Preparation method and system for mineral insulated flexible cable

Abstract

The invention relates to the technical field of cable preparation, and discloses a preparation method and system for a mineral insulated flexible cable, and the method comprises the steps: judging whether a preparation condition is met or not according to an environment dust value, determining a predicted preparation temperature value based on a cable comprehensive value and a cable preparation model, and determining the cable preparation similarity, based on a historical preparation temperature value and a predicted preparation temperature value corresponding to the cable preparation similarity, whether the predicted preparation temperature value is adjusted is judged, when it is judged that the predicted preparation temperature value is adjusted, number sequence division is conducted on each clustering distance in the clustering temperature set to determine a preparation number sequence, and a fitting curve is determined based on the preparation number sequence; and preparing the insulated flexible cable according to the adjusted predicted preparation temperature value. According to the method, dynamic adjustment is carried out by utilizing historical cable data, so that the preparation reliability of mineral insulated flexible cables with different sizes is ensured, and the dependence on human experience is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of cable preparation, and more particularly, to a preparation method and system for a mineral insulated flexible cable. Background Art

[0002] In the field of cables, mineral insulated flexible cables are widely used in many industries with strict requirements for cable performance, such as petrochemical, metallurgy, electric power, aerospace, etc., due to their excellent electrical properties, high temperature resistance characteristics, and good flexibility. The preparation process of cables is extremely complex, involving multiple precision processes. From the processing of wire cores, the laying of insulating layers to the forming of sheaths, each link plays a decisive role in the final quality of the cables. In the actual preparation process, the required preparation temperatures for cables of different sizes are different. Due to the differences in the skill levels, work experience, and operating habits of different workers, the preparation temperature is easily affected by humans, resulting in insufficient efficiency and reliability in the preparation of cables.

[0003] Therefore, how to provide a preparation method and system for a mineral insulated flexible cable is an urgent technical problem to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, the present invention proposes a preparation method and system for a mineral insulated flexible cable, aiming to solve the problem that the required preparation temperatures for cables of different sizes are different. Due to the differences in the skill levels, work experience, and operating habits of different workers, the preparation temperature is easily affected by humans, resulting in insufficient efficiency and reliability in the preparation of cables.

[0005] On the one hand, the present invention proposes a preparation method for a mineral insulated flexible cable, including: Obtaining a plurality of dust data in the preparation area of the insulated flexible cable, preprocessing each dust data, determining the environmental dust value based on the result of the preprocessing, judging whether it meets the preparation conditions according to the environmental dust value, and when the preparation conditions are met, obtaining the preparation parameters of the insulated flexible cable, and determining the cable comprehensive value based on the preparation parameters; Determining the predicted preparation temperature value based on the cable comprehensive value and the cable preparation model, determining the cable preparation similarity based on the predicted preparation temperature value and the historical cable data, and judging whether to adjust the predicted preparation temperature value based on the historical preparation temperature value corresponding to the cable preparation similarity and the predicted preparation temperature value; When it is determined to adjust the predicted preparation temperature value, analyzing the historical cable data, determining the temperature deviation value from the predicted preparation temperature value, establishing a clustering temperature set, and dividing each clustering distance in the clustering temperature set to determine the preparation sequence; Determine a fitting curve based on the prepared sequence numbers. According to the fitting curve, determine an adjustment coefficient for the predicted preparation temperature value, and prepare the insulated flexible cable according to the adjusted predicted preparation temperature value.

[0006] Further, when preprocessing each dust data, determining an environmental dust value based on the results of the preprocessing, and judging whether it meets the preparation conditions according to the environmental dust value, it includes: The preprocessing includes data cleaning and data standardization; Statistically analyze all preprocessed dust data and take the average value to determine the environmental dust value, and compare the environmental dust value with the standard environmental dust value to judge whether it meets the preparation conditions; When the environmental dust value is greater than or equal to the standard environmental dust value, it is determined that the preparation conditions are not met; When the environmental dust value is less than the standard environmental dust value, it is determined that the preparation conditions are met.

[0007] Further, when determining the cable comprehensive value based on the preparation parameters, it includes: The preparation parameters include the cable cross-sectional area, insulation layer thickness, number of cable layers, and number of cable cores of the insulated flexible cable; Normalize the cable cross-sectional area, the insulation layer thickness, the number of cable layers, and the number of cable cores, and determine the cable comprehensive value according to the normalization results. The cable comprehensive value is obtained according to the following formula:

[0008] Among them, SN represents the cable comprehensive value, M represents the normalized insulation layer thickness, H represents the normalized cable cross-sectional area, L represents the normalized number of cable layers, and R represents the normalized number of cable cores.

[0009] Further, when determining the predicted preparation temperature value based on the cable comprehensive value and the cable preparation model, it includes: Obtain a cable preparation set, and divide the cable preparation set into a training set and a test set; Pre-select a random forest model, perform iterative training on the random forest model according to the training set, evaluate the area under the AUC-ROC curve of the iteratively trained random forest model according to the test set, and determine the cable preparation model; If the area under the AUC-ROC curve of the random forest model after the current iterative training is greater than or equal to the area under the AUC-ROC curve of the random forest model after the previous iterative training and greater than the preset area under the AUC-ROC curve, stop the iterative training to obtain the cable preparation model; otherwise, use grid search to find the hyperparameters of the random forest model and continue the iterative training until the preset number of iterations is reached.

[0010] Further, when determining the cable preparation similarity based on the predicted preparation temperature value and historical cable data, it includes: The historical cable data includes a number of historical cable comprehensive values and a number of historical preparation temperature values, and each historical cable comprehensive value corresponds to a historical preparation temperature value. Calculate the cable preparation similarity for each one through the following formula:

[0011] where Fi represents the cable preparation similarity of the i-th historical cable comprehensive value in the historical cable data, Si represents the i-th historical cable comprehensive value, SN represents the cable comprehensive value, Ti represents the i-th historical preparation temperature value in the historical cable data, and TN represents the predicted preparation temperature value.

