Logistics path intelligent optimization method and system based on coal quality detection

Abstract

The invention relates to a logistics path intelligent optimization method and system based on coal quality detection, and the method comprises the following steps: collecting the quality data of coal on a transport vehicle in real time, carrying out the preprocessing, inputting a trained coal quality detection model, and obtaining a coal quality detection result, the quality data comprises physical and chemical attribute data and spectral data of the coal, and the physical and chemical attribute data comprises moisture, ash content and sulfur content of the coal; according to the coal quality detection result, whether the coal on the transport vehicle has a flammable risk or not is judged, if yes, a column generation algorithm is adopted to solve a distribution optimization model, the advancing path of the transport vehicle is adjusted according to the solving result, and the distribution optimization model takes the minimum total ton kilometer price as the target, and the distribution optimization model is used for optimizing the total ton kilometer price. And vehicle operation constraints and time window constraints are used as constraint conditions. Compared with the prior art, the logistics path can be adjusted according to the change of the coal quality, and the coal quality is prevented from being reduced in the transportation process.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent logistics management, and in particular relates to a method and system for intelligent optimization of logistics paths based on coal quality detection. Background Art

[0002] As the cornerstone energy for economic development, the efficient use and quality assurance of coal play a vital role in promoting green and sustainable development. However, the quality of coal is volatile, especially in the transportation process, which is significantly affected by environmental factors, becoming a major problem restricting its efficient use. During transportation, the mode of transportation and the environment will have a certain impact on the moisture and ash content of coal, which in turn affects the quality of coal. Therefore, logistics and transportation companies are facing unprecedented challenges and opportunities - how to ensure the high quality of coal while minimizing transportation losses has become a core issue that needs to be overcome.

[0003] The traditional coal logistics model relies on manual monitoring and fixed transportation routes. This model is powerless in dealing with the dynamic changes in coal quality, and it is difficult to achieve real-time and accurate monitoring of key indicators such as coal moisture, ash, and sulfur. This not only increases the potential loss during transportation, especially under extreme weather conditions (such as high temperature drying), but is also likely to accelerate the deterioration of coal quality, causing irreparable economic losses. Patent application 201880022780.6 discloses a logistics method and logistics base for granular wood biomass fuel. After extracting part of the acceptance material fuel for analysis, the quality and storage destination of the acceptance material fuel are specified, and the acceptance material fuel is transported to the designated place, which can stably supply granular wood biomass fuel of a quality corresponding to the requirements of the demand area. However, the above method still does not take into account the possible changes in coal during transportation, and cannot intelligently adjust the transportation strategy according to the real-time status of coal and changes in the external environment, and lacks flexible adaptability. Therefore, it is urgent to design an intelligent optimization method for logistics paths to avoid the decline in coal quality during transportation. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a method and system for intelligent optimization of logistics paths based on coal quality detection, which can adjust the logistics paths according to changes in coal quality to avoid the decline of coal quality during transportation.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] The present invention provides a method for intelligent optimization of logistics paths based on coal quality detection, comprising the following steps:

[0007] Collect the quality data of coal on the transport vehicle in real time, input it into the trained coal quality detection model after preprocessing, and obtain the coal quality detection result, wherein the quality data includes the physical and chemical property data and spectral data of the coal, wherein the physical and chemical property data includes the moisture content, ash content and sulfur content of the coal;

[0008] Based on the coal quality inspection results, it is determined whether the coal on the transport vehicle has a flammable risk. If so, a column generation algorithm is used to solve the distribution optimization model, and the travel path of the transport vehicle is adjusted according to the solution results. The distribution optimization model aims to minimize the total ton-kilometer price, with vehicle operation constraints and time window constraints as constraints.

[0009] Furthermore, the quality data of the coal on the transport vehicle is collected in real time by timing and / or alarm triggering.

[0010] Furthermore, the preprocessing includes denoising and smoothing.

[0011] Furthermore, the preprocessing includes extracting characteristic wavelengths from the spectral data and calculating spectral characteristic values, including absorbance and reflectance.

