Transformer processing and manufacturing platform

Abstract

The invention discloses a transformer processing and manufacturing platform, and belongs to the technical field of intelligent manufacturing. The platform comprises a material performance analysis module, a structure process analysis module, an insulation state analysis module, a comprehensive performance analysis module and a drying vacuum degree optimization module. The platform carries out quantitative fusion and evaluation on multi-source quality data in the transformer manufacturing process through a material performance model, a structure model, an insulation state model and a comprehensive performance adaptation degree model, and finally self-adaptive adjustment of process parameters is achieved through a drying vacuum degree optimization model. According to the invention, full-process digital quality control from raw materials to finished products is realized, traditional post inspection is converted into prospective optimization based on model prediction and feedback, and the precision, consistency and intelligent level of transformer manufacturing are effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of intelligent manufacturing technology, and in particular relates to a transformer processing and manufacturing platform. Background Technology

[0002] As a core component of the power system, the manufacturing quality of transformers directly affects the reliability and energy efficiency of the power grid. With the development of smart grids and new energy sources, the requirements for transformer performance, efficiency, and reliability are increasing. Traditional manufacturing models relying on fixed processes and discrete inspections are no longer sufficient to meet the demands for high-quality, customized production. Therefore, intelligent transformer processing and manufacturing platforms integrating sensing, analysis, and decision-making functions have become an important development direction for the industry.

[0003] Existing transformer manufacturing platforms mostly focus on automating single processes, such as CNC winding, automatic lamination, or vacuum impregnation. While this improves local efficiency, quality data from each stage is isolated, lacking a collaborative analysis and optimization mechanism that spans the entire design, production, and testing process. Setting process parameters often relies on experience, making it difficult to dynamically adjust based on raw material fluctuations and real-time operating conditions. This results in bottlenecks in quality consistency control and long cycles for problem tracing and process improvement.

[0004] Based on this, existing technologies have the following shortcomings: First, they lack comprehensive modeling of the quantitative correlation between raw material characteristics, process parameters, and final product performance, making it impossible to predict quality problems early and pinpoint their root causes. Second, the parameter settings for key processes (such as vacuum drying) are fixed, preventing adaptive optimization based on real-time material, structural, and insulation conditions, thus hindering further improvements in product quality and energy efficiency. Finally, information from various stages of quality control is isolated, failing to form an intelligent closed loop of "monitoring-evaluation-control," which limits the overall efficiency of the manufacturing platform and the continuous accumulation of process knowledge. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a transformer processing and manufacturing platform, which solves the aforementioned problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a transformer processing and manufacturing platform, comprising:

[0007] The material performance analysis module obtains material performance coefficients based on the unit iron loss value of silicon steel sheets, resistivity of electromagnetic wire conductors, breakdown voltage of insulating oil, and moisture content of insulating paperboard through a material performance model.

[0008] The structural process analysis module obtains structural coefficients based on the core lamination coefficient, winding DC resistance imbalance rate, and impregnation tank vacuum leakage rate through a structural model.

[0009] The insulation condition analysis module obtains insulation condition coefficients based on insulation resistance and sealing performance leakage rate through an insulation condition model.

[0010] The comprehensive performance analysis module, based on the no-load loss, load loss and partial discharge under the material performance coefficient and structural coefficient, obtains the comprehensive performance fit degree through the comprehensive performance fit degree model.

[0011] The drying vacuum degree optimization module obtains the target vacuum degree for final drying based on comprehensive performance adaptability, insulation state coefficient, and the current final vacuum degree of vacuum drying through a drying vacuum degree optimization model.

[0012] Based on the above technical solutions, the present invention also provides the following optional technical solutions:

[0013] A further technical solution: In the vacuum degree optimization model for drying, the target final vacuum degree for vacuum drying increases with the increase of the insulation state coefficient, and approaches the current final vacuum degree for vacuum drying as the deviation between the comprehensive performance fit and the target comprehensive performance fit decreases.

[0014] Further technical solution: The steps of the comprehensive performance analysis module are as follows:

[0015] Obtain no-load loss, load loss, and partial discharge quantity;

[0016] The no-load loss, load loss, and partial discharge quantity are compared with the corresponding reference values ​​to obtain the no-load loss index, load loss index, and partial discharge quantity index.

