CN116934220A - Intelligent warehouse layout method based on intelligent data analysis and algorithm optimization - Google Patents
Intelligent warehouse layout method based on intelligent data analysis and algorithm optimization Download PDFInfo
- Publication number
- CN116934220A CN116934220A CN202310819180.5A CN202310819180A CN116934220A CN 116934220 A CN116934220 A CN 116934220A CN 202310819180 A CN202310819180 A CN 202310819180A CN 116934220 A CN116934220 A CN 116934220A
- Authority
- CN
- China
- Prior art keywords
- warehouse
- intelligent
- layout
- algorithm
- data analysis
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000007405 data analysis Methods 0.000 title claims abstract description 40
- 238000013178 mathematical model Methods 0.000 claims abstract description 17
- 238000012544 monitoring process Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000010354 integration Effects 0.000 claims abstract description 8
- 239000002245 particle Substances 0.000 claims description 52
- 230000035772 mutation Effects 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 15
- 238000001816 cooling Methods 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 13
- 230000002068 genetic effect Effects 0.000 claims description 13
- 238000007726 management method Methods 0.000 claims description 13
- 108090000623 proteins and genes Proteins 0.000 claims description 10
- 238000002922 simulated annealing Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 9
- 210000000349 chromosome Anatomy 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 claims description 3
- 108700028369 Alleles Proteins 0.000 claims description 2
- 238000013499 data model Methods 0.000 claims description 2
- 230000003094 perturbing effect Effects 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 30
- 230000008569 process Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 3
- 238000000137 annealing Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Finance (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an intelligent warehouse layout method based on intelligent data analysis and algorithm optimization, aiming at improving warehouse operation efficiency, accuracy and intelligent level. By collecting and processing warehouse data, applying intelligent data analysis and establishing a mathematical model and utilizing an optimization algorithm to perform layout optimization, the intelligent warehouse system can realize the optimized layout of intelligent warehouse and improve the warehouse space utilization rate and the goods access efficiency. The layout method combines real-time monitoring, intelligent decision support and system integration, can improve accuracy and automation level of warehouse operation, provides decision reference and assistance for warehouse management personnel, achieves the goal of intelligent warehouse management, and brings important technical progress and innovation for development of warehouse industry.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent warehouse layout method based on intelligent data analysis and algorithm optimization.
Background
Traditional warehouse management often relies on experience and intuition to perform warehouse layout, and lacks scientific and intelligent support. The existing warehouse management system often cannot meet the intelligent requirements of warehouse operation, and has the problems of low space utilization rate, long goods storage and taking time and the like. Over the past decades, with the rapid development of information technology and data analysis algorithms, intelligent data analysis and optimization algorithms have been increasingly applied to the field of warehouse management.
The intelligent data analysis technology can mine and analyze a large amount of warehouse data, and extract key information and rules. Through analysis of the goods storage and flow conditions, key indexes and influencing factors of warehouse operation can be obtained, and data support is provided for optimizing layout. The optimization algorithm can find an optimal warehouse layout scheme under a plurality of constraint conditions through the establishment and solution of a mathematical model, and the warehouse space utilization rate and the goods access efficiency are improved.
However, the intelligent warehouse layout strategy in the prior art still has some problems. For example, the integration degree of data analysis and algorithm optimization is low, and functions of real-time monitoring and intelligent decision support are lacked. Therefore, there is a need for an intelligent warehouse layout strategy that combines intelligent data analysis and algorithm optimization to improve the level of intelligence and overall benefits of warehouse operations. The invention provides an innovative solution to the problems, and brings new technological breakthrough and development opportunities for intelligent warehouse management.
Disclosure of Invention
The invention provides an intelligent warehouse layout method based on intelligent data analysis and algorithm optimization, which can fully utilize warehouse data and advanced algorithm technology through intelligent data analysis and optimization algorithm, and provides intelligent, optimized and automatic layout strategies for the warehouse industry.
