Port coal transfer planning optimization method based on artificial intelligence

Abstract

The invention relates to the technical field of transportation planning of an intelligent port, in particular to a port coal transfer planning optimization method based on artificial intelligence, which comprises the following steps: S1, acquiring a coal loading image and a coal loading weight; s2, inputting a coal loading image of a transport vehicle into the coal type identification model to obtain a coal type prediction result; s3, inputting a coal loading image of the transport vehicle into the loading volume prediction model to obtain a coal loading volume prediction result; s4, selecting an optimal unloading area based on the coal loading weight, the coal type prediction result and the coal loading volume prediction result in combination with the coal stacking real-time state of the coal storage yard; and S5, generating transfer planning information based on the position information of the optimal unloading area. According to the invention, the uniformity and safety of stacking of the coal in the storage yard are obviously enhanced, the space utilization rate of the port coal storage yard is greatly improved, and intelligent, efficient and safe management of the whole process of port coal transfer is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of transportation planning for smart ports, and in particular to an artificial intelligence-based port coal transshipment planning optimization method. Background Art

[0002] In the global energy trade and logistics sector, ports, as crucial transit hubs for bulk cargo like coal, shoulder the crucial task of transferring coal from transport vessels and other vehicles to coal storage yards for storage. Within the entire coal transshipment process at ports, the unloading of coal from the port yard to the coal storage yard is crucial.

[0003] Coal types primarily include anthracite, coking coal, fat coal, lean coal, lignite, long flame coal, and lean coal. Because different types of coal differ in physical and chemical properties, as well as their subsequent uses, port unloading requires strict separation into designated areas to prevent mixing of different types. This mixing not only increases the cost and difficulty of subsequent coal sorting and processing, but can also affect coal quality and sales price, and even adversely impact subsequent processing and utilization.

[0004] However, the existing coal transshipment and unloading processes at ports face numerous pressing challenges, severely hindering the efficiency and quality of port coal transshipment: 1) Currently, some ports still rely on traditional manual judgment to determine coal type. This judgment is influenced by various factors, including personal experience, subjective perception, and the working environment, and is prone to errors. For example, in low-light conditions or when the coal's appearance is unclear, workers may struggle to accurately distinguish between different types of coal, resulting in coal being mistakenly unloaded into non-designated areas. Furthermore, manual judgment is relatively slow, and faced with a large number of transport vehicles and frequent coal unloading tasks, it is impossible to identify coal types in a timely and efficient manner, thus affecting the efficiency of the entire unloading process. While some ports have introduced simple automated equipment, these devices are relatively limited in functionality and can only detect certain surface features of the coal. They are unable to comprehensively and accurately identify the coal type, making them difficult to meet the demand for precise coal type identification in actual production. 2) When multiple unloading areas are available for a certain type of coal, existing technologies struggle to effectively and rationally select the optimal area for unloading. When selecting an unloading area, multiple factors must be considered, including available space, the stability of the coal stack, and safety. However, existing port management systems often lack the comprehensive analysis and decision-making capabilities to analyze these factors. Some ports randomly assign unloading tasks based solely on the availability of unloading areas, without fully considering the uniformity and stability of coal stacking. This can lead to excessive coal accumulation in some unloading areas, increasing stacking instability and safety risks. Other unloading areas may remain underutilized for extended periods, resulting in a waste of space resources. Summary of the Invention

[0005] In view of the deficiencies of the above-mentioned prior art, the technical problem to be solved by the present invention is: how to provide an artificial intelligence-based port coal transshipment planning optimization method, accurately identify the type of coal through intelligent recognition technology, rely on dynamic optimization algorithms to improve the efficiency and accuracy of coal unloading and transshipment, significantly enhance the uniformity and safety of coal stacking in the yard, greatly improve the space utilization rate of the port coal storage yard, and realize the intelligent, efficient and safe management of the entire process of port coal transshipment.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] The artificial intelligence-based optimization method for port coal transshipment planning includes:

[0008] S1: Acquire coal loading images after the transport vehicle at the port is loaded with coal, and the coal loading weight;

[0009] S2: Input the coal loading image of the transport vehicle into the trained coal type recognition model and output the corresponding coal type prediction result;

[0010] S3: Input the coal loading image of the transport vehicle into the trained loading volume prediction model and output the corresponding coal loading volume prediction result;

[0011] S4: Based on the coal loading weight, coal type prediction results, and coal loading volume prediction results, combined with the real-time status of coal stacking in the coal storage yard, the optimal unloading area is selected for the transport vehicle;

[0012] S5: Generate transfer planning information based on the location information of the optimal unloading area to guide the transport vehicle to the optimal unloading area for unloading.

