Electric energy substitution potential prediction method and device of electric agricultural machine

Abstract

The invention relates to the technical field of electric energy substitution analysis, and particularly provides an electric energy substitution potential prediction method and device for an electric agricultural machine, and the method comprises the steps: enabling a historical quantitative index of the electric agricultural machine in a target region to serve as an input quantity of a pre-trained neural network model, obtaining an inventory prediction value of the electric agricultural machinery output by a pre-trained neural network model; predicting the electric energy substitution amount of the electric agricultural machinery in the target region based on the inventory prediction value of the electric agricultural machinery; wherein the quantitative indexes comprise at least one of the following indexes: the per capita total production value, the ratio of the price of the electric agricultural machinery to the per capita disposable income, the quantitative value of the technical level of the electric agricultural machinery, the quantitative value of the subsidy strength of the electric agricultural machinery, and the quantitative value of the influence degree of the agricultural emission reduction requirement on the electric agricultural machinery; and the mastering difficulty quantized value of the use skill of the electric agricultural machine. According to the technical scheme, prediction of the electric energy substitution amount of the electric agricultural machine is converted into prediction of the inventory, the prediction feasibility is improved, and a good foundation is laid for analysis of the electric energy substitution potential of the electric agricultural machine.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy substitution analysis, and in particular to a method and device for predicting the electric energy substitution potential of an electric agricultural machine. Background Art

[0002] With the continuous improvement of agricultural mechanization, all production links of modern agriculture cannot be separated from the participation of agricultural machinery, and the requirements for green, environmental protection and clean production and life are getting higher and higher. Traditional agricultural machinery has caused serious pollution to the environment. At present, nearly 80% of agricultural machinery is powered by diesel engines. On the one hand, the pollution comes from the exhaust gas emissions of the diesel engine itself, and on the other hand, the dripping and waste oil emissions of the diesel engine also cause serious pollution to farmland. The serious pollution problem of traditional fuel agricultural machinery has forced agricultural machinery to turn to clean and environmentally friendly energy. Thanks to the development of mechanical and electronic technology and battery technology, electric drive technology has been applied in various industries. In the past 20 years, the research and development, promotion and application of electric vehicles have had a good foundation, and the large-scale application of electric agricultural machinery has been foreseen. When electric agricultural machinery is applied on a large scale in various links of agricultural production, there will be a huge and increasing demand for agricultural machinery charging every year to replace the fuel demand of traditional agricultural machinery.

[0003] Electricity substitution refers to the use of electricity to replace coal, oil and other energy consumption methods in the terminal energy consumption link, and ultimately achieve a clean transformation of energy development mode. Electricity substitution is not only an important means to accelerate the adjustment of energy structure, but also an important measure to promote the adjustment of energy consumption proportion. Scientific prediction of the scale of future electricity substitution can provide an objective basis for the expansion of the terminal consumption market of electricity and provide strong and scientific support for the development of electricity substitution.

[0004] At present, most of the research on the prediction of electric energy substitution potential is based on direct predictions based on historical electricity consumption data, and there is no analysis of the progress of a certain type of electric energy substitution technology such as electric agricultural machinery. Current research has not yet conducted a quantitative assessment of the impact of factors related to electric energy substitution for electric agricultural machinery, let alone a predictive analysis of the electric energy substitution potential of large-scale application of electric agricultural machinery. Summary of the invention

[0005] In order to overcome the above-mentioned defects, the present invention proposes a method and device for predicting the electric energy substitution potential of electric agricultural machinery.

[0006] In a first aspect, a method for predicting the electric energy substitution potential of an electric agricultural machinery is provided, the method comprising:

[0007] The historical quantitative indicators of electric agricultural machinery in the target area are used as the input of the pre-trained neural network model to obtain the predicted value of the number of electric agricultural machinery output by the pre-trained neural network model;

[0008] Predicting the amount of electric energy replacement of the electric agricultural machinery in the target area based on the predicted value of the number of electric agricultural machinery in stock;

[0009] Among them, the quantitative indicators include at least one of the following: per capita gross domestic product, the ratio of electric agricultural machinery prices to per capita disposable income, the quantitative value of the technical level of electric agricultural machinery, the quantitative value of the intensity of electric agricultural machinery subsidies, the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery, and the quantitative value of the difficulty of mastering electric agricultural machinery use skills.

[0010] Preferably, the training process of the pre-trained neural network model includes:

[0011] The training data is constructed using the quantitative indicators of the historically designated reference years of electric plant protection drones and the number of electric plant protection drones in the historically designated forecast years;

[0012] The initial neural network model is trained using the training data to obtain the pre-trained neural network model.

[0013] Preferably, the per capita GDP is as follows:

[0014]

[0015] In the above formula, ED(t) is the per capita GDP in the tth year, GDP(t) is the gross domestic product in the tth year, and H(t) is the population in the tth year.