[0017] The material performance coefficients and structural coefficients are imported into a preset comprehensive performance model to obtain the comprehensive performance coefficients. In the comprehensive performance model, the comprehensive performance coefficients increase as the material performance coefficients and structural coefficients increase.

[0018] The comprehensive performance coefficient, no-load loss index, load loss index, and partial discharge index are imported into the comprehensive performance fit model to obtain the comprehensive performance fit. In the comprehensive performance fit model, the comprehensive performance fit increases with the increase of the comprehensive performance coefficient and decreases with the increase of the no-load loss index, the load loss index, and the partial discharge index.

[0019] Further technical solution: The steps of the insulation state analysis module are as follows:

[0020] The insulation resistance and sealing performance leakage rate are obtained and the two are subjected to maximum-minimum normalization to obtain the insulation resistance index and sealing performance leakage rate index.

[0021] The insulation resistance index and the sealing performance leakage rate index are imported into the insulation state model to obtain the insulation state coefficient.

[0022] Further technical solution: The steps of the structural process analysis module are as follows:

[0023] The lamination coefficient of the iron core, the DC resistance imbalance rate of the winding, and the vacuum leakage rate of the impregnation tank are obtained and compared with the corresponding reference values ​​to obtain the lamination coefficient index, the resistance imbalance rate index, and the vacuum leakage rate index of the impregnation tank.

[0024] The structural coefficients are obtained by importing the lamination coefficient index, resistance imbalance rate index, and impregnation tank vacuum leakage rate index into the structural model.

[0025] Further technical solution: The performance analysis module includes the following steps:

[0026] The breakdown voltage of insulating oil is subjected to maximum-minimum normalization to obtain the breakdown voltage exponent.

[0027] After performing maximum-minimum normalization on the unit iron loss value of silicon steel sheet, resistivity of electromagnetic wire conductor, and moisture content of insulating paperboard, the complement is taken to obtain the iron loss value index, resistivity index, and moisture content index.

[0028] The iron loss index, resistivity index, breakdown voltage index, and quantity index are imported into the material performance model to obtain the material performance coefficients.

[0029] A further technical solution: In the insulation state model, the insulation state coefficient is positively correlated with the insulation resistance index and negatively correlated with the sealing performance leakage rate index.

[0030] A further technical solution: In the structural model, the structural coefficient is positively correlated with the lamination coefficient index and negatively correlated with the resistance imbalance rate index and the impregnation tank vacuum leakage rate index.

[0031] A further technical solution: In the material performance model, the material performance coefficients are negatively correlated with the iron loss index, resistivity index, and moisture content index, and positively correlated with the breakdown voltage index.

[0032] This invention provides a transformer processing and manufacturing platform, which has the following advantages compared with the prior art:

[0033] 1. This invention realizes the quantitative integration and comprehensive evaluation of multi-dimensional quality indicators throughout the entire transformer manufacturing process. Through models such as material performance coefficient, structural coefficient, insulation state coefficient, and comprehensive performance adaptability, discrete data is transformed into decision-making basis with clear physical meaning, thereby improving the systematicness and foresight of quality control.

[0034] 2. This invention achieves a closed-loop adaptive optimization of process parameters based on quality data feedback. In particular, the drying vacuum degree optimization module can dynamically adjust the process according to the overall performance adaptability and insulation state, realizing a shift from "experience-driven" to "data and model-driven" manufacturing mode, thereby improving product consistency and reliability.

[0035] 3. This invention connects the data chain from raw materials and manufacturing process to finished product testing, and establishes a collaborative analysis mechanism covering the supply chain, production site and laboratory. It not only supports real-time quality early warning and problem traceability, but also provides core platform support for the digital accumulation and continuous improvement of process knowledge. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0038] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0039] Please see Figure 1 A transformer processing and manufacturing platform, provided in one embodiment of the present invention, includes:

[0040] The material performance analysis module obtains material performance coefficients based on the unit iron loss value of silicon steel sheets, resistivity of electromagnetic wire conductors, breakdown voltage of insulating oil, and moisture content of insulating paperboard through a material performance model.

[0041] The structural process analysis module obtains structural coefficients based on the core lamination coefficient (the ratio of the total thickness of the lamination to the thickness of a single lamination multiplied by the number of laminations), the winding DC resistance imbalance rate (the percentage of the maximum deviation to the average value calculated by measuring the DC resistance of each phase (or branch) winding), and the impregnation tank vacuum leakage rate (the pressure rise per unit time during the pressure holding stage).

