Gas production arc extinguishing polymer design method, system and product of low-voltage circuit breaker

Abstract

The invention belongs to the field of low-voltage circuit breakers, and discloses a gas production arc extinguishing polymer design method and system for a low-voltage circuit breaker and a product, and the method comprises the steps: obtaining a plurality of groups of to-be-selected organic additive molecules from a pre-constructed candidate database, inputting the to-be-selected organic additive molecules into a pre-training performance prediction model based on a graph neural network, and outputting a prediction result of an intermediate performance index; and screening out candidate molecules based on a preset threshold value, and blending the candidate molecules with a nylon matrix to prepare the arc extinguishing polymer. The graph neural network learns complex nonlinear mapping of the structure and the performance from a training data set by processing molecular structure graph data, objective and unified evaluation of dynamic comprehensive indexes is achieved, and experience-driven trial and error are avoided. By adopting the method, the research and development period is remarkably shortened, the research and development cost is reduced, the screening success rate is improved, the comprehensive performance of the material in a real arc environment is screened and optimized through the threshold value, and development and application of the efficient arc extinguishing material are accelerated.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of low-voltage circuit breakers, and particularly relates to a gas production arc extinguishing polymer design method, system and product for a low-voltage circuit breaker. BACKGROUND

[0002] In the field of low-voltage circuit breakers, the performance of the arc extinguishing chamber is directly related to the safe and stable operation of the equipment, and currently, structural members thereof widely adopt high molecular materials such as polyamide (nylon). In order to further improve the arc extinguishing effect, the industry generally adds organic additives to the nylon matrix to improve the gas production efficiency of the material under the action of the arc, so as to enhance the arc extinguishing performance. Such materials play an important role in the application of low-voltage circuit breakers.

[0003] However, in the development process of traditional arc extinguishing materials, the selection of additives is severely dependent on experimental trial and error. R&D personnel often choose candidate molecules for synthesis and testing based on experience. This process not only has a long cycle and high cost, but also has a low success rate. Due to the extremely large space of molecular design, it is almost impossible to conduct comprehensive screening through experimental means, which greatly hinders the research and application of new high-efficiency arc extinguishing materials. At the same time, the existing technology lacks unified and objective standards for evaluating the performance of arc extinguishing materials, and the evaluation focuses on a single indicator, ignoring the dynamic and comprehensive performance of the material in the real arc environment, such as arc burning time and instantaneous gas pressure, resulting in a large deviation between the evaluation results and the actual application effect.

[0004] Therefore, for the gas production arc extinguishing polymer of a low-voltage circuit breaker, the traditional experimental trial and error method leads to a long development cycle, high cost, and low success rate, which greatly limits the discovery and application of high-efficiency arc extinguishing materials. SUMMARY

[0005] The application provides a gas production arc extinguishing polymer design method, system and product for a low-voltage circuit breaker, which can shorten the entire development cycle, reduce the cost and improve the success rate of research and development.

[0006] A design method of a gas production arc extinguishing polymer for a low-voltage circuit breaker, comprising: obtaining a plurality of groups of candidate organic additive molecules in a pre-constructed candidate database; inputting the candidate organic additive molecules into a pre-trained performance prediction model to obtain intermediate performance index prediction results corresponding to each group of candidate organic additive molecules; wherein the performance prediction model is used to represent the mapping relationship between the organic additive molecule structure and the corresponding intermediate performance index, and the base model of the performance prediction model is a graph neural network model, which is trained based on a data set containing organic additive molecule structures and corresponding intermediate performance indexes; filtering out the to-be-selected organic additive molecules satisfying the intermediate performance index threshold from the intermediate performance index prediction results as candidate organic additive molecules based on the preset intermediate performance index threshold; the candidate organic additive molecules are used to be blended with the nylon matrix at a predetermined ratio to prepare the gas-producing arc-extinguishing polymer of the low-voltage circuit breaker.

[0007] Further, the graph neural network model adopts a graph convolution network, a graph attention network or a message passing neural network.

[0008] Further, the nylon matrix adopts polyamide 6, polyamide 46, polyamide 66 or polyamide 12.

[0009] Further, the training process of the performance prediction model comprises: constructing a data set according to the molecular structures of a plurality of organic additives and the corresponding intermediate performance indexes; constructing a graph neural network model of the performance prediction model; wherein the graph neural network model adopts a graph attention network; the graph attention network comprises an embedding module for feature mapping, a graph information aggregation module composed of a plurality of graph attention layers, a readout module for generating a molecular graph level representation, and a fully connected prediction module for outputting a final prediction value; dividing the data set into a training set, a validation set and a test set according to a preset ratio; training, testing and validating the constructed graph neural network model based on the training set, the validation set and the test set in sequence to output the trained performance prediction model.

[0010] Further, after filtering out the to-be-selected organic additive molecules satisfying the intermediate performance index threshold from the intermediate performance index prediction results as candidate organic additive molecules based on the preset intermediate performance index threshold, the method further comprises: blending the candidate organic additive molecules with the nylon matrix at a predetermined ratio to prepare the gas-producing arc-extinguishing polymer of the low-voltage circuit breaker; obtaining a gas-producing arc-extinguishing polymer sample, comprehensively evaluating the gas-producing arc-extinguishing polymer sample to output an evaluation result; determining whether the gas-producing arc-extinguishing polymer sample satisfies the material arc-extinguishing standard requirement according to the evaluation result: if yes, a gas-producing arc-extinguishing polymer satisfying the material arc-extinguishing standard requirement is obtained; otherwise, intermediate performance index experimental results of the candidate organic additive molecules are obtained through experiments, and the candidate organic additive molecules and the corresponding intermediate performance index experimental results are supplemented to the data set.

