CN117707093A - Intelligent cold chain monitoring and control system - Google Patents
Intelligent cold chain monitoring and control system Download PDFInfo
- Publication number
- CN117707093A CN117707093A CN202410001844.1A CN202410001844A CN117707093A CN 117707093 A CN117707093 A CN 117707093A CN 202410001844 A CN202410001844 A CN 202410001844A CN 117707093 A CN117707093 A CN 117707093A
- Authority
- CN
- China
- Prior art keywords
- temperature
- temperature control
- refrigeration
- intelligent
- particle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 239000002245 particle Substances 0.000 claims abstract description 118
- 238000005057 refrigeration Methods 0.000 claims abstract description 104
- 239000013598 vector Substances 0.000 claims abstract description 14
- 230000001960 triggered effect Effects 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 117
- 238000011217 control strategy Methods 0.000 claims description 82
- 238000005265 energy consumption Methods 0.000 claims description 54
- 230000008859 change Effects 0.000 claims description 53
- 238000000034 method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 15
- 238000009472 formulation Methods 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 230000006872 improvement Effects 0.000 abstract description 4
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 description 11
- 238000007726 management method Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 7
- 239000002699 waste material Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000000275 quality assurance Methods 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 229920002430 Fibre-reinforced plastic Polymers 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011151 fibre-reinforced plastic Substances 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013068 supply chain management Methods 0.000 description 1
Landscapes
- Devices That Are Associated With Refrigeration Equipment (AREA)
Abstract
The invention relates to the technical field of cold chain temperature control, in particular to an intelligent cold chain monitoring and controlling system, which comprises: a supply chain network, a refrigeration appliance, and a temperature control system; each refrigeration appliance acts as a node in the supply chain network; the supply chain network is a blockchain network, wherein each node is interconnected with each other; the temperature control system is arranged in each refrigeration device and is used for collecting real-time temperature data of each refrigeration device, and responding to a temperature control instruction issued by a supply chain network, the temperature of each refrigeration device is controlled by using a set self-adaptive feedback control algorithm; an intelligent temperature control contract is arranged in the supply chain network; the intelligent temperature control contract is automatically formulated by acquiring real-time temperature data of each refrigeration device and supporting a vector particle swarm algorithm, and the intelligent temperature control contract is automatically triggered. The invention realizes the intellectualization of the cold chain management and the improvement of the energy benefit.
Description
Technical Field
The invention belongs to the technical field of cold chain temperature control, and particularly relates to an intelligent cold chain monitoring and controlling system.
Background
The modern cold chain logistics industry plays a vital role in the fields of food, medicine, chemical industry and the like, and ensures the safety, freshness and quality of a plurality of commodities. Cold chain logistics rely on various refrigeration equipment, such as refrigerated vehicles, refrigerated containers, and refrigerated warehouses, to maintain the proper temperature of the commodity throughout the supply chain. However, with the increasing complexity and scale of the global supply chain, conventional cold chain management methods face a series of challenges and problems such as energy waste, temperature fluctuations, resource waste, and insufficient monitoring.
Conventional cold chain management typically relies on manual monitoring and temperature recording, which has the following problems: conventional cold chain systems typically maintain refrigeration equipment at a fixed temperature and cannot be intelligently adjusted according to actual needs. This results in waste of energy, especially at low or no load. Temperature fluctuations can lead to quality degradation and loss of goods, which are difficult for conventional systems to discover and address in time. The resource allocation of conventional cold chain systems is often too conservative, which tends to result in wasted and inefficient use of resources. The conventional cold chain system has limited monitoring of the refrigerating apparatus, and it is difficult to acquire and analyze the apparatus state and temperature data in real time, so that the reaction is slow when a problem occurs.
Disclosure of Invention
The invention mainly aims to provide an intelligent cold chain monitoring and controlling system, which realizes the intellectualization of cold chain management and the improvement of energy benefit through an intelligent temperature control contract, a self-adaptive feedback control algorithm and a block chain network, thereby improving the transparency, the temperature stability and the resource utilization efficiency of a supply chain.
In order to solve the problems, the technical scheme of the invention is realized as follows:
an intelligent cold chain monitoring and control system, the system comprising: a supply chain network, a refrigeration appliance, and a temperature control system; each refrigeration appliance acts as a node in the supply chain network; the supply chain network is a blockchain network, wherein each node is interconnected with each other; the temperature control system is arranged in each refrigeration device and is used for collecting real-time temperature data of each refrigeration device, sending the collected real-time temperature data into a supply chain network for storage, and simultaneously responding to a temperature control instruction issued by the supply chain network, and controlling the temperature of each refrigeration device by using a set self-adaptive feedback control algorithm; an intelligent temperature control contract is arranged in the supply chain network; the intelligent temperature control contract is automatically formulated by acquiring real-time temperature data of each refrigeration device and using minimized temperature control frequency and minimized energy consumption as constraint conditions through a support vector particle swarm algorithm, and meanwhile, the intelligent temperature control contract is automatically triggered under the condition that the contract triggering conditions are met according to preset contract triggering conditions.
Further, the refrigeration device at least includes: refrigerated vehicles, refrigerated containers, and refrigerated warehouses;
further, the making process of the intelligent temperature control contract comprises the following steps:
step 1: real-time temperature data of the refrigeration equipment is expressed as T i Wherein i is an index of the refrigerating equipment, the value of i is an integer from 1 to N, and N is the number of the refrigerating equipment; in order to minimize the temperature control frequency and the energy consumption, an objective function F is defined;
step 2: initializing a particle swarm, wherein the position of each particle represents a temperature control strategy; the position of each particle contains control parameters of the refrigeration appliance i, said control parameters comprising: target temperature T i,target Rate of change of temperature d (T i ,T i,target ) Dt and temperature control adjustment frequency f;
for the position of particlesThe representation is made of a combination of a first and a second color,
wherein i represents a refrigeration equipment index, j represents a particle index, and the value of j is an integer from 1 to N;
step 3: setting the velocity of each particle by V i,j A representation;
step 4: according to the objective function F and the real-time temperature of the refrigeration applianceAccording to T i Calculating the fitness of each particle; setting the objective function as a target for minimizing the temperature control frequency and minimizing the energy consumption;
step 5: updating the position and velocity of each particle based on the fitness of each particle; updating the individual optimal position and the global optimal position for each particle;
Step 6: according to the set maximum iteration times, performing the steps 1 to 5 in an iteration mode; and generating an intelligent temperature control contract according to the global optimal position.
