An environmental suitability data analysis method for high temperature superconducting magnets

Abstract

The application provides an environmental adaptability data analysis method for a high-temperature superconducting magnet, and belongs to the technical field of process control of computer systems, and comprises the following steps: step 1, monitoring and collecting operation environment parameters of the high-temperature superconducting magnet and a plurality of types of process parameters of the high-temperature superconducting magnet; step 2, determining a real-time growth control coefficient of the high-temperature superconducting magnet and determining a growth environment adaptation coefficient corresponding to each operation environment parameter; step 3, analyzing the growth environment adaptation coefficients corresponding to all the operation environment parameters, and determining a plurality of key operation environment parameters based on an analysis result; step 4, adjusting the key operation environment parameters, and then constructing a simulation model; and step 5, evaluating and optimizing an output result of the simulation model, and then obtaining an optimal parameter combination. The method realizes automatic adjustment of the process parameters of the magnet and the operation environment, and ensures the stability and high efficiency of the magnet in a complex environment.

Description

Technical Field

[0001] This invention relates to the field of process control technology for computer systems, and in particular to a method for analyzing environmental adaptability data for high-temperature superconducting magnets. Background Technology

[0002] High-temperature superconducting magnets are widely used in modern industry and scientific research, especially in high-tech fields such as magnetic resonance imaging (MRI), particle accelerators, and nuclear magnetic resonance. Due to the unique electromagnetic properties of high-temperature superconducting materials, they can conduct current without resistance at low temperatures in their superconducting state, thereby generating extremely strong magnetic fields. However, the operation of superconducting magnets is extremely demanding in terms of environmental conditions; environmental factors such as temperature, magnetic field, and humidity have a significant impact on superconducting performance.

[0003] Currently, there are various technical solutions for monitoring and controlling the operating environment of superconducting magnets. These include installing multiple sensors to collect environmental parameters such as temperature, pressure, and current in real time, and then adjusting the working state of the superconducting magnet in conjunction with certain process parameters. However, most existing technologies rely on fixed parameter settings or simple feedback control systems, which cannot adjust the magnet's process parameters in a timely and accurate manner according to environmental changes. This results in poor magnet operating stability and low efficiency. The main technical shortcomings of current solutions are: existing technologies lack flexibility in dealing with dynamic changes in the operating environment of high-temperature superconducting magnets, and cannot quickly respond to and adjust magnet process parameters, easily leading to magnet performance degradation or even failure.

[0004] Therefore, the present invention provides a method for analyzing environmental adaptability data for high-temperature superconducting magnets. Summary of the Invention

[0005] This invention provides a method for analyzing the environmental adaptability of high-temperature superconducting magnets, addressing the shortcomings of existing technologies that cannot quickly respond to changes in the operating environment, leading to a decrease in magnet performance. This invention collects the operating environment parameters of the high-temperature superconducting magnet through preset sensors, and generates real-time growth control coefficients and environmental adaptability coefficients by combining them with process parameters. By analyzing and optimizing these parameters, the invention ultimately achieves automatic adjustment of the magnet's process parameters and operating environment, ensuring the stability and efficiency of the magnet in complex environments.

[0006] This invention provides a method for analyzing environmental adaptability data of high-temperature superconducting magnets, comprising:

[0007] Step 1: Collect the operating environment parameters of the high-temperature superconducting magnet through preset sensors. At the same time, monitor and collect several types of process parameters of the high-temperature superconducting magnet based on preset monitoring tools.

[0008] Step 2: Determine the real-time growth control coefficient of high-temperature superconducting magnets based on the process parameters of several types of high-temperature superconducting magnets, and determine the growth environment adaptation coefficient corresponding to each operating environment parameter in combination with the operating environment parameters of each high-temperature superconducting magnet;

[0009] Step 3: Analyze the growth environment adaptability coefficients corresponding to all operating environment parameters, and determine several key operating environment parameters based on the analysis results;

[0010] Step 4: Adjust the key operating environment parameters based on the growth environment adaptability coefficient, and then construct a simulation model based on several types of process parameters of high-temperature superconducting magnets and the adjusted key operating environment parameters of the magnets;

[0011] Step 5: Evaluate and optimize the output of the simulation model, and then obtain the optimal combination of process parameters for several types of high-temperature superconducting magnets and the operating environment parameters of the high-temperature superconducting magnets based on the optimized simulation model.

[0012] The present invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets, which includes preset sensors such as a temperature sensor, a pressure sensor, a humidity sensor, a vibration sensor, and a magnetic field sensor.

[0013] Pre-set monitoring tools include: current monitoring tool, voltage monitoring tool, cooling system monitoring tool, strain monitoring tool, and power monitoring tool.

[0014] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets, which determines the real-time growth control coefficients of high-temperature superconducting magnets based on process parameters of several types of high-temperature superconducting magnets, including:

[0015] ;in, denoted as the real-time growth control coefficient of the high-temperature superconducting magnet at time t. Let be the real-time value of the i-th process parameter at time t. Let be the weighting coefficient corresponding to the i-th process parameter, and n be the number of process parameter types. Let j be the real-time value of the j-th process parameter at time t. Let be the weighting coefficient corresponding to the interaction between the i-th process parameter and the j-th process parameter. Let i be the preset initial influence value of the i-th process parameter. It is the time decay constant corresponding to the i-th process parameter. Let t be the time from the initial time to time t. The preset basic weights are the values ​​corresponding to the i-th process parameter. The interaction weights are the values ​​corresponding to the i-th process parameter. This represents the time decay weight corresponding to the i-th process parameter.

[0016] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets, which determines the growth environment adaptability coefficient corresponding to each operating environment parameter by combining the operating environment parameters of each high-temperature superconducting magnet, including:

[0017] ;in, It is the growth environment adaptability coefficient of the k-th environmental parameter at time t. denoted as the real-time growth control coefficient of the high-temperature superconducting magnet at time t. It is the preset optimal growth control coefficient for high-temperature superconducting magnets under ideal conditions. It is the real-time value of the k-th environmental parameter at time t. It is the preset optimal value of the k-th environmental parameter. It is the preset standard value of the k-th environmental parameter. It is the time decay coefficient corresponding to the k-th environmental parameter. Let t be the time from the initial time to time t.

