Intelligent cold chain monitoring and control system

Abstract

The present application relates to cold chain temperature control technology field, and further relates to an intelligent cold chain monitoring and control system, the system comprises: a supply chain network, a refrigeration equipment and a temperature control system; each refrigeration equipment is as a node in the supply chain network; the supply chain network is a block chain network, and each node in the block chain network is interconnected with each other; the temperature control system is arranged in each refrigeration equipment, and is used for collecting real-time temperature data of each refrigeration equipment, responding to the temperature control instruction issued by the supply chain network, using the set adaptive feedback control algorithm to control the temperature of each refrigeration equipment; the supply chain network is provided with an intelligent temperature control contract; the intelligent temperature control contract automatically formulates the intelligent temperature control contract and automatically triggers the intelligent temperature control contract by acquiring the real-time temperature data of each refrigeration equipment and by supporting the vector particle swarm algorithm. The present application realizes the intelligentization of cold chain management and the improvement of energy efficiency.

Description

Technical Field

[0001] This invention belongs to the field of cold chain temperature control technology, specifically relating to an intelligent cold chain monitoring and control system. Background Technology

[0002] The modern cold chain logistics industry plays a vital role in the food, pharmaceutical, and chemical industries, ensuring the safety, freshness, and quality of many goods. Cold chain logistics relies on various refrigeration equipment, such as refrigerated vehicles, refrigerated containers, and cold storage warehouses, to maintain suitable temperatures for goods throughout the supply chain. However, with the increasing complexity and scale of global supply chains, traditional cold chain management methods face a series of challenges and problems, such as energy waste, temperature fluctuations, resource waste, and insufficient monitoring.

[0003] Traditional cold chain management typically relies on manual monitoring and temperature recording, which presents several problems: Traditional cold chain systems usually maintain refrigeration equipment at a fixed temperature, unable to intelligently adjust according to actual needs. This leads to energy waste, especially under low or no load conditions. Temperature fluctuations can cause product quality degradation and loss, and traditional systems struggle to detect and respond to these fluctuations in a timely manner. Resource allocation in traditional cold chain systems is often overly conservative, easily leading to resource waste and inefficient use. Furthermore, traditional cold chain systems have limited monitoring of refrigeration equipment, making it difficult to acquire and analyze equipment status and temperature data in real time, resulting in a slow response when problems arise. Summary of the Invention

[0004] The main objective of this invention is to provide an intelligent cold chain monitoring and control system. This invention achieves intelligent cold chain management and improved energy efficiency through intelligent temperature control contracts, adaptive feedback control algorithms, and blockchain networks, thereby improving supply chain transparency, temperature stability, and resource utilization efficiency.

[0005] To solve the above problems, the technical solution of the present invention is implemented as follows:

[0006] An intelligent cold chain monitoring and control system includes: a supply chain network, refrigerated equipment, and a temperature control system; each refrigerated equipment is a node in the supply chain network; the supply chain network is a blockchain network in which each node is interconnected; the temperature control system is installed in each refrigerated equipment to collect real-time temperature data of each refrigerated equipment, send the collected real-time temperature data to the supply chain network for storage, and respond to temperature control commands issued by the supply chain network by using a set adaptive feedback control algorithm to control the temperature of each refrigerated equipment; the supply chain network is equipped with intelligent temperature control contracts; the intelligent temperature control contracts automatically formulate intelligent temperature control contracts by acquiring real-time temperature data from each refrigerated equipment and using the support vector particle swarm optimization algorithm, with the constraints of minimizing temperature control frequency and minimizing energy consumption, and automatically trigger the intelligent temperature control contracts according to preset contract trigger conditions when the contract trigger conditions are met.

[0007] Furthermore, the refrigeration equipment includes at least: refrigerated vehicles, refrigerated containers, and refrigerated warehouses;

[0008] Furthermore, the process of developing a smart temperature control contract includes:

[0009] Step 1: Express the real-time temperature data of the refrigeration equipment as T. i , where i is the index of the refrigeration equipment, and the value of i is an integer from 1 to N, and N is the number of refrigeration equipment; in order to minimize the temperature control frequency and energy consumption, an objective function F is defined;

[0010] Step 2: Initialize a particle swarm, where the position of each particle represents a temperature control strategy; the position of each particle contains the control parameters of the refrigeration device i, including: target temperature T. i,target , temperature change rate d(T) i ,T i,target ) / dt and temperature control adjustment frequency f;

[0011] The position of the particle is used express,

[0012] Where i represents the refrigeration equipment index, j represents the particle index, and the value of j is an integer from 1 to N;

[0013] Step 3: Set the velocity of each particle, using V. i,j express;

[0014]

[0015] Step 4: Based on the objective function F and the real-time temperature data T of the refrigeration equipment i Calculate the fitness of each particle; set the objective function to minimize the temperature control frequency and minimize energy consumption;

[0016] Step 5: Based on the fitness of each particle, update the position and velocity of each particle; for each particle, update the individual optimal position and the global optimal position;

[0017] Step 6: Iterate through steps 1 to 5 according to the set maximum number of iterations; generate a smart temperature control contract based on the global optimal position.