[0013] Preferably, in step S1, image enhancement processing is performed on the acquired coal loading image through the following steps:

[0014] S101: performing contrast transformation on each pixel value in the coal loading image;

[0015] S102: performing brightness adjustment on each pixel value in the contrast-adjusted coal loading image to obtain an enhanced coal loading image.

[0016] Preferably, in step S2, the coal type recognition model is constructed based on a convolutional neural network.

[0017] Preferably, in step S2, a convolutional neural network of a coal type recognition model is constructed.

[0018] Preferably, in step S4, the real-time status of coal stacking in the coal storage yard includes a coal stacking stability score and a coal stacking safety score for each unloading area.

[0019] Preferably, in step S4, the coal stacking stability score of the unloading area is generated by the following steps:

[0020] S401: Obtaining coal physical property parameters of different types of coal;

[0021] S402: constructing a corresponding real-time three-dimensional coal model based on the coal stacking image of the unloading area;

[0022] S403: Determine the type of coal stacked in the unloading area; use finite element analysis to divide the real-time three-dimensional model of the coal in the unloading area into a finite number of small cells, and assign corresponding coal physical property parameters to each small cell based on the type of coal; use finite element analysis software to solve the stress, strain, and displacement of each small cell, and then calculate the stress, strain, and displacement analysis results of the unloading area;

[0023] S404: Determine a coal stacking stability score of the unloading area based on the stress, strain, and displacement analysis results of the unloading area in combination with preset standard values.

[0024] Preferably, in step S404, the coal stacking stability in the unloading area is divided into four score levels: stable, basically stable, unstable and unstable;

[0025] in:

[0026] When the stress in the unloading area is less than 70% of the stress standard value, the strain is less than 70% of the strain standard value, and the displacement is less than 70% of the displacement standard value, the coal stacking stability score is determined to be stable;

[0027] When the stress in the unloading area is between 70% and 90% of the stress standard value, the strain is between 70% and 90% of the strain standard value, and the displacement is between 70% and 90% of the displacement standard value, the coal stacking stability score is determined to be basically stable;

[0028] When the stress in the unloading area is between 90% and 110% of the stress standard value, the strain is between 90% and 110% of the strain standard value, and the displacement is between 90% and 110% of the displacement standard value, the coal stacking stability score is judged to be understable;

[0029] When the stress in the unloading area is greater than 110% of the stress standard value, the strain is greater than 110% of the strain standard value, or the displacement is greater than 110% of the displacement standard value, the coal stacking stability score is judged to be unstable.

[0030] Preferably, in step S4, the coal stacking safety score of the unloading area is generated by the following steps:

[0031] S411: Obtain the stacking weight of the coal loaded in the unloading area;

[0032] S412: Calculating a corresponding stacking pressure based on the stacking weight of the coal loaded in the unloading area;

[0033] The formula is:

[0034] Stacking pressure = stacking weight / bottom area of ​​stacking area;

[0035] S413: Obtaining a spontaneous combustion tendency index; calculating a corresponding spontaneous combustion risk index based on the measured spontaneous combustion tendency index of the coal loaded in the unloading area and a preset standard range;

[0036] The formula is:

[0037] Spontaneous combustion risk index = α × (measured oxygen absorption capacity - standard minimum oxygen absorption capacity) / (standard maximum oxygen absorption capacity - standard minimum oxygen absorption capacity) + β × (standard maximum ignition point temperature - measured ignition point temperature) / (standard maximum ignition point temperature - standard minimum ignition point temperature) + γ × (measured heat release intensity - standard minimum heat release intensity) / (standard maximum heat release intensity - standard minimum heat release intensity);

[0038] Where: α, β, γ represent the set weight parameters;

[0039] S414: Calculating a corresponding ventilation efficiency index based on the ventilation volume of the unloading area and a preset standard ventilation volume;

[0040] The formula is:

[0041] Ventilation efficiency index = actual ventilation volume / standard ventilation volume;

[0042] S415: Determine a coal stacking safety score for the unloading area based on the stacking pressure, spontaneous combustion risk index, and ventilation efficiency index of the unloading area in combination with a preset safety threshold and a danger threshold.

