Intelligent management system and method for raw materials in the production process of dry-type power transformers

Abstract

The invention relates to the technical field of transformer manufacturing, and discloses an intelligent management system and method for raw materials in the production process of dry-type power transformers, comprising obtaining initial information of raw materials to be processed, determining the weight of silicon micropowder based on the weight of the raw materials to be processed, inputting the proportion of the raw materials to be processed into a pre-constructed micropowder proportion determination model, obtaining the proportion of silicon micropowder, dividing the stirring period into a start-up phase, a working phase and a termination phase based on a real-time stirring speed, determining a second moment based on the working phase and the termination phase, and preheating a transformer mold based on the second moment; the invention realizes the control of the amount and proportion of the raw materials of the dry-type transformer, and realizes the linkage between the stirring device and the transformer mold through the second moment, so that the temperature of the transformer mold is just at the optimal molding temperature, so that the solidification speed of the raw materials to be solidified after being stirred is more uniform after contacting the surface of the transformer mold.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer manufacturing, and more specifically, to an intelligent management system and method for raw materials in the production process of dry-type power transformers. Background Art

[0002] Resin cast dry-type transformers have been widely used for their excellent environmental protection and fire and explosion-proof properties, especially in scenarios where they need to go deep into the load center, such as buildings, shopping malls, hotels, etc. In addition, different climates and environmental conditions have put forward requirements on the ability of epoxy resin cast dry-type transformers to withstand low temperature and humidity. Especially with the development of social industry and the increasing scope of human activities in recent years, the application scenarios of dry-type transformers have become more and more abundant. In the existing technology, the process of producing dry-type transformers is usually monitored, or the process of producing dry-type transformers is adjusted. There are fewer adjustments and controls to the raw materials for producing dry-type transformers. At the same time, there are fewer adjustments to production parameters during the production process.

[0003] For example, the Chinese patent with publication number CN1 14580973A provides a quality monitoring method and system for the transformer production process. The patent obtains the electrical characteristics of the transformer and the distribution network through test operations, performs feature analysis on the operating condition information, and constructs an electrical characteristic quality monitoring solution with a high degree of individualization; the Chinese patent with publication number CN1 16151778A provides a transformer production and manufacturing process management system based on the Internet of Things. The patent can monitor the production equipment management risks according to the production area of ​​the equipment and the operating status of the production equipment through the production management module.

[0004] Although the above patent realizes the management of the production process of dry-type transformers, the existing technology is unable to control the amount and proportion of raw materials of dry-type transformers. In addition, since the production of dry-type transformers requires mixing equipment and transformer molds, it is impossible to achieve a linkage relationship between the mixing equipment and the transformer mold, resulting in poor quality of the dry-type transformer.

[0005] In view of this, the present invention proposes an intelligent management system and method for raw materials in the production process of dry-type power transformers to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent management system and method for raw materials in the production process of dry-type power transformers.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] Intelligent management methods for raw materials in the production process of dry-type power transformers, including:

[0009] S10: Acquire initial information of the raw materials to be processed, wherein the initial information at least includes the weight of the raw materials to be processed and the proportion of the raw materials to be processed;

[0010] S20: determining the weight of silicon micropowder based on the weight of the raw material to be processed, inputting the ratio of the raw material to be processed into a pre-built micropowder ratio determination model, and obtaining the silicon micropowder ratio, where the silicon micropowder ratio refers to the ratio between silicon micropowders of different particle sizes;

[0011] S30: stirring the raw materials to be processed, and obtaining a stirring period and a real-time stirring speed, and dividing the stirring period into a start-up phase, a working phase, and a termination phase based on the real-time stirring speed;

[0012] S40: determining a first moment based on the startup phase and the working phase, adding silicon micropowder to the raw material to be processed to generate the raw material to be solidified according to the first moment, determining a second moment based on the working phase and the termination phase, and preheating the transformer mold based on the second moment;

[0013] S50: Inject the raw material to be solidified into the transformer mold, obtain the viscosity of N first sub-regions and S second sub-regions of the transformer mold, calculate the viscosity coefficient based on the viscosity of the N sub-regions and the viscosity of the S second sub-regions, and determine whether to perform a solidification operation on the raw material to be solidified according to the viscosity coefficient, where N is an integer greater than 1.

[0014] Furthermore, the method for constructing the micro powder ratio determination model includes:

[0015] A sample data set is obtained, wherein the sample data set includes a historical ratio of raw materials to be processed and a historical ratio of silicon micropowder. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical ratio of raw materials to be processed in the sample training set is used as input data of the regression network, and the historical ratio of silicon micropowder in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time ratio of silicon micropowder. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a micropowder ratio determination model.

[0016] Further, the method for obtaining the stirring period includes:

[0017] The sum of the weight of the raw material to be processed and the weight of the silicon micropowder is calculated, and the sum of the weight of the raw material to be processed and the weight of the silicon micropowder is taken as the total raw material weight. The corresponding stirring period is determined based on the total raw material weight and the mapping relationship.