[0018] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets. It analyzes the growth environment adaptability coefficients corresponding to all operating environment parameters and determines several key operating environment parameters based on the analysis results, including:

[0019] The input dataset is constructed based on the operating environment parameters and the growth environment adaptation coefficient.

[0020] Based on a pre-set training algorithm, similar data points in the input dataset are mapped to similar positions in the network topology, thereby mapping the data distribution in the input dataset into a three-dimensional topological grid. Each cell of the network represents a combination of operating environment parameters and growth environment adaptation coefficients with similar characteristics.

[0021] Based on a preset analysis algorithm, several operating environment parameters are determined by analyzing the three-dimensional topology network.

[0022] This invention provides a data analysis method for environmental adaptability of high-temperature superconducting magnets. Based on a preset training algorithm, it maps similar data points in the input dataset to similar positions in a network topology, thereby mapping the data distribution in the input dataset into a three-dimensional topological mesh. The method includes:

[0023] A three-dimensional mesh is constructed based on a preset training algorithm, and a random weight vector is assigned to each network unit;

[0024] Based on a preset algorithm, the distance between each set of input data and the weight vector of each network unit in the input dataset is determined, and the network unit with the smallest distance between each set of input data and the weight vector of all network units is selected to map the input data.

[0025] Based on the similarity between each set of input data and the network unit, the weight vector of each network unit is updated. At the same time, the weight vectors of other network units within a preset radius around the network unit are also updated, thereby generating a three-dimensional topological mesh.

[0026] Repeat the above process and evaluate the 3D topology mesh based on the preset error judgment method. Stop the above process when the error between the input dataset and the 3D topology mesh is less than the preset error threshold.

[0027] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets, which adjusts key operating environment parameters based on the growth environment adaptability coefficient, including:

[0028] The key operating environment parameters in the simulation model were adjusted based on the growth environment adaptation coefficient.

[0029] ;in, This is the p-th critical runtime environment parameter after adjustment. For the p-th original critical runtime environment parameter, The preset base weights are the values ​​corresponding to the p-th critical runtime environment parameter. Let be the growth environment adaptability coefficient at time t. To preset the critical value for adaptation to the growth environment, Let be the weight of the growth environment adaptation adjustment term corresponding to the p-th key operating environment parameter. For preset adjustment coefficients, The preset weight is the weight corresponding to the growth item of the p-th key operating environment parameter.

[0030] This invention provides a data analysis method for the environmental adaptability of high-temperature superconducting magnets. The method evaluates and optimizes the output results of a simulation model, and then, based on the optimized simulation model, obtains the optimal combination of process parameters for several types of high-temperature superconducting magnets, as well as the operating environment parameters of the high-temperature superconducting magnets, including:

[0031] Collect all output data from the simulation model and analyze the output data to obtain parameter scores for high-temperature superconducting magnets under different process parameters and environmental parameters;

[0032] The parameter scores of high-temperature superconducting magnets under different process parameters and environmental parameters are compared with the preset performance scores.

[0033] If the parameter score of the high-temperature superconducting magnet is less than the preset performance score, then the process parameters of several types of high-temperature superconducting magnets and the key operating environment parameters of the high-temperature superconducting magnets in the simulation model are adjusted based on the preset optimization algorithm.

[0034] Rerun the simulation model using the adjusted parameter settings and obtain the model output results for evaluation;

[0035] Repeat the above process until the parameter score of the high-temperature superconducting magnet is greater than the preset performance score. The set of scores with the highest scores of the high-temperature superconducting magnet under different process parameters and environmental parameters is determined as the optimal combination of process parameters for several types of magnets and the operating environment parameters of the magnet.

[0036] Compared with the prior art, the beneficial effects of this application are as follows:

[0037] By collecting the operating environment parameters of the high-temperature superconducting magnet through preset sensors and combining them with process parameters, real-time growth control coefficients and environmental adaptability coefficients are generated. By analyzing and optimizing these parameters, the automatic adjustment of the magnet's process parameters and operating environment is finally realized, ensuring the stability and efficiency of the magnet in complex environments. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating a method for analyzing the environmental adaptability of high-temperature superconducting magnets, as provided in an embodiment of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0041] Example 1

[0042] This invention provides a method for analyzing environmental adaptability data of high-temperature superconducting magnets, such as... Figure 1 As shown, it includes:

[0043] Step 1: Collect the operating environment parameters of the high-temperature superconducting magnet through preset sensors. At the same time, monitor and collect several types of process parameters of the high-temperature superconducting magnet based on preset monitoring tools.

[0044] Step 2: Determine the real-time growth control coefficient of high-temperature superconducting magnets based on the process parameters of several types of high-temperature superconducting magnets, and determine the growth environment adaptation coefficient corresponding to each operating environment parameter in combination with the operating environment parameters of each high-temperature superconducting magnet;

[0045] Step 3: Analyze the growth environment adaptability coefficients corresponding to all operating environment parameters, and determine several key operating environment parameters based on the analysis results;

[0046] Step 4: Adjust the key operating environment parameters based on the growth environment adaptability coefficient, and then construct a simulation model based on several types of process parameters of high-temperature superconducting magnets and the adjusted key operating environment parameters of the magnets;

[0047] Step 5: Evaluate and optimize the output of the simulation model, and then obtain the optimal combination of process parameters for several types of high-temperature superconducting magnets and the operating environment parameters of the high-temperature superconducting magnets based on the optimized simulation model.

[0048] In this embodiment, process parameters refer to various technical indicators that affect the performance of a high-temperature superconducting magnet during its manufacturing or operation, including: temperature, current intensity, voltage, cooling fluid pressure, strain, power consumption, and magnetic field strength. For example, during the operation of a high-temperature superconducting magnet, process parameters may include operating temperature, cooling fluid pressure, and current intensity.

