Intelligent supply chain logistics management system based on artificial intelligence

Abstract

The invention discloses a supply chain logistics intelligent management system based on artificial intelligence. The system comprises a client and a logistics supply management platform. The client is used for generating a logistics distribution request and can be a mobile terminal such as a mobile phone or a PC (Personal Computer); the logistics supply management platform is used for task issuing, monitoring, path planning, warehouse management, path planning and the like. The method has the following advantages: 1, a reasonable driving route can be planned for the freight vehicle; 2, when an emergency occurs to the freight vehicle, a driving route can be re-planned for the freight vehicle at the first time to reduce loss; 3, not only is the safety of the freight vehicle improved, but also the transportation efficiency is ensured; 4, re-planning a driving route for the freight vehicle when the freight vehicle has an emergency (the freight vehicle is on fire or enters water); and 5, an artificial intelligence algorithm is utilized to accurately predict the storage (goods storage) demand, so that the warehouse management is more intelligent.

Description

Technical Field

[0001] This invention relates to the field of logistics management systems, specifically an intelligent supply chain logistics management system based on artificial intelligence. Background Technology

[0002] A supply chain refers to the network structure formed by upstream and downstream enterprises involved in the production and distribution process, encompassing the activities of providing products or services to end users—the entire chain from supplier to consumer. Logistics is a part of the supply chain and is inseparable from it; the two promote and coordinate each other. Supply chain logistics refers to the activities of integrating and coordinating the flow of information, materials, and funds to smoothly deliver products or services from suppliers to end consumers. It covers all stages from raw material procurement, material transportation in manufacturing, product storage, all the way to product delivery to end customers.

[0003] Artificial intelligence (AI) refers to the ability of computer systems to perform tasks that typically require human intelligence, such as learning, reasoning, problem-solving, language understanding, image recognition, planning, and decision-making. It is an interdisciplinary field that integrates computer science, cybernetics, information theory, neurophysiology, psychology, linguistics, philosophy, and other disciplines.

[0004] Currently, artificial intelligence has been widely applied in many fields, including:

[0005] 1. Medical Field: In disease diagnosis, artificial intelligence can assist doctors. For example, by analyzing medical images (such as X-rays, CT scans, and MRIs), deep learning models can identify lesion characteristics, helping doctors to more accurately detect diseases, such as early cancer screening. In drug development, artificial intelligence can predict drug activity and safety, accelerating the drug development process by analyzing large amounts of compound and biological data.

[0006] 2. Transportation: Vehicles collect data about their surroundings using various sensors (such as cameras and radar), and utilize artificial intelligence algorithms for road condition analysis, target recognition, and route planning, thereby achieving autonomous driving. Furthermore, in intelligent traffic management, artificial intelligence can optimize traffic light control, adjusting signal durations in real time based on traffic flow to alleviate traffic congestion.

[0007] 3. Financial Sector: In risk assessment, artificial intelligence can analyze customer credit data, transaction records, and other information to evaluate customer credit and financial risks. For example, banks can use machine learning models to determine whether loan applicants have the ability and willingness to repay. In financial market forecasting, by analyzing data from financial markets such as stocks and bonds, artificial intelligence can predict market trends and help investors make decisions.

[0008] 4. Manufacturing Sector: Artificial intelligence (AI) can be used for product quality inspection. For example, in the electronics manufacturing industry, machine vision systems can be used to inspect the appearance of electronic products, identifying surface defects (such as scratches and solder joint defects), thus improving the efficiency and accuracy of product quality inspection. Simultaneously, in terms of production process optimization, AI can analyze production data, predict equipment failures, optimize production plans, and improve production efficiency. Existing AI-based logistics management systems typically focus on the inbound and outbound information of goods, neglecting the transportation process and failing to plan reasonable routes for freight vehicles.

[0009] At the same time, it is not possible to replan the route of freight vehicles in the event of an emergency to reduce losses, which is a certain drawback. Summary of the Invention

[0010] In view of the shortcomings of the existing technology, the purpose of this invention is to provide an intelligent supply chain logistics management system based on artificial intelligence.