[0018] Further, the method of dividing the stirring period into a start-up phase, a working phase and a termination phase based on the real-time stirring speed includes:

[0019] The real-time stirring acceleration is calculated according to the real-time stirring speed. When the real-time stirring acceleration is less than a preset first acceleration threshold, a first time tag is obtained, and the stirring period is divided into a startup stage and an intermediate stage according to the first time tag. When the real-time stirring acceleration is less than a preset second acceleration threshold, a second time tag is obtained, and the intermediate stage is divided into a working stage and a termination stage according to the second time tag, and the first acceleration threshold is greater than the second acceleration threshold.

[0020] Further, the method for determining the first moment based on the startup phase and the working phase includes:

[0021] The first intersection moment of the startup phase and the working phase is obtained, and the first intersection moment is taken as the first moment.

[0022] Further, the method for determining the second time based on the working phase and the termination phase includes:

[0023] The second intersection moment of the working phase and the termination phase is obtained, and the second intersection moment is taken as the second moment.

[0024] Furthermore, the method for obtaining the viscosities of the N first sub-regions and the S second sub-regions includes:

[0025] A mold design drawing corresponding to the transformer mold is obtained, and the transformer mold is divided into N first sub-areas and S second sub-areas based on the mold design drawing, and corresponding viscosities are respectively obtained according to viscosity sensors arranged in the first sub-areas and the second sub-areas.

[0026] Further, the method for calculating the viscosity coefficient based on the N first sub-region viscosities and the S second sub-region viscosities includes:

[0027]

[0028] Wherein, VCf is the viscosity coefficient, Vfn is the viscosity of the first sub-region, VSn is the viscosity of the second sub-region, u1 and u2 are both weight factors, and u1<u2.

[0029] Further, the method for judging whether to perform a curing operation on the raw material to be cured according to the viscosity coefficient includes:

[0030] It is determined whether the viscosity coefficient is greater than a preset coefficient threshold value. If so, a curing operation is performed; if not, no curing operation is performed.

[0031] The intelligent management system for raw materials in the production process of dry-type power transformers is used to implement the intelligent management method for raw materials in the production process of dry-type power transformers, including:

[0032] Data acquisition module: used to acquire initial information of the raw materials to be processed, wherein the initial information at least includes the weight and proportion of the raw materials to be processed;

[0033] Ratio determination module: used to determine the weight of silicon micropowder based on the weight of the raw material to be processed, input the ratio of the raw material to be processed into the pre-built micropowder ratio determination model, and obtain the silicon micropowder ratio. The silicon micropowder ratio refers to the ratio between silicon micropowders of different particle sizes;

[0034] Division module: used to stir the raw materials to be processed, obtain the stirring period and real-time stirring speed, and divide the stirring period into the start-up phase, the working phase and the termination phase based on the real-time stirring speed;

[0035] Linkage module: used to determine the first moment based on the startup phase and the working phase, add silicon micropowder to the raw material to be processed to generate the raw material to be solidified according to the first moment, determine the second moment based on the working phase and the termination phase, and preheat the transformer mold based on the second moment;

[0036] Coefficient generation module: used to inject the raw material to be solidified into the transformer mold, obtain the viscosity of N first sub-regions and S second sub-regions of the transformer mold, calculate the viscosity coefficient based on the viscosity of the N sub-regions and the viscosity of the S second sub-regions, and determine whether to perform a solidification operation on the raw material to be solidified according to the viscosity coefficient, where N is an integer greater than 1.

[0037] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the above-mentioned intelligent raw material management method in the production process of dry-type power transformers.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention obtains initial information of raw materials to be processed, determines the weight of silicon micropowder based on the weight of the raw materials to be processed, inputs the proportion of the raw materials to be processed into a pre-constructed micropowder proportion determination model, obtains the proportion of silicon micropowder, stirs the raw materials to be processed, divides the stirring period into a start-up stage, a working stage and a termination stage based on a real-time stirring speed, determines a second moment based on the working stage and the termination stage, preheats a transformer mold based on the second moment, injects the raw materials to be solidified into the transformer mold, and determines whether to perform a solidification operation on the raw materials to be solidified according to the viscosity coefficient. The present invention realizes the control of the amount and proportion of the raw materials of the dry-type transformer, and realizes the linkage between the stirring device and the transformer mold through the second moment, so that the temperature of the transformer mold is just at the optimal molding temperature, so that the solidification speed of the raw materials to be solidified after being stirred is more uniform after contacting the surface of the transformer mold. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of the intelligent management method of raw materials in the production process of dry-type power transformers in the present invention;

[0041] Figure 2 It is a structural schematic diagram of the intelligent management system of raw materials in the production process of dry-type power transformers in the present invention;

[0042] Figure 3 A schematic diagram of a computer-readable storage medium in the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Example 1

[0045] See also Figure 1 As shown, this embodiment discloses a method for intelligent management of raw materials in the production process of dry-type power transformers, including:

[0046] S10: Acquire initial information of the raw materials to be processed, wherein the initial information at least includes the weight of the raw materials to be processed and the proportion of the raw materials to be processed;