[0018] Furthermore, the objective function F is expressed using the following formula:

[0019]

[0020] Where N represents the number of refrigeration units; α1 is a weighting factor used to balance the rate of temperature change and energy consumption, ranging from 0.2 to 0.4; β1 is a weighting factor used to balance energy consumption and the rate of temperature change, ranging from 0.5 to 0.35; γ is a weighting factor used to penalize temperature differences between different refrigeration units; δ is a weighting factor used to penalize the rate of temperature change of refrigeration units, ranging from 0.4 to 0.6; θ is a weighting factor used to minimize the temperature of refrigeration units, ranging from 0.6 to 0.8; and φ is a weighting factor used to balance the second-order temperature change and the target temperature T. i,target The weighting factor ranges from 0.5 to 0.8; λ is a weighting factor used to consider the correlation between the rate of temperature change and energy consumption; d(T i ,T i,target ) / dt represents the real-time temperature data T of refrigeration equipment i. i Relative to target temperature T i,target The rate of temperature change; E i Energy consumption of refrigeration equipment i; d(T) i ,T k ) / dτ is the rate of change of the difference in real-time temperature data between refrigeration equipment i and refrigeration equipment j over time; d(T) i ,T i,prev ) / dt represents the temperature of refrigeration equipment i relative to the temperature T of the previous time step. i,prev The rate of change of d. 2 (T i ,T i,target ) / dt 2 Real-time temperature data T for refrigeration equipment i i Relative to target temperature T i,target The second-order rate of temperature change.

[0021] Furthermore, in step 4, the following formula is used, based on the objective function F and the real-time temperature data T of the refrigeration equipment. i Calculate the fitness of each particle. i,j :

[0022]

[0023] Where λ1 is the first constraint factor, ranging from 0.35 to 0.45; λ2 is the second constraint factor, ranging from 0.55 to 0.65; g1(P i,j g2(P) is the first constraint function; i,j ) is the second constraint function.

[0024] Furthermore, the first constraint function is expressed using the following formula:

[0025]

[0026] Among them, T min The minimum permissible temperature for refrigeration equipment; T max This refers to the maximum permissible temperature for refrigeration equipment.

[0027] Furthermore, the second constraint function is expressed using the following formula:

[0028]

[0029] Furthermore, step 5 uses the following formula to update the position and velocity of each particle based on its fitness:

[0030]

[0031] Where ω is the inertia weight, and c1 and c2 are both learning factors.

[0032] Furthermore, the optimal position of an individual is updated using the following formula. and the global optimal position

[0033] Furthermore, the contract trigger condition is: when Fitness i,j If the sum of values ​​is less than the set trigger threshold, then Fitness is selected. i,j If the temperature of a refrigerated device falls below the set warning threshold, the smart temperature control contract will be triggered.

[0034] The intelligent cold chain monitoring and control system of this invention has the following beneficial effects: Through intelligent temperature control contracts and adaptive feedback control algorithms, this invention can monitor the temperature data of each refrigeration device in real time and formulate the optimal temperature control strategy based on the support vector particle swarm optimization algorithm. This precise temperature control ensures that the cold chain system can maintain the temperature within the target range, effectively solving the problem of temperature fluctuations in traditional cold chain management. The intelligent temperature control contract of this invention can automatically adjust the temperature control strategy of refrigeration equipment with constraints of minimizing temperature control frequency and minimizing energy consumption. This feature helps to reduce the energy consumption of the cold chain system, improves energy efficiency, and significantly saves energy compared with traditional constant temperature operation. Through the formulation of intelligent temperature control contracts, this invention can intelligently configure the resources of refrigeration equipment according to different supply chain needs and situations. This means that more resources can be allocated during high loads, while resource usage can be reduced during low loads or no loads, optimizing resource allocation and utilization efficiency. The temperature control system in this invention can monitor the temperature data of refrigeration equipment in real time and automatically respond to temperature control commands, using an adaptive feedback control algorithm to adjust the temperature. This feature reduces the need for manual intervention and improves the efficiency and accuracy of cold chain management. Supply chains utilizing blockchain networks offer high transparency, allowing nodes to share temperature data and control strategies in real time. This feature enhances traceability and visibility, reducing information asymmetry and data inconsistencies. Through smart temperature control contracts, this invention ensures cold chain equipment consistently meets preset temperature requirements. The contracts can also automatically formulate temperature control strategies based on compliance requirements, ensuring cold chain operations comply with relevant regulations and standards, thus improving product quality assurance. The smart temperature control contracts of this invention incorporate support vector particle swarm optimization (SFO) algorithms, enabling dynamic temperature control strategy formulation based on real-time data and multiple parameters. This flexibility allows the contracts to adapt to different situations and needs, providing a higher level of intelligence and adaptability, helping to cope with ever-changing supply chain conditions. Attached Figure Description

[0035] Figure 1 A schematic diagram of the system structure of the intelligent cold chain monitoring and control system provided in an embodiment of the present invention. Detailed Implementation

[0036] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0037] Example 1: Reference Figure 1An intelligent cold chain monitoring and control system is described, comprising: a supply chain network, refrigerated equipment, and a temperature control system; each refrigerated equipment is a node in the supply chain network; the supply chain network is a blockchain network in which each node is interconnected; the temperature control system is installed in each refrigerated equipment to collect real-time temperature data of each refrigerated equipment, sends the collected real-time temperature data to the supply chain network for storage, and responds to temperature control commands issued by the supply chain network by using a pre-defined adaptive feedback control algorithm to control the temperature of each refrigerated equipment; the supply chain network is equipped with intelligent temperature control contracts; the intelligent temperature control contracts automatically formulate intelligent temperature control contracts by acquiring real-time temperature data from each refrigerated equipment and using a support vector particle swarm optimization algorithm, with the constraints of minimizing temperature control frequency and minimizing energy consumption; and automatically trigger the intelligent temperature control contracts according to preset contract trigger conditions, provided the contract trigger conditions are met.