[0012] Furthermore, the coal quality detection model includes a convolution module, a residual module, a pooling module and a fully connected module connected in sequence, and the convolution module includes multiple stacked convolution layers for extracting features at different levels.

[0013] Furthermore, the coal quality detection model is trained through incremental learning.

[0014] Furthermore, the specific process of judging whether the coal on the transport vehicle has a flammable risk according to the coal quality test result is as follows:

[0015] The current coal quality test results are compared with the set threshold to determine whether there is a flammable risk. If not, the current coal quality test results are compared with the coal quality test results of the adjacent test time period to further determine whether there is a flammable risk.

[0016] Furthermore, the vehicle operation constraints include node constraints, no-travel constraints, flow constraints, warehouse constraints, vehicle capacity constraints and load constraints, wherein the node constraints are used to restrict that there is only one transport vehicle passing through each demand node in the logistics path, the no-travel constraints are used to restrict the types of prohibited vehicles, the flow constraints are used to restrict the vehicle flow balance at each demand node, the warehouse constraints are used to restrict whether it is necessary to go to the warehouse to pick up goods, the vehicle capacity constraints are used to restrict the coal carried by any transport vehicle to not exceed its volume, and the load constraints are used to restrict the coal carried by any transport vehicle to not exceed its load.

[0017] Furthermore, the time window constraint is used to limit the time for the transport vehicle to arrive at each demand node in the logistics path.

[0018] The present invention also provides a logistics path intelligent optimization system based on coal quality detection, including a data acquisition module, a quality detection module and a logistics path planning module;

[0019] The data acquisition module is used to collect quality data of coal on the transport vehicle in real time and perform preprocessing, wherein the quality data includes physical and chemical property data and spectral data of the coal, wherein the physical and chemical property data includes moisture, ash and sulfur content of the coal;

[0020] The quality detection module includes a coal quality detection model for outputting coal quality detection results based on the preprocessed quality data;

[0021] The logistics path planning module is used to determine whether there is a flammable risk in the coal on the transport vehicle based on the coal quality inspection results. If so, a column generation algorithm is used to solve the distribution optimization model, and the travel path of the transport vehicle is adjusted according to the solution results. The distribution optimization model aims to minimize the total ton-kilometer price, with vehicle operation constraints and time window constraints as constraints.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] 1. The present invention designs a method for intelligent optimization of logistics paths based on coal quality detection. First, the quality data of coal on the transport vehicle is collected in real time, and the data is input into the trained coal quality detection model after preprocessing, so that accurate coal quality detection results can be obtained in real time. The quality data includes the physical and chemical property data and spectral data of the coal, which can comprehensively reflect the actual quality of the coal. The physical and chemical property data includes the moisture, ash and sulfur content of the coal, which are factors that have an important impact on the quality of the coal; then, according to the coal quality detection results, it is judged whether the coal on the transport vehicle has a flammable risk. If so, the column generation algorithm is used to solve the distribution optimization model, and the travel path of the transport vehicle is adjusted according to the solution result. The distribution optimization model aims to minimize the total ton-kilometer price, and takes the vehicle operation constraints and time window constraints as constraints. Through the above method, it can be judged in real time whether the logistics path needs to be adjusted according to the changes in coal quality, and then a more reasonable and efficient transportation route can be planned, the loss of coal in distribution can be reduced, and the safety of transportation can be improved.

[0024] 2. In the present invention, the coal quality detection model is trained through incremental learning. The model can use the output coal quality detection results and their corresponding input data as new training samples, and improve the accuracy and adaptability of the model through continuous optimization.

[0025] 3. In the present invention, the current coal quality test result is compared with the set threshold to determine whether there is a flammable risk. If not, the current coal quality test result is compared with the coal quality test result of the adjacent test period to further determine whether there is a flammable risk. The second comparison can take preventive measures in advance when the coal quality fluctuates sharply, thereby further ensuring the safety of transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 Flow chart of the method of the present invention. DETAILED DESCRIPTION

[0027] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0028] Example 1

[0029] This embodiment provides a method for intelligent optimization of logistics paths based on coal quality detection. Figure 1 As shown, the following steps are included:

[0030] S1. Collect the quality data of coal on the transport vehicles in real time and perform pre-processing.