[0047] It should be noted that the raw materials to be processed include at least resin, modified toughening agent and methyltetrahydrophthalic anhydride, the weight of the corresponding raw materials to be processed refers to the weight of the resin, modified toughening agent and methyltetrahydrophthalic anhydride mixed together, the ratio of the raw materials to be processed refers to the ratio between the resin, modified toughening agent and methyltetrahydrophthalic anhydride, the weight of the raw materials to be processed can be directly obtained by the weight sensor in the stirring device, and the ratio of the raw materials to be processed is predetermined, and several ratios of the raw materials to be processed can be pre-set to generate the raw materials to be processed by mixing;

[0048] It is understandable that the corresponding proportion of the raw materials to be processed is selected according to the purpose of the dry-type transformer to be produced. For example, when the purpose of producing the dry-type transformer is mainly a relatively high temperature environment, then a relatively high proportion of methyltetrahydrophthalic anhydride is selected as the raw material to be processed.

[0049] S20: determining the weight of silicon micropowder based on the weight of the raw material to be processed, inputting the ratio of the raw material to be processed into a pre-built micropowder ratio determination model, and obtaining the silicon micropowder ratio, where the silicon micropowder ratio refers to the ratio between silicon micropowders of different particle sizes;

[0050] Methods for determining the weight of silicon powder based on the weight of the raw material to be processed include:

[0051] The weight of the raw material to be processed is multiplied by a preset constant to generate the weight of the silicon powder;

[0052] It should be added that silicon powder is a commonly used filler in the production process of dry-type transformers, which has the effect of reducing the resin curing shrinkage and the linear expansion coefficient of the cured product, and improving the thermal conductivity of the cast insulation. The above-mentioned preset constant represents the proportion of silicon powder in the raw material to be processed. According to experiments conducted by personnel in this field, the preset constant is preferably 0.6, and 0.62 can also be selected. This embodiment does not limit this;

[0053] In the above, the silicon micropowder ratio refers to the ratio between silicon micropowders of different particle sizes. For example, the silicon micropowder includes 400-mesh silicon micropowder and 1200-mesh silicon micropowder. Then the silicon micropowder ratio refers to the ratio between 400-mesh silicon micropowder and 1200-mesh silicon micropowder. It can be understood that large-size and small-size silicon micropowders are selected and mixed in a certain ratio to be filled in the raw materials to be processed, which is easier to distribute evenly and reduces sedimentation than simply adding silicon micropowder of one particle size.

[0054] The method for constructing the micro powder ratio determination model includes:

[0055] Obtain a sample data set, wherein the sample data set includes a historical ratio of raw materials to be processed and a historical ratio of silicon micropowder, divide the sample data set into a sample training set and a sample test set, construct a regression network, use the historical ratio of raw materials to be processed in the sample training set as input data of the regression network, use the historical ratio of silicon micropowder in the sample training set as output data of the regression network, train the regression network, obtain an initial regression network for predicting the real-time silicon micropowder ratio, test the initial regression network using the sample test set, output an initial regression network that satisfies a preset error value as a micropowder ratio determination model, and the initial regression network is preferably a neural network model;

[0056] It is not difficult to understand that the above-mentioned historical silicon micropowder ratio is obtained based on expert experience or experiments conducted by personnel in this field, because by mixing large-particle size and small-particle size silicon micropowder in a certain ratio and filling them into the raw materials to be processed, it is easier to distribute evenly than simply adding silicon micropowder of one particle size, which reduces sedimentation. Then, when the sedimentation is reduced, the mechanical and electrical properties of the final dry-type electric transformer material will be improved. Therefore, in the experiment, only the silicon micropowder ratio is changed. By measuring the mechanical and electrical properties of the subsequent dry-type electric transformer materials, the optimal silicon micropowder ratio can be determined, and the optimal silicon micropowder ratio is used as the output data for subsequent model training.

[0057] S30: stirring the raw materials to be processed, and obtaining a stirring period and a real-time stirring speed, and dividing the stirring period into a start-up phase, a working phase, and a termination phase based on the real-time stirring speed;

[0058] In this embodiment, the silicon micropowder is not mixed with the raw material to be processed before stirring because the silicon micropowder is added during the stirring of the raw material to be processed, so that the silicon micropowder can be quickly and fully integrated into the raw material to be processed, which can improve the mixing effect of the raw material to be processed and the silicon micropowder;

[0059] Methods for obtaining the mixing period include:

[0060] Calculate the sum of the weight of the raw material to be processed and the weight of the silicon micropowder, take the sum of the weight of the raw material to be processed and the weight of the silicon micropowder as the total raw material weight, and determine the corresponding stirring period based on the total raw material weight and the mapping relationship;

[0061] It can be understood that the stirring period refers to the time period from the beginning of stirring the raw material to be processed, the addition of silicon powder in the middle, to the subsequent completion of the stirring. Similarly, the stirring period is positively correlated with the total raw material weight, which can be obtained by experiments conducted by those skilled in the art, and a mapping relationship between the stirring period and the total raw material weight can be established subsequently. For example, a functional relationship between the stirring period and the total raw material weight can be established;

[0062] In this embodiment, the real-time stirring speed refers to the rotation speed of the stirring shaft. The real-time stirring speed can be obtained in real time by a photoelectric sensor. When a constant current is passed through the motor of the stirring device, the stirring shaft connected to the motor rotates at a relatively constant speed. However, the rotation speed of the stirring shaft will be affected by the raw materials to be processed. It can be understood that when the motor is just started, the real-time stirring speed will increase rapidly until it is in a stable working state. The real-time stirring speed is in a stable fluctuating state. When silicon micropowder is added later, the viscosity of the total raw materials inside the stirring device will become larger and larger, resulting in a decrease in the real-time stirring speed.