[0043] Preferably, in step S415, the safety of coal stacking in the unloading area is divided into three score levels: safe, generally safe, and dangerous;

[0044] When all indicators of the unloading area are within the safety threshold, the coal stacking safety score is determined to be safe;

[0045] When one or two indicators in the unloading area exceed the safety threshold but do not exceed the danger threshold, the coal stacking safety score is judged to be generally safe;

[0046] When all indicators in the unloading area exceed the safety threshold or some indicators reach the danger threshold, the coal stacking safety score is judged to be dangerous.

[0047] Preferably, in step S4, the optimal unloading area is selected for the transport vehicle by:

[0048] S411: selecting a primary screening and unloading area for placing the corresponding type of coal according to the coal type prediction result of the transport vehicle;

[0049] S412: Calculating the remaining loadable weight and volume of coal in each primary screening unloading area based on the maximum loadable weight and volume of coal in each primary screening unloading area and the weight and volume of the currently loaded coal;

[0050] S413: Selecting a target unloading area from the pre-screened unloading area, where the remaining loadable coal weight and volume meet the predicted coal loading weight and coal loading volume of the transport vehicle;

[0051] S414: Selecting an unloading area with the highest coal stacking stability score and coal stacking safety score from the target unloading areas as the optimal unloading area.

[0052] Compared with the existing technology, the port coal transshipment planning optimization method based on artificial intelligence in the present invention has the following beneficial effects:

[0053] This invention uses a neural network to process coal loading images, quickly and accurately outputting coal type and loading volume. After training with a large number of samples, the neural network can capture subtle characteristic differences in coal images, accurately identify different types of coal, and accurately predict volume. This provides reliable and timely data support for the subsequent selection of unloading areas, thereby improving the efficiency of the entire coal unloading decision-making process and addressing issues such as inaccurate or time-consuming manual judgment.

[0054] The present invention selects the optimal unloading area by comprehensively considering the coal loading weight, coal type and coal loading volume, and can quickly and accurately plan the most suitable unloading location for the transport vehicle, avoiding the situation where the transport vehicle frequently searches for the unloading area in the port due to incomplete information or unreasonable decision-making, reducing the vehicle's driving distance and waiting time, so that the transport vehicle can go directly to the optimal unloading area according to the generated transfer planning information, thereby improving the efficiency of port transport vehicle transfer and coal unloading. At the same time, different types of coal have different physical properties. Selecting the unloading area based on the predicted results of coal loading weight, coal type and coal loading volume can better plan the stacking location of coal in the coal storage yard, ensure that different types of coal are reasonably distributed in the coal storage yard, avoid the situation where too much or too little coal is piled up in local areas, and effectively improve the uniformity of coal stacking in the port.

[0055] The present invention, based on the consideration of coal loading weight, coal type and coal loading volume, further combines the real-time status of coal stacking in the coal storage yard (coal stacking stability score and coal stacking safety score) to select the optimal unloading area for transport vehicles. The real-time status of coal stacking in the coal storage yard reflects the current usage and carrying capacity of the coal storage yard, which can avoid guiding transport vehicles to areas with poor stacking stability or safety hazards. By selecting unloading areas with good stability and high safety, it can ensure that the unloading process proceeds smoothly, reduce unloading interruptions caused by unexpected situations, thereby improving coal unloading efficiency and ensuring the efficient operation of the port coal unloading process. At the same time, by selecting unloading areas based on the real-time status of the coal storage yard, the newly arrived coal can be reasonably distributed according to the stacking situation of each area in the current coal storage yard, which can avoid the situation where the stability is reduced or the safety hazard is increased due to excessive accumulation of coal in local areas, making the coal stacking in the entire coal storage yard more uniform and reasonable, and improving the space utilization rate of the coal storage yard. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to make the purpose, technical solutions and advantages of the invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings, in which:

[0057] Figure 1 This is the logical block diagram of the artificial intelligence-based port coal transshipment planning optimization method. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but only represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0059] It should be noted that similar reference numerals and letters denote similar items in the following figures. Therefore, once an item is defined in one figure, it does not require further definition or explanation in subsequent figures. In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer" indicate positions or relationships based on the positions or relationships shown in the figures, or the positions or relationships in which the inventive product is typically placed when in use. These terms are intended solely to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation, and are therefore not to be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third," etc., are used solely to distinguish descriptions and are not to be construed as indicating or implying relative importance. Furthermore, terms such as "horizontal" and "vertical" do not imply that a component is absolutely horizontal or overhanging, but rather may be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but rather may be slightly tilted. In the description of the present invention, it should also be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0060] The following is a further detailed description through specific implementation methods:

[0061] Example:

[0062] This embodiment discloses an artificial intelligence-based port coal transshipment planning optimization method.

[0063] like Figure 1 As shown in the figure, the artificial intelligence-based port coal transshipment planning optimization method includes:

[0064] S1: Acquire coal loading images after the transport vehicle at the port is loaded with coal, and the coal loading weight;

[0065] In this embodiment, the coal loading image refers to an image of the coal loaded in the carriage of a transport vehicle after loading. The coal loading image can be captured by a high-definition camera installed in a coal yard or coal storage area. The coal loading weight is obtained using a weighbridge installed at the port or coal storage area.

[0066] S2: Input the coal loading image of the transport vehicle into the trained coal type recognition model and output the corresponding coal type prediction result;

[0067] In this embodiment, the types of coal mainly include anthracite, coking coal, fat coal, lean coal, lignite, long flame coal, lean coal and the like. Among them, anthracite, coking coal, fat coal, lean coal and the like mainly appear in the form of blocks, while lignite, long flame coal, lean coal and the like mainly appear in the form of powder. Among them, the powdered coal stored in the port yard has fine particles, which are very easy to raise dust during loading and unloading, storage and wind action, which not only seriously pollutes the surrounding air and environment, but also poses a safety hazard. For this reason, it is very important to spray water on the powdered coal to prevent dust. Ports generally set up water spraying devices to spray water evenly on the surface of the coal pile, increase the humidity and particle weight of the coal, effectively reduce the flying of dust, reduce the dust concentration in the air, and keep it away from the explosion limit. At the same time, water spraying can also improve the working environment, significantly reduce the inhalation of coal dust, and protect the health of workers.

[0068] S3: Input the coal loading image of the transport vehicle into the trained loading volume prediction model and output the corresponding coal loading volume prediction result;

[0069] S4: Based on the coal loading weight, coal type prediction results, and coal loading volume prediction results, combined with the real-time status of coal stacking in the coal storage yard, the optimal unloading area is selected for the transport vehicle;

[0070] S5: Generate transfer planning information based on the location information of the optimal unloading area to guide the transport vehicle to the optimal unloading area for unloading.

[0071] In this embodiment, the location information of the optimal unloading area and the real-time location information of the transport vehicle can be combined to generate the optimal unloading navigation path as the transfer planning information using a path planning algorithm.

[0072] This invention uses a neural network to process coal loading images, quickly and accurately outputting coal type and loading volume. After training with a large number of samples, the neural network can capture subtle characteristic differences in coal images, accurately identify different types of coal, and accurately predict volume. This provides reliable and timely data support for the subsequent selection of unloading areas, thereby improving the efficiency of the entire coal unloading decision-making process and addressing issues such as inaccurate or time-consuming manual judgment.

[0073] The present invention selects the optimal unloading area by comprehensively considering the coal loading weight, coal type and coal loading volume, and can quickly and accurately plan the most suitable unloading location for the transport vehicle, avoiding the situation where the transport vehicle frequently searches for the unloading area in the port due to incomplete information or unreasonable decision-making, reducing the vehicle's driving distance and waiting time, so that the transport vehicle can go directly to the optimal unloading area according to the generated transfer planning information, thereby improving the efficiency of port transport vehicle transfer and coal unloading. At the same time, different types of coal have different physical properties. Selecting the unloading area based on the predicted results of coal loading weight, coal type and coal loading volume can better plan the stacking location of coal in the coal storage yard, ensure that different types of coal are reasonably distributed in the coal storage yard, avoid the situation where too much or too little coal is piled up in local areas, and effectively improve the uniformity of coal stacking in the port.