[0042] The insulation condition analysis module, based on insulation resistance and sealing performance leakage rate (for transformers filled with positive pressure dry air or nitrogen, the pressure drop is monitored for 24 hours using a precision pressure sensor, or measured using a helium mass spectrometer leak detector), obtains the insulation condition coefficient through the insulation condition model;

[0043] The comprehensive performance analysis module, based on the no-load loss, load loss and partial discharge quantity (measured at a specified voltage in the partial discharge test) under the material performance coefficient and structural coefficient, obtains the comprehensive performance fit degree through the comprehensive performance fit degree model.

[0044] The drying vacuum degree optimization module obtains the target vacuum degree for final drying based on comprehensive performance adaptability, insulation state coefficient, and the current final vacuum degree of vacuum drying through a drying vacuum degree optimization model.

[0045] This invention, by introducing material performance analysis, structural process analysis, insulation condition analysis, and comprehensive performance analysis modules, achieves comprehensive modeling of the quantitative correlation between transformer raw material characteristics, process parameters, and final product performance. This multi-dimensional, quantitative evaluation system enables early prediction and root cause localization of quality problems, overcoming the deficiency of comprehensive modeling in existing technologies. Furthermore, this platform, through a drying vacuum optimization module, achieves adaptive optimization of key process parameters. This contrasts with existing technologies that rely on experience or fixed parameter settings, significantly improving the flexibility and accuracy of process parameter settings, thereby effectively improving product quality and energy efficiency.

[0046] Overall, this transformer manufacturing platform constructs an intelligent closed loop of "monitoring-evaluation-control." From raw material performance evaluation to process monitoring during manufacturing, and then to a comprehensive assessment of insulation status and overall performance, ultimately feeding back to the optimization and adjustment of key process parameters, each module collaborates closely, and data is interconnected. This intelligent closed-loop mechanism effectively solves the problem of isolated quality control information in existing technologies, improves the overall efficiency of the manufacturing platform, and promotes the continuous accumulation and optimization of process knowledge.

[0047] Preferably, the performance analysis module includes the following steps:

[0048] Obtain the unit iron loss value of silicon steel sheet, resistivity of electromagnetic wire conductor (at 20°C), breakdown voltage of insulating oil, and moisture content of insulating paperboard;

[0049] The breakdown voltage of insulating oil is subjected to maximum-minimum normalization to obtain the breakdown voltage exponent.

[0050] After performing maximum-minimum normalization on the unit iron loss value of silicon steel sheet, resistivity of electromagnetic wire conductor, and moisture content of insulating paperboard, the complement is taken to obtain the iron loss value index, resistivity index, and moisture content index.

[0051] The iron loss index, resistivity index, breakdown voltage index, and moisture content index are imported into the material performance model to obtain material performance coefficients. In the material performance model, the material performance coefficients are negatively correlated with the iron loss index, resistivity index, and moisture content index, and positively correlated with the breakdown voltage index.

[0052] The material property model is expressed as follows:

[0053]

[0054] in, Indicates the material performance coefficient. Indicates the iron loss index. Represents the resistivity index. Indicates the breakdown voltage index. Indicates a quantity index. Represents the weight coefficient and The The higher the value, the better the material properties.

