minimize the cumulative error of multi-round demagnetization, and the objective function is defined as:

[0093]

[0094] is the measured magnetic induction intensity after the t-th round of demagnetization; n is the total number of demagnetization rounds.

[0095] Through reinforcement learning algorithms (such as Q-learning or policy gradient), dynamically adjust the gain coefficient k and the current step size to ensure rapid convergence to the target value.

[0096] If ΔB > 0 (i.e., B measured < B target ):

[0097] It is necessary to enhance the demagnetization effect and increase the current intensity I next (For example: k takes a positive value).

[0098] If ΔB < 0 (i.e., B measured > B target ):

[0099] It is necessary to weaken the demagnetization effect and reduce the current intensity I next (For example: k takes a negative value or reduces the absolute value).

[0100] Magnetic field direction adjustment: According to the residual magnetic distribution map of the previous round of demagnetization, adjust the direction of a specific area. If a relatively high residual magnetism is detected in a certain part of the material to be demagnetized, this area can be processed by changing the arrangement angle of the permanent magnets.

[0101] Time adjustment: For materials with high remanence, extend the demagnetization time to ensure sufficient magnetic field action; for materials with low remanence, shorten the time to improve efficiency.

[0102] For materials with complex shapes, optimize the magnetic field distribution in zones, specifically including:

[0103] Complex-shaped materials can lead to uneven magnetic field distribution, and "magnetic hysteresis dead corners" are likely to form in some areas, resulting in relatively high residual magnetism. Through zoning optimization, different magnetic field intensities and directions can be set for different regions to ensure global uniform degaussing.

[0104] Zoning optimization method: Zoning detection → Zoning processing → Simulation verification → Dynamic adjustment.

[0105] Zoning detection: Use high-precision magnetic field sensors to obtain the magnetic field distribution map of complex-shaped materials; divide the material into multiple regions and mark the key parts with high residual magnetism intensity.

[0106] Zoning processing: Optimize the magnetic field intensity and direction for each region separately.

[0107] Simulation verification: Use simulation software such as Maxwell to simulate the magnetic field distribution of complex-shaped materials under the condition of zoned degaussing and verify the optimization effect.

[0108] Dynamic adjustment: According to the detection results after each round of degaussing, further refine the zoning, and increase the degaussing intensity or extend the time for regions with high residual magnetism.

[0109] Based on the same inventive concept, the embodiment of the present application also provides a magnetic material degaussing system based on an artificial intelligence control system. Each module included is used to execute each step in the corresponding embodiment of the magnetic material degaussing method based on the artificial intelligence control system.

[0110] In the above embodiments disclosed in the present application, the method is described in detail. The method of the present application can be implemented by various forms of devices. Therefore, the present application also discloses a magnetic material degaussing system based on an artificial intelligence control system. Specific embodiments are given below for detailed description.

[0111] Please refer to the atta Figure 7 , Figure 7 which is a schematic structural diagram of a magnetic material degaussing system based on an artificial intelligence control system disclosed in the embodiment of the present application. The system includes:

[0112] Initial data acquisition module: Configured to place the material to be degaussed in the detection area, and use sensors to collect its residual magnetism intensity, shape, material, and temperature and humidity environment parameters in real time. The collected data is transmitted to the artificial intelligence control system after A / D conversion;

[0113] Degaussing determination module: Configured to compare the data collected by the artificial intelligence control system with a preset magnetic requirement threshold. It can be set that the residual magnetism intensity ≤ 0.05 mT is the qualified standard. If the magnetism of the material to be degaussed exceeds the threshold, it enters the degaussing stage; otherwise, the material to be degaussed directly passes through;

[0114] Demagnetization execution module: Configured to, based on the initial detection data, the artificial intelligence control system uses an optimization algorithm to calculate the required demagnetization parameters, including magnetic field strength (A / m) and / or magnetic field direction, and accordingly determines the arrangement of permanent magnets in the demagnetization device to perform a demagnetization operation on the material to be demagnetized; after demagnetization is completed, the residual magnetic strength of the material to be demagnetized is detected again. If the residual magnetic strength of the material to be demagnetized is lower than the preset threshold, the demagnetization process ends. If the set standard is not reached, the artificial intelligence control system adjusts the parameters and re-executes the demagnetization operation;

[0115] Multi-round optimization and data storage module: Configured to, based on historical demagnetization data, the artificial intelligence control system optimizes subsequent demagnetization parameters through a reinforcement learning algorithm, adjusts the magnetic field strength, direction, and / or time according to the demagnetization effect of the previous round; for materials to be demagnetized with complex shapes, adopts the methods of partition detection, partition processing, simulation verification, and dynamic adjustment to optimize the magnetic field distribution; repeats data acquisition and demagnetization operations until the material to be demagnetized meets the target magnetic requirements, then the system stops the demagnetization process and records the data.