[0038] Specifically, the supply chain network is a blockchain network, meaning each refrigerated unit is a node in the network. Using blockchain technology, it features decentralization, immutability, and security. This differs from traditional cold chain monitoring systems, which typically use centralized databases and are susceptible to data tampering and single points of failure. Each refrigerated unit is equipped with a temperature control system that not only collects real-time temperature data but also responds to temperature control commands within the supply chain network. This means the system has real-time monitoring and control capabilities, quickly responding to temperature changes to ensure product quality and safety. This offers higher accuracy and real-time performance compared to traditional timed data collection and manual temperature control methods. The system employs an adaptive feedback control algorithm, which automatically adjusts the temperature settings of the refrigerated units based on real-time temperature data. This differs from traditional fixed-temperature control methods, which often require manual intervention. The adaptive algorithm intelligently adjusts according to different situations and needs, minimizing energy consumption while maintaining product temperature stability. The intelligent temperature control contract automatically formulates temperature control strategies based on real-time temperature data and support vector particle swarm optimization. By minimizing temperature control frequency and energy consumption, this contract ensures that the refrigerated units operate under optimal conditions, thereby saving energy costs. In addition, contracts can be executed automatically based on preset contract triggering conditions, which increases the automation level of the system and reduces the need for manual intervention.

[0039] When using a pre-defined adaptive feedback control algorithm to control the temperature of each refrigeration unit, a game will occur between each unit, the process of which is represented by the following formula:

[0040]

[0041] u i(t) represents the temperature control strategy of device i, where i = 1, 2, ..., N. i (t) represents the energy consumption cost function of device i, used to measure its energy consumption. λ is a tradeoff parameter in the game, used to balance the impact of each device's energy consumption on the energy consumption of other devices. In this formula, each device is minimizing its own energy consumption cost function J. i While considering the energy consumption of other devices, the energy consumption of (t) is also taken into account. The parameter λ can be used to adjust this trade-off. If λ is small, devices tend to minimize their own energy consumption; if λ is large, devices tend to cooperate to reduce overall energy consumption. This formula reflects the complexity of the Boyar process, where each device considers its own influence and that of other devices in its decision-making. The application of Boyar theory makes temperature control strategies more intelligent, enabling cooperation and competition among multiple devices to minimize overall energy consumption.

[0042]

[0043] In this formula, J i (t) is the energy consumption cost function of device i, which includes the following terms: α i ·u i (t) 2 This is related to the temperature control output u i A term proportional to the square of (t). It indicates that the energy consumed by device i is related to the magnitude of the temperature control output. A larger α i The value indicates that the equipment is more focused on energy consumption. This is a term proportional to the rate of change of the temperature control output. It represents the impact of the rate at which device i adjusts the temperature on energy consumption. A larger β... i This value can prompt the equipment to adjust the temperature more carefully. γ i ·(T i (t)-SP(t)) 2 This is related to temperature error (T) i (t)-SP(t)) 2 A proportional term. It indicates that the energy consumed by device i is related to the difference between the actual temperature and the set temperature. A larger γ i The value indicates that the device is more focused on keeping the temperature close to the set point.

[0044] Example 2: The refrigeration equipment includes at least: refrigerated vehicles, refrigerated containers, and refrigerated warehouses.

[0045] Refrigerated vehicles are mobile refrigerated facilities typically used to transport temperature-sensitive goods from one location to another. These vehicles are usually equipped with specialized refrigeration systems to maintain a constant temperature. Their characteristics include: refrigerated vehicles can transport goods between different locations, suitable for both long-distance and short-distance transport; they have advanced temperature control systems to maintain the required temperature range; and they are typically equipped with temperature sensors and monitoring systems to monitor and record temperature data in real time. Refrigerated containers are mobile containers used to store temperature-sensitive goods, typically used in container shipping. These containers can be used in conjunction with different modes of transport (such as cargo ships, trains, and trucks) during transport. Their characteristics include: they can be loaded onto different modes of transport, facilitating international freight transport; the size and capacity of the containers can be adjusted as needed to accommodate different quantities and types of goods; and the containers are typically insulated to prevent the effects of external temperatures on the goods. Cold storage warehouses are fixed storage facilities used for long-term or temporary storage of temperature-sensitive goods. They are typically located in logistics centers, distribution centers, or food processing plants. Their characteristics include: cold storage warehouses provide a stable storage environment suitable for long-term storage of goods. They typically have large capacity, capable of storing large quantities of goods. Warehouses are usually equipped with advanced monitoring and management systems to ensure the quality and safety of the goods.

[0046] Example 3: The process of formulating a smart temperature control contract includes:

[0047] Step 1: Express the real-time temperature data of the refrigeration equipment as T. i , where i is the index of the refrigeration equipment, and the value of i is an integer from 1 to N, and N is the number of refrigeration equipment; in order to minimize the temperature control frequency and energy consumption, an objective function F is defined;

[0048] In step 1, the real-time temperature data T i This was used to construct the objective function F. This objective function is a multivariate function, whose independent variables are different temperature control strategy parameters, such as the target temperature T. i,target , temperature change rate d(T) i ,T i,target ) / dt and temperature control adjustment frequency f iThe objective function is typically constructed based on the performance requirements of refrigeration equipment and the goals of supply chain management to measure the quality of temperature control strategies under different operating conditions. The objective function aims to minimize temperature control frequency and energy consumption. This is because temperature control equipment needs to maintain the required temperature while minimizing the temperature control frequency (i.e., the number of temperature adjustments) to reduce energy consumption, extend equipment life, and reduce operating costs. The objective function F provides a clear optimization objective: minimizing temperature control frequency and energy consumption. This objective is used in subsequent particle swarm optimization (PSO) algorithms to search for optimal temperature control strategy parameters that minimize the objective function. The objective function F allows for quantitative evaluation of different temperature control strategies to determine their impact on refrigeration equipment performance. By comparing the objective function values ​​of different strategies, it can be determined which strategies are closer to the optimal solution. The objective function F is the objective function of the PSO algorithm, guiding the algorithm to search for the optimal solution in the search space. The algorithm will strive to find the combination of temperature control strategy parameters that minimizes the objective function value, thereby achieving optimal performance. In summary, the objective function F of the steps is constructed and its purpose is to provide a clear optimization objective for subsequent optimization algorithms, helping refrigeration equipment to formulate optimal temperature control strategies to minimize temperature control frequency and energy consumption under different conditions. This objective function will vary depending on the equipment performance requirements and management objectives, and therefore can be used for different types of refrigeration equipment and supply chain scenarios.