[0012] Further, when determining whether to adjust the predicted preparation temperature value based on the historical preparation temperature value corresponding to the cable preparation similarity and the predicted preparation temperature value, it includes: Determine the maximum cable preparation similarity among all cable preparation similarities, and use the corresponding historical preparation temperature value as the temperature comparison value; When the maximum cable preparation similarity among all cable preparation similarities is unique, use the corresponding historical preparation temperature value as the temperature comparison value; When the maximum cable preparation similarity among all cable preparation similarities is not unique, use the average value of the historical preparation temperature values corresponding to each data as the temperature comparison value; When the temperature comparison value is greater than the predicted preparation temperature value, determine to adjust the predicted preparation temperature value; When the temperature comparison value is less than or equal to the predicted preparation temperature value, determine not to adjust the predicted preparation temperature value, and prepare the insulated flexible cable according to the predicted preparation temperature value.

[0013] Further, when analyzing the historical cable data to determine the temperature deviation value from the predicted preparation temperature value, establishing a clustering temperature set, and dividing each clustering distance in the clustering temperature set to determine a preparation sequence, it includes: Analyze all historical preparation temperature values in the historical cable data, determine the temperature deviation values between each historical preparation temperature value and the predicted preparation temperature value, and cluster all the temperature deviation values to establish the clustering temperature set; Determine the clustering center of the clustering temperature set, obtain the clustering distance from each temperature deviation value to the clustering center of the clustering temperature set, and determine the clustering distance variance and the clustering distance mean of the clustering temperature set; Compare the clustering distance variance and the clustering distance mean, and determine the preparation sequence according to the comparison result for sequence division; When the clustering distance variance is not equal to the clustering distance mean, according to the clustering distance variance or the clustering distance mean, perform sequence division on each clustering distance in the clustering temperature set to determine the preparation sequence; When the clustering distance variance is equal to the clustering distance mean, determine the clustering number of all clustering distances, take the natural logarithm of the clustering number, and determine it as the adjustment coefficient of the predicted preparation temperature value.

[0014] Further, when the clustering distance variance is not equal to the clustering distance mean, and according to the clustering distance variance or the clustering distance mean, performing sequence division on each clustering distance in the clustering temperature set to determine the preparation sequence includes: When the clustering distance variance is greater than the clustering distance mean, perform sequence division according to the clustering distance variance to determine the preparation sequence; When the clustering distance variance is less than the clustering distance mean, perform sequence division according to the clustering distance mean to determine the preparation sequence; The preparation sequence includes a first preparation sequence, a second preparation sequence, and a third preparation sequence; When performing sequence division according to the clustering distance variance to determine the preparation sequence, it includes: Divide the clustering distances in the clustering temperature set that are greater than the clustering distance variance into the first preparation sequence, divide the clustering distances in the clustering temperature set that are equal to the clustering distance variance into the second preparation sequence, and divide the clustering distances in the clustering temperature set that are less than the clustering distance variance into the third preparation sequence; When performing sequence division according to the clustering distance mean to determine the preparation sequence, it includes: Divide the clustering distances in the clustering temperature set that are greater than the clustering distance mean into the first preparation sequence, divide the clustering distances in the clustering temperature set that are equal to the clustering distance mean into the second preparation sequence, and divide the clustering distances in the clustering temperature set that are less than the clustering distance mean into the third preparation sequence.

[0015] Further, when determining the fitting curve based on the prepared sequence numbers, determining the adjustment coefficient of the predicted preparation temperature value according to the fitting curve, and preparing the insulated flexible cable according to the adjusted predicted preparation temperature value, it includes: Performing curve fitting on the clustering distances in the first prepared sequence number to determine the first distance fitting curve, obtaining the slope corresponding to each clustering distance on the first distance fitting curve, and determining the average slope k1; Performing curve fitting on the clustering distances in the second prepared sequence number to determine the second distance fitting curve, obtaining the slope corresponding to each clustering distance on the second distance fitting curve, and determining the average slope k2; Performing curve fitting on the clustering distances in the third prepared sequence number to determine the third distance fitting curve, obtaining the slope corresponding to each clustering distance on the third distance fitting curve, and determining the average slope k3; The adjustment coefficient of the predicted preparation temperature value is e k1+k2+k3 ; The adjustment coefficient is in a proportional relationship with the predicted preparation temperature value.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: By collecting and preprocessing dust data, judging the preparation conditions based on the environmental dust value, ensuring that the cable is prepared in a suitable environment, effectively avoiding dust and other impurities from entering the interior of the cable, reducing the risk of faults such as insulation performance degradation and short circuits caused by impurities, improving the quality and stability of the prepared cable, using a cable preparation model to determine the predicted preparation temperature value, avoiding reliance on human experience, and determining the cable preparation similarity with historical cable data to judge whether to adjust the predicted preparation temperature value, ensuring the reliability and accuracy of the predicted preparation temperature value. When the predicted preparation temperature value needs to be adjusted, determining the fitting curve through the analysis of historical cable data not only conforms to the characteristics of historical cable data but also meets the actual needs of cable preparation, avoiding the time and resource waste brought by the judgment or repeated attempts of workers' experience during the preparation process, thereby improving the reliability of cable preparation.