[0016] Preferably, the ratio of the price of the electric agricultural machinery to the per capita disposable income is as follows:

[0017]

[0018] In the above formula, EP(t) is the ratio of the price of electric agricultural machinery to the per capita disposable income in year t, P(t) is the average price of electric agricultural machinery in year t, and PCDI(t) is the per capita disposable income in year t.

[0019] Preferably, the technical level quantification value of the electric agricultural machinery is as follows:

[0020]

[0021] In the above formula, ET(t) is the quantitative value of the technical level of electric agricultural machinery in year t, d e (t) is the driving time of the electric agricultural machinery in year t, d f (t) is the endurance of traditional agricultural machinery in year t, η e (t) is the working efficiency of electric agricultural machinery in year t, η f (t) is the working efficiency of traditional agricultural machinery in year t.

[0022] Preferably, the quantified value of the electric agricultural machinery subsidy is as follows:

[0023]

[0024] In the above formula, EC(t) is the quantitative value of the subsidy intensity for electric agricultural machinery in year t, S(t) is the subsidy amount that can be obtained by purchasing an electric agricultural machinery in year t, and P(t) is the average price of electric agricultural machinery in year t.

[0025] Preferably, the quantitative value of the impact of the agricultural emission reduction requirements on electric agricultural machinery is as follows:

[0026]

[0027] In the above formula, EI(t) is the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery in year t, and PO f (t) is the pollutant emission level of a single traditional agricultural machinery in year t, e (t) is the pollutant emission level of a single electric agricultural machinery in year t.

[0028] Furthermore, the pollutant emission level of a single electric agricultural machine in the tth year is as follows:

[0029] PO e (t) = O p (t)+O b (t)

[0030] In the above formula, O p (t) is the pollutant emission from the power generation process of a single electric agricultural machine in year t, O b (t) is the pollutant emission from a single electric agricultural machine in year t taking into account battery disposal.

[0031] Preferably, the quantified value of the difficulty of mastering the electric agricultural machinery use skills is as follows:

[0032]

[0033] In the above formula, ES(t) is the quantitative value of the difficulty of mastering the skills of using electric agricultural machinery in the tth year, k is the training duration of the use of electric agricultural machinery, h represents hours, and a, b and c represent easy, general and difficult respectively.

[0034] Preferably, the amount of electric energy replaced by the electric agricultural machinery is as follows:

[0035] Q=N·P·T

[0036] In the above formula, Q is the amount of electric energy replaced by the electric agricultural machinery, N is the predicted value of the number of electric agricultural machinery in stock, P is the operating power of the electric agricultural machinery, and T is the annual operating hours of the electric agricultural machinery.

[0037] In a second aspect, a device for predicting the potential of electric energy substitution for an electric agricultural machine is provided, the device comprising:

[0038] An analysis module is used to use the historical quantitative indicators of electric agricultural machinery in the target area as input quantities of a pre-trained neural network model to obtain a predicted value of the number of electric agricultural machinery output by the pre-trained neural network model;

[0039] A prediction module, used for predicting the electric energy replacement amount of the electric agricultural machinery in the target area based on the predicted value of the number of electric agricultural machinery in stock;

[0040] Among them, the quantitative indicators include at least one of the following: per capita gross domestic product, the ratio of electric agricultural machinery prices to per capita disposable income, the quantitative value of the technical level of electric agricultural machinery, the quantitative value of the intensity of electric agricultural machinery subsidies, the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery, and the quantitative value of the difficulty of mastering electric agricultural machinery use skills.

[0041] Preferably, the training process of the pre-trained neural network model includes:

[0042] The training data is constructed using the quantitative indicators of the historically designated reference years of electric plant protection drones and the number of electric plant protection drones in the historically designated forecast years;

[0043] The initial neural network model is trained using the training data to obtain the pre-trained neural network model.

[0044] Preferably, the per capita GDP is as follows:

[0045]

[0046] In the above formula, ED(t) is the per capita GDP in the tth year, GDP(t) is the gross domestic product in the tth year, and H(t) is the population in the tth year.

[0047] Preferably, the ratio of the price of the electric agricultural machinery to the per capita disposable income is as follows:

[0048]

[0049] In the above formula, EP(t) is the ratio of the price of electric agricultural machinery to the per capita disposable income in year t, P(t) is the average price of electric agricultural machinery in year t, and PCDI(t) is the per capita disposable income in year t.

[0050] Preferably, the technical level quantification value of the electric agricultural machinery is as follows:

[0051]

[0052] In the above formula, ET(t) is the quantitative value of the technical level of electric agricultural machinery in year t, d e (t) is the driving time of the electric agricultural machinery in year t, d f (t) is the endurance of traditional agricultural machinery in year t, η e (t) is the working efficiency of electric agricultural machinery in year t, η f (t) is the working efficiency of traditional agricultural machinery in year t.

[0053] Preferably, the quantified value of the electric agricultural machinery subsidy is as follows:

[0054]

[0055] In the above formula, EC(t) is the quantitative value of the subsidy intensity for electric agricultural machinery in year t, S(t) is the subsidy amount that can be obtained by purchasing an electric agricultural machinery in year t, and P(t) is the average price of electric agricultural machinery in year t.