[0049] In this embodiment, the real-time growth control coefficient refers to the dynamic evolution coefficient of the performance of the high-temperature superconducting magnet during silicon single crystal growth, as the performance changes with time and environmental conditions. It characterizes the behavior of the magnet under different process parameters and environmental influences, providing guidance for optimizing the silicon single crystal growth process. Silicon single crystal growth typically relies on precise temperature and magnetic field control. The high-temperature superconducting magnet plays a role in stabilizing the magnetic field and reducing energy consumption during crystal growth. However, the performance of the high-temperature superconducting magnet also changes over time and with changes in environmental conditions (such as temperature, humidity, and magnetic field strength). This change needs to be monitored in real time and characterized in the form of control coefficients to ensure the stability and efficiency of the magnet throughout the entire silicon single crystal growth process. For example, suppose that in a certain silicon single crystal growth process, the initial high-temperature superconducting magnet operates at a temperature of 1000℃ with an initial magnetic field strength of 10 Tesla. After a period of time, the ambient temperature gradually rises to 1050℃. At this time, the performance of the magnet begins to change. The real-time growth control coefficient monitors that the magnetic field strength gradually decreases to 9.8 Tesla. In order to ensure that the growth process of the silicon single crystal is not affected, the system adjusts the current in real time according to this control coefficient to compensate for the attenuation of the magnetic field and keep the magnetic field strength stable in the range close to 10 Tesla. This control coefficient will continuously monitor the state of the magnet throughout the entire silicon single crystal growth process to ensure that the magnet can always output stably in the high-temperature environment, thereby improving the quality and efficiency of crystal growth.

[0050] In this embodiment, operating environment parameters refer to the external environmental conditions that affect the performance of high-temperature superconducting magnets. These typically include temperature, humidity, magnetic field strength, and air pressure. For example, the external temperature, humidity, surrounding magnetic field strength, and air pressure during magnet operation are all considered operating environment parameters.

[0051] In this embodiment, the growth environment adaptability coefficient is the adaptability coefficient of the growth performance of a high-temperature superconducting magnet under specific environmental conditions. It is used to measure the adaptability level of the magnet under different operating environments. For example, if the superconducting magnet performs well at a certain ambient temperature, its growth environment adaptability coefficient will be high; while at extreme temperatures, its adaptability may decrease, and the coefficient will become lower.

[0052] In this embodiment, the simulation model is used to simulate the operation of a high-temperature superconducting magnet. By inputting different process parameters and operating environment parameters, its performance is simulated, thereby evaluating the impact of various parameter combinations on the magnet's performance. For example, using the simulation model, different cooling temperatures, current densities, and other parameters can be input to simulate the superconducting performance of the magnet under these conditions.

[0053] The beneficial effects of the above technical solution are: by collecting the operating environment parameters of the high-temperature superconducting magnet through preset sensors, and combining them with process parameters to generate real-time growth control coefficients and environmental adaptability coefficients, and by analyzing and optimizing these parameters, the automatic adjustment of the magnet process parameters and operating environment can be achieved, ensuring the stability and efficiency of the magnet in complex environments.

[0054] Example 2

[0055] This invention provides a method for analyzing environmental adaptability data of high-temperature superconducting magnets, with preset sensors including: a temperature sensor, a pressure sensor, a humidity sensor, a vibration sensor, and a magnetic field sensor.

[0056] Pre-set monitoring tools include: current monitoring tool, voltage monitoring tool, cooling system monitoring tool, strain monitoring tool, and power monitoring tool.

[0057] In this embodiment, the temperature sensor is used to measure the temperature around the magnet or its cooling system to help monitor its operating status at a specific temperature. For example, when a high-temperature superconducting magnet is running, the temperature sensor can measure the ambient temperature or the temperature of the coolant around the magnet to ensure that the temperature is kept within a suitable range for superconductivity.

[0058] In this embodiment, the pressure sensor is used to measure the pressure of the gas or liquid in the magnet system to ensure that the equipment operates under safe pressure conditions. For example, the pressure sensor can monitor the pressure of the coolant to ensure its smooth flow and maintain efficient cooling.

[0059] In this embodiment, the humidity sensor is used to measure the humidity in the operating environment to ensure that the ambient humidity does not have an adverse effect on the operation of the magnet, such as changes in the performance of the insulating material. For example, the humidity sensor can detect the humidity in the laboratory or equipment box where the magnet is located, so as to avoid high humidity affecting the normal operation of the equipment.

[0060] In this embodiment, the vibration sensor is used to detect vibrations in the equipment or operating environment to help monitor mechanical stability and prevent vibrations from affecting the performance of the magnet. For example, the vibration sensor can be mounted on the equipment bracket to detect small vibrations that may affect the precise operation of the magnet.

[0061] In this embodiment, the magnetic field sensor is used to monitor the magnetic field strength around the magnet to ensure that the external magnetic field does not interfere with the operation or measurement of the magnet. For example, during the operation of the superconducting magnet, the magnetic field sensor can monitor the changes in the external interfering magnetic field to prevent it from affecting the performance of the magnet.

[0062] In this embodiment, the current monitoring tool is used to monitor the current flow in the magnet to ensure that the current intensity is within the design range and to avoid current overload or undercurrent. For example, the current monitoring tool can be used to measure the current intensity in the superconducting magnet in real time to ensure its stable superconducting state.

[0063] In this embodiment, the voltage monitoring tool is used to monitor the voltage across the magnet to ensure that the voltage meets the design standards and to avoid voltage fluctuations affecting performance. The voltage monitoring tool can measure the power supply voltage of the high-temperature superconducting magnet to ensure a stable power supply.

[0064] In this embodiment, the cooling system monitoring tool is used to monitor the operation of the magnet cooling system, such as the flow rate, temperature and pressure of the coolant, to ensure efficient cooling. The cooling system monitoring tool can detect the flow rate and temperature of the coolant in the cooling pipes to ensure that the cooling effect meets the requirements of magnet superconductivity.

[0065] In this embodiment, the strain monitoring tool is used to detect the stress and strain of the magnet or its supporting structure to ensure that the equipment is not subjected to excessive mechanical stress during operation. The strain monitoring tool can also be used to measure whether the magnet coil deforms under the action of current to ensure its structural integrity.

[0066] In this embodiment, the power monitoring tool is used to monitor the power consumed by the magnet to ensure that the power is used within the design range and to avoid power waste or insufficiency. The power monitoring tool can measure the power consumption of the superconducting magnet under different current conditions to optimize energy management.

[0067] The beneficial effects of the above technical solution are: by combining multiple sensors such as temperature, pressure, humidity, vibration, and magnetic field, as well as current, voltage, cooling system, strain, and power monitoring tools, comprehensive monitoring of the operating status of high-temperature superconducting magnets can be achieved. The multi-parameter linkage monitoring method can capture subtle changes in the environment and operating status in real time, provide more accurate environmental adaptability analysis, and improve the reliability and safety of high-temperature superconducting magnets under complex working conditions.