[0017] On the other hand, the present application also provides a preparation system for a mineral insulated flexible cable for applying the above-mentioned preparation method for a mineral insulated flexible cable, including: A collection module configured to obtain a plurality of dust data in the preparation area of the insulated flexible cable, preprocess each dust data, determine the environmental dust value based on the preprocessing result, judge whether it meets the preparation conditions according to the environmental dust value, and when the preparation conditions are met, obtain the preparation parameters of the insulated flexible cable and determine the cable comprehensive value according to the preparation parameters; A judgment module, configured to determine a predicted preparation temperature value based on the comprehensive cable value and the cable preparation model, determine a cable preparation similarity based on the predicted preparation temperature value and historical cable data, and determine whether to adjust the predicted preparation temperature value based on the historical preparation temperature value corresponding to the cable preparation similarity and the predicted preparation temperature value; A processing module, configured to analyze the historical cable data to determine a temperature deviation value from the predicted preparation temperature value, establish a clustering temperature set, and perform a sequence division on each clustering distance in the clustering temperature set to determine a preparation sequence when it is determined to adjust the predicted preparation temperature value; A preparation module, configured to determine a fitting curve based on the preparation sequence, determine an adjustment coefficient for the predicted preparation temperature value according to the fitting curve, and prepare the mineral insulated flexible cable according to the adjusted predicted preparation temperature value.

[0018] It can be understood that the above-mentioned method and system for preparing a mineral insulated flexible cable have the same beneficial effects, which will not be elaborated here. Description of the Drawings

[0019] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered as limiting the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 is a flowchart of a method for preparing a mineral insulated flexible cable provided by an embodiment of the present invention; Figure 2 is a functional block diagram of a system for preparing a mineral insulated flexible cable provided by an embodiment of the present invention. Detailed Embodiments

[0020] Hereinafter, the exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0021] Refer to Figure 1 As shown, in some embodiments of the present application, this embodiment provides a method for preparing a mineral insulated flexible cable, including: S100: Obtain several dust data of the preparation area of the insulated flexible cable, preprocess each dust data, determine the environmental dust value based on the result of the preprocessing, judge whether it meets the preparation conditions according to the environmental dust value, when the preparation conditions are met, obtain the preparation parameters of the insulated flexible cable, and determine the cable comprehensive value based on the preparation parameters; S200: Determine the predicted preparation temperature value based on the cable comprehensive value and the cable preparation model, determine the cable preparation similarity based on the predicted preparation temperature value and the historical cable data, and judge whether to adjust the predicted preparation temperature value based on the historical preparation temperature value and the predicted preparation temperature value corresponding to the cable preparation similarity; S300: When it is determined to adjust the predicted preparation temperature value, analyze the historical cable data, determine the temperature deviation value from the predicted preparation temperature value, establish a clustering temperature set, and divide each clustering distance in the clustering temperature set into a sequence to determine the preparation sequence; S400: Determine the fitting curve based on the preparation sequence, determine the adjustment coefficient of the predicted preparation temperature value according to the fitting curve, and prepare the insulated flexible cable according to the adjusted predicted preparation temperature value.

[0022] Specifically, a particulate sensor and other acquisition devices are used to obtain a number of dust data in the preparation area of the insulated flexible cable. Preferably, 10 dust data are obtained. Obtaining multiple dust data avoids the risk of misjudgment caused by accidental acquisition errors. Through preprocessing, the influence of the dimension between different dust data can be eliminated, so as to determine the environmental dust value. By judging the environmental dust value, the environmental requirements required during cable preparation are ensured, and dust and other impurities are prevented from entering the cable during preparation, thereby affecting its electrical performance and insulation performance, and improving the reliability of cable preparation. The preparation temperature is predicted according to the cable comprehensive value and in combination with the cable preparation model. The cable preparation model uses machine learning methods to output the predicted preparation temperature value, avoiding relying on manual experience to determine the preparation temperature. The historical cable data reflects the experience of successful preparations in the past. By comparing the predicted preparation temperature value with the historical cable data, calculating the cable preparation similarity between the data, and finding the corresponding historical preparation temperature value, the two are compared to judge whether the predicted preparation temperature value needs to be adjusted, ensuring the efficiency of cable preparation, improving the accuracy of predicting the preparation temperature, and avoiding adjustment errors caused by simply relying on manual experience. When it is determined that the predicted preparation temperature value needs to be adjusted, the historical cable data is deeply analyzed, and the temperature deviation value between it and the predicted preparation temperature value is calculated. The data with deviation characteristics are clustered to form a clustering temperature set, so as to obtain the law of temperature deviation, providing a quantitative basis for the adjustment of the predicted preparation temperature value. The number sequence is divided for each clustering distance in the clustering temperature set to determine the preparation number sequence, so as to further explore the relationship between the temperature deviation and the predicted preparation temperature value, improving the pertinence of adjusting the predicted preparation temperature value, as well as the flexibility and adaptability of the preparation process.

[0023] It can be understood that the fitting curve constructed based on the preparation number sequence can accurately reflect the trend of temperature deviation. Based on this, the adjustment coefficient is determined, improving the accuracy of adjusting the predicted preparation temperature value, enhancing the reliability and efficiency of cable preparation, avoiding the risk of rework and resource waste caused by inappropriate preparation temperature relying on manual experience, and improving the efficiency of cable preparation.

[0024] In some embodiments of the present application, when preprocessing each dust data, determining the environmental dust value based on the preprocessing result, and judging whether it meets the preparation conditions according to the environmental dust value, it includes: the preprocessing includes data cleaning and data standardization, counting all the preprocessed dust data and taking the average value to determine the environmental dust value, and comparing the environmental dust value with the standard environmental dust value to judge whether it meets the preparation conditions. When the environmental dust value is greater than or equal to the standard environmental dust value, it is determined that it does not meet the preparation conditions; when the environmental dust value is less than the standard environmental dust value, it is determined that it meets the preparation conditions.