[0116] The beneficial effects of the magnetic material demagnetization system based on the artificial intelligence control system of the present invention are mainly reflected in the following aspects:

[0117] I. Significantly improve demagnetization efficiency: By using an artificial intelligence control system for intelligent parameter optimization, the present invention can dynamically adjust demagnetization parameters such as current intensity, frequency, and time according to the real-time data of the material to be demagnetized, so that under the same conditions, the demagnetization efficiency is increased by 30%-50%. This improvement not only shortens the demagnetization cycle but also improves the overall throughput of the production line.

[0118] II. Achieve high efficiency and energy saving: The closed-loop feedback mechanism and high-precision sensors of the present invention can monitor the residual magnetic state of magnetic materials in real time and perform precise control through AI algorithms. This control method can avoid material damage or waste caused by over-demagnetization, and at the same time, by dynamically optimizing the magnetic field strength and direction, significantly reduce the power consumption during the demagnetization process, and the energy consumption is reduced by about 20%-40%.

[0119] III. Ensure precise demagnetization effect: Through multi-round data acquisition and parameter optimization, the present invention can control the residual magnetic amount of the material to be demagnetized below 0.05 mT, meeting international standards and meeting the requirements of high-precision fields. This precise demagnetization effect improves the quality and reliability of products.

[0120] IV. Enhance the universality and automation level of the system: The present invention is applicable to demagnetization processing of various materials and complex geometric shapes, with wide applicability. At the same time, by realizing the automation process of real-time data acquisition, transmission, detection, and demagnetization operation of materials, significantly reducing manual intervention, improving the intelligent level of the production line, and providing strong support for the deep integration of batch production lines.

[0121] In summary, the degaussing system of magnetic materials based on the artificial intelligence control system provided by the present invention shows significant beneficial effects in aspects such as improving degaussing efficiency, achieving high energy efficiency, ensuring accurate degaussing effect, and enhancing the universality and automation level of the system, and has broad market application prospects and important economic value.

[0122] In the initial data acquisition module, the material to be degaussed is carefully and precisely placed in a carefully designed detection area. This detection area has a special layout to ensure that the data obtained by the sensors is highly reliable and representative. In the detection area, a variety of advanced sensors are distributed, each performing its own function and working together to complete the real-time acquisition of various key parameters of the material.

[0123] As one of the core indicators for measuring the degaussing demand of magnetic materials, the residual magnetic intensity is measured by a high-sensitivity magnetic field sensor. This sensor adopts advanced magnetoelectric conversion technology and can accurately sense extremely weak magnetic field changes around the material and convert them into electrical signals. Whether it is the inherent magnetic field remaining in the material due to processing, storage, etc., or the additional magnetic field generated under the interference of the external environment, it can be accurately captured, providing a key basis for subsequent judgment of whether the material needs degaussing and determination of degaussing parameters.

[0124] For the acquisition of the material shape, a non-contact optical measurement sensor and a structure scanning sensor are combined. The optical measurement sensor uses the principle of optical imaging to scan the surface of the material in all directions to obtain its two-dimensional contour information; the structure scanning sensor emits electromagnetic waves with a specific frequency to penetrate a certain depth of the material surface and detect its internal structure characteristics. The data of the two complement each other, and after being processed by algorithms, an accurate three-dimensional shape model of the material can be constructed, recording in detail information such as the size, geometric shape, internal holes or defects of the material, which is of great significance for subsequent determination of the arrangement of permanent magnets in the degaussing device and optimization of the magnetic field distribution.

[0125] The identification and analysis of the material are jointly completed by a spectral analyzer and a component detection sensor. The spectral analyzer irradiates the surface of the material with light of a specific wavelength and analyzes the main element composition and chemical bond structure of the material according to the absorption, reflection, and scattering characteristics of the material to light; the component detection sensor uses microelectromechanical sensing technology to accurately measure the content of various trace elements in the material. Through the data fusion and comparison of the two, not only can the material type, such as ferromagnetic materials, ferrimagnetic materials, etc., be accurately judged, but also detailed chemical composition information of the material can be obtained, providing strong support for formulating personalized degaussing schemes according to the material characteristics.

