Intelligent fuel consumption prediction method and system based on big data

Abstract

The invention relates to the technical field of fuel consumption prediction, and discloses an intelligent fuel consumption prediction method and system based on big data, and the method comprises the steps: collecting a plurality of fuel consumption historical quantities of a fuel storage device, and obtaining a first fuel consumption historical quantity sequence, a second fuel consumption historical quantity sequence and a third fuel consumption historical quantity sequence; calculating a deficient fuel consumption factor based on the fluctuation change of the first fuel consumption historical amount sequence, and calculating an excess fuel consumption factor based on the fluctuation change of the third fuel consumption historical amount sequence; calculating a historical fuel consumption change metric value of the fuel storage device according to the deficient fuel consumption factor and the excess fuel consumption factor; the current planned fuel consumption amount is adjusted according to the historical fuel consumption change metric value, the predicted fuel consumption amount of the fuel storage equipment is obtained, the fuel consumption fluctuation characteristics are accurately quantified, the current planned amount is dynamically adjusted on the basis, and the prediction precision and prediction comprehensiveness of the fuel consumption amount are guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fuel consumption prediction, in particular to a fuel consumption intelligent prediction method and system based on big data. BACKGROUND

[0002] Accurate prediction of fuel consumption is crucial for energy management, cost control and operational efficiency optimization, especially in industrial production, transportation and energy supply, etc. The fuel consumption prediction of fuel storage equipment (such as oil storage tanks, gas storage, etc.) is directly related to inventory management, procurement planning and risk prevention and control.

[0003] Traditional fuel consumption prediction methods rely on statistical analysis of historical data or simple time series models, such as moving average method, exponential smoothing method, etc. Although these methods are easy to implement, they often fail to capture the complex fluctuations and nonlinear characteristics in the fuel consumption process, resulting in limited prediction accuracy. And the existing prediction methods usually only focus on the overall consumption trend, and fail to fully consider the fluctuation characteristics of fuel consumption under different working conditions, especially the sensitivity to abnormal fluctuations in consumption (such as significantly lower or higher than the planned amount). In actual operation, fuel consumption is often affected by multiple factors such as equipment status, environmental factors, production plan adjustment, etc., showing unstable fluctuation characteristics. If only based on fixed planned amount or simple historical average for prediction, it is easy to ignore the potential rules behind these fluctuations, causing the predicted results to deviate from the actual demand. SUMMARY

[0004] The present application provides a fuel consumption intelligent prediction method and system based on big data, which accurately quantifies the fluctuation characteristics of fuel consumption and dynamically adjusts the current planned amount based on this to ensure the prediction accuracy and comprehensiveness of fuel consumption.

[0005] In order to achieve the above purpose, the present application provides a fuel consumption intelligent prediction method based on big data, comprising:

[0006] Collecting a plurality of fuel consumption historical amounts of a fuel storage equipment, dividing the fuel consumption historical amounts to obtain a plurality of fuel consumption historical amount sequences, wherein the fuel consumption historical amount sequences include a first fuel consumption historical amount sequence, a second fuel consumption historical amount sequence and a third fuel consumption historical amount sequence;

[0007] Calculating the deficient fuel consumption factor of the fuel storage equipment based on the fluctuation change of the first fuel consumption historical amount sequence, and calculating the excess fuel consumption factor of the fuel storage equipment based on the fluctuation change of the third fuel consumption historical amount sequence;

[0008] calculating a historical fuel consumption variation metric value of the fuel storage device according to the deficient fuel consumption factor and the excess fuel consumption factor;

[0009] obtaining a current fuel consumption plan value of the fuel storage device, adjusting the current fuel consumption plan value according to the historical fuel consumption variation metric value to obtain a fuel consumption prediction value of the fuel storage device.

[0010] Further, when the fuel consumption history value is divided to obtain a plurality of fuel consumption history value sequences, comprising:

[0011] determining a preset fuel consumption plan value range, wherein the fuel consumption plan value range comprises a first preset fuel consumption plan value and a second preset fuel consumption plan value;

[0012] when the fuel consumption history value is less than the first preset fuel consumption plan value, the corresponding fuel consumption plan value is divided into a first fuel consumption history value sequence;

[0013] when the fuel consumption history value is greater than or equal to the first preset fuel consumption plan value and less than or equal to the second preset fuel consumption plan value, the corresponding fuel consumption plan value is divided into a second fuel consumption history value sequence;

[0014] when the fuel consumption history value is greater than the second preset fuel consumption plan value, the corresponding fuel consumption plan value is divided into a third fuel consumption history value sequence.

[0015] Further, when calculating the deficient fuel consumption factor of the fuel storage device based on the fluctuation change of the first fuel consumption history value sequence, comprising:

[0016] calculating a deficient change value of each fuel consumption history value according to each fuel consumption history value and a corresponding historical collection time;

[0017] calculating the deficient fuel consumption factor of the fuel storage device according to all the deficient change values.

