Fuel efficiency optimization method and system based on material type

Abstract

The present application relates to the field of engineering machinery control technology, specifically to a fuel efficiency optimization method and system based on material type, an image of the forward direction of the engineering machinery is obtained, the texture features and color features of the material in the image are extracted and fused to obtain fused features; the material type is determined according to the contrast and energy in the fused features, and the material wetness is determined according to the brightness standard deviation and saturation in the fused features; according to the material type and wetness, the corresponding torque coefficient, pressure compensation value, speed compensation value and oil supply correction coefficient are determined based on the pre-constructed fuel mapping database, and the engine speed and power of the engineering machinery are adjusted to realize fuel optimization. The texture features and color features of the material are obtained through visual recognition, the material type and the corresponding wetness are classified, the pre-established fuel mapping database is combined to determine different corresponding correction coefficients, and the related parameters of the fuel control system are optimized.

Description

Technical Field

[0001] This invention relates to the field of engineering machinery control technology, specifically to a fuel efficiency optimization method and system based on material type. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] The existing control systems of construction machinery rely solely on engine speed and torque to control fuel supply, which cannot distinguish between different types of materials. This results in a mismatch between power output and load (different materials have different levels of moisture and generate different loads; for example, with the same fuel supply, there may be insufficient fuel supply during rock excavation or excessive power supply during earthmoving). Summary of the Invention

[0004] To address the technical problems mentioned above, this invention provides a fuel efficiency optimization method and system based on material type. The method acquires the texture and color features of materials through visual recognition, and after fusion, classifies the material type and corresponding wettability. Combined with a pre-established fuel mapping database, the method determines the correction coefficients corresponding to different types and wettability of materials, thereby optimizing the relevant parameters of the fuel control system.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a fuel efficiency optimization method based on material type, comprising the following steps: The image of the construction machinery's forward direction is acquired, the texture and color features of the materials in the image are extracted, and then fused to obtain the fused features; The material type is determined based on the contrast and energy in the fusion characteristics, and the material wettability is determined based on the lightness standard deviation and saturation in the fusion characteristics. Based on the material type and moisture content, and using a pre-built fuel mapping database, the corresponding torque coefficient, pressure compensation value, speed compensation value, and fuel supply correction coefficient are determined, and the engine speed and power of the construction machinery are adjusted to achieve fuel optimization.

[0006] Furthermore, an image of the direction of the construction machinery's movement is acquired, and after preprocessing and target detection, an image of the area where the material is located is obtained, and the texture and color features of the image of the area where the material is located are extracted.

[0007] Furthermore, texture features are extracted, including extracting texture features through a gray-level co-occurrence matrix and quantizing the gray levels.

[0008] Furthermore, extracting texture features also includes obtaining contrast, energy, and homogeneity based on gray-level indexes, the original frequencies of co-occurrence of corresponding gray levels, and normalized probability values.

[0009] Furthermore, the extracted color features are converted from RGB space to HSV space to obtain hue, saturation, and lightness, and the standard deviation of lightness and hue distribution entropy are further determined.

[0010] Furthermore, feature fusion is performed as shown in the following equation: ; in, w t For texture weights, w c For color weights, Contrast For contrast, Energy For energy, Homogeneity Homogeneity m S The average saturation value. s V The standard deviation of lightness. H entropy Let be the hue distribution entropy.

[0011] Furthermore, the material type is determined based on the contrast and energy in the fusion characteristics, specifically: When the contrast ratio is greater than threshold A and the energy is less than threshold a, the material is stone. When the contrast is between threshold A and threshold B, and the energy is between threshold a and threshold b, the material is earth and rock. All other cases involve earthwork.

[0012] Furthermore, the material wetting degree is determined based on the brightness standard deviation and saturation in the fusion characteristics, specifically as follows: If the standard deviation of brightness is greater than the threshold X and the saturation is less than the threshold X, the material is considered dry. If the standard deviation of brightness is greater than the threshold Y and the saturation is less than the threshold y, the wettability of the material is slightly wet. If the standard deviation of brightness is greater than the threshold Z and the saturation is less than the threshold Z, the wettability of the material is moderate. In all other cases, the humidity is extremely high.