[0055] Among them, the unit iron loss value of silicon steel sheets directly determines the no-load loss (iron loss) of the transformer. The lower the value, the higher the energy conversion efficiency of the material used to manufacture the iron core, the less energy consumption and heat generated by excitation during transformer operation, and the higher the energy efficiency level. It is the most critical material property affecting the economical operation of the transformer. The unit iron loss value of silicon steel sheets can be obtained by measuring with an Epstein square or a single-sheet measuring instrument. The resistivity of the electromagnetic conductor at standard temperature (20°C) characterizes the inherent ability of the conductive material (copper or aluminum) to impede the passage of current. It is a physical property of the material itself. The resistivity of the electromagnetic conductor directly determines the DC resistance of the winding coil, thus affecting the load loss (copper loss) and operating temperature rise of the transformer. The lower the resistivity of the electromagnetic conductor, the smaller the resistance of the conductor under the same current carrying capacity and cross-sectional area, and the smaller the loss and heat generation during power transmission. The resistivity of the electromagnetic conductor can be obtained by measuring with a DC resistance bridge or a micro-ohmmeter. The breakdown voltage of insulating oil measures the maximum electrical strength of insulating oil (transformer oil) to withstand high voltage without breakdown. During testing, a voltage is applied between two standard electrodes until breakdown occurs in the oil gap. Insulating oil is the main insulating and cooling medium in oil-immersed transformers. The breakdown voltage is the most direct and important comprehensive indicator for judging the cleanliness, dryness (moisture content), and aging degree of the insulating oil. A higher value indicates better insulation performance and a larger insulation safety margin for the transformer. The breakdown voltage of insulating oil can be measured using an insulating oil dielectric strength tester. The moisture content of insulating paperboard refers to the percentage of water by mass in the insulating paperboard. It is a key parameter for assessing the dryness and potential storage condition of solid insulating materials. Moisture is the biggest enemy of insulating materials; excessive moisture content drastically reduces the electrical strength of the insulating paperboard, increases dielectric loss, and accelerates the aging and decomposition of the insulating material during operation, seriously affecting the lifespan and reliability of the transformer. A lower value is better. The moisture content of insulating paperboard can be detected using a Karl Fischer micro-moisture analyzer (coulometric method). Weighting coefficients are also important. It can be determined through expert experience; in addition, weighting coefficients... Optimization can also be achieved through data-driven methods, such as using historical data and machine learning algorithms to analyze the relationship between various material indicators and the final transformer performance, thereby automatically learning and adjusting weights to maximize the correlation between material performance coefficients and actual performance.

[0056] Through the implementation of the aforementioned performance analysis module, the performance evaluation of key transformer raw materials no longer relies on a simple listing of raw data. Instead, standardized data processing and weighted model calculations integrate multi-dimensional material performance indicators into a unified, physically meaningful material performance coefficient. This refined quantitative method effectively solves the problems of inconsistent dimensions of raw data, opposing evaluation directions, and difficulties in direct comprehensive evaluation, ensuring the accuracy and reliability of the material performance coefficient. Therefore, the comprehensive performance suitability evaluation based on this material performance coefficient will be more accurate, providing a more reliable input for the drying vacuum degree optimization module. This allows the final target vacuum drying vacuum degree to more accurately reflect the actual material and process conditions of the transformer, avoiding over-drying or under-drying due to inaccurate material performance evaluation, and significantly improving the quality control level and production efficiency of transformer manufacturing.

[0057] Preferably, the steps of the structural process analysis module are as follows:

[0058] The lamination factor of the core is obtained by measuring the ratio of the total thickness of the lamination to the thickness of a single lamination multiplied by the number of laminations, the DC resistance imbalance rate of the winding is obtained by measuring the DC resistance of each phase (or branch) winding and calculating the percentage of the maximum deviation to the average value, and the vacuum leakage rate of the impregnation tank is obtained by comparing these values ​​with the corresponding reference values.

[0059] The stacking coefficient index, resistance imbalance rate index, and impregnation tank vacuum leakage rate index are imported into the structural model to obtain structural coefficients. In the structural model, the structural coefficients are positively correlated with the stacking coefficient index and negatively correlated with the resistance imbalance rate index and the impregnation tank vacuum leakage rate index.

[0060] The structural model is represented as follows:

[0061]

[0062] in, Represents structural coefficients. Indicates the stacking factor index. This represents the resistance imbalance rate index. Indicators representing the vacuum leakage rate index of the impregnation tank. Indicates the influence of weight coefficients and The Furthermore, the higher the value, the better the manufacturing process.