[0068] Example 3

[0069] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets, which determines the real-time growth control coefficients of high-temperature superconducting magnets based on several types of process parameters, including:

[0070] in, denoted as the real-time growth control coefficient of the high-temperature superconducting magnet at time t. Let be the real-time value of the i-th process parameter at time t. Let be the weighting coefficient corresponding to the i-th process parameter, and n be the number of process parameter types. Let j be the real-time value of the j-th process parameter at time t. Let be the weighting coefficient corresponding to the interaction between the i-th process parameter and the j-th process parameter. Let i be the preset initial influence value of the i-th process parameter. It is the time decay constant corresponding to the i-th process parameter. Let t be the time from the initial time to time t. The preset basic weights are the values ​​corresponding to the i-th process parameter. The interaction weights are the values ​​corresponding to the i-th process parameter. This represents the time decay weight corresponding to the i-th process parameter.

[0071] In this embodiment, the real-time value of the process parameter refers to the current actual value of a certain process parameter collected at a specific time (e.g., time tt), reflecting the specific state or value of the process parameter at that time. Assuming the process parameter is temperature, the real-time value is the temperature value measured at time tt. For example, the temperature reading of the cooling system at time tt is 77K.

[0072] In this embodiment, the weighting coefficients corresponding to the process parameters are used to measure the degree of influence of a certain process parameter in the overall system. Different process parameters may have different effects on the growth control coefficient of the system. The weighting coefficients are used to reflect this difference. If the current intensity has a greater impact on the system and the humidity has a smaller impact, the weighting coefficient of the current can be set to 0.5 and the weighting coefficient of the humidity can be set to 0.1.

[0073] In this embodiment, the number of types of process parameters refers to the total number of types of process parameters involved in the calculation, that is, how many different types of process parameters will affect the growth control coefficient of the system. If the process parameters of the high-temperature superconducting magnet include five parameters such as temperature, current, pressure, humidity, and magnetic field strength, then the number of types of process parameters nn is 5.

[0074] In this embodiment, the weighting coefficient corresponding to the interaction of process parameters is used to represent the degree of influence of the interaction between two different process parameters on the system. Different combinations of process parameters may have a combined effect on the system performance, and this weighting coefficient is used to quantify the influence of this combined effect. Assuming that the interaction between temperature and current intensity has a significant impact on the system, their interaction weighting coefficient may be relatively large, such as 0.3, while the interaction between humidity and pressure has a smaller impact, and its weighting coefficient may be set to 0.05.

[0075] In this embodiment, the preset initial influence value of the process parameters refers to the degree of initial influence of each process parameter on the system when the system starts running. It is based on the parameters preset during the system design and is used to reflect the influence of these parameters in the early stage of operation. Assuming that the temperature of the cooling system plays a very critical role in the early operation of the superconducting magnet, its preset initial influence value may be set to a high value, such as 1.0.

[0076] In this embodiment, the time decay constant and its value range are used to describe the degree to which the influence of process parameters on the system gradually decreases over time. As time progresses, the influence of certain process parameters may gradually weaken. The decay constant is used to control this rate of change. The decay constant is usually a positive number, with a common value range between 0 and 1. The smaller the value, the faster the decay; the larger the value, the slower the decay. If the time decay constant for a certain process parameter is set to 0.9, it means that the influence of that parameter decays slowly; while setting it to 0.2 indicates that the influence of that parameter decays quickly.

[0077] In this embodiment, the interaction weight corresponding to the process parameter refers to the weight of the interaction between a certain process parameter and other process parameters in the overall model. The interaction weight is used to measure the impact of a specific process parameter on the system when it interacts with other parameters. If the interaction between current intensity and magnetic field intensity has a significant impact on the system, then their interaction weight may be set to 0.8, while the interaction between temperature and humidity has a smaller impact on the system, and the interaction weight may be only 0.1.

[0078] In this embodiment, the time decay weight is a weighting factor used to characterize how the influence of a certain process parameter on the system changes over time. As time goes by, the weight gradually decreases, indicating that the influence of the process parameter gradually declines. Suppose that the time decay weight of a certain process parameter is 0.7, which means that its influence gradually decreases over time, while the time decay weight of another parameter is 0.3, indicating that its influence weakens faster.

[0079] The beneficial effects of the above technical solution are as follows: by integrating multiple process parameters and their interaction relationships, the real-time growth control coefficient of high-temperature superconducting magnets is dynamically calculated. Time decay weight and interaction weight are introduced to improve the sensitivity to changes in process parameters. The independent influence of parameters is considered, and the interaction between process parameters is analyzed. A more accurate growth control coefficient evaluation model is provided, which improves the adaptability and stability of high-temperature superconducting magnets under different process conditions and optimizes the accuracy of system performance regulation.

[0080] Example 4

[0081] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets, which determines the growth environment adaptability coefficient corresponding to each operating environment parameter by combining the operating environment parameters of each high-temperature superconducting magnet, including:

[0082] ;in, It is the growth environment fitness coefficient of the k-th environmental parameter at time t. denoted as the real-time growth control coefficient of the high-temperature superconducting magnet at time t. It is the preset optimal growth control coefficient for high-temperature superconducting magnets under ideal conditions. It is the real-time value of the k-th environmental parameter at time t. It is the preset optimal value of the k-th environmental parameter. It is the preset standard value of the k-th environmental parameter. It is the time decay coefficient corresponding to the k-th environmental parameter. Let t be the time from the initial time to time t.