[0025] Specifically, data cleaning can effectively identify and eliminate outliers and incorrect data in the dust data. For example, during the data collection process, data collection devices such as particulate matter sensors may generate incorrect data that deviates from the actual situation due to electromagnetic interference or other interference factors. Data cleaning can remove this incorrect data to ensure the stability of the subsequent calculation of the environmental dust value. Data normalization, on the other hand, unifies data of different magnitudes and distributions into a specific range or scale, improving the accuracy of the calculation of the environmental dust value. Taking the mean of all preprocessed dust data to determine the environmental dust value, the environmental dust value comprehensively reflects the overall dust situation in the preparation area. Comparing the environmental dust value with the standard environmental dust value provides a clear and quantitative basis for judging whether the preparation environment meets the standards. The standard environmental dust value is determined according to the actual cable preparation process requirements. By comparing the environmental dust value with the standard environmental dust value, it is determined whether the preparation conditions are met, reducing the possibility of dust adhering to the insulation layer or the core of the cable and ensuring the efficiency of cable preparation.

[0026] In some embodiments of the present application, when determining the cable comprehensive value based on the preparation parameters, it includes: the preparation parameters include the cable cross-sectional area, insulation layer thickness, number of cable layers, and number of cable cores of the insulated flexible cable. Normalize the cable cross-sectional area, insulation layer thickness, number of cable layers, and number of cable cores, and determine the cable comprehensive value according to the normalization result. The cable comprehensive value is obtained according to the following formula:

[0027] Where SN represents the cable comprehensive value, M represents the normalized insulation layer thickness, H represents the normalized cable cross-sectional area, L represents the normalized number of cable layers, and R represents the normalized number of cable cores.

[0028] Specifically, preparation parameters such as the cable cross-sectional area and insulation layer thickness are difficult to directly calculate and comprehensively analyze due to different physical meanings and dimensions. The normalization process transforms these parameters into a unified scale range, eliminating the influence of dimensional differences, enabling each parameter to be calculated under the same standard. This lays the foundation for the calculation of the cable comprehensive value. The cable comprehensive value can comprehensively reflect the actual characteristics of the cable from multiple dimensions, avoiding the situation where the preparation temperature does not match the requirements of the insulated flexible cable due to human experience judgment, effectively improving the preparation efficiency, and ensuring the stability of the cable quality.

[0029] In some embodiments of the present application, when determining the predicted preparation temperature value based on the cable comprehensive value and the cable preparation model, the following steps are included: obtaining a cable preparation set, dividing the cable preparation set into a training set and a test set, pre-selecting a random forest model, iteratively training the random forest model according to the training set, evaluating the area under the AUC-ROC curve of the iteratively trained random forest model according to the test set to determine the cable preparation model. If the area under the AUC-ROC curve of the currently iteratively trained random forest model is greater than or equal to the area under the AUC-ROC curve of the previously iteratively trained random forest model and greater than the preset AUC-ROC curve area, then stop the iterative training to obtain the cable preparation model. Otherwise, use grid search to find the hyperparameters of the random forest model and continue the iterative training until the preset number of iterations is reached.

[0030] Specifically, the cable preparation set contains key data such as cable comprehensive values, preparation temperatures, and cable material specifications. These data record the temperature conditions of cable preparation under different sizes and models. The cable preparation set is divided into a training set and a test set. The training set is used to train the random forest model, while the test set is used to evaluate the performance of the trained model. Use 50% - 80% of the data as the training set and the rest as the test set. Ensure that both the training set and the test set contain data on various temperature conditions to improve the generalization ability of the model. The random forest model includes the number of trees, the maximum depth of the trees, etc., and aims to capture the complex relationships in the data. By training the random forest model, the predicted preparation temperature value for each cable comprehensive value can be output, avoiding the judgment of human experience. During each iterative training process, the model tries to learn the patterns and relationships in the data to improve its prediction or classification ability. After each iterative training, the data in the test set is used to evaluate the model. If the area under the AUC-ROC curve of the currently iteratively trained random forest model is greater than or equal to the area under the AUC-ROC curve of the previously iteratively trained random forest model and greater than the preset AUC-ROC curve area, it indicates that the model performance has improved or remained stable. Then stop the iterative training, believing that the model has reached a satisfactory performance level, which helps the model to stably approach the global optimal solution. Otherwise, use grid search to find the hyperparameters of the random forest model. Grid search exhaustively searches parameter combinations in the parameter space to improve the prediction ability of the model and continue the iterative training until the preset number of iterations is reached.

[0031] It is understandable that using cables to prepare the training random forest model makes full use of the temperature conditions of cable preparation under different sizes and models to improve the prediction ability of the model. Grid search and evaluation of the area under the AUC-ROC curve ensure the optimization of model parameters and enhance the stability and reliability of the model on different data. During the model training and validation process, by continuously adjusting parameters and evaluating model performance, a cable preparation model is finally obtained, improving the accuracy of predicting the preparation temperature value.

[0032] In some embodiments of the present application, when determining the cable preparation similarity based on the predicted preparation temperature value and historical cable data, it includes: the historical cable data includes a number of historical cable comprehensive values and a number of historical preparation temperature values, and each historical cable comprehensive value corresponds to a historical preparation temperature value. Calculate each cable preparation similarity through the following formula:

[0033] Where Fi represents the cable preparation similarity of the i-th historical cable comprehensive value in the historical cable data, Si represents the i-th historical cable comprehensive value, SN represents the cable comprehensive value, Ti represents the i-th historical preparation temperature value in the historical cable data, and TN represents the predicted preparation temperature value.