Further, the objective function F is expressed using the following formula:
wherein N is the number of refrigeration equipment; alpha 1 The weight factor for balancing the temperature change rate and the energy consumption is in the range of 0.2 to 0.4; beta 1 The weight factor for balancing the energy consumption and the temperature change rate is in the range of 0.5 to 0.35; gamma is a weighting factor for penalizing temperature differences between different refrigeration appliances. Delta is a weight factor for punishing the speed of change in temperature of the refrigeration appliance; the value range is 0.4 to 0.6; θ is a weight factor for minimizing the temperature of the refrigeration appliance, ranging from 0.6 to 0.8; phi is a temperature T for balancing the second-order temperature change and the target temperature i,target The weight factor of (2) is in the range of 0.5 to 0.8; λ is a weight factor for taking into account the correlation between the temperature change rate and the energy consumption; d (T) i ,T i,target ) Dt is the real-time temperature data T of the refrigerating device i i Relative to target temperature T i,target A rate of change of temperature thereof; e (E) i Energy consumption for the refrigeration appliance i; d (T) i ,T k ) Dτ is the rate of change over time of the difference in real-time temperature data between refrigeration appliance i and refrigeration appliance j; d (T) i ,T i,prev ) The value of/dt is the temperature T of the refrigerating device i relative to the temperature T of the previous time step i,prev Is a rate of change of (c). d, d 2 (T i ,T i,target )/dt 2 For real-time temperature of the refrigerating apparatus iData T i Relative to target temperature T i,target Is a second order rate of temperature change.
Further, in step 4, the following formula is used, according to the objective function F and the real-time temperature data T of the refrigeration equipment i Calculating Fitness Fitness of each particle i,j ：
Wherein lambda is 1 Taking the value range of 0.35 to 0.45 as a first constraint factor; lambda (lambda) 2 Taking the value range of 0.55 to 0.65 as a second constraint factor; g 1 (P i,j ) Is a first constraint function; g 2 (P i,j ) Is a second constraint function.
Further, the first constraint function is expressed using the following formula:
wherein T is min Is the minimum allowable temperature of the refrigeration equipment; t (T) max Is the maximum allowable temperature of the refrigeration equipment.
Further, the second constraint function is expressed using the following formula:
further, step 5 updates the position and velocity of each particle based on its fitness using the following formula:
where ω is the inertial weight, c 1 And c 2 Are learning factors.
Further, the following formula is used to updateIndividual optimum positionAnd global optimum position->
Further, the contract trigger condition is: when Fitness is the i,j When the sum of the values is smaller than the set trigger threshold, then the Fitness Fitness is selected i,j And triggering the intelligent temperature control contract by the refrigerating equipment smaller than the set warning threshold value.
The intelligent cold chain monitoring and controlling system has the following beneficial effects: through the intelligent temperature control contract and the self-adaptive feedback control algorithm, the temperature data of each refrigeration device can be monitored in real time, and an optimal temperature control strategy is formulated according to the support vector particle swarm 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 conventional cold chain management. The intelligent temperature control contract can automatically adjust the temperature control strategy of the refrigeration equipment by taking minimized temperature control frequency and minimized energy consumption as constraint conditions. This feature helps to reduce the energy consumption of the cold chain system, improves energy efficiency, and saves significant energy compared to conventional constant temperature operation. By making intelligent temperature control contracts, the invention can intelligently configure the resources of the refrigeration equipment according to different supply chain demands and conditions. This means that more resources can be allocated at high load, while resource usage can be reduced at low or no load, optimizing the configuration and utilization efficiency of the resources. The temperature control system can monitor the temperature data of the refrigerating equipment in real time and automatically respond to the temperature control instruction to adjust the temperature by using the self-adaptive feedback control algorithm. This feature reduces the need for human intervention and improves the efficiency and accuracy of cold chain management. The supply chain adopting the blockchain network has high transparency, and each node can share temperature data and temperature control strategies in real time. This feature helps to improve traceability and visibility of the supply chain, reducing the problems of information asymmetry and data inconsistency. Through the intelligent temperature control contract, the invention ensures that the cold chain equipment can always meet the preset temperature requirement. The contract can also automatically prepare a temperature control strategy according to compliance requirements, ensure that the cold chain operation accords with related regulations and standards, and improve the quality assurance level of commodities. The intelligent temperature control contract combines a support vector particle swarm algorithm, and can dynamically prepare a temperature control strategy according to real-time data and a plurality of parameters. This flexibility enables contracts to accommodate different situations and needs, providing a higher level of intelligence and adaptivity, helping to cope with changing supply chain conditions.
Drawings
Fig. 1 is a schematic system architecture diagram of an intelligent cold chain monitoring and control system according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1: referring to fig. 1, an intelligent cold chain monitoring and control system, the system comprising: a supply chain network, a refrigeration appliance, and a temperature control system; each refrigeration appliance acts as a node in the supply chain network; the supply chain network is a blockchain network, wherein each node is interconnected with each other; the temperature control system is arranged in each refrigeration device and is used for collecting real-time temperature data of each refrigeration device, sending the collected real-time temperature data into a supply chain network for storage, and simultaneously responding to a temperature control instruction issued by the supply chain network, and controlling the temperature of each refrigeration device by using a set self-adaptive feedback control algorithm; an intelligent temperature control contract is arranged in the supply chain network; the intelligent temperature control contract is automatically formulated by acquiring real-time temperature data of each refrigeration device and using minimized temperature control frequency and minimized energy consumption as constraint conditions through a support vector particle swarm algorithm, and meanwhile, the intelligent temperature control contract is automatically triggered under the condition that the contract triggering conditions are met according to preset contract triggering conditions.