[0018] Further, when calculating the deficient change value of each fuel consumption history value according to each fuel consumption history value and a corresponding historical collection time, comprising:

[0019] calculating a mean value of the first fuel consumption history value sequence as a sequence mean value;

[0020] extracting a fuel consumption history value as a standard fuel consumption history value;

[0021] calculating a first difference absolute value between the standard fuel consumption history value and the sequence mean value as a sequence change coefficient;

[0022] determining a pre-fuel consumption history amount and a post-fuel consumption history amount corresponding to the standard fuel consumption history amount based on the historical collection time;

[0023] determining a second difference absolute value of the pre-fuel consumption history amount and the standard fuel consumption history amount as a pre-amount change coefficient, and determining a third difference absolute value of the post-fuel consumption history amount and the standard fuel consumption history amount as a post-amount change coefficient;

[0024] taking a sum value of the pre-amount change coefficient and the post-amount change coefficient as an amount change coefficient;

[0025] extracting a standard historical collection time corresponding to the standard fuel consumption history amount, extracting a pre-historical collection time corresponding to the pre-fuel consumption history amount, and extracting a post-historical collection time corresponding to the post-fuel consumption history amount;

[0026] determining a first time interval of the standard historical collection time and the pre-historical collection time, and determining a second time interval of the standard historical collection time and the post-historical collection time;

[0027] calculating a deficiency change value of each fuel consumption history amount according to the sequence change coefficient, the amount change coefficient, the first time interval and the second time interval.

[0028] Further, in the calculation of the deficiency change value of each fuel consumption history amount according to the sequence change coefficient, the amount change coefficient, the first time interval and the second time interval, comprising:

[0029] calculating the deficiency change value according to the following formula:

[0030] q=s1×y1+s2×y2+s3×|t1-t2|;

[0031] wherein q is the deficiency change value, s1 is the first calculation coefficient, s2 is the second calculation coefficient, s3 is the third calculation coefficient, and s1>s2>s3, s1+s2+s3=1, y1 is the sequence change coefficient, y2 is the amount change coefficient, t1 is the first time interval, and t2 is the second time interval.

[0032] Further, in the calculation of the deficiency fuel consumption factor of the fuel storage device according to all the deficiency change values, comprising:

[0033] extracting the same deficiency change value from all the deficiency change values, and obtaining a plurality of deficiency change value sets;

[0034] counting a first deficiency change value set number of the deficiency change value sets;

[0035] extracting one missing change value from the remaining missing change value set respectively, and calculating a first missing change value sum;

[0036] calculating a missing change value mean of all same missing change values, eliminating all missing change value sets less than the missing change value mean, and counting a second missing change value set number of the remaining missing change value set;

[0037] extracting one missing change value from the remaining missing change value set respectively, and calculating a second missing change value sum;

[0038] calculating a missing fuel consumption factor of the fuel storage device according to the first missing change value set number, the second missing change value set number, the first missing change value sum and the second missing change value sum.

[0039] Further, in calculating the missing fuel consumption factor of the fuel storage device according to the first missing change value set number, the second missing change value set number, the first missing change value sum and the second missing change value sum, comprising:

[0040]

[0041] wherein p1 is the missing fuel consumption factor of the fuel storage device, g1 is the first missing change value set number, g2 is the second missing change value set number, h1 is the first missing change value sum, and h2 is the second missing change value sum.

[0042] Further, in calculating the historical fuel consumption change measure value of the fuel storage device according to the missing fuel consumption factor and the excess fuel consumption factor, comprising:

[0043] calculating the historical fuel consumption change measure value of the fuel storage device according to the following formula:

[0044]

[0045] wherein k is the historical fuel consumption change measure value of the fuel storage device, p1 is the missing fuel consumption factor, p2 is the excess fuel consumption factor, m1 is the number of fuel consumption historical quantities in the first fuel consumption historical quantity sequence, m2 is the number of fuel consumption historical quantities in the second fuel consumption historical quantity sequence, and m3 is the number of fuel consumption historical quantities in the third fuel consumption historical quantity sequence.

[0046] Further, in adjusting the current fuel consumption planning quantity according to the historical fuel consumption change measure value to obtain the fuel consumption prediction quantity of the fuel storage device, comprising:

[0047] pre-set a first pre-set historical fuel consumption change measure value and a second pre-set historical fuel consumption change measure value;

[0048] pre-set a first pre-set adjustment value, a second pre-set adjustment value and a third pre-set adjustment value;

[0049] when the historical fuel consumption change measure value is less than the first pre-set historical fuel consumption change measure value, then a first product value of the first pre-set adjustment value and the current fuel consumption plan quantity is calculated as the fuel consumption prediction of the fuel storage device;

[0050] when the historical fuel consumption change measure value is greater than or equal to the first pre-set historical fuel consumption change measure value and less than the second pre-set historical fuel consumption change measure value, then a second product value of the second pre-set adjustment value and the current fuel consumption plan quantity is calculated as the fuel consumption prediction of the fuel storage device;

[0051] when the historical fuel consumption change measure value is greater than or equal to the second pre-set historical fuel consumption change measure value, then a third product value of the third pre-set adjustment value and the current fuel consumption plan quantity is calculated as the fuel consumption prediction of the fuel storage device.