[0011] Further, the comprehensive evaluation of the gas-producing arc-extinguishing polymer sample comprises: The gas-generating arc-extinguishing polymer sample is placed in an arc test device to perform arc-extinguishing test under a preset short-circuit current condition; The macro evaluation parameters of the gas-generating arc-extinguishing polymer sample are collected in real time by the sensor; the macro evaluation parameters include arc voltage, arc current, arc burning time, arc-extinguishing chamber gas pressure and ablation gas temperature; According to the collected macro evaluation parameters of the gas-generating arc-extinguishing polymer sample, the gas-generating arc-extinguishing polymer sample is comprehensively evaluated in combination with the material arc-extinguishing standard requirements to output the evaluation result.

[0012] Further, the comprehensive evaluation of the gas-generating arc-extinguishing polymer sample according to the collected macro evaluation parameters of the gas-generating arc-extinguishing polymer sample in combination with the material arc-extinguishing standard requirements to output the evaluation result includes: It is judged whether the macro evaluation parameters of the gas-generating arc-extinguishing polymer sample meet the following conditions: Condition one, the peak value of the arc-extinguishing chamber gas pressure is greater than 0.5 MPa; Condition two, the ablation gas temperature in the arc-extinguishing chamber is lower than 400 DEG C; Condition three, the peak value of the arc voltage is greater than 400 V; Condition four, the peak value of the arc current is lower than 2 kA; Condition five, the arc burning time is less than 40 ms; If the gas-generating arc-extinguishing polymer sample meets at least one of the conditions one to five, it is judged that the gas-generating arc-extinguishing polymer sample meets the material arc-extinguishing standard requirements; otherwise, it is judged that the gas-generating arc-extinguishing polymer sample does not meet the material arc-extinguishing standard requirements.

[0013] Further, the intermediate performance index includes gas generation efficiency and thermal stability.

[0014] A gas-generating arc-extinguishing polymer system of a low-voltage circuit breaker is used to realize the steps of the design method of the gas-generating arc-extinguishing polymer of the low-voltage circuit breaker, and includes: A data acquisition module is configured to acquire a plurality of groups of candidate organic additive molecules from a pre-constructed candidate database; An index prediction module is configured to input the candidate organic additive molecules into a pre-trained performance prediction model to obtain intermediate performance index prediction results corresponding to each group of candidate organic additive molecules; wherein the performance prediction model is used to represent the mapping relationship between the organic additive molecule structure and the corresponding intermediate performance index, and the base model of the performance prediction model is a graph neural network model, which is trained based on a data set containing organic additive molecule structures and corresponding intermediate performance indexes; The molecular screening module is used to screen out candidate organic additive molecules meeting the intermediate performance index threshold requirement from the intermediate performance index prediction results as candidate organic additive molecules based on a preset intermediate performance index threshold; and the candidate organic additive molecules are used to be blended with a nylon matrix at a predetermined ratio to prepare the gas-producing arc extinguishing polymer of the low-voltage circuit breaker.

[0015] The gas-producing arc extinguishing polymer product of the low-voltage circuit breaker is prepared based on the design method of the low-voltage circuit breaker gas-producing arc extinguishing polymer.

[0016] Compared with the prior art, the present application has the following beneficial effects: The present application provides a design method of a gas-producing arc extinguishing polymer of a low-voltage circuit breaker. The method obtains a plurality of groups of candidate organic additive molecules from a pre-constructed candidate database, inputs them into a pre-trained performance prediction model based on a graph neural network, outputs prediction results of intermediate performance indexes, and screens out candidate molecules based on a preset threshold to prepare arc extinguishing polymers by blending with a nylon matrix. The graph neural network learns the complex nonlinear mapping between structure and performance from the training data set by processing molecular structure graph data, realizes objective and unified evaluation of dynamic comprehensive indexes, and avoids experience-driven trial and error. The use of this method significantly shortens the research and development cycle, reduces the research and development cost, improves the screening success rate, and optimizes the comprehensive performance of the material in the real arc environment through threshold screening, thereby accelerating the development and application of high-efficiency arc extinguishing materials.

[0017] Preferably, in the present application, the specific architecture of the graph neural network includes a graph convolution network, a graph attention network, etc. These network architectures can accurately represent molecular structures, and in particular, the graph attention network can capture the topological relationship and electronic effect between atoms, more accurately learn the nonlinear mapping between molecular structure and performance, and improve the prediction accuracy. The message passing neural network dynamically optimizes the molecular representation by iteratively aggregating neighbor node information, and is suitable for multi-scale performance prediction of complex organic additives.

[0018] Preferably, in the present application, the specific types of the nylon matrix include different models such as polyamide 6 and polyamide 66. These nylon matrices have different thermal stability and mechanical properties, providing a diversified matrix selection for the gas-producing arc extinguishing polymer. Different models of nylon matrix can form different interactions with organic additives, thereby optimizing the comprehensive performance of the final product. This clear matrix selection range helps to develop the optimal arc extinguishing material for different application scenarios.

[0019] Preferably, in the present application, the training process of the performance prediction model includes the construction of the data set, the design of the network architecture, and the training and validation process. By adopting the multi-module structure of the graph attention network, the molecular features can be effectively extracted and the end-to-end performance prediction can be performed. The division of the training set, the validation set and the test set ensures the generalization ability of the model. This systematic training method guarantees the reliability of the prediction model and provides a solid technical foundation for subsequent molecular screening.