[0074] The present invention, based on the consideration of coal loading weight, coal type and coal loading volume, further combines the real-time status of coal stacking in the coal storage yard (coal stacking stability score and coal stacking safety score) to select the optimal unloading area for transport vehicles. The real-time status of coal stacking in the coal storage yard reflects the current usage and carrying capacity of the coal storage yard, which can avoid guiding transport vehicles to areas with poor stacking stability or safety hazards. By selecting unloading areas with good stability and high safety, it can ensure that the unloading process proceeds smoothly, reduce unloading interruptions caused by unexpected situations, thereby improving coal unloading efficiency and ensuring the efficient operation of the port coal unloading process. At the same time, by selecting unloading areas based on the real-time status of the coal storage yard, the newly arrived coal can be reasonably distributed according to the stacking situation of each area in the current coal storage yard, which can avoid the situation where the stability is reduced or the safety hazard is increased due to excessive accumulation of coal in local areas, making the coal stacking in the entire coal storage yard more uniform and reasonable, and improving the space utilization rate of the coal storage yard.

[0075] In the specific implementation process, the acquired coal loading images are enhanced through the following steps:

[0076] S101: performing contrast transformation on each pixel value in the coal loading image;

[0077] The formula is:

[0078] I′=clip((I-μ)·(1+α)+μ);

[0079] Where: I′ represents the pixel value after contrast adjustment of pixel value I; I represents the single pixel value of the coal loading image; μ represents the average grayscale value of the coal loading image; a is the contrast adjustment factor; clip represents the pixel value truncation operation;

[0080] S102: adjusting the brightness of each pixel value in the contrast-adjusted coal loading image to obtain an enhanced coal loading image;

[0081] The formula is:

[0082] I″=clip(I′·(1+β));

[0083] Where x″ represents the pixel value x′ after brightness adjustment; I′ represents the single pixel value of the coal loading image after contrast adjustment; β is the brightness adjustment factor; and clip represents the pixel value clipping operation.

[0084] The present invention can effectively enhance the local edge and texture features of the image through contrast transformation, which can help improve the subsequent model's perception of faint sandblasting marks; at the same time, through brightness adjustment, it can simulate changes in ambient light intensity and enhance the robustness of the model under extreme conditions such as low light or strong light.

[0085] During the specific implementation process, the coal type recognition model is constructed based on the convolutional neural network.

[0086] In this embodiment, a data set containing a large number of images of coal loading of different types is constructed, and a coal type recognition model is obtained by training using a convolutional neural network, so that the model learns the characteristic differences of different types of coal in images, thereby realizing type recognition.

[0087] During the specific implementation process, the coal type recognition model is constructed based on the convolutional neural network.

[0088] In this embodiment, a data set containing a large number of different types of coal loading images is constructed, and an improved convolutional neural network is used for training to obtain a loading volume prediction model, so that the model learns the characteristic differences of different volumes of coal in the images, thereby achieving the coal loading volume prediction results.

[0089] During the specific implementation process, the real-time status of coal stacking in the coal storage yard includes the coal stacking stability score and coal stacking safety score of each unloading area.

[0090] In the specific implementation process, the coal stacking stability score of the unloading area is generated through the following steps:

[0091] S401: Obtaining coal physical property parameters of different types of coal;

[0092] In this example, different types of coal samples were obtained and laboratory tests were performed to determine the physical properties of the coal, including particle size distribution, density, internal friction angle, cohesion, and other physical properties. For example, particle size distribution can be determined using sieving, density can be measured using a densitometer, and internal friction angle and cohesion can be determined using a direct shear test.