[0056] Preferably, the quantitative value of the impact of the agricultural emission reduction requirements on electric agricultural machinery is as follows:

[0057]

[0058] In the above formula, EI(t) is the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery in year t, and PO f (t) is the pollutant emission level of a single traditional agricultural machinery in year t, e (t) is the pollutant emission level of a single electric agricultural machinery in year t.

[0059] Furthermore, the pollutant emission level of a single electric agricultural machine in the tth year is as follows:

[0060] PO e (t) = O p (t)+O b (t)

[0061] In the above formula, O p (t) is the pollutant emission from the power generation process of a single electric agricultural machine in year t, O b (t) is the pollutant emission from a single electric agricultural machine in year t taking into account battery disposal.

[0062] Preferably, the quantified value of the difficulty of mastering the electric agricultural machinery use skills is as follows:

[0063]

[0064] In the above formula, ES(t) is the quantitative value of the difficulty of mastering the skills of using electric agricultural machinery in the tth year, k is the training duration of the use of electric agricultural machinery, h represents hours, and a, b and c represent easy, general and difficult respectively.

[0065] Preferably, the amount of electric energy replaced by the electric agricultural machinery is as follows:

[0066] Q=N·P·T

[0067] In the above formula, Q is the amount of electric energy replaced by the electric agricultural machinery, N is the predicted value of the number of electric agricultural machinery in stock, P is the operating power of the electric agricultural machinery, and T is the annual operating hours of the electric agricultural machinery.

[0068] In a third aspect, a computer device is provided, comprising: one or more processors;

[0069] The processor is configured to execute one or more programs;

[0070] When the one or more programs are executed by the one or more processors, the method for predicting the electric energy substitution potential of the electric agricultural machinery is implemented.

[0071] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed, the method for predicting the electric energy substitution potential of electric agricultural machinery is implemented.

[0072] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0073] The present invention relates to the technical field of electric energy substitution analysis, and specifically provides a method and device for predicting the electric energy substitution potential of electric agricultural machinery, comprising: using historical quantitative indicators of electric agricultural machinery in a target area as input quantities of a pre-trained neural network model to obtain a predicted value of the number of electric agricultural machinery output by the pre-trained neural network model; predicting the electric energy substitution amount of the electric agricultural machinery in the target area based on the predicted value of the number of electric agricultural machinery; wherein the quantitative indicators include at least one of the following: per capita gross domestic product, the ratio of the price of electric agricultural machinery to per capita disposable income, a quantitative value of the technical level of electric agricultural machinery, a quantitative value of the intensity of electric agricultural machinery subsidies, a quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery, and a quantitative value of the difficulty of mastering electric agricultural machinery use skills. The technical solution provided by the present invention can link the number of electric agricultural machinery in stock with the amount of electric energy replaced by the electric agricultural machinery, and convert the prediction of the electric energy replacement amount of electric agricultural machinery into the prediction of the number of stocks, thereby improving the feasibility of the prediction and laying a solid foundation for the analysis of the electric energy substitution potential of electric agricultural machinery. Furthermore, the quantitative index system of the main influencing factors of electric agricultural machinery in the process of electric energy substitution established by the present invention can well summarize the main influencing factors of the promotion of electric agricultural machinery, and is also suitable for many emerging technology products that are being electrified. The comprehensive quantitative index system of influencing factors has laid a good foundation for the establishment of a prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a schematic flow chart of the main steps of the method for predicting the electric energy substitution potential of an electric agricultural machinery according to an embodiment of the present invention;

[0075] Figure 2 4 is a diagram of prediction results of different development scenarios according to an embodiment of the present invention. DETAILED DESCRIPTION

[0076] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0077] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0078] The above scheme is described in detail below.

[0079] Example 1

[0080] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart showing the main steps of a method for predicting the electric energy substitution potential of an electric agricultural machinery according to an embodiment of the present invention. Figure 1 As shown, the method for predicting the electric energy substitution potential of an electric agricultural machinery in an embodiment of the present invention mainly includes the following steps:

[0081] Step S101: using the historical quantitative indicators of electric agricultural machinery in the target area as the input of the pre-trained neural network model to obtain the predicted value of the number of electric agricultural machinery output by the pre-trained neural network model;

[0082] Step S102: predicting the amount of electric energy replacement of the electric agricultural machinery in the target area based on the predicted value of the number of electric agricultural machinery in stock;

[0083] Among them, the quantitative indicators include at least one of the following: per capita gross domestic product, the ratio of electric agricultural machinery prices to per capita disposable income, the quantitative value of the technical level of electric agricultural machinery, the quantitative value of the intensity of electric agricultural machinery subsidies, the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery, and the quantitative value of the difficulty of mastering electric agricultural machinery use skills.

[0084] In this embodiment, the training process of the pre-trained neural network model includes:

[0085] The training data is constructed using the quantitative indicators of the historically designated reference years of electric plant protection drones and the number of electric plant protection drones in the historically designated forecast years;

[0086] The initial neural network model is trained using the training data to obtain the pre-trained neural network model.