[0011] To achieve the above objectives, the technical solution provided by the present invention is as follows:

[0012] An AI-based intelligent supply chain logistics management system, comprising a client and a logistics supply management platform;

[0013] The client is used to generate logistics delivery requests;

[0014] The logistics supply management platform includes:

[0015] The task issuing unit is used to receive the logistics delivery request and match drivers and transport vehicles according to the logistics delivery request;

[0016] The monitoring unit is used to acquire real-time driver work status information and vehicle location information during the logistics and distribution process; the location information is acquired based on BeiDou navigation.

[0017] The route planning unit is used to receive the location information, plan the driving route for the cargo transport vehicle, and replan the route when an emergency event of the cargo transport vehicle is triggered.

[0018] As one specific implementation of this application, the route planning unit is specifically used for:

[0019] Receive the current location of the transport vehicle and mark it as P1; mark the delivery destination location as P2.

[0020] Select the route with the fewest traffic lights between P1 and P2 on the map and mark it as W1. Select the route with the shortest distance between P1 and P2 on the map and mark it as W2. Select the route with the most lanes (six or more lanes in both directions) between P1 and P2 on the map and mark it as W3.

[0021] Collect the current network time, determine the current network time period and mark it as Ti, i = 1, 2, ..., 23, 24;

[0022] Collect the average traffic flow of W1, W2, and W3 within the time period Ti over the past month and label them as Q1, Q2, and Q3;

[0023] Collect the average number of traffic accidents that occurred in W1, W2, and W3 within the time period Ti over the past month and label them as G1, G2, and G3;

[0024] Calculate the risk value of W1: V1 = (Q1 / preset value) + G1, the risk value of W2: V2 = (Q2 / preset value) + G2, and the risk value of W3: V3 = (Q3 / preset value) + G3.

[0025] The route with the lowest risk value will be output as the planned driving route.

[0026] Furthermore, as a preferred implementation of this application, the monitoring unit is also used for:

[0027] Temperature and humidity sensors are used to monitor the current temperature and humidity of the environment in which the ordered goods are transported.

[0028] If the current temperature is higher than the preset temperature, it indicates that the goods being transported are on fire.

[0029] If the current temperature is less than or equal to the preset temperature, it means that the temperature of the environment in which the goods are currently being transported is normal.

[0030] If the current humidity is greater than the preset humidity, it means that the waterproofing measures for the goods being transported have been compromised.

[0031] If the current humidity is less than or equal to the preset humidity, it means that the humidity of the environment in which the goods are being transported is normal.

[0032] Furthermore, as a preferred implementation of this application, the system further includes an emergency event handling unit, used for:

[0033] If the cargo being transported catches fire or the waterproofing measures of the cargo are breached, an emergency event is triggered on the cargo transport vehicle. An alarm message is sent to the nearest fire station and the route planning unit is prompted to replan the vehicle's route.

[0034] As one specific implementation of this application, the path planning unit replans the vehicle's driving route, specifically as follows:

[0035] Collect the location of the nearest fire station to the cargo transport vehicle and mark it as P3;

[0036] Mark all routes from P1 to P3 as Mi, i = 1 ... n, and then select the five routes with the shortest travel time from Mi and mark them as Sj, j = 1 ... 5;

[0037] Divide Sj into three equal segments according to the distance, and mark the middle segment as sj, j = 1···5;

[0038] The total number of residential buildings, hospitals, schools, and office buildings along both sides of road sj is counted and labeled as Xj, where j = 1...5;

[0039] The average road width on sj is calculated and labeled as Yj, where j = 1...5;

[0040] Calculate the rescue risk value Zj for sj: Zj = 40% * (Xj / 10) - 60% * (Yj / preset road width);

[0041] The route with the lowest rescue risk value Zj will be used as the replanned route.

[0042] Furthermore, as a preferred implementation of this application, the system further includes a storage unit for:

[0043] The system acquires inbound and outbound records, and extracts various types of goods data from these records; the goods data includes the type, quantity, and specifications of the goods.

[0044] The warehouse prediction model is trained using data from various goods.

[0045] Predict the demand for goods storage using a trained warehousing model.

[0046] Compared with the prior art, the beneficial effects of the present invention are reflected in:

[0047] 1. This application can plan reasonable driving routes for freight vehicles. At the same time, in the event of an emergency, it can replan the driving route for freight vehicles in the first instance to reduce losses.