[0020] Preferably, in the present application, the experimental verification and feedback optimization are added, forming a complete R&D closed loop. On the basis of model prediction, actual sample preparation and testing are carried out to verify the reliability of the prediction results. For samples that do not meet the standards, the training data set is improved by supplementing experimental data to realize continuous optimization of the model. This R&D mode not only utilizes the efficiency of computational prediction, but also guarantees the accuracy of the results through experimental verification, significantly improving the R&D efficiency.

[0021] Preferably, in the present application, a comprehensive evaluation method for gas-producing arc-extinguishing polymer samples is proposed, which simulates the real working environment through an arc testing device. A multi-parameter synchronous monitoring method is adopted, including key indicators such as arc voltage, current, and arc time, to comprehensively evaluate material performance. This testing method can truly reflect the performance of the material in actual application, avoiding the limitations of single indicator evaluation, and providing comprehensive data support for material optimization.

[0022] Preferably, in the present application, the material arc-extinguishing standard evaluation system sets evaluation conditions from multiple dimensions such as gas pressure, temperature, voltage, current, and time. This multi-dimensional evaluation standard can ensure that the material has reliable arc-extinguishing performance in actual application. At the same time, the evaluation method that meets at least one condition ensures basic performance requirements and provides flexible selection space for different application scenarios.

[0023] Preferably, in the present application, the intermediate performance indicators include gas production efficiency and thermal stability, which are two key parameters. Gas production efficiency directly affects the arc-extinguishing effect, while thermal stability determines the reliability of the material in high-temperature environments. The setting of these two indicators captures the core elements of arc-extinguishing material performance, providing a clear direction for molecular design and screening. By optimizing these two indicators, the overall performance of the arc-extinguishing material can be systematically improved.

[0024] The application also provides a gas-producing arc-extinguishing polymer product, which is prepared based on the gas-producing arc-extinguishing polymer design method of the low-voltage circuit breaker, the graph neural network learns the nonlinear mapping between the molecular structure and the dynamic performance of the arc environment through the topological relationship of atoms and bonds, and replaces the experience screening in the traditional trial-and-error method; at the same time, the model takes the comprehensive index of the real arc environment as the evaluation standard, and solves the single index evaluation deviation problem. The product significantly shortens the research and development cycle, reduces the research and development cost, and improves the discovery efficiency of efficient materials, ensures the comprehensive arc-extinguishing performance of the material in the arc environment through dynamic performance threshold screening, breaks through the limitation of the molecular design space of the traditional trial-and-error method, and provides an expandable technical path for performance optimization of the nylon-based arc-extinguishing polymer. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 A flowchart of the design method of the gas-producing arc-extinguishing polymer provided by the embodiment of the application is shown in the figure. Figure 2 An experimental device schematic diagram of the evaluation method of the gas-producing arc-extinguishing polymer provided by the embodiment of the application is shown in the figure. Figure 3 A hardware structure block diagram of the computer device for executing the design method or the evaluation method provided by the embodiment of the application is shown in the figure. Figure 4 A thermogravimetric analysis curve comparison diagram of three gas-producing arc-extinguishing polymer samples prepared by the embodiment of the application is shown in the figure. Figure 5 A scanning electron microscope photo of the surface of the sample provided by the embodiment of the application is shown in the figure; wherein (a) is a nylon matrix of pure polyamide 66; (b) is a nylon matrix of polyamide 66+ guanidine carbonate; Figure 6 A flowchart of the gas-producing arc-extinguishing polymer design method of the low-voltage circuit breaker provided by the application is shown in the figure. Figure 7 A structural schematic diagram of the gas-producing arc-extinguishing polymer design system of the low-voltage circuit breaker provided by the application is shown in the figure. DETAILED DESCRIPTION

[0026] In order to further understand the content of the application, the application will be described in detail below in combination with the drawings and specific embodiments. It should be understood that the embodiments are only used to explain the application but not to limit the application.

[0027] As described in the background, traditional additive screening relies heavily on experimental trial and error method, and researchers select candidate molecules for synthesis and testing according to experience, which is a long process, high cost, and low success rate. The huge molecular design space makes it almost impossible to conduct comprehensive screening through experimental means, which greatly limits the discovery and application of new efficient arc extinguishing materials. In addition, the existing technology also lacks unified and objective standards for evaluating the performance of arc extinguishing materials. The evaluation often only focuses on a single indicator, ignoring the dynamic and comprehensive performance of the material in the real arc environment (such as arc burning time, instantaneous gas pressure, etc.), resulting in a deviation between the evaluation results and the actual application effect.

[0028] To solve the above problems, the embodiment provides a gas-producing arc extinguishing polymer design method for low-voltage circuit breakers, which provides a new technical paradigm that can realize rapid and accurate prediction and systematic design of high-performance gas-producing arc extinguishing materials.

[0029] As shown in Figure 6 , the embodiment provides a gas-producing arc extinguishing polymer design method for low-voltage circuit breakers, which includes: Obtain multiple groups of candidate organic additive molecules in a pre-constructed candidate database; Input the candidate organic additive molecules into a pre-trained performance prediction model to obtain intermediate performance index prediction results corresponding to each group of candidate organic additive molecules; wherein the performance prediction model is used to represent the mapping relationship between the organic additive molecule structure and the corresponding intermediate performance index, and the base model of the performance prediction model is a graph neural network model, which is trained based on a data set containing organic additive molecule structures and corresponding intermediate performance indexes; Based on the pre-set intermediate performance index threshold, the candidate organic additive molecules that meet the intermediate performance index threshold requirement are selected from the intermediate performance index prediction results as candidate organic additive molecules; the candidate organic additive molecules are used to blend with the nylon matrix at a predetermined ratio to prepare a gas-producing arc extinguishing polymer for low-voltage circuit breakers.