[0087] In one embodiment, a particle swarm optimization neural network regression prediction model is used, the electric agricultural machinery influencing factor index is used as the network model input layer, the electric agricultural machinery inventory is used as the output layer, and the historical development data of electric plant protection drones is used as a reference to train the network to complete the prediction. The BP neural network can quickly adapt to various problems, but it is also prone to local optimal and overfitting problems, which affect the prediction results. The introduction of the PSO algorithm to achieve global optimization can avoid falling into the local optimal solution, and reduce the risk of overfitting by optimizing the weight parameters to improve the accuracy of the prediction model. Therefore, the present invention constructs a PSO-BP model to predict the amount of electric energy substitution promoted by electric agricultural machinery.

[0088] The specific steps are as follows: 1) Analyze the influencing factors of electric agricultural machinery substitution, and obtain the quantitative indicators of the influencing factors as the input layer data of the prediction model; set the number of electric agricultural machinery as the output layer, and the number of hidden layer nodes is determined by the empirical formula; 2) Use the particle swarm algorithm to find the optimal weight parameters and bias values ​​of the BP neural network to improve the prediction accuracy and prediction stability of the prediction model; 3) Electric plant protection drones are the earliest type of agricultural machinery in the study of agricultural machinery electrification, and have nearly ten years of development data. The development data of electric plant protection drones in the past few years is used as a training set, and the prediction performance of PSO-BP is evaluated using relevant error indicators; 4) Determine the baseline, optimistic, and pessimistic scenarios for the development of electric agricultural machinery, set the development parameters under the baseline, optimistic, and pessimistic scenarios for the development of electric agricultural machinery, predict the number of electric agricultural machinery in the future based on the trained model, and then obtain the amount of electric agricultural machinery substitution, and analyze the potential for electric agricultural machinery substitution.

[0089] In this embodiment, the state of economic development has a significant impact on the demand and consumption of terminal electric energy. The overall economic development of a region will have an impact on the consumption of electricity and other energy. In addition, for the purchase and replacement of electric agricultural machinery, the initial purchase cost of electric agricultural machinery is higher than that of traditional fuel agricultural machinery for agricultural machinery users. In comparison, the power system and fuel supply of traditional fuel agricultural machinery are already relatively mature and popular. Although the long-term operating cost of electric agricultural machinery is relatively lower, its operation and use of subsidized electricity prices, and maintenance expenses are also lower than traditional agricultural machinery, for agricultural machinery users, the initial high investment in electric agricultural machinery will still affect whether agricultural machinery users will purchase and replace it. Therefore, economic development has a very important impact on the electric energy substitution of electric agricultural machinery. This study uses the ratio of regional per capita GDP, electric agricultural machinery prices and regional per capita disposable income to represent the impact of regional economic development and agricultural machinery purchase costs on electric energy substitution during the electrification of agricultural machinery. The per capita GDP is as follows:

[0090]

[0091] In the above formula, ED(t) is the per capita GDP in the tth year, GDP(t) is the gross domestic product in the tth year, and H(t) is the population in the tth year.

[0092] The ratio of the price of electric agricultural machinery to per capita disposable income is as follows:

[0093]

[0094] In the above formula, EP(t) is the ratio of the price of electric agricultural machinery to the per capita disposable income in year t, P(t) is the average price of electric agricultural machinery in year t, and PCDI(t) is the per capita disposable income in year t.

[0095] In this embodiment, the technical level of electric agricultural machinery is the key to whether it can achieve large-scale application. Agricultural machinery operations have a variety of production scenarios, and there are high requirements for the power, operating efficiency, and endurance of agricultural machinery during operation. The higher and more mature the technical level of electric agricultural machinery, the more it is suitable for actual use in agricultural production environments, and the faster the process of agricultural machinery electric energy substitution.

[0096] The impact of technical level on the substitution of electric energy for agricultural machinery can be quantified from two aspects. On the one hand, it can be expressed from the endurance of electric agricultural machinery. The longer the endurance of electric agricultural machinery, the more it can complete actual agricultural production. On the other hand, it can be reflected from the operating efficiency of electric agricultural machinery. The higher the operating efficiency, the more farmers will choose to use electric agricultural machinery. The quantitative values ​​of the technical level of electric agricultural machinery are as follows:

[0097]

[0098] In the above formula, ET(t) is the quantitative value of the technical level of electric agricultural machinery in year t, d e (t) is the driving time of the electric agricultural machinery in year t, d f (t) is the endurance of traditional agricultural machinery in year t, η e (t) is the working efficiency of electric agricultural machinery in year t, η f (t) is the working efficiency of traditional agricultural machinery in year t.