[0048] 2. When planning routes for freight vehicles, this application selects routes with the fewest traffic lights, the shortest distance, and the most lanes (i.e., the most main roads) with six or more lanes in both directions. The selected routes are all representative. The risk value of the selected routes is then calculated, and the route with the lowest risk value is extracted as the planned route. This not only improves the safety of freight vehicles but also ensures transportation efficiency.

[0049] 3. In the event of an emergency (cargo fire or water ingress) involving a freight vehicle, this application will replan the driving route for the freight vehicle. When the freight vehicle is on fire, a route will be planned simultaneously for the freight vehicle and the nearest fire station so that they can proceed in both directions to speed up the rescue. When the cargo is flooded, the driving route will be replanned for the freight vehicle so that it can reach the nearest underground parking lot as soon as possible to prevent the cargo from being further flooded and to facilitate the testing of waterproofing measures.

[0050] 4. This application utilizes artificial intelligence algorithms to accurately predict warehousing (goods storage) demand, making warehouse management more intelligent. Attached Figure Description

[0051] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0052] Figure 1 This is a structural block diagram of an AI-based intelligent supply chain logistics management system provided in an embodiment of the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0054] Please refer to Figure 1 The AI-based intelligent supply chain logistics management system provided in this embodiment of the invention includes a client and a logistics supply management platform; the client is used to generate logistics delivery requests and can be a mobile terminal such as a mobile phone or a PC; the logistics supply management platform is used for task issuance, monitoring, route planning, warehouse management, and route planning, etc.

[0055] As shown in the figure, the logistics supply management platform includes:

[0056] The task issuing unit is used to receive the logistics delivery request and match drivers and transport vehicles according to the logistics delivery request;

[0057] The monitoring unit is used to acquire real-time driver work status information and vehicle location information during the logistics and distribution process; the location information is acquired based on BeiDou navigation.

[0058] The route planning unit is used to receive the location information, plan the driving route for the cargo transport vehicle, and replan the route when an emergency event of the cargo transport vehicle is triggered.

[0059] The emergency incident handling unit is used to trigger an emergency incident on the cargo transport vehicle when the cargo catches fire or the waterproofing measures of the cargo are flooded. It sends an alarm message to the nearest fire station and prompts the route planning unit to replan the vehicle's route.

[0060] Storage units are used to forecast the demand for goods storage.

[0061] In this embodiment, the route planning unit is specifically used for:

[0062] Collect the current location of the freight transport vehicle and mark it as P1; collect the delivery destination location and mark it as P2; filter the route with the fewest traffic lights between P1 and P2 on the map and mark it as W1; filter the route with the shortest distance between P1 and P2 on the map and mark it as W2; filter the route with the most lanes (six or more lanes in both directions) between P1 and P2 on the map and mark it as W3; collect the current network time, determine the current network time period and mark it as Ti, i = 1, 2, ..., 23, 24; collect the previous one The average traffic flow of W1, W2, and W3 within the time period Ti during the month is collected and labeled as Q1, Q2, and Q3; the average number of traffic accidents that occurred in W1, W2, and W3 within the time period Ti in the previous month is collected and labeled as G1, G2, and G3; the risk value V1 of W1 is calculated as (Q1 / preset value) + G1, the risk value V2 of W2 is calculated as (Q2 / preset value) + G2, and the risk value V3 of W3 is calculated as (Q3 / preset value) + G3; the route with the lowest risk value is output as the planned driving route.

[0063] When planning routes for freight vehicles, this application selects routes with the fewest traffic lights, the shortest distance, and the most lanes (i.e., the most avenues) with six or more lanes in both directions. The selected routes are all representative. The risk value of the selected routes is then calculated, and the route with the lowest risk value is extracted as the planned route. This not only improves the safety of freight vehicles but also ensures transportation efficiency.

[0064] In this embodiment, the cargo monitoring unit is specifically used for:

[0065] Temperature and humidity sensors are used to monitor the current temperature and humidity of the environment in which the ordered goods are transported.

[0066] If the current temperature is higher than the preset temperature, it indicates that the goods being transported are on fire.