[0063] The method of dividing the stirring period into the starting stage, the working stage and the termination stage based on the real-time stirring speed includes:

[0064] Calculating the real-time stirring acceleration according to the real-time stirring speed, obtaining a first time tag when the real-time stirring acceleration is less than a preset first acceleration threshold, dividing the stirring period into a start-up stage and an intermediate stage according to the first time tag, obtaining a second time tag when the real-time stirring acceleration is less than a preset second acceleration threshold, dividing the intermediate stage into a working stage and a termination stage according to the second time tag, and the first acceleration threshold>the second acceleration threshold;

[0065] It should be noted that when the motor is just started, the real-time stirring speed will increase rapidly, and the real-time stirring acceleration will also be in a large state. When the real-time stirring acceleration is less than the preset first acceleration threshold, it indicates that the real-time stirring speed is already in a stable fluctuation state. It can be understood that when the real-time stirring speed decreases, the real-time stirring acceleration is a negative value. Therefore, the second acceleration threshold in this embodiment is also a negative value. When the real-time stirring acceleration is less than the preset second acceleration threshold, it indicates that the real-time stirring speed decreases rapidly. At this time, the motor should be stopped and the final stirring should be completed by the inertia of the stirring shaft. The first time label and the second time label mentioned above can both be obtained through the timer in the system.

[0066] S40: determining a first moment based on the startup phase and the working phase, adding silicon micropowder to the raw material to be processed to generate the raw material to be solidified according to the first moment, determining a second moment based on the working phase and the termination phase, and preheating the transformer mold based on the second moment;

[0067] Methods for determining the first moment based on the startup phase and the working phase include:

[0068] Obtain the first intersection moment of the startup phase and the working phase, and take the first intersection moment as the first moment;

[0069] The method for determining the second time based on the working phase and the termination phase includes:

[0070] Obtain the second intersection moment of the working phase and the termination phase, and use the second intersection moment as the second moment;

[0071] It should be added that, in this embodiment, the first intersection moment refers to the first time label mentioned above, and the second intersection moment refers to the second time label mentioned above, but this is just an example, and the first intersection moment + T can also be used as the first moment of this application, and this embodiment is not limited to this;

[0072] In this embodiment, when the motor switches from the starting stage to the working stage, it means that the raw material to be processed has been stirred for a certain time. Therefore, directly adding silicon micropowder to the raw material to be processed can make the silicon micropowder quickly and fully integrated into the raw material to be processed, further improving the mixing effect of the raw material to be processed and the silicon micropowder. When the motor switches from the working stage to the termination stage, it indicates that the stirring work is about to be completed. Then, after the stirring of the raw material to be processed and the silicon micropowder is completed, they need to be formed through a transformer mold. Therefore, this embodiment can preheat the transformer mold in advance when the stirring work is about to be completed, so that the temperature of the transformer mold is just at the optimal molding temperature, so that the raw material to be solidified after being stirred is more uniform after contacting the surface of the transformer mold, reducing problems caused by shrinkage, and ensuring the quality and surface smoothness of the final dry transformer.

[0073] S50: injecting the raw material to be solidified into the transformer mold, obtaining the viscosity of N first sub-regions and the viscosity of S second sub-regions of the transformer mold, calculating the viscosity coefficient based on the viscosity of the N sub-regions and the viscosity of the S second sub-regions, and judging whether to perform a solidification operation on the raw material to be solidified according to the viscosity coefficient, where N is an integer greater than 1;

[0074] The method for obtaining the N first sub-region viscosities and the S second sub-region viscosities includes:

[0075] Obtain a mold design drawing corresponding to the transformer mold, divide the transformer mold into N first sub-areas and S second sub-areas based on the mold design drawing, and obtain corresponding viscosities according to viscosity sensors set in the first sub-areas and the second sub-areas respectively;

[0076] It should be noted that the mold design drawing mentioned above may be a mold CAD drawing. A dry-type transformer generally includes an insulating part, an iron core part, a shell part, and a connecting part. Then, the corresponding mold design drawing will also have an insulating part sub-graph, an iron core part sub-graph, a shell part sub-graph, and a connecting part sub-graph. In this embodiment, the insulating part sub-graph, the iron core part sub-graph, the shell part sub-graph, and the connecting part sub-graph are pre-divided into a first sub-region and a second sub-region based on expert experience. The basis for the division is determined according to the importance of each part in the forming process of the dry-type transformer.