[0030] The candidate question recommendation method provided by the embodiment will be described in more detail as follows: Embodiment 1 As shown in Figure 1 , the embodiment provides a gas-producing arc extinguishing polymer design method for low-voltage circuit breakers, and the specific steps are as follows: Step S1: Establish a data set containing molecular structure and intermediate performance index First, a data set for model training is established. The data set is obtained by organizing existing public literature data and supplemented by internal experiments, and contains the molecular structures of 100 different organic additives and their corresponding intermediate performance indexes.

[0031] In this embodiment, the molecular structure of each organic additive is stored in the form of its SMILES (Simplified Molecular Input Line Entry System) string. The intermediate performance indicators associated with its molecular structure specifically include: Gas production efficiency: determined by thermal gravimetric analysis. Specifically, the sample is heated from room temperature to 800°C at a heating rate of 10°C / min under a nitrogen protective atmosphere, and the total mass loss percentage of the material at 800°C is taken as the characterization of the gas production efficiency. For example, a carbon residue rate of 20% corresponds to a gas production efficiency of 80%.

[0032] Thermal stability: also determined by thermal gravimetric analysis, characterized by the temperature at which the sample thermal decomposition results in a 5% mass loss, denoted as T_d5.

[0033] Step S2: Training the graph neural network prediction model The data set established in step S1 is used to train the graph neural network model to establish a performance prediction model.

[0034] In a preferred embodiment, the specific implementation of this step is as follows: First, convert the SMILES string of each molecule in the data set into a graph data structure, where atoms are nodes of the graph and chemical bonds are edges of the graph, and configure initial feature vectors for nodes and edges that can represent their chemical properties.

[0035] Second, construct a graph neural network model. In this embodiment, the model is a graph attention network. The network architecture of this model can include an embedding module for feature mapping, a graph information aggregation module composed of multiple graph attention layers, a readout module for generating a molecular graph-level representation, and a fully connected prediction module for outputting the final prediction value.

[0036] Finally, the constructed model is trained. In this embodiment, to achieve effective training and evaluation of the model, the data set is divided into a training set, a validation set, and a test set in the ratio of 8:1:1. The training set is used to train the model parameters, the validation set is used to adjust the hyperparameters and prevent overfitting, and the test set is used to finally evaluate the generalization ability of the model. Subsequently, the mean square error is selected as the loss function, and the Adam optimizer is used to update the network parameters of the model. After multiple cycles of iterative training, the final performance prediction model is obtained. In a specific verification experiment, the graph attention network model used contains 4 graph attention layers; the initial learning rate is set to 0.001 and the batch size is 32 during training. The final performance prediction model has a determination coefficient of more than 0.9 for predicting the gas production efficiency and thermal stability, proving its good prediction accuracy and generalization ability.

[0037] Step S3: Batch prediction of candidate molecule performance A candidate database containing more than 10,000 commercially available or easily synthesized nitrogen-containing organic compounds is established. Using the performance prediction model trained in step S2, batch prediction of intermediate performance indicators is performed on all candidate molecules in the candidate database.

[0038] Step S4: Screening of candidate additives meeting performance screening thresholds According to the actual requirements of low-voltage circuit breakers for the performance of gas-producing arc-extinguishing polymers, the following performance screening thresholds are set: predicted gas production efficiency > 90%, and predicted thermal stability T_d5 > 300℃.

[0039] According to the prediction results of the model, and further considering factors such as the synthesis cost, commercial availability and environmental friendliness of each candidate molecule, a compound named "guanidine carbonate" is finally selected from the molecules meeting the above thresholds as a preferred candidate additive of this embodiment, and is denoted as additive A.

[0040] Step S5: Preparation of gas-producing arc-extinguishing material samples To verify the actual arc-extinguishing performance of additive A and compare it with the prior art, the following three samples are prepared respectively: Inventive sample: After drying, the polyamide 66 matrix and additive A are melt blended and extruded into granules in a twin-screw extruder at a mass ratio of 95:5 and at a temperature of 260-280℃, and finally a standard test sample is prepared by injection molding.

[0041] Comparative Example 1: A test sample of pure polyamide 66 is prepared using the same process as the inventive sample, as a performance benchmark.

[0042] Comparative Example 2: A test sample is prepared by blending a conventional additive commonly used in the art, melamine cyanurate, with the polyamide 66 matrix at a mass ratio of 95:5 using the same process as the inventive sample.

[0043] As shown in Figure 2 Step S6: Comprehensive evaluation of arc-extinguishing performance (experimental verification) S6.1 Performance evaluation: As shown in Figure 3As shown, in the embodiment, the arc test device includes a hollow cylindrical sample 1, a closed arc-extinguishing chamber 2, an arc-starting copper wire 3, an LC oscillation circuit 4, a positive connection terminal 5, a negative connection terminal 6, a high-voltage voltage probe 7, a positive voltage connection terminal 8, a negative voltage connection terminal 9, a high-frequency current mutual inductance coil 10, a connection line 11, a high-speed acquisition oscilloscope 12, a No. 1 signal transmission line 13, a current acquisition channel 14, a No. 2 signal transmission line 15, a voltage acquisition channel 16, a high-speed air pressure sensor 17, a No. 3 signal transmission line 18, an air pressure acquisition channel 19, a high-speed response thermocouple sensor 20, a No. 4 signal transmission line 21, an upper computer 22, a signal acquisition port 23, a data output port 24, and a No. 5 signal transmission line 25.