In particular, the supply chain network is a blockchain network, meaning that each refrigeration appliance is a node in the network. Using blockchain technology, it has the properties of being decentralised, non-tamperable and secure. This is in contrast to conventional cold chain monitoring systems, which typically use centralized databases, which are susceptible to data tampering and single point of failure. Each refrigeration appliance is equipped with a temperature control system that is not only used for real-time temperature acquisition, but also responds to temperature control instructions in the supply chain network. This means that the system has real-time monitoring and control capability, can rapidly cope with temperature changes, and ensures the quality and safety of products. Compared with the traditional timing acquisition and manual temperature control method, the method has higher accuracy and real-time performance. The system adopts an adaptive feedback control algorithm which can automatically adjust the temperature setting of the refrigeration equipment according to the real-time temperature data. This is in contrast to conventional fixed temperature control methods, which typically require manual intervention. The self-adaptive algorithm can be intelligently adjusted according to different conditions and requirements, so that the energy consumption is reduced to the greatest extent, and meanwhile, the temperature stability of the product is maintained. The intelligent temperature control contract automatically prepares a temperature control strategy based on real-time temperature data and a support vector particle swarm algorithm. By minimizing the frequency of temperature control and energy consumption, this contract ensures that the refrigeration unit is operated under optimal conditions, thereby saving energy costs. In addition, the contracts can be automatically executed according to preset contract triggering conditions, so that the degree of automation of the system is increased, and the requirement of manual intervention is reduced.
When the temperature of each refrigerating device is controlled by using a set self-adaptive feedback control algorithm, a game is played among the refrigerating devices, and the process is expressed by using the following formula:
u i (t) represents the temperature control strategy of device i, i=1, 2, …, N. J (J) i (t) represents the energy consumption cost function of the device i for measuring its energy consumption. Lambda is a trade-off parameter in gaming for balancing the impact between the energy consumption of each device and the energy consumption of other devices. In this formula, each device is minimizing its own energy consumption cost function J i (t) while taking into account the energy consumption of other devices. The parameter lambda may be used to adjust this trade-off. If λ is smaller, the devices are more prone to minimize their own energy consumption, and if λ is larger, the devices are more prone to cooperate to reduce overall energy consumption. This formula reflects the complexity of the blogging process, each device taking into account its own and other device effects in the decision. The application of the blogs theory makes the temperature control strategy more intelligent, and cooperation and competition can be realized among a plurality of devices so as to minimize the total energy consumption.
In this formula, J i (t) is an energy consumption cost function of device i, which includes the following: alpha i ·u i (t) 2 : this is related to the temperature control output u i (t) a term proportional to the square of t. It shows that the energy that the device i needs to consume is related to the magnitude of the temperature control output. Larger alpha i The value means that the device is more concerned about energy consumption.This is a term proportional to the rate of change of the temperature control output. It shows the effect of the speed of temperature adjustment of the device i on the energy consumption. Larger beta i The value may cause the device to adjust the temperature more carefully. Gamma ray i ·(T i (t)-SP(t)) 2 : this is a function of the temperature error (T i (t)-SP(t)) 2 Proportional terms. It shows that the energy that the device i needs to consume is related to the difference between the actual temperature and the set temperature. Larger gamma i The value indicates that the device is more concerned with maintaining the temperature close to the set point.
Example 2: the refrigeration appliance includes at least: refrigerated vehicles, refrigerated containers, and refrigerated warehouses.
A refrigerated vehicle is a mobile refrigeration appliance that is commonly used to transport temperature sensitive cargo from one location to another. These vehicles are typically equipped with a dedicated refrigeration system that can maintain a constant temperature. The method is characterized by comprising the following steps: refrigerated vehicles can transport cargo between different locations, and are suitable for long-distance and short-distance transportation. They have advanced temperature control systems that can maintain a desired temperature range. Temperature sensors and monitoring systems are typically equipped to monitor and record temperature data in real time. Refrigerated containers are removable containers for storing temperature sensitive goods, commonly used for shipping containers. These containers may be used in connection with different transportation vehicles (e.g., cargo ships, trains, and trucks) during transportation. The method is characterized by comprising the following steps: they can be loaded onto different transport means for international cargo transportation. The size and capacity of the container can be adjusted as needed to accommodate different amounts and types of cargo. The container is generally insulated to prevent the effects of ambient temperature on the cargo. A refrigerated warehouse is a stationary storage device used for long-term or temporary storage of temperature sensitive goods. They are typically located in a logistics center, distribution center or food processing plant or the like. The method is characterized by comprising the following steps: the refrigerated warehouse provides a stable storage environment that can be used for long-term storage of goods. They typically have a large capacity and can store large volumes of cargo. Warehouses are often equipped with advanced monitoring and management systems to ensure the quality and safety of the goods. .
Example 3: the intelligent temperature control contract making process comprises the following steps:
step 1: real-time temperature data of the refrigeration equipment is expressed as T i Wherein i is the index of the refrigeration equipment, i is an integer from 1 to N, N is the refrigeration equipmentThe number of preparations; in order to minimize the temperature control frequency and the energy consumption, an objective function F is defined;
in step 1, real-time temperature data T i Is used to construct an objective function F. The objective function is a multi-variable function whose independent variables are different temperature control strategy parameters, such as target temperature T i,target Rate of change of temperature d (T i ,T i,target ) /dt and temperature control adjustment frequency f i . The construction of the objective function is typically based on the performance requirements of the refrigeration appliance and the goals of supply chain management in order to measure the quality of the temperature control strategy under different operating conditions. The objective of the objective function is to minimize the temperature control frequency and the energy consumption. This is because the temperature control device needs to minimize the temperature control frequency (i.e., the number of temperature adjustments) while maintaining the desired temperature to reduce energy consumption, extend the lifetime of the device, and reduce operating costs. The objective function F provides a well-defined optimization objective, i.e. minimizing the temperature control frequency and the energy consumption. This optimization objective will be used in the subsequent particle swarm algorithm to search for the optimal temperature control strategy parameters, so that the value of the objective function is minimized. The objective function F allows for a quantitative evaluation of the different temperature control strategies to determine their impact on the performance of the refrigeration appliance. 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 an objective function of the particle swarm algorithm, which is used to guide the algorithm to search for the optimal solution in the space. The algorithm will strive to find a combination of temperature control strategy parameters that minimizes the objective function value to achieve optimal performance. In summary, the objective function F of the step is constructed and acts to provide a specific optimization objective for the subsequent optimization algorithm to help the refrigeration appliance to formulate an optimal temperature control strategy to achieve the objective of minimizing temperature control frequency and energy consumption under different conditions. This objective function will vary depending on the equipment performance requirements and management objectives and thus can be used for different types of refrigeration equipment and supply chain scenarios.