[0013] Furthermore, adjust the engine speed and power of the construction machinery as shown in the following formula: ; n target = n base + Δn ; in,n base Based on the base speed, Δn This is the speed compensation value. n target The adjusted engine speed. P req The adjusted power, β This is the fuel supply correction factor. Kt The torque coefficient, t base This is the engine's reference torque (read by the ECU). ΔP This is the pressure compensation value. Q max This refers to the maximum flow rate of the hydraulic pump in the construction machinery.

[0014] A second aspect of the present invention provides a fuel efficiency optimization system based on material type, comprising: The visual recognition module is configured to: acquire an image of the direction of travel of the construction machinery, extract the texture and color features of the materials in the image, and perform fusion processing to obtain fused features; The material classification module is configured to: determine the material type based on the contrast and energy in the fusion features, and determine the material wetness based on the brightness standard deviation and saturation in the fusion features; The fuel efficiency optimization module is configured to: determine the corresponding torque coefficient, pressure compensation value, speed compensation value and fuel supply correction coefficient based on the material type and wettability and a pre-built fuel mapping database, and adjust the engine speed and power of the construction machinery to achieve fuel optimization.

[0015] Compared with existing technologies, one or more of the above technical solutions have the following beneficial effects: 1. Traditional fuel control methods for construction machinery rely solely on speed / torque feedback, which cannot distinguish between loose dry soil and sticky wet rock. This easily leads to problems of excessive or insufficient power. Power mismatch with material type causes fuel waste or overload stalling. Overload stalling requires restarting, indirectly causing fuel waste. This solution uses a dual-channel visual system to identify the texture and color of materials. Contrast and energy in texture features are used to differentiate material hardness and classify material types. Saturation and brightness in color features are used to determine the material's moisture level. This allows subsequent control parameters to cover more complex scenarios, solving the problem that empirical parameters cannot cover complex situations.

[0016] 2. Construct a fuel mapping database based on material type (3 categories) × wettability (4 levels). After obtaining the material type and wettability level, dynamically match the torque coefficient, pressure compensation, speed compensation and fuel supply correction coefficient through the database to make the fuel supply match the load in real time and reduce the overall fuel consumption.

[0017] 3. By using visual methods for prediction, the material type and moisture content are identified by its color and texture before the bucket contacts the material. Relevant control parameters are then invoked to execute fuel control, shortening response time and resolving control delay issues. Simultaneously, this visual method relies on the overall vehicle movement performance of the construction machinery, unaffected by different drivers' operating habits, ensuring consistent and uniform final actions of the machinery.

[0018] 4. The overall solution has stronger migration capabilities. When the material type changes, it can be adapted by pre-updating the identification model and fuel mapping database, making it easier to migrate to different types of engineering machinery control systems. Attached Figure Description

[0019] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0020] Figure 1 This is a schematic diagram of the overall process of the fuel efficiency optimization method based on material type provided in one or more embodiments of the present invention; Figure 2 This is a schematic diagram of the structure of a fuel efficiency optimization system based on material type provided in one or more embodiments of the present invention. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0023] As described in the background section, existing control systems for construction machinery rely solely on engine speed and torque to control fuel supply, failing to differentiate between different material types. This leads to a mismatch between power output and load. Different material types cause variations in moisture levels, which in turn cause dynamic fluctuations in mechanical load, necessitating adjustments to engine power and fuel supply to match actual demands.

[0024] Dry materials (such as dry soil and dry sand) are loosely granular and prone to sliding during excavation, resulting in less resistance to the bucket and thus a lower load. Wet materials (such as wet clay and slurry), with their higher water content, increase the cohesion between material particles, making them adhere more easily to the bucket and significantly increasing the load. Simultaneously, the weight per unit volume increases after the material absorbs water, and the surface of wet materials may reduce the coefficient of friction between the bucket and the material; if the material is predominantly viscous (such as clay), friction may actually increase. These are all factors that cause variations in load.

[0025] Therefore, the fuel efficiency optimization method and system based on material type given in the following embodiments obtain the texture and color features of the material through visual recognition, and classify the material type and corresponding wettability after fusion. Combined with a pre-established fuel mapping database, the correction coefficients corresponding to different types and wettability of materials are determined, thereby optimizing the relevant parameters of the fuel control system.