[0052] In order to achieve the above-mentioned purpose, the present application also provides a big data-based intelligent fuel consumption prediction system, comprising:

[0053] a sequence construction module, configured to collect a plurality of fuel consumption historical quantities of a fuel storage device, divide the fuel consumption historical quantities to obtain a plurality of fuel consumption historical quantity sequences, wherein the fuel consumption historical quantity sequences comprise a first fuel consumption historical quantity sequence, a second fuel consumption historical quantity sequence and a third fuel consumption historical quantity sequence;

[0054] a first calculation module, configured to calculate a deficient fuel consumption factor of the fuel storage device based on fluctuation changes of the first fuel consumption historical quantity sequence, and calculate an excessive fuel consumption factor of the fuel storage device based on fluctuation changes of the third fuel consumption historical quantity sequence;

[0055] a second calculation module, configured to calculate a historical fuel consumption change measure value of the fuel storage device according to the deficient fuel consumption factor and the excessive fuel consumption factor;

[0056] a consumption prediction module, configured to obtain a current fuel consumption plan quantity of the fuel storage device, and adjust the current fuel consumption plan quantity according to the historical fuel consumption change measure value to obtain a fuel consumption prediction of the fuel storage device.

[0057] Compared with the prior art, the present application has the advantages that:

[0058] The application discloses a fuel consumption intelligent prediction method and system based on big data, collects a plurality of fuel consumption historical quantities of a fuel storage device, obtains a first fuel consumption historical quantity sequence, a second fuel consumption historical quantity sequence and a third fuel consumption historical quantity sequence, calculates a deficient fuel consumption factor based on fluctuation changes of the first fuel consumption historical quantity sequence, calculates an excessive fuel consumption factor based on fluctuation changes of the third fuel consumption historical quantity sequence, calculates a historical fuel consumption change degree value of the fuel storage device according to the deficient fuel consumption factor and the excessive fuel consumption factor, adjusts a current fuel consumption plan quantity according to the historical fuel consumption change degree value, obtains a fuel consumption prediction quantity of the fuel storage device, accurately quantifies fuel consumption fluctuation characteristics, and dynamically adjusts the current plan quantity based on the fuel consumption fluctuation characteristics, so that the prediction accuracy and prediction comprehensiveness of the fuel consumption quantity are ensured. BRIEF DESCRIPTION OF DRAWINGS

[0059] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not intended to limit the scope of the application. Furthermore, the same reference numerals are intended to denote the same components throughout the accompanying drawings. In the drawings:

[0060] Figure 1 A flowchart of a fuel consumption intelligent prediction method based on big data in an embodiment of the application is shown;

[0061] Figure 2 A structure diagram of a fuel consumption intelligent prediction system based on big data in an embodiment of the application is shown. DETAILED DESCRIPTION

[0062] The specific embodiments of the application will be further described in detail below with reference to the accompanying drawings and embodiments. The following embodiments are used to illustrate the application, but are not used to limit the scope of the application.

[0063] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0064] The terms "first", "second", "third", etc. are used only for descriptive purposes and do not connote or imply relative importance or an ordering between or among the indicated technical features. Thus, a feature defined with "first", "second", etc. can include one or more of the features implicitly or explicitly.

[0065] In the description of the present application, it should be noted that unless specifically stated and limited otherwise, the terms "mounting", "connection", "connecting" should be understood broadly, for example, can be fixed connection, can also be detachable connection, or integral connection, can be mechanical connection, can also be electrical connection, can be direct connection, can also be indirect connection through intermediate medium, can be internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0066] The following is a description of the preferred embodiments of the present application in conjunction with the accompanying drawings.

[0067] As shown in Figure 1 The embodiments of the present application disclose a fuel consumption intelligent prediction method based on big data, comprising:

[0068] S110: Collecting a plurality of fuel consumption historical amounts of a fuel storage device, dividing the fuel consumption historical amounts to obtain a plurality of fuel consumption historical amount sequences, wherein the fuel consumption historical amount sequences include a first fuel consumption historical amount sequence, a second fuel consumption historical amount sequence and a third fuel consumption historical amount sequence;

[0069] In some embodiments of the present application, when the fuel consumption historical amounts are divided to obtain a plurality of fuel consumption historical amount sequences, it includes:

[0070] Determining a preset fuel consumption plan amount range, wherein the fuel consumption plan amount range includes a first preset fuel consumption plan amount and a second preset fuel consumption plan amount;

[0071] When the fuel consumption historical amount is less than the first preset fuel consumption plan amount, the corresponding fuel consumption plan amount is divided into the first fuel consumption historical amount sequence;

[0072] When the fuel consumption historical amount is greater than or equal to the first preset fuel consumption plan amount and less than or equal to the second preset fuel consumption plan amount, the corresponding fuel consumption plan amount is divided into the second fuel consumption historical amount sequence;

[0073] When the fuel consumption historical amount is greater than the second preset fuel consumption plan amount, the corresponding fuel consumption plan amount is divided into the third fuel consumption historical amount sequence.

[0074] In this embodiment, the preset fuel consumption plan amount range is [8 tons, 13 tons], and the actual demand can be adaptively adjusted.