[0067] If the current temperature is less than or equal to the preset temperature, it means that the temperature of the environment in which the goods are currently being transported is normal.

[0068] If the current humidity is greater than the preset humidity, it means that the waterproofing measures for the goods being transported have been compromised.

[0069] If the current humidity is less than or equal to the preset humidity, it means that the humidity of the environment in which the goods are being transported is normal.

[0070] In this embodiment, when a fire in the transported goods triggers an emergency event for the transport vehicle, the logistics supply management platform sends an alarm message to the fire station closest to the transport vehicle and issues an instruction to the route planning unit to replan the route. After receiving the instruction, the route planning unit replans the vehicle's route and copies the replanned route into two copies, one sent to the transport vehicle and the other sent to the fire station.

[0071] The specific process of the route planning unit replanning the vehicle's driving route is as follows:

[0072] The location of the nearest fire station to the freight transport vehicle is collected and marked as P3; all routes from P1 to P3 are marked as Mi, i = 1...n, and the five routes with the shortest travel time are selected from Mi and marked as Sj, j = 1...5; Sj is divided into three equal segments according to distance, and the middle segment is marked as sj, j = 1...5; the total number of residential buildings, hospitals, schools, and office buildings along both sides of sj is counted and marked as Xj, j = 1...5; the average road width on sj is counted and marked as Yj, j = 1...5; the rescue risk value Zj of sj is calculated as Zj = 40%*(Xj / 10) - 60%*(Yj / preset road width); the route with the smallest rescue risk value Zj is used as the replanned route. This application replans the travel route for freight vehicles in the event of an emergency (freight fire), simultaneously planning routes for both the freight vehicle and the nearest fire station to allow them to travel in both directions, thus accelerating the rescue speed. In addition, when replanning the route, the selected route is calculated based on the sum of the number of residential buildings, hospitals, schools and office buildings in the middle of the route, as well as the corresponding average road width. It should be noted that vehicle fires can easily damage vehicles on the road and buildings on both sides of the road. In this case, the wider the road and the fewer key buildings on both sides, the lower the risk of vehicle fires. This application selects the route with the lowest risk from the selected routes as the route to be replanned.

[0073] Furthermore, the storage unit is specifically used for:

[0074] The system acquires inbound and outbound records, and extracts various types of goods data from these records; the goods data includes the type, quantity, and specifications of the goods.

[0075] The warehouse prediction model is trained using data from various goods.

[0076] Predict the demand for goods storage using a trained warehousing model.

[0077] Specifically, the warehouse prediction model is trained using various types of cargo data as follows:

[0078] Normalize the data of various goods, and then randomly divide the processed data according to a set ratio to obtain a data training set and a data validation set.

[0079] Set the initial particle distribution for the particle swarm optimization algorithm, improve the position and velocity update strategy, and obtain an improved particle swarm optimization algorithm.

[0080] A support vector machine prediction model is constructed, and the kernel function parameters and penalty coefficients of the support vector machine prediction model are optimized based on the particle swarm optimization algorithm. The optimized support vector machine prediction model is then trained and validated using the vaccination data training set and the vaccination data validation set.

[0081] Furthermore, the position and velocity update strategy is improved, including the following steps:

[0082] Set the global optimal change threshold and location mutation strategy;

[0083] Based on the magnitude of the change in the global optimum and the global optimum change threshold, execute either the first update strategy or the second update strategy.

[0084] The first update strategy satisfies the following formula:

[0085]

[0086]

[0087] in, Let λ represent the velocity of the i-th particle in the (t+1)-th iteration after the first update strategy in the j-th dimension. t V represents the weighting factor. i,j (t) represents the velocity of the i-th particle in the j-th dimension at the t-th iteration, c1 and c2 represent acceleration constants, r1 and r2 represent random constants between (0, 1), and P i,j (t) represents the historical best particle in the first t iterations of the i-th particle in the j-th dimension, Pg,j (t) represents the historical best particle of dimension j in the first t iterations, X i,j (t) represents the position of the i-th particle in the j-th dimension. Let represent the position of the i-th particle in the (t+1)-th iteration after the first update strategy in the j-th dimension, where Cauchy(·) represents the Cauchy operator, and Cauchy(0,1) represents a random number that satisfies the standard Cauchy distribution.