[0099] In this embodiment, policy support has an important impact on the promotion and use of agricultural machinery, and agricultural machinery purchase subsidies are an important way of policy support. Since the relevant policies on agricultural machinery purchase subsidies were introduced in 2004, the intensity of support has gradually increased, the scope of benefits has continued to expand, and the policy effects have continued to emerge. Agricultural machinery purchase subsidies can help promote the improvement of agricultural machinery equipment levels and agricultural mechanization levels. At the same time, the adjustment of subsidy scope and standards can also guide farmers to purchase and use advanced and applicable agricultural machinery, promote agricultural mechanization to transform and upgrade to high-quality and high-efficiency throughout the entire process, and accelerate the modernization of the agricultural mechanization industry chain. Therefore, the promotion and application of electric agricultural machinery cannot be separated from policy support and promotion. The intensity of policy support can be expressed by the ratio of purchase subsidies to the average price of electric agricultural machinery. The quantitative value of the electric agricultural machinery subsidy intensity is as follows:

[0100]

[0101] In the above formula, EC(t) is the quantitative value of the subsidy intensity for electric agricultural machinery in year t, S(t) is the subsidy amount that can be obtained by purchasing an electric agricultural machinery in year t, and P(t) is the average price of electric agricultural machinery in year t.

[0102] In this embodiment, it is a consensus in the industry that the electrification of agricultural machinery is conducive to the protection of the ecological environment. Electric agricultural machinery does not emit pollutants during agricultural production operations and is a clean and environmentally friendly agricultural machinery. Moreover, the use of electric agricultural machinery is more conducive to the health of the operator. Modern agriculture emphasizes the protection of agricultural practitioners. Traditional agricultural machinery burns diesel during operation and emits a large amount of pollutants while working, which not only damages the ecological environment, but also harms the health of agricultural machinery users. The emission-free, low noise and low vibration of electric agricultural machinery during use are beneficial to the physical and mental health of the operator.

[0103] Traditional agricultural machinery directly emits pollutants when burning diesel, while electric agricultural machinery does not emit pollutants when in use. However, in the power generation stage, if it is thermal power generation, pollutants will be emitted, and the battery waste stage will also produce pollutant emissions. However, as the proportion of new energy power generation increases, battery processing technology continues to improve, and the emission reduction effect of electric agricultural machinery will become more and more obvious. Therefore, agricultural emission reduction requirements play an important role in promoting the promotion and use of electric agricultural machinery.

[0104] Here, the pollutant emission reduction of electric agricultural machinery compared with traditional agricultural machinery is used as a quantitative indicator to reflect the impact of agricultural emission reduction requirements on the replacement of agricultural machinery with electric energy. The quantitative values ​​of the impact of agricultural emission reduction requirements on electric agricultural machinery are as follows:

[0105]

[0106] In the above formula, EI(t) is the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery in year t, and PO f(t) is the pollutant emission level of a single traditional agricultural machinery in year t, e (t) is the pollutant emission level of a single electric agricultural machinery in year t.

[0107] The pollutant emission levels of a single electric agricultural machine in year t are as follows:

[0108] PO e (t) = O p (t)+O b (t)

[0109] In the above formula, O p (t) is the pollutant emission from the power generation process of a single electric agricultural machine in year t, O b (t) is the pollutant emission from a single electric agricultural machine in year t taking into account battery disposal.

[0110] In this embodiment, the use of electric agricultural machinery helps to improve the sustainability of agricultural production, helps to solve the environmental pollution problem of traditional agricultural machinery, and can bring long-term economic benefits, social benefits and environmental benefits to the development of rural areas. The promotion of electric agricultural machinery first requires farmers to have corresponding use skills and maintenance knowledge. The ease of use of electric agricultural machinery determines the degree and speed of farmers' acceptance of electric agricultural machinery. Therefore, the ease of use of electric agricultural machinery is also an important factor in promoting the substitution of agricultural machinery with electric energy. The quantitative value of the difficulty of mastering the skills of using electric agricultural machinery is as follows:

[0111]

[0112] In the above formula, ES(t) is the quantitative value of the difficulty of mastering the skills of using electric agricultural machinery in the tth year, k is the training duration of the use of electric agricultural machinery, h represents hours, and a, b and c represent easy, general and difficult respectively.

[0113] In this embodiment, the amount of electric energy replaced by the electric agricultural machinery is as follows:

[0114] Q=N·P·T

[0115] In the above formula, Q is the amount of electric energy replaced by the electric agricultural machinery, N is the predicted value of the number of electric agricultural machinery in stock, P is the operating power of the electric agricultural machinery, and T is the annual operating hours of the electric agricultural machinery.

[0116] In order to verify the effectiveness of the electric energy substitution potential prediction method for electric agricultural machinery of the present invention, the relevant development data of electric plant protection UAVs in the past 9 years were selected, as shown in Table 1.

[0117] Table 1

[0118]

[0119] According to the development data of electric plant protection UAVs in the past nine years obtained from the statistics in Table 1, the development data was processed according to the corresponding formula for indicator quantification of the present invention, and the quantitative results of five influencing factors, including regional economy and agricultural machinery purchase cost, electric agricultural machinery technical level, electric agricultural machinery policy subsidies, agricultural emission reduction requirements, and difficulty in mastering electric agricultural machinery use skills, were obtained, as shown in Table 2.