In order to achieve the purpose of the invention, the technical scheme adopted is as follows: an intelligent warehouse layout method based on intelligent data analysis and algorithm optimization is characterized in that: the intelligent warehouse layout method comprises the following steps:
s1, data collection and processing: collecting warehouse related data in real time by using a sensor and an internet of things technology;
s2, intelligent data analysis: processing and analyzing warehouse data by applying a data mining and analyzing technology;
s3, constructing a data model: establishing a mathematical model of the warehouse layout based on the collected warehouse related data and the analysis result of the intelligent data;
s4, optimizing algorithm application: selecting a proper optimization algorithm to optimize the mathematical model of the built warehouse layout;
s5, layout evaluation and adjustment: evaluating the mathematical model of the optimized warehouse layout obtained in the step S4;
s6, visual display and decision support: displaying the optimized warehouse layout in the step S5 to a user through a visual interface;
s7, real-time monitoring and adjustment: setting a real-time monitoring system to collect actual operation data, and adjusting and optimizing the layout according to the actual operation data;
s8, intelligent decision support: developing an intelligent decision system by combining intelligent data analysis and an optimization algorithm;
s9, intelligent warehouse system integration: the intelligent warehouse layout method based on intelligent data analysis and algorithm optimization is applied to the existing warehouse management system for integration.
As an optimization scheme of the present invention, in step S1, the warehouse-related data includes warehouse size, cargo type, demand, and storage location.
As an optimization scheme of the present invention, in step S2: classifying cargoes by using a cluster analysis method, and finding out the similarity and the difference between cargoes; using an association rule mining method to find the association relation between cargoes; and establishing a prediction model to predict the demand and storage position of the goods.
As an optimization scheme of the invention, in step S3, a mathematical model of a warehouse layout contains an objective function and constraint conditions, and the objective function includes a minimum cargo access time; the constraints include cargo flow path constraints, shelf capacity constraints, and cargo classification requirements constraints.
As an optimization scheme of the present invention, in step S4, a genetic algorithm is used to optimize a warehouse layout, and an optimal solution is found, which specifically includes:
s4-1, coding: representing the goods placement position on the goods shelf by binary codes;
s4-2, initializing population: randomly generating a certain number of individuals as an initial population;
s4-3, evaluation: calculating the fitness value of each individual, evaluating the quality of the goods shelf layout or goods placement scheme represented by the chromosome, and calculating the fitness according to the characteristics of the goods and the limitation conditions of the warehouse;
s4-4, selecting: selecting according to the fitness of the individual, wherein a selection operator adopts roulette selection or tournament selection;
s4-5, crossing: randomly pairing selected individuals, performing cross operation on the paired individuals according to a certain probability to form new individuals, wherein a single-point cross or multi-point cross is adopted by a cross operator;
s4-6, changing the gene value of one or a plurality of genes into the allele value according to a certain mutation probability for each individual in the population, wherein a mutation operator adopts basic position mutation or uniform mutation;
s4-7, loop iteration: repeating the steps S4-3 to S4-6 until the preset iteration times are reached or convergence conditions are met;
s4-8, decoding: and decoding the optimal solution individuals in the final population to obtain an optimal solution or an approximate optimal solution.
As an optimization scheme of the invention, in step S4, the warehouse layout is optimized by using a simulated annealing algorithm, an optimal solution is found,
1) Initializing: defining parameters of a warehouse layout problem, including an initial state S, an initial temperature T, a termination temperature tf, a cooling constant c and a Markov chain length L;
2) Searching: at each temperature, an L-round search was performed, for each round of search the following operations were performed:
A. randomly perturbing the current state S to generate a new state S';
B. calculating a fitness value f (S ') of the new state S ', wherein the fitness value f (S ') is the degree of merit of calculating the new layout, and the degree of merit includes space utilization and access efficiency;
C. judging whether to accept the new state S': if f (S ') > f (S), accepting the new state S ' with probability min {1, exp (f (S ') -f (S)/T) }; otherwise, the new state S' is not accepted;
D. and (3) cooling: multiplying the current temperature T by a cooling constant c;
E. judging whether the temperature is lower than the termination temperature tf: if the solution is lower than the preset threshold, ending the algorithm and outputting an optimal solution; otherwise, returning to the step B.