[0031] The quality data of coal on the transport vehicles is collected in real time through timing or alarm triggering. The timing method refers to collecting the quality data of coal on the transport vehicles at regular intervals, and the alarm triggering method refers to obtaining the quality data collected on the transport vehicles when the collected quality data exceeds a certain threshold, i.e., the alarm value. For example, when the temperature detected by the temperature sensor exceeds a certain value, an alarm will be generated. When the alarm is detected, the quality data of the coal collected on the delivery vehicle will be obtained. You can also choose the above two schemes at the same time. The combination of the two methods can not only monitor the quality of coal regularly, but also monitor the situation when the coal quality changes suddenly.

[0032] The quality data includes the physical and chemical property data and spectral data of coal. The physical and chemical property data include the moisture content, ash content and sulfur content of coal. Preprocessing includes denoising and smoothing, as well as extracting characteristic wavelengths or characteristic regions from spectral data and calculating spectral characteristic values, such as absorbance and reflectance. The preprocessing step can improve the quality of the data input into the model.

[0033] S2. Input the preprocessed quality data into the trained coal quality detection model to obtain the coal quality detection result.

[0034] The coal quality detection model includes a convolution module, a residual module, a pooling module and a fully connected module connected in sequence. The convolution module includes multiple stacked convolution layers, which are used to extract features at different levels, including low-level features and high-level features. Low-level features are preliminary representations of physical and chemical property data and spectral data, and high-level features are more abstract representations of low-level features. For example, the nonlinear transformation and feature combination of the convolution layer can capture the possible correlation or interaction between different physical and chemical properties, as well as the texture and pattern features related to the internal microstructure or component distribution of coal in the spectral data. The residual module adopts the jump connection method to avoid the gradient vanishing or gradient exploding problems caused by deep neural networks. The pooling module is used to perform feature dimensionality reduction to reduce the amount of calculation and reduce the risk of overfitting. The fully connected module is often used for tasks such as classification or regression, and can also optimize model parameters and improve model performance.

[0035] In this embodiment, for coal whose quality is detected by the coal quality detection model, its quality data is used as a training sample, and the current coal quality detection model is incrementally learned to obtain the coal quality detection model after incremental learning, which is used for the next detection. This method can continuously optimize the accuracy and adaptability of the model.

[0036] S3. Determine whether the coal on the transport vehicle is flammable based on the coal quality test results. If so, use the column generation algorithm to solve the distribution optimization model and adjust the travel path of the transport vehicle based on the solution results.

[0037] The specific process of judging whether the coal on the transport vehicle has a flammable risk based on the coal quality test results is as follows:

[0038] Compare the current coal quality test results with the set threshold to determine whether there is a flammable risk. If not, it cannot be ruled out that there is no flammable risk. Compare the current coal quality test results with the coal quality test results of the adjacent test period to further determine whether there is a flammable risk. The second comparison can detect whether the quality of the coal has changed significantly within a certain period of time, so as to determine whether the coal is likely to deteriorate. In the event of a sharp fluctuation in the quality of the coal, preventive measures can be taken in advance to further ensure the safety of transportation. For example, at several time points in sequence, the quality of the coal detected at time point t1 is a1, the quality of the coal detected at time point t2 is a2, the quality of the coal detected at time point t3 is a3, and the current quality of the coal detected at the current time point t4 is a4. If the quality of the coal a3 and a4 at time points t3 and t4 are both lower than the threshold, but the difference between a4 and a3 exceeds a certain value, it is determined that the coal is likely to be flammable. The threshold can be set according to factors such as the variety and type of coal.

[0039] The distribution optimization model aims to minimize the total ton-kilometer price, with vehicle operation constraints and time window constraints as constraints.

[0040] The expression of the objective function is as follows:

[0041]

[0042] Among them, P k is the ton-kilometer cost of transport vehicle k, Q ik is the vehicle load of transport vehicle k at node i, c ij is the distance from node i to node j, x ijk is whether the transport vehicle k goes from node i to node j, and its value is 0 (yes) or 1 (no). M is the set of all nodes (including virtual nodes), and K is the set of transport vehicles.