Step 2: initializing a particle swarm, wherein the position of each particle represents a temperature control strategy; the position of each particle contains the control parameters of the refrigeration equipment i, and the control parameters compriseThe method comprises the following steps: target temperature T i,target Rate of change of temperature d (T i ,T i,target ) Dt and temperature control adjustment frequency f;
for the position of particlesThe representation is made of a combination of a first and a second color,
wherein i represents a refrigeration equipment index, j represents a particle index, and the value of j is an integer from 1 to N;
in step 2, a population of particles is first initialized, wherein each particle represents a temperature control strategy. The position of each particle contains control parameters of the refrigerating apparatus, such as target temperature T i, target, temperature Rate of change d (T) i ,T i,target ) /dt and temperature control adjustment frequency f i . These parameters are key components of the temperature control strategy. Each particle represents one potential temperature control strategy, so the entire particle population represents a plurality of possible temperature control strategy sets. These policies may be searched and compared during iterations of the particle swarm algorithm to find an optimal combination of policies. In the particle group, i denotes an index of the refrigerator, and j denotes an index of the particles. This means that for each refrigerator there are a number of possible temperature control strategies to be considered, the effect of which will be evaluated and optimised in the algorithm. The main function of step 2 is to create an initial set of temperature control strategies that will be further searched and optimized in subsequent particle swarm algorithms. By initializing a plurality of different temperature control strategies, it can be ensured that the algorithm can take into account diversity without trapping local minima. The location of each particle represents a combination of parameters of a temperature control strategy, including target temperature, rate of temperature change, and 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 an initial boundary of the temperature control strategy search space. This search space will be continually narrowed in subsequent iterations to find the optimal strategy. The diversity of the initialization helps to explore the search space more fully.
Step 3: setting eachVelocity of particles, by V i,j A representation;
in step 3, a velocity is set for each particle:
V i,j ＝(T i ,d(T i ,T i,target )/dt,f i )。
these velocity vectors are used to update the position of the particles, reflecting the direction and speed of movement of the particles in the temperature control strategy parameter space. Each component in the velocity vector is associated with a temperature control strategy parameter. For example T i Represents the change rate of the target temperature, d (T i ,T i,target ) Dt represents the rate of change of the temperature change rate, f i Indicating 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 is controlled by an algorithm, typically based on the best position (individual best position and global best position) and some randomness in the particle swarm algorithm. The magnitude of the speed influences the adjustment amplitude of the temperature control strategy parameters, and the direction of the speed determines the increasing or decreasing direction of the parameters. The setting of the velocity vector affects the updating of the temperature control strategy parameters, which means their movement and adjustment in the temperature control strategy parameter space. The magnitude and direction of the velocity vector determine the degree and direction of change of the parameter, which affects the next position update. The setting of the velocity vector typically takes into account the requirements of balance exploration and development. The greater speed may cause the particles to explore the parameter space faster, looking for new potential solutions. The smaller speed may focus the particles more around the current optimal solution for deeper optimization. The speed vector is usually set with a degree of randomness to increase the diversity of the algorithm and prevent the local minimum from being trapped. This helps the algorithm more fully search the temperature control strategy parameter space.
Step 4: according to the objective function F and the real-time temperature data T of the refrigeration appliance i Calculate each grainAdaptability of the son; setting the objective function as a target for minimizing the temperature control frequency and minimizing the energy consumption;
in step 4, real-time temperature data T of the refrigeration appliance based on the objective function F i The fitness of each particle is calculated. The objective function F is a multi-variable function in which the independent variables are of different frequencies F i . Calculating the value of the objective function reflects the performance of each temperature control strategy under the current conditions. The objective of the objective function is to minimize the temperature control frequency and the energy consumption. Thus, calculating the value of the objective function is actually in evaluating the quality of each temperature control strategy, with lower objective function values indicating better performance.
The main role of step 4 is to evaluate the performance of the temperature control strategy represented by each particle. By calculating the value of the objective function F, the performance of the current temperature control strategy under the actual condition can be known. A lower objective function value indicates a more excellent temperature control strategy. The objective function value is typically used as a fitness of the particle, which reflects the performance of the particle. Particles with lower fitness values are more likely to be selected and retained in subsequent particle swarm algorithms to drive the algorithm toward a more optimal direction. By continuously calculating and comparing the objective function values, the particle swarm algorithm can gradually find the optimal temperature control strategy parameter combination so as to realize the minimization of the objective function. This process is performed in multiple iterations, helping to gradually optimize the temperature control strategy. Based on the objective function values, the particle swarm algorithm may determine the direction of evolution of each particle. A lower objective function value may result in a greater speed update to advance faster in the search space, while a higher objective function value may result in a reduced speed update to prevent skipping over the potentially optimal solution.
Step 5: updating the position and velocity of each particle based on the fitness of each particle; updating the individual optimal position and the global optimal position for each particle;
in step 5, the position and velocity of each particle are updated according to the fitness (objective function value) of each particle and the individual optimal position and the global optimal position. This update is based on the core principle of a particle swarm algorithm, which simulates the movement of particles in the temperature control strategy parameter space and the process of searching for the optimal solution. Each particle maintains an individual optimal location that represents the optimal temperature control strategy historically found by the particle itself, and a global optimal location that represents the optimal temperature control strategy historically found by the entire particle swarm. These two positions are used to guide the search direction of the particle. The local search is based on an individual optimal location, while the global search is based on a global optimal location.
The main function of the step 5 is to push the particle swarm algorithm to carry out iterative optimization. By updating the position and velocity of each particle, the algorithm attempts to search for a more optimal combination of temperature control strategy parameters to achieve minimization of the objective function. This process is iterative until a set number of iterations is reached or a stop condition is met. The particle swarm algorithm balances between local search and global search through the guidance of the individual optimal position and the global optimal position. The individual optimal position guide particles find a local optimal solution in the self search space, while the global optimal position guide particles find a global optimal solution in the whole population. This helps avoid trapping in the locally optimal solution. After each iteration, the particle swarm algorithm has the opportunity to find a strategy closer to the optimal solution by updating the temperature control strategy parameters. Gradually optimizing the temperature control strategy parameters to achieve the goal of minimizing temperature control frequency and energy consumption. Depending on the fitness and historically optimal location of the different particles, the different particles may move at different speeds and directions, thereby creating a dynamic search process in the search space. This helps the algorithm more fully explore possible solutions.
Step 6: according to the set maximum iteration times, performing the steps 1 to 5 in an iteration mode; and generating an intelligent temperature control contract according to the global optimal position.