[0120] Table 2

[0121]

[0122] In this embodiment, three application scenarios are preset to test the technical solution provided by the present invention. A general scenario is set. In terms of economic development, the economic development goal strives to achieve a preset level of per capita GDP in 2035, realize agricultural modernization, and the operation technology is continuously improved with reference to the existing plant protection drones. The operation efficiency is far superior to the traditional electric plant protection drones after development. By 2035, the ecological civilization system will be more perfect, the air quality will be fundamentally improved, the proportion of clean energy in electricity production will continue to increase, the battery processing technology will continue to improve, the purchase subsidy will be set to maintain at 35%, the farmers' understanding of electric agricultural machinery will continue to improve, and the ease of use of electric plant protection drones will continue to improve. As shown in Table 3:

[0123] Table 3

[0124]

[0125] The optimistic scenario takes into account the accelerated economic growth rate, intensified agricultural machinery transformation efforts, rapid improvement in the operating capacity of electric plant protection drones, stable purchase subsidies for electric plant protection drones, higher growth rate of the proportion of clean energy in electricity production compared to the baseline scenario, smooth agricultural emission reduction, and rapid development of the ease of use of electric plant protection drones. The details are shown in Table 4:

[0126] Table 4

[0127]

[0128] The pessimistic scenario sets the regional economic growth rate to be significantly lower than the expected planning target, the operation level of electric plant protection drones improves slowly, the purchase subsidy of electric plant protection drones remains stable, the growth rate of the proportion of clean energy in electricity production slows down compared with the baseline scenario, and the ease of use of electric plant protection drones improves slowly. The details are shown in Table 5:

[0129] Table 5

[0130]

[0131] The forecast results of the three development scenarios are as follows Figure 2 The predicted results of the inventory are shown in Table 6.

[0132] Table 6

[0133]

[0134]

[0135] The power of existing electric plant protection drones is generally between 10kW and 20kW. Taking 15kW as an example, assuming that the average annual working hours are 500 hours, the predicted results of the electric energy substitution potential of electric plant protection drones can be calculated according to the formula, as shown in Table 7.

[0136] Table 7

[0137]

[0138] Example 2

[0139] Based on the same inventive concept, the present invention also provides a device for predicting the potential of electric energy substitution for electric agricultural machinery, the device comprising:

[0140] An analysis module is used to use the historical quantitative indicators of electric agricultural machinery in the target area as input quantities of a pre-trained neural network model to obtain a predicted value of the number of electric agricultural machinery output by the pre-trained neural network model;

[0141] A prediction module, used for predicting the electric energy replacement amount of the electric agricultural machinery in the target area based on the predicted value of the number of electric agricultural machinery in stock;

[0142] Among them, the quantitative indicators include at least one of the following: per capita gross domestic product, the ratio of electric agricultural machinery prices to per capita disposable income, the quantitative value of the technical level of electric agricultural machinery, the quantitative value of the intensity of electric agricultural machinery subsidies, the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery, and the quantitative value of the difficulty of mastering electric agricultural machinery use skills.

[0143] Preferably, the training process of the pre-trained neural network model includes:

[0144] The training data is constructed using the quantitative indicators of the historically designated reference years of electric plant protection drones and the number of electric plant protection drones in the historically designated forecast years;

[0145] The initial neural network model is trained using the training data to obtain the pre-trained neural network model.

[0146] Preferably, the per capita GDP is as follows:

[0147]

[0148] In the above formula, ED(t) is the per capita GDP in the tth year, GDP(t) is the gross domestic product in the tth year, and H(t) is the population in the tth year.

[0149] Preferably, the ratio of the price of the electric agricultural machinery to the per capita disposable income is as follows:

[0150]

[0151] In the above formula, EP(t) is the ratio of the price of electric agricultural machinery to the per capita disposable income in year t, P(t) is the average price of electric agricultural machinery in year t, and PCDI(t) is the per capita disposable income in year t.

[0152] Preferably, the technical level quantification value of the electric agricultural machinery is as follows:

[0153]

[0154] In the above formula, ET(t) is the quantitative value of the technical level of electric agricultural machinery in year t, d e (t) is the driving time of the electric agricultural machinery in year t, d f (t) is the endurance of traditional agricultural machinery in year t, η e (t) is the working efficiency of electric agricultural machinery in year t, η f (t) is the working efficiency of traditional agricultural machinery in year t.

[0155] Preferably, the quantified value of the electric agricultural machinery subsidy is as follows:

[0156]

[0157] In the above formula, EC(t) is the quantitative value of the subsidy intensity for electric agricultural machinery in year t, S(t) is the subsidy amount that can be obtained by purchasing an electric agricultural machinery in year t, and P(t) is the average price of electric agricultural machinery in year t.