[0077] Exemplarily, after the raw material to be solidified is injected into the transformer mold, the raw material to be solidified is formed in the transformer mold. In the forming process, it is necessary to focus on the forming of the insulating part and the connecting part. Therefore, it is necessary to divide the insulating part sub-graph and the connecting part sub-graph into the first sub-region, and divide the core part sub-graph and the shell part sub-graph into the second sub-region. In this embodiment, the importance of the first sub-region representation is greater than the importance of the second sub-region representation.

[0078] The method for calculating the viscosity coefficient based on the N first sub-region viscosities and the S second sub-region viscosities includes:

[0079]

[0080] Where VCf is the viscosity coefficient, Vfn is the viscosity of the first sub-region, Vsn is the viscosity of the second sub-region, u1 and u2 are both weight factors, and u1<u2;

[0081] Methods for judging whether to perform curing operation on the raw material to be cured according to the viscosity coefficient include:

[0082] Determine whether the viscosity coefficient is greater than a preset coefficient threshold, if so, perform a curing operation, if not, do not perform a curing operation;

[0083] It should be noted that when the raw material to be solidified is injected into the transformer mold, the fluidity of the raw material to be solidified is relatively large, and the corresponding viscosity is relatively small. After being molded in the transformer mold for a period of time, the fluidity of the raw material to be solidified disappears, and the corresponding viscosity is relatively large. Therefore, when the viscosity of the raw material to be solidified is relatively large, it indicates that the molding effect of the raw material to be solidified is better. However, during the molding process, it is necessary to focus on the molding of a certain part, for example, it is necessary to focus on the molding of the insulating part and the connecting part.

[0084] Therefore, in this embodiment, the weight factor u1 corresponding to the first sub-region is set to be smaller than the weight factor u2 corresponding to the second sub-region. It can be concluded from the above content that in this embodiment, whether to perform a curing operation is determined based on the size of the viscosity coefficient. In order to make the viscosity coefficient meet the requirements, u1 < u2, which means that the value of Vfn itself is greater than the value of Vsn itself. Therefore, when the viscosity coefficient meets the requirements, Vfn is at a larger value, indicating that the molding effect of the raw material to be cured inside the first sub-region corresponding to Vfn is better, and therefore subsequent curing operations can be performed.

[0085] In this embodiment, initial information of the raw material to be processed is obtained, the weight of silicon micropowder is determined based on the weight of the raw material to be processed, the proportion of the raw material to be processed is input into a pre-constructed micropowder proportion determination model, the proportion of silicon micropowder is obtained, the raw material to be processed is stirred, and the stirring period and the real-time stirring speed are obtained. The stirring period is divided into a startup stage, a working stage and a termination stage based on the real-time stirring speed, the first moment is determined based on the startup stage and the working stage, the silicon micropowder is added to the raw material to be processed according to the first moment to generate the raw material to be solidified, the second moment is determined based on the working stage and the termination stage, the transformer mold is preheated based on the second moment, the raw material to be solidified is injected into the transformer mold, and whether to perform a solidification operation on the raw material to be solidified is determined according to the viscosity coefficient. In this embodiment, the amount and proportion of the raw materials of the dry-type transformer are controlled, and the linkage between the stirring device and the transformer mold is achieved through the second moment, so that the temperature of the transformer mold is just at the optimal molding temperature, so that the solidification speed of the raw material to be solidified after being stirred is more uniform after contacting the surface of the transformer mold.

[0086] Example 2

[0087] like Figure 2 As shown, this embodiment, based on the first embodiment, provides an intelligent management system for raw materials in the production process of dry-type power transformers, including:

[0088] Data acquisition module: used to acquire initial information of the raw materials to be processed, wherein the initial information at least includes the weight and proportion of the raw materials to be processed;

[0089] It should be noted that the raw materials to be processed include at least resin, modified toughening agent and methyltetrahydrophthalic anhydride, the weight of the corresponding raw materials to be processed refers to the weight of the resin, modified toughening agent and methyltetrahydrophthalic anhydride mixed together, the ratio of the raw materials to be processed refers to the ratio between the resin, modified toughening agent and methyltetrahydrophthalic anhydride, the weight of the raw materials to be processed can be directly obtained by the weight sensor in the stirring device, and the ratio of the raw materials to be processed is predetermined, and several ratios of the raw materials to be processed can be pre-set to generate the raw materials to be processed by mixing;

[0090] It is understandable that the corresponding proportion of the raw materials to be processed is selected according to the purpose of the dry-type transformer to be produced. For example, when the purpose of producing the dry-type transformer is mainly a relatively high temperature environment, then a relatively high proportion of methyltetrahydrophthalic anhydride is selected as the raw material to be processed.