In step 6, the particle swarm algorithm will iterate a plurality of times according to the set maximum number of iterations. Each iteration includes steps 1 to 5, which means that the temperature control strategy parameters will be continuously adjusted and optimized in each iteration. In each iteration, the algorithm will record the global optimum, i.e. the combination of the optimal temperature control strategy parameters historically found for the whole population of particles. The global optimum represents the best solution found so far. The algorithm will perform a number of iterations, which is determined by the set maximum number of iterations. Once the maximum number of iterations is reached, the algorithm will stop executing. The main function of step 6 is to find the optimal temperature control strategy parameter combination through multiple iterations, so as to achieve the minimization of 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 so that the temperature control strategy parameters are closer to the optimal solution. This process is progressive, with each iteration leading to some improvement. The global optimum position records the best temperature control strategy found in the whole algorithm execution history. Once the set maximum number of iterations is reached, the algorithm will generate an intelligent temperature control contract using the parameters of the globally optimal location. Once the set maximum number of iterations is reached, the algorithm will generate an intelligent temperature control contract using the temperature control strategy parameters for the globally optimal location. This contract will contain the optimal parameter settings to achieve the goal of minimizing temperature control frequency and energy consumption.
Example 4: the objective function F is expressed using the following formula:
wherein N is the number of refrigeration equipment; alpha 1 The weight factor for balancing the temperature change rate and the energy consumption is in the range of 0.2 to 0.4; beta 1 The weight factor for balancing the energy consumption and the temperature change rate is in the range of 0.5 to 0.35; gamma is a weighting factor for penalizing temperature differences between different refrigeration appliances. Delta is a weight factor for punishing the speed of change in temperature of the refrigeration appliance; the value range is 0.4 to 0.6; θ is a weight factor for minimizing the temperature of the refrigeration appliance, ranging from 0.6 to 0.8; phi is a temperature T for balancing the second-order temperature change and the target temperature i,target The weight factor of (2) is in the range of 0.5 to 0.8; λ is a weight factor for taking into account the correlation between the temperature change rate and the energy consumption; d (T) i ,T i,target ) Dt is refrigerationReal-time temperature data T of device i i Relative to target temperature T i,target A rate of change of temperature thereof; e (E) i Energy consumption for the refrigeration appliance i; d (T) i ,T k ) Dτ is the rate of change over time of the difference in real-time temperature data between refrigeration appliance i and refrigeration appliance j; d (T) i ,T i,prev ) The value of/dt is the temperature T of the refrigerating device i relative to the temperature T of the previous time step i,prev Is a rate of change of (c). d, d 2 (T i ,T i,target )/dt 2 Real-time temperature data T for a refrigerating device i i Relative to target temperature T i,target Is a second order rate of temperature change.
Specifically, the objective function F plays a critical role in the intelligent cold chain monitoring and control system, which comprehensively considers a plurality of key factors to evaluate the temperature control strategy performance of the refrigeration equipment. The main objective of this complex objective function is to minimize the temperature control frequency and energy consumption by reasonable trade-offs, while ensuring the stability and co-operation of the refrigeration appliance. First, the first term of the objective function consists of two parts, each of which is defined by a weight factor α 1 And beta 1 And (5) controlling. Wherein alpha is 1 For balancing the rate of change of temperature and the energy consumption, beta 1 For balancing energy consumption and temperature change rate. This section considers the relationship between the device temperature and the target temperature and the energy consumption, with the aim of optimizing the stability of the temperature and the efficient use of energy. Second, the second term of the objective function is controlled by a weight factor γ, which penalizes the temperature differences between the different refrigeration appliances. This helps to ensure that the temperature tends to be uniform between the devices, thereby improving the temperature control efficiency of the overall system. The third term considers the speed of the temperature change of the refrigeration appliance and is controlled by a weighting factor delta. A larger temperature change rate results in more energy consumption, so that this part contributes to a reduction in severe temperature fluctuations and an improvement in energy saving. Next, the fourth term of the objective function is controlled by a weighting factor θ, which aims to minimize the temperature of the refrigeration appliance. By reducing the overall temperature, the energy consumption of the system can be reduced and the working efficiency of the refrigeration equipment can be improved. The fifth item is controlled by the weight factor phi to balance the second-order temperature change And a target temperature. It takes into account the acceleration of the temperature, helping to ensure that the temperature changes smoothly. Finally, the sixth term is controlled by a weighting factor λ, which takes into account the correlation between the rate of change of temperature and the energy consumption. This section reflects the relationship between the rate of change of temperature and energy consumption, helping to optimize the temperature control strategy to balance these two factors. In summary, the objective function F integrates a plurality of factors for evaluating the performance of the temperature control strategy of the cooling device in the cooling chain monitoring and control system. By adjusting the weight factors of each item and optimizing the temperature control strategy parameters, the aims of minimizing the temperature control frequency and the energy consumption can be achieved, and meanwhile, the stability and the cooperative work of the refrigeration equipment are ensured. The application of the objective function in cold chain management is expected to improve the efficiency and the sustainability of a cold chain system and ensure the quality and the safety of products.
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 appliance i Calculating Fitness Fitness of each particle i,j ：
Wherein lambda is 1 Taking the value range of 0.35 to 0.45 as a first constraint factor; lambda (lambda) 2 Taking the value range of 0.55 to 0.65 as a second constraint factor; g 1 (P i,j ) Is a first constraint function; g 2 (P i,j ) Is a second constraint function.
Specifically, the fitness function is a key component in a Particle Swarm Optimization (PSO), and plays a crucial role in the intelligent temperature control contract making process. The main purpose of the fitness function is to evaluate the merits of each temperature control strategy to help the PSO algorithm find the optimal temperature control strategy parameter combination. Let us analyze in detail the principle and the role of the fitness function formula:
the fitness function formula is as follows: this formula includes three key components:
a first part:this part is the objective function F and the real-time temperature data T of the refrigeration appliance i Related items. The molecular fraction F represents the objective function value, i.e. the performance evaluation of the temperature control strategy. By dividing the objective function value by the real-time temperature T of the current refrigeration appliance i This section takes into account the relationship of the performance of the temperature control strategy to the current state of the device. The closer the device temperature is to the target temperature, the greater the contribution of this term to the fitness and vice versa.