[0126] In terms of environmental parameters, the temperature and humidity environmental parameters have a non-negligible impact on the magnetic performance of magnetic materials and the demagnetization process. The temperature sensor adopts high-precision thermistor technology and can quickly respond to changes in the ambient temperature. The humidity sensor is based on the principle of capacitive sensing and can measure the relative humidity of the environment in real time. These two sensors transmit the collected temperature and humidity data in a timely manner for subsequent compensation and correction of relevant parameters during the demagnetization process to ensure that the demagnetization effect is not interfered by environmental factors.

[0127] All the analog signals collected by the sensors are quickly and accurately converted into digital signals by the A / D conversion module. The A / D conversion module uses high-speed and high-precision conversion chips, which can effectively reduce the errors in the data conversion process. The converted digital signals are stably and quickly transmitted to the artificial intelligence control system through high-speed data transmission buses such as SPI and USB. After receiving the data, the artificial intelligence control system integrates, stores, and preliminarily analyzes it, laying a solid data foundation for subsequent determination of whether demagnetization is required and calculation of demagnetization parameters.

[0128] In the demagnetization determination module, after the artificial intelligence control system receives a series of information including the residual magnetic intensity, shape, material, and temperature and humidity environmental parameters transmitted from the data acquisition module, it quickly starts the built-in data analysis and determination program. The system will first extract the residual magnetic intensity data and accurately compare it with the pre-set magnetic requirement threshold. In the present invention, it is clearly defined that the residual magnetic intensity ≤ 0.05 mT is used as the qualified standard. This standard is determined through verification of a large amount of experimental data and in combination with the usage requirements of magnetic materials in the industry, and can ensure that the processed magnetic materials meet the needs of the vast majority of application scenarios.

[0129] In the demagnetization execution module, as Figure 2 shown, the demagnetization device includes a demagnetizing coil and an alternating arrangement of multiple permanent magnets.

[0130] The arrangement direction and intensity of the permanent magnets will affect the demagnetization effect. By changing the N and S poles of the permanent magnets, the magnetic field direction of the action of the permanent magnets on the magnetic material can be changed. Therefore, arranging the permanent magnets reasonably can form a uniform magnetic field in the target area to achieve complete demagnetization. The arrangement method of the permanent magnets is determined through the analysis of the initial magnetic field direction and the residual magnetic intensity distribution of the material to be demagnetized detected by the sensor.

[0131] According to the magnetic field intensity distribution diagram during the demagnetization process, as Figure 5 and Figure 6 , the residual magnetic situation of the material to be demagnetized in the current situation can be accurately known. The high residual magnetic area (corresponding to the high-intensity red area), the low residual magnetic area (blue area). The high residual magnetic red area requires a stronger external magnetic field to ensure magnetic domain flipping; the blue area does not require excessive magnetic field input, thus avoiding unnecessary energy consumption.

[0132] The arrangement of permanent magnets can be divided into:

[0133] Parallel arrangement: Suitable for uniformly distributed long strip materials, providing a strong magnetic field in a single direction.

[0134] Cross arrangement: For materials with complex geometries, a multi-directional magnetic field is formed through cross arrangement to enhance the demagnetization effect.

[0135] Array arrangement: Used for demagnetization of large-area materials to ensure uniform magnetic field coverage.

[0136] Here, a polar alternating array arrangement is used. To avoid waste, three permanent magnets are selected for arrangement as follows:

[0137] When the magnetic field on the surface of the material to be measured is the N pole, it is eliminated by the N-S-N array composed of 3 magnets; when the surface magnetic field is the S pole, it is eliminated by the S-N of the latter two magnets; when the surface is not magnetized, after the first magnet magnetizes the material to be measured, the S-N array composed of the latter two magnets can eliminate the influence.

[0138] In the demagnetization execution module, the current intensity and frequency are dynamically optimized:

[0139] Since the remanence characteristics of magnetic materials are closely related to the intensity and frequency of the applied magnetic field. Different materials require different combinations of current intensity and frequency to achieve the best demagnetization effect. The demagnetization process can gradually reduce the magnetic induction intensity through an alternating magnetic field, so that the remanence inside the material gradually decreases below the target value.