[0075] The beneficial effects of the above technical solution are that the fuel consumption history amount is divided into the corresponding fuel consumption history amount sequence according to different ranges, which can more finely classify and analyze the fuel consumption. It is helpful to take different analysis and processing strategies for different ranges of fuel consumption, thereby improving the accuracy and reliability of the prediction.

[0076] S120: calculating a deficient fuel consumption factor of the fuel storage device based on the fluctuation change of the first fuel consumption history amount sequence, and calculating an excess fuel consumption factor of the fuel storage device based on the fluctuation change of the third fuel consumption history amount sequence;

[0077] In some embodiments of the present application, when calculating the deficient fuel consumption factor of the fuel storage device based on the fluctuation change of the first fuel consumption history amount sequence, it includes:

[0078] According to each fuel consumption history amount and the corresponding historical collection time, calculating a deficient change value of each fuel consumption history amount;

[0079] According to all the deficient change values, calculating the deficient fuel consumption factor of the fuel storage device.

[0080] In some embodiments of the present application, when calculating the deficient change value of each fuel consumption history amount according to each fuel consumption history amount and the corresponding historical collection time, it includes:

[0081] Calculating the mean value of the first fuel consumption history amount sequence as a sequence mean value;

[0082] Extracting a fuel consumption history amount as a standard fuel consumption history amount;

[0083] Calculating the first difference absolute value between the standard fuel consumption history amount and the sequence mean value as a sequence change coefficient;

[0084] Based on the historical collection time, determining the previous fuel consumption history amount and the subsequent fuel consumption history amount corresponding to the standard fuel consumption history amount;

[0085] Determining the second difference absolute value between the previous fuel consumption history amount and the standard fuel consumption history amount as a previous amount change coefficient, and determining the third difference absolute value between the subsequent fuel consumption history amount and the standard fuel consumption history amount as a subsequent amount change coefficient;

[0086] The sum of the front quantity change coefficient and the rear quantity change coefficient is taken as a quantity change coefficient;

[0087] A standard historical acquisition time corresponding to the standard fuel consumption history quantity is extracted, a front historical acquisition time corresponding to the front fuel consumption history quantity is extracted, and a rear historical acquisition time corresponding to the rear fuel consumption history quantity is extracted;

[0088] A first time interval between the standard historical acquisition time and the front historical acquisition time is determined, and a second time interval between the standard historical acquisition time and the rear historical acquisition time is determined;

[0089] The deficiency change value of each fuel consumption history quantity is calculated according to the sequence change coefficient, the quantity change coefficient, the first time interval and the second time interval.

[0090] In the embodiment, each fuel consumption history quantity corresponds to a different historical acquisition time.

[0091] In the embodiment, the front fuel consumption history quantity and the rear fuel consumption history quantity can be determined according to the historical acquisition time. For example, the historical acquisition times are the past 5th second, the past 10th second and the past 15th second, the fuel consumption history quantity corresponding to the past 10th second is the standard fuel consumption history quantity, the fuel consumption history quantity corresponding to the past 5th second is the front fuel consumption history quantity, and the fuel consumption history quantity corresponding to the past 15th second is the rear fuel consumption history quantity. It should be noted that, in order to avoid errors, when the standard fuel consumption history quantity is selected, the fuel consumption history quantities corresponding to the first historical acquisition time and the last historical acquisition time are not selected.

[0092] The beneficial effects of the above technical solution are as follows: by calculating the deficiency change value of each fuel consumption history quantity in detail, the fluctuation characteristics of fuel consumption can be captured more accurately, which provides a reliable basis for subsequent calculation of the deficiency fuel consumption factor, and helps to improve the evaluation accuracy of the fuel consumption of the fuel storage device. The deficiency fuel consumption factor is calculated based on the fluctuation change of the first fuel consumption history quantity sequence, which can effectively reflect the characteristics of the fuel storage device in the case of relatively insufficient fuel consumption, and provides an important reference for subsequent fuel consumption prediction.

[0093] In some embodiments of the present application, when the deficiency change value of each fuel consumption history quantity is calculated according to the sequence change coefficient, the quantity change coefficient, the first time interval and the second time interval, the following is included:

[0094] The deficiency change value is calculated according to the following formula:

[0095] q=s1×y1+s2×y2+s3×|t1-t2|;

[0096] Wherein, q is the missing change value, s1 is the first calculation coefficient, s2 is the second calculation coefficient, s3 is the third calculation coefficient, and s1>s2>s3, s1+s2+s3=1, y1 is the sequence change coefficient, y2 is the quantity change coefficient, t1 is the first time interval, and t2 is the second time interval.

[0097] In some embodiments of the present application, when calculating the missing fuel consumption factor of the fuel storage device according to all missing change values, the following steps are included:

[0098] Extracting the same missing change values from all missing change values and obtaining a plurality of missing change value sets;

[0099] Counting the number of first missing change value sets of the missing change value sets;

[0100] Extracting one missing change value from each of all missing change value sets and calculating the first missing change value sum;

[0101] Calculating the missing change value mean of all the same missing change values, eliminating all missing change value sets less than the missing change value mean, and counting the number of second missing change value sets of the remaining missing change value sets;

[0102] Extracting one missing change value from each of the remaining missing change value sets and calculating the second missing change value sum;

[0103] Calculating the missing fuel consumption factor of the fuel storage device according to the number of first missing change value sets, the number of second missing change value sets, the first missing change value sum, and the second missing change value sum.