[0026] Example 1: like Figure 1 As shown, the fuel efficiency optimization method based on material type includes the following steps: The image of the construction machinery's forward direction is acquired, the texture and color features of the materials in the image are extracted, and then fused to obtain the fused features; The material type is determined based on the contrast and energy in the fusion characteristics, and the material wettability is determined based on the lightness standard deviation and saturation in the fusion characteristics. Based on the material type and moisture content, and using a pre-built fuel mapping database, the corresponding torque coefficient, pressure compensation value, speed compensation value, and fuel supply correction coefficient are determined, and the engine speed and power of the construction machinery are adjusted to achieve fuel optimization.

[0027] The system acquires images within a certain range in front of the construction machinery. After preprocessing and target detection, it obtains images of the area where the material is located. It extracts texture and color features from the material images, performs GLCM texture analysis on the texture features, and performs HSV color space conversion on the color features. The texture analysis results and the converted color features are then used for feature fusion to make a classification decision and output the material type.

[0028] Preprocessing includes noise reduction, illumination correction, and geometric correction.

[0029] Texture features are extracted, including grayscale processing, GLCM calculation, and texture feature calculation, to obtain contrast, energy, homogeneity, and correlation.

[0030] Extract color features, including color space transformation to obtain a color histogram, and determine the distribution of hue (H), saturation (S), and lightness (V).

[0031] Texture features are extracted using the Gray-Level Co-occurrence Matrix (GLCM), including the following steps: By reducing the grayscale value, the computational complexity is reduced, specifically: I g (x, y) = [Gray(x, y) / 16] × 16, used to compress 256 levels of grayscale into 16 levels (16 × 16 GLCM matrix), where I g (x, y) represents the quantized grayscale value (0-15), G ray (x, y) represents the gray value (0-255) of the original image at coordinates (x, y); Generate the GLCM matrix (distance d=1, angle θ=0°); Extract texture features as shown in the following formula: ; ; ; in, For contrast, For energy, Homogeneity i and j This represents the gray level index of the grayscale image, with a value range of 0-15 (because 256 gray levels are compressed to 16 levels). i The grayscale level of the reference pixel; j The gray level of adjacent pixels; P(i,j) grayscale i and j The original frequency values ​​of co-occurrence; P n (i, j) This is the normalized probability value.

[0032] Normalized probability value P n (i, j) As shown in the following formula: ; in, m This is the row index of the matrix (value range: 0 to 15). n The column index of the matrix (value range: 0 to 15).

[0033] Color characteristics are converted from RGB space to HSV space: R'=R / 255, G'=G / 255, B'=B / 255; M = max(R', G', B'); m = min(R', G', B'); Δ=Mm.

[0034] Hue H: If M=R': H=60×((G'-B') / Δ); If M=G': H=60×((B'-R') / Δ+2); If M=B': H=60×((R'-G') / Δ+4); If H < 0: H = H + 360.

[0035] Saturation S: If M=0: S=0; otherwise: S=Δ / M.

[0036] Brightness V: V=M.

[0037] Mean saturation: N = total number of pixels.

[0038] Standard deviation of lightness: ; m v =Mean brightness.

[0039] Hue distribution entropy divides the hue range of 0-360° into 12 intervals (each interval being 30°), specifically: ; in, p k Let be the probability that the hue value falls within the k-th interval. p k = Number of pixels in the k-th interval / Total number of pixels (k=1, 2, ..., 12).

[0040] Feature fusion is shown in the following formula: ; Among them, w t =0.6 (texture weight), w c =0.4 (color weight) Feature normalization: all feature values ​​are scaled to [0, 1].

[0041] The classification decision is as follows: ; Where, sign is the sign function, which outputs +1 when the result inside the parentheses is greater than 0, and -1 when it is less than 0; α i For the first i The Lagrange multipliers (weights) corresponding to each support vector are obtained through optimization during training. y i For the first i The true class label (+1 or -1) of each support vector; K(F)i ，F） =exp(- c||F i -F||2） ; c This is the kernel width parameter (0.5 in this system). |F i -F| The distance is Euclidean. b This is the bias term (the intercept of the decision function), obtained during training.

[0042] The decision-making process includes the following steps: (1) Calculate similarity: Calculate input features F With each support vector F i Similarity: s i =K(F i ，F） ; (2) Weighted summation: Multiply the similarity by the label weight and then sum them, as shown in the following formula: ; in, α i For the first i The Lagrange multipliers (weights) corresponding to each support vector. y i For the first i The true class labels of the support vectors. s i Similarity; (3) Add bias terms b : S′=S+b (4) Determination of sign function: ; When classifying materials according to the same type using symbolic functions, each material type is determined using a corresponding symbolic function. For example: Earthwork classifier output f( F ) =-1 means it does not belong to earthwork; Earthwork classifier output f( F ) =-1 means it does not belong to earthwork; Stone Classifier Output f( F ) =+1 indicates that it belongs to the stone square; Final assessment: It belongs to the stone section.