A second part: lambda (lambda) 1 ·g 1 (P i,j ) This part is combined with a first constraint function g 1 (P i,j ) Correlation by constraint factor lambda 1 Weighing. Constraint function g 1 (P i,j ) Evaluate the current temperature control strategy parameter P i,j Whether the first constraint of the system is satisfied. Constraints may relate to energy consumption of the device, rate of change of temperature, or other limitations. If the current policy satisfies the constraint condition, the value of the term is zero, otherwise, the value will be a positive number, increasing according to the degree of violation of the constraint.
Third section: lambda (lambda) 2 ·g 2 (P i,j ) This part is combined with a second constraint function g 2 (P i,j ) Related, also by constraint factor lambda 2 Weighing. Constraint function g 2 (P i,j ) Evaluate the current temperature control strategy parameter P i,j Whether a second constraint of the system is satisfied. Similar to the first part, if the current policy satisfies the constraint, the value of the term is zero, otherwise the value will be a positive number, increasing according to the degree of violation of the constraint.
The core idea of the fitness function is to comprehensively consider the performance evaluation of the objective function and the satisfaction degree of the constraint condition. The PSO algorithm continuously optimizes the temperature control strategy parameters by minimizing the value of the fitness function so that the objective function value is as small as possible (i.e., the temperature control strategy performance is as good as possible), while ensuring that the constraint conditions are met.
Constraint factor lambda 1 And lambda (lambda) 2 Is to adjust the relative importance of the objective function and the constraint function in the fitness function. Their range of values can be set according to the requirements of the problem, different values resulting in different algorithmic behavior. Larger lambda 1 And lambda (lambda) 2 The value will enhance the importance of the constraint, thereby more emphasizing the satisfaction of the constraint; while smaller values more emphasize minimization of the objective function. Therefore, the design of the fitness function allows the balance between the targets and the constraints to be flexibly adjusted under different problem scenes so as to meet the requirements of practical application. The fitness function plays an important role in the PSO algorithm, combines an objective function, constraint conditions and weight factors, and provides effective assessment and optimization means for intelligent temperature control contract formulation. By continuously updating the position and the speed of the particles, the PSO algorithm searches for the temperature control strategy parameter combination with the highest fitness value, thereby realizing the automation and optimization of the formulation process of the intelligent temperature control contract. The method is expected to improve the efficiency, quality and sustainability of cold chain management and ensure the safety and reliability of products.
Example 6: the first constraint function is expressed using the following formula:
wherein T is min Is the minimum allowable temperature of the refrigeration equipment; t (T) max Is the maximum allowable temperature of the refrigeration equipment.
Specifically, the main purpose of the constraint function is to evaluate the temperature control strategy parameter P in the intelligent temperature control contract making process i,j Whether the temperature constraints of the device are met. It plays a key role in ensuring that the temperature of the refrigeration appliance is always kept within a reasonable range. Minimum temperature constraint (T) min ): this constraint ensures that the temperature of the refrigeration appliance is not below the minimum allowable temperature T min . If the temperature of a device is lower than T min Then the value of this part will be T min -T i Indicating a deviation of the current temperature below the minimum temperature. Maximum temperature constraint (T) max ): this constraint ensures that the temperature of the refrigeration appliance is not higher than the maximum allowable temperature T max . If the temperature of a certain device is higher than T max Then the value of this part will be |T i -T max I, represents the deviation of the current temperature above the maximum temperature. The first constraint function applies the constraint conditions of the above two aspects to all the refrigerating apparatuses, and calculates an overall constraint function value by accumulating the deviation of each apparatus. The specific calculation is as follows: for each device i, calculate its relative T min And T max And then sums them. If the temperature of a certain 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 accumulated to obtain an overall constraint function value. Constraint factor lambda in constraint function 1 The degree of influence of the constraint conditions on the fitness function is controlled. By adjusting lambda 1 Can balance the importance between the performance objectives of the temperature control strategy and the temperature constraints. The first constraint function is used for ensuring the formulated temperature control strategy parameters P i,j Without causing any deviation of the temperature of the refrigeration appliance from the allowable range. If the temperature of a certain device exceeds the allowable range, the corresponding constraint function value will increase, thereby negatively affecting the value of the fitness function. The particle swarm algorithm is forced to meet temperature constraint conditions while optimizing performance targets when searching temperature control strategy parameters, and reliability of a cold chain system and safety of products are ensured. The first constraint function plays a critical role in intelligent temperature control contract formulation. The temperature constraint condition is considered, so that the formulated temperature control strategy can meet the performance target and can not violate the temperature limit of equipment, and robustness and reliability are provided for cold chain management. The design of the constraint function is helpful to optimize the temperature control strategy parameters so as to realize the efficient operation of the cold chain system and the quality assurance of products.
Example 7: the second constraint function is expressed using the following formula:
/>
in particular, as beforeThe constraint function first considers the rate of change of temperature of the refrigeration applianceIndicating the rate of change of the device temperature relative to the target temperature. If the rate of change of temperature of a device is too great, the value of this portion will increase, indicating that the constraint on the rate of change of temperature is violated. The constraint function also takes into account the temperature difference T between different refrigeration appliances i -T k I, where i and k represent different devices, respectively. If the temperature difference between certain devices is too large, the value of this portion will also increase, indicating that the constraint of temperature difference between devices is violated. Finally, the constraint function takes into account the temperature control adjustment frequency difference |f between different refrigeration appliances i -f k | a. The invention relates to a method for producing a fibre-reinforced plastic composite. If the temperature control adjustment frequency of some devices is too different, the value of this portion will also increase, indicating that the temperature control adjustment frequency constraint is violated. In general, the values of the second constraint function are obtained by calculating the temperature change rate, the temperature difference, and the temperature control adjustment frequency difference between different devices, and then accumulating them. If a certain temperature control strategy causes the differences to be beyond the allowable range, the corresponding constraint function value will be increased, and the value of the fitness function will be negatively affected. The second constraint function is used to ensure that the formulated temperature control strategy maintains temperature consistency among different devices and that the temperature control adjusts the frequency relative balance. This helps to avoid over-regulation of temperature or causing temperature fluctuations in certain devices, thereby improving the efficiency and reliability of the overall cold chain system. By combining the constraint function and the fitness function, the particle swarm algorithm can find the optimal temperature control strategy parameter combination meeting the performance target and constraint condition, and the optimization formulation of the intelligent temperature control contract is realized.
Example 8: step 5 updates the position and velocity of each particle based on its fitness using the following formula:
where ω is the inertial weight, c 1 And c 2 Are learning factors.
