A method for evaluating the transportability of large cargo based on channel model

Abstract

The present invention discloses a method for evaluating the transport passability of large-scale cargo based on a channel model, and relates to the field of logistics technology. The method comprises the following steps: formulating a multi-dimensional sensor data fusion strategy; generating a comprehensive and accurate environment model and channel model; edge computing real-time data processing and evaluation; that is, receiving real-time sensor data through edge computing devices pre-deployed at key nodes of the transportation path, and quickly processing and analyzing the data, updating and optimizing the channel model; and planning the obstacle avoidance path based on the channel model and obstacle information updated in real time using an intelligent obstacle avoidance algorithm. The present invention adopts a multi-sensor data fusion algorithm to comprehensively process multi-source data, generate a more accurate environment model and channel model, effectively improve the accuracy of the evaluation results, and adopts Kalman filtering and a multi-sensor data fusion algorithm to comprehensively process multi-source data, generate a more accurate channel model, and improve the accuracy of the evaluation results.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics, and in particular to a method for evaluating the transportability of large-scale cargo based on a channel model. Background Art

[0002] Large cargo transportation plays an important role in logistics and supply chain management, especially in the fields of engineering construction, machinery and equipment transportation, aerospace and energy industries. The safety and efficiency of large cargo transportation directly affect the progress and cost of the project. However, large cargo transportation faces many challenges, such as the complexity of transportation routes, the existence of multiple obstacles, and the dynamic changes of environmental conditions.

[0003] Traditional passability assessment methods usually rely on manual experience and static assessment models, which are difficult to respond to dynamic changes in the actual transportation process in real time, resulting in unforeseen risks and obstacles in the transportation process, thus affecting transportation efficiency and safety. In existing technologies, passability assessment methods are mostly based on data collection from a single sensor, lacking multi-dimensional data fusion and real-time processing capabilities. These methods usually find it difficult to provide accurate environmental models and dynamic channel models, resulting in inaccurate assessment results and unable to effectively guide the transportation path planning and obstacle avoidance operations of large cargo. In addition, traditional methods lack the application of intelligent obstacle avoidance technology, have limitations in identifying and handling obstacles, and cannot ensure the safe passage of large cargo in complex environments. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the problems existing in the existing large-scale cargo transportation passability evaluation method based on the channel model, the present invention is proposed.

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

[0007] A method for evaluating the transportability of large-scale cargo based on a channel model, the method comprising the following steps:

[0008] Formulate a multi-dimensional sensor data fusion strategy; that is, pre-process the different data collected by multiple sensors deployed at key nodes and large cargo along the transportation route, and use data fusion algorithms to integrate multi-source data to generate a comprehensive and accurate environmental model and channel model;

[0009] Edge computing real-time data processing and evaluation: that is, edge computing devices pre-deployed at key nodes of the transportation path receive real-time sensor data, quickly process and analyze the data, update and optimize the channel model, and adjust it according to new environmental data to ensure the dynamic and accuracy of the model;

[0010] Based on the real-time updated channel model and obstacle information, an intelligent obstacle avoidance algorithm is used to plan the obstacle avoidance path to ensure that the obstacle avoidance path can ensure the safe passage of large goods while minimizing transportation time and cost.

[0011] As a preferred solution of the large-scale cargo transportation passability evaluation method based on the channel model described in the present invention, the data preprocessing method is to use a Gaussian filter function After processing, the filtered data can be expressed as:

[0012] ;

[0013] in, is the standard deviation parameter of the Gaussian filter.

[0014] As a preferred solution of the large-scale cargo transportation passability evaluation method based on the channel model described in the present invention, the data fusion algorithm includes: multi-source data fusion in the form of data normalization and weighted summation;

[0015] Among them, the preprocessed data is normalized to obtain normalized data :

[0016] Then the normalization function It is expressed as:

[0017] = ;

[0018] Among them, the multi-source data is fused by weighted summation, and the fusion result It is expressed as:

[0019] = ;

[0020] Represents the weight, which is determined by Kalman filtering. The fusion result in the formula Represents the comprehensive environment model and channel model data after the fusion of all sensor data at time t.

[0021] As a preferred solution of the large-scale cargo transportation passability evaluation method based on the channel model described in the present invention, the high-order integral function is used based on the fusion result of multi-source data. For feature extraction, we have: = ;

[0022] in, To fuse data The attenuation coefficient of the high-order integral feature extraction part controls the influence of the data in the past;

[0023] Use the feature extracted data to model the channel To update, the model is updated using the Kalman filter algorithm:

[0024] ;

[0025] in, is the Kalman gain, H is the observation matrix;

[0026] Use the updated channel model to evaluate the passability of large cargo, and evaluate the function It is expressed as:

[0027] = ;

[0028] in, is the weight; β is the attenuation coefficient used for the evaluation part of the channel model C(t), which controls the attenuation effect of the channel model over time and affects the weight distribution in the real-time passability evaluation; for The mean of .

[0029] As a preferred solution of the large-scale cargo transportation passability evaluation method based on the channel model described in the present invention, wherein: and sensor data To identify obstacles, identification function:

[0030] ;

[0031] Among them, the attenuation coefficient Controls the influence of data in the past, smoothing parameters Used to adjust the sensitivity of the recognition results. represents the comprehensive obstacle recognition result at time t;

[0032] Detailed analysis of the type, location and size of obstacles. Obstacle information analysis results:

[0033] ;

[0034] in, and Represents the mean and standard deviation, respectively, used to standardize and normalize obstacle data and obstacle information analysis results Represents the result of obstacle analysis at time t.

[0035] As a preferred solution of the large-scale cargo transportation passability evaluation method based on the channel model described in the present invention, wherein: based on the real-time updated channel model C(t) and the obstacle information analysis results , using the intelligent obstacle avoidance algorithm to plan the obstacle avoidance path, the path planning function R(t) can be expressed as:

[0036] ;

[0037] Among them, P is the set of all possible paths, k is the adjustment parameter, which controls the relationship between the channel model and obstacles; is the weight parameter to adjust the impact of obstacles in path planning, p(τ) represents the path position at time τ, Indicates the path location Analysis results of obstacle information The Euclidean distance between .

[0038] As a preferred solution of the large-scale cargo transportation passability evaluation method based on the channel model described in the present invention, it is assumed that: The credibility is ,

[0039] ;

[0040] in, is the actual data of the ith sensor at time t, is the data of the sensor at time t after data fusion;

[0041] If the credibility of the multi-source fusion result F(t) If it is greater than the first threshold, it is determined that the accuracy of the environment model and the channel model is high, and normal path planning is performed; >First Threshold Path planning;

[0042] If the credibility of the multi-source fusion result F(t) If the value is less than the second threshold, it is determined that the accuracy of the environment model and the channel model is low, and data fusion and model update are performed again; <Second Threshold Reintegrate data;

[0043] If the credibility of the multi-source fusion result F(t) If the value is between the second threshold and the first threshold, the accuracy of the environment model and the channel model is determined to be medium, and cautious path planning is performed; the second threshold ≤ CF(t) ≤ the first threshold Plan your route carefully.

[0044] A large-scale cargo transportation passability assessment system based on a channel model, the system is applied to the above-mentioned large-scale cargo transportation passability assessment method based on a channel model, and the system includes the following modules:

[0045] The multi-dimensional sensor data fusion module processes the different data collected by various sensors through the Gaussian filter function, and fuses the multi-source data through data normalization and weighted summation to generate a comprehensive and accurate environment model and channel model;

[0046] The real-time data processing and evaluation module uses a high-order integral function to extract features based on the fusion results of multi-source data, updates the channel model through the extracted data, and uses the updated channel model to evaluate the passability of large-scale goods;

[0047] The intelligent obstacle avoidance module plans the obstacle avoidance path through an intelligent obstacle avoidance algorithm based on the real-time updated channel model and obstacle information.

[0048] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a large-scale cargo transportation passability assessment method based on a channel model as described in any one of claims 1 to 7 are implemented.

[0049] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method for evaluating the transport passability of large-scale cargo based on a channel model as described in any one of claims 1 to 7 are implemented.

[0050] Beneficial effects of the present invention:

[0051] 1. The present invention adopts a multi-sensor data fusion algorithm to comprehensively process multi-source data, generate more accurate environmental models and channel models, and effectively improve the accuracy of the evaluation results. It also adopts Kalman filtering and a multi-sensor data fusion algorithm to comprehensively process multi-source data, generate more accurate environmental models and channel models, and effectively improve the accuracy of the evaluation results.

[0052] 2. The present invention combines real-time data processing and intelligent obstacle avoidance technology to dynamically evaluate the passability of large cargo and provide real-time transportation route optimization solutions. By comprehensively considering environmental conditions, obstacle information and transportation routes, it achieves optimal route planning, improves transportation efficiency, and reduces transportation risks and costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0054] Figure 1 This is a schematic diagram of the process structure of a large-scale cargo transportation passability assessment method based on a channel model proposed by the present invention. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0057] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0058] Embodiment 1, refer to Figure 1 , as an embodiment of the present invention, provides a method for evaluating the transportability of large-scale cargo based on a channel model, and the method includes the following three steps.

[0059] Step 1: Develop a multi-dimensional sensor data fusion strategy; that is, pre-process the different data collected by various sensors deployed at key nodes and large cargo along the transportation route, and use data fusion algorithms to integrate multi-source data to generate a comprehensive and accurate environmental model and channel model.

[0060] Specifically, the data is preprocessed using a Gaussian filter function After processing, the filtered data can be expressed as:

[0061] ;

[0062] in, is the standard deviation parameter of the Gaussian filter.

[0063] The above-mentioned data fusion algorithm includes: data normalization and weighted summation to perform multi-source data fusion;

[0064] Among them, the preprocessed data is normalized to obtain normalized data ;

[0065] Then the normalization function It is expressed as:

[0066] = ; Normalized data It has a value range of [0,1], which indicates the relative size of each sensor data relative to its own minimum and maximum values.

[0067] Among them, the multi-source data is fused by weighted summation, and the fusion result It is expressed as:

[0068] = ;

[0069] Represents the weight, which is determined by Kalman filtering. The fusion result in the formula Represents the comprehensive environment model and channel model data after the fusion of all sensor data at time t.

[0070] Step 2: Edge computing real-time data processing and evaluation; that is, receiving real-time sensor data through edge computing devices pre-deployed at key nodes of the transportation path, and quickly processing and analyzing the data, updating and optimizing the channel model, and adjusting it according to new environmental data to ensure the dynamic and accuracy of the model.

[0071] Specifically, based on the fusion results of multi-source data, a high-order integral function is used For feature extraction, we have: = ;

[0072] in, To fuse data The attenuation coefficient of the high-order integral feature extraction part controls the influence of the data in the past;

[0073] Use the feature extracted data to model the channel To update, the model is updated using the Kalman filter algorithm:

[0074] ;

[0075] in, is the Kalman gain, H is the observation matrix;

[0076] Use the updated channel model to evaluate the passability of large cargo, and evaluate the function It is expressed as:

[0077] = ;

[0078] in, is the weight; β is the attenuation coefficient used for the evaluation part of the channel model C(t), which controls the attenuation effect of the channel model over time and affects the weight distribution in the real-time passability evaluation; for The mean of It represents the passability assessment result of large cargo based on the updated channel model and multi-source fusion results at time t. The square root term of the denominator is used for normalization and standardization to ensure the rationality and interpretability of the assessment results. The value range of the comprehensive data P(t) depends on the sensor data, fusion result F(t), Kalman filter gain K(t), weight , usually the value range of P(t) is between [0,1], indicating the relative size of the passability.

[0079] Step 3: Based on the real-time updated channel model and obstacle information, use the intelligent obstacle avoidance algorithm to plan the obstacle avoidance path to ensure that the obstacle avoidance path can ensure the safe passage of large goods while minimizing transportation time and cost.

[0080] Specifically, through the real-time channel model and sensor data To identify obstacles, identification function:

[0081] ;

[0082] Among them, the attenuation coefficient Controls the influence of data in the past, smoothing parameters Used to adjust the sensitivity of the recognition results. represents the comprehensive obstacle recognition result at time t;

[0083] Detailed analysis of obstacle type, location and size. Obstacle information analysis results:

[0084] ;

[0085] in, and Represents the mean and standard deviation, respectively, used to standardize and normalize obstacle data and obstacle information analysis results Indicates the result of obstacle analysis at time t, obstacle information analysis result The value combines the obstacle recognition function The results are integrated over time and the normalization effect of the recognition results is taken into account.

[0086] Based on the real-time updated channel model C(t) and obstacle information analysis result A(t), the intelligent obstacle avoidance algorithm is used to plan the obstacle avoidance path. The path planning function R(t) can be expressed as:

[0087] ;

[0088] Among them, P is the set of all possible paths, k is the adjustment parameter, which controls the relationship between the channel model and obstacles; is the weight parameter to adjust the impact of obstacles in path planning, p(τ) represents the path position at time τ, Indicates the path location Analysis results of obstacle information The Euclidean distance between .

[0089] This embodiment also provides a computer device, which is applicable to a method for evaluating the transport passability of large-sized cargo based on a channel model, and includes: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement a method for evaluating the transport passability of large-sized cargo based on a channel model as proposed in the above embodiment.

[0090] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0091] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a large-scale cargo transportation passability assessment method based on a channel model as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0092] Example 2, assuming fusion results The credibility is ;

[0093] Credibility It corresponds to the output result of the multidimensional sensor data fusion formula in the invention process, that is, The credibility evaluation of the fusion result A quantitative assessment of the accuracy and reliability of a It can be obtained by calculating the difference between the fusion result and the actual sensor data. This is an evaluation indicator of the data fusion effect and is used to determine the subsequent path planning and obstacle avoidance operations.

[0094] ;

[0095] in, is the actual data of the ith sensor at time t, is the data of the sensor at time t after data fusion;

[0096] If the credibility of the multi-source fusion result F(t) If it is greater than the first threshold, it is determined that the accuracy of the environment model and the channel model is high, and normal path planning is performed; >First Threshold Path planning;

[0097] If the credibility of the multi-source fusion result F(t) If the value is less than the second threshold, it is determined that the accuracy of the environment model and the channel model is low, and data fusion and model update are performed again; <Second Threshold Reintegrate data;

[0098] If the credibility of the multi-source fusion result F(t) If the value is between the second threshold and the first threshold, the accuracy of the environment model and the channel model is determined to be medium, and cautious path planning is performed; the second threshold ≤ CF(t) ≤ the first threshold Plan your route carefully.

[0099] At the same time, in order to verify the effect of the present invention, simulation data was used for testing. The following parameters were set in the simulation environment: number of obstacles: 20;

[0100] Sensor sampling frequency: 10Hz

[0101] Experiment time: 60 seconds

[0102] The method of the present invention is compared with the traditional path planning method (based only on single sensor data) to evaluate the following indicators: path planning success rate, average number of obstacle avoidances, and average transportation time.

[0103] The following table shows the comparison results:

[0104] index Traditional methods Method of the present invention Path planning success rate (%) 75 95 Average obstacle avoidance times 12 8 Average transport time (seconds) 90 70

[0105] It can be seen from the results that the method of the present invention is superior to the traditional method in terms of path planning success rate, obstacle avoidance times and transportation time. In summary, the present invention adopts a multi-sensor data fusion algorithm to comprehensively process multi-source data, generate a more accurate environmental model and channel model, and effectively improve the accuracy of the evaluation results. It also adopts Kalman filtering and a multi-sensor data fusion algorithm to comprehensively process multi-source data, generate a more accurate environmental model and channel model, and effectively improve the accuracy of the evaluation results. The present invention combines real-time data processing and intelligent obstacle avoidance technology to dynamically evaluate the passability of large goods, provide a real-time transportation path optimization solution, and achieve optimal path planning by comprehensively considering environmental conditions, obstacle information and transportation paths, improve transportation efficiency, and reduce transportation risks and costs.

[0106] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating the transportability of large cargo based on a channel model, characterized in that: The method comprises the following steps: Formulate a multi-dimensional sensor data fusion strategy; that is, pre-process the different data collected by multiple sensors deployed at key nodes and large cargo along the transportation route, and use data fusion algorithms to integrate multi-source data to generate a comprehensive and accurate environmental model and channel model; Edge computing real-time data processing and evaluation: that is, edge computing devices pre-deployed at key nodes of the transportation path receive real-time sensor data, quickly process and analyze the data, update and optimize the channel model, and adjust it according to new environmental data to ensure the dynamic and accuracy of the model; Based on the real-time updated channel model and obstacle information, an intelligent obstacle avoidance algorithm is used to plan obstacle avoidance paths to ensure that the obstacle avoidance paths can ensure the safe passage of large goods while minimizing transportation time and costs; Among them, the data is preprocessed by using a Gaussian filter function After processing, the filtered data is expressed as: ； in, is the standard deviation parameter of Gaussian filtering, Represents sensor data; the data fusion algorithm includes: data normalization and weighted summation to perform multi-source data fusion; Among them, the preprocessed data is normalized to obtain normalized data Then the normalization function It is expressed as: = ； Among them, the multi-source data is fused by weighted summation, and the fusion result It is expressed as: = ； Represents the weight, which is determined by Kalman filtering. The fusion result in the formula Indicates at time The comprehensive environment model and channel model data after all sensor data are fused; Based on the fusion results of multi-source data, a high-order integral function is used For feature extraction, we have: = ; in, To fuse data The attenuation coefficient of the high-order integral feature extraction part controls the influence of the data in the past; Use the feature extracted data to model the channel To update, the model is updated using the Kalman filter algorithm: ； in, is the Kalman gain, H is the observation matrix; Use the updated channel model to evaluate the passability of large cargo, and evaluate the function It is expressed as: = ； in, is the weight; β is the attenuation coefficient used for the evaluation part of the channel model C(t), which controls the attenuation effect of the channel model over time and affects the weight distribution in the real-time passability evaluation; for The mean of .

2. The method for evaluating the transportability of large-sized cargo based on a channel model according to claim 1 is characterized by: Real-time channel model and sensor data To identify obstacles, identification function: ; Among them, the attenuation coefficient Controls the influence of data in the past, smoothing parameters Used to adjust the sensitivity of the recognition results. represents the comprehensive obstacle recognition result at time t; Detailed analysis of the type, location and size of obstacles. Obstacle information analysis results: = ； in, and Represents the mean and standard deviation, respectively, used to standardize and normalize obstacle data and obstacle information analysis results Represents the result of obstacle analysis at time t.

3. The method for evaluating the transportability of large-sized cargo based on a channel model according to claim 2 is characterized by: Analysis results based on channel model C(t) and obstacle information , use intelligent obstacle avoidance algorithm to plan obstacle avoidance path, path planning function It is expressed as: ； Among them, P is the set of all possible paths, k is the adjustment parameter, which controls the relationship between the channel model and obstacles; is the weight parameter to adjust the impact of obstacles in path planning. represents the path position at time τ, Indicates the path location Analysis results of obstacle information The Euclidean distance between .

4. The method for evaluating the transportability of large-sized cargo based on a channel model according to claim 3 is characterized by: Assume the fusion result The credibility is ； in, is the actual data of the ith sensor at time t, is the data of the sensor at time t after data fusion; If the fusion result Credibility If it is greater than the first threshold, it is determined that the accuracy of the environment model and the channel model is high, and normal path planning is performed; If the fusion result Credibility If the value is less than the second threshold, it is determined that the accuracy of the environment model and the channel model is low, and data fusion and model update are performed again; If the fusion result Credibility If it is between the second threshold and the first threshold, it is determined that the accuracy of the environment model and the channel model is medium, and cautious path planning is performed.

5. A large-piece cargo transportation passability assessment system based on a channel model, the system is applied to a large-piece cargo transportation passability assessment method based on a channel model as claimed in any one of claims 1 to 4, characterized in that: The system includes the following modules: The multi-dimensional sensor data fusion module processes the different data collected by various sensors through the Gaussian filter function, and fuses the multi-source data through data normalization and weighted summation to generate a comprehensive and accurate environment model and channel model; The real-time data processing and evaluation module uses a high-order integral function to extract features based on the fusion results of multi-source data, updates the channel model with the extracted data, and uses the updated channel model to evaluate the passability of large cargo; The intelligent obstacle avoidance module plans the obstacle avoidance path through an intelligent obstacle avoidance algorithm based on the real-time updated channel model and obstacle information.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for evaluating the transportability of large-scale cargo based on a channel model as described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for evaluating the transportability of large-scale cargo based on a channel model as described in any one of claims 1 to 4 are implemented.

Images