[0043] When making a decision, the material is classified into a category by the "+1" output of the sign function in the three classifiers. For example, when the sign function output in the rock classifier is "+1", the material is classified into "rock"; when the sign function output in the earthwork classifier is "+1", the material is classified into "earthwork".

[0044] The material classification rules are as follows: When the contrast ratio is >0.35 (threshold A) and the energy is <0.2 (threshold a), the material is stone. When the contrast ratio is 0.25-0.35 (between threshold A and threshold B) and the energy is 0.2-0.4 (between threshold a and threshold b), the material is earth and stone. All other cases involve earthwork.

[0045] Contrast ratio reflects the hardness and edge sharpness of materials. High contrast indicates a large difference in grayscale values ​​between adjacent pixels in an image, corresponding to sharp edges and rough surfaces of materials (such as the sharp edges of rocks or the unevenness of broken rocks). Low contrast indicates a gradual change in grayscale values, corresponding to uniform particle size and smooth surfaces of materials (such as loose soil or fine sand).

[0046] In rock formations, the fracture surfaces of the rock produce a large number of sharp edges, which significantly increases the number of off-diagonal elements in the GLCM, resulting in a higher contrast value.

[0047] In the earthwork, the soil particles are small and evenly distributed, and the GLCM is concentrated near the diagonal, resulting in low contrast.

[0048] In earthwork, the mixture of gravel and soil results in a texture that is somewhere in between, thus having moderate contrast.

[0049] Energy is used to characterize the complexity of a material's structure. At low energy, GLCM elements are dispersed, indicating a chaotic and disordered texture (such as the random fracture surfaces of rock). At high energy, GLCM elements are concentrated, indicating a uniform and repetitive texture (such as the periodic particle arrangement of compacted soil).

[0050] The humidity level is determined as follows: If the standard deviation of lightness is >0.7 (threshold X) and the saturation is <0.3 (threshold x), the material is considered dry. If the standard deviation of lightness is >0.6 (threshold Y) and the saturation is <0.5 (threshold y), the material's wettability is slightly wet. The material is moderately wet if the standard deviation of lightness is >0.4 (threshold Z) and the saturation is <0.7 (threshold z). In all other cases, the humidity is extremely high.

[0051] The standard deviation of lightness reflects the uneven distribution of moisture on the surface of a material. Dry materials have rough surfaces, uniform diffuse reflection of light, and small variations in lightness (low V standard deviation). In moist but unsaturated materials, water films accumulate in depressions, forming alternating bright spots (high lightness) and dry areas (low lightness), resulting in drastic fluctuations in lightness. In heavily moist materials (such as mud), moisture completely covers the surface, creating uniform specular reflection, and the lightness tends to be consistent.

[0052] The mean saturation value (S-mean) is used to characterize the dilution effect of water on color. Water dilutes the surface color, reducing saturation. For example, the surface color of dry materials is bright (e.g., loess S≈0.6); water molecules in wet materials scatter light, diluting the color (reducing the S-value); in extreme cases, mud saturates close to 0 due to the water film covering it.

[0053] This embodiment uses 2000 labeled construction site images as a training set, with a feature dimension of 6 (3 textures + 3 colors). After training, the obtained material type and wettability are used to look up the fuel mapping database to obtain the corresponding torque coefficient, pressure compensation, speed compensation and fuel supply correction coefficient.

[0054] Data is collected through experiments or simulations to build a fuel mapping database. For example, fuel consumption test data under various operating conditions in the original state are collected; simulation parameters are adjusted through bench experiments to screen out the parameters that need to be adjusted and their approximate range. The specific values ​​of the parameters were adjusted and determined using actual vehicles.

[0055] The fuel mapping database is shown in Table 1.

[0056] Table 1 Fuel Mapping Database

[0057] Based on the obtained torque coefficient, pressure compensation, speed compensation, and fuel supply correction coefficient, the control parameters are adjusted, including speed adjustment and power adjustment.

