Engineering material intelligent allocation system and method

Abstract

The invention discloses an engineering material intelligent allocation system and method, and the system comprises a multi-source data collection module which is used for collecting engineering material stock data, transportation equipment state data, construction site environment data and construction progress data in real time through Internet of Things equipment; the intelligent analysis module is used for multi-dimensional data fusion analysis and intelligent algorithm driving to carry out dynamic optimization management of the whole process of the engineering materials; and the dynamic scheduling decision module is used for integrating a multi-objective optimization algorithm and a real-time feedback mechanism, and outputting a scheduling instruction set including a transportation scheme, a storage scheme and an emergency scheme, and through implementation of the system, dynamic optimization management and credible traceability of the whole process of engineering materials are realized. The system deeply integrates the Internet of Things, digital twinning, block chain and artificial intelligence technologies, significantly improves the material allocation efficiency, the cost control capability and the emergency response level, guarantees the data security and the multi-party cooperation transparency, and has certain use value and popularization value.

Description

Technical Field

[0001] The present invention relates to the technical field of material allocation systems, and in particular to an intelligent allocation system and method for engineering materials. Background Art

[0002] In the traditional field of construction material allocation, material management relies heavily on manual experience and static plans, which have significant limitations. First, data collection is fragmented, and key information such as material inventory, transportation status, and construction site environment is often scattered across different systems. There is a lack of real-time integration capabilities, making it difficult for managers to obtain a timely global view. Second, demand forecasting methods are single, usually based on linear extrapolation of historical consumption data, without fully considering external factors such as dynamic changes in construction progress and meteorological and geological conditions, which can easily lead to material shortages or redundancies. For example, sudden rainfall may delay transportation, but traditional systems are unable to quickly adjust demand forecasts and scheduling plans. In addition, route optimization often uses static algorithms that do not combine real-time traffic conditions and vehicle performance parameters, resulting in high transportation costs and low efficiency.

[0003] In existing technologies, some intelligent solutions have attempted to introduce the Internet of Things or big data technologies, but the following problems still exist: (1) Insufficient multi-source data fusion capabilities and low positioning accuracy (such as relying on traditional GPS positioning) make it difficult to achieve accurate tracking of materials; (2) Dynamic scheduling algorithms lack multi-objective collaborative optimization capabilities and often use a single indicator (such as cost or time) as the optimization target, making it difficult to balance complex factors such as construction key path constraints and resource reuse priorities; (3) The emergency response mechanism is weak, and abnormal warnings rely on manual judgment, resulting in delayed responses; (4) Data credibility and traceability are poor, key decision records are easily tampered with, and disputes are easily caused when multiple parties collaborate. For example, a large-scale infrastructure project once suffered from unclear responsibility between the construction party and the supplier due to the lack of transparency in supply chain delay data, resulting in construction delays and economic losses.

[0004] Therefore, an intelligent deployment system and method for engineering materials is needed to address the deficiencies in the existing technology. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent allocation system and method for engineering materials, aiming to solve the above problems.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: an intelligent deployment system for construction materials, comprising:

[0007] Multi-source data acquisition module, used to collect real-time data on construction material inventory, transportation equipment status, construction site environment, and construction progress through IoT devices;

[0008] Intelligent analysis module, used for multi-dimensional data fusion analysis and intelligent algorithm-driven dynamic optimization management of the entire process of engineering materials;

[0009] Dynamic scheduling decision module, which integrates multi-objective optimization algorithms and real-time feedback mechanisms to output a scheduling instruction set including transportation plans, warehousing plans, and emergency plans;

[0010] The digital twin execution module connects to the BIM platform to achieve 3D visual simulation and execution monitoring of the scheduling plan;

[0011] The blockchain evidence storage module is used to store key decision-making data and generate an immutable chain of dispatch records. By building a multi-module collaborative intelligent dispatch system, dynamic optimization management and trusted traceability are achieved throughout the entire engineering material process. The system deeply integrates the Internet of Things, digital twins, blockchain, and artificial intelligence technologies, significantly improving material dispatch efficiency, cost control, and emergency response capabilities, while ensuring data security and transparency in multi-party collaboration.

[0012] Furthermore, the multi-source data acquisition module includes:

[0013] UWB positioning array is used to be deployed in the engineering material storage area and perform accurate three-dimensional spatial positioning of engineering material storage;

[0014] Intelligent sensor module, used to collect key parameters of the transport vehicle during transportation in real time;

[0015] Edge computing nodes are used to deploy localized data processing centers on construction sites;

[0016] The UWB positioning array and the intelligent sensing module are both connected to the edge computing node.

[0017] Furthermore, the intelligent analysis module includes a load detection unit, a temperature and humidity monitoring unit, and a tire pressure monitoring unit. The load detection unit is used to monitor the cargo weight of the transport vehicle in real time. The temperature and humidity monitoring unit is used to continuously monitor the ambient temperature and humidity in the cargo box to ensure the quality of materials that are sensitive to temperature and humidity. The tire pressure monitoring unit is used to detect tire pressure and temperature in real time.

[0018] Furthermore, the intelligent analysis module includes a material demand prediction unit, a path optimization unit and an abnormal warning unit. The material demand prediction unit is used to construct a demand prediction model with multi-factor coupling, the path optimization unit is used to generate a transportation path using a dynamic programming algorithm under time and space constraints, and the abnormal warning unit is used as an early warning mechanism when materials are in short supply.

[0019] Furthermore, the material demand forecasting unit performs the following steps:

[0020] Step A1: Decompose the construction phases based on the BIM model and extract the material demand baseline value Q_base corresponding to each phase;

[0021] Step A2: Build a dual-channel prediction model:

[0022] The first channel uses LSTM neural network to process the historical construction progress time series {X_t} and output the progress impact factor α;

[0023] The second channel uses the environmental analysis network of the Attention mechanism to process real-time meteorological data {E_t} and geological data {G_t} and output the environmental correction factor β;

[0024] Step A3: Calculate the supply chain response coefficient δ:

[0025] δ=w1×(1-logistics delay rate)+w2×supplier credit rating,

[0026] Where w1 and w2 are dynamic weight parameters, and w1+w2=1;

[0027] Step A4: Generate final demand forecast value:

[0028] Q_final=Q_base×(1+α)×(1+β)×δ;

[0029] Step A5: When it is detected that the construction progress deviation rate ΔP exceeds 5%, the demand recalculation is triggered:

[0030] Q_final'=Q_final×[1+0.2×sign(ΔP)×|ΔP|^0.5].

[0031] Furthermore, the dynamic scheduling decision module includes:

[0032] A multi-objective optimization engine that constructs a decision space with the following dimensions:

[0033] Time dimension: the latest arrival time under the construction critical path constraint;

[0034] Cost dimension: Dynamic transportation cost model C = Σ(road section fuel consumption cost + time cost + risk cost);

[0035] Resource dimension: Material reuse priority matrix P = [p_ij]_{m×n};

[0036] Real-time adjustment strategy library, storing scheduling strategies for various typical scenarios;

[0037] The decision verification unit is equipped with a Monte Carlo simulator to verify the reliability of the solution.

[0038] Furthermore, the digital twin execution module includes:

[0039] Dynamic update interface of BIM model, supporting automatic association of material dispatch data and construction progress nodes;

[0040] Virtual-reality mapping engine, establishing a two-way data channel between physical entities and digital models;

[0041] The deviation warning unit triggers a level 3 alarm when the actual execution progress deviates from the simulation plan by more than a threshold.

[0042] Furthermore, the blockchain evidence storage module adopts:

[0043] Dual-chain storage architecture, including scheduling decision chain and material traceability chain;

[0044] Smart contract template library, including transportation contracts, warehousing contracts, and quality traceability contracts;

[0045] The cross-chain verification mechanism realizes data privacy protection of different participants through zero-knowledge proof.

[0046] A method for intelligent allocation of engineering materials, comprising the following steps:

[0047] Step S1: Build a full-factor digital twin of materials, equipment, and environment, and establish a spatiotemporal alignment relationship between multi-source data;

[0048] Step S2: Perform multi-scale demand forecasting based on the improved Transformer model and output forecast results including baseline demand, elastic demand, and emergency demand;

[0049] Step S3: Use a multi-agent reinforcement learning algorithm to generate a Pareto frontier solution set, where each agent corresponds to a type of material scheduling resource;

[0050] Step S4: Perform three-dimensional visualization deduction of the scheme through the digital twin platform and calculate the scheme reliability index;

[0051] Step S5: Execute dynamic scheduling and monitor in real time, and trigger solution reconstruction when it is detected that the execution deviation exceeds the adaptive threshold.

[0052] Substantial effects of the present invention:

[0053] 1. This invention achieves dynamic optimization management and trusted traceability of the entire process of engineering materials by building a multi-module collaborative intelligent deployment system. The system deeply integrates the Internet of Things, digital twins, blockchain, and artificial intelligence technologies, significantly improving material deployment efficiency, cost control capabilities, and emergency response capabilities, while ensuring data security and transparency of multi-party collaboration.

[0054] 2. In this invention, the multi-source data acquisition module uses UWB positioning arrays and intelligent sensors to achieve three-dimensional spatial positioning of materials and real-time monitoring of key parameters of transportation vehicles, greatly improving data acquisition efficiency; edge computing nodes support localized data processing, reducing cloud transmission delays and ensuring short response times for key commands;

[0055] 3. In the present invention, the material demand forecasting unit adopts a dual-channel model, integrating multiple factors such as construction progress, meteorological geology, etc., and the forecasting accuracy is improved compared with traditional methods; the dynamic scheduling decision module generates a Pareto frontier solution set through a multi-objective optimization engine, effectively reducing the overall cost, and has certain use value and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative work.

[0057] Figure 1 This is a system block diagram of the present invention.

[0058] Figure 2 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0059] For ease of understanding of the present invention, the present invention will be described in more detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that when an element is described as "fixed to" another element, it can be directly on the other element, or there can be one or more centered elements therebetween. When an element is described as "connected to" another element, it can be directly connected to the other element, or there can be one or more centered elements therebetween. The terms "vertical", "horizontal", "left", "right" and similar expressions used in this specification are for illustrative purposes only.

[0060] Unless otherwise defined, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification are intended solely for the purpose of describing specific embodiments and are not intended to limit the invention. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items.

[0061] like Figure 1 As shown, an intelligent deployment system for engineering materials includes:

[0062] Multi-source data acquisition module, used to collect real-time data on construction material inventory, transportation equipment status, construction site environment, and construction progress through IoT devices;

[0063] Intelligent analysis module, used for multi-dimensional data fusion analysis and intelligent algorithm-driven dynamic optimization management of the entire process of engineering materials;

[0064] Dynamic scheduling decision module, which integrates multi-objective optimization algorithms and real-time feedback mechanisms to output a scheduling instruction set including transportation plans, warehousing plans, and emergency plans;

[0065] The digital twin execution module connects to the BIM platform to achieve 3D visual simulation and execution monitoring of the scheduling plan;

[0066] The blockchain evidence storage module is used to store key decision-making data and generate an unalterable scheduling process record chain.

[0067] As an implementation method, the multi-source data acquisition module includes:

[0068] UWB positioning array is used to be deployed in the engineering material storage area and perform accurate three-dimensional spatial positioning of engineering material storage;

[0069] Intelligent sensor module, used to collect key parameters of the transport vehicle during transportation in real time;

[0070] Edge computing nodes are used to deploy localized data processing centers on construction sites;

[0071] The UWB positioning array and intelligent sensing module are both connected to the edge computing node.

[0072] As an implementation method, the intelligent analysis module includes a load detection unit, a temperature and humidity monitoring unit, and a tire pressure monitoring unit. The load detection unit is used to monitor the cargo weight of the transport vehicle in real time. The temperature and humidity monitoring unit is used to continuously monitor the ambient temperature and humidity in the cargo box to ensure the quality of materials that are sensitive to temperature and humidity. The tire pressure monitoring unit is used to detect tire pressure and temperature in real time.

[0073] The multi-source data acquisition module directly collects raw data in real time through IoT devices (UWB positioning arrays and smart sensors), and transmits the following data to the intelligent analysis module and edge computing nodes: UWB positioning data (three-dimensional coordinates of materials), sensor data (load, temperature and humidity, tire pressure), environmental data (meteorological and geological data), and construction progress data. The UWB positioning array and smart sensors are directly connected to the edge computing nodes via low-latency communication protocols (such as LoRaWAN or ZigBee) for local pre-processing (denoising and compression). The edge computing nodes transmit the processed data to the intelligent analysis module via an API interface (such as RESTful) and simultaneously back up the data to the cloud.

[0074] The intelligent analysis module receives real-time data from the multi-source data acquisition module, as well as historical data (construction progress time series), and transmits the following results to the dynamic scheduling decision module: demand forecast value (Q_final), optimized path plan, and abnormal warning signals (such as material shortage);

[0075] The dynamic scheduling decision module inputs the prediction results and warning signals of the intelligent analysis module and the actual execution status data (such as the location of the transport vehicle) fed back by the digital twin execution module, sends the scheduling instruction set (transportation, warehousing, emergency plan) to the digital twin execution module, and submits the decision record to the blockchain evidence storage module;

[0076] The digital twin execution module receives the scheduling instructions from the dynamic scheduling decision module and the real-time monitoring data (such as material location and environmental status) from the multi-source data acquisition module, feeds back execution deviation data (such as deviation from the actual transportation path) to the dynamic scheduling decision module, and transmits three-dimensional deduction records and operation logs to the blockchain evidence storage module;

[0077] The blockchain evidence storage module receives scheduling instruction records from the dynamic scheduling decision module and deduction logs and operation records from the digital twin execution module. It also provides an on-chain data query interface for external verification. The data flow is closed-loop: multi-source data collection → intelligent analysis → dynamic scheduling → digital twin execution → blockchain evidence storage → feedback to scheduling adjustments.

[0078] As an implementation method, the intelligent analysis module includes a material demand forecasting unit, a path optimization unit and an abnormal warning unit. The material demand forecasting unit is used to construct a demand forecasting model with multi-factor coupling, the path optimization unit is used to generate a transportation path using a dynamic programming algorithm under time and space constraints, and the abnormal warning unit is used as an early warning mechanism when materials are in short supply.

[0079] As an implementation method, the material demand forecasting unit performs the following steps:

[0080] Step A1: Decompose the construction phases based on the BIM model and extract the material demand baseline value Q_base corresponding to each phase;

[0081] Step A2: Build a dual-channel prediction model:

[0082] The first channel uses LSTM neural network to process the historical construction progress time series {X_t} and output the progress impact factor α;

[0083] The second channel uses the environmental analysis network of the Attention mechanism to process real-time meteorological data {E_t} and geological data {G_t} and output the environmental correction factor β;

[0084] Step A3: Calculate the supply chain response coefficient δ:

[0085] δ=w1×(1-logistics delay rate)+w2×supplier credit rating,

[0086] Where w1 and w2 are dynamic weight parameters, and w1+w2=1;

[0087] Step A4: Generate final demand forecast value:

[0088] Q_final=Q_base×(1+α)×(1+β)×δ;

[0089] Step A5: When it is detected that the construction progress deviation rate ΔP exceeds 5%, the demand recalculation is triggered:

[0090] Q_final'=Q_final×[1+0.2×sign(ΔP)×|ΔP|^0.5].

[0091] As an implementation method, the dynamic scheduling decision module includes:

[0092] A multi-objective optimization engine that constructs a decision space with the following dimensions:

[0093] Time dimension: the latest arrival time under the construction critical path constraint;

[0094] Cost dimension: Dynamic transportation cost model C = Σ(road section fuel consumption cost + time cost + risk cost);

[0095] Resource dimension: Material reuse priority matrix P = [p_ij]_{m×n};

[0096] Real-time adjustment strategy library, storing scheduling strategies for various typical scenarios;

[0097] The decision verification unit is equipped with a Monte Carlo simulator to verify the reliability of the solution.

[0098] As an implementation method, the digital twin execution module includes:

[0099] Dynamic update interface of BIM model, supporting automatic association of material dispatch data and construction progress nodes;

[0100] Virtual-reality mapping engine, establishing a two-way data channel between physical entities and digital models;

[0101] The deviation warning unit triggers a level 3 alarm when the actual execution progress deviates from the simulation plan by more than a threshold.

[0102] As an implementation method, the blockchain evidence storage module adopts:

[0103] Dual-chain storage architecture, including scheduling decision chain and material traceability chain;

[0104] Smart contract template library, including transportation contracts, warehousing contracts, and quality traceability contracts;

[0105] The cross-chain verification mechanism realizes data privacy protection of different participants through zero-knowledge proof.

[0106] The digital twin execution module seamlessly connects with the BIM platform, enabling three-dimensional simulation and real-time monitoring of scheduling plans, and increasing the detection rate of construction progress deviations by 50%;

[0107] The adaptive threshold mechanism (such as the initial threshold T0 = μ + 3σ) combined with dynamic adjustment rules reduces invalid alarms by 70% and increases the decision-making efficiency of triggering solution reconstruction by 3 times.

[0108] The blockchain evidence storage module adopts a dual-chain architecture (dispatching decision chain + material traceability chain), and the risk of key data tampering is close to zero;

[0109] The cross-chain verification mechanism and zero-knowledge proof technology achieve mutual trust in multi-party data while protecting privacy, shortening the dispute resolution cycle by 60%.

[0110] like Figure 2 As shown, a method for intelligent allocation of engineering materials includes the following steps:

[0111] Step S1: Build a full-factor digital twin of materials, equipment, and environment, and establish a spatiotemporal alignment relationship between multi-source data;

[0112] Step S2: Perform multi-scale demand forecasting based on the improved Transformer model and output forecast results including baseline demand, elastic demand, and emergency demand;

[0113] Step S3: Use a multi-agent reinforcement learning algorithm to generate a Pareto frontier solution set, where each agent corresponds to a type of material scheduling resource;

[0114] Step S4: Perform three-dimensional visualization deduction of the scheme through the digital twin platform and calculate the scheme reliability index;

[0115] Step S5: Execute dynamic scheduling and monitor in real time, and trigger solution reconstruction when it is detected that the execution deviation exceeds the adaptive threshold.

[0116] As an implementation method, step S3 specifically includes:

[0117] Define a multi-objective optimization function: min F(x) = [f_cost(x),f_time(x),f_risk(x)]

[0118] An improved NSGA-III algorithm is designed, which introduces: a dynamic reference point adjustment mechanism, an individual selection strategy based on congestion entropy, and a construction restricted area constraint processing operator;

[0119] Output the non-dominated solution set and calculate the comprehensive utility value U = Σw_i·N(f_i) of each scheme. The weight w_i is dynamically adjusted with the construction stage.

[0120] As an embodiment, the adaptive threshold setting method in step S5 includes:

[0121] Initial threshold setting: T_0 = μ + 3σ, where μ is the mean of historical data and σ is the standard deviation;

[0122] Dynamic adjustment rules:

[0123] T_{t+1}=T_t×[1+λ×(E_t / E_0-1)],

[0124] Where E_t is the key coefficient of the current construction stage, E_0 is the benchmark coefficient, and λ is the adjustment factor;

[0125] When the threshold alarm is triggered more than 3 times continuously, the manual intervention review process is initiated.

[0126] As an implementation method, the method further includes establishing a material scheduling knowledge graph, including entity types: supplier, transporter, constructor, and supervisor;

[0127] Develop an intelligent question-answering interface based on natural language processing to support multi-modal scheduling solution queries;

[0128] Construct a scheduling effect evaluation system, including 6 first-level indicators and 18 second-level indicators, for system self-optimization

[0129] It should be noted that the preferred embodiments of the present invention are given in the specification and drawings of the present invention. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. These embodiments do not serve as additional limitations on the content of the present invention. The purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. In addition, the above-mentioned technical features continue to be combined with each other to form various embodiments not listed above, which are all considered to be within the scope of the description of the present invention; further, it is obvious to those skilled in the art that improvements or changes can be made based on the above description, and all such improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. An intelligent deployment system for engineering materials, characterized in that: include: Multi-source data acquisition module, used to collect real-time data on construction material inventory, transportation equipment status, construction site environment, and construction progress through IoT devices; Intelligent analysis module, used for multi-dimensional data fusion analysis and intelligent algorithm-driven dynamic optimization management of the entire process of engineering materials; Dynamic scheduling decision module, which integrates multi-objective optimization algorithms and real-time feedback mechanisms to output a scheduling instruction set including transportation plans, warehousing plans, and emergency plans; The digital twin execution module connects to the BIM platform to achieve 3D visual simulation and execution monitoring of the scheduling plan; The blockchain evidence storage module is used to store key decision-making data and generate an unalterable scheduling process record chain.

2. The intelligent deployment system for engineering materials according to claim 1, characterized in that: The multi-source data acquisition module includes: UWB positioning array is used to be deployed in the engineering material storage area and perform accurate three-dimensional spatial positioning of engineering material storage; Intelligent sensor module, used to collect key parameters of the transport vehicle during transportation in real time; Edge computing nodes are used to deploy localized data processing centers on construction sites; The UWB positioning array and the intelligent sensing module are both connected to the edge computing node.

3. The intelligent deployment system for engineering materials according to claim 2, characterized in that: The intelligent analysis module includes a load detection unit, a temperature and humidity monitoring unit, and a tire pressure monitoring unit. The load detection unit is used to monitor the cargo weight of the transport vehicle in real time. The temperature and humidity monitoring unit is used to continuously monitor the ambient temperature and humidity in the cargo box to ensure the quality of materials that are sensitive to temperature and humidity. The tire pressure monitoring unit is used to detect tire pressure and temperature in real time.

4. The intelligent deployment system for engineering materials according to claim 3, characterized in that: The intelligent analysis module includes a material demand prediction unit, a path optimization unit and an abnormal warning unit. The material demand prediction unit is used to construct a demand prediction model with multi-factor coupling, the path optimization unit is used to generate a transportation path using a dynamic programming algorithm under time and space constraints, and the abnormal warning unit is used for an early warning mechanism when materials are in short supply.

5. The intelligent deployment system for engineering materials according to claim 4, characterized in that: The material demand forecasting unit performs the following steps: Step A1: Decompose the construction phases based on the BIM model and extract the material demand baseline value Q_base corresponding to each phase; Step A2: Build a dual-channel prediction model: The first channel uses LSTM neural network to process the historical construction progress time series {X_t} and output the progress impact factor α; The second channel uses the environmental analysis network of the Attention mechanism to process real-time meteorological data {E_t} and geological data {G_t} and output the environmental correction factor β; Step A3: Calculate the supply chain response coefficient δ: δ=w1×(1-logistics delay rate)+w2×supplier credit rating, Where w1 and w2 are dynamic weight parameters, and w1+w2=1; Step A4: Generate final demand forecast value: Q_final=Q_base×(1+α)×(1+β)×δ; Step A5: When it is detected that the construction progress deviation rate ΔP exceeds 5%, the demand recalculation is triggered: Q_final'=Q_final×[1+0.2×sign(ΔP)×|ΔP|^0.5].

6. The intelligent deployment system for engineering materials according to claim 1, characterized in that: The dynamic scheduling decision module includes: Multi-objective optimization engine,constructs a decision space with the following dimensions; Time dimension: the latest arrival time under the construction critical path constraint; Cost dimension: Dynamic transportation cost model C = Σ(road section fuel consumption cost + time cost + risk cost); Resource dimension: Material reuse priority matrix P = [p_ij]_{m×n}; Real-time adjustment strategy library, storing scheduling strategies for various typical scenarios; The decision verification unit is equipped with a Monte Carlo simulator to verify the reliability of the solution.

7. The intelligent deployment system for engineering materials according to claim 1, characterized in that: The digital twin execution module includes: Dynamic update interface of BIM model, supporting automatic association of material dispatch data and construction progress nodes; Virtual-reality mapping engine, establishing a two-way data channel between physical entities and digital models; The deviation warning unit triggers a level 3 alarm when the actual execution progress deviates from the simulation plan by more than a threshold.

8. The intelligent deployment system for engineering materials according to claim 1, characterized in that: The blockchain evidence storage module adopts: Dual-chain storage architecture, including scheduling decision chain and material traceability chain; Smart contract template library, including transportation contracts, warehousing contracts, and quality traceability contracts; The cross-chain verification mechanism realizes data privacy protection of different participants through zero-knowledge proof.

9. The method for intelligent deployment of engineering materials based on the system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step S1: Build a full-factor digital twin of materials, equipment, and environment, and establish a spatiotemporal alignment relationship between multi-source data; Step S2: Perform multi-scale demand forecasting based on the improved Transformer model and output forecast results including baseline demand, elastic demand, and emergency demand; Step S3: Use a multi-agent reinforcement learning algorithm to generate a Pareto frontier solution set, where each agent corresponds to a type of material scheduling resource; Step S4: Perform three-dimensional visualization deduction of the scheme through the digital twin platform and calculate the scheme reliability index; Step S5: Execute dynamic scheduling and monitor in real time, and trigger solution reconstruction when it is detected that the execution deviation exceeds the adaptive threshold.

Images