[0083] In this embodiment, the real-time growth control coefficient refers to the state of the magnet's growth or performance relative to the ideal environment at a specific moment and under the actual operating environment of the high-temperature superconducting magnet. It reflects the magnet's adaptability or growth state under current operating conditions and measures the gap between the current conditions and the ideal growth conditions. This coefficient is usually calculated by comparing actual operating environment parameters (such as temperature, humidity, current, etc.) with their optimal values ​​and is updated in real time to reflect the growth situation at the current moment. The real-time growth control coefficient ranges between 0 and 1: 1: indicates that at this moment, the high-temperature superconducting magnet is in the optimal growth state, that is, the actual environmental parameters are completely consistent with the preset optimal environmental conditions, and the magnet performance reaches the ideal state; 0: indicates that growth is completely stagnant, meaning that the current environmental conditions are extremely undesirable, possibly far from the optimal conditions, and may even cause the magnet to malfunction. (0, 1) Values ​​between: These indicate that although the actual operating environment conditions of the magnet are not optimal, they still have a certain degree of adaptability. As the conditions approach the optimal, the coefficient gets closer to 1, and as it gets further away from the optimal, it gets closer to 0. Assuming that a high-temperature superconducting magnet operates at an ideal temperature of 77K and humidity of 40%, the real-time growth control coefficient is 1, indicating that the magnet's performance is at its best. When the temperature rises to 85K and the humidity increases to 55%, the real-time growth control coefficient drops to 0.75, indicating that the magnet's performance has decreased, but it still maintains good adaptability. If the temperature continues to rise to 100K and the humidity reaches 70%, the real-time growth control coefficient may drop to 0.2, indicating that the magnet's performance has decreased significantly and is approaching its limit.

[0084] In this embodiment, the preset optimal growth control coefficient refers to the growth coefficient corresponding to the optimal state of growth or operation of the high-temperature superconducting magnet under ideal conditions. It is a theoretical ideal value used as a reference standard to measure the difference between the actual growth situation and the ideal state. Assuming that the optimal growth control coefficient of the high-temperature superconducting magnet is 1.0 under ideal conditions (e.g., constant temperature, no interference, stable pressure), then this value is the preset optimal growth control coefficient. If the growth control coefficient under actual conditions is lower than 1.0, it indicates a decrease in system performance.

[0085] In this embodiment, the preset optimal value of the environmental parameter refers to the optimal value of a specific environmental parameter (such as temperature, humidity, etc.) under ideal conditions. At this optimal value, the performance or growth effect of the high-temperature superconducting magnet can reach its best state. For example, assuming that the high-temperature superconducting magnet performs best in a liquid nitrogen environment at 77K, then 77K is the preset optimal value of the temperature parameter. Similarly, assuming that the optimal humidity for the superconducting magnet is 40%, then the preset optimal value for humidity is 40%.

[0086] In this embodiment, the preset specification value refers to a reference or specified value for a certain environmental parameter under normal or standard operating conditions. This value is not necessarily the optimal value, but it reflects the standard value that the equipment should maintain under normal operating conditions. If the high-temperature superconducting magnet is operating normally, the temperature specification value is usually maintained between 80K and 85K. Temperatures within this range can ensure stable operation of the equipment. For example, the preset specification value for temperature could be 80K, while the preset specification value for humidity might be 50%.

[0087] In this embodiment, it is assumed that a high-temperature superconducting magnet operates in a liquid nitrogen-cooled environment. The relevant process and environmental parameters are as follows: Temperature parameter: The preset optimal value is 77K, because the superconducting magnet achieves its best performance at 77K; the preset standard value is 80K, because a stable superconducting effect can still be maintained at 80K, but the performance may decrease slightly. Humidity parameter: The preset optimal value is 40%, as the superconducting magnet performs best in a low-humidity environment; the preset standard value is 50%, which is the humidity standard at which the equipment can work normally but is not necessarily optimal. By comparing the current actual values ​​with the preset optimal and standard values, combined with factors such as the time decay coefficient, the adaptability of the superconducting magnet in the current environment can be analyzed, and its proximity to the ideal state or the existence of optimization space can be evaluated.

[0088] The beneficial effects of the above technical solution are as follows: by combining the operating environment parameters of the high-temperature superconducting magnet, the growth environment adaptability coefficient of each parameter is accurately calculated, the performance changes of the magnet under different environments are dynamically evaluated, and the time decay coefficient and the comparison analysis between the real-time and preset optimal values ​​are introduced. This can reflect the impact of environmental changes on the magnet performance in real time, effectively improve the adaptability and stability of the magnet in complex environments, optimize the operating efficiency, and provide a more refined basis for performance control.

[0089] Example 5

[0090] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets. It analyzes the growth environment adaptability coefficients corresponding to all operating environment parameters and determines several key operating environment parameters based on the analysis results, including:

[0091] The input dataset is constructed based on the operating environment parameters and the growth environment adaptation coefficient.

[0092] Based on a pre-set training algorithm, similar data points in the input dataset are mapped to similar positions in the network topology, thereby mapping the data distribution in the input dataset into a three-dimensional topological grid. Each cell of the network represents a combination of operating environment parameters and growth environment adaptation coefficients with similar characteristics.

[0093] Based on a preset analysis algorithm, several operating environment parameters are determined by analyzing the three-dimensional topology network.

[0094] In this embodiment, the input dataset refers to a comprehensive dataset constructed from various environmental parameters (such as temperature, humidity, and pressure) of the high-temperature superconducting magnet during actual operation, along with their corresponding growth environment adaptation coefficients. This data is used for subsequent analysis and algorithm training. The input dataset may include environmental parameters collected at different time points, such as values ​​for temperature, humidity, current, and magnetic field strength at a given moment, along with their corresponding growth environment adaptation coefficients. A data point might be: temperature = 80K, humidity = 45%, current = 500A, adaptation coefficient = 0.85.

[0095] In this embodiment, the preset training algorithm refers to a machine learning or data training algorithm pre-defined for classifying or analyzing the input dataset. This algorithm maps data points to a certain network structure based on the similarity between them. Common preset training algorithms include neural networks, K-means clustering, and SOM (Self-Organizing Map). Assuming SOM is used as the preset training algorithm, it will group data points with similar environmental parameters and growth fitness coefficients together.

[0096] In this embodiment, "proximate positions" in the network topology refer to data points with similar characteristics that are located close to each other in the network, based on the training algorithm. The network topology refers to the relationships between data points generated by a certain algorithm (such as a neural network or SOM), reflecting their similarities. If two data points are similar in parameters such as temperature and humidity, they will be mapped to proximate positions in the topology, possibly in adjacent cells. For example, one point represents data with an operating environment of 80K and 45% humidity, while another point represents 79K and 46% humidity; they may be mapped to adjacent nodes in the network.