[0063] The core lamination factor reflects the tightness and uniformity of the core stacking. It can be obtained by measuring the total lamination thickness using a laser thickness gauge or high-precision vernier calipers and comparing it to the thickness of a single lamination multiplied by the number of laminations. The winding DC resistance imbalance rate is an important indicator of winding manufacturing consistency. It can be obtained by measuring the DC resistance of each phase or branch winding using a precision resistance tester and calculating the percentage of the maximum deviation relative to the average value. The impregnation tank vacuum leakage rate characterizes the sealing performance of the impregnation process. It can be obtained by monitoring the pressure rise per unit time during the pressure holding stage using a vacuum gauge and pressure sensor. The structural model maps multiple input indices to a single structural coefficient, which intuitively reflects the current transformer manufacturing quality. Weighting coefficients. (in The weights are used to adjust the importance of each index on the structural coefficients. These weights can be determined based on actual production experience or through data optimization methods. It is worth noting that the resistance imbalance rate index... and the vacuum leakage rate index of the impregnation tank In the model, the complement is used. and The calculation is based on the fact that smaller values ​​for these two indicators generally indicate better process quality, while larger values ​​after rounding indicate better process quality, thus relating to the stacking factor index. Maintain a consistent positive association. The function, acting as an activation function, maps the result of a linear combination to the interval (0, 1), ensuring the structural coefficients... The range of values ​​is reasonable and it has good nonlinear expressive power, making The higher the value, the better the transformer's manufacturing process.

[0064] Through the above technical solution, this application effectively solves the problems of difficulty in uniformly quantifying multi-dimensional indicators and insufficient evaluation accuracy in traditional structural process evaluation. By standardizing the ratios of key process parameters such as core lamination coefficient, winding DC resistance imbalance rate, and impregnation tank vacuum leakage rate, these parameters are transformed into a unified exponential form, eliminating interference from different physical dimensions. Furthermore, a method based on... The structural model of the function can scientifically integrate various indices and use weighting coefficients. Furthermore, by processing the complement of negative indicators, the nonlinear effects of various process parameters on the overall process level are accurately captured, thereby generating an accurate and quantifiable structural coefficient. The structural coefficient This allows for a more accurate reflection of the transformer's structural and technological level, providing a more reliable input for subsequent calculations of overall performance suitability. This enables the transformer manufacturing platform to exercise more precise control and optimization over process quality, ultimately contributing to improved overall transformer performance and operational reliability, and reducing quality risks during production.

[0065] Preferably, the steps of the insulation state analysis module are as follows:

[0066] Obtain the insulation resistance and sealing performance leakage rate (for transformers filled with positive pressure dry air or nitrogen, monitor the pressure drop over 24 hours using a precision pressure sensor, or measure using a helium mass spectrometer leak detector) and perform maximum-minimum normalization on both to obtain the insulation resistance index and sealing performance leakage rate index.

[0067] The insulation resistance index and the sealing performance leakage rate index are imported into the insulation state model to obtain the insulation state coefficient. In the material performance model, the material performance coefficient is negatively correlated with the iron loss index, resistivity index and moisture content index, and positively correlated with the breakdown voltage index.

[0068] The insulation state model is represented as follows:

[0069]

[0070] in, Indicates the insulation condition factor. Indicates the insulation resistance index. The leakage index indicates the sealing performance. Represents the weight coefficient and The Furthermore, the larger the value, the better the overall condition of the insulation system.

[0071] Insulation resistance is a crucial parameter for measuring the ability of insulating materials to impede current flow. Its value directly reflects the degree of moisture absorption and aging of the insulating material. In practical applications, professional insulation resistance testing equipment such as megohmmeters can be used to measure the insulation resistance between transformer windings and ground or between windings under specific voltages. Alternatively, methods such as absorption ratio or polarization index can be used to measure insulation resistance values ​​at different time points to more comprehensively assess the overall condition of the insulation system. The leakage rate of the sealing performance measures the ability of the transformer body or impregnation tank to maintain a seal under certain pressure. It directly relates to the effectiveness of the transformer in preventing the intrusion of external moisture and gases during operation or handling, thus affecting the performance of insulating oil and insulating paperboard. This leakage rate can be calculated as the percentage of pressure drop per unit time by monitoring the pressure drop over 24 hours for a transformer filled with positive pressure dry air or nitrogen using a precision pressure sensor, or by measuring helium leakage using high-precision equipment such as a helium mass spectrometer leak detector to obtain more accurate sealing performance data. The insulation condition model is a mathematical model designed to comprehensively evaluate the overall health of the transformer insulation system. The model takes the normalized insulation resistance index and sealing performance leakage rate index as inputs, and uses a power function form combined with weighting coefficients. , This adjusts the influence of various indicators on the final insulation state coefficient, thereby quantifying it into a single insulation state coefficient between 0 and 1. This coefficient can intuitively reflect the overall health status of the insulation system. The larger the value, the better the insulation system status. It provides a key quantitative basis for subsequent comprehensive performance evaluation and drying vacuum degree optimization. Each weight coefficient can be determined by expert experience or by the analytic hierarchy process.