[0044] In a specific connection mode, the hollow cylindrical sample 1 is placed in the closed arc-extinguishing chamber 2; the arc-starting copper wire 3 is passed through the hollow cylindrical sample 1; the arc-starting copper wire 3 is connected to the positive connection terminal 5 and the negative connection terminal 6 of the LC oscillation circuit 4; the high-voltage voltage probe 7 is connected to the positive voltage connection terminal 8 and the negative voltage connection terminal 9 of the LC oscillation circuit 4; the high-frequency current mutual inductance coil 10 is passed through the connection line 11 of the LC oscillation circuit 4; the high-frequency current mutual inductance coil 10 is connected to the current acquisition channel 14 of the high-speed acquisition oscilloscope 12 through the No. 1 signal transmission line 13; the positive voltage connection terminal 8 is connected to the voltage acquisition channel 16 of the high-speed acquisition oscilloscope 12 through the No. 2 signal transmission line 15; the high-speed air pressure sensor 17 fixed inside the closed arc-extinguishing chamber 2 is connected to the air pressure acquisition channel 19 of the high-speed acquisition oscilloscope 12 through the No. 3 signal transmission line 18; the high-speed response thermocouple sensor 20 fixed inside the closed arc-extinguishing chamber 2 is connected to the signal acquisition port 23 of the upper computer 22 through the No. 4 signal transmission line 21; and the data output port 24 of the high-speed acquisition oscilloscope 12 is connected to the signal acquisition port 23 of the upper computer 22 through the No. 5 signal transmission line 25. The test result is shown in Table 1: Table 1 is a test result summary

[0045] As can be clearly seen from the experimental results in Table 1, the comprehensive performance of the sample in the embodiment is significantly better than that of the comparative examples 1 and 2. Specifically, the actually measured peak gas pressure is greater than 0.5 MPa, the gas temperature peak value is lower than 400 ℃, the arc voltage peak value is greater than 400 V, the current peak value after current limiting is lower than 2 kA, and the arc burning time is less than 40 ms. This indicates that it simultaneously meets the five performance conditions, and the results powerfully prove the effectiveness and advancement of the design method of the present application.

[0046] In order to further explore the reason why the performance of the sample in the embodiment of the present application is superior from the intrinsic properties and micro mechanism of the material, the sample is subjected to thermogravimetric analysis and scanning electron microscope characterization.

[0047] AsFigure 4 The thermogravimetric analysis curves of the inventive sample (curve c), comparative example 1 (pure polyamide 66, curve a) and comparative example 2 (conventional additive, curve b) are shown in FIG. 1. From the curves, it can be clearly seen that the thermal decomposition onset temperature of the inventive sample is significantly lower than that of the pure polyamide 66 matrix, and its pyrolysis rate (i.e. the slope of the curve) in the main decomposition stage is also significantly faster. This indicates that the addition of guanidine carbonate effectively promotes the rapid and violent decomposition of the polymer matrix at a lower temperature. It is this lower pyrolysis temperature and faster pyrolysis rate that enables the material to generate a large amount of gas in an instant when subjected to the high temperature impact of the arc, thereby rapidly establishing a higher gas pressure in the arc chamber and forming a strong gas flow to blow out the arc, which is the key internal reason for its higher peak gas pressure and shorter arc time. Figure 4

[0048] As shown in FIG. 2, specifically as shown in FIG. (a) and FIG. (b), which respectively demonstrate the post-arc surface micro-morphology of the comparative example 1 sample and the inventive example sample. For this characterization, the post-arc sample surface was treated with gold spraying to enhance the electrical conductivity, and then the surface morphology was observed on a SU3500 scanning electron microscope at an acceleration voltage of 15.0 kV. As shown in FIG. (a), the post-arc surface of comparative example 1 (pure polyamide 66) is relatively flat, mainly presenting a "fine crack network" formed after melting and cooling, with only a small amount of irregular small holes. This morphology indicates that its surface melting erosion under the action of the arc is mainly, and the gas production process is relatively gentle and has no directionality, making it difficult to form an effective arc extinguishing gas flow. Figure 5 In sharp contrast, as shown in FIG. (b), the post-arc surface of the inventive example sample is covered with dense and various-sized circular holes, which resemble "meteor craters" on the surface of the moon. What is particularly critical is that many of the holes have clear, raised edges, which is a typical feature of the internal gas in the material expanding sharply at high temperature, breaking through the molten polymer surface and erupting out. Each "meteor crater" represents a strong gas eruption event. This intense, eruptive gas production mode not only directly verifies the rapid pyrolysis characteristics revealed by TGA analysis, but also morphologically proves that the gas production arc extinguishing polymer of the inventive example can produce high-speed, high-pressure directional arc extinguishing gas flow, thereby effectively blowing off the arc and cooling the arc root, which is the fundamental reason for its macroscopic arc extinguishing performance far superior to that of the comparative example material.

[0049]

[0050] S6.2 Feedback and iteration: ​​If the experimental result of additive B does not meet the requirement, a feedback iteration is needed. Specifically, actual thermogravimetric analysis is performed on additive B, and the actual gas production efficiency is measured to be 70%, and T_d5 is 280°C. Then, the new data point of "molecular structure of additive B, 70%, 280°C" is added to the data set described in step S1.