[0088] The second update strategy satisfies the following formula:

[0089]

[0090] in, Let k represent the velocity of the i-th particle in the (t+1)-th iteration after the second update strategy is applied in the j-th dimension. i (t) represents the fitness ranking of the i-th particle in the t-th iteration, N represents the number of particles, and V i,j (t) represents the velocity of the i-th particle in the j-th dimension at the t-th iteration. P represents the position of the i-th particle in the (t+1)-th iteration after the second update strategy in the j-th dimension. i，j (t) represents the historical best particle of the i-th particle in the j-th dimension during the previous t iterations, where t represents the current iteration number, iter max X represents the maximum number of iterations. i,j (t) represents the position of the i-th particle in the j-th dimension, and m represents a random constant between (0, 1).

[0091] As can be seen from the above description, the system provided in the embodiments of the present invention has the following advantages:

[0092] 1. This application can plan reasonable driving routes for freight vehicles. At the same time, in the event of an emergency, it can replan the driving route for freight vehicles in the first instance to reduce losses.

[0093] 2. When planning routes for freight vehicles, this application selects routes with the fewest traffic lights, the shortest distance, and the most lanes (i.e., the most main roads) with six or more lanes in both directions. The selected routes are all representative. The risk value of the selected routes is then calculated, and the route with the lowest risk value is extracted as the planned route. This not only improves the safety of freight vehicles but also ensures transportation efficiency.

[0094] 3. In the event of an emergency (cargo fire or water ingress) involving a freight vehicle, this application will replan the driving route for the freight vehicle. When the freight vehicle is on fire, a route will be planned simultaneously for the freight vehicle and the nearest fire station so that they can proceed in both directions to speed up the rescue. When the cargo is flooded, the driving route will be replanned for the freight vehicle so that it can reach the nearest underground parking lot as soon as possible to prevent the cargo from being further flooded and to facilitate the testing of waterproofing measures.

[0095] 4. This application utilizes artificial intelligence algorithms to accurately predict warehousing (goods storage) demand, making warehouse management more intelligent.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. 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 or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. An intelligent supply chain logistics management system based on artificial intelligence, characterized in that, This includes client-side and logistics supply management platforms; The client is used to generate logistics delivery requests; The logistics supply management platform includes: The task issuing unit is used to receive the logistics delivery request and match drivers and transport vehicles according to the logistics delivery request; The monitoring unit is used to acquire real-time driver work status information and vehicle location information during the logistics and distribution process; the location information is acquired based on BeiDou navigation. The route planning unit is used to receive the location information, plan the driving route for the cargo transport vehicle, and replan the route when an emergency event of the cargo transport vehicle is triggered.

2. The system according to claim 1, characterized in that, The route planning unit is specifically used for: Receive the current location of the transport vehicle and mark it as P1; mark the delivery destination location as P2. Select the route with the fewest traffic lights between P1 and P2 on the map and mark it as W1. Select the route with the shortest distance between P1 and P2 on the map and mark it as W2. Select the route with the most lanes (six or more lanes in both directions) between P1 and P2 on the map and mark it as W3. Collect the current network time, determine the current network time period and mark it as Ti, i = 1, 2, ..., 23, 24; Collect the average traffic flow of W1, W2, and W3 within the time period Ti over the past month and label them as Q1, Q2, and Q3; Collect the average number of traffic accidents that occurred in W1, W2, and W3 within the time period Ti over the past month and label them as G1, G2, and G3; Calculate the risk value of W1: V1 = (Q1 / preset value) + G1, the risk value of W2: V2 = (Q2 / preset value) + G2, and the risk value of W3: V3 = (Q3 / preset value) + G3. The route with the lowest risk value will be output as the planned driving route.

3. The system as described in claim 1, characterized in that, The monitoring unit is also used for: Temperature and humidity sensors are used to monitor the current temperature and humidity of the environment in which the ordered goods are transported. If the current temperature is higher than the preset temperature, it indicates that the goods being transported are on fire. If the current temperature is less than or equal to the preset temperature, it means that the temperature of the environment in which the goods are currently being transported is normal. If the current humidity is greater than the preset humidity, it means that the waterproofing measures for the goods being transported have been compromised. If the current humidity is less than or equal to the preset humidity, it means that the humidity of the environment in which the goods are being transported is normal.