[0091] Ratio determination module: used to determine the weight of silicon micropowder based on the weight of the raw material to be processed, input the ratio of the raw material to be processed into the pre-built micropowder ratio determination model, and obtain the silicon micropowder ratio. The silicon micropowder ratio refers to the ratio between silicon micropowders of different particle sizes;

[0092] Methods for determining the weight of silicon powder based on the weight of the raw material to be processed include:

[0093] The weight of the raw material to be processed is multiplied by a preset constant to generate the weight of the silicon powder;

[0094] It should be added that silicon powder is a commonly used filler in the production process of dry-type transformers, which has the effect of reducing the resin curing shrinkage and the linear expansion coefficient of the cured product, and improving the thermal conductivity of the cast insulation. The above-mentioned preset constant represents the proportion of silicon powder in the raw material to be processed. According to experiments conducted by personnel in this field, the preset constant is preferably 0.6, and 0.62 can also be selected. This embodiment does not limit this;

[0095] In the above, the silicon micropowder ratio refers to the ratio between silicon micropowders of different particle sizes. For example, the silicon micropowder includes 400-mesh silicon micropowder and 1200-mesh silicon micropowder. Then the silicon micropowder ratio refers to the ratio between 400-mesh silicon micropowder and 1200-mesh silicon micropowder. It can be understood that large-size and small-size silicon micropowders are selected and mixed in a certain ratio to be filled in the raw materials to be processed, which is easier to distribute evenly and reduces sedimentation than simply adding silicon micropowder of one particle size.

[0096] Division module: used to stir the raw materials to be processed, obtain the stirring period and real-time stirring speed, and divide the stirring period into the start-up phase, the working phase and the termination phase based on the real-time stirring speed;

[0097] In this embodiment, the silicon micropowder is not mixed with the raw material to be processed before stirring because the silicon micropowder is added during the stirring of the raw material to be processed, so that the silicon micropowder can be quickly and fully integrated into the raw material to be processed, which can improve the mixing effect of the raw material to be processed and the silicon micropowder;

[0098] Methods for obtaining the mixing period include:

[0099] Calculate the sum of the weight of the raw material to be processed and the weight of the silicon micropowder, take the sum of the weight of the raw material to be processed and the weight of the silicon micropowder as the total raw material weight, and determine the corresponding stirring period based on the total raw material weight and the mapping relationship;

[0100] It can be understood that the stirring period refers to the time period from the beginning of stirring the raw material to be processed, the addition of silicon powder in the middle, to the subsequent completion of the stirring. Similarly, the stirring period is positively correlated with the total raw material weight, which can be obtained by experiments conducted by those skilled in the art, and a mapping relationship between the stirring period and the total raw material weight can be established subsequently. For example, a functional relationship between the stirring period and the total raw material weight can be established;

[0101] In this embodiment, the real-time stirring speed refers to the rotation speed of the stirring shaft. The real-time stirring speed can be obtained in real time by a photoelectric sensor. When a constant current is passed through the motor of the stirring device, the stirring shaft connected to the motor rotates at a relatively constant speed. However, the rotation speed of the stirring shaft will be affected by the raw materials to be processed. It can be understood that when the motor is just started, the real-time stirring speed will increase rapidly until it is in a stable working state. The real-time stirring speed is in a stable fluctuating state. When silicon micropowder is added later, the viscosity of the total raw materials inside the stirring device will become larger and larger, resulting in a decrease in the real-time stirring speed.

[0102] The method of dividing the stirring period into the starting stage, the working stage and the termination stage based on the real-time stirring speed includes:

[0103] The real-time stirring acceleration is calculated according to the real-time stirring speed. When the real-time stirring acceleration is less than a preset first acceleration threshold, a first time tag is obtained, and the stirring period is divided into a startup stage and an intermediate stage according to the first time tag. When the real-time stirring acceleration is less than a preset second acceleration threshold, a second time tag is obtained, and the intermediate stage is divided into a working stage and a termination stage according to the second time tag, and the first acceleration threshold is greater than the second acceleration threshold.

[0104] Linkage module: used to determine the first moment based on the startup phase and the working phase, add silicon micropowder to the raw material to be processed to generate the raw material to be solidified according to the first moment, determine the second moment based on the working phase and the termination phase, and preheat the transformer mold based on the second moment;

[0105] Methods for determining the first moment based on the startup phase and the working phase include:

[0106] Obtain the first intersection moment of the startup phase and the working phase, and take the first intersection moment as the first moment;

[0107] The method for determining the second time based on the working phase and the termination phase includes:

[0108] Obtain the second intersection moment of the working phase and the termination phase, and use the second intersection moment as the second moment;

[0109] It should be added that, in this embodiment, the first intersection moment refers to the first time label mentioned above, and the second intersection moment refers to the second time label mentioned above, but this is just an example, and the first intersection moment + T can also be used as the first moment of this application, and this embodiment is not limited to this;

[0110] In this embodiment, when the motor switches from the starting stage to the working stage, it means that the raw material to be processed has been stirred for a certain time. Therefore, directly adding silicon micropowder to the raw material to be processed can make the silicon micropowder quickly and fully integrated into the raw material to be processed, further improving the mixing effect of the raw material to be processed and the silicon micropowder. When the motor switches from the working stage to the termination stage, it indicates that the stirring work is about to be completed. Then, after the stirring of the raw material to be processed and the silicon micropowder is completed, they need to be formed through a transformer mold. Therefore, this embodiment can preheat the transformer mold in advance when the stirring work is about to be completed, so that the temperature of the transformer mold is just at the optimal molding temperature, so that the raw material to be solidified after being stirred is more uniform after contacting the surface of the transformer mold, reducing problems caused by shrinkage, and ensuring the quality and surface smoothness of the final dry transformer.

[0111] A coefficient generation module: used to inject the raw material to be solidified into the transformer mold, obtain the viscosity of N first sub-regions and S second sub-regions of the transformer mold, calculate the viscosity coefficient based on the viscosity of the N sub-regions and the viscosity of the S second sub-regions, and determine whether to perform a solidification operation on the raw material to be solidified according to the viscosity coefficient, where N is an integer greater than 1;

[0112] The method for obtaining the N first sub-region viscosities and the S second sub-region viscosities includes:

[0113] Obtain a mold design drawing corresponding to the transformer mold, divide the transformer mold into N first sub-areas and S second sub-areas based on the mold design drawing, and obtain corresponding viscosities according to viscosity sensors set in the first sub-areas and the second sub-areas respectively;

[0114] It should be noted that the mold design drawing mentioned above may be a mold CAD drawing. A dry-type transformer generally includes an insulating part, an iron core part, a shell part, and a connecting part. Then, the corresponding mold design drawing will also have an insulating part sub-graph, an iron core part sub-graph, a shell part sub-graph, and a connecting part sub-graph. In this embodiment, the insulating part sub-graph, the iron core part sub-graph, the shell part sub-graph, and the connecting part sub-graph are pre-divided into a first sub-region and a second sub-region based on expert experience. The basis for the division is determined according to the importance of each part in the forming process of the dry-type transformer.

[0115] Exemplarily, after the raw material to be solidified is injected into the transformer mold, the raw material to be solidified is formed in the transformer mold. In the forming process, it is necessary to focus on the forming of the insulating part and the connecting part. Therefore, it is necessary to divide the insulating part sub-graph and the connecting part sub-graph into the first sub-region, and divide the core part sub-graph and the shell part sub-graph into the second sub-region. In this embodiment, the importance of the first sub-region representation is greater than the importance of the second sub-region representation.

[0116] The method for calculating the viscosity coefficient based on the N first sub-region viscosities and the S second sub-region viscosities includes:

[0117]

[0118] Where VCf is the viscosity coefficient, Vfn is the viscosity of the first sub-region, Vsn is the viscosity of the second sub-region, u1 and u2 are both weight factors, and u1<u2;

[0119] Methods for judging whether to perform curing operation on the raw material to be cured according to the viscosity coefficient include:

[0120] Determine whether the viscosity coefficient is greater than a preset coefficient threshold, if so, perform a curing operation, if not, do not perform a curing operation;

[0121] It should be noted that when the raw material to be solidified is injected into the transformer mold, the fluidity of the raw material to be solidified is relatively large, and the corresponding viscosity is relatively small. After being molded in the transformer mold for a period of time, the fluidity of the raw material to be solidified disappears, and the corresponding viscosity is relatively large. Therefore, when the viscosity of the raw material to be solidified is relatively large, it is characterized that the molding effect of the raw material to be solidified is better. However, during the molding process, it is necessary to focus on the molding condition of a certain part, for example, it is necessary to focus on the molding condition of the insulating part and the connecting part.

[0122] Example 3

[0123] The present embodiment discloses an electronic device, including a power supply, an interface, a keyboard, a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the intelligent raw material management method in the production process of dry-type power transformers provided by the above methods is implemented. The interface includes a network interface and a data interface. The network interface includes a wired or wireless interface, and the data interface includes an input or output interface.

[0124] Since the electronic device introduced in this embodiment is an electronic device used to implement the method for intelligent management of raw materials in the production process of dry-type power transformers in the embodiment of this application, based on the method for intelligent management of raw materials in the production process of dry-type power transformers introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the method for intelligent management of raw materials in the production process of dry-type power transformers in the embodiment of this application, it belongs to the scope of protection of this application.

[0125] Example 4

[0126] like Figure 3 As shown, the present embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the above-mentioned method for intelligent management of raw materials in the production process of dry-type power transformers is implemented.