[0097] In this embodiment, the three-dimensional topological mesh is a structure that visualizes the distribution of data points in a three-dimensional form. A preset algorithm maps the input dataset onto this three-dimensional mesh, where each mesh cell represents a combination of similar operating environment parameters and growth environment adaptation coefficients. The three-dimensional structure helps to more intuitively understand the clustering and distribution of data. For example, assuming the analysis of three environmental parameters—temperature, humidity, and current intensity—results in a three-dimensional mesh, where each point represents a specific environmental combination. A data point with a temperature of 80K, humidity of 45%, and current of 500A might be mapped to a specific cell in the three-dimensional mesh, while other similar points would be distributed in neighboring mesh cells.

[0098] In this embodiment, the preset analysis algorithm refers to an algorithm used to analyze the three-dimensional topological mesh structure and identify key features or patterns after the data has been trained and mapped. This algorithm helps extract the most influential key environmental parameters from complex topological structures and includes clustering analysis algorithms or dimensionality reduction algorithms (such as principal component analysis, PCA). By analyzing the three-dimensional topological mesh, the algorithm can identify certain parameters (such as temperature and humidity) as key factors affecting the adaptability of the growth environment. Assuming the analysis results show that fluctuations in temperature and humidity have the greatest impact on superconducting magnets, they will be identified as key operating environment parameters.

[0099] The beneficial effects of the above technical solution are as follows: by mapping operating environment parameters and growth environment adaptability coefficients to a three-dimensional topological mesh, efficient data clustering and visualization analysis are achieved. Through the analysis of the three-dimensional topological structure, key operating environment parameters can be accurately determined, effectively improving the adaptability and performance optimization of high-temperature superconducting magnets in complex environments. Combining the growth environment adaptability coefficient and topological analysis significantly improves the accuracy and efficiency of parameter selection and reduces the complexity of data processing.

[0100] Example 6

[0101] This invention provides a method for environmental adaptability data analysis of high-temperature superconducting magnets. Based on a preset training algorithm, similar data points in the input dataset are mapped to similar positions in a network topology, thereby mapping the data distribution in the input dataset into a three-dimensional topological mesh. The method includes:

[0102] A three-dimensional mesh is constructed based on a preset training algorithm, and a random weight vector is assigned to each network unit;

[0103] Based on a preset algorithm, the distance between each set of input data and the weight vector of each network unit in the input dataset is determined, and the network unit with the smallest distance between each set of input data and the weight vector of all network units is selected to map the input data.

[0104] Based on the similarity between each set of input data and the network unit, the weight vector of each network unit is updated. At the same time, the weight vectors of other network units within a preset radius around the network unit are updated, thereby generating a three-dimensional topological mesh.

[0105] Repeat the above process and evaluate the 3D topology mesh based on the preset error judgment method. Stop the above process when the error between the input dataset and the 3D topology mesh is less than the preset error threshold.

[0106] In this embodiment, the preset algorithm is a pre-selected computational method used to process and analyze the input data. In this embodiment, the preset algorithm can be a Self-Organizing Map (SOM) algorithm for constructing network topology or other machine learning algorithms. It helps map data with similar characteristics onto a three-dimensional topological mesh and updates the weight vectors of network cells. Assuming the SOM algorithm is used, the input data includes parameters such as temperature, current, and humidity. The SOM algorithm finds clusters of similar data points and maps them onto the three-dimensional mesh, while continuously adjusting the weights of these cells through training.

[0107] In this embodiment, the distance between each set of input data and the weight vector of each network unit refers to the distance calculated between the feature vector of the input data and the weight vector of the network unit. This distance is used to determine which unit the input data best matches (i.e., is most similar to). Commonly used distance calculation methods include Euclidean distance, Manhattan distance, etc.

[0108] In this embodiment, the preset radius is a range limitation used to update weights during training. That is, in addition to the selected network unit, the surrounding units will also have their weights adjusted based on the input data, but only within a certain radius. This radius gradually decreases during training to refine the mapping. If a certain input data is mapped to a central unit of a 3D mesh with a radius of 3, then other units within 3 units of that unit (neighboring units) on the 3D mesh will also have their weights updated. As training progresses, this radius may shrink to 2 or 1 to improve mapping accuracy.

[0109] In this embodiment, updating the weight vectors of other network units within a preset radius surrounding a network unit means that when a network unit is selected as the unit that best matches the input data, not only is the weight of this unit updated, but the weights of other units within its preset radius are also updated. The degree of weight update for these neighboring units typically decreases according to their distance from the central unit. Assuming the weight vector of the central unit is (80K, 50%, 300A) and the input data is (85K, 55%, 310A), the weight of the central unit might be updated to (81K, 51%, 305A). The weight updates for surrounding units will be even smaller, for example (79K, 49%, 298A), to reflect their greater distance.

[0110] In this embodiment, the preset error threshold is a standard used to determine whether training is complete. When the error (such as distance error or mean square error) between the input data and the generated 3D topological mesh is less than the threshold, the training process stops. If the preset error threshold is set to 0.01, when the mean square error (MSE) between the input data and the mesh cells drops to 0.009, the algorithm stops training, indicating that the 3D mesh has accurately reflected the distribution and characteristics of the input data.

[0111] In this embodiment, the preset error judgment method includes quantization error and topographic error. Reducing the error is to ensure that the weights of network units converge to features that can well represent the input data.

[0112] The beneficial effects of the above technical solution are as follows: By mapping similar data points to nearby positions in a three-dimensional topological structure through a pre-set training algorithm, efficient clustering and visualization of the input dataset are achieved. By dynamically updating network units and their neighborhood weight vectors, an accurate three-dimensional topological mesh is constructed, thereby optimizing the spatial distribution mapping of the data. Its innovation lies in its ability to accurately identify and classify complex data, improving the adaptability analysis effect of high-temperature superconducting magnets in different environments, and reducing errors and computational complexity.

[0113] Example 7

[0114] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets, which adjusts key operating environment parameters based on the growth environment adaptability coefficient, including:

[0115] The key operating environment parameters in the simulation model were adjusted based on the growth environment adaptation coefficient.

[0116] ;

[0117] in, This is the p-th critical runtime environment parameter after adjustment. For the p-th original critical runtime environment parameter, The preset base weights are the values ​​corresponding to the p-th critical runtime environment parameter. Let be the growth environment adaptability coefficient at time t. To preset the critical value for adaptation to the growth environment, Let be the weight of the growth environment adaptation adjustment term corresponding to the p-th key operating environment parameter. For preset adjustment coefficients, The preset weight is the weight corresponding to the growth item of the p-th key operating environment parameter.