[0034] In some embodiments of the present application, when determining whether to adjust the predicted preparation temperature value based on the historical preparation temperature value corresponding to the cable preparation similarity and the predicted preparation temperature value, it includes: determining the largest cable preparation similarity among all cable preparation similarities and using the corresponding historical preparation temperature value as the temperature comparison value. When the largest cable preparation similarity among all cable preparation similarities is unique, use its corresponding historical preparation temperature value as the temperature comparison value. When the largest cable preparation similarity among all cable preparation similarities is not unique, use the average value of the historical preparation temperature values corresponding to each data as the temperature comparison value. When the temperature comparison value is greater than the predicted preparation temperature value, it is determined to adjust the predicted preparation temperature value. When the temperature comparison value is less than or equal to the predicted preparation temperature value, it is determined not to adjust the predicted preparation temperature value, and an insulated flexible cable is prepared according to the predicted preparation temperature value.

[0035] Specifically, the similarity of cable preparation is used to judge the matching degree between the current preparation conditions and the historical successful conditions. When the historical data with the maximum cable preparation similarity is found, the historical preparation temperature value corresponding to the maximum cable preparation similarity can be directly used as the temperature comparison value. If there are multiple maximum cable preparation similarities, the average value of the historical preparation temperature values corresponding to each data is used as the temperature comparison value, which ensures the flexibility and adaptability of determining the temperature comparison value. When the temperature comparison value is greater than the predicted preparation temperature value, the insulating material cannot be fully cross-linked or cured, resulting in unqualified indicators such as the electrical insulation performance and mechanical strength of the material. For example, if the predicted preparation temperature value is low, the toughness of the insulating layer is insufficient, and cracks and other situations will occur during the use of the cable, which will affect the service life and safety of the cable. Therefore, it is necessary to adjust the predicted preparation temperature value. When the temperature comparison value is less than or equal to the predicted preparation temperature value, it means that the predicted preparation temperature value is within the historical successful preparation temperature range, which can ensure that the preparation process follows the effective process parameters verified in history, reduces the dependence on manual experience and intuition, and reduces the uncertainty and preparation risk brought by human judgment. By comprehensively using a large amount of historical cable data, it is possible to make judgments and adjustments from historical experience, thereby continuously improving the efficiency of cable preparation.

[0036] In some embodiments of the present application, when analyzing historical cable data to determine and predict the temperature deviation value of the preparation temperature value, establishing a clustering temperature set, and dividing each clustering distance in the clustering temperature set into a sequence to determine the preparation sequence, it includes: analyzing all the historical preparation temperature values in the historical cable data, determining the temperature deviation value between each historical preparation temperature value and the predicted preparation temperature value, clustering all the temperature deviation values, establishing a clustering temperature set, determining the clustering center of the clustering temperature set, obtaining the clustering distance from each temperature deviation value to the clustering center of the clustering temperature set, determining the clustering distance variance and the clustering distance mean of the clustering temperature set, comparing the clustering distance variance and the clustering distance mean, and dividing the sequence according to the comparison result to determine the preparation sequence. When the clustering distance variance is not equal to the clustering distance mean, according to the clustering distance variance or the clustering distance mean, each clustering distance in the clustering temperature set is divided into a sequence to determine the preparation sequence. When the clustering distance variance is equal to the clustering distance mean, determining the clustering number of all clustering distances, taking the natural logarithm of the clustering number, and determining it as the adjustment coefficient of the predicted preparation temperature value.

[0037] Specifically, by analyzing the deviation between the historical preparation temperature value and the predicted preparation temperature value, the clustering center can be determined using algorithms such as the K-means algorithm, hierarchical clustering algorithm, density clustering algorithm, spectral clustering algorithm, etc. It is sufficient to select one of these algorithms for determination, and no specific limitation is imposed here. Moreover, the method for determining the clustering distance is lengthy and mature, so no detailed introduction will be provided here. Through clustering analysis, data with similar temperature deviation characteristics are grouped into one category, providing a basis for targeted adjustment of the predicted preparation temperature value. This effectively avoids quality problems such as a decline in the cable insulation performance and loose connection of the wire core caused by inappropriate predicted preparation temperature values, and improves the stability of the preparation. When the variance of the clustering distance is not equal to the mean of the clustering distance, based on these two values, a sequence division is performed on the sequence, which can fully consider the dispersion degree of the temperature deviation values, thereby determining an adjustment strategy that conforms to the actual situation. When the variance of the clustering distance is equal to the mean of the clustering distance, it indicates that all clustering distances tend to be stable and the temperature deviation situations are relatively concentrated. By taking the natural logarithm of the number of clusters to determine the adjustment coefficient, it ensures that the adjustment of the predicted preparation temperature value not only conforms to the characteristics of the historical cable data but also meets the actual requirements of cable preparation, avoiding the waste of time and resources brought about by the judgment or repeated attempts based on the experience of workers during the preparation process, thus improving the reliability of cable preparation.

[0038] In some embodiments of the present application, when the variance of the clustering distance is not equal to the mean of the clustering distance, when determining the preparation sequence by performing a sequence division on each clustering distance in the clustering temperature set according to the variance of the clustering distance or the mean of the clustering distance, it includes: when the variance of the clustering distance is greater than the mean of the clustering distance, determining the preparation sequence by performing a sequence division according to the variance of the clustering distance; when the variance of the clustering distance is less than the mean of the clustering distance, determining the preparation sequence by performing a sequence division according to the mean of the clustering distance. The preparation sequence includes a first preparation sequence, a second preparation sequence, and a third preparation sequence. When determining the preparation sequence by performing a sequence division according to the variance of the clustering distance, it includes: dividing the clustering distances in the clustering temperature set that are greater than the variance of the clustering distance into the first preparation sequence, dividing the clustering distances in the clustering temperature set that are equal to the variance of the clustering distance into the second preparation sequence, and dividing the clustering distances in the clustering temperature set that are less than the variance of the clustering distance into the third preparation sequence. When determining the preparation sequence by performing a sequence division according to the mean of the clustering distance, it includes: dividing the clustering distances in the clustering temperature set that are greater than the mean of the clustering distance into the first preparation sequence, dividing the clustering distances in the clustering temperature set that are equal to the mean of the clustering distance into the second preparation sequence, and dividing the clustering distances in the clustering temperature set that are less than the mean of the clustering distance into the third preparation sequence.