[0158] Preferably, the quantitative value of the impact of the agricultural emission reduction requirements on electric agricultural machinery is as follows:

[0159]

[0160] In the above formula, EI(t) is the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery in year t, and PO f (t) is the pollutant emission level of a single traditional agricultural machinery in year t, e (t) is the pollutant emission level of a single electric agricultural machinery in year t.

[0161] Furthermore, the pollutant emission level of a single electric agricultural machine in the tth year is as follows:

[0162] PO e(t) = O p (t)+O b (t)

[0163] In the above formula, O p (t) is the pollutant emission from the power generation process of a single electric agricultural machine in year t, O b (t) is the pollutant emission from a single electric agricultural machine in year t taking into account battery disposal.

[0164] Preferably, the quantified value of the difficulty of mastering the electric agricultural machinery use skills is as follows:

[0165]

[0166] In the above formula, ES(t) is the quantitative value of the difficulty of mastering the skills of using electric agricultural machinery in the tth year, k is the training duration of the use of electric agricultural machinery, h represents hours, and a, b and c represent easy, general and difficult respectively.

[0167] Preferably, the amount of electric energy replaced by the electric agricultural machinery is as follows:

[0168] Q=N·P·T

[0169] In the above formula, Q is the amount of electric energy replaced by the electric agricultural machinery, N is the predicted value of the number of electric agricultural machinery in stock, P is the operating power of the electric agricultural machinery, and T is the annual operating hours of the electric agricultural machinery.

[0170] Example 3

[0171] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of the electric energy substitution potential prediction method of an electric agricultural machinery in the above embodiment.

[0172] Example 4

[0173] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of a method for predicting the electric energy substitution potential of an electric agricultural machinery in the above embodiment.

[0174] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0175] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0178] 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, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for predicting the electric energy substitution potential of electric agricultural machinery, characterized in that: The method comprises: The historical quantitative indicators of electric agricultural machinery in the target area are used as the input of the pre-trained neural network model to obtain the predicted value of the number of electric agricultural machinery output by the pre-trained neural network model; Predicting the amount of electric energy replacement of the electric agricultural machinery in the target area based on the predicted value of the number of electric agricultural machinery in stock; Among them, the quantitative indicators include at least one of the following: per capita gross domestic product, the ratio of electric agricultural machinery prices to per capita disposable income, the quantitative value of the technical level of electric agricultural machinery, the quantitative value of the intensity of electric agricultural machinery subsidies, the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery, and the quantitative value of the difficulty of mastering electric agricultural machinery use skills.

2. The method according to claim 1, characterized in that The training process of the pre-trained neural network model includes: The training data is constructed using the quantitative indicators of the historically designated reference years of electric plant protection drones and the number of electric plant protection drones in the historically designated forecast years; The initial neural network model is trained using the training data to obtain the pre-trained neural network model.

3. The method according to claim 1, characterized in that The GDP per capita is as follows: In the above formula, ED(t) is the per capita GDP in the tth year, GDP(t) is the gross domestic product in the tth year, and H(t) is the population in the tth year.

4. The method according to claim 1, characterized in that The ratio of the price of electric agricultural machinery to per capita disposable income is as follows: In the above formula, EP(t) is the ratio of the price of electric agricultural machinery to the per capita disposable income in year t, P(t) is the average price of electric agricultural machinery in year t, and PCDI(t) is the per capita disposable income in year t.

5. The method according to claim 1, characterized in that The quantified values ​​of the technical level of the electric agricultural machinery are as follows: In the above formula, ET(t) is the quantitative value of the technical level of electric agricultural machinery in year t, d e (t) is the driving time of the electric agricultural machinery in year t, d f (t) is the endurance of traditional agricultural machinery in year t, η e (t) is the working efficiency of electric agricultural machinery in year t, η f (t) is the working efficiency of traditional agricultural machinery in year t.

6. The method according to claim 1, characterized in that The quantitative values ​​of the electric agricultural machinery subsidy are as follows: In the above formula, EC(t) is the quantitative value of the subsidy intensity for electric agricultural machinery in year t, S(t) is the subsidy amount that can be obtained by purchasing an electric agricultural machinery in year t, and P(t) is the average price of electric agricultural machinery in year t.

7. The method according to claim 1, characterized in that The quantitative values ​​of the impact of the agricultural emission reduction requirements on electric agricultural machinery are as follows: In the above formula, EI(t) is the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery in year t, and PO f (t) is the pollutant emission level of a single traditional agricultural machinery in year t, e (t) is the pollutant emission level of a single electric agricultural machinery in year t.

8. The method according to claim 7, characterized in that The pollutant emission levels of a single electric agricultural machine in year t are as follows: PO e (t)=O p (t)+O b (t) In the above formula, O p (t) is the pollutant emission from the power generation process of a single electric agricultural machine in year t, O b (t) is the pollutant emission from a single electric agricultural machine in year t taking into account battery disposal.