[0058] The rotation speed is adjusted as shown in the following formula: n target = n base + Δn ; in, n base Based on the base speed, Δn This is the engine speed compensation value (obtained from the fuel mapping database).

[0059] Power adjustment is shown in the following formula: ; in, tbase This is the engine's reference torque (read by the ECU). Q max This refers to the maximum flow rate of the hydraulic pump (equipment parameter). P req The output power is the required power, and ΔP is the pressure compensation obtained based on the fuel mapping database. β This is the fuel supply correction factor obtained based on the fuel mapping database.

[0060] Traditional fuel control methods for construction machinery rely on engine speed / torque and data feedback from various sensors. They cannot distinguish the type of material being excavated and its moisture level. Therefore, all situations are configured with fixed parameters, which can easily lead to problems of excessive or insufficient power. Mismatch between power and material type can cause fuel waste or overload shutdown. Overload shutdown requires restarting, which indirectly causes fuel waste.

[0061] This solution uses dual-channel vision to identify the texture and color of materials. It uses contrast and energy in texture features to distinguish material hardness and classify material types. It uses saturation and brightness in color features to determine the moisture level of materials. This allows the control parameters queried later to cover more complex scenarios, solving the problem that fixed parameters cannot cover complex scenarios.

[0062] A fuel mapping database is constructed based on material type (3 categories) × wettability (4 levels). After obtaining the material type and wettability level, the database dynamically matches the torque coefficient, pressure compensation, speed compensation, and fuel supply correction coefficient to ensure that the fuel supply matches the load in real time and reduce overall fuel consumption.

[0063] Traditional systems rely on engine speed / torque and sensor data feedback, leading to lag in adjustments during sudden load changes (e.g., when suddenly encountering wet clay, the ECU needs to reduce engine speed before adding fuel) and a high misjudgment rate (different operator habits and additional actions can affect data interpretation). This solution, however, uses visual prediction to more quickly and accurately determine material type and moisture content. Operator habits and any additional actions will not affect the visual judgment of material type and moisture content. Before the bucket contacts the material, the system identifies the material type and moisture content through its color and texture, then calls upon relevant control parameters to execute fuel control, thus shortening response time and resolving the control delay problem.

[0064] The solution has stronger overall migration capabilities. When the material type changes, it can be adapted by pre-updating the identification model and fuel mapping database, making it easier to migrate to different types of engineering machinery control systems.

[0065] Example 2: Material type-based fuel efficiency optimization systems include: The visual recognition module is configured to: acquire an image of the direction of travel of the construction machinery, extract the texture and color features of the materials in the image, and perform fusion processing to obtain fused features; The material classification module is configured to: determine the material type based on the contrast and energy in the fusion features, and determine the material wetness based on the brightness standard deviation and saturation in the fusion features; The fuel efficiency optimization module is configured to: determine the corresponding torque coefficient, pressure compensation value, speed compensation value and fuel supply correction coefficient based on the material type and wettability and a pre-built fuel mapping database, and adjust the engine speed and power of the construction machinery to achieve fuel optimization.

[0066] By recognizing the texture and color of materials through dual visual channels, and using the contrast and energy in the texture features to distinguish the hardness of materials and classify them into different types, and using the saturation and brightness in the color features to determine the moisture level of materials, the control parameters that can be queried later can cover more complex scenarios, solving the problem that empirical parameters cannot cover complex scenarios.

[0067] A fuel mapping database is constructed based on material type (3 categories) × wettability (4 levels). After obtaining the material type and wettability level, the database dynamically matches the torque coefficient, pressure compensation, speed compensation, and fuel supply correction coefficient to ensure that the fuel supply matches the load in real time and reduce overall fuel consumption.

[0068] Traditional systems rely on engine speed / torque feedback, resulting in lag in adjustments during sudden load changes (e.g., when suddenly encountering wet clay, the ECU needs to reduce engine speed before adding fuel). This solution, however, uses visual prediction to identify the material type and moisture level by its color and texture before the bucket contacts the material. It then calls upon relevant control parameters to execute fuel control, thus shortening the response time and resolving the control delay problem.

[0069] The solution has stronger overall migration capabilities. When the material type changes, it can be adapted by pre-updating the identification model and fuel mapping database, making it easier to migrate to different types of engineering machinery control systems.