As an optimization scheme of the present invention, in step S4, a particle swarm algorithm is used to optimize a warehouse layout, and an optimal solution is found: the method comprises the following specific steps:
(1) Initializing: setting the number N of particles, the dimension D of a search space, acceleration constants c1 and c2, an inertia weight w, the maximum iteration number MaxIter and a modulus M of modular operation;
(2) Randomly generating N particles, each particle having a position and a velocity in a D-dimensional space, and a minimum and a maximum in each dimension;
(3) Calculating the fitness value of each particle, and updating the individual extremum and the global extremum according to the fitness value;
(4) The following steps are repeated until the maximum number of iterations is reached:
a. updating the speed and the position of each particle according to a speed updating formula, specifically:
i. for each dimension, if the absolute value of the particle velocity is greater than the dimension, searching for a null
A range between, limiting the speed to the range;
if the modulus of particle velocity is greater than M, the velocity is limited to [ -M, M ]
Between them;
m represents the upper limit of the modulus of the velocity, the meaning of this formula being to limit the component of the particle velocity between [ -M, M ] if it is greater than M; if the component of particle velocity is less than-M, it is limited to between [ -M, M ]; if the component of the particle velocity is between [ -M, M ], it remains unchanged. By performing such a limiting operation, it is ensured that the modulus of the particle velocity does not exceed M, avoiding that the search loses convergence due to too fast a particle movement.
b. Limiting the position of the particles within the search space and if the range is exceeded then weighing
Initializing newly;
c. updating the individual extremum and the global extremum;
(5) And returning the global optimal solution and the fitness value.
The invention has the positive effects that: 1) The invention aims to improve the operation efficiency, accuracy and intelligent level of a warehouse. By collecting and processing warehouse data, applying intelligent data analysis and establishing a mathematical model and utilizing an optimization algorithm to perform layout optimization, the intelligent warehouse system can realize the optimized layout of intelligent warehouse and improve the warehouse space utilization rate and the goods access efficiency. The layout strategy combines real-time monitoring, intelligent decision support and system integration, can improve accuracy and automation level of warehouse operation, and provides decision reference and assistance for warehouse management personnel. According to the intelligent warehouse management system, the aim of intelligent warehouse management is fulfilled, and important technical progress and innovation are brought to the development of the warehouse industry;
2) The invention can fully utilize warehouse data and advanced algorithm technology through intelligent data analysis and optimization algorithm, and provides intelligent, optimized and automatic layout strategy for warehouse industry. The application potential of the technical field is huge, and the promotion of the warehouse management level and the development of an intelligent warehouse system can be promoted;
3) The warehouse operation efficiency is improved: through intelligent data analysis and algorithm optimization, the strategy can effectively optimize warehouse layout, reduce cargo access time and operation path, and improve warehouse operation efficiency. The optimized layout scheme can reduce the moving distance and time of the goods, reduce the cost of searching and taking out the goods, and enable warehouse operation to be more efficient.
2. Maximizing warehouse space utilization: by comprehensively considering the cargo flow rules and the warehouse space layout, the strategy can maximize the utilization of the storage space of the warehouse. Through intelligent data analysis and algorithm optimization, cargoes can be reasonably distributed and stored, space waste in the warehouse is reduced, and space utilization rate of the warehouse is improved.
3. Optimizing cargo flow paths: the strategy can identify and optimize the path and rule of the cargo flow through data analysis and algorithm optimization. According to the attribute, the demand and the flow condition of goods, the optimized layout scheme can enable the flow path of the goods to be more reasonable and efficient, reduce logistics congestion and redundancy, and improve the transportation efficiency of the goods.
4. Personalized layout scheme: the strategy can generate a personalized layout scheme according to the characteristics of different warehouses and business requirements. Through data analysis and algorithm optimization, an optimal layout scheme is automatically generated according to the specific situation and limiting condition of the warehouse, personalized requirements of the warehouse are met, and the adaptability and flexibility of layout are improved.