[0104] In the present embodiment, if the missing change values corresponding to the values are v1, v2, v3, v3, v4, v4, v4, v5, v6, v6, the same missing change values are v3, v3, v4, v4, v4, v6, v6, and the missing change value sets obtained are {v3, v3}, {v4, v4, v4}, and {v6, v6}.

[0105] The beneficial effects of the above technical solution are: through classification and statistical processing of missing change values, the missing fuel consumption factor of the fuel storage device can be accurately calculated. Various possible fuel consumption fluctuations are fully considered, and errors that may be caused by single or simple calculation methods are avoided, thereby improving the accuracy and reliability of the missing fuel consumption factor calculation and laying a solid foundation for more accurate subsequent fuel consumption prediction.

[0106] In some embodiments of the present application, when calculating the excess fuel consumption factor of the fuel storage device based on the fluctuation change of the third fuel consumption history quantity sequence, the excess change value of each fuel consumption history quantity is also calculated according to each fuel consumption history quantity and the corresponding historical collection time. The specific process is similar to calculating the lack change value. First, the mean value of the third fuel consumption history quantity sequence is calculated as the sequence mean value, and the standard fuel consumption history quantity is selected. The first difference absolute value between the standard fuel consumption history quantity and the sequence mean value is calculated as the sequence change coefficient. Then, the front and rear fuel consumption history quantities are determined based on the historical collection time, and the difference absolute values between the standard fuel consumption history quantity and the front and rear fuel consumption history quantities are calculated as the front and rear quantity change coefficients. The sum of the two is taken as the quantity change coefficient. At the same time, the corresponding historical collection time is extracted to determine the time interval between the standard historical collection time and the front and rear historical collection time. Finally, the excess change value of each fuel consumption history quantity is calculated according to the sequence change coefficient, the quantity change coefficient, the first time interval and the second time interval, according to the formula similar to calculating the lack change value. However, the calculation coefficient in the formula is different. When calculating the excess fuel consumption factor of the fuel storage device based on all the excess change values, a method similar to calculating the lack fuel consumption factor is also used. The same excess change value is extracted from all the excess change values to obtain a plurality of excess change value sets, and the first excess change value set quantity of the excess change value set is counted. One excess change value is extracted from each of the excess change value sets, and the first excess change value sum is calculated. The mean value of all the same excess change values is calculated, and all the excess change value sets less than the mean value are removed. The second excess change value set quantity of the remaining excess change value sets is counted. One excess change value is extracted from each of the remaining excess change value sets, and the second excess change value sum is calculated. The excess fuel consumption factor of the fuel storage device is calculated according to the first excess change value set quantity, the second excess change value set quantity, the first excess change value sum and the second excess change value sum. The specific determination process is not repeated here, and can be adaptively obtained according to actual needs.

[0107] The beneficial effects of the above technical solutions are: effectively reflecting the characteristics of the fuel storage device under the condition of relative excess fuel consumption. Combined with the calculation of the lack fuel consumption factor, different situations of fuel consumption are considered comprehensively, which provides an important basis for subsequent adjustment of the current fuel consumption plan quantity according to the historical fuel consumption change degree measurement value, and further improves the accuracy and reliability of the entire fuel consumption intelligent prediction method.

[0108] In some embodiments of the present application, when calculating the excess fuel consumption factor of the fuel storage device based on the fluctuation change of the third fuel consumption history quantity sequence, the excess change value of each fuel consumption history quantity is also calculated according to each fuel consumption history quantity and the corresponding historical collection time. The specific process is similar to calculating the lack change value. First, the mean value of the third fuel consumption history quantity sequence is calculated as the sequence mean value, and the standard fuel consumption history quantity is selected. The first difference absolute value between the standard fuel consumption history quantity and the sequence mean value is calculated as the sequence change coefficient. Then, the front and rear fuel consumption history quantities are determined based on the historical collection time, and the difference absolute values between the standard fuel consumption history quantity and the front and rear fuel consumption history quantities are calculated as the front and rear quantity change coefficients. The sum of the two is taken as the quantity change coefficient. At the same time, the corresponding historical collection time is extracted to determine the time interval between the standard historical collection time and the front and rear historical collection time. Finally, the excess change value of each fuel consumption history quantity is calculated according to the sequence change coefficient, the quantity change coefficient, the first time interval and the second time interval, according to the formula similar to calculating the lack change value. However, the calculation coefficient in the formula is different. When calculating the excess fuel consumption factor of the fuel storage device based on all the excess change values, a method similar to calculating the lack fuel consumption factor is also used. The same excess change value is extracted from all the excess change values to obtain a plurality of excess change value sets, and the first excess change value set quantity of the excess change value set is counted. One excess change value is extracted from each of the excess change value sets, and the first excess change value sum is calculated. The mean value of all the same excess change values is calculated, and all the excess change value sets less than the mean value are removed. The second excess change value set quantity of the remaining excess change value sets is counted. One excess change value is extracted from each of the remaining excess change value sets, and the second excess change value sum is calculated. The excess fuel consumption factor of the fuel storage device is calculated according to the first excess change value set quantity, the second excess change value set quantity, the first excess change value sum and the second excess change value sum. The specific determination process is not repeated here, and can be adaptively obtained according to actual needs.