[0070] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A fuel efficiency optimization method based on material type, characterized in that, Includes the following steps: The image of the construction machinery's forward direction is acquired, the texture and color features of the materials in the image are extracted, and then fused to obtain the fused features; The material type is determined based on the contrast and energy in the fusion characteristics, and the material wettability is determined based on the lightness standard deviation and saturation in the fusion characteristics. Based on the material type and moisture content, and using a pre-built fuel mapping database, the corresponding torque coefficient, pressure compensation value, speed compensation value, and fuel supply correction coefficient are determined, and the engine speed and power of the construction machinery are adjusted to achieve fuel optimization. The adjustment of the engine speed and power of the construction machinery is as shown in the following formula: ； n target = n base + Δn ； in, n base Based on the base speed, Δn This is the speed compensation value. n target The adjusted engine speed. P req The adjusted power, β This is the fuel supply correction factor. Kt The torque coefficient, τ base The engine reference torque is read by the ECU. ΔP This is the pressure compensation value. Q max This refers to the maximum flow rate of the hydraulic pump in the construction machinery.

2. The fuel efficiency optimization method based on material type as described in claim 1, characterized in that, The image of the direction of the construction machinery's movement is acquired, preprocessed, and target detected to obtain an image of the area where the material is located. The texture and color features of the image of the area where the material is located are then extracted.

3. The fuel efficiency optimization method based on material type as described in claim 1, characterized in that, Extracting texture features includes extracting texture features through a gray-level co-occurrence matrix and quantizing the gray levels.

4. The fuel efficiency optimization method based on material type as described in claim 1, characterized in that, Extracting texture features also includes obtaining contrast, energy, and homogeneity based on gray-level indexes, the original frequencies of co-occurrence of corresponding gray levels, and normalized probability values.

5. The fuel efficiency optimization method based on material type as described in claim 1, characterized in that, The extracted color features are converted from RGB space to HSV space to obtain hue, saturation and lightness, and then the standard deviation of lightness and hue distribution entropy are determined.

6. The fuel efficiency optimization method based on material type as described in claim 1, characterized in that, Feature fusion is shown in the following formula: ； in, w t For texture weights, w c For color weights, Contrast For contrast, Energy For energy, Homogeneity Homogeneity μ S The average saturation value. σ V The standard deviation of lightness. H entropy Let be the hue distribution entropy.

7. The fuel efficiency optimization method based on material type as described in claim 1, characterized in that, The material type is determined based on the contrast and energy in the fusion characteristics, specifically: When the contrast ratio is >0.35 and the energy is <0.2, the material is stone. When the contrast ratio is between 0.25 and 0.35 and the energy is between 0.2 and 0.4, the material is earth and stone. All other cases involve earthwork.

8. The fuel efficiency optimization method based on material type as described in claim 1, characterized in that, The degree of material wettability is determined based on the standard deviation of lightness and saturation in the blending characteristics, specifically: If the standard deviation of lightness is >0.7 and the saturation is <0.3, the material is considered dry. The material has a lightness standard deviation > 0.6 and a saturation < 0.5, indicating a slightly moist condition. The material has a lightness standard deviation > 0.4 and a saturation < 0.7, indicating that its moisture content is moderate. In all other cases, the humidity is extremely high.

9. A system for implementing the fuel efficiency optimization method based on material type as described in any one of claims 1-8, characterized in that, include: The visual recognition module is configured to: acquire an image of the direction of travel of the construction machinery, extract the texture and color features of the materials in the image, and perform fusion processing to obtain fused features; The material classification module is configured to: determine the material type based on the contrast and energy in the fusion features, and determine the material wetness based on the brightness standard deviation and saturation in the fusion features; The fuel efficiency optimization module is configured to: determine the corresponding torque coefficient, pressure compensation value, speed compensation value and fuel supply correction coefficient based on the material type and wettability and a pre-built fuel mapping database, and adjust the engine speed and power of the construction machinery to achieve fuel optimization; The adjustment of the engine speed and power of the construction machinery is as shown in the following formula: ； n target = n base + Δn ； in, n base Based on the base speed, Δn This is the speed compensation value. n target The adjusted engine speed. P req The adjusted power, β This is the fuel supply correction factor. Kt The torque coefficient, τ base The engine reference torque is read by the ECU. ΔP This is the pressure compensation value. Q max This refers to the maximum flow rate of the hydraulic pump in the construction machinery.

Images