[0051] Then, steps S2 to S6 are repeated, i.e., the original performance prediction model is retrained using the expanded new data set to obtain an updated model with better prediction ability, and a new round of screening, preparation and verification is performed using the new model. This closed-loop process ensures that the prediction ability of the method of the present application can be continuously improved as the experimental data accumulates.

[0052] Example 2: Comprehensive evaluation of gas production arc-extinguishing polymer performance To objectively and quantitatively evaluate the comprehensive performance of arc-extinguishing materials, a comprehensive performance scoring model is established in this embodiment. In a preferred embodiment, the mathematical model is as follows: (1) wherein, S is the comprehensive performance score; P max is the peak pressure in the arc chamber (unit: MPa); T arc is the ablation gas temperature in the arc chamber (unit: °C); U max is the peak arc voltage (unit: V); I max is the peak arc current (unit: kA); t arc is the arc time (unit: ms); w 1、 w 2、 w 3、 w 4、 w 5is the weight coefficient of each performance parameter, and the sum is 1. In this embodiment, according to the requirements of the low-voltage circuit breaker safety standard, the arc time ( w 5=0.3) is considered to be the most critical factor in determining the success of arc extinguishing, so it is given the highest weight; and the core parameters such as pressure, temperature and voltage ( w 1, w 2, w 3=0.2) are also very important; the current limiting capability ( w 4=0.1) is considered as an auxiliary consideration, and the weight is slightly lower.

[0053] Based on the experimental data obtained in Example 1, the comprehensive performance scores of each material sample are calculated as follows: Example sample (polyamide 66 + guanidine carbonate):

[0054] Comparative example 1 (pure polyamide 66):

[0055] Comparative example 2 (pure polyamide 66 + melamine cyanurate):

[0056] The calculation results clearly show that the material of the present embodiment (comprehensive score 2.734) has the highest comprehensive performance score compared with the pure matrix material (comprehensive score 1.157) and the material using traditional additives (comprehensive score 1.398).

[0057] As Figure 7 shown, the present embodiment also provides a design system of gas generating arc extinguishing polymer of low-voltage circuit breaker, comprising a data acquisition module configured to acquire a plurality of groups of candidate organic additive molecules from a pre-constructed candidate database; an index prediction module configured to input the candidate organic additive molecules into a pre-trained performance prediction model to obtain intermediate performance index prediction results corresponding to each group of candidate organic additive molecules; wherein the performance prediction model is configured to represent a mapping relationship between organic additive molecule structures and corresponding intermediate performance indexes, and a base model of the performance prediction model is a graph neural network model trained based on a dataset containing organic additive molecule structures and corresponding intermediate performance indexes; and a molecule screening module configured to screen candidate organic additive molecules satisfying intermediate performance index threshold requirements from the intermediate performance index prediction results based on a pre-set intermediate performance index threshold, so as to be used as candidate organic additive molecules; and the candidate organic additive molecules are configured to be blended with a nylon matrix at a predetermined ratio to prepare a gas generating arc extinguishing polymer of low-voltage circuit breaker.

[0058] The present application also provides a design device of gas generating arc extinguishing polymer of low-voltage circuit breaker, comprising: a memory configured to store a computer program; and a processor configured to execute the computer program to implement the steps of the design method of gas generating arc extinguishing polymer of low-voltage circuit breaker.

[0059] The present application also provides a computer program product comprising computer programs / instructions configured to implement the steps of the design method of gas generating arc extinguishing polymer of low-voltage circuit breaker when executed by a processor.

[0060] The processor executes the computer program to implement the steps of designing the gas generating arc-extinguishing polymer of the low-voltage circuit breaker, for example: obtaining a plurality of groups of candidate organic additive molecules in a pre-constructed candidate database; inputting the candidate organic additive molecules into a pre-trained performance prediction model to obtain intermediate performance index prediction results corresponding to each group of candidate organic additive molecules; wherein the performance prediction model is used to represent the mapping relationship between the organic additive molecule structure and the corresponding intermediate performance index, and the base model of the performance prediction model is a graph neural network model, which is trained based on a data set containing organic additive molecule structures and corresponding intermediate performance indexes; based on a pre-set intermediate performance index threshold, candidate organic additive molecules that meet the intermediate performance index threshold requirement are selected from the intermediate performance index prediction results as candidate organic additive molecules; the candidate organic additive molecules are used to be blended with a nylon matrix at a predetermined ratio to prepare the gas generating arc-extinguishing polymer of the low-voltage circuit breaker.

[0061] Exemplarily, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a predetermined function, which are used to describe the execution process of the computer program in the device. For example, the computer program can be divided into a data acquisition module, an index prediction module and a molecule screening module; the specific functions of each module are as follows: the data acquisition module is used to obtain a plurality of groups of candidate organic additive molecules in a pre-constructed candidate database; the index prediction module is used to input the candidate organic additive molecules into a pre-trained performance prediction model to obtain intermediate performance index prediction results corresponding to each group of candidate organic additive molecules; wherein the performance prediction model is used to represent the mapping relationship between the organic additive molecule structure and the corresponding intermediate performance index, and the base model of the performance prediction model is a graph neural network model, which is trained based on a data set containing organic additive molecule structures and corresponding intermediate performance indexes; the molecule screening module is used to select candidate organic additive molecules that meet the intermediate performance index threshold requirement from the intermediate performance index prediction results as candidate organic additive molecules based on a pre-set intermediate performance index threshold; the candidate organic additive molecules are used to be blended with a nylon matrix at a predetermined ratio to prepare the gas generating arc-extinguishing polymer of the low-voltage circuit breaker.