[0109]

[0110] wherein p1 is a deficient fuel consumption factor of the fuel storage device, g1 is a first deficient change value set quantity, g2 is a second deficient change value set quantity, h1 is a first deficient change value sum, and h2 is a second deficient change value sum.

[0111] S130: calculating a historical fuel consumption change metric value of the fuel storage device according to the deficient fuel consumption factor and the excessive fuel consumption factor;

[0112] In some embodiments of the present application, when calculating the historical fuel consumption change metric value of the fuel storage device according to the deficient fuel consumption factor and the excessive fuel consumption factor, it comprises:

[0113] The historical fuel consumption change metric value of the fuel storage device is calculated according to the following formula:

[0114]

[0115] wherein k is a historical fuel consumption change metric value of the fuel storage device, p1 is a deficient fuel consumption factor, p2 is an excessive fuel consumption factor, m1 is a quantity of fuel consumption historical quantities in a first fuel consumption historical quantity sequence, m2 is a quantity of fuel consumption historical quantities in a second fuel consumption historical quantity sequence, and m3 is a quantity of fuel consumption historical quantities in a third fuel consumption historical quantity sequence.

[0116] The beneficial effects of the above technical solution are: by combining the deficient fuel consumption factor and the excessive fuel consumption factor, and comprehensively considering the quantities of historical quantities in different fuel consumption historical quantity sequences, the historical fuel consumption change of the fuel storage device can be accurately quantified. The one-sidedness that may be caused by a single factor or simple quantity statistics is avoided, and the historical fluctuation characteristics of fuel consumption are more comprehensively and accurately reflected, which provides a key and reliable basis for subsequent fuel consumption prediction based on historical data, and helps to improve the accuracy and effectiveness of the entire prediction process.

[0117] S140: obtaining a current fuel consumption planned quantity of the fuel storage device, adjusting the current fuel consumption planned quantity according to the historical fuel consumption change metric value to obtain a fuel consumption prediction quantity of the fuel storage device.

[0118] In the present embodiment, the current fuel consumption planned quantity herein refers to a fuel consumption quantity pre-set according to production demand, equipment operating condition and other factors.

[0119] In some embodiments of the present application, when the current fuel consumption plan is adjusted according to the historical fuel consumption change metric value, the fuel consumption prediction of the fuel storage device is obtained, comprising:

[0120] The first preset historical fuel consumption change metric value and the second preset historical fuel consumption change metric value are preset;

[0121] The first preset adjustment value, the second preset adjustment value and the third preset adjustment value are preset;

[0122] When the historical fuel consumption change metric value is less than the first preset historical fuel consumption change metric value, a first product value of the first preset adjustment value and the current fuel consumption plan is calculated as the fuel consumption prediction of the fuel storage device;

[0123] When the historical fuel consumption change metric value is greater than or equal to the first preset historical fuel consumption change metric value and less than the second preset historical fuel consumption change metric value, a second product value of the second preset adjustment value and the current fuel consumption plan is calculated as the fuel consumption prediction of the fuel storage device;

[0124] When the historical fuel consumption change metric value is greater than or equal to the second preset historical fuel consumption change metric value, a third product value of the third preset adjustment value and the current fuel consumption plan is calculated as the fuel consumption prediction of the fuel storage device.

[0125] In the embodiment, the first preset historical fuel consumption change metric value is preferably 3.5, and the second preset historical fuel consumption change metric value is preferably 6.5, and can be adaptively adjusted according to actual needs.

[0126] In the embodiment, the first preset adjustment value is preferably 0.85, the second preset adjustment value is preferably 1.15, and the third preset adjustment value is preferably 1.25, and can be adaptively adjusted according to actual needs.

[0127] The beneficial effects of the above technical solution are: since the historical fuel consumption change metric value comprehensively reflects the characteristics of the fuel storage device under different fuel consumption conditions and the historical fluctuation characteristics, adjusting the current fuel consumption plan quantity according to the historical fuel consumption change metric value can make the obtained fuel consumption prediction quantity more in line with the actual situation. If the historical fuel consumption change metric value shows that the fuel storage device often has excess fuel consumption in the past period of time, the prediction quantity can be appropriately reduced when adjusting the current fuel consumption plan quantity, so as to avoid unnecessary fuel waste; on the contrary, if the historical data shows that the fuel consumption is often insufficient, the prediction quantity can be appropriately increased to ensure the normal operation of the device. Through such an adjustment process, the final fuel consumption prediction quantity can provide more accurate and valuable reference for fuel management, production arrangement and the like, further improving the practicability and reliability of the entire fuel consumption quantity intelligent prediction method.

[0128] In order to further illustrate the technical idea of the present application, the technical solution of the present application will be described in combination with specific application scenarios.