[0093] S402: constructing a corresponding real-time three-dimensional coal model based on the coal stacking image of the unloading area;

[0094] S403: Determine the type of coal stored in the unloading area; use the finite element analysis (FEA) method to divide the real-time three-dimensional model of the coal in the unloading area into a finite number of small cells, and assign corresponding coal physical property parameters to each small cell based on the coal type; use finite element analysis software (such as ABAQUS) to solve the stress, strain, and displacement of each small cell, and calculate the stress, strain, and displacement analysis results of the unloading area;

[0095] S404: Determine a coal stacking stability score of the unloading area based on the stress, strain, and displacement analysis results of the unloading area in combination with preset standard values.

[0096] Specifically, the coal stacking stability in the unloading area is divided into four scoring levels: stable (90 points), basically stable (80 points), unstable (70 points) and unstable (60 points);

[0097] in:

[0098] When the stress in the unloading area is less than 70% of the stress standard value, the strain is less than 70% of the strain standard value, and the displacement is less than 70% of the displacement standard value, the coal stacking stability score is determined to be stable (90 points);

[0099] When the stress in the unloading area is between 70% and 90% of the stress standard value, the strain is between 70% and 90% of the strain standard value, and the displacement is between 70% and 90% of the displacement standard value, the coal stacking stability score is judged to be basically stable (80 points);

[0100] When the stress in the unloading area is between 90% and 110% of the stress standard value, the strain is between 90% and 110% of the strain standard value, and the displacement is between 90% and 110% of the displacement standard value, the coal stacking stability score is judged to be understable (70 points);

[0101] When the stress in the unloading area is greater than 110% of the stress standard value, the strain is greater than 110% of the strain standard value, or the displacement is greater than 110% of the displacement standard value, the coal stacking stability score is judged to be unstable (60 points).

[0102] During the specific implementation process, the coal stacking safety score of the unloading area is generated through the following steps:

[0103] S411: Obtain the stacking weight of the coal loaded in the unloading area;

[0104] In this embodiment, the weight and volume of the loaded coal can be obtained by recording the weight and volume of coal unloaded by each transport vehicle in the unloading area. Image processing technology can also be used to determine the boundaries and shape of the coal stacking area based on the collected images of the loaded coal in the unloading area. The coal stacking weight of each area can then be calculated based on a preset reference table of unit volume coal weights (different types of coal have different unit volume weights, for example, lignite is approximately 0.8-1.1 tons / cubic meter, bituminous coal is approximately 1.2-1.4 tons / cubic meter, and anthracite is approximately 1.4-1.8 tons / cubic meter) combined with the volume obtained through image analysis (volume estimation can be performed by approximating the stacking area as a regular geometric shape).

[0105] S412: Calculating a corresponding stacking pressure based on the stacking weight of the coal loaded in the unloading area;

[0106] The formula is:

[0107] Stacking pressure = stacking weight / bottom area of ​​stacking area;

[0108] The bottom area can be calculated based on the contour obtained by image analysis.

[0109] S413: Obtaining a spontaneous combustion tendency index; calculating a corresponding spontaneous combustion risk index based on the measured spontaneous combustion tendency index of the coal loaded in the unloading area and a preset standard range;

[0110] In this embodiment, the spontaneous combustion tendency index includes oxygen absorption capacity, maximum ignition point temperature and heat release intensity, and the standard range of each spontaneous combustion tendency index is obtained based on experimental data;

[0111] The formula is:

[0112] Spontaneous combustion risk index = 0.4 × (measured oxygen absorption capacity - standard minimum oxygen absorption capacity) / (standard maximum oxygen absorption capacity - standard minimum oxygen absorption capacity) + 0.3 × (standard maximum ignition point temperature - measured ignition point temperature) / (standard maximum ignition point temperature - standard minimum ignition point temperature) + 0.3 × (measured heat release intensity - standard minimum heat release intensity) / (standard maximum heat release intensity - standard minimum heat release intensity);

[0113] In this embodiment, chemical analysis is performed on coal samples taken from the unloading area to determine the actual spontaneous combustion tendency indicators, such as using an oxygen bomb calorimeter to measure the oxygen absorption amount, using a thermogravimetric analyzer to measure the ignition point temperature, and using a calorimeter to measure the heat release intensity.

[0114] S414: Calculating a corresponding ventilation efficiency index based on the ventilation volume of the unloading area and a preset standard ventilation volume;

[0115] In this embodiment, based on the coal storage area layout drawings and ventilation equipment operation data, the ventilation conditions of each area are simulated using fluid mechanics principles (such as the Bernoulli equation) to calculate the ventilation efficiency index of the unloading area.