[0043] Vehicle operation constraints include node constraints, no-travel constraints, flow constraints, warehouse constraints, vehicle capacity constraints, and load constraints. The expressions are as follows:

[0044] Node constraints are used to limit each demand node on the logistics path to have only one transport vehicle passing through:

[0045]

[0046] Among them, N c The set of demand nodes.

[0047] The prohibition constraint is used to restrict the prohibited vehicle types, and the demand point S f The prohibited vehicle type is S v :

[0048]

[0049] Flow constraints are used to limit the traffic balance at each demand node:

[0050]

[0051] Warehouse constraints are used to limit whether you need to go to the warehouse to pick up goods. For any warehouse, if there is one or more demand points that need to pick up goods, you need to go to this warehouse to pick up goods. Otherwise, you do not need to go to this warehouse:

[0052]

[0053] Among them, q ir Whether node i needs coal from warehouse r, N d A collection of warehouse nodes.

[0054] Vehicle capacity constraint and load constraint are used to limit the coal carried by any transport vehicle to not exceed its volume and load respectively:

[0055]

[0056] Among them, v j is the volume of coal required at node j, V k and W k are the volume and load of transport vehicle k respectively.

[0057] The time window constraint is used to limit the time for transport vehicles to arrive at each demand node in the logistics path. It refers to the latest time when the coal needs to be delivered to the corresponding distribution station based on the current quality of the coal. This time is determined by the type or category of coal:

[0058] T ik +t ij -M′(1-x ijk )≤T jk

[0059] T ik +t ij +M ′ (1-x ijk )≥T jk

[0060] T ik ≤ b i

[0061] T ik ≥0

[0062] Among them, T ik is the time when transport vehicle k arrives at node i, t ij is the time from node i to node j, and M′ is an infinite constant.

[0063] The optimal path can be obtained by solving the above model using the generated column algorithm. The specific process is as follows:

[0064] Set the path from the vehicle's current location to the original delivery site as the current logistics path;

[0065] Calculate the cost of each reachable distribution station when inserted into the current logistics path, select the reachable distribution station with the lowest cost to insert into the current logistics path, and determine whether it is feasible to insert the distribution station into the current logistics path under the constraints of the time window. If feasible, insert the distribution station into the current path and update the logistics path; if not feasible, keep the current logistics path unchanged.

[0066] The above method integrates two core functions: real-time detection of coal quality and dynamic adjustment of logistics routes. Once a change in coal quality is detected, such as signs of severe quality deterioration or flammability, the logistics route can be intelligently adjusted immediately based on the current location information of the transport vehicle, combined with multi-dimensional factors such as traffic conditions and destination demand, to plan a more reasonable and efficient route so that it can be diverted to a more suitable distribution site, thereby effectively reducing the loss of coal during the distribution process and improving overall logistics efficiency.

[0067] If the above method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0068] Example 2

[0069] This embodiment provides a logistics path intelligent optimization system based on coal quality detection, which can implement the method described in Example 1. The system includes a data acquisition module, a quality detection module and a logistics path planning module.

[0070] Among them, the data acquisition module is used to collect the quality data of coal on the transport vehicles in real time and perform preprocessing. The quality data includes the physical and chemical property data and spectral data of the coal. The physical and chemical property data includes the moisture, ash and sulfur content of the coal.

[0071] The quality detection module includes a coal quality detection model, which is used to output coal quality detection results based on preprocessed quality data.

[0072] The logistics path planning module is used to determine whether the coal on the transport vehicle is flammable based on the coal quality inspection results. If so, the column generation algorithm is used to solve the distribution optimization model, and the travel path of the transport vehicle is adjusted according to the solution results. The distribution optimization model aims to minimize the total ton-kilometer price, with vehicle operation constraints and time window constraints as constraints.

[0073] The above description of the embodiments is to facilitate the understanding and use of the invention by those skilled in the art. It is obvious that those skilled in the art can easily make various modifications to these embodiments and apply the general principles described herein to other embodiments without creative work. Therefore, the present invention is not limited to the above embodiments, and improvements and modifications made by those skilled in the art based on the disclosure of the present invention without departing from the scope of the present invention should be within the scope of protection of the present invention.

Claims

1. A method for intelligent optimization of logistics paths based on coal quality detection, characterized in that: The following steps are involved: Collect the quality data of coal on the transport vehicle in real time, input it into the trained coal quality detection model after preprocessing, and obtain the coal quality detection result, wherein the quality data includes the physical and chemical property data and spectral data of the coal, wherein the physical and chemical property data includes the moisture content, ash content and sulfur content of the coal; Based on the coal quality inspection results, it is determined whether the coal on the transport vehicle has a flammable risk. If so, a column generation algorithm is used to solve the distribution optimization model, and the travel path of the transport vehicle is adjusted according to the solution results. The distribution optimization model aims to minimize the total ton-kilometer price, with vehicle operation constraints and time window constraints as constraints.

2. The method for intelligent optimization of logistics paths based on coal quality detection according to claim 1 is characterized in that: The quality data of coal on the transport vehicles is collected in real time through timing and / or alarm triggering.

3. The method for intelligent optimization of logistics paths based on coal quality detection according to claim 1 is characterized in that: The preprocessing includes denoising and smoothing.

4. The method for intelligent optimization of logistics paths based on coal quality detection according to claim 1 is characterized in that: The preprocessing includes extracting characteristic wavelengths from the spectral data and calculating spectral characteristic values, including absorbance and reflectance.

5. The method for intelligent optimization of logistics paths based on coal quality detection according to claim 1 is characterized in that: The coal quality detection model includes a convolution module, a residual module, a pooling module and a fully connected module connected in sequence, and the convolution module includes a plurality of stacked convolution layers for extracting features at different levels.

6. The method for intelligent optimization of logistics paths based on coal quality detection according to claim 1 is characterized in that: The coal quality detection model is trained through incremental learning.

7. The method for intelligent optimization of logistics paths based on coal quality detection according to claim 1 is characterized in that: The specific process of judging whether the coal on the transport vehicle has a flammable risk based on the coal quality test results is as follows: The current coal quality test results are compared with the set threshold to determine whether there is a flammable risk. If not, the current coal quality test results are compared with the coal quality test results of the adjacent test time period to further determine whether there is a flammable risk.

8. The method for intelligent optimization of logistics paths based on coal quality detection according to claim 1 is characterized in that: The vehicle operation constraints include node constraints, no-travel constraints, flow constraints, warehouse constraints, vehicle capacity constraints and load constraints, wherein the node constraints are used to restrict that there is only one transport vehicle passing through each demand node in the logistics path, the no-travel constraints are used to restrict the types of prohibited vehicles, the flow constraints are used to restrict the vehicle flow balance at each demand node, the warehouse constraints are used to restrict whether it is necessary to go to the warehouse to pick up goods, the vehicle capacity constraints are used to restrict the coal carried by any transport vehicle to not exceed its volume, and the load constraints are used to restrict the coal carried by any transport vehicle to not exceed its load.

9. The method for intelligent optimization of logistics paths based on coal quality detection according to claim 1 is characterized in that: The time window constraint is used to limit the time it takes for a transport vehicle to arrive at each demand node in the logistics path.

10. A logistics path intelligent optimization system based on coal quality detection, characterized in that: Including data collection module, quality inspection module and logistics route planning module; The data acquisition module is used to collect quality data of coal on the transport vehicle in real time and perform preprocessing, wherein the quality data includes physical and chemical property data and spectral data of the coal, wherein the physical and chemical property data includes moisture, ash and sulfur content of the coal; The quality detection module includes a coal quality detection model for outputting coal quality detection results based on the preprocessed quality data; The logistics path planning module is used to determine whether there is a flammable risk in the coal on the transport vehicle based on the coal quality inspection results. If so, a column generation algorithm is used to solve the distribution optimization model, and the travel path of the transport vehicle is adjusted according to the solution results. The distribution optimization model aims to minimize the total ton-kilometer price, with vehicle operation constraints and time window constraints as constraints.

Images