[0118] In this embodiment, key operating environment parameters refer to environmental conditions or physical quantities that have a significant impact on the performance of a high-temperature superconducting magnet during operation. Changes in these parameters will significantly affect the stability, performance, and lifespan of the magnet. These parameters are adjusted through the growth environment adaptability coefficient to optimize the operating state of the magnet. For example, when the external ambient temperature rises from 77K to 85K, temperature, as a key operating environment parameter, needs to be adjusted to ensure that the magnet continues to operate stably.

[0119] In this embodiment, the preset adjustment coefficient is a value used to adjust key operating environment parameters. It affects the magnitude of change of each parameter during the adjustment process. The larger the value, the steeper the transition; the smaller the value, the smoother the transition. The value of this coefficient determines the system's response speed and sensitivity to environmental changes. A larger adjustment coefficient means a faster response to environmental changes, while a smaller adjustment coefficient indicates a more moderate response. The preset adjustment coefficient is usually set according to the specific magnet application and its sensitivity to environmental changes. The value range can be between 0 and 1. For example: 0.1 to 0.3: indicates a slow response to environmental changes, with a small system adjustment magnitude; 0.4 to 0.7: indicates a moderate response, with the system adjusting key operating parameters moderately according to changes; 0.8 to 1: indicates a rapid response, with the system significantly adjusting key parameters according to environmental changes. Assuming the preset adjustment coefficient is 0.5, it means that if a change in the environmental adaptability coefficient causes the temperature to deviate from the optimal operating conditions, the temperature adjustment will be a moderate response magnitude. If this coefficient is set to 0.9, the temperature adjustment will be more rapid and obvious when the environmental adaptability coefficient changes, ensuring that the magnet adapts quickly to environmental changes.

[0120] The beneficial effects of the above technical solution are as follows: By introducing a dynamic adaptation coefficient, the key operating environment parameters of the high-temperature superconducting magnet are dynamically adjusted, enabling it to adapt more accurately to complex environments. This not only considers the basic weights and adjustment coefficients of multiple weight parameters, but also optimizes the parameters of the magnet boundary value by adjusting the coefficients and the weights of the growth terms under different environments, significantly improving the magnet adjustment process and thus enhancing the environmental adaptability and reliability of the magnet.

[0121] Example 8

[0122] This invention provides a method for analyzing the environmental adaptability data of high-temperature superconducting magnets. The method evaluates and optimizes the output of a simulation model, and then, based on the optimized simulation model, obtains the optimal combination of process parameters for several types of high-temperature superconducting magnets, as well as the operating environment parameters of the high-temperature superconducting magnets. The method includes:

[0123] Collect all output data from the simulation model and analyze the output data to obtain parameter scores for high-temperature superconducting magnets under different process parameters and environmental parameters;

[0124] The parameter scores of high-temperature superconducting magnets under different process parameters and environmental parameters are compared with the preset performance scores.

[0125] If the parameter score of the high-temperature superconducting magnet is less than the preset performance score, then the process parameters of several types of high-temperature superconducting magnets and the key operating environment parameters of the high-temperature superconducting magnets in the simulation model are adjusted based on the preset optimization algorithm.

[0126] Rerun the simulation model using the adjusted parameter settings and obtain the model output results for evaluation;

[0127] Repeat the above process until the parameter score of the high-temperature superconducting magnet is greater than the preset performance score. The set of scores with the highest scores of the high-temperature superconducting magnet under different process parameters and environmental parameters is determined as the optimal combination of process parameters for several types of magnets and the operating environment parameters of the magnet.

[0128] In this embodiment, parameter scoring refers to the quantitative evaluation of the performance of a high-temperature superconducting magnet under specific process parameters and environmental conditions based on the data output by the simulation model. It reflects the magnet's overall performance, such as the quality of indicators like stability, efficiency, and magnetic field strength. For example, in a simulation, if the magnet's operating environment parameters are set to 80K temperature, 300A current, and 40% humidity, the corresponding output results would be: magnetic field strength: 8.5 T, loss: 20 W, stability: good.

[0129] If the above score is 85, then this value is the parameter score for this set of process and environmental parameters.

[0130] In this embodiment, the preset performance score is a minimum standard set to measure whether the magnet performance meets expectations. If the parameter score of the simulation result does not reach this performance score, it indicates that the performance of the parameter combination is not ideal and needs further optimization. The setting of the performance score is related to specific application requirements and performance indicators. If the preset performance score is set to 90 points, and the parameter score obtained from the above simulation is 85 points, it means that the current parameter combination is not ideal and process and environmental parameters need to be adjusted for optimization. The system will only accept the parameter combination when the score reaches or exceeds 90 points.

[0131] In this embodiment, a preset optimization algorithm is used to adjust the process and environmental parameters in the simulation model so that the output results gradually approach or exceed the preset performance score. The optimization algorithms include: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Gradient Descent, and Simulated Annealing. For example, using a genetic algorithm as the preset optimization algorithm, a set of random combinations of temperature, current, and humidity parameters are initially generated, and the simulation model is run to calculate the parameter scores. Based on the score results, the better parameter combinations are selected for crossover and mutation to generate new parameter combinations. This process is repeated until the optimal parameter combination that meets the performance score requirements is found. Optimization process: Initial parameter combination 1: Temperature = 77K, Current = 300A, Humidity = 35% (Score: 88 points); Optimized combination 2: Temperature = 79K, Current = 310A, Humidity = 40% (Score: 92 points, meets the requirements).

[0132] The beneficial effects of the above technical solution are as follows: By using an iterative optimization method based on simulation models, the performance of high-temperature superconducting magnets under different process and environmental parameters can be accurately evaluated and optimized, and parameter combinations can be automatically adjusted to ensure optimal operation of the magnet in complex environments. This method not only improves the operational stability and adaptability of the magnet, but also reduces the complexity and error of manual adjustments, thereby improving design and operational efficiency.

