Intelligent storage space optimization method based on digital twinning technology

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent storage space optimization method based on a digital twin technology. The method comprises the following steps: collecting original data, and preprocessing the original data to obtain preprocessed data; constructing a digital twinborn model based on the preprocessed data; based on a digital twin model, a self-adaptive probability space distribution optimization algorithm under multi-factor guidance is introduced, a storage space layout is designed, and the storage space layout is dynamically adjusted in combination with original cargo data. The technical problems that a traditional storage space layout mode is low in storage space utilization rate and unbalanced in resource allocation due to the fact that the accuracy of processing and analyzing storage environment, goods information and the like is low are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent storage space optimization method based on digital twin technology. Background Art

[0002] With the rapid development of the logistics industry and the continuous growth of warehousing business, storage space management has become a core link in modern logistics systems. Traditional storage space layout methods are mostly designed based on artificial rules or static configuration methods. They rely on preset cargo classification, historical circulation experience and fixed warehouse structure parameters. They lack dynamic perception and adaptive adjustment capabilities and are difficult to cope with realistic application scenarios such as high cargo mobility, high operation frequency and changing demand structure. In multi-category, multi-batch and high-frequency warehousing operations, static layout methods often lead to problems such as low space utilization, channel congestion, long operation paths, low handling efficiency and frequent operation conflicts, which seriously restrict the operation efficiency and service capabilities of the warehousing system.

[0003] Therefore, the above technology has technical problems such as low utilization of storage space and unbalanced resource allocation due to low accuracy in processing and analyzing the storage environment, cargo information, etc. Summary of the invention

[0004] The present invention provides an intelligent storage space optimization method based on digital twin technology to solve the technical problems of low storage space utilization and unbalanced resource allocation caused by low accuracy of processing and analysis of storage environment, cargo information, etc. in traditional storage space layout.

[0005] The present invention provides an intelligent storage space optimization method based on digital twin technology, which specifically includes the following technical solutions: An intelligent storage space optimization method based on digital twin technology includes the following steps: S1. Collect raw data and preprocess the raw data to obtain preprocessed data; build a digital twin model based on the preprocessed data; S2. Based on the digital twin model, an adaptive probability spatial distribution optimization algorithm guided by multiple factors is introduced to design the storage space layout, and the storage space layout is dynamically adjusted in combination with the original cargo data.

[0006] Preferably, the S1 specifically includes: In the process of building the digital twin model, the physical space of the warehouse is geometrically modeled based on the physical components in the preprocessed data. On the basis of the completion of the geometric modeling, the topological modeling logic is introduced to construct a topological map structure, and through the topological mapping operation, the constructed topological map structure is bound to the preprocessed data.

[0007] Preferably, the S1 specifically includes: Real-time state variables are defined for each spatial node in the topological graph structure, and a state vector is constructed based on the real-time state variables. A vector field modeling method is used to bind each state vector to the corresponding spatial node, and a multi-dimensional state field is constructed to express the distribution characteristics of the state vector.

[0008] Preferably, the S1 specifically includes: In the process of building the digital twin model, a state update mechanism is introduced, and the warehouse state transfer function and reward function are set to enable the digital twin model to have time-varying response capabilities.

[0009] Preferably, the S1 specifically includes: In the status update mechanism, based on the warehouse operation data retrieved in real time from the warehouse entry and exit records, the action function is dynamically called to update the real-time status variables of each spatial node.

[0010] Preferably, the S2 specifically includes: Based on the digital twin model, the storage space is discretely divided to generate spatial sub-areas. The original cargo data is collected by sensors deployed in each spatial sub-area, and the original cargo data is constructed into attribute vectors and normalized. The normalized attribute vectors are weighted and superimposed to obtain the priority factor of the cargo.

[0011] Preferably, the S2 specifically includes: In the process of implementing the adaptive probabilistic spatial distribution optimization algorithm guided by multiple factors, the attractiveness weight of the spatial sub-area is obtained based on the location characteristics in the preprocessed data, the spatial environment characteristics in the warehouse operation data, and the historical task density.

[0012] Preferably, the S2 specifically includes: Based on the priority factor of the goods and the attractiveness weight of the space sub-region, the sub-region allocation probability of the goods is calculated; based on the sub-region allocation probability of the goods, the storage space layout is carried out to obtain the distribution state of the storage space.