5. Human error is reduced: by means of an intelligent layout strategy, the influence of human factors on warehouse operation is reduced, and the occurrence probability of human errors is reduced. The automatic layout scheme can reduce subjective factors of manual decisions, provide scientific and reliable references, reduce errors and faults in warehouse operation, and improve the accuracy and reliability of warehouse operation.
Drawings
The invention will be described in further detail with reference to the drawings and the detailed description.
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
As shown in fig. 1, the invention discloses an intelligent warehouse layout method based on intelligent data analysis and algorithm optimization, which comprises the following steps:
1. data collection and processing: by using sensors and internet of things technology, warehouse related data including warehouse size, cargo type, demand, storage location, etc. is collected in real time. The collected data is subjected to preprocessing steps such as cleaning, noise removal, abnormal value removal and the like so as to ensure the accuracy and the reliability of the data.
2. Intelligent data analysis: advanced data mining and analysis techniques are applied to process and analyze warehouse data. The method comprises the steps of classifying cargoes by using a cluster analysis method, and finding the similarity and the difference between different categories; using an association rule mining method to find the association relation between cargoes; and establishing a prediction model to predict the demand quantity, storage position and the like of the goods. Through the analysis means, key information and rules can be extracted from warehouse data, and scientific basis is provided for optimization of warehouse layout.
3. And (3) constructing a mathematical model: based on the collected data and the results of the intelligent data analysis, a mathematical model of the warehouse layout is established. This model describes the problem of warehouse layout, including the location and arrangement of shelves, storage locations and aisles, etc. At the same time, the model contains objective functions and constraint conditions to ensure that the warehouse layout meets the requirements of warehouse operation. Through the establishment of a mathematical model, the warehouse layout problem is converted into an optimization problem, and accurate input is provided for a subsequent optimization algorithm.
4. The optimization algorithm is applied: an appropriate optimization algorithm is selected to address the mathematical model established. Common optimization algorithms include genetic algorithms, simulated annealing algorithms, ant colony algorithms, and the like. The algorithms gradually optimize the warehouse layout in a searching and iterative mode to find the optimal solution or near the optimal solution. And the optimizing algorithm adjusts the storage positions of the cargoes and the layout of the warehouse according to the objective function and constraint conditions defined in the mathematical model so as to improve the operation efficiency and accuracy of the warehouse.
In step S4, the warehouse layout is optimized using a genetic algorithm, an optimal solution is found,
(1) The genetic algorithm is based on the thought of natural evolution, and simulates the operations of selection, crossover, mutation and the like in the genetic process. Through these operations, the preferred individuals will be selected and retained, while through crossover and mutation operations, new individuals will be introduced as well, in hopes of finding the optimal solution in the search space. Through continuous iteration and evolution, the genetic algorithm can gradually optimize the warehouse layout scheme.
(2) Algorithm model:
individual representation: each individual is a warehouse layout plan, represented by a set of genes. Each gene corresponds to a warehouse location.
Fitness function: according to the quality of the warehouse layout scheme, an adaptability function is defined to evaluate the adaptability value of the individual.
Selecting: using the selection operation, a part of the excellent individuals are selected as parents according to fitness values of the individuals.
Crossover and mutation: new offspring individuals are generated by crossover and mutation operations. The crossover operation combines the genes of two parent individuals, and the mutation operation randomly transforms the genes of child individuals.
Updating: and updating the current individual population according to the newly generated offspring individuals.
Termination condition: a preset termination condition is reached (e.g., a maximum number of iterations is reached or a satisfactory solution is reached).
(3) The method comprises the following specific steps:
encoding: the entity of the shelf, warehouse, vehicle, etc. is transformed into a chromosome, for example, the goods placement location on the shelf is represented in binary code.
Initializing a population: a number of individuals are randomly generated as an initial population.
Evaluation: and calculating the fitness value of each individual, namely evaluating the quality of the goods shelf layout or goods placement scheme represented by the chromosome. The fitness may be calculated based on characteristics of the goods and constraints of the warehouse, such as calculating space utilization of the shelves, efficiency of access, picking path length of the goods, etc.