4. The system as described in claim 3, characterized in that, The system also includes an emergency event handling unit for: If the cargo being transported catches fire or the waterproofing measures of the cargo are breached, an emergency event is triggered on the cargo transport vehicle. An alarm message is sent to the nearest fire station and the route planning unit is prompted to replan the vehicle's route.

5. The system as described in claim 4, characterized in that, The path planning unit replans the vehicle's driving route, specifically as follows: Collect the location of the nearest fire station to the cargo transport vehicle and mark it as P3; Mark all routes from P1 to P3 as Mi, i = 1 ... n, and then select the five routes with the shortest travel time from Mi and mark them as Sj, j = 1 ... 5; Divide Sj into three equal segments according to the distance, and mark the middle segment as sj, j = 1···5; The total number of residential buildings, hospitals, schools, and office buildings along both sides of road sj is counted and labeled as Xj, where j = 1...5; The average road width on sj is calculated and labeled as Yj, where j = 1...5; Calculate the rescue risk value Zj for sj: Zj = 40% * (Xj / 10) - 60% * (Yj / preset road width); The route with the lowest rescue risk value Zj will be used as the replanned route.

6. The system according to any one of claims 1-5, characterized in that, The system also includes a storage unit for: The system acquires inbound and outbound records, and extracts various types of goods data from these records; the goods data includes the type, quantity, and specifications of the goods. The warehouse prediction model is trained using data from various goods. Predict the demand for goods storage using a trained warehousing model.

7. The system as described in claim 6, characterized in that, The warehouse prediction model is trained using various types of cargo data as follows: Normalize the data of various goods, and then randomly divide the processed data according to a set ratio to obtain a data training set and a data validation set. Set the initial particle distribution for the particle swarm optimization algorithm, improve the position and velocity update strategy, and obtain an improved particle swarm optimization algorithm. A support vector machine prediction model is constructed, and the kernel function parameters and penalty coefficients of the support vector machine prediction model are optimized based on the particle swarm optimization algorithm. The optimized support vector machine prediction model is then trained and validated using the vaccination data training set and the vaccination data validation set.

8. The system as described in claim 7, characterized in that, The improved position and velocity update strategy includes the following steps: Set the global optimal change threshold and location mutation strategy; Based on the magnitude of the change in the global optimum and the global optimum change threshold, execute either the first update strategy or the second update strategy.

9. The system as described in claim 8, characterized in that, The first update strategy satisfies the following formula: in, Let λ represent the velocity of the i-th particle in the (t+1)-th iteration after the first update strategy in the j-th dimension. t V represents the weighting factor. i，j (t) represents the velocity of the i-th particle in the j-th dimension at the t-th iteration, c1 and c2 represent acceleration constants, r1 and r2 represent random constants between (0, 1), and P i，j (t) represents the historical best particle in the first t iterations of the i-th particle in the j-th dimension, P g，j (t) represents the historical best particle of dimension j in the first t iterations, X i，j (t) represents the position of the i-th particle in the j-th dimension. Let represent the position of the i-th particle in the (t+1)-th iteration after the first update strategy in the j-th dimension, where Cauchy(·) represents the Cauchy operator, and Cauchy(0,1) represents a random number that satisfies the standard Cauchy distribution. The second update strategy satisfies the following formula: in, Let k represent the velocity of the i-th particle in the (t+1)-th iteration after the second update strategy is applied in the j-th dimension. i (t) represents the fitness ranking of the i-th particle in the t-th iteration, N represents the number of particles, and V i，j (t) represents the velocity of the i-th particle in the j-th dimension at the t-th iteration. P represents the position of the i-th particle in the (t+1)-th iteration after the second update strategy in the j-th dimension. i，j (t) represents the historical best particle of the i-th particle in the j-th dimension during the previous t iterations, where t represents the current iteration number, iter max X represents the maximum number of iterations. i，j (t) represents the position of the i-th particle in the j-th dimension, and m represents a random constant between (0, 1).

Images