[0129] Correspondingly, as shown in Figure 2 The present application also provides a fuel consumption quantity intelligent prediction system based on big data, which comprises:

[0130] A sequence construction module is configured to collect a plurality of fuel consumption historical quantities of a fuel storage device, divide the fuel consumption historical quantities, and obtain a plurality of fuel consumption historical quantity sequences, wherein the fuel consumption historical quantity sequences comprise a first fuel consumption historical quantity sequence, a second fuel consumption historical quantity sequence and a third fuel consumption historical quantity sequence.

[0131] A first calculation module is configured to calculate a deficient fuel consumption factor of the fuel storage device based on fluctuation changes of the first fuel consumption historical quantity sequence, and calculate an excess fuel consumption factor of the fuel storage device based on fluctuation changes of the third fuel consumption historical quantity sequence.

[0132] A second calculation module is configured to calculate a historical fuel consumption change metric value of the fuel storage device according to the deficient fuel consumption factor and the excess fuel consumption factor.

[0133] A consumption prediction module is configured to obtain a current fuel consumption plan quantity of the fuel storage device, adjust the current fuel consumption plan quantity according to the historical fuel consumption change metric value, and obtain a fuel consumption prediction quantity of the fuel storage device.

[0134] In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0135] Although the present application has been described with reference to the above embodiments, various modifications can be made to the application and equivalents thereof without departing from the scope of the application. In particular, features of the disclosed embodiments can be used in any combination without departing from the scope of the application, and the description of the various embodiments does not imply that the combinations of features are not combinable unless the description states that a combination is not possible. The description of the various embodiments is not meant to limit the application but merely to provide examples of the application.

[0136] It is to be understood that the above description is merely a preferred example of the application and is not intended to limit the application, and that modifications can be made by those ordinarily skilled in the art with the content of the above without departing from the scope of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall be included in the scope of the protection of the application.

Claims

1. A method for intelligent prediction of fuel consumption based on big data, characterized in that, include: Collect multiple historical fuel consumption data from fuel storage devices, divide the historical fuel consumption data into multiple historical fuel consumption data sequences, wherein the historical fuel consumption data sequences include a first historical fuel consumption data sequence, a second historical fuel consumption data sequence, and a third historical fuel consumption data sequence; The fuel shortage factor of the fuel storage device is calculated based on the fluctuation of the first fuel consumption history sequence, and the fuel surplus factor of the fuel storage device is calculated based on the fluctuation of the third fuel consumption history sequence. Calculate the historical fuel consumption change metric of the fuel storage device based on the insufficient fuel consumption factor and the excess fuel consumption factor; Obtain the current planned fuel consumption of the fuel storage device, and adjust the current planned fuel consumption based on the historical fuel consumption change metric to obtain the predicted fuel consumption of the fuel storage device.

2. The intelligent fuel consumption prediction method based on big data according to claim 1, characterized in that, When dividing the historical fuel consumption data to obtain multiple historical fuel consumption sequences, the following are included: A preset fuel consumption plan range is determined, wherein the fuel consumption plan range includes a first preset fuel consumption plan and a second preset fuel consumption plan; When the historical fuel consumption is less than the first preset fuel consumption plan, the corresponding fuel consumption plan is assigned to the first historical fuel consumption sequence. When the historical fuel consumption is greater than or equal to the first preset fuel consumption plan and less than or equal to the second preset fuel consumption plan, the corresponding fuel consumption plan is assigned to the second historical fuel consumption sequence. When the historical fuel consumption amount is greater than the second preset fuel consumption plan amount, the corresponding fuel consumption plan amount is assigned to the third historical fuel consumption amount sequence.

3. The intelligent fuel consumption prediction method based on big data according to claim 1, characterized in that, When calculating the fuel shortage consumption factor of the fuel storage device based on the fluctuations of the first fuel consumption history sequence, the following steps are included: Calculate the deficit change value of each historical fuel consumption based on each historical fuel consumption amount and the corresponding historical data collection time. The fuel shortage consumption factor of the fuel storage device is calculated based on all the shortage variation values.

4. The intelligent fuel consumption prediction method based on big data according to claim 3, characterized in that, When calculating the deficit change value for each historical fuel consumption based on each historical fuel consumption amount and the corresponding historical data collection time, the following is included: Calculate the mean of the first historical fuel consumption sequence as the sequence mean; Extract a historical fuel consumption value as the standard historical fuel consumption value; Calculate the absolute value of the first difference between the historical standard fuel consumption and the mean of the series, and use it as the series variation coefficient; Based on the historical data collection time, determine the previous fuel consumption history and the subsequent fuel consumption history corresponding to the standard fuel consumption history. The absolute value of the second difference between the previous fuel consumption history and the standard fuel consumption history is determined as the previous amount change coefficient, and the absolute value of the third difference between the subsequent fuel consumption history and the standard fuel consumption history is determined as the subsequent amount change coefficient. The sum of the coefficient of change of the preceding quantity and the coefficient of change of the following quantity is taken as the coefficient of change of quantity; Extract the standard historical acquisition time corresponding to the standard fuel consumption history, extract the previous historical acquisition time corresponding to the previous fuel consumption history, and extract the subsequent historical acquisition time corresponding to the subsequent fuel consumption history. Determine the first time interval between the standard historical acquisition time and the previous historical acquisition time, and determine the second time interval between the standard historical acquisition time and the subsequent historical acquisition time; The deficit change value for each historical fuel consumption is calculated based on the sequence change coefficient, the quantity change coefficient, the first time interval, and the second time interval.