[0140] Current intensity (A): According to Ampere's circuital law, there is N: Number of turns of the coil; l: Magnetic path length. It can be seen that the intensity H of the applied magnetic field is proportional to the current I. Dynamically adjusting the current intensity can control the magnetic field intensity.

[0141] Frequency (Hz): The frequency of the magnetic field determines the rate of magnetic domain flipping. High frequency can quickly flip magnetic domains, and low frequency is suitable for fine adjustment. The dynamic response formula between the remanence Br and the applied magnetic field frequency f is B r =B r0 .e -af ,

[0142] where, B r0 : Static remanence; f: Applied magnetic field frequency (Hz); a: Constant related to the magnetic hysteresis characteristics of the material; e is the natural constant.

[0143] A high-frequency applied magnetic field can quickly flip magnetic domains, reduce the ordered arrangement between magnetic domains, and thus reduce the remanence Br; under low-frequency conditions, the magnetic domain flipping is slower, the magnetic hysteresis effect is stronger, and the remanence Br is larger.

[0144] Therefore, it is necessary to monitor the magnetic field strength B value of the material to be degaussed in real time through a sensor and feed the data back to the artificial intelligence control system.

[0145] If the initial residual magnetic intensity is high, the artificial intelligence control system will select a large current intensity and high frequency; when the magnetic field gradually weakens, the system will gradually reduce the current intensity and frequency.

[0146] The optimization process is divided into an initial stage, an intermediate stage, and an end stage.

[0147] Initial stage: In the high residual magnetic state, an alternating magnetic field with a high current intensity and high frequency is used to quickly flip the magnetic domains inside the material to be degaussed and reduce the hysteresis phenomenon.

[0148] Intermediate stage: Monitor the residual magnetic intensity, reduce the current intensity according to the feedback result, gradually reduce the ordered arrangement of magnetic domains, and optimize the frequency to adapt to the characteristics of different materials to be degaussed.

[0149] End stage: Use a magnetic field with a low current intensity and low frequency to perform fine degaussing on the material to be degaussed and eliminate the weak residual magnetism.

[0150] In the multi-round optimization and data storage module: The magnetic field strength, direction, or time is adjusted as follows:

[0151] The ultimate goal of the degaussing process is to reduce the residual magnetism of the material to be degaussed below the target value. Through multiple rounds of degaussing operations, the residual magnetic field in the material to be degaussed can be gradually reduced.

[0152] Measure the magnetic induction intensity B of the material to be degaussed in real time through a sensor measured , and compare it with the target value B target , and calculate the error:

[0153] ΔB = B target - B measured

[0154] According to the error ΔB, adjust the current intensity I of the next round of degaussing through the proportional gain coefficient k next :

[0155] I next = I current + k·ΔB

[0156] Among them, I current : The current intensity of the current degaussing round, and k is the gain coefficient preset by the system, which is used to balance the adjustment speed and stability.

[0157] The physical relationship between the magnetic field strength H and the current I is:

[0158]

[0159] N: Number of turns of the coil; L: Length of the magnetic circuit. Therefore, the magnetic field strength H can be directly controlled by adjusting the current I.

[0160] The goal of parameter optimization is to minimize the cumulative error of multi-round demagnetization, and the objective function is defined as:

[0161]

[0162] is the measured magnetic induction intensity after the t-th round of demagnetization; n is the total number of demagnetization rounds.

[0163] Through reinforcement learning algorithms (such as Q-learning or policy gradient), the gain coefficient k and the current step size are dynamically adjusted to ensure rapid convergence to the target value.

[0164] If ΔB > 0 (i.e., B measured < B target ):

[0165] It is necessary to enhance the demagnetization effect and increase the current intensity I next (For example: k takes a positive value).

[0166] If ΔB < 0 (i.e., B measured > B target ):

[0167] It is necessary to weaken the demagnetization effect and reduce the current intensity I next (For example: k takes a negative value or reduces the absolute value).

[0168] Magnetic field direction adjustment: According to the residual magnetic distribution map of the previous round of demagnetization, the direction of a specific area is adjusted. If a high residual magnetism is detected in a certain part of the material to be demagnetized, this area can be processed by changing the arrangement angle of the permanent magnets.

[0169] Time adjustment: For materials with high remanence, extend the demagnetization time to ensure sufficient magnetic field action; for materials with low remanence, shorten the time to improve efficiency.