[0072] Through the above technical solutions, this application can accurately quantify insulation resistance and sealing performance leakage rate, and eliminate the influence of different physical dimensions on the evaluation results through normalization. By introducing an insulation state model, these key indicators are integrated into an insulation state coefficient, achieving a comprehensive and quantitative assessment of the health status of the transformer insulation system. This accurate insulation state assessment provides a reliable input for the drying vacuum degree optimization module, making the determination of the final vacuum degree of the target vacuum drying more scientific and targeted. Ultimately, this helps to avoid drying process deviations caused by inaccurate insulation state assessment, thereby effectively improving the insulation performance and overall operational reliability of the transformer, reducing the risk of transformer failure during operation, and extending its service life.

[0073] Preferably, the steps of the comprehensive performance analysis module are as follows:

[0074] Obtain no-load loss, load loss, and partial discharge quantity;

[0075] The no-load loss, load loss, and partial discharge quantity are compared with the corresponding reference values ​​to obtain the no-load loss index, load loss index, and partial discharge quantity index.

[0076] The material performance coefficients and structural coefficients are imported into a preset comprehensive performance model to obtain the comprehensive performance coefficients. In the comprehensive performance model, the comprehensive performance coefficients increase as the material performance coefficients and structural coefficients increase.

[0077] The comprehensive performance model is expressed as follows:

[0078]

[0079] in, Indicates the overall performance coefficient. Indicates the material performance coefficient. Indicates structural coefficients;

[0080] The comprehensive performance coefficient, no-load loss index, load loss index, and partial discharge index are imported into the comprehensive performance fit model to obtain the comprehensive performance fit. In the comprehensive performance fit model, the comprehensive performance fit increases with the increase of the comprehensive performance coefficient and decreases with the increase of the no-load loss index, the load loss index, and the partial discharge index.

[0081] The comprehensive performance adaptability model is expressed as follows:

[0082]

[0083] in, Indicates overall performance compatibility. Indicates the overall performance coefficient. Indicates the no-load loss index. This represents the load loss index. The partial discharge quantity index is represented by the following. Furthermore, the larger the value, the better the overall performance of the transformer.

[0084] Specifically, no-load loss can be obtained by conducting a no-load test on the transformer, measuring its no-load current and no-load loss power at rated voltage, for example, using a power analyzer connected to the high-voltage or low-voltage side of the transformer. Load loss can be obtained by conducting a short-circuit test on the transformer, measuring its short-circuit voltage and short-circuit loss power at rated current, for example, by adjusting the power supply voltage to allow rated current to flow through the transformer windings and measuring the loss using a power analyzer. Partial discharge can be measured by using partial discharge detection equipment, such as a partial discharge detector, to conduct a partial discharge test on the transformer at a specified voltage, for example, using the pulse current method or ultra-high frequency method. Ratio processing can divide the measured value by a preset industry standard value, design target value, or average value of similar products; for example, the no-load loss index can be defined as the actual no-load loss divided by the standard no-load loss. Material performance coefficients and structural coefficients are imported into a preset comprehensive performance model to obtain comprehensive performance coefficients. This step aims to comprehensively evaluate the intrinsic quality level of the materials and manufacturing processes used in the transformer, providing a basis for subsequent comprehensive performance compatibility calculations. Material performance coefficients Structural coefficients provided by the materials performance analysis module Provided by the structural process analysis module, both are calculated according to the given formula. The calculation, a geometric mean, reflects the combined influence of both material and structural aspects on overall performance. The overall performance fit model incorporates intrinsic mass (…). ) and actual operating performance indicators ( , , By combining these factors and using an exponential function, even small changes in performance metrics can be more sensitively reflected in fit.