[0039] Specifically, the variance of the clustering distance reflects the degree of dispersion of the data, while the mean of the clustering distance reflects the average level of the data. When the variance of the clustering distance is greater than the mean of the clustering distance, it indicates that the degree of dispersion of the data is relatively large. At this time, when dividing the sequence according to the variance of the clustering distance, the dispersed characteristics of the data can be fully considered for targeted processing. On the contrary, when the variance of the clustering distance is less than the mean of the clustering distance, dividing according to the mean of the clustering distance can better fit the relatively concentrated characteristics of the data, ensuring that the determination of the prepared sequence can accurately adapt to the data characteristics, laying a foundation for subsequent adjustment of the predicted preparation temperature value. By dynamically dividing the clustering distance into the corresponding prepared sequences, refined classification of the temperature deviation value is achieved. Different prepared sequences correspond to different degrees of temperature deviation, thereby realizing precise control of the predicted preparation temperature value, avoiding time waste caused by error accumulation due to relying on human experience in the preparation process, and improving the efficiency of the preparation.

[0040] In some embodiments of the present application, when determining the fitting curve based on the prepared sequence, determining the adjustment coefficient of the predicted preparation temperature value according to the fitting curve, and preparing the insulated flexible cable according to the adjusted predicted preparation temperature value, it includes: performing curve fitting on the clustering distances in the first prepared sequence to determine the first distance fitting curve, obtaining the slope corresponding to each clustering distance on the first distance fitting curve, and determining the average slope k1; performing curve fitting on the clustering distances in the second prepared sequence to determine the second distance fitting curve, obtaining the slope corresponding to each clustering distance on the second distance fitting curve, and determining the average slope k2; performing curve fitting on the clustering distances in the third prepared sequence to determine the third distance fitting curve, obtaining the slope corresponding to each clustering distance on the third distance fitting curve, and determining the average slope k3. The adjustment coefficient of the predicted preparation temperature value is e k1+k2+k3 , and the adjustment coefficient is in a direct proportional relationship with the predicted preparation temperature value.

[0041] Specifically, when performing curve fitting, any one of the algorithms of polynomial fitting, spline interpolation, and least squares method can be selected, and no specific limitation is made here. The average slopes of the respective distance fitting curves (the first distance fitting curve, the second distance fitting curve, and the third distance fitting curve) can effectively reflect the changing trends of the clustering distances in different sequences. e is equal to the base of the natural logarithm, and here it is preferably 2.718. Adjust the predicted preparation temperature value according to the adjustment coefficient. Assume that the adjustment coefficient is determined as W, the predicted preparation temperature value determined through the model is Z, and the adjusted predicted preparation temperature value is determined as W*Z. By establishing a direct proportional relationship between the adjustment coefficient and the predicted preparation temperature value, the accuracy of adjusting the predicted preparation temperature value when the temperature comparison value is greater than the predicted preparation temperature value is achieved, thereby reducing the dependence on human experience, reducing human errors in the preparation process, and improving the reliability and efficiency of cable preparation.

[0042] In summary, the beneficial effects of the present invention are as follows: By collecting and preprocessing dust data, and judging the preparation conditions based on the environmental dust value, it ensures that the cable is prepared in a suitable environment, effectively avoiding the entry of dust and other impurities into the interior of the cable, reducing the risk of faults such as a decline in insulation performance and short circuits caused by impurities, improving the quality and stability of the prepared cable. The cable preparation model is used to determine the predicted preparation temperature value, avoiding the dependence on human experience, and determining the cable preparation similarity with historical cable data to judge whether to adjust the predicted preparation temperature value, ensuring the reliability and accuracy of the predicted preparation temperature value. When the predicted preparation temperature value needs to be adjusted, the fitting curve is determined by analyzing the historical cable data, which not only conforms to the characteristics of the historical cable data but also meets the actual requirements of cable preparation, avoiding the waste of time and resources brought by the judgment of workers' experience or repeated attempts during the preparation process, thereby improving the reliability of the prepared cable.

[0043] In another preferred embodiment based on the above embodiments, refer to Figure 2 As shown, this embodiment provides a preparation system for a mineral insulated flexible cable, which is used to apply the above-mentioned preparation method for a mineral insulated flexible cable, including: A collection module, configured to obtain a plurality of dust data in the preparation area of the insulated flexible cable, preprocess each dust data, determine the environmental dust value based on the result of the preprocessing, judge whether it meets the preparation conditions according to the environmental dust value, and when the preparation conditions are met, obtain the preparation parameters of the insulated flexible cable and determine the cable comprehensive value according to the preparation parameters; A judgment module, configured to determine the predicted preparation temperature value based on the cable comprehensive value and the cable preparation model, determine the cable preparation similarity based on the predicted preparation temperature value and historical cable data, and judge whether to adjust the predicted preparation temperature value based on the historical preparation temperature value and the predicted preparation temperature value corresponding to the cable preparation similarity; A processing module, configured to analyze the historical cable data when it is determined to adjust the predicted preparation temperature value, determine the temperature deviation value from the predicted preparation temperature value, establish a clustering temperature set, and divide each clustering distance in the clustering temperature set into a sequence to determine the preparation sequence; A preparation module, configured to determine the fitting curve based on the preparation sequence, determine the adjustment coefficient of the predicted preparation temperature value according to the fitting curve, and prepare the insulated flexible cable according to the adjusted predicted preparation temperature value.