[0049] Step 2: Initialize a particle swarm, where the position of each particle represents a temperature control strategy; the position of each particle contains the control parameters of the refrigeration device i, including: target temperature T. i,target , temperature change rate d(T) i ,T i,target ) / dt and temperature control adjustment frequency f;

[0050] The position of the particle is used express,

[0051] Where i represents the refrigeration equipment index, j represents the particle index, and the value of j is an integer from 1 to N;

[0052] In step 2, a particle swarm is first initialized, where each particle represents a temperature control strategy. The position of each particle contains the control parameters of the refrigeration equipment, such as the target temperature T. i,target、温度 rate of change d(T) i ,T i,target ) / dt and temperature control adjustment frequency f iThese parameters are key components of the temperature control strategy. Each particle represents a potential temperature control strategy, thus the entire particle swarm represents a set of multiple possible temperature control strategies. These strategies can be searched and compared during the iterative process of the particle swarm optimization algorithm to find the optimal strategy combination. In the particle swarm, i represents the index of the refrigeration device, and j represents the index of the particle. This means that for each refrigeration device, multiple possible temperature control strategies are considered, and their effects will be evaluated and optimized in the algorithm. The main purpose of step 2 is to create an initial set of temperature control strategies, which will be further searched and optimized in subsequent particle swarm optimization algorithms. By initializing multiple different temperature control strategies, it can be ensured that the algorithm can take diversity into account and avoid getting trapped in local minima. The position of each particle represents a combination of parameters for a temperature control strategy, including the target temperature, the rate of temperature change, and the temperature control adjustment frequency. These parameters are the core of the temperature control strategy, and they will be dynamically adjusted and updated in the algorithm to find the optimal strategy parameters. The initialization of the particle swarm defines the initial boundary of the temperature control strategy search space. This search space will be continuously narrowed in subsequent iterations to find the optimal strategy. The diversity of initialization helps to explore the search space more comprehensively.

[0053] Step 3: Set the velocity of each particle, using V. i,j express;

[0054]

[0055] In step 3, a velocity was set for each particle:

[0056] V i,j =(T i ,d(T i ,T i,target ) / dt,f i ).

[0057] These velocity vectors are used to update the particle's position, reflecting the particle's direction and velocity of movement within the temperature control strategy parameter space. Each component of the velocity vector is associated with a temperature control strategy parameter. For example, T i d(T) represents the rate of change of the target temperature. i ,T i,target ) / dt represents the rate of change of temperature, f iThis represents the rate of change of the temperature control adjustment frequency. These velocity components determine how the parameters of the temperature control strategy are updated in the next step. The magnitude and direction of the velocity are controlled by the algorithm, typically determined based on the optimal position (individual optimal position and global optimal position) in the particle swarm optimization algorithm and some randomness. The magnitude of the velocity affects the adjustment range of the temperature control strategy parameters, while the direction of the velocity determines the direction of parameter increase or decrease. The setting of the velocity vector affects the updating of the temperature control strategy parameters, meaning their movement and adjustment within the temperature control strategy parameter space. The magnitude and direction of the velocity vector determine the degree and direction of parameter change, thus affecting the next position update. The setting of the velocity vector usually considers the need to balance exploration and development. A larger velocity may prompt particles to explore the parameter space more quickly, searching for new potential solutions. A smaller velocity may allow particles to concentrate more near the current optimal solution for deeper optimization. The setting of the velocity vector usually includes a certain degree of randomness to increase the diversity of the algorithm and prevent getting trapped in local minima. This helps the algorithm to search the temperature control strategy parameter space more comprehensively.

[0058] Step 4: Based on the objective function F and the real-time temperature data T of the refrigeration equipment i Calculate the fitness of each particle; set the objective function to minimize the temperature control frequency and minimize energy consumption;

[0059] In step 4, based on the objective function F and the real-time temperature data T of the refrigeration equipment... i The fitness of each particle is calculated. The objective function F is a multivariable function, where the independent variables are different frequencies f. i The objective function reflects the performance of each temperature control strategy under the current conditions. The objective function aims to minimize the temperature control frequency and energy consumption. Therefore, calculating the objective function effectively evaluates the quality of each temperature control strategy; a lower objective function value indicates better performance.

[0060] The main purpose of step 4 is to evaluate the performance of the temperature control strategy represented by each particle. By calculating the objective function F, we can understand how the current temperature control strategy performs in real-world situations. A lower objective function value indicates a better temperature control strategy. The objective function value is often used as the particle's fitness, reflecting its performance. Particles with lower fitness values ​​are more likely to be selected and retained in subsequent particle swarm optimization (PSO) iterations, prompting the algorithm to move towards a more optimized direction. By continuously calculating and comparing the objective function values, the PSO algorithm can progressively find the optimal combination of temperature control strategy parameters to minimize the objective function. This process is carried out in multiple iterations, helping to gradually optimize the temperature control strategy. Based on the objective function value, the PSO algorithm can determine the evolutionary direction of each particle. A lower objective function value may lead to a larger velocity update, allowing for faster progress in the search space, while a higher objective function value may lead to a smaller velocity update, preventing skipping potential optimal solutions.