[0085] Through the above technical solution, this application provides a structured and quantitative comprehensive performance evaluation method, effectively solving the problems of ambiguity and inaccuracy that may exist in traditional evaluation methods. By organically combining the transformer's intrinsic quality (materials and processes) with its extrinsic operating performance indicators (losses and discharges), and using an exponential function model for calculation, the comprehensive performance fit can more comprehensively and sensitively reflect the actual quality level of the transformer. This refined evaluation result can provide more accurate guidance for subsequent optimization of drying vacuum, thereby ensuring that the transformer can reach its optimal performance state during the manufacturing process, avoiding excessive or insufficient process treatment due to inaccurate evaluation, and improving production efficiency and product quality.

[0086] Preferably, in the drying vacuum degree optimization model, the target final vacuum degree of vacuum drying increases with the increase of the insulation state coefficient, and approaches the current final vacuum degree of vacuum drying as the deviation between the comprehensive performance fit and the target comprehensive performance fit decreases. The drying vacuum degree optimization model is expressed as follows:

[0087]

[0088] in, This indicates the final vacuum level of the target vacuum drying process. This indicates the final vacuum level of the current vacuum drying process. Indicates the insulation condition factor. Indicates overall performance compatibility. This indicates the overall performance suitability of the target.

[0089] in, The target vacuum drying final vacuum degree is the optimized vacuum degree that the transformer is expected to reach at the end of drying, calculated by the model. This value can be directly used as the setting parameter of the drying equipment to guide the operation of the vacuum pump and the control of the drying process; or, this value can also be used as a reference for operators to assist in fine-tuning the drying parameters manually. The current final vacuum level in vacuum drying refers to the final vacuum level actually achieved in the current drying cycle or the final vacuum level used as a benchmark in historical drying cycles. This value can be read in real time from the vacuum sensor of the drying equipment to reflect the current process status; or, this value can also be obtained from historical production data as the starting point for this optimization. The insulation state coefficient is calculated by the insulation state analysis module and is used to quantitatively reflect the overall state of the transformer insulation system. The overall performance fit is calculated by the overall performance analysis module and is used to quantify the overall performance level of the transformer. This fit can be directly output by the overall performance analysis module as input to the drying vacuum degree optimization model. The target overall performance adaptability is a preset, expected overall performance level that the transformer should achieve after drying. This value can be manually set by the user according to the transformer's design requirements, specific customer needs, or industry standards. Alternatively, this value can be automatically determined based on historical best practices or preset quality control standards.

[0090] The solution in this application introduces the aforementioned specific vacuum degree optimization model for drying, enabling the transformer manufacturing platform to quantify, dynamically, and intelligently adjust the final vacuum degree of vacuum drying. This model organically combines the transformer's current final vacuum degree, insulation state coefficient, overall performance adaptability, and a preset target overall performance adaptability. When the transformer's current overall performance adaptability... Below the target overall performance fit At that time, the model will calculate a higher target vacuum drying final vacuum degree. (i.e., a deeper vacuum) to ensure a more thorough drying process, thereby improving transformer performance. Conversely, when the current overall performance is well-suited... Achieve or exceed target overall performance suitability At that time, the model may calculate a relatively loose one. This allows for optimization of the drying cycle or reduction of energy consumption while maintaining performance. Insulation state coefficient In the model, the multiplier, acting as an exponential term, adjusts the model's sensitivity to differences in overall performance adaptability. That is, the better the insulation condition, the more significant the model's response to performance differences, and the greater the adjustment range of the vacuum degree. In this way, the platform can dynamically adjust the drying process parameters based on the actual performance of the transformer's materials, structure, and insulation, avoiding the limitations of traditional methods that rely on fixed vacuum degrees or experience-based adjustments, thus achieving intelligent and precise control of the drying process.

[0091] Through the above technical solution, this application enables the quantification, dynamic, and intelligent adjustment of the final vacuum degree during transformer vacuum drying. The model comprehensively considers the transformer's insulation state and overall performance suitability, allowing the drying process to be optimized according to the transformer's actual performance requirements, avoiding uncertainties caused by blind settings or empirical adjustments. This helps ensure that the transformer reaches or approaches the expected overall performance level after drying, thereby improving the overall quality and reliability of the transformer. Simultaneously, when the transformer performance meets the requirements, the model can also identify and allow for appropriate relaxation of vacuum degree requirements, potentially optimizing the drying cycle and improving production efficiency.