Specifically, in the position and velocity update of each particle, the velocity V is calculated first i,j . This velocity is a three-dimensional vector comprising three parts: the inertial weight represents the extent to which the particle maintains its original velocity direction as it is updated. A larger value of ω will make the particles more prone to continue moving in the original velocity direction, helping to avoid locally optimal solutions, but possibly resulting in slower search speeds. Smaller ω values will make it easier for the particles to change speed direction, helping to explore the search space more widely, but may lead to premature trapping into a locally optimal solution. Individual experience itemsThis section is used to take into account individual particle experiences. It indicates the optimal position of the particle according to its own history +.>And the current position P i,j The difference between them is then multiplied by a learning factor c 1 And a weight factor alpha 1 . The effect of this is to make the particles more prone to move towards once achieving good results, to preserve the experience of the individual. Global experience item->This section is used to consider the global optimum position +. >And the current position P i,j The difference between them is then multiplied by a learning factor c 2 And a weight factor beta 1 . The effect of this term is to attract the particles to the best results in the whole population to encourage the particles to find better solutions in the whole search space. Once the velocity V is calculated i,j It is used to update the position P of the particle i,j . The new position will replace the current position so that the particle will search based on the new position in the next iteration. This update procedureThe goal is to move the particles towards a better solution by adjusting the speed and position of the particles based on their own experience and global best experience. This helps the particle swarm algorithm gradually converge to the optimal solution in the search space, while preserving the exploration of diversity. By repeatedly executing the process, the particle swarm algorithm can find out the optimal temperature control strategy parameter combination meeting the performance target and the constraint condition, and the optimization formulation of the intelligent temperature control contract is realized. />
Example 9: updating the individual optimal position using the following formulaAnd global optimum position->
Specifically, individual optimal location updatesThe individual optimal position of particle i in the j-th iteration is represented, which is calculated from the fitness function. Specifically, for each particle i, its fitness value is calculated in each iteration, and then updated +. >To minimize the fitness value. This means that the particle will remember the best position it has found in the search space to reference at the next iteration. Global optimum position update->The global optimal position of the whole particle swarm in the jth iteration is represented, and the global optimal position is obtained by carrying out combination calculation on the individual optimal positions of all particles. Specifically, the individual optimal position for each particle i +.>They are accumulated. This means +.>The location of the best solution found in the search space for the whole population of particles is shown. By updating the individual and global optimal positions, the particle swarm algorithm can continually find 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 whole population. The updating of these two locations ensures that the algorithm has the ability to balance between exploration and utilization, thereby hopefully finding the best combination of temperature control strategy parameters that meet performance objectives and constraints.
Example 10: the contract trigger conditions are: when Fitness is the i,j When the sum of the values is smaller than the set trigger threshold, then the Fitness Fitness is selected i,j And triggering the intelligent temperature control contract by the refrigerating equipment smaller than the set warning threshold value.
Specifically, first, fitness value Fitness for each particle i i,j The summation is performed, and this summation value represents the fitness state of the whole particle swarm in the current iteration. A trigger threshold is set indicating that the intelligent temperature control contract is triggered when the fitness value sum is below the threshold. This threshold is typically set according to the needs and performance criteria of the particular application, and may be a predetermined fixed value or a value that is dynamically adjusted according to real-time system conditions. Upon triggering, the system will select those Fitness Fitness i,j A refrigeration appliance that is less than a set alert threshold. These devices may be considered to require further adjustments to their temperature control strategies to improve performance. Once the refrigeration appliance to be conditioned is selected, the system triggers an intelligent temperature control contract, and the temperature control strategy appropriate for those appliances is re-formulated according to the intelligent temperature control contract formulation process (steps mentioned earlier) to meet the performance objectives and constraints. In general, the effect of this trigger condition is to monitor the performance of the system in real time, when the performance drops to a certain extentAt that time, action is automatically taken to optimize the temperature control strategy of the cold chain system. By triggering the intelligent temperature control contract, the system can be more flexibly adapted to the changes under different conditions, and the robustness and the self-adaptability of the cold chain system are improved. This helps ensure that the cold chain system can maintain the desired level of performance under different conditions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An intelligent cold chain monitoring and control system, the system comprising: a supply chain network, a refrigeration appliance, and a temperature control system; each refrigeration appliance acts as a node in the supply chain network; the supply chain network is a blockchain network, wherein each node is interconnected with each other; the temperature control system is arranged in each refrigeration device and is used for collecting real-time temperature data of each refrigeration device, sending the collected real-time temperature data into a supply chain network for storage, and simultaneously responding to a temperature control instruction issued by the supply chain network, and controlling the temperature of each refrigeration device by using a set self-adaptive feedback control algorithm; an intelligent temperature control contract is arranged in the supply chain network; the intelligent temperature control contract is automatically formulated by acquiring real-time temperature data of each refrigeration device and using minimized temperature control frequency and minimized energy consumption as constraint conditions through a support vector particle swarm algorithm, and meanwhile, the intelligent temperature control contract is automatically triggered under the condition that the contract triggering conditions are met according to preset contract triggering conditions.
2. The intelligent cold chain monitoring and control system of claim 1, wherein the refrigeration appliance comprises at least: refrigerated vehicles, refrigerated containers, and refrigerated warehouses.
3. The intelligent cold chain monitoring and control system of claim 2, wherein the intelligent temperature control contract formulation process comprises:
step 1: real-time temperature data of the refrigeration equipment is expressed as T i Wherein i is an index of the refrigerating equipment, the value of i is an integer from 1 to N, and N is the number of the refrigerating equipment; in order to minimize the temperature control frequency and the energy consumption, an objective function F is defined;
step 2: initializing a particle swarm, wherein the position of each particle represents a temperature control strategy; the position of each particle contains control parameters of the refrigeration appliance i, said control parameters comprising: target temperature T i,target Rate of change of temperature d (T i ,T i,target ) Dt and temperature control adjustment frequency f;
for the position of particlesThe representation is made of a combination of a first and a second color,
wherein i represents a refrigeration equipment index, j represents a particle index, and the value of j is an integer from 1 to N;
step 3: setting the velocity of each particle by V i,j A representation;
step 4: according to the objective function F and the real-time temperature data T of the refrigeration appliance i Calculating the fitness of each particle; setting the objective function as a target for minimizing the temperature control frequency and minimizing the energy consumption;
Step 5: updating the position and velocity of each particle based on the fitness of each particle; updating the individual optimal position and the global optimal position for each particle;
step 6: according to the set maximum iteration times, performing the steps 1 to 5 in an iteration mode; and generating an intelligent temperature control contract according to the global optimal position.