[0170] For materials with complex shapes, the magnetic field distribution is optimized by zones, specifically including:

[0171] Materials with complex shapes can cause uneven magnetic field distribution, and "magnetic hysteresis dead corners" are likely to form in some areas, resulting in high residual magnetism. Through zone optimization, different magnetic field strengths and directions can be set for different areas to ensure global uniform demagnetization.

[0172] Zone optimization method: Zone detection → Zone processing → Simulation verification → Dynamic adjustment.

[0173] Partition detection: Use a high-precision magnetic field sensor to obtain the magnetic field distribution map of materials with complex shapes; divide the material into multiple regions and mark the key parts with high residual magnetic intensity.

[0174] Partition processing: Optimize the magnetic field intensity and direction for each region separately.

[0175] Simulation verification: Use simulation software such as Maxwell to simulate the magnetic field distribution of materials with complex shapes under the condition of partition degaussing, and verify the optimization effect.

[0176] Dynamic adjustment: According to the detection results after each round of degaussing, further refine the partition, and increase the degaussing intensity or extend the time for regions with high residual magnetism.

[0177] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium provided in the embodiments of the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments of the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments of the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0178] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0179] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for demagnetizing magnetic materials based on an artificial intelligence control system, characterized in that: The steps include: Initial data collection steps: Place the material to be demagnetized in the detection area, and use sensors to collect its residual magnetic intensity, shape, material, and temperature and humidity environmental parameters in real time. The collected data is transmitted to the artificial intelligence control system after A / D conversion; Demagnetization determination step: the artificial intelligence control system compares the collected data with the preset magnetic requirement threshold. If the magnetism of the material to be demagnetized exceeds the threshold, it enters the demagnetization stage, otherwise the material to be demagnetized passes directly; Demagnetization execution steps: Based on the initial detection data, the artificial intelligence control system uses an optimization algorithm to calculate the required demagnetization parameters, including magnetic field strength and / or magnetic field direction, and determines the arrangement of permanent magnets in the demagnetization equipment based on this, and performs demagnetization operations on the materials to be demagnetized; after the demagnetization is completed, the residual magnetic strength of the materials to be demagnetized is detected again. If the residual magnetic strength of the materials to be demagnetized is lower than the preset threshold, the demagnetization process ends. If it does not meet the set standards, the artificial intelligence control system adjusts the parameters and re-executes the demagnetization operation; Multiple rounds of optimization and data storage steps: The artificial intelligence control system optimizes subsequent demagnetization parameters based on historical demagnetization data through a reinforcement learning algorithm, and adjusts the magnetic field strength, direction and / or time according to the effect of the previous round of demagnetization; for complex-shaped materials to be demagnetized, the magnetic field distribution is optimized by partition detection, partition processing, simulation verification, and dynamic adjustment; data collection and demagnetization operations are repeated until the material to be demagnetized meets the target magnetic requirements, at which time the system stops the demagnetization process and records the data.

2. The method for demagnetizing magnetic materials based on an artificial intelligence control system according to claim 1, characterized in that: In the demagnetization execution step, the permanent magnet arrangement is determined according to the initial magnetic field direction and residual magnetic intensity distribution of the material to be demagnetized detected by the sensor, and the permanent magnet arrangement includes parallel arrangement, cross arrangement and array arrangement; When an alternating polarity array is used, different permanent magnet combinations are used for demagnetization according to the different states of the surface magnetic field of the material to be tested. If the surface magnetic field is N-pole, an array of three magnets NSN is used to eliminate it; if the surface magnetic field is S-pole, the last two magnets SN are used to eliminate it; if the surface is not magnetized, the first magnet is used to magnetize the material to be tested, and then the last two magnets form an array SN to eliminate the influence.

3. The method for demagnetizing magnetic materials based on an artificial intelligence control system according to claim 1, characterized in that: The dynamic optimization of the current intensity and frequency in the demagnetization execution step specifically includes: Since the residual magnetic properties of magnetic materials are closely related to the strength and frequency of the external magnetic field, different magnetic materials require different current strength and frequency combinations to achieve the best demagnetization effect. The demagnetization process gradually reduces the magnetic induction intensity through the alternating magnetic field, so that the residual magnetism inside the material gradually decreases to below the target value. The sensor monitors the magnetic field strength B value of the material to be demagnetized in real time, and feeds the data back to the artificial intelligence control system; if the initial residual magnetic intensity is high, the artificial intelligence control system will select a larger current intensity and high frequency; when the magnetic field gradually weakens, the system gradually reduces the current intensity and frequency.