[0116] The formula is:

[0117] Ventilation efficiency index = actual ventilation volume / standard ventilation volume;

[0118] Among them, the standard ventilation volume can be calculated based on the coal stacking volume and the ventilation volume required per unit volume of coal. The ventilation volume required per unit volume of coal can be determined based on experience or relevant standards.

[0119] S415: Determine a coal stacking safety score for the unloading area based on the stacking pressure, spontaneous combustion risk index, and ventilation efficiency index of the unloading area in combination with a preset safety threshold and a danger threshold.

[0120] Specifically, the safety of coal stacking in the unloading area is divided into three levels: safe (90 points), generally safe (80 points), and dangerous (60 points);

[0121] When all indicators of the unloading area are within the safety threshold, the coal stacking safety score is judged to be safe (90 points);

[0122] When one or two indicators in the unloading area exceed the safety threshold but do not exceed the danger threshold, the coal stacking safety score is judged to be generally safe (80 points);

[0123] When all indicators in the unloading area exceed the safety threshold or some indicators reach the danger threshold, the coal stacking safety score is judged to be dangerous (60 points).

[0124] During the specific implementation process, the optimal unloading area for the transport vehicle is selected as follows:

[0125] S411: selecting a primary screening and unloading area for placing the corresponding type of coal according to the coal type prediction result of the transport vehicle;

[0126] S412: Calculating the remaining loadable weight and volume of coal in each primary screening unloading area based on the maximum loadable weight and volume of coal in each primary screening unloading area and the weight and volume of the currently loaded coal;

[0127] S413: Selecting a target unloading area from the pre-screened unloading area, where the remaining loadable coal weight and volume meet the predicted coal loading weight and coal loading volume of the transport vehicle;

[0128] S414: Selecting an unloading area with the highest coal stacking stability score and coal stacking safety score from the target unloading areas as the optimal unloading area.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the technical solutions. Those skilled in the art should understand that modifications or equivalent replacements of the technical solutions of the present invention that do not depart from the purpose and scope of the technical solutions of the present invention should be included in the scope of the claims of the present invention.

Claims

1. The port coal transshipment planning optimization method based on artificial intelligence is characterized by: include: S1: Acquire coal loading images after the transport vehicle at the port is loaded with coal, and the coal loading weight; S2: Input the coal loading image of the transport vehicle into the trained coal type recognition model and output the corresponding coal type prediction result; S3: Input the coal loading image of the transport vehicle into the trained loading volume prediction model and output the corresponding coal loading volume prediction result; S4: Based on the coal loading weight, coal type prediction results, and coal loading volume prediction results, combined with the real-time status of coal stacking in the coal storage yard, the optimal unloading area is selected for the transport vehicle; S5: Generate transfer planning information based on the location information of the optimal unloading area to guide the transport vehicle to the optimal unloading area for unloading.

2. The method for optimizing port coal transshipment planning based on artificial intelligence according to claim 1, characterized in that: In step S1, the acquired coal loading image is subjected to image enhancement processing through the following steps: S101: performing contrast transformation on each pixel value in the coal loading image; S102: performing brightness adjustment on each pixel value in the contrast-adjusted coal loading image to obtain an enhanced coal loading image.

3. The artificial intelligence-based port coal transshipment planning optimization method according to claim 1, characterized in that: In step S4, the real-time status of coal stacking in the coal storage yard includes the coal stacking stability score and the coal stacking safety score of each unloading area.

4. The artificial intelligence-based port coal transshipment planning optimization method according to claim 3, characterized in that: In step S4, the coal stacking stability score of the unloading area is generated through the following steps: S401: Obtaining coal physical property parameters of different types of coal; S402: constructing a corresponding real-time three-dimensional coal model based on the coal stacking image of the unloading area; S403: Determine the type of coal stacked in the unloading area; use finite element analysis to divide the real-time three-dimensional model of the coal in the unloading area into a finite number of small cells, and assign corresponding coal physical property parameters to each small cell based on the type of coal; use finite element analysis software to solve the stress, strain, and displacement of each small cell, and then calculate the stress, strain, and displacement analysis results of the unloading area; S404: Determine a coal stacking stability score of the unloading area based on the stress, strain, and displacement analysis results of the unloading area in combination with preset standard values.