4. The intelligent cold chain monitoring and control system of claim 3, wherein the objective function F is expressed using the following formula:
wherein N is the number of refrigeration equipment; alpha 1 The weight factor for balancing the temperature change rate and the energy consumption is in the range of 0.2 to 0.4; beta 1 The weight factor for balancing the energy consumption and the temperature change rate is in the range of 0.5 to 0.35; gamma is a weighting factor for penalizing temperature differences between different refrigeration appliances. Delta is a weight factor for punishing the speed of change in temperature of the refrigeration appliance; the value range is 0.4 to 0.6; θ is a weight factor for minimizing the temperature of the refrigeration appliance, ranging from 0.6 to 0.8; phi is a temperature T for balancing the second-order temperature change and the target temperature i,target The weight factor of (2) is in the range of 0.5 to 0.8; λ is a weight factor for taking into account the correlation between the temperature change rate and the energy consumption; d (T) i ,T i,target ) Dt is the real-time temperature data T of the refrigerating device i i Relative to target temperature T i,target A rate of change of temperature thereof; e (E) i Energy consumption for the refrigeration appliance i; d (T) i ,T k ) Dτ is the rate of change over time of the difference in real-time temperature data between refrigeration appliance i and refrigeration appliance j; d (T) i ,T i,prev ) The value of/dt is the temperature T of the refrigerating device i relative to the temperature T of the previous time step i,prev Is a rate of change of (c). d, d 2 (T i ,T i,target )/dt 2 Real-time temperature data T for a refrigerating device i i Relative to target temperature T i,target Is a second order rate of temperature change.
5. The intelligent cold chain monitoring and control system according to claim 4, wherein in step 4, the following formula is used according to the objective function F and the real-time temperature of the refrigerating apparatusData T i Calculating Fitness Fitness of each particle i,j ：
Wherein lambda is 1 Taking the value range of 0.35 to 0.45 as a first constraint factor; lambda (lambda) 2 Taking the value range of 0.55 to 0.65 as a second constraint factor; g 1 (P i,j ) Is a first constraint function; g 2 (P i,j ) Is a second constraint function.
6. The intelligent cold chain monitoring and control system of claim 5, wherein the first constraint function is expressed using the formula:
wherein T is min Is the minimum allowable temperature of the refrigeration equipment; t (T) max Is the maximum allowable temperature of the refrigeration equipment.
7. The intelligent cold chain monitoring and control system of claim 6, wherein the second constraint function is expressed using the formula:
8. The intelligent cold chain monitoring and control system of claim 7, wherein step 5 updates the position and velocity of each particle based on its fitness using the following formula:
where ω is the inertial weight, c 1 And c 2 Are learning factors.
9. The intelligent cold chain monitoring and control system of claim 8, wherein the individual optimal position is updated using the following formulaAnd global optimum position->
10. The intelligent cold chain monitoring and control system of claim 9, wherein the contract trigger conditions are: when Fitness is the i,j When the sum of the values is smaller than the set trigger threshold, then the Fitness Fitness is selected i,j And triggering the intelligent temperature control contract by the refrigerating equipment smaller than the set warning threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410001844.1A CN117707093A (en) | 2024-01-02 | 2024-01-02 | Intelligent cold chain monitoring and control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410001844.1A CN117707093A (en) | 2024-01-02 | 2024-01-02 | Intelligent cold chain monitoring and control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117707093A true CN117707093A (en) | 2024-03-15 |
Family
ID=90149935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410001844.1A Pending CN117707093A (en) | 2024-01-02 | 2024-01-02 | Intelligent cold chain monitoring and control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117707093A (en) |
-
2024
- 2024-01-02 CN CN202410001844.1A patent/CN117707093A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| He et al. | Prediction modelling of cold chain logistics demand based on data mining algorithm | |
| He et al. | A hybrid particle swarm optimization with a feasibility-based rule for constrained optimization | |
| Wang et al. | The multi-objective optimization for perishable food distribution route considering temporal-spatial distance | |
| Zhao et al. | Cold chain logistics path optimization via improved multi-objective ant colony algorithm | |
| Ozsoydan | Effects of dominant wolves in grey wolf optimization algorithm | |
| Peng et al. | Deep reinforcement learning approach for capacitated supply chain optimization under demand uncertainty | |
| Kot et al. | Theory of inventory management based on demand forecasting | |
| Lin et al. | Towards quality-aware control of perishable goods in synchromodal transport networks | |
| Fu et al. | A multiobjective particle swarm optimization algorithm based on multipopulation coevolution for weapon-target assignment | |
| Seidmann | Intelligent control schemes for automated storage and retrieval systems | |
| Revillot-Narváez et al. | Optimising the storage assignment and order-picking for the compact drive-in storage system | |
| CN117707093A (en) | Intelligent cold chain monitoring and control system | |
| CN116880612A (en) | Temperature control method and system for cold chain transportation and electronic equipment | |
| Chołodowicz et al. | Control of perishable inventory system with uncertain perishability process using neural networks and robust multicriteria optimization | |
| Yu | Research on fresh product logistics transportation scheduling based on deep reinforcement learning | |
| Kumabe et al. | Learning General Inventory Management Policy for Large Supply Chain Network | |
| CN113850448A (en) | Management method and system for consumption and scheduling of spare parts | |
| Aoun et al. | Self inertia weight adaptation for the particle swarm optimization | |
| Pasha et al. | Integrated quality-based production-distribution planning in two-echelon supply chains | |
| Tuljak Suban et al. | Influence of transportation mode to the deterioration rate: Case study of food transport by ship | |
| Cone et al. | Reward Function Optimization of a Deep Reinforcement Learning Collision Avoidance System | |
| Benyahia et al. | Robust Model-Based Reinforcement Learning Control of a Batch Crystallization Process | |
| Lu et al. | Corrigendum to “The Fourth-Party Logistics Routing Problem Using Ant Colony System-Improved Grey Wolf Optimization” | |
| Gao et al. | Multi-task and multi-stage commodity sorting algorithm for distributed e-commerce logistics system | |
| Govindaiah et al. | Applying Reinforcement Learning to Plan Manufacturing Material Handling Part 2: Experimentation and Results |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |