An order-based power transformer supply early warning method and system

Abstract

The present invention relates to the technical field of power transformer supply warning. An order-based power transformer supply warning method establishes a mapping table of power transformer specifications and models and raw material weights; based on the mapping table, the historical prices of silicon steel sheets and copper in a first preset time period are determined, and the prices of the silicon steel sheets and copper in a second time period are predicted, wherein the silicon steel sheets and copper are materials for making the power transformer, and the second time period represents the time period from when the order is signed to when the order is delivered; based on the predicted prices of the silicon steel sheets and copper in the second time period and the length of the delivery period, the delivery time is determined, wherein the delivery period represents the time from delivery; based on the delivery time, the warning conditions are determined; based on the warning conditions, warning information is proposed; based on the warning information, a response strategy is determined. It has good warning properties and improves the resilience and stability of the supply chain.

Description

Technical Field

[0001] The present invention relates to the technical field of power transformer supply early warning, and in particular to an order-based power transformer supply early warning method and system. Background Art

[0002] The continued fluctuations in global bulk prices have led to sharp fluctuations in the prices of raw materials such as silicon steel sheets and copper. This has placed higher demands on the stable operation of the power transformer supply chain, which uses silicon steel sheets and copper as the main raw materials. It is necessary to judge the impact of the prices of raw materials such as silicon steel sheets and copper on power transformers. For example, when placing an order for a power transformer, it is necessary to judge the production volume, production time, and the prices of silicon steel sheets and copper during the production period. This is to avoid profit margins when the order is placed, but in the process of completing the order, the impact of rising raw material prices may result in negative profits when the order is finally delivered.

[0003] Based on the above reasons, there is an urgent need for a method to analyze the disturbance of the power transformer supply chain based on the price fluctuations of silicon steel sheets and copper required for the ordered power transformers. Summary of the Invention

[0004] The purpose of the present invention is to provide an order-based power transformer supply early warning method and system, which can solve the impact of price fluctuations of silicon steel sheets and copper required for ordered power transformers on the power transformer supply chain.

[0005] A first aspect of the present invention provides an order-based power transformer supply early warning method, the method comprising:

[0006] Establish a mapping table between power transformer specifications and raw material weights;

[0007] Based on the mapping table, determining historical prices of silicon steel sheets and copper within a first preset time period, and predicting prices of the silicon steel sheets and copper within a second time period, wherein the silicon steel sheets and the copper are materials for manufacturing the power transformer, and the second time period represents a time period from when the order is signed to when the order is delivered;

[0008] Determining the duration of the upcoming delivery based on the predicted prices of the silicon steel sheet and the copper within the second time period and the duration of the delivery period, wherein the delivery period represents the time until delivery;

[0009] Determining the warning condition according to the duration of the impending delivery;

[0010] Propose early warning information according to the warning conditions;

[0011] Determine response strategies based on early warning information.

[0012] In one practicable manner, the step of establishing a mapping table of power transformer specifications and models and raw material weights includes:

[0013] Obtaining information on power transformers of different specifications and models, and determining the proportions of the silicon steel sheets and the copper in the raw materials of the power transformers of different specifications and models;

[0014] Based on the specific gravity of the silicon steel sheet and the copper, a mapping table between the raw materials and the specifications and models of the power transformer is established.

[0015] In one practicable manner, the step of predicting the prices of the silicon steel sheet and the copper in a second time period based on the historical prices of the silicon steel sheet and the copper in a first preset time period includes:

[0016] Obtaining historical prices of the silicon steel sheet and the copper within a first preset time period;

[0017] Decomposing the price history series of the silicon steel sheet and the copper into multiple series respectively according to the empirical mode decomposition method;

[0018] According to the hierarchical clustering method, the plurality of said sequences are reconstructed into four sequences of high-frequency, medium-frequency and low-frequency data, and trend items;

[0019] According to the characteristic distribution of the four sequences, ARMA model, neural network model and nonlinear regression are used for prediction respectively;

[0020] The four predicted sequences are used to determine prediction results, wherein the prediction results represent prices of the silicon steel sheet and the copper in the second time period.

[0021] In one practicable manner, the step of determining the duration of the upcoming delivery based on the predicted prices of the silicon steel sheet and the copper and the duration of the delivery period within the second time period includes:

[0022] Obtain the actual delivery date and the time required for power transformer production;

[0023] Determine the start time of power transformer production based on the actual delivery date and the time required for power transformer production;

[0024] The prices of the silicon steel sheet and the copper at the start time of production of the power transformer are determined according to the prices in the second time period.

[0025] In one practicable manner, the step of determining the warning condition based on the upcoming delivery time includes:

[0026] According to the upcoming delivery time, the prices of the silicon steel sheet and the copper at the start time of the power transformer production are determined, wherein:

[0027] The formula for calculating the cost of raw materials at the time of order signing is:

[0028] p con (Cu)=N Cu ×p Cu (t 签订 )

[0029] p con (Si)=N Si ×p Si (t 签订 )

[0030] p con (original) = p con (Cu)+p con (Si)

[0031] Among them, the p con (Cu), p con (Si) represents the cost of raw materials copper and silicon steel sheet at the time of contract signing, N Cu 、N Si Respectively represent the weight of copper and silicon steel sheet, p Cu (t 签订 ), p Si (t 签订 ) represent the prices of raw materials copper and silicon steel sheets at the time of contract signing, P con (Original) indicates the total price of raw materials copper and silicon steel sheets at the time of contract signing;

[0032] Establish the formula for calculating raw material costs at the time of contract execution:

[0033] p′ con (Cu)=N Cu ×p Cu (t 执行 )

[0034] p′ con (Si)=N Si ×p Si (t 执行 )

[0035] p′ con (original) = p′ con (Cu)+p′ con (Si)

[0036] Among them, p' con (Cu), p' con(Si) represents the cost of raw materials copper and silicon steel sheets at the time of contract execution, p' con (Original) indicates the total price of raw materials at the time of contract execution;

[0037] The early warning identification conditions are:

[0038]

[0039] Among them, p con Indicates the contract price of power transformers.

[0040] In one practicable manner, the step of providing early warning information according to the warning condition includes:

[0041] According to the warning condition, the warning level threshold is determined, wherein the calculation formula is:

[0042]

[0043]

[0044]

[0045] Among them, error represents the model error, profit-rate is the profit rate, min() and max() respectively represent the comparison of minimum and maximum values, and default-cost represents the default cost.

[0046] In one practicable manner, the step of determining a response strategy based on the early warning information includes:

[0047] If the response strategy is formula (1), it means that the price of raw materials is greater than zero and less than the first threshold of the raw material price increase set when the contract is signed, and the first time required to replenish the raw materials is determined based on the existing raw materials and the required raw materials;

[0048] If the response strategy is formula (2), it means that the raw material price is greater than the first threshold of the raw material price increase set when the contract is signed, the raw materials are available and needed, and the second time for preparing the raw materials is determined;

[0049] If the response strategy is formula (3), it means that the raw material price is greater than the second raw material price increase threshold set when the contract is signed, and the contract is canceled; wherein,

[0050] The second threshold is greater than the first threshold, and both the first threshold and the second threshold represent a percentage of the price increase.

[0051] A second aspect of the present application provides an order-based power transformer supply early warning system, which is applied to the aforementioned order-based power transformer supply early warning method. The system includes:

[0052] Establishing a unit for establishing a mapping table between power transformer specifications and raw material weights;

[0053] a prediction unit, configured to determine, based on the mapping table, historical prices of silicon steel sheets and copper within a first preset time period, and predict prices of the silicon steel sheets and copper within a second time period, wherein the silicon steel sheets and copper are materials for making the power transformer, and the second time period represents a time period from when the order is signed to when the order is delivered;

[0054] a near-due delivery time unit, configured to determine the near-due delivery time based on the predicted prices of the silicon steel sheet and the copper and the delivery time within the second time period, wherein the delivery time represents the time until delivery;

[0055] An early warning condition unit, configured to determine the early warning condition according to the duration of the impending delivery;

[0056] A warning information raising unit, configured to raise early warning information according to the warning condition;

[0057] The response strategy unit is used to determine the response strategy based on the early warning information.

[0058] A third aspect of the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the aforementioned order-based power transformer supply early warning method when executing the computer program.

[0059] A fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the aforementioned order-based power transformer supply early warning method are implemented.

[0060] Beneficial effects of the present invention:

[0061] Establish a mapping table between transformer specifications and raw material weights. Based on the mapping table, determine the historical prices of the required silicon steel sheets and copper within the first preset time period, and predict the prices of the silicon steel sheets and copper within the second time period; then, determine the duration of the impending delivery based on the predicted prices of the silicon steel sheets and copper within the second time period and the duration of the delivery period; next, determine the warning conditions based on the impending delivery period; then, provide warning information based on the warning conditions; and finally, determine the response strategy based on the warning information. Using the above method, the required quantity of silicon steel sheets and copper and the historical prices within the first preset time period can be obtained through the mapping table, and the prices of silicon steel sheets and copper within the second time period can be preset based on the historical prices within the first preset time period, and the expected contract execution price of the transformer and the changes in the winning bid price can be analyzed in real time. When the prices of silicon steel sheets and copper within the second time period and the duration of the delivery period are obtained, timely reminders can be given to internal and external parties to prepare response measures in advance, comprehensively improving the resilience and stability of the transformer supply chain, and providing strong material support for serving the production and construction of power grid enterprises and serving power supply security. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 This is a flow chart of an order-based power transformer supply early warning method of the present invention;

[0064] Figure 2 A flowchart of establishing a mapping table for an order-based power transformer supply early warning method of the present invention;

[0065] Figure 3 A flowchart of a price prediction method for a second time period based on an order for early warning of power transformer supply according to the present invention;

[0066] Figure 4 A flow chart of determining the price of raw materials in a raw material price forecasting model of an order-based power transformer supply early warning method of the present invention;

[0067] Figure 5 A monthly average price trend chart of silicon steel (30Q120) according to an embodiment of an order-based power transformer supply early warning method of the present invention;

[0068] Figure 6These are four different frequency sequence graphs obtained by using a hierarchical clustering method for an order-based power transformer supply early warning method of the present invention;

[0069] Figure 7 Schematic diagram of four sequence feature distributions of an order-based power transformer supply early warning method of the present invention;

[0070] Figure 8 Schematic diagram of the distribution of four sequence characteristics of an order-based power transformer supply early warning method of the present invention. DETAILED DESCRIPTION

[0071] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0072] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like to indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention.

[0073] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a communication between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0074] The following are some explanations of some terms that appear in this application to facilitate understanding of this solution:

[0075] Empirical Mode Decomposition (EMD), an adaptive time-frequency data analysis method, decomposes signals based on the time scale characteristics of the data itself without pre-setting any basis functions. It is a time-frequency domain signal processing method.

[0076] Hierarchical clustering method calculates the similarity between nodes through some similarity measure, sorts them from high to low according to the similarity, and gradually reconnects the nodes.

[0077] ARMA model, Autoregressive moving average model, is an important method for studying time series. It is composed of a "mixture" of autoregressive model (AR model for short) and moving average model (MA model for short).

[0078] Neural network model, neural network is also called artificial neural network, which is the core of deep learning algorithm and a model built using artificial neural network.

[0079] Nonlinear regression is a regression in which the regression function has a nonlinear structure with respect to the unknown regression coefficients. Commonly used methods include linear iteration of the regression function, piecewise regression, and iterative least squares method.

[0080] Power transformer production primarily uses silicon steel sheets and copper as raw materials, and the production cycle is long. Therefore, the production cost of power transformers is significantly affected by the market prices of these sheets. Therefore, price analysis of these sheets is necessary to ensure profitability. This means estimating the future market prices of these sheets based on orders.

[0081] This application provides an order-based power transformer supply early warning method, comprising:

[0082] like Figure 1 As shown, S100: establishing a mapping table between power transformer specifications and raw material weights.

[0083] Among them, due to the particularity of power transformers, it is necessary to analyze the proportion of silicon steel sheets and copper in the cost of power transformers of different voltage levels, and further determine the cost of silicon steel sheets and copper required for the power transformer based on the proportion.

[0084] Specifically, the step of establishing the mapping table includes S101 and S102.

[0085] like Figure 2 As shown, S101: obtaining information of power transformers of different specifications and models, and determining the proportion of silicon steel sheets and copper in raw materials of power transformers of different specifications and models.

[0086] Among them, information on power transformers of different specifications and models in the order is obtained based on the order information. After obtaining the information on power transformers of different specifications and models, the proportion of the required silicon steel sheets and copper in the raw materials can be analyzed, thereby obtaining the quantity of silicon steel sheets and copper.

[0087] S102: Based on the specific gravity of silicon steel sheets and copper, a mapping table is established between raw materials and specifications of power transformers.

[0088] By analyzing the ratios of silicon steel sheets to copper in power transformers of different voltage levels, we developed a mapping table between power transformer specifications and raw material weights. This table reflects the weight of raw materials required for each power transformer. This provides a direct understanding of the raw material costs required to produce a single power transformer.

[0089] S200: Based on the mapping table, determine the historical prices of silicon steel sheets and copper in a first preset time period, and predict the prices of silicon steel sheets and copper in a second time period.

[0090] Among them, silicon steel sheets and copper are materials for making power transformers, and the second time period represents the time period from when the order is signed to when the order is delivered.

[0091] Specifically, historical prices of silicon steel sheets and copper within a first preset time period are determined based on the mapping table. The historical prices may be prices over a period of time in the past. The time period may be set as needed, for example, to one month, one quarter, two quarters, or one year. Based on the price trends of silicon steel sheets and copper within the first preset time period, prices of silicon steel sheets and copper within a second time period are preset.

[0092] It should be noted that the step of predicting the price in the second time period based on the historical price in the first preset time period includes: S201 to S205.

[0093] like Figure 3 As shown, S201: obtaining historical prices of silicon steel sheets and copper within a first preset time period.

[0094] For example, the historical prices of silicon steel sheets and copper for 60 months over the past five years are calculated on a monthly basis and plotted as a graph. The price trends of silicon steel sheets and copper are then observed and analyzed separately.

[0095] S202: Decompose the price history series of silicon steel sheets and copper into multiple series respectively according to the empirical mode decomposition method.

[0096] The empirical mode decomposition method is used to decompose the historical price curves of silicon steel sheets and copper into multiple sequences. This allows the sequences to be reconstructed in subsequent actions to predict the future prices of silicon steel sheets and copper.

[0097] S203: Based on the hierarchical clustering method, the multiple sequences are reconstructed into four sequences of high-frequency data, medium-frequency data, low-frequency data, and trend items.

[0098] The hierarchical clustering method is used to reconstruct the multiple sequences formed by the decomposition of the curve graph. Specifically, the high-frequency, medium-frequency, and low-frequency data, as well as the trend, are used as similarities to form four sequences. This ensures that each sequence has the same characteristics.

[0099] S204: forecasting is performed using the ARMA model, the neural network model, and the nonlinear regression model according to the characteristic distribution of the four sequences.

[0100] Among them, according to the characteristic distribution of the four sequences, the distribution is integrated by using ARMA model, neural network model and nonlinear regression for prediction.

[0101] Sequentially, the four sequences are predicted and integrated using ARMA model, neural network model and nonlinear regression.

[0102] S205: Determine the prediction results of the four predicted sequences.

[0103] The prediction results represent the prices of silicon steel sheets and copper in the second time period.

[0104] Specifically, the four sequences are preset and integrated to obtain prediction results, which are recorded as the prices of silicon steel sheets and copper in the second time period.

[0105] After knowing the prices of silicon steel sheets and copper in the second time period, the amount of silicon steel sheets and copper required can be determined based on the proportion of silicon steel sheets and copper required for the power transformer in the order, and then the profit when delivering the order can be determined.

[0106] S300: Determine the delivery time based on the predicted prices of silicon steel sheets and copper in the second time period and the delivery time.

[0107] The delivery date indicates the time until delivery. The final delivery time indicates the time required to produce the power transformer of the corresponding model in the order from production to completion.

[0108] Specifically, the step of reversely deducing the price of raw materials in the raw material price prediction model based on the actual delivery date and the limit production time includes S301 to S303.

[0109] like Figure 4As shown, S301: obtaining the actual delivery date and the time required for the production of the power transformer.

[0110] The order details reveal the actual delivery date for the power transformers (the actual delivery date is included in the order). Once the actual delivery date is determined, the production cycle for the power transformer model in the order is determined. Based on the production cycle, the start date for power transformer production can be determined.

[0111] S302: Determine the start time of power transformer production based on the actual delivery date and the time required for power transformer production.

[0112] The actual delivery date and the time required to produce the power transformers will determine when production must begin to ensure the power transformers are completed within the order's actual delivery date. For example, if the order's actual delivery date is December 25, 2022, and the production cycle for the power transformer model in the order is 10 days, production must begin at least on December 15, 2022. It is understood that the 10-day period is for illustrative purposes only and the specific production time will prevail.

[0113] S303: Determine the prices of silicon steel sheets and copper at the start time of power transformer production based on the prices in the second time period.

[0114] Among them, based on the predicted prices of silicon steel sheets and copper in the second time period, the price trends of silicon steel sheets and copper in the second time period are determined. Continuing with the above example, for illustrative purposes, if December 25, 2022 is the actual delivery date of the order and the production time requires 10 days, it is necessary to understand the prices of silicon steel sheets and copper on December 15, 2022. It should be noted that December 15, 2022 is a future time point. If today is December 1, 2022, it is necessary to predict the prices of silicon steel sheets and copper in the second time period based on the prediction results obtained in the above steps. In other words, it is necessary to predict the prices of silicon steel sheets and copper on December 15, 2022. Based on the prices of silicon steel sheets and copper on December 15, 2022, and the proportion of silicon steel sheets and copper required for the power transformer in the overall material, it is determined whether there is a profit. If there is a profit, it means that the order can be signed. If there is no profit, the order may not be signed.

[0115] Specifically, the actual delivery date and the maximum production time are used to reverse the process and determine the maximum length T of the raw material price forecast model. F -M.

[0116] Where, M = 1, 2, ..., 180 days; T F The number of days from the actual delivery date.

[0117] S400: Determine the warning conditions based on the upcoming delivery time.

[0118] Among them, according to the due delivery time obtained in the above steps, by querying the mapping table of power transformer specifications and raw material weights, the weight of raw materials required for the power transformer of the corresponding model in the order is calculated, the winning time (the winning time means the time when the order is signed) and the raw material cost at the predicted time are calculated, so as to identify the early warning conditions.

[0119] Specifically, the prices of silicon steel sheets and copper at the time of winning the bid can be determined based on the current market prices of silicon steel sheets and copper. It should be understood that the prices of silicon steel sheets and copper at the time of winning the bid are not equal to the prices of silicon steel sheets and copper during actual production. For example, when the prices of silicon steel sheets and copper are 1 respectively at the time of winning the bid, in actual production, the prices of silicon steel sheets and copper will change due to price fluctuations over time. For example, if production starts half a month after winning the bid, it is necessary to consider whether the prices of silicon steel sheets and copper are 1 half a month after winning the bid. If the price is greater than 1, it means that the profit has decreased or there is no profit. If it is less than 1, it means that there is profit. Based on the above reasons, it is necessary to determine the prices of silicon steel sheets and copper at the start time of power transformer production based on the duration of delivery, and calculate it using the following formula:

[0120] p con (Cu)=N Cu ×p Cu (t 签订 )

[0121] p con (Si)=N Si ×p Si (t 签订 )

[0122] p con (original) = p con (Cu)+p con (Si)

[0123] Among them, p con (Cu), p con (Si) represents the cost of raw materials copper and silicon steel sheet at the time of contract signing, N Cu 、N Si Respectively represent the weight of copper and silicon steel sheet, p Cu (t 签订 ), p Si (t 签订 ) represent the prices of raw materials copper and silicon steel sheets at the time of contract signing. con (Original) represents the total price of raw materials copper and silicon steel sheets at the time of contract signing.

[0124] It should be noted that after calculating the raw material cost calculation formula at the time of contract signing, it is also necessary to establish the raw material cost calculation formula at the time of contract execution:

[0125] p′ con (Cu)=N Cu ×p Cu (t 执行 )

[0126] p′ con (Si)=N Si ×p Si (t 执行 )

[0127] p′ con (original) = p′ con (Cu)+p′ con (Si)

[0128] Among them, p' con (Cu), p' con (Si) represents the cost of raw materials copper and silicon steel sheets at the time of contract execution, p' con (Original) represents the total price of raw materials at the time of contract execution.

[0129] Furthermore, the early warning identification conditions are established:

[0130]

[0131] Among them, p con Indicates the contract price of power transformers.

[0132] The above formula can be used to derive the early warning identification conditions, which can be used as the judgment conditions for whether the contract is signed.

[0133] S500: Providing early warning information according to the warning conditions.

[0134] Among them, after the warning conditions are obtained, early warning information is established according to the warning conditions.

[0135] Specifically, based on the warning conditions, the warning level threshold is determined, and based on the warning level threshold, it is further determined whether the contract has been signed and should be terminated. The warning level threshold is:

[0136]

[0137]

[0138]

[0139] Among them, error represents the model error, profit-rate is the profit rate, min() and max() respectively represent the comparison of minimum and maximum values, and default-cost represents the default cost.

[0140] Specifically, error is expressed as a model error of approximately 5%, profit-rate is the profit rate that can be estimated through the profit statement of the bidding business document (for example, the profit rate of a transformer company in the profit statement for the past two years was 3%), and default-cost is the supplier's default cost, which can be agreed upon through the contractual default clause (for example, if the supplier terminates the contract due to reasons, he shall pay a penalty of 20% of the total contract amount).

[0141] S600: Determine a response strategy based on the warning information.

[0142] Among them, the response strategy is further specified according to formulas (1) to (3) of the warning level threshold.

[0143] Specifically, if the response strategy is formula (1), which means that the raw material price is greater than zero and less than the first threshold of raw material price increase set when the contract is signed, the first time required to replenish the raw materials is determined based on the existing raw materials and the required raw materials.

[0144] For example, formula (1) shows that the price of raw materials has increased slightly compared to when the contract was signed. The project unit should confirm whether the material preparation has been completed for the order. If not, the supplier should be urged to prepare the materials as soon as possible to lock in the raw material price.

[0145] If the response strategy is formula (2), it means that the raw material price is greater than the first threshold of raw material price increase set when the contract is signed, the raw materials are available and needed, and the second time for raw material preparation is determined.

[0146] For example, formula (2) shows that if raw material prices rise significantly, the supplier is likely to suffer losses. The project unit should confirm whether the material preparation for the order has been completed. If not, the project unit should take measures such as increasing collection efforts, changing delivery dates, and strengthening quality supervision.

[0147] If the response strategy is formula (3), it means that the raw material price is greater than the second threshold of raw material price increase set when the contract is signed, and the contract is canceled.

[0148] For example, formula (3) indicates that raw material prices have risen significantly, and the supplier's raw material costs have exceeded the winning bid price, so the order is definitely a loss. The project unit should confirm whether the material preparation for the order has been completed. If not, the project unit should take measures such as increasing collection efforts, changing the delivery date, changing the contract price, and negotiating the contract termination.

[0149] The second threshold is greater than the first threshold, and both the first threshold and the second threshold represent the percentage of the price increase.

[0150] Example:

[0151] like Figure 5-8 As shown, if an order for power transformers is about to be signed, an early warning analysis of the raw material supply is conducted.

[0152] 1. Establish a mapping table between transformer specifications and raw material weights.

[0153] Power transformers are electrical equipment consisting of windings, an iron core, transformer oil, a tank, and other necessary components. The primary raw materials used are copper, silicon steel sheets, insulating oil, and structural steel. Research has shown that copper and silicon steel sheets are the most important raw materials for power transformers.

[0154] A survey of 110 kV to 750 kV transformers shows that the average proportion of copper and silicon steel sheet costs relative to the unit order price is 30.96% and 20.76%, respectively, with standard deviations of 3.58% and 2.34%, respectively. Transformer voltage levels and other related parameters have little impact on the proportion of copper and silicon steel sheet costs. Table 1 shows the average proportion of raw materials for transformers of different voltage levels.

[0155]

[0156] Table 1

[0157] 2. Make price forecasts for silicon steel sheets and copper.

[0158] (1) Silicon steel sheet (30Q120, 30Q120 is the model of silicon steel sheet):

[0159] like Figure 5 As shown in the figure, the monthly average price of silicon steel (30Q120) since 2016 was selected for analysis, with a total of 78 observations.

[0160] like Figure 6 As shown in the figure, the monthly average price of silicon steel (30Q120) is decomposed and reconstructed into four different frequency series (high-frequency, medium-frequency, low-frequency data and trend items) according to the hierarchical clustering method, and the model is fitted.

[0161] like Figure 7 As shown in the figure, the high-frequency data is trained and fitted using a neural network model, the medium-frequency and low-frequency data are fitted using support vector machine regression, and the trend term is fitted using nonlinear regression. The overall fitting effect is relatively good.

[0162] Forecasting for the next six periods (six months), the forecast prices for No. 1 electrolytic copper from May to October are 73701.7, 72640.7, 71571.9, 70562.8, 69825.9, and 69413.9 yuan per ton, respectively. Compared with the price levels of 70510.0, 71297.5, 72991.4, and 74345.5 yuan per ton in the first four months of 2022, the price of No. 1 electrolytic copper will fall from its historical high in the next six months, and may fall back to 70,000 yuan per ton in the third quarter, with a monthly decline of about 1%. By October, the price of No. 1 electrolytic copper is expected to fall by more than 6.5% from its historical high in April.

[0163] 3. Determine the length of the delivery date

[0164] Order status: XXXX, material description: "110kV oil-immersed on-load transformer, 50MVA, 110 / 10, horizontally split", quantity: 2 units, order effective date: June 18, 2021, delivery date: September 5, 2022. The winning bid price, including tax, is RMB 2.1297 million.

[0165] Raw material prices at the time of production: Based on September 5, 2022, copper and silicon steel sheets, the main raw materials for transformers, must be put into production at least 70 days and 60 days in advance, respectively. Therefore, copper prices are forecasted to June 25, 2022, and silicon steel sheet prices to July 5, 2022. Based on the copper and silicon steel sheet forecasting models, the June 2022 copper price forecast is 72,866.02 yuan / ton; the July 2022 price forecast for grain-oriented silicon steel sheet is 17,000 yuan / ton. Raw material prices at the time of order signing: Based on June 18, 2021, historical raw material prices indicate that copper prices were 699,378,600 yuan / ton and silicon steel sheet prices were 14,150 yuan / ton.

[0166] 4. Identify warning conditions

[0167] Based on the raw material quantity, and by checking the material description in the survey table, we know that 8 tons of copper and 25.8 tons of silicon steel sheets are needed. The winning bid price (at the time of signing) for the copper and silicon steel sheets required for each transformer in this order is:

[0168] p con (Cu) = 8 tons × 69,937.86 yuan / ton = 559,502.88 yuan

[0169] p con (S i ) = 25.8 tons × 14,150 yuan / ton = 365,070 yuan

[0170] Taking copper and silicon steel sheets into consideration, the winning bid price is:

[0171] p con (original) = pcon (Cu)+p con (Si) = 559,502.88 yuan + 365,070 yuan = 924,572.88 yuan

[0172] The order price, including tax, was 2.1297 million yuan. The estimated proportions of copper and silicon steel sheets in the order price were 26.27% and 17.14%, respectively. This is slightly lower than the survey's 30% and 21%, respectively. The margin of error was 3.73% and 3.86%, respectively.

[0173] The execution price of copper and silicon steel sheets (the latest purchase time price) is:

[0174] p′ con (Cu) = 8 tons × 72,866.02 yuan / ton = 582,928.16 yuan

[0175] p′ con (Si) = 25.8 tons × 17,000 yuan / ton = 438,600 yuan

[0176] Taking into account the copper and silicon steel sheets, the contract execution price is:

[0177] p′ con (original) = p′ con (Cu)+p′ con (Si) = 582,928.16 yuan + 438,600 yuan = 1,021,528.16 yuan

[0178]

[0179] 5. Provide early warning information

[0180] The 4.55% exceeds the model error of 3.86% and the supplier's average profit margin is about 3%, which is less than the default cost of 20%, positioning the warning level of formula (2).

[0181] 6. Determine a response strategy

[0182] Response strategies can be tailored to the specific circumstances and are not limited in this application. For example, if the order execution price exceeds the maximum of the supplier's profit margin and the model's error rate, but is less than the default cost, the supplier may request an extension to wait and see the market conditions for raw materials. Project tracking and supplier production tracking should be strengthened. If materials are being prepared, the project unit must ensure timely delivery. If materials are not being prepared, production tracking and inspections must be strengthened to ensure material preparation is in place.

[0183] A second aspect of the present application provides an order-based power transformer supply early warning system, which is applied to the aforementioned order-based power transformer supply early warning method. The system includes:

[0184] Establishing a unit for establishing a mapping table between power transformer specifications and raw material weights;

[0185] a prediction unit, configured to determine, based on the mapping table, historical prices of silicon steel sheets and copper within a first preset time period, and predict prices of the silicon steel sheets and copper within a second time period, wherein the silicon steel sheets and copper are materials for making the power transformer, and the second time period represents a time period from when the order is signed to when the order is delivered;

[0186] a near-due delivery time unit, configured to determine the near-due delivery time based on the predicted prices of the silicon steel sheet and the copper and the delivery time within the second time period, wherein the delivery time represents the time until delivery;

[0187] An early warning condition unit, configured to determine the early warning condition according to the duration of the impending delivery;

[0188] A warning information raising unit, configured to raise early warning information according to the warning condition;

[0189] The response strategy unit is used to determine the response strategy based on the early warning information.

[0190] A third aspect of the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the aforementioned order-based power transformer supply early warning method when executing the computer program.

[0191] A fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the aforementioned order-based power transformer supply early warning method are implemented.