[0013] Preferably, the S2 specifically includes: In the process of implementing the adaptive probabilistic spatial distribution optimization algorithm guided by multiple factors, the usage density of the spatial sub-region is calculated based on the sub-region allocation probability of the goods; the sub-region allocation probability of the goods is adjusted by calculating the gradient of the usage density of the spatial sub-region and combining it with the attractiveness weight of the spatial sub-region.

[0014] Preferably, the S2 specifically includes: In the process of implementing the adaptive probability spatial distribution optimization algorithm guided by multiple factors, a prediction error feedback mechanism is introduced. Based on historical cargo data, a prediction model is constructed through a neural network to obtain the expected frequency of cargo in and out of the warehouse. Based on the expected frequency of cargo in and out of the warehouse and the actual frequency of cargo in and out of the warehouse, the prediction error is defined. Based on the prediction error, the priority factor of the cargo is corrected, and the corrected priority factor is used to calculate the sub-area allocation probability of the cargo in the subsequent rounds, forming a closed-loop optimization process.

[0015] The beneficial effects of the technical solution of the present invention are: 1. By building a digital twin model, the equipment status, cargo distribution, task flow, etc. in the storage space can be mapped in real time, the storage geometry and accessibility topological relationship can be accurately expressed, the space utilization can be maximized, the concentrated congestion of cargo or the vacancy of resources can be avoided, and the spatial scheduling accuracy and flexibility of the storage can be improved.

[0016] 2. By constructing an adaptive probabilistic spatial distribution optimization algorithm guided by multiple factors, the cargo data of each spatial sub-region is taken as input, and the imbalance of the current spatial density is measured by calculating the usage density of the spatial sub-region. The spatial distribution structure is automatically optimized through the gradient descent method to realize the intelligent migration of cargo flow from dense areas to sparse areas, and the spatial distribution strategy is adaptively adjusted to improve the layout robustness and intelligence level under complex tasks and changing environments.

[0017] 3. By establishing a neural network prediction model driven by historical data, the future frequency of goods entering and leaving the warehouse is predicted and compared with the actual frequency of goods entering and leaving the warehouse. According to the prediction error, the priority factor of the goods is dynamically adjusted to improve the responsiveness to changes in external demand, enhance the foresight and anti-disturbance capabilities of the layout strategy, and avoid resource mismatches caused by inaccurate demand forecasts. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of an intelligent storage space optimization method based on digital twin technology described in the present invention. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0021] The following is a detailed description of a specific solution of an intelligent storage space optimization method based on digital twin technology provided by the present invention in conjunction with the accompanying drawings.

[0022] See attached Figure 1 , which shows a flow chart of an intelligent storage space optimization method based on digital twin technology provided by an embodiment of the present invention, the method comprising the following steps: S1. Collect raw data and preprocess the raw data to obtain preprocessed data; build a digital twin model based on the preprocessed data; The raw data is acquired by deploying data acquisition equipment in the storage environment, and the raw data includes information data such as cargo information, equipment status, environmental changes, item storage location, access frequency, physical components, etc.; the data acquisition equipment includes environmental sensors, RFID tags and scanners, barcode scanners, video surveillance equipment, robots or automation equipment, environmental monitoring equipment, etc.; the raw data is preprocessed to obtain preprocessed data; the preprocessing process includes data cleaning (such as removing repeated data, filling missing values ​​by methods such as interpolation, mean filling, nearest neighbor interpolation, etc.), data conversion and standardization (such as converting data from different devices to the same time scale to ensure that all data have consistent timestamps, and converting units for physical quantities in different units), data smoothing and noise reduction (such as moving average, Gaussian filtering), data aggregation (such as aggregating data according to time period), data feature extraction, etc. In the preprocessing process, existing technical means well known to those skilled in the art are adopted, which will not be elaborated here; Furthermore, a digital twin model is constructed based on the preprocessed data; the digital twin model can map the operating status of the storage space in real time and provide a basis for subsequent space optimization; the specific process is as follows: First, the storage space needs to be geometrically modeled and topologically modeled; specifically, geometric modeling uses three-dimensional modeling technology (such as building information modeling BIM modeling technology or open source modeling platform Open3D) to accurately restore the key components in the storage space based on the physical components in the preprocessed data (such as the location and size of the shelves, the width and length of the aisles, the occupied volume of fixed equipment, the boundary range of the working area, etc.); the physical components are expressed in a three-dimensional coordinate system. Its spatial position and geometric properties make the digital twin model highly restored in the structural dimension. The spatial scene output by geometric modeling has a complete structural boundary and spatial constraint relationship, which is the physical basis for building a highly simulated virtual storage environment; On the basis of geometric modeling, topological modeling logic is introduced to give the digital twin model semantic connection and accessibility; each geometric entity (such as cargo compartments, entrances and exits, and cargo loading points) is abstracted as a node (i.e., spatial node) in the topological map structure, and the physical accessibility relationship or operation path between the geometric entities is defined as an edge, and attributes (such as traffic status, traffic time, channel capacity, constraints, etc.) are added to the edge to establish a complete topological map structure. The above process is topological modeling, which can convert the logic of "shelf A can reach exit C through channel B" in reality into a path sequence of A→B→C in the topological map structure; further through the topological mapping operation, the constructed topological map structure is bound to the preprocessed data, so that the digital twin model has core capabilities such as path search, connectivity analysis, area division, and connectivity verification; After the geometric modeling and topological modeling are completed in coordination, the state expression stage is entered, that is, the real-time state variables are defined for each spatial node in the topological spectrum structure, mainly including the current volume occupancy rate, number of cargo stacking layers, access frequency, cargo type coding, operation task density, regional temperature and humidity, vibration amplitude, equipment workload and other multi-dimensional indicators; based on the real-time state variables, a state vector is constructed. In order to express the distribution characteristics of the state vector in the entire space, a vector field modeling method is used to bind each state vector to its corresponding spatial node, and a multi-dimensional state field is constructed to describe the attribute set presented by any point in the storage space at a certain moment; Furthermore, in order to enable the digital twin model to have dynamic evolution capabilities and to maintain a synchronous mapping of the actual warehouse status during actual operation, a state update mechanism is introduced to enable the digital twin model to have time-varying response capabilities. The state update mechanism is based on the Markov decision process (MDP) theory, and sets the warehouse state transfer function and reward function. The warehouse state transfer function defines how the warehouse state is transferred from the current state to the next state after a certain warehouse operation (such as goods shelving, picking, replenishment, etc.) is executed. Factors considered in the state transfer process include changes in space occupancy, channel accessibility, and cargo flow priority. The reward function uses space utilization improvement, cargo turnover rate, response time, etc. as evaluation indicators to guide the evolution of the warehouse space toward the target optimal state. The data of the factors involved in the warehouse state transfer function and the reward function are all from the preprocessed data. The warehouse state transfer function and the reward function are both technical means well known to technicians in this field, and will not be elaborated here. In the state update mechanism, warehouse operation data (including goods entry records, outbound behavior, path usage frequency, etc.) are retrieved in real time from the warehouse entry and exit records, and used as the basis for the state update of the digital twin model. The real-time state variables of each spatial node are updated by dynamically calling the action function. For example, when the goods are transferred from shelf A to shelf B, the volume occupancy rate, access frequency and other parameters of the two spatial nodes will be automatically modified through the action function, and the traffic load distribution of the entire topology map will be adjusted to ensure that the digital twin model can respond in real time with actual operations. For variables that are difficult to observe directly, such as equipment failure risk, operating efficiency trend, and path congestion probability, a particle filter is introduced for state estimation, a hypothetical trajectory is established, and the possibility of the hypothetical trajectory is evaluated based on the preprocessed data, so as to infer the potential state of the warehouse that is closest to the actual state. The particle filter and action function are technical means well known to those skilled in the art and will not be elaborated here; After the above process, the digital twin model is obtained.

[0023] S2. Based on the digital twin model, an adaptive probability spatial distribution optimization algorithm guided by multiple factors is introduced to design the storage space layout, and the storage space layout is dynamically adjusted in combination with the original cargo data.

[0024] Based on the digital twin model, an adaptive probability spatial distribution optimization algorithm guided by multiple factors is introduced, and real-time data input, prediction model and prediction error feedback mechanism are integrated to dynamically optimize the warehouse layout. The specific implementation process is as follows: First, based on the digital twin model, the entire storage space is discretely divided through the existing automated geometric division technology to generate spatial sub-areas; the original cargo data is collected through sensors deployed in each spatial sub-area, including the basic attributes of all cargoes, storage location, current task scheduling status, and historical storage trajectory; the basic attributes of the cargo include volume, quality, frequency of entry and exit, temperature and humidity sensitivity (calculated by modeling the temperature and humidity fluctuation range under different temperatures and humidities), and handling costs; the above original cargo data constitutes an attribute vector, and in order to unify the order of magnitude differences between different attributes, the attribute vector is normalized to eliminate the dimensional effect. The normalization method uses the extreme difference standardization method, the purpose of which is to make the variables of all dimensions on the same numerical scale in the subsequent weight calculation, so as to prevent the variables of a certain dimension from having a dominant influence on the calculation results due to their large values; After normalization, in order to quantify the sensitivity or priority demand of each cargo for storage space, define the cargo priority factor , indicating the The spatial scheduling weight of a cargo in the entire warehouse is generated by weighted superposition of multiple attribute vectors of the cargo; At the same time, the concept of regional attractiveness is introduced into the storage space. The attractiveness weight of each spatial sub-region is obtained through experimental fitting based on parameters such as location characteristics (such as channel accessibility), spatial environmental characteristics (such as temperature and humidity control capabilities, equipment support), and historical task density. Among them, the location characteristics come from pre-processed data, the spatial environmental characteristics come from storage operation data, and the historical task density comes from an existing database. Furthermore, based on the priority factor of the goods and the attractiveness weight of the spatial sub-region, the probability of sub-region allocation of the goods is calculated. The specific formula is: , in, It is Goods are assigned to The probability of each spatial sub-region describes the distribution tendency of each commodity in different spatial sub-regions, that is, the probability of the commodity being allocated to a sub-region; It is Priority factor for each shipment; Indicates The attraction weight of each spatial sub-region; It is the number of spatial sub-areas obtained after dividing the storage space; Specifically, the storage space layout is performed based on the probability of sub-area allocation of goods to obtain the distribution state of the storage space; each item tends to be allocated to an area with higher attractiveness (such as an area close to the main channel or with better temperature and humidity control capabilities); Furthermore, the goods included in the scheduling optimization in the storage space are traversed, the sub-region allocation probability of each goods is multiplied and summed by the three-dimensional space volume occupied by the goods, and the usage density of each space sub-region is calculated to measure whether a certain space sub-region is currently in a high-density, oversaturated or resource-wasting state; by calculating the gradient of the usage density of the space sub-region, the sub-region allocation probability of the goods is adjusted; the specific adjustment formula is: , in, is Moment Goods are assigned to The probability of a spatial sub-region; is Moment Goods are assigned to The probability of a spatial sub-region; is the probability adjustment coefficient, which is determined according to the expert experience method and has a value range of ; is The gradient of the usage density of the spatial sub-region at a certain moment, wherein the gradient calculation is a technical means well known to those skilled in the art and will not be described in detail here; It is The three-dimensional space volume occupied by each cargo; Finally, a prediction error feedback mechanism is introduced to correct the layout error caused by inaccurate external task demand estimation. Based on the historical cargo data called from the existing database, a prediction model is constructed through the existing neural network to predict the expected frequency of entry and exit of each cargo; the neural network is a technical means well known to those skilled in the art and will not be described here; based on the expected frequency of entry and exit of the cargo, combined with the actual frequency of entry and exit of the cargo, the prediction error is defined, and based on the prediction error, the priority factor of the cargo is corrected to obtain the corrected priority factor; the specific formula is: , in, is a small positive real number used to prevent the denominator from being zero, and its value is ; is Moment The expected frequency of goods entering and leaving the warehouse; is Moment The actual frequency of goods entering and leaving the warehouse comes from the existing database; is the revised priority factor, which replaces the priority factor before the revision , and is used to calculate the probability of sub-area allocation of goods in subsequent rounds, thus forming a closed-loop optimization process of "prediction-execution-feedback-adjustment". The continuous correction of the priority factor of goods realizes dynamic adaptive layout, so that the storage space not only responds to static data, but also continuously learns and corrects strategies from the operation history.

[0025] In summary, an intelligent storage space optimization method based on digital twin technology was completed.

[0026] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0027] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0028] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent storage space optimization method based on digital twin technology, characterized in that: The following steps are involved: S1. Collecting raw data and preprocessing the raw data to obtain preprocessed data; Build a digital twin model based on the preprocessed data; S2. Based on the digital twin model, an adaptive probability spatial distribution optimization algorithm guided by multiple factors is introduced to design the storage space layout, and the storage space layout is dynamically adjusted in combination with the original cargo data.

2. According to claim 1, a smart storage space optimization method based on digital twin technology is characterized in that: The S1 specifically includes: In the process of building the digital twin model, the physical space of the warehouse is geometrically modeled based on the physical components in the preprocessed data. On the basis of the completion of the geometric modeling, the topological modeling logic is introduced to construct a topological map structure, and through the topological mapping operation, the constructed topological map structure is bound to the preprocessed data.

3. According to claim 2, a smart storage space optimization method based on digital twin technology is characterized in that: The S1 specifically includes: Real-time state variables are defined for each spatial node in the topological graph structure, and a state vector is constructed based on the real-time state variables. A vector field modeling method is used to bind each state vector to the corresponding spatial node, and a multi-dimensional state field is constructed to express the distribution characteristics of the state vector.

4. According to claim 3, the intelligent storage space optimization method based on digital twin technology is characterized in that: The S1 specifically includes: In the process of building the digital twin model, a state update mechanism is introduced, and the warehouse state transfer function and reward function are set to enable the digital twin model to have time-varying response capabilities.

5. According to claim 4, a smart storage space optimization method based on digital twin technology is characterized in that: The S1 specifically includes: In the status update mechanism, based on the warehouse operation data retrieved in real time from the warehouse entry and exit records, the action function is dynamically called to update the real-time status variables of each spatial node.

6. According to claim 5, a smart storage space optimization method based on digital twin technology is characterized in that: The S2 specifically includes: Based on the digital twin model, the storage space is discretely divided to generate spatial sub-areas. The original cargo data is collected by sensors deployed in each spatial sub-area, and the original cargo data is constructed into attribute vectors and normalized. The normalized attribute vectors are weighted and superimposed to obtain the priority factor of the cargo.

7. The intelligent storage space optimization method based on digital twin technology according to claim 6 is characterized in that: The S2 specifically includes: In the process of implementing the adaptive probabilistic spatial distribution optimization algorithm guided by multiple factors, the attractiveness weight of the spatial sub-area is obtained based on the location characteristics in the preprocessed data, the spatial environment characteristics in the warehouse operation data, and the historical task density.

8. The intelligent storage space optimization method based on digital twin technology according to claim 7 is characterized in that: The S2 specifically includes: Based on the priority factor of the goods and the attractiveness weight of the space sub-region, the sub-region allocation probability of the goods is calculated; based on the sub-region allocation probability of the goods, the storage space layout is carried out to obtain the distribution state of the storage space.

9. The intelligent storage space optimization method based on digital twin technology according to claim 8 is characterized in that: The S2 specifically includes: In the process of implementing the adaptive probabilistic spatial distribution optimization algorithm guided by multiple factors, the usage density of the spatial sub-region is calculated based on the sub-region allocation probability of the goods; the sub-region allocation probability of the goods is adjusted by calculating the gradient of the usage density of the spatial sub-region and combining it with the attractiveness weight of the spatial sub-region.

10. The intelligent storage space optimization method based on digital twin technology according to claim 9 is characterized in that: The S2 specifically includes: In the process of implementing the adaptive probability spatial distribution optimization algorithm guided by multiple factors, a prediction error feedback mechanism is introduced. Based on historical cargo data, a prediction model is constructed through a neural network to obtain the expected frequency of cargo in and out of the warehouse. Based on the expected frequency of cargo in and out of the warehouse and the actual frequency of cargo in and out of the warehouse, the prediction error is defined. Based on the prediction error, the priority factor of the cargo is corrected, and the corrected priority factor is used to calculate the sub-area allocation probability of the cargo in the subsequent rounds, forming a closed-loop optimization process.

Images