4. The method for demagnetizing magnetic materials based on an artificial intelligence control system according to claim 1, characterized in that: In the multiple rounds of optimization and data storage steps, the magnetic field strength, direction, and time are adjusted as follows: The ultimate goal of the demagnetization process is to reduce the residual magnetism of the material to be demagnetized to below the target value. Through multiple rounds of demagnetization operations, the residual magnetic field in the material to be demagnetized can be gradually reduced; The sensor measures the magnetic induction intensity B of the demagnetized material in real time measured and the target value B target Compare and calculate the error: ΔB=B target -B measuered According to the error ΔB, the current intensity I of the next round of demagnetization is adjusted by the proportional gain coefficient k. next : I next =I current +k·ΔB Among them, I current : The current intensity of the current demagnetization round, k is the gain coefficient preset by the system, which is used to balance the adjustment speed and stability; The physical relationship between magnetic field intensity H and current I is: N: number of coil turns; L: length of magnetic circuit. The magnetic field strength H can be directly controlled by adjusting the current I; The goal of parameter optimization is to minimize the cumulative error of multiple rounds of demagnetization. The objective function is defined as: is the measured magnetic induction intensity after the tth round of demagnetization; n is the total number of demagnetization rounds; Through the reinforcement learning algorithm, the gain coefficient k and current step size are dynamically adjusted to ensure rapid convergence to the target value; If ΔB>0, the demagnetization effect needs to be enhanced and the current intensity I next ; If ΔB<0, the demagnetization effect needs to be weakened and the current intensity I next ; Adjustment of magnetic field direction: Adjust the direction of a specific area according to the residual magnetism distribution diagram of the previous demagnetization; if it is detected that the residual magnetism of a certain part of the material to be demagnetized is high, the area can be processed by changing the arrangement angle of the permanent magnet; Time adjustment: For high remanence materials, extend the demagnetization time to ensure that the magnetic field is fully effective; for low remanence materials, shorten the time to improve efficiency.

5. The method for demagnetizing magnetic materials based on an artificial intelligence control system according to claim 1, characterized in that: In the multiple rounds of optimization and data storage steps, the partition optimization magnetic field distribution for complex-shaped materials specifically includes: Use high-precision magnetic field sensors to obtain the magnetic field distribution map of complex-shaped materials, divide the materials into multiple areas, and mark the key parts with high residual magnetic intensity; Optimize magnetic field strength and direction for each region individually; Use simulation software to simulate the magnetic field distribution of complex-shaped materials under partition demagnetization conditions to verify the optimization effect; Based on the test results after each round of demagnetization, the partitions are further refined, and the demagnetization intensity is increased or the time is extended for areas with high residual magnetism.

6. A magnetic material demagnetization system based on an artificial intelligence control system, characterized in that: include: Initial data acquisition module: It is configured to place the material to be demagnetized in the detection area, and use sensors to collect its residual magnetic intensity, shape, material, and temperature and humidity environmental parameters in real time. The collected data is transmitted to the artificial intelligence control system after A / D conversion; Demagnetization determination module: configured such that the artificial intelligence control system compares the collected data with a preset magnetic requirement threshold. If the magnetism of the material to be demagnetized exceeds the threshold, the demagnetization stage is entered; otherwise, the material to be demagnetized passes directly; Demagnetization execution module: configured such that, based on the initial detection data, the artificial intelligence control system uses an optimization algorithm to calculate the required demagnetization parameters, including magnetic field strength and / or magnetic field direction, and determines the arrangement of permanent magnets in the demagnetization equipment based on this, and performs a demagnetization operation on the material to be demagnetized; after the demagnetization is completed, the residual magnetic strength of the material to be demagnetized is detected again. If the residual magnetic strength of the material to be demagnetized is lower than a preset threshold, the demagnetization process ends. If the set standard is not reached, the artificial intelligence control system adjusts the parameters and re-executes the demagnetization operation; Multi-round optimization and data storage module: The artificial intelligence control system is configured to optimize subsequent demagnetization parameters based on historical demagnetization data through a reinforcement learning algorithm, and adjust the magnetic field strength, direction and / or time according to the effect of the previous round of demagnetization; for complex-shaped materials to be demagnetized, the magnetic field distribution is optimized by partition detection, partition processing, simulation verification, and dynamic adjustment; data collection and demagnetization operations are repeated until the material to be demagnetized meets the target magnetic requirements, and the system stops the demagnetization process and records the data.