[0062] The design device of the gas generating arc extinguishing polymer of the low-voltage circuit breaker can be a computing device such as a desktop computer, a notebook computer, a palm computer, and a cloud server. The design device of the gas generating arc extinguishing polymer of the low-voltage circuit breaker can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above is an example of the design device of the gas generating arc extinguishing polymer of the low-voltage circuit breaker, and does not constitute a limitation on the design device of the gas generating arc extinguishing polymer of the low-voltage circuit breaker, which can include more components than the above, or combine certain components, or different components, for example, the design device of the gas generating arc extinguishing polymer of the low-voltage circuit breaker can also include an input / output device, a network access device, a bus, and the like.

[0063] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and the like. The general-purpose processor can be a microprocessor or the processor can be any conventional processor. The processor is the control center of the design of the gas generating arc extinguishing polymer of the low-voltage circuit breaker, and is connected to each part of the design device of the gas generating arc extinguishing polymer of the low-voltage circuit breaker through various interfaces and lines.

[0064] The memory can be used to store the computer programs and / or modules, and the processor realizes various functions of the design device of the gas generating arc extinguishing polymer of the low-voltage circuit breaker by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory.

[0065] The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application program required for a function (such as a sound playing function, an image playing function, and the like), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, and the like), and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0066] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the low-voltage circuit breaker gas production arc-extinguishing polymer design method.

[0067] The modules / units of the low-voltage circuit breaker gas production arc-extinguishing polymer design system are stored in a computer readable storage medium if they are implemented in the form of software function units and sold or used as independent products.

[0068] Based on the understanding, all or part of the low-voltage circuit breaker gas production arc-extinguishing polymer design method can also be completed by instructing related hardware through a computer program, the computer program can be stored in a computer readable storage medium, and the computer program can implement the steps of the low-voltage circuit breaker gas production arc-extinguishing polymer design method when executed by a processor. The computer program includes computer program codes, which can be in the form of source codes, object codes, executable files or preset intermediate forms.

[0069] The computer readable storage medium can include any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier wave signal, telecommunication signal and software distribution medium, etc. that can carry the computer program codes.

[0070] It should be noted that the content included in the computer readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable storage medium does not include electric carrier wave signals and telecommunication signals.

[0071] In summary, the application provides a low-voltage circuit breaker gas production arc-extinguishing polymer design method, system and product, which has the following advantages: First, the research and development efficiency and cost advantage: the application replaces the traditional "universal experiment-accidental discovery" mode with the "computational screening-experimental verification" mode, shortens the research and development period from several months or even several years to several weeks, and replaces a large number of physical experiments with computer virtual screening, greatly reducing the cost of manpower, material resources and time.

[0072] Second, design accuracy and performance upper limit: the powerful non-linear fitting ability of the graph neural network can accurately predict the material performance from the molecular structure level, and systematically evaluate a large number of candidate molecules, thereby discovering new materials with more excellent comprehensive performance that are difficult to reach by traditional trial-and-error methods, and breaking through the performance bottleneck of existing materials.

[0073] Third, scientific closed loop and self-evolution ability: the present application constructs a "prediction-verification-feedback-iteration" closed loop system. The system enables the performance prediction model to continuously learn and evolve from new experimental data, and its prediction accuracy and reliability are constantly improved with the increase of application times.

[0074] Fourth, objectivity and standardization of evaluation: the multi-parameter and dynamic comprehensive evaluation method proposed by the present application provides a unified standard for objectively and quantitatively comparing the performance of different arc extinguishing materials, overcoming the one-sidedness of previous evaluation methods based on single static indicators, so that the evaluation results can more truly reflect the actual application effect of the materials.

[0075] The above examples are only one of the implementation manners of the technical solutions of the present application, and the scope of protection of the present application is not limited to the above examples, but also includes any changes, substitutions and other implementation manners that are easily thought of by those skilled in the art within the technical scope disclosed by the present application.

[0076] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application and not to limit them, although the present application has been described in detail with reference to the above examples, those skilled in the art should understand that: the specific implementation of the present application can still be modified or replaced, without departing from the spirit and scope of the present application, any modification or equivalent replacement, which should be covered within the protection scope of the claims of the present application.

Claims

1. A design method for a gas-generating arc-extinguishing polymer for a low-voltage circuit breaker, characterized in that, include: Multiple groups of candidate organic additive molecules were obtained from a pre-constructed candidate database; The candidate organic additive molecules are input into a pre-trained performance prediction model to obtain the prediction results of the intermediate performance indicators corresponding to each group of candidate organic additive molecules; wherein, the performance prediction model is used to characterize the mapping relationship between the molecular structure of organic additives and the corresponding intermediate performance indicators, and the basic model of the performance prediction model is a graph neural network model, which is trained on a dataset containing the molecular structure of organic additives and the corresponding intermediate performance indicators. Based on a preset intermediate performance index threshold, candidate organic additive molecules that meet the intermediate performance index threshold requirements are selected from the intermediate performance index prediction results as candidate organic additive molecules; the candidate organic additive molecules are used to blend with the nylon matrix in a predetermined ratio to prepare the gas-generating arc-extinguishing polymer for low-voltage circuit breakers.

2. The design method of a gas-generating arc-extinguishing polymer for a low-voltage circuit breaker according to claim 1, characterized in that, The graph neural network model employs graph convolutional networks, graph attention networks, or message passing neural networks.