9. The method according to claim 1, characterized in that The quantitative values ​​of the difficulty of mastering the electric agricultural machinery use skills are as follows: In the above formula, ES(t) is the quantitative value of the difficulty of mastering the skills of using electric agricultural machinery in the tth year, k is the training duration of the use of electric agricultural machinery, h represents hours, and a, b and c represent easy, general and difficult respectively.

10. The method according to claim 1, characterized in that The amount of electric energy replaced by the electric agricultural machinery is as follows: Q=N·P·T In the above formula, Q is the amount of electric energy replaced by the electric agricultural machinery, N is the predicted value of the number of electric agricultural machinery in stock, P is the operating power of the electric agricultural machinery, and T is the annual operating hours of the electric agricultural machinery.

11. A device for predicting the potential of electric energy substitution for electric agricultural machinery, characterized in that: The device comprises: An analysis module is used to use the historical quantitative indicators of electric agricultural machinery in the target area as input quantities of a pre-trained neural network model to obtain a predicted value of the number of electric agricultural machinery output by the pre-trained neural network model; A prediction module, used for predicting the electric energy replacement amount of the electric agricultural machinery in the target area based on the predicted value of the number of electric agricultural machinery in stock; Among them, the quantitative indicators include at least one of the following: per capita gross domestic product, the ratio of electric agricultural machinery prices to per capita disposable income, the quantitative value of the technical level of electric agricultural machinery, the quantitative value of the intensity of electric agricultural machinery subsidies, the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery, and the quantitative value of the difficulty of mastering electric agricultural machinery use skills.

12. The device according to claim 11, characterized in that The training process of the pre-trained neural network model includes: The training data is constructed using the quantitative indicators of the historically designated reference years of electric plant protection drones and the number of electric plant protection drones in the historically designated forecast years; The initial neural network model is trained using the training data to obtain the pre-trained neural network model.

13. The device according to claim 11, characterized in that The GDP per capita is as follows: In the above formula, ED(t) is the per capita GDP in the tth year, GDP(t) is the gross domestic product in the tth year, and H(t) is the population in the tth year.

14. The device according to claim 11, characterized in that The ratio of the price of electric agricultural machinery to per capita disposable income is as follows: In the above formula, EP(t) is the ratio of the price of electric agricultural machinery to the per capita disposable income in year t, P(t) is the average price of electric agricultural machinery in year t, and PCDI(t) is the per capita disposable income in year t.

15. The device according to claim 11, characterized in that The quantified values ​​of the technical level of the electric agricultural machinery are as follows: In the above formula, ET(t) is the quantitative value of the technical level of electric agricultural machinery in year t, d e (t) is the driving time of the electric agricultural machinery in year t, d f (t) is the endurance of traditional agricultural machinery in year t, η e (t) is the working efficiency of electric agricultural machinery in year t, η f (t) is the working efficiency of traditional agricultural machinery in year t.

16. The device according to claim 11, characterized in that The quantitative values ​​of the electric agricultural machinery subsidy are as follows: In the above formula, EC(t) is the quantitative value of the subsidy intensity for electric agricultural machinery in year t, S(t) is the subsidy amount that can be obtained by purchasing an electric agricultural machinery in year t, and P(t) is the average price of electric agricultural machinery in year t.

17. The device according to claim 11, characterized in that The quantitative values ​​of the impact of the agricultural emission reduction requirements on electric agricultural machinery are as follows: In the above formula, EI(t) is the quantitative value of the impact of agricultural emission reduction requirements on electric agricultural machinery in year t, and PO f (t) is the pollutant emission level of a single traditional agricultural machinery in year t, e (t) is the pollutant emission level of a single electric agricultural machinery in year t.

18. The device according to claim 17, characterized in that The pollutant emission levels of a single electric agricultural machine in year t are as follows: PO e (t)=O p (t)+O b (t) In the above formula, O p (t) is the pollutant emission from the power generation process of a single electric agricultural machine in year t, O b (t) is the pollutant emission from a single electric agricultural machine in year t taking into account battery disposal.

19. The device according to claim 11, characterized in that The quantitative values ​​of the difficulty of mastering the electric agricultural machinery use skills are as follows: In the above formula, ES(t) is the quantitative value of the difficulty of mastering the skills of using electric agricultural machinery in the tth year, k is the training duration of the use of electric agricultural machinery, h represents hours, and a, b and c represent easy, general and difficult respectively.

20. The device according to claim 11, characterized in that The amount of electric energy replaced by the electric agricultural machinery is as follows: Q=N·P·T In the above formula, Q is the amount of electric energy replaced by the electric agricultural machinery, N is the predicted value of the number of electric agricultural machinery in stock, P is the operating power of the electric agricultural machinery, and T is the annual operating hours of the electric agricultural machinery.

21. A computer device, characterized in that: include: one or more processors; The processor is configured to execute one or more programs; When the one or more programs are executed by the one or more processors, the method for predicting the electric energy substitution potential of an electric agricultural machinery as described in any one of claims 1 to 10 is implemented.

22. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed, the method for predicting the electric energy substitution potential of an electric agricultural machinery as described in any one of claims 1 to 10 is implemented.

Images