[0044] Specifically, by collecting and preprocessing dust data, the preparation conditions are determined based on the environmental dust value to ensure that the cable is prepared in a suitable environment, effectively preventing dust and other impurities from entering the interior of the cable, reducing the risk of faults such as insulation performance degradation and short circuits caused by impurities, improving the quality and stability of the prepared cable. The cable preparation model is used to determine the predicted preparation temperature value, avoiding reliance on human experience, and the similarity of cable preparation is determined with historical cable data to judge whether to adjust the predicted preparation temperature value, ensuring the reliability and accuracy of the predicted preparation temperature value. When the predicted preparation temperature value needs to be adjusted, the fitting curve is determined through the analysis of historical cable data, which not only conforms to the characteristics of historical cable data but also meets the actual requirements of cable preparation, avoiding the waste of time and resources caused by the judgment or repeated attempts based on the experience of workers during the preparation process, thereby improving the reliability of cable preparation.

[0045] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0046] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 or multiple flows and / or blocks.

[0047] These computer program instructions can also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable storage medium generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one or more flows and / or blocks Figure 1 or multiple flows and / or blocks.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the steps of the process Figure 1 in one process or a plurality of processes and / or boxes Figure 1 or steps for implementing the functions specified in one box or a plurality of boxes.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for preparing a mineral insulated flexible cable, characterized in that: include: Acquire a plurality of dust data of a preparation area of ​​the insulated flexible cable, preprocess each dust data, determine an environmental dust value based on the preprocessing result, judge whether the preparation conditions are met according to the environmental dust value, and when the preparation conditions are met, obtain the preparation parameters of the insulated flexible cable, and determine the comprehensive value of the cable based on the preparation parameters; Determine a predicted preparation temperature value based on the cable comprehensive value and the cable preparation model, determine the cable preparation similarity based on the predicted preparation temperature value and historical cable data, and determine whether to adjust the predicted preparation temperature value based on the historical preparation temperature values ​​corresponding to the cable preparation similarity and the predicted preparation temperature value; When it is determined that the predicted preparation temperature value is to be adjusted, the historical cable data is analyzed to determine the temperature deviation value from the predicted preparation temperature value, a cluster temperature set is established, and each cluster distance in the cluster temperature set is divided into a series to determine a preparation series; A fitting curve is determined based on the preparation series, an adjustment coefficient of the predicted preparation temperature value is determined according to the fitting curve, and the insulated flexible cable is prepared according to the adjusted predicted preparation temperature value.

2. The method for preparing a mineral insulated flexible cable according to claim 1, characterized in that: When preprocessing each dust data, determining the environmental dust value based on the preprocessing result, and judging whether the preparation condition is met according to the environmental dust value, the method includes: The preprocessing includes data cleaning and data standardization; Counting all pre-processed dust data and taking the average to determine the environmental dust value, and comparing the environmental dust value with the standard environmental dust value to determine whether the preparation conditions are met; When the environmental dust value is greater than or equal to the standard environmental dust value, it is determined that the preparation condition is not met; When the environmental dust value is less than the standard environmental dust value, it is determined that the preparation condition is met.

3. The method for preparing a mineral insulated flexible cable according to claim 2, characterized in that: When determining the comprehensive value of the cable based on the preparation parameters, it includes: The preparation parameters include the cable cross-sectional area, insulation layer thickness, number of cable layers and number of cable cores of the insulated flexible cable; The cable cross-sectional area, the insulation layer thickness, the number of cable layers and the number of cable cores are normalized, and the cable comprehensive value is determined according to the normalized result. The cable comprehensive value is obtained according to the following formula: ； Among them, SN represents the comprehensive value of the cable, M represents the normalized insulation layer thickness, H represents the normalized cable cross-sectional area, L represents the normalized number of cable layers, and R represents the normalized number of cable cores.

4. The method for preparing a mineral insulated flexible cable according to claim 3, characterized in that: When the predicted preparation temperature value is determined based on the cable comprehensive value and the cable preparation model, it includes: Acquire a cable preparation set, and divide the cable preparation set into a training set and a test set; Preselecting a random forest model, and iteratively training the random forest model according to the training set, evaluating the area under the AUC-ROC curve of the iteratively trained random forest model according to the test set, and determining the cable preparation model; If the area under the AUC-ROC curve of the random forest model after the current iterative training is greater than or equal to the area under the AUC-ROC curve of the random forest model after the previous iterative training, and is greater than the area under the preset AUC-ROC curve, the iterative training is stopped to obtain the cable preparation model. Otherwise, a grid search is used to find the hyperparameters of the random forest model, and iterative training is continued until the preset number of iterations is reached.

5. The method for preparing a mineral insulated flexible cable according to claim 4, characterized in that: When determining the cable preparation similarity based on the predicted preparation temperature value and the historical cable data, it includes: The historical cable data includes several historical cable comprehensive values ​​and several historical preparation temperature values, and each historical cable comprehensive value corresponds to a historical preparation temperature value. The similarity of each cable preparation is calculated by the following formula: ； Among them, Fi represents the cable preparation similarity of the i-th historical cable comprehensive value in the historical cable data, Si represents the i-th historical cable comprehensive value, SN represents the cable comprehensive value, Ti represents the i-th historical preparation temperature value in the historical cable data, and TN represents the predicted preparation temperature value.