[0061] Step 5: Based on the fitness of each particle, update the position and velocity of each particle; for each particle, update the individual optimal position and the global optimal position;

[0062] In step 5, the position and velocity of each particle are updated based on its fitness (objective function value), individual optimal position, and global optimal position. This update is based on the core principle of the particle swarm optimization algorithm, which simulates the movement and search for optimal solutions by particles in the temperature control strategy parameter space. Each particle maintains an individual optimal position, representing the best temperature control strategy found in its own history, and a global optimal position, representing the best temperature control strategy found in the history of the entire particle swarm. These two positions guide the particle's search direction. Local search is based on the individual optimal position, while global search is based on the global optimal position.

[0063] Step 5 primarily serves to drive the iterative optimization of the particle swarm optimization (PSO) algorithm. By updating the position and velocity of each particle, the algorithm attempts to search for a better combination of temperature control strategy parameters to minimize the objective function. This process is iterative until a set number of iterations is reached or a stopping condition is met. The PSO algorithm strikes a balance between local and global search by being guided by individual optimal positions and global optimal positions. Individual optimal positions guide particles to find local optima within their own search space, while global optimal positions guide particles to find global optima across the entire swarm. This helps avoid getting trapped in local optima. After each iteration, by updating the temperature control strategy parameters, the PSO algorithm has the opportunity to find a strategy closer to the optimal solution. The temperature control strategy parameters are progressively optimized to minimize the temperature control frequency and energy consumption. Depending on the fitness and historical optimal positions of different particles, different particles may move at different speeds and directions, thus creating a dynamic search process in the search space. This helps the algorithm explore possible solutions more comprehensively.

[0064] Step 6: Iterate through steps 1 to 5 according to the set maximum number of iterations; generate a smart temperature control contract based on the global optimal position.

[0065] In step 6, the particle swarm optimization (PSO) algorithm iterates multiple times according to the set maximum number of iterations. Each iteration includes steps 1 through 5, meaning that the temperature control strategy parameters are continuously adjusted and optimized in each iteration. In each iteration, the algorithm records the global optimum, which is the best combination of temperature control strategy parameters found throughout the entire history of the particle swarm. The global optimum represents the best solution found so far. The algorithm executes a certain number of iterations, determined by the set maximum number of iterations. Once the maximum number of iterations is reached, the algorithm stops executing. The main purpose of step 6 is to find the optimal combination of temperature control strategy parameters through multiple iterations to minimize the objective function. Each iteration attempts to further optimize the temperature control strategy to approach the optimal solution. Through multiple iterations, the algorithm can gradually optimize the temperature control strategy parameters, bringing them closer to the optimal solution. This process is gradual, with each iteration bringing some improvements. The global optimum records the best temperature control strategy found throughout the entire algorithm's execution history. Once the set maximum number of iterations is reached, the algorithm generates a smart temperature control contract using the parameters of the global optimum. Once the set maximum number of iterations is reached, the algorithm will generate a smart temperature control contract using the temperature control strategy parameters at the globally optimal location. This contract will contain the optimal parameter settings to achieve the goal of minimizing temperature control frequency and energy consumption.

[0066] Example 4: The objective function F is expressed using the following formula:

[0067]

[0068] Where N represents the number of refrigeration units; α1 is a weighting factor used to balance the rate of temperature change and energy consumption, ranging from 0.2 to 0.4; β1 is a weighting factor used to balance energy consumption and the rate of temperature change, ranging from 0.5 to 0.35; γ is a weighting factor used to penalize temperature differences between different refrigeration units; δ is a weighting factor used to penalize the rate of temperature change of refrigeration units, ranging from 0.4 to 0.6; θ is a weighting factor used to minimize the temperature of refrigeration units, ranging from 0.6 to 0.8; and φ is a weighting factor used to balance the second-order temperature change and the target temperature T. i,target The weighting factor ranges from 0.5 to 0.8; λ is a weighting factor used to consider the correlation between the rate of temperature change and energy consumption; d(T i ,T i,target ) / dt represents the real-time temperature data T of refrigeration equipment i. i Relative to target temperature T i,target The rate of temperature change; E i Energy consumption of refrigeration equipment i; d(T) i ,T k ) / dτ is the rate of change of the difference in real-time temperature data between refrigeration equipment i and refrigeration equipment j over time; d(T) i ,T i,prev ) / dt represents the temperature of refrigeration equipment i relative to the temperature T of the previous time step. i,prev The rate of change of d. 2 (T i ,T i,target ) / dt 2 Real-time temperature data T for refrigeration equipment i i Relative to target temperature T i,target The second-order rate of temperature change.

[0069] Specifically, the objective function F plays a crucial role in the intelligent cold chain monitoring and control system. It comprehensively considers multiple key factors to evaluate the performance of the temperature control strategy for refrigeration equipment. The main objective of this complex objective function is to minimize the temperature control frequency and energy consumption through reasonable trade-offs, while ensuring the stability and coordinated operation of the refrigeration equipment. First, the first term of the objective function comprises two parts, controlled by weighting factors α1 and β1, respectively. α1 balances the rate of temperature change and energy consumption, while β1 balances energy consumption and the rate of temperature change. This part considers the relationship between the equipment temperature and the target temperature, as well as energy consumption, aiming to optimize temperature stability and efficient energy utilization. Second, the second term of the objective function is controlled by the weighting factor γ, which penalizes temperature differences between different refrigeration units. This helps ensure that the temperature between units tends to be consistent, thereby improving the overall system's temperature control efficiency. The third term considers the rate of temperature change of the refrigeration equipment and is controlled by the weighting factor δ. A larger rate of temperature change leads to more energy consumption, so this part helps to reduce drastic temperature fluctuations and improve energy conservation. Finally, the fourth term of the objective function is controlled by the weighting factor θ, which aims to minimize the temperature of the refrigeration equipment. By lowering the overall temperature, system energy consumption can be reduced, and the efficiency of refrigeration equipment can be improved. The fifth term, controlled by the weighting factor φ, balances the second-order temperature change and the target temperature. It considers the acceleration of temperature change, helping to ensure smooth temperature changes. Finally, the sixth term, controlled by the weighting factor λ, considers the correlation between the rate of temperature change and energy consumption. This part reflects the relationship between the rate of temperature change and energy consumption, helping to optimize the temperature control strategy to balance these two factors. In summary, the objective function F integrates multiple factors to evaluate the performance of the temperature control strategy for refrigeration equipment in a cold chain monitoring and control system. By adjusting the weighting factors of each term and optimizing the temperature control strategy parameters, the goal of minimizing temperature control frequency and energy consumption can be achieved, while ensuring the stability and coordinated operation of refrigeration equipment. The application of this objective function in cold chain management is expected to improve the efficiency and sustainability of the cold chain system, ensuring product quality and safety.