7. The magnetic material demagnetization system based on artificial intelligence control system according to claim 6 is characterized in that: In the demagnetization execution module, the permanent magnet arrangement is determined according to the initial magnetic field direction and residual magnetic intensity distribution of the material to be demagnetized detected by the sensor, and the permanent magnet arrangement includes parallel arrangement, cross arrangement and array arrangement; When an alternating polarity array is used, different permanent magnet combinations are used for demagnetization according to the different states of the surface magnetic field of the material to be tested. If the surface magnetic field is N-pole, an array of three magnets NSN is used to eliminate it; if the surface magnetic field is S-pole, the last two magnets SN are used to eliminate it; if the surface is not magnetized, the first magnet is used to magnetize the material to be tested, and then the last two magnets form an array SN to eliminate the influence.

8. The magnetic material demagnetization system based on artificial intelligence control system according to claim 6 is characterized in that: In the demagnetization execution module, the dynamic optimization of the current intensity and frequency specifically includes: Since the residual magnetic properties of magnetic materials are closely related to the strength and frequency of the external magnetic field, different magnetic materials require different current strength and frequency combinations to achieve the best demagnetization effect. The demagnetization process gradually reduces the magnetic induction intensity through the alternating magnetic field, so that the residual magnetism inside the material gradually decreases to below the target value. The sensor monitors the magnetic field strength B value of the material to be demagnetized in real time, and feeds the data back to the artificial intelligence control system; if the initial residual magnetic intensity is high, the artificial intelligence control system will select a larger current intensity and high frequency; when the magnetic field gradually weakens, the system gradually reduces the current intensity and frequency.

9. The magnetic material demagnetization system based on artificial intelligence control system according to claim 6, characterized in that: In the multi-round optimization and data storage module, the magnetic field strength, direction, and time are adjusted as follows: The ultimate goal of the demagnetization process is to reduce the residual magnetism of the material to be demagnetized to below the target value. Through multiple rounds of demagnetization operations, the residual magnetic field in the material to be demagnetized can be gradually reduced; The sensor measures the magnetic induction intensity B of the demagnetized material in real time measured and the target value B target Compare and calculate the error: ΔB=B target -B measured According to the error ΔB, the current intensity I of the next round of demagnetization is adjusted by the proportional gain coefficient k. next : I next =I current +k·ΔB Among them, I current : The current intensity of the current demagnetization round, k is the gain coefficient preset by the system, which is used to balance the adjustment speed and stability; The physical relationship between magnetic field intensity H and current I is: N: number of coil turns; L: length of magnetic circuit. The magnetic field strength H can be directly controlled by adjusting the current I; The goal of parameter optimization is to minimize the cumulative error of multiple rounds of demagnetization. The objective function is defined as: is the measured magnetic induction intensity after the tth round of demagnetization; n is the total number of demagnetization rounds; Through the reinforcement learning algorithm, the gain coefficient k and current step size are dynamically adjusted to ensure rapid convergence to the target value; If ΔB>0, the demagnetization effect needs to be enhanced and the current intensity I next ; If ΔB<0, the demagnetization effect needs to be weakened and the current intensity I next ; Adjustment of magnetic field direction: Adjust the direction of a specific area according to the residual magnetism distribution diagram of the previous demagnetization; if it is detected that the residual magnetism of a certain part of the material to be demagnetized is high, the area can be processed by changing the arrangement angle of the permanent magnet; Time adjustment: For high remanence materials, extend the demagnetization time to ensure that the magnetic field is fully effective; for low remanence materials, shorten the time to improve efficiency.

10. The magnetic material demagnetization system based on artificial intelligence control system according to claim 6, characterized in that: In the multi-round optimization and data storage module, the partition optimization magnetic field distribution for complex-shaped materials specifically includes: Use high-precision magnetic field sensors to obtain the magnetic field distribution map of complex-shaped materials, divide the materials into multiple areas, and mark the key parts with high residual magnetic intensity; Optimize magnetic field strength and direction for each region individually; Use simulation software to simulate the magnetic field distribution of complex-shaped materials under partition demagnetization conditions to verify the optimization effect; Based on the test results after each round of demagnetization, the partitions are further refined, and the demagnetization intensity is increased or the time is extended for areas with high residual magnetism.

Images