6. The method for preparing a mineral insulated flexible cable according to claim 5, characterized in that: When judging whether to adjust the predicted preparation temperature value based on the historical preparation temperature value corresponding to the cable preparation similarity and the predicted preparation temperature value, it includes: Determine the largest cable preparation similarity among all cable preparation similarities, and use the corresponding historical preparation temperature value as the temperature comparison value; When the largest cable preparation similarity among all cable preparation similarities is unique, the corresponding historical preparation temperature value is used as the temperature comparison value; When the largest cable preparation similarity among all cable preparation similarities is not unique, the average of the historical preparation temperature values ​​corresponding to each data is used as the temperature comparison value; When the temperature comparison value is greater than the predicted preparation temperature value, determining to adjust the predicted preparation temperature value; When the temperature comparison value is less than or equal to the predicted preparation temperature value, it is determined that the predicted preparation temperature value is not to be adjusted, and the insulated flexible cable is prepared according to the predicted preparation temperature value.

7. The method for preparing a mineral insulated flexible cable according to claim 6, characterized in that: When analyzing the historical cable data, determining the temperature deviation value from the predicted preparation temperature value, establishing a cluster temperature set, and dividing each cluster distance in the cluster temperature set into a series to determine the preparation series, it includes: Analyze all historical preparation temperature values ​​in the historical cable data, determine the temperature deviation value between each historical preparation temperature value and the predicted preparation temperature value, cluster all the temperature deviation values, and establish the clustered temperature set; Determine the cluster center of the cluster temperature set, obtain the cluster distance from each temperature deviation value to the cluster center of the cluster temperature set, and determine the cluster distance variance of the cluster temperature set and the cluster distance mean of the cluster temperature set; Comparing the cluster distance variance with the cluster distance mean, and performing series division according to the comparison result to determine the preparation series; When the cluster distance variance is not equal to the cluster distance mean, dividing each cluster distance in the cluster temperature set into series according to the cluster distance variance or the cluster distance mean to determine the prepared series; When the cluster distance variance is equal to the cluster distance mean, the number of clusters of all cluster distances is determined, and the natural logarithm of the number of clusters is taken to determine the adjustment coefficient of the predicted preparation temperature value.

8. The method for preparing a mineral insulated flexible cable according to claim 7, characterized in that: When the cluster distance variance is not equal to the cluster distance mean, dividing each cluster distance in the cluster temperature set into a series according to the cluster distance variance or the cluster distance mean to determine the prepared series, the method includes: When the cluster distance variance is greater than the cluster distance mean, performing series division according to the cluster distance variance to determine the prepared series; When the cluster distance variance is less than the cluster distance mean, performing series division according to the cluster distance mean to determine the prepared series; The preparing a number sequence includes preparing a first number sequence, preparing a second number sequence, and preparing a third number sequence; When performing series division according to the cluster distance variance to determine the prepared series, it includes: The cluster distances in the cluster temperature set that are greater than the cluster distance variance are divided into the prepared first number series, the cluster distances in the cluster temperature set that are equal to the cluster distance variance are divided into the prepared second number series, and the cluster distances in the cluster temperature set that are less than the cluster distance variance are divided into the prepared third number series; When performing series division according to the cluster distance mean to determine the prepared series, it includes: The cluster distances in the cluster temperature set that are greater than the cluster distance mean are divided into the prepared first series, the cluster distances in the cluster temperature set that are equal to the cluster distance mean are divided into the prepared second series, and the cluster distances in the cluster temperature set that are less than the cluster distance mean are divided into the prepared third series.

9. The method for preparing a mineral insulated flexible cable according to claim 8, characterized in that: When determining a fitting curve based on the preparation series, determining an adjustment coefficient of the predicted preparation temperature value according to the fitting curve, and preparing the insulated flexible cable according to the adjusted predicted preparation temperature value, the method includes: Performing curve fitting on the cluster distances in the prepared first series, determining a distance fitting first curve, obtaining a slope corresponding to each cluster distance on the distance fitting first curve, and determining an average slope k1; Performing curve fitting on the cluster distances in the prepared second series, determining a distance fitting second curve, obtaining a slope corresponding to each cluster distance on the distance fitting second curve, and determining an average slope k2; Performing curve fitting on the cluster distances in the prepared third series, determining a distance fitting third curve, obtaining a slope corresponding to each cluster distance on the distance fitting third curve, and determining an average slope k3; The adjustment coefficient of the predicted preparation temperature value is e k1+k2+k3 ; The adjustment coefficient is directly proportional to the predicted preparation temperature value.

10. A system for preparing a mineral insulated flexible cable, used for applying the method for preparing a mineral insulated flexible cable according to any one of claims 1 to 9, characterized in that: include: The acquisition module is configured to obtain a plurality of dust data of a preparation area of ​​the insulated flexible cable, preprocess each dust data, determine an environmental dust value based on a result of the preprocessing, determine whether the preparation conditions are met according to the environmental dust value, obtain the preparation parameters of the insulated flexible cable when the preparation conditions are met, and determine the cable comprehensive value according to the preparation parameters; A judgment module is configured to determine a predicted preparation temperature value based on the cable comprehensive value and the cable preparation model, determine the cable preparation similarity based on the predicted preparation temperature value and historical cable data, and judge whether to adjust the predicted preparation temperature value based on the historical preparation temperature value corresponding to the cable preparation similarity and the predicted preparation temperature value; A processing module is configured to analyze the historical cable data, determine the temperature deviation value from the predicted preparation temperature value, establish a cluster temperature set, and divide each cluster distance in the cluster temperature set into a series to determine a preparation series when it is determined that the predicted preparation temperature value is adjusted; The preparation module is configured to determine a fitting curve based on the preparation series, determine an adjustment coefficient of the predicted preparation temperature value according to the fitting curve, and prepare the insulated flexible cable according to the adjusted predicted preparation temperature value.

Images