[0070] Example 5: In step 4, the following formula is used, based on the objective function F and the real-time temperature data T of the refrigeration equipment. i Calculate the fitness of each particle. i,j :

[0071]

[0072] Where λ1 is the first constraint factor, ranging from 0.35 to 0.45; λ2 is the second constraint factor, ranging from 0.55 to 0.65; g1(P i,j g2(P) is the first constraint function; i,j ) is the second constraint function.

[0073] Specifically, the fitness function is a key component of the Particle Swarm Optimization (PSO) algorithm, playing a crucial role in the development of smart temperature control contracts. The main purpose of the fitness function is to evaluate the merits of each temperature control strategy, helping the PSO algorithm find the optimal combination of temperature control strategy parameters. Let's analyze the principles and functions of the fitness function formula in detail:

[0074] The fitness function formula is shown below: This formula includes three key parts:

[0075] Part One: This section relates the objective function F to the real-time temperature data T of the refrigeration equipment. i The relevant terms. The numerator F represents the objective function value, i.e., the performance evaluation of the temperature control strategy. This is achieved by dividing the objective function value by the real-time temperature T of the refrigeration unit. i This section considers the relationship between the performance of the temperature control strategy and the current state of the equipment. The closer the equipment temperature is to the target temperature, the greater this factor contributes to the fitness, and vice versa.

[0076] Part Two: λ1·g1(P) i,j This part is related to the first constraint function g1(P) i,j The constraint function g1(P) is related to the constraint factor λ1. i,j The current temperature control strategy parameter P was evaluated. i,j Does the system satisfy its first constraint? Constraints may relate to limitations on equipment energy consumption, rate of temperature change, or other aspects. If the current policy satisfies the constraint, this value is zero; otherwise, it is a positive number, increasing according to the degree of constraint violation.

[0077] Part Three: λ²·g²(P) i,j This part is related to the second constraint function g2(P) i,j Related to this, it is also weighed by the constraint factor λ2. The constraint function g2(P) i,j The current temperature control strategy parameter P was evaluated. i,j Does the system's second constraint condition satisfy? Similar to the first part, if the current policy satisfies the constraint condition, the value of this item is zero; otherwise, the value will be positive, increasing according to the degree of constraint violation.

[0078] The core idea of ​​the fitness function is to comprehensively consider the performance evaluation of the objective function and the degree to which the constraints are satisfied. The PSO algorithm continuously optimizes the temperature control strategy parameters by minimizing the value of the fitness function, so as to make the objective function value as small as possible (i.e., the performance of the temperature control strategy as good as possible), while ensuring that the constraints are met.

[0079] The constraint factors λ1 and λ2 are used to adjust the relative importance of the objective function and constraint functions in the fitness function. Their values ​​can be set according to the problem requirements, and different values ​​lead to different algorithmic behaviors. Larger values ​​of λ1 and λ2 enhance the importance of constraints, thus emphasizing constraint satisfaction; while smaller values ​​emphasize minimizing the objective function. Therefore, the design of the fitness function allows for flexible adjustment of the balance between the objective and constraints in different problem scenarios to meet the needs of practical applications. The fitness function plays a crucial role in the PSO algorithm, combining the objective function, constraints, and weighting factors to provide an effective evaluation and optimization tool for smart temperature control contract formulation. By continuously updating the position and velocity of particles, the PSO algorithm finds the combination of temperature control strategy parameters with the highest fitness value, thereby automating and optimizing the smart temperature control contract formulation process. This method is expected to improve the efficiency, quality, and sustainability of cold chain management, ensuring product safety and reliability.

[0080] Example 6: The first constraint function is expressed using the following formula:

[0081]

[0082] Among them, T min The minimum permissible temperature for refrigeration equipment; T max This refers to the maximum permissible temperature for refrigeration equipment.

[0083] Specifically, the main purpose of this constraint function is to evaluate the temperature control strategy parameter P during the smart temperature control contract formulation process. i,j Does the equipment meet its temperature constraints? It plays a crucial role in ensuring that the temperature of the refrigeration equipment is always maintained within a reasonable range. Minimum temperature constraint (T...) min This constraint ensures that the temperature of the refrigeration equipment will not fall below the minimum allowable temperature T. min If the temperature of a device is below T min Then the value of this part will be T. min -T i This indicates the deviation of the current temperature from the minimum temperature. Maximum temperature constraint (T) max This constraint ensures that the temperature of the refrigeration equipment will not exceed the maximum allowable temperature T. max If the temperature of a device is higher than T max Then the value of this part will be |T i -T max | represents the deviation of the current temperature from the maximum temperature. The first constraint function applies the above two constraints to all refrigeration equipment, calculating the overall constraint function value by summing the deviations of each equipment. The specific calculation is as follows: For each equipment i, calculate its deviation relative to T.min and T max The deviations of all devices are calculated and then summed. If the temperature of a device is within a reasonable range, the deviation term is zero and does not contribute to the constraint function value. The deviations of all devices are summed to obtain the overall constraint function value. The constraint factor λ1 in the constraint function controls the degree of influence of the constraints on the fitness function. By adjusting the value of λ1, the importance between the performance objectives of the temperature control strategy and the temperature constraints can be balanced. The role of the first constraint function is to ensure that the parameters P of the established temperature control strategy are within acceptable limits. i,j This will not cause any refrigeration equipment's temperature to deviate from the allowable range. If the temperature of any equipment exceeds the allowable range, the corresponding constraint function value will increase, negatively impacting the fitness function value. This forces the particle swarm optimization algorithm to optimize performance objectives while satisfying temperature constraints when searching for temperature control strategy parameters, ensuring the reliability of the cold chain system and the safety of products. The first constraint function plays a crucial role in the formulation of smart temperature control contracts. By considering temperature constraints, it ensures that the formulated temperature control strategy meets performance objectives without violating equipment temperature limits, thus providing robustness and reliability for cold chain management. The design of this constraint function helps optimize temperature control strategy parameters to achieve efficient operation of the cold chain system and ensure product quality.