5. The intelligent fuel consumption prediction method based on big data according to claim 4, characterized in that, Calculating the deficit change value for each historical fuel consumption amount based on the sequence change coefficient, the quantity change coefficient, the first time interval, and the second time interval includes: The deficit change value is calculated using the following formula: q=s1×y1+s2×y2+s3×|t1-t2|; Where q is the missing change value, s1 is the first calculation coefficient, s2 is the second calculation coefficient, s3 is the third calculation coefficient, and s1 > s2 > s3, s1 + s2 + s3 = 1, y1 is the sequence change coefficient, y2 is the quantity change coefficient, t1 is the first time interval, and t2 is the second time interval.

6. The intelligent fuel consumption prediction method based on big data according to claim 3, characterized in that, When calculating the shortage fuel consumption factor of the fuel storage device based on all shortage change values, the following is included: Extract the same missing change value from all missing change values ​​and obtain multiple sets of missing change values; The number of the first set of missing change values ​​in the statistical set of missing change values; Extract one missing change value from each of the sets of missing change values, and calculate the first missing change value and the value. Calculate the mean of all the same missing change values, remove all sets of missing change values ​​that are less than the mean of the missing change values, and count the number of the second set of missing change values ​​in the remaining set of missing change values. Extract one missing change value from the remaining set of missing change values, and calculate the second missing change value and the value; The fuel shortage factor of the fuel storage device is calculated based on the number of the first set of shortage change values, the number of the second set of shortage change values, the sum of the first and second sets of shortage change values.

7. The intelligent fuel consumption prediction method based on big data according to claim 6, characterized in that, When calculating the fuel shortage consumption factor of the fuel storage device based on the quantity of the first set of shortage change values, the quantity of the second set of shortage change values, the sum of the first and second sets of shortage change values, the following steps are included: Where p1 is the fuel consumption factor of the fuel storage device, g1 is the number of the first set of deficit change values, g2 is the number of the second set of deficit change values, h1 is the sum of the first deficit change values, and h2 is the sum of the second deficit change values.

8. The intelligent fuel consumption prediction method based on big data according to claim 1, characterized in that, When calculating the historical fuel consumption change metric of the fuel storage device based on the insufficient fuel consumption factor and the excess fuel consumption factor, the following is included: The historical fuel consumption variation metric of the fuel storage device is calculated using the following formula: Where k is the historical fuel consumption change measure of the fuel storage device, p1 is the fuel shortage factor, p2 is the fuel surplus factor, m1 is the number of historical fuel consumption values ​​in the first fuel consumption history sequence, m2 is the number of historical fuel consumption values ​​in the second fuel consumption history sequence, and m3 is the number of historical fuel consumption values ​​in the third fuel consumption history sequence.

9. The intelligent fuel consumption prediction method based on big data according to claim 1, characterized in that, When adjusting the current planned fuel consumption based on the historical fuel consumption change metric to obtain the predicted fuel consumption of the fuel storage device, the following steps are included: Pre-set a first preset historical fuel consumption change metric value and a second preset historical fuel consumption change metric value; Preset the first preset adjustment value, the second preset adjustment value, and the third preset adjustment value; When the historical fuel consumption change metric is less than the first preset historical fuel consumption change metric, the first product of the first preset adjustment value and the current fuel consumption plan is calculated as the fuel consumption prediction of the fuel storage device. When the historical fuel consumption change metric is greater than or equal to the first preset historical fuel consumption change metric and less than the second preset historical fuel consumption change metric, the second product of the second preset adjustment value and the current fuel consumption plan is calculated as the fuel consumption prediction of the fuel storage device. When the historical fuel consumption change metric is greater than or equal to the second preset historical fuel consumption change metric, the third product of the third preset adjustment value and the current fuel consumption plan is calculated as the fuel consumption prediction of the fuel storage device.

10. A fuel consumption intelligent prediction system based on big data, applied to the fuel consumption intelligent prediction method based on big data as described in any one of claims 1-9, characterized in that, include: A sequence construction module is used to collect multiple historical fuel consumption data from a fuel storage device, divide the historical fuel consumption data into multiple historical fuel consumption data sequences, wherein the historical fuel consumption data sequences include a first historical fuel consumption data sequence, a second historical fuel consumption data sequence, and a third historical fuel consumption data sequence. The first calculation module is used to calculate the fuel shortage factor of the fuel storage device based on the fluctuation changes of the first fuel consumption history sequence, and to calculate the fuel surplus factor of the fuel storage device based on the fluctuation changes of the third fuel consumption history sequence. The second calculation module is used to calculate the historical fuel consumption change metric of the fuel storage device based on the fuel shortage consumption factor and the fuel surplus consumption factor. The consumption prediction module is used to obtain the current planned fuel consumption of the fuel storage device, adjust the current planned fuel consumption based on the historical fuel consumption change metric, and obtain the predicted fuel consumption of the fuel storage device.

Images