[0133] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing environmental adaptability data of high-temperature superconducting magnets, characterized in that, include: Step 1: Collect the operating environment parameters of the high-temperature superconducting magnet using preset sensors. At the same time, monitor and collect several types of process parameters of the high-temperature superconducting magnet using preset monitoring tools. The preset sensors include: temperature sensor, pressure sensor, humidity sensor, vibration sensor, and magnetic field sensor. The preset monitoring tools include: current monitoring tool, voltage monitoring tool, cooling system monitoring tool, strain monitoring tool, and power monitoring tool. Step 2: Determine the real-time growth control coefficient of high-temperature superconducting magnets based on the process parameters of several types of high-temperature superconducting magnets, and determine the growth environment adaptation coefficient corresponding to each operating environment parameter in combination with the operating environment parameters of each high-temperature superconducting magnet; Step 3: Analyze the growth environment adaptability coefficients corresponding to all operating environment parameters, and determine several key operating environment parameters based on the analysis results; Step 4: Adjust the key operating environment parameters based on the growth environment adaptability coefficient, and then construct a simulation model based on several types of process parameters of high-temperature superconducting magnets and the adjusted key operating environment parameters of the magnets; Step 5: Evaluate and optimize the output of the simulation model, and then obtain the optimal combination of process parameters for several types of high-temperature superconducting magnets and the operating environment parameters of the high-temperature superconducting magnets based on the optimized simulation model; Among them, the real-time growth control coefficients of high-temperature superconducting magnets are determined based on several types of process parameters, including: ;in, denoted as the real-time growth control coefficient of the high-temperature superconducting magnet at time t. Let be the real-time value of the i-th process parameter at time t. Let be the weighting coefficient corresponding to the i-th process parameter, and n be the number of process parameter types. Let j be the real-time value of the j-th process parameter at time t. Let be the weighting coefficient corresponding to the interaction between the i-th process parameter and the j-th process parameter. Let i be the preset initial influence value of the i-th process parameter. It is the time decay constant corresponding to the i-th process parameter. Let t be the time from the initial time to time t. The preset basic weights are the values ​​corresponding to the i-th process parameter. The interaction weights are the values ​​corresponding to the i-th process parameter. This represents the time decay weight corresponding to the i-th process parameter; The growth environment adaptability coefficient corresponding to each operating environment parameter is determined based on the operating environment parameters of each high-temperature superconducting magnet, including: ;in, It is the growth environment fitness coefficient of the k-th environmental parameter at time t. denoted as the real-time growth control coefficient of the high-temperature superconducting magnet at time t. It is the preset optimal growth control coefficient for high-temperature superconducting magnets under ideal conditions. It is the real-time value of the k-th environmental parameter at time t. It is the preset optimal value of the k-th environmental parameter. It is the preset standard value of the k-th environmental parameter. It is the time decay coefficient corresponding to the k-th environmental parameter. Let t be the time from the initial time to time t.

2. The method for analyzing environmental adaptability data of high-temperature superconducting magnets according to claim 1, characterized in that, The growth environment adaptability coefficients corresponding to all operating environment parameters were analyzed, and several key operating environment parameters were determined based on the analysis results, including: The input dataset is constructed based on the operating environment parameters and the growth environment adaptation coefficient. Based on a pre-set training algorithm, similar data points in the input dataset are mapped to similar positions in the network topology, thereby mapping the data distribution in the input dataset into a three-dimensional topological grid. Each cell of the network represents a combination of operating environment parameters and growth environment adaptation coefficients with similar characteristics. Based on a preset analysis algorithm, several operating environment parameters are determined by analyzing the three-dimensional topology network.

3. The method for analyzing environmental adaptability data of high-temperature superconducting magnets according to claim 2, characterized in that, Based on a pre-defined training algorithm, similar data points in the input dataset are mapped to similar positions in the network topology, thereby mapping the data distribution in the input dataset into a three-dimensional topological mesh, including: A three-dimensional mesh is constructed based on a preset training algorithm, and a random weight vector is assigned to each network unit; Based on a preset algorithm, the distance between each set of input data and the weight vector of each network unit in the input dataset is determined, and the network unit with the smallest distance between each set of input data and the weight vector of all network units is selected to map the input data. Based on the similarity between each set of input data and the network unit, the weight vector of each network unit is updated. At the same time, the weight vectors of other network units within a preset radius around the network unit are also updated, thereby generating a three-dimensional topological mesh. Repeat the above process and evaluate the 3D topology mesh based on the preset error judgment method. Stop the above process when the error between the input dataset and the 3D topology mesh is less than the preset error threshold.

4. The method for analyzing environmental adaptability data of high-temperature superconducting magnets according to claim 1, characterized in that, Adjustments to key operating environment parameters are made based on the growth environment adaptability coefficient, including: The key operating environment parameters in the simulation model were adjusted based on the growth environment adaptation coefficient. ;in, This is the p-th critical runtime environment parameter after adjustment. For the p-th original critical runtime environment parameter, The preset base weights are the values ​​corresponding to the p-th critical runtime environment parameter. Let be the growth environment adaptability coefficient at time t. To preset the critical value for adaptation to the growth environment, Let be the weight of the growth environment adaptation adjustment term corresponding to the p-th key operating environment parameter. For preset adjustment coefficients, The preset weight is the weight corresponding to the growth item of the p-th key operating environment parameter.

5. The method for analyzing environmental adaptability data of high-temperature superconducting magnets according to claim 1, characterized in that, The output of the simulation model is evaluated and optimized. Based on the optimized simulation model, several optimal combinations of process parameters for high-temperature superconducting magnets and their operating environment parameters are obtained, including: Collect all output data from the simulation model and analyze the output data to obtain parameter scores of the high-temperature superconducting magnet under different process parameters and environmental parameters; The parameter scores of high-temperature superconducting magnets under different process parameters and environmental parameters are compared with the preset performance scores. If the parameter score of the high-temperature superconducting magnet is less than the preset performance score, then the process parameters of several types of high-temperature superconducting magnets and the key operating environment parameters of the high-temperature superconducting magnets in the simulation model are adjusted based on the preset optimization algorithm. Rerun the simulation model using the adjusted parameter settings and obtain the model output results for evaluation; Repeat the above process until the parameter score of the high-temperature superconducting magnet is greater than the preset performance score. The set of scores with the highest scores of the high-temperature superconducting magnet under different process parameters and environmental parameters is determined as the optimal combination of process parameters for several types of magnets and the operating environment parameters of the magnet.

Images