[0084] Example 7: The second constraint function is expressed using the following formula:

[0085]

[0086] Specifically, as before, the constraint function first considers the rate of temperature change of the refrigeration equipment. This represents the rate of temperature change of the equipment relative to the target temperature. If the rate of temperature change of a certain piece of equipment is too large, this value will increase, indicating a violation of the temperature change rate constraint. The constraint function also considers the temperature difference |T| between different refrigeration units. i -T k |, where i and k represent different devices. If the temperature difference between some devices is too large, this part will also increase, indicating a violation of the constraint on temperature difference between devices. Finally, the constraint function considers the difference in temperature control adjustment frequency |f between different refrigeration devices. i -f kIf the temperature control adjustment frequencies of some devices differ too much, this part of the value will also increase, indicating a violation of the temperature control adjustment frequency constraint. Overall, the value of the second constraint function is obtained by calculating the temperature change rate, temperature difference, and temperature control adjustment frequency difference between different devices, and then summing them up. If a temperature control strategy causes these differences to exceed the allowable range, the corresponding constraint function value will increase, negatively impacting the fitness function value. The role of the second constraint function is to ensure that the formulated temperature control strategy maintains temperature consistency across different devices and that the temperature control adjustment frequency is relatively balanced. This helps avoid some devices over-adjusting the temperature or causing temperature fluctuations, thereby improving the efficiency and reliability of the entire cold chain system. By combining the constraint function with the fitness function, the particle swarm optimization algorithm can find the optimal combination of temperature control strategy parameters that satisfies the performance objectives and constraints, achieving optimized formulation of smart temperature control contracts.

[0087] Example 8: Step 5 uses the following formula to update the position and velocity of each particle based on its fitness:

[0088]

[0089] Where ω is the inertia weight, and c1 and c2 are both learning factors.

[0090] Specifically, in the position and velocity update of each particle, the velocity V is first calculated. i,j This velocity is a three-dimensional vector comprising three parts: The inertia weight represents the degree to which the particle maintains its original velocity direction during updates. A larger ω value makes the particle more inclined to continue moving along its original velocity direction, helping to avoid local optima, but may result in a slower search speed. A smaller ω value makes the particle more likely to change its velocity direction, helping to explore the search space more broadly, but may lead to premature entrapment in local optima. Individual experience term. This section considers the individual experience of the particle. It represents the particle's position based on its own historical best position. With current position P i,j The difference between the two is then multiplied by the learning factor c1 and the weighting factor α1. This term makes the particle more likely to move in the direction where it previously achieved good results, thus preserving individual experience. Global experience term. This section is used to consider the globally optimal position. With current position P i,j The difference between them is then multiplied by the learning factor c2 and the weighting factor β1. This term aims to attract the particle to the best outcome in the entire population, prompting the particle to seek better solutions throughout the search space. Once the velocity V is calculated... i,j It is then used to update the particle's position P. i,jThe new position replaces the current position, allowing the particle to search based on it in the next iteration. The goal of this update process is to adjust the particle's velocity and position based on its own experience and the global best experience, guiding it towards a better solution. This helps the particle swarm optimization algorithm gradually converge to the optimal solution in the search space while preserving the exploration of diversity. By repeatedly executing this process, the particle swarm optimization algorithm can find the optimal combination of temperature control strategy parameters that satisfies performance objectives and constraints, enabling the optimized formulation of smart temperature control contracts.

[0091] Example 9: Update the individual's optimal position using the following formula. and global optimal position

[0092] Specifically, individual optimal position update This represents the optimal position of particle i in the j-th iteration, calculated based on the fitness function. Specifically, for each particle i, its fitness value is calculated in each iteration and then updated. The position that minimizes the fitness value. This means that the particle remembers the best position it has found in the search space for reference in the next iteration. Global optimal position update. This represents the globally optimal position of the entire particle swarm in the j-th iteration, which is obtained by combining the individual optimal positions of all particles. Specifically, for each particle i, the individual optimal position... They will all be accumulated. This means This represents the position of the optimal solution found by the entire particle swarm in the search space. By updating the individual optimal position and the global optimal position, the particle swarm optimization algorithm can continuously search for better solutions in the search space. The individual optimal position preserves the individual experience of each particle, while the global optimal position reflects the common best result of the entire population. Updating these two positions ensures that the algorithm has the ability to strike a balance between exploration and exploitation, thus potentially finding the optimal combination of temperature control strategy parameters that satisfies performance objectives and constraints.

[0093] Example 10: The contract triggering condition is: when Fitness i,j If the sum of values ​​is less than the set trigger threshold, then Fitness is selected. i,j If the temperature of a refrigerated device falls below the set warning threshold, the smart temperature control contract will be triggered.