5. The method for optimizing port coal transshipment planning based on artificial intelligence according to claim 4, characterized in that: In step S404, the coal stacking stability in the unloading area is divided into four score levels: stable, basically stable, unstable, and unstable; in: When the stress in the unloading area is less than 70% of the stress standard value, the strain is less than 70% of the strain standard value, and the displacement is less than 70% of the displacement standard value, the coal stacking stability score is determined to be stable; When the stress in the unloading area is between 70% and 90% of the stress standard value, the strain is between 70% and 90% of the strain standard value, and the displacement is between 70% and 90% of the displacement standard value, the coal stacking stability score is determined to be basically stable; When the stress in the unloading area is between 90% and 110% of the stress standard value, the strain is between 90% and 110% of the strain standard value, and the displacement is between 90% and 110% of the displacement standard value, the coal stacking stability score is judged to be understable; When the stress in the unloading area is greater than 110% of the stress standard value, the strain is greater than 110% of the strain standard value, or the displacement is greater than 110% of the displacement standard value, the coal stacking stability score is judged to be unstable.

6. The artificial intelligence-based port coal transshipment planning optimization method according to claim 3, characterized in that: In step S4, the coal stacking safety score of the unloading area is generated through the following steps: S411: Obtain the stacking weight of the coal loaded in the unloading area; S412: Calculating a corresponding stacking pressure based on the stacking weight of the coal loaded in the unloading area; The formula is: Stacking pressure = stacking weight / bottom area of ​​stacking area; S413: Obtaining a spontaneous combustion tendency index; calculating a corresponding spontaneous combustion risk index based on the measured spontaneous combustion tendency index of the coal loaded in the unloading area and a preset standard range; The formula is: Spontaneous combustion risk index = α × (measured oxygen absorption capacity - standard minimum oxygen absorption capacity) / (standard maximum oxygen absorption capacity - standard minimum oxygen absorption capacity) + β × (standard maximum ignition point temperature - measured ignition point temperature) / (standard maximum ignition point temperature - standard minimum ignition point temperature) + γ × (measured heat release intensity - standard minimum heat release intensity) / (standard maximum heat release intensity - standard minimum heat release intensity); Where: α, β, γ represent the set weight parameters; S414: Calculating a corresponding ventilation efficiency index based on the ventilation volume of the unloading area and a preset standard ventilation volume; The formula is: Ventilation efficiency index = actual ventilation volume / standard ventilation volume; S415: Determine a coal stacking safety score for the unloading area based on the stacking pressure, spontaneous combustion risk index, and ventilation efficiency index of the unloading area in combination with a preset safety threshold and a danger threshold.

7. The artificial intelligence-based port coal transshipment planning optimization method according to claim 6, characterized in that: In step S415, the safety of coal stacking in the unloading area is divided into three score levels: safe, generally safe, and dangerous; When all indicators of the unloading area are within the safety threshold, the coal stacking safety score is determined to be safe; When one or two indicators in the unloading area exceed the safety threshold but do not exceed the danger threshold, the coal stacking safety score is judged to be generally safe; When all indicators in the unloading area exceed the safety threshold or some indicators reach the danger threshold, the coal stacking safety score is judged to be dangerous.

8. The artificial intelligence-based port coal transshipment planning optimization method according to claim 3, characterized in that: In step S4, the optimal unloading area is selected for the transport vehicle as follows: S411: selecting a primary screening and unloading area for placing the corresponding type of coal according to the coal type prediction result of the transport vehicle; S412: Calculating the remaining loadable weight and volume of coal in each primary screening unloading area based on the maximum loadable weight and volume of coal in each primary screening unloading area and the weight and volume of the currently loaded coal; S413: Selecting a target unloading area from the pre-screened unloading area, where the remaining loadable coal weight and volume meet the predicted coal loading weight and coal loading volume of the transport vehicle; S414: Selecting an unloading area with the highest coal stacking stability score and coal stacking safety score from the target unloading areas as the optimal unloading area.

Images