[0192] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An order-based power transformer supply early warning method, characterized in that: include: Establish a mapping table between power transformer specifications and raw material weights, including: Obtain information on power transformers of different specifications and models, and determine the proportion of silicon steel sheets and copper in the raw materials of the power transformers of different specifications and models; Based on the specific gravity of the silicon steel sheet and the copper, a mapping table is established between the raw materials and the specifications and models of the power transformer; Based on the mapping table, determining historical prices of silicon steel sheets and copper within a first preset time period, and predicting prices of the silicon steel sheets and copper within a second time period, wherein the silicon steel sheets and the copper are materials for manufacturing the power transformer, and the second time period represents a time period from when the order is signed to when the order is delivered; Determining the duration of the upcoming delivery based on the predicted prices of the silicon steel sheet and the copper within the second time period and the duration of the delivery period, wherein the delivery period represents the time until delivery; Based on the duration of the impending delivery, determine the warning conditions, including: According to the upcoming delivery time, the prices of the silicon steel sheet and the copper at the start time of the power transformer production are determined, wherein: The formula for calculating the cost of raw materials at the time of order signing is: Among them, the p con ( Cu ), p con ( Si ) represent the cost of raw materials copper and silicon steel sheets at the time of contract signing, N Cu 、 N Si Respectively represent the weight of copper and silicon steel sheets, p Cu ( t 签订 ), p Si ( t 签订 ) represent the prices of raw materials copper and silicon steel sheets at the time of contract signing, P con (Original) represents the total price of raw materials copper and silicon steel sheets at the time of contract signing; Establish the formula for calculating raw material costs at the time of contract execution: in, p’ con ( Cu ), p’ con ( Si ) represent the cost of raw materials copper and silicon steel sheets at the time of contract execution, p ’ con (Original) represents the total price of raw materials at the time of contract execution; The warning conditions are: in, p con represents the contract price of power transformer; According to the warning conditions, early warning information is provided, including: According to the warning conditions, the warning level threshold is determined, wherein the calculation formula is: （1） （2） （3） in, Expressed as the model error, is the profit margin, They correspond to the comparison of minimum and maximum values, represents the cost of default; Determine response strategies based on early warning information.

2. The order-based power transformer supply early warning method according to claim 1, characterized in that: The step of predicting the prices of the silicon steel sheet and the copper in a second time period based on the historical prices of the silicon steel sheet and the copper in a first preset time period includes: Obtaining historical prices of the silicon steel sheet and the copper within a first preset time period; Decomposing the price history series of the silicon steel sheet and the copper into multiple series respectively according to the empirical mode decomposition method; According to the hierarchical clustering method, the plurality of said sequences are reconstructed into four sequences of high-frequency, medium-frequency and low-frequency data, and trend items; According to the characteristic distribution of the four sequences, ARMA model, neural network model and nonlinear regression are used for prediction respectively; The four predicted sequences are used to determine prediction results, wherein the prediction results represent prices of the silicon steel sheet and the copper in the second time period.

3. The order-based power transformer supply early warning method according to claim 1, characterized in that: The step of determining the duration of the upcoming delivery based on the predicted prices of the silicon steel sheet and the copper and the duration of the delivery period within the second time period includes: Obtain the actual delivery date and the time required for power transformer production; Determine the start time of power transformer production based on the actual delivery date and the time required for power transformer production; The prices of the silicon steel sheet and the copper at the start time of production of the power transformer are determined according to the prices in the second time period.

4. The order-based power transformer supply early warning method according to claim 1, characterized in that: The step of determining a response strategy based on the early warning information includes: If the response strategy is formula (1), it means that the price of raw materials is greater than zero and less than the first threshold of the raw material price increase set when the contract is signed, and the first time required to replenish the raw materials is determined based on the existing raw materials and the required raw materials; If the response strategy is formula (2), it means that the raw material price is greater than the first threshold of the raw material price increase set when the contract is signed, the raw materials are available and needed, and the second time for preparing the raw materials is determined; If the response strategy is formula (3), it means that the raw material price is greater than the second raw material price increase threshold set when the contract is signed, and the contract is canceled; wherein, The second threshold is greater than the first threshold, and both the first threshold and the second threshold represent a percentage of the price increase.

5. An order-based power transformer supply early warning system, characterized in that: The order-based power transformer supply early warning method according to any one of claims 1 to 4 is implemented, wherein the system comprises: Establishing a unit for establishing a mapping table between power transformer specifications and raw material weights; a prediction unit, configured to determine, based on the mapping table, historical prices of silicon steel sheets and copper within a first preset time period, and predict prices of the silicon steel sheets and copper within a second time period, wherein the silicon steel sheets and copper are materials for making the power transformer, and the second time period represents a time period from when the order is signed to when the order is delivered; a near-due delivery time unit, configured to determine the near-due delivery time based on the predicted prices of the silicon steel sheet and the copper and the delivery time within the second time period, wherein the delivery time represents the time until delivery; An early warning condition unit, configured to determine an early warning condition based on the duration of the impending delivery; A warning information raising unit, configured to raise warning information according to the warning conditions; The response strategy unit is used to determine the response strategy based on the early warning information.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the order-based power transformer supply early warning method according to any one of claims 1 to 4 is implemented.

7. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the order-based power transformer supply early warning method according to any one of claims 1 to 4 are implemented.

Images