[0092] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0093] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A transformer processing and manufacturing platform, characterized in that, include: The material performance analysis module obtains material performance coefficients based on the unit iron loss value of silicon steel sheets, resistivity of electromagnetic wire conductors, breakdown voltage of insulating oil, and moisture content of insulating paperboard through a material performance model. The structural process analysis module obtains structural coefficients based on the core lamination coefficient, winding DC resistance imbalance rate, and impregnation tank vacuum leakage rate through a structural model. The insulation condition analysis module obtains insulation condition coefficients based on insulation resistance and sealing performance leakage rate through an insulation condition model. The comprehensive performance analysis module, based on the no-load loss, load loss and partial discharge under the material performance coefficient and structural coefficient, obtains the comprehensive performance fit degree through the comprehensive performance fit degree model. The drying vacuum degree optimization module obtains the target vacuum degree for final drying based on comprehensive performance adaptability, insulation state coefficient, and the current final vacuum degree of vacuum drying through a drying vacuum degree optimization model.

2. The transformer processing and manufacturing platform according to claim 1, characterized in that, In the vacuum degree optimization model, the target final vacuum degree of vacuum drying increases with the increase of the insulation state coefficient, and approaches the current final vacuum degree of vacuum drying as the deviation between the target comprehensive performance adaptability and the comprehensive performance adaptability decreases.

3. The transformer processing and manufacturing platform according to claim 2, characterized in that, The steps of the comprehensive performance analysis module are as follows: Obtain no-load loss, load loss, and partial discharge quantity; The no-load loss, load loss, and partial discharge quantity are compared with the corresponding reference values ​​to obtain the no-load loss index, load loss index, and partial discharge quantity index. The material performance coefficients and structural coefficients are imported into a preset comprehensive performance model to obtain the comprehensive performance coefficients. In the comprehensive performance model, the comprehensive performance coefficients increase as the material performance coefficients and structural coefficients increase. The comprehensive performance coefficient, no-load loss index, load loss index, and partial discharge index are imported into the comprehensive performance fit model to obtain the comprehensive performance fit. In the comprehensive performance fit model, the comprehensive performance fit increases with the increase of the comprehensive performance coefficient and decreases with the increase of the no-load loss index, the load loss index, and the partial discharge index.

4. The transformer processing and manufacturing platform according to claim 2, characterized in that, The steps of the insulation state analysis module are as follows: The insulation resistance and sealing performance leakage rate are obtained and the two are subjected to maximum-minimum normalization to obtain the insulation resistance index and sealing performance leakage rate index. The insulation resistance index and the sealing performance leakage rate index are imported into the insulation state model to obtain the insulation state coefficient.

5. The transformer processing and manufacturing platform according to claim 3, characterized in that, The steps of the structural process analysis module are as follows: The lamination coefficient of the iron core, the DC resistance imbalance rate of the winding, and the vacuum leakage rate of the impregnation tank are obtained and compared with the corresponding reference values ​​to obtain the lamination coefficient index, the resistance imbalance rate index, and the vacuum leakage rate index of the impregnation tank. The structural coefficients are obtained by importing the lamination coefficient index, resistance imbalance rate index, and impregnation tank vacuum leakage rate index into the structural model.

6. The transformer processing and manufacturing platform according to claim 3, characterized in that, The performance analysis module includes the following steps: The breakdown voltage of insulating oil is subjected to maximum-minimum normalization to obtain the breakdown voltage exponent. After performing maximum-minimum normalization on the unit iron loss value of silicon steel sheet, resistivity of electromagnetic wire conductor, and moisture content of insulating paperboard, the complement is taken to obtain the iron loss value index, resistivity index, and moisture content index. The iron loss index, resistivity index, breakdown voltage index, and quantity index are imported into the material performance model to obtain the material performance coefficients.

7. The transformer processing and manufacturing platform according to claim 4, characterized in that, In the insulation state model, the insulation state coefficient is positively correlated with the insulation resistance index and negatively correlated with the sealing performance leakage rate index.

8. The transformer processing and manufacturing platform according to claim 5, characterized in that, In the structural model, the structural coefficients are positively correlated with the lamination coefficient index and negatively correlated with the resistance imbalance rate index and the impregnation tank vacuum leakage rate index.

9. The transformer processing and manufacturing platform according to claim 6, characterized in that, In the material performance model, the material performance coefficients are negatively correlated with the iron loss index, resistivity index, and moisture content index, and positively correlated with the breakdown voltage index.

Images