[0127] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0128] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0129] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0134] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0135] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The intelligent management method of raw materials in the production process of dry-type power transformers is characterized by: include: S10: Obtaining initial information of the raw materials to be processed, wherein the initial information at least includes the weight and proportion of the raw materials to be processed; S20: Determine the weight of silicon micropowder based on the weight of the raw material to be processed, input the proportion of the raw material to be processed into a pre-constructed micropowder proportion determination model, and obtain the silicon micropowder proportion, where the silicon micropowder proportion refers to the proportion between silicon micropowders of different particle sizes; S30: stirring the raw material to be processed, and obtaining the stirring period and the real-time stirring speed, and dividing the stirring period into a start-up phase, a working phase and a termination phase based on the real-time stirring speed; S40: Determine a first moment based on the startup phase and the working phase, add silicon powder to the raw material to be processed to generate the raw material to be solidified according to the first moment, determine a second moment based on the working phase and the termination phase, and preheat the transformer mold based on the second moment; S50: injecting the raw material to be solidified into the transformer mold, obtaining the viscosity of N first sub-regions and the viscosity of S second sub-regions of the transformer mold, calculating the viscosity coefficient based on the viscosity of the N sub-regions and the viscosity of the S second sub-regions, and judging whether to perform a solidification operation on the raw material to be solidified according to the viscosity coefficient, where N is an integer greater than 1; The method for constructing the micropowder ratio determination model comprises: Acquire a sample data set, wherein the sample data set includes a historical ratio of raw materials to be processed and a historical ratio of silicon micropowder, divide the sample data set into a sample training set and a sample test set, construct a regression network, use the historical ratio of raw materials to be processed in the sample training set as input data of the regression network, use the historical ratio of silicon micropowder in the sample training set as output data of the regression network, train the regression network, obtain an initial regression network for predicting the real-time silicon micropowder ratio, test the initial regression network using the sample test set, and output the initial regression network that satisfies a preset error value as a micropowder ratio determination model; The method for obtaining the N first sub-region viscosities and the S second sub-region viscosities comprises: Obtain a mold design drawing corresponding to the transformer mold, divide the transformer mold into N first sub-areas and S second sub-areas based on the mold design drawing, and obtain corresponding viscosities according to viscosity sensors set in the first sub-areas and the second sub-areas respectively; The method for calculating the viscosity coefficient based on the N first sub-region viscosities and the S second sub-region viscosities comprises: Where VCf is the viscosity coefficient, Vfn is the viscosity of the first sub-region, Vsn is the viscosity of the second sub-region, u1 and u2 are both weight factors, and u1<u2; The method for judging whether to perform a curing operation on the raw material to be cured according to the viscosity coefficient includes: It is determined whether the viscosity coefficient is greater than a preset coefficient threshold value. If so, a curing operation is performed; if not, no curing operation is performed.

2. The method for intelligent management of raw materials in the production process of dry-type power transformers according to claim 1 is characterized in that: The method for obtaining the stirring period comprises: The sum of the weight of the raw material to be processed and the weight of the silicon micropowder is calculated, and the sum of the weight of the raw material to be processed and the weight of the silicon micropowder is taken as the total raw material weight. The corresponding stirring period is determined based on the total raw material weight and the mapping relationship.

3. The method for intelligent management of raw materials in the production process of dry-type power transformers according to claim 2 is characterized in that: The method for dividing the stirring period into a start-up phase, a working phase and a termination phase based on the real-time stirring speed comprises: The real-time stirring acceleration is calculated according to the real-time stirring speed. When the real-time stirring acceleration is less than a preset first acceleration threshold, a first time tag is obtained, and the stirring period is divided into a startup stage and an intermediate stage according to the first time tag. When the real-time stirring acceleration is less than a preset second acceleration threshold, a second time tag is obtained, and the intermediate stage is divided into a working stage and a termination stage according to the second time tag, and the first acceleration threshold is greater than the second acceleration threshold.

4. The method for intelligent management of raw materials in the production process of dry-type power transformers according to claim 3 is characterized in that: The method for determining the first moment based on the startup phase and the working phase includes: The first intersection moment of the startup phase and the working phase is obtained, and the first intersection moment is taken as the first moment.

5. The method for intelligent management of raw materials in the production process of dry-type power transformers according to claim 3 is characterized in that: The method for determining the second time based on the working phase and the termination phase includes: The second intersection moment of the working phase and the termination phase is obtained, and the second intersection moment is taken as the second moment.

6. An intelligent management system for raw materials in the production process of dry-type power transformers, which is used to implement the intelligent management method for raw materials in the production process of dry-type power transformers according to any one of claims 1 to 5, characterized in that: include: Data acquisition module: used to obtain initial information of the raw materials to be processed, the initial information at least including the weight and proportion of the raw materials to be processed; Ratio determination module: used to determine the weight of silicon micropowder based on the weight of the raw material to be processed, input the ratio of the raw material to be processed into the pre-built micropowder ratio determination model, and obtain the silicon micropowder ratio, which refers to the ratio between silicon micropowders of different particle sizes; Division module: used to stir the raw materials to be processed, obtain the stirring period and real-time stirring speed, and divide the stirring period into a start-up phase, a working phase and a termination phase based on the real-time stirring speed; Linkage module: used to determine a first moment based on a startup phase and a working phase, add silicon micropowder to the raw material to be processed to generate a raw material to be solidified according to the first moment, determine a second moment based on the working phase and the termination phase, and preheat the transformer mold based on the second moment; Coefficient generation module: used to inject the raw material to be solidified into the transformer mold, obtain the viscosity of N first sub-regions and S second sub-regions of the transformer mold, calculate the viscosity coefficient based on the viscosity of the N sub-regions and the viscosity of the S second sub-regions, and determine whether to perform a solidification operation on the raw material to be solidified according to the viscosity coefficient, where N is an integer greater than 1.

Images