3. The design method of a gas-generating arc-extinguishing polymer for a low-voltage circuit breaker according to claim 1, characterized in that, The nylon matrix is ​​made of polyamide 6, polyamide 46, polyamide 66 or polyamide 12.

4. The design method of a gas-generating arc-extinguishing polymer for a low-voltage circuit breaker according to claim 1, characterized in that, The training process of the performance prediction model includes: A dataset was constructed based on the molecular structures and corresponding intermediate performance indicators of various organic additives. A graph neural network model for constructing a performance prediction model is provided. The graph neural network model adopts a graph attention network. The graph attention network includes an embedding module for feature mapping, a graph information aggregation module consisting of multiple graph attention layers, a readout module for generating molecular graph-level representations, and a fully connected prediction module for outputting the final prediction value. The dataset is divided into training set, validation set and test set according to a preset ratio; The constructed graph neural network model is trained, tested, and validated sequentially based on the training set, validation set, and test set to output a trained performance prediction model.

5. The design method of a gas-generating arc-extinguishing polymer for a low-voltage circuit breaker according to claim 1, characterized in that, After selecting candidate organic additive molecules that meet the intermediate performance index threshold requirements from the intermediate performance index prediction results based on a preset intermediate performance index threshold, the process further includes: Candidate organic additive molecules are blended with nylon matrix in a predetermined ratio to prepare a gas-generating arc-extinguishing polymer for low-voltage circuit breakers. Obtain gas-generating arc-extinguishing polymer samples, conduct a comprehensive evaluation of the gas-generating arc-extinguishing polymer samples, and output the evaluation results; Based on the evaluation results, determine whether the gas-generating arc-extinguishing polymer sample meets the material arc-extinguishing standard requirements: if it does, obtain the gas-generating arc-extinguishing polymer that meets the material arc-extinguishing standard requirements; otherwise, obtain the experimental results of intermediate performance indicators of the candidate organic additive molecules through experiments, and supplement the candidate organic additive molecules and the corresponding intermediate performance indicator experimental results into the dataset.

6. The design method of a gas-generating arc-extinguishing polymer for a low-voltage circuit breaker according to claim 5, characterized in that, The comprehensive evaluation of the gas-generating arc-extinguishing polymer samples includes: The gas-generating arc-extinguishing polymer sample was placed in an arc testing device and an arc-extinguishing test was performed under a preset short-circuit current condition. Macroscopic evaluation parameters of the gas-generating arc-extinguishing polymer sample are collected in real time by sensors; the macroscopic evaluation parameters include arc voltage, arc current, arc time, arc-extinguishing chamber pressure, and ablation gas temperature. Based on the macroscopic evaluation parameters of the collected gas-generating arc-extinguishing polymer samples, and in conjunction with the material arc-extinguishing standard requirements, a comprehensive evaluation of the gas-generating arc-extinguishing polymer samples is conducted to output the evaluation results.

7. The design method of a gas-generating arc-extinguishing polymer for a low-voltage circuit breaker according to claim 6, characterized in that, The process involves comprehensively evaluating the gas-generating arc-extinguishing polymer samples based on the macroscopic evaluation parameters collected and in conjunction with the material arc-extinguishing standard requirements, to output evaluation results, including: The macroscopic evaluation parameters for determining whether a polymer sample generates gas to quench arcs must meet the following conditions: Condition 1: The peak pressure of the arc-extinguishing chamber is greater than 0.5 MPa; Condition 2: The temperature of the ablation gas in the arc-extinguishing chamber is below 400℃; Condition 3: The peak value of the arc voltage is greater than 400V; Condition 4: The peak value of the arc current is less than 2kA; Condition 5: Arcing time is less than 40ms; If the gas-generating arc-extinguishing polymer sample meets at least one of conditions one through five, then the gas-generating arc-extinguishing polymer sample is judged to meet the material arc-extinguishing standard requirements; otherwise, the gas-generating arc-extinguishing polymer sample is judged not to meet the material arc-extinguishing standard requirements.

8. The design method of a gas-generating arc-extinguishing polymer for a low-voltage circuit breaker according to claim 1, characterized in that, The intermediate performance indicators include gas production efficiency and thermal stability.

9. A gas-generating arc-extinguishing polymer system for a low-voltage circuit breaker, comprising the steps of designing the gas-generating arc-extinguishing polymer for the low-voltage circuit breaker according to any one of claims 1-8, characterized in that, include: The data acquisition module is used to acquire multiple sets of candidate organic additive molecules from a pre-built candidate database; The index prediction module is used to input candidate organic additive molecules into a pre-trained performance prediction model to obtain the prediction results of intermediate performance indices for each group of candidate organic additive molecules. The performance prediction model is used to characterize the mapping relationship between the molecular structure of organic additives and the corresponding intermediate performance indices. The basic model of the performance prediction model is a graph neural network model, which is trained on a dataset containing the molecular structure of organic additives and the corresponding intermediate performance indices. The molecular screening module is used to screen out candidate organic additive molecules that meet the intermediate performance index threshold requirements from the intermediate performance index prediction results based on a preset intermediate performance index threshold, and to use them as candidate organic additive molecules; the candidate organic additive molecules are used to blend with the nylon matrix in a predetermined ratio to prepare the gas-generating arc-extinguishing polymer for the low-voltage circuit breaker.

10. A gas-generating arc-extinguishing polymer product for low-voltage circuit breakers, characterized in that, The polymer for generating arc extinguishing gas in the low-voltage circuit breaker according to any one of claims 1-8 was prepared using the design method.

Images