Selecting: the selection is performed according to the fitness of the individual, and the probability that the individual with higher fitness is selected is higher. The selection operator may be in the form of roulette selection, tournament selection, or the like.
Crossing: randomly pairing selected individuals, and performing cross operation on the paired individuals according to a certain probability to form new individuals. The crossover operator may use single-point crossover, multi-point crossover, etc.
Variation: for each individual in the population, the genetic value on one or some genes is changed to other allelic values with a certain probability (mutation probability). The mutation operator can adopt basic position mutation, uniform mutation and other modes.
And (3) loop iteration: repeating the steps 3-6 until the preset iteration times are reached or a certain convergence condition is met.
Decoding: and decoding the optimal solution individuals in the final population to obtain an optimal solution or an approximate optimal solution.
Through the steps, the genetic algorithm can simulate the natural evolution process, and an optimal solution or an approximate optimal solution is found in the optimization problem of the warehouse layout strategy. The specific implementation of the genetic algorithm will be affected by factors such as selection operators, crossover operators, mutation operators, etc.
In step S4, the warehouse layout is optimized using a simulated annealing algorithm, finding the optimal solution:
(1) Basic principle:
the simulated annealing algorithm is inspired by the solid matter annealing cooling process. By accepting the strategy of poor solution, the simulated annealing algorithm has a larger chance of escaping from the locally optimal solution in the searching process, so that the globally optimal storage layout scheme is found. Through the process of reducing the temperature, the simulated annealing algorithm can gradually narrow the search range in hopes of finding the optimal solution.
(2) Algorithm model:
solution space: the solution space represents all possible warehouse layout schemes.
Initial solution: an initial warehouse layout scheme is randomly generated as the current solution.
Neighborhood search: and generating a new warehouse layout scheme in the solution space according to a certain neighborhood searching strategy.
Energy function: and calculating the energy difference between the current solution and the new solution according to the evaluation function, wherein the energy difference reflects the quality degree of the new solution relative to the current solution.
Probability of acceptance: and calculating the probability of accepting the new solution according to the energy difference and the current temperature.
Updating: and determining whether to accept the new solution according to the acceptance probability. If a new solution is accepted, the current solution is updated to be the new solution.
Reducing the temperature: the current temperature is reduced and the cooling process in the annealing process is simulated.
Termination condition: a preset termination condition is reached (e.g., the temperature decreases to a minimum or a maximum number of iterations is reached).
(3) The method comprises the following specific steps:
initializing: defining an initial state S of the warehouse layout problem, and setting parameters such as an initial temperature T, a termination temperature tf, a cooling constant c, a Markov chain length L and the like.
Searching: at each temperature, an L round of search was performed. For each round of search, the following operations are performed:
a. the current state S is randomly perturbed to generate a new state S'.
b. The fitness value f (S ') of the new state S' is calculated, i.e., the degree of merit (e.g., space utilization, access efficiency, etc.) of the new layout is calculated.
c. Judging whether to accept the new state S': if f (S ') > f (S), accepting the new state S ' with probability min {1, exp (f (S ') -f (S)/T) }; otherwise, the new state S' is not accepted.
And (3) cooling: the current temperature T is multiplied by a cooling constant c.
Judging whether the temperature is lower than the termination temperature tf: if the solution is lower than the preset threshold, ending the algorithm and outputting an optimal solution; otherwise, returning to the step 2.
In the problem of searching the optimal layout of the goods shelves, the fitness function can calculate factors such as space utilization rate, access time, picking path length of goods and the like of the goods shelves so as to achieve the aims of improving the space utilization rate, the access efficiency, the goods picking efficiency and the like of the warehouse.
In step S4, the warehouse layout is optimized using a particle swarm algorithm, finding the optimal solution:
(1) Basic principle of
Particle swarm algorithms are inspired by the swarm behavior of a bird or fish swarm. The particle swarm algorithm simulates interaction and learning processes among individuals in the population through cooperation and information sharing among the particles. By updating the position and speed of the particles, the particle swarm algorithm can gradually converge to a better warehouse layout scheme in the search space.
(2) Algorithm model
Particle swarm: each particle represents a warehouse layout plan.
Position and velocity: each particle has a location and a velocity attribute, the location representing a warehouse layout plan, the velocity being used to update the location.
Global optimal solution and individual optimal solution: each particle maintains information of a globally optimal solution and an individually optimal solution.
Updating: and updating the speed and the position of the particles according to the current position, the speed, the global optimal solution and the information of the individual optimal solution.
Termination condition: a preset termination condition is reached (e.g., a maximum number of iterations is reached or a satisfactory solution is reached).
(3) The particle swarm optimization method comprises the following steps:
the modulo particle swarm algorithm (Modal Particle Swarm Optimization, modal PSO for short) is an improved particle swarm algorithm, and the global searching capability of the algorithm is enhanced by introducing modulo operation (Modular Arithmetic), so that the optimization performance of the algorithm is improved. The modulo operation is an operation method in which division is performed on two integers and then the remainder is used as a result. In the Modal PSO algorithm, modulo arithmetic is used to limit the speed and direction of flight of the particles, thereby enhancing the global search capability of the algorithm.
The following steps for solving the problem of optimizing the warehouse layout strategy by using the Modal PSO algorithm are as follows:
initializing: the method comprises the steps of setting the number N of particles, the dimension D of a search space, acceleration constants c1 and c2, an inertia weight w, the maximum iteration number MaxIter and a modulus M of modular operation.
N particles are randomly generated, each particle having a position and velocity in D-dimensional space, and a minimum and maximum in each dimension.
And calculating the fitness value of each particle, and updating the individual extremum and the global extremum according to the fitness value.
The following steps are repeated until the maximum number of iterations is reached:
a. updating the speed and position of each particle according to a speed update formula:
i. for each dimension, if the absolute value of the particle velocity is greater than the range of the dimension search space, the velocity is limited to that range.
if the modulus of particle velocity is greater than M, the velocity is limited to [ -M, M ]
Between them.
b. Limiting the position of the particles to be within the search space range and reinitializing if the range is exceeded.
c. Updating the individual extremum and the global extremum, and if a better solution is found, updating the corresponding extremum with a new solution.
And returning the global optimal solution and the fitness value thereof.
5. Layout evaluation and adjustment: and simulating and evaluating the layout scheme obtained by optimization. The evaluation index may include warehouse space utilization, time of goods access, operational accuracy, etc. And according to the evaluation result, adjusting and optimizing the layout scheme to meet the requirements and actual conditions of warehouse operation.
6. Visual presentation and decision support: and displaying the optimized warehouse layout scheme to a user through a visual interface. The user can intuitively know the effect and performance index of the layout scheme, and make decisions and adjustments. Meanwhile, the software application provides a decision support function, automatically generates a plurality of alternative schemes according to the requirements and constraint conditions of the user, gives corresponding evaluation results and helps the user make reasonable decisions.
7. Real-time monitoring and adjustment: in the layout implementation process, a real-time monitoring system is arranged to collect actual operation data and compare and analyze the actual operation data with predicted data. And adjusting and optimizing the layout according to the actual situation so as to maintain the optimal warehouse layout state.
8. Intelligent decision support: and developing an intelligent decision support system by combining the intelligent data analysis and the optimization algorithm. The system can automatically provide an optimized layout scheme and an optimized operation strategy according to warehouse data and operation requirements, and provides decision references and assistance for warehouse management personnel.
9. Integration of the intelligent warehousing system: and integrating the intelligent warehouse layout strategy based on intelligent data analysis and algorithm optimization with the existing warehouse management system. Through interface and data interaction, comprehensive optimization and intelligent management of the intelligent warehouse system are realized.
The algorithm functions are applied in specific business scenarios as follows;
1. objective function: in the smart warehouse layout, the objective function may be defined according to specific requirements. For example, for a scenario where the goal is to increase the efficiency of cargo access, the objective function may be to minimize cargo access time. In this case, the objective function will take into account factors such as the cargo flow path, storage location and operating time in order to find an optimal layout