[0094] Specifically, firstly, for each particle i, the fitness value is... i,jThe summation represents the fitness state of the entire particle swarm in the current iteration. A trigger threshold is set, indicating when the sum of fitness values ​​falls below this threshold, the smart temperature control contract is activated. This threshold is typically set based on the specific application requirements and performance metrics; it can be a predetermined fixed value or a value dynamically adjusted based on real-time system conditions. Upon triggering, the system selects those fitness values... i,j Refrigerated equipment operating below a set warning threshold may be deemed to require further adjustments to its temperature control strategy to improve performance. Once the refrigerated equipment requiring adjustment is selected, the system triggers a smart temperature control contract. Following the smart temperature control contract creation process (as mentioned earlier), a new temperature control strategy is developed to suit these devices, meeting performance targets and constraints. In essence, this triggering condition monitors system performance in real time and automatically takes action to optimize the cold chain system's temperature control strategy when performance degrades to a certain level. By triggering the smart temperature control contract, the system can more flexibly adapt to changes under different conditions, improving the robustness and adaptability of the cold chain system. This helps ensure that the cold chain system can maintain the required performance levels under various circumstances.

[0095] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent cold chain monitoring and control system, characterized in that, The system includes: a supply chain network, refrigerated equipment, and a temperature control system; each refrigerated device is a node in the supply chain network; the supply chain network is a blockchain network in which each node is interconnected; the temperature control system is installed in each refrigerated device to collect real-time temperature data of each refrigerated device, send the collected real-time temperature data to the supply chain network for storage, and respond to temperature control commands issued by the supply chain network by using a set adaptive feedback control algorithm to control the temperature of each refrigerated device; the supply chain network is equipped with smart temperature control contracts; the smart temperature control contracts automatically formulate smart temperature control contracts by acquiring real-time temperature data from each refrigerated device and using the support vector particle swarm optimization algorithm, with the constraints of minimizing temperature control frequency and minimizing energy consumption; and automatically trigger the smart temperature control contracts according to preset contract trigger conditions when the contract trigger conditions are met. The process of developing a smart temperature control contract includes: Step 1: Express the real-time temperature data of the refrigeration equipment as follows: ,in For indexing refrigeration equipment, The value ranges from 1 to integers, Let the number of refrigeration units be specified; to minimize temperature control frequency and energy consumption, define an objective function. ; Step 2: Initialize a particle swarm, where the position of each particle represents a temperature control strategy; the position of each particle contains the refrigeration equipment. The control parameters include: target temperature. Temperature change rate and temperature control adjustment frequency ; The position of the particle is used express, in This represents an index of refrigeration equipment. Indicates particle index, The value ranges from 1 to Integers; Step 3: Set the velocity of each particle, using... express; ； Step 4: Based on the objective function Real-time temperature data of refrigeration equipment Calculate the fitness of each particle; set the objective function to minimize the temperature control frequency and minimize energy consumption; Step 5: Based on the fitness of each particle, update the position and velocity of each particle; for each particle, update the individual optimal position and the global optimal position; Step 6: Iterate through steps 1 to 5 according to the set maximum number of iterations; generate a smart temperature control contract based on the global optimal position; objective function Express it using the following formula: ； in, The number of refrigeration equipment; This is a weighting factor used to balance the rate of temperature change and energy consumption, with a value ranging from 0.2 to 0.

4. The weighting factor used to balance energy consumption and the rate of temperature change ranges from 0.5 to 0.

35. This is a weighting factor used to penalize temperature differences between different refrigeration units; This is a weighting factor used to penalize the rate of temperature change in refrigeration equipment; its value ranges from 0.4 to 0.

6. The weighting factor used to minimize the temperature of the refrigeration equipment ranges from 0.6 to 0.

8. To balance the second-order temperature change and the target temperature The weighting factor ranges from 0.5 to 0.8; This is a weighting factor used to consider the correlation between the rate of temperature change and energy consumption; For refrigeration equipment Real-time temperature data Relative to target temperature Its rate of temperature change; For refrigeration equipment Energy consumption; For refrigeration equipment and refrigeration equipment The rate of change of the difference in real-time temperature data between them over time; For refrigeration equipment Temperature relative to the temperature at the previous time step The rate of change; For refrigeration equipment Real-time temperature data Relative to target temperature The second-order rate of temperature change.

2. The intelligent cold chain monitoring and control system as described in claim 1, characterized in that, The refrigeration equipment includes at least: refrigerated vehicles, refrigerated containers, and refrigerated warehouses.

3. The intelligent cold chain monitoring and control system as described in claim 1, characterized in that, In step 4, the following formula is used based on the objective function. Real-time temperature data of refrigeration equipment Calculate the fitness of each particle. : ； in, This is the first constraint factor, with a value ranging from 0.35 to 0.45; This is the second constraint factor, with a value ranging from 0.55 to 0.65; This is the first constraint function; This is the second constraint function.

4. The intelligent cold chain monitoring and control system as described in claim 3, characterized in that, The first constraint function is expressed using the following formula: ； in, This refers to the minimum permissible temperature for refrigeration equipment. This refers to the maximum permissible temperature for refrigeration equipment.

5. The intelligent cold chain monitoring and control system as described in claim 4, characterized in that, The second constraint function is expressed using the following formula: 。 6. The intelligent cold chain monitoring and control system as described in claim 5, characterized in that, Step 5 uses the following formula to update the position and velocity of each particle based on its fitness: ； in, It is inertial weight. and All of them are learning factors.

7. The intelligent cold chain monitoring and control system as described in claim 6, characterized in that, Update the individual's optimal position using the following formula. and the global optimal position : 。 8. The intelligent cold chain monitoring and control system as described in claim 7, characterized in that, The contract trigger condition is: when If the sum of values ​​is less than the set trigger threshold, then fitness is selected. If the temperature of a refrigerated device falls below the set warning threshold, the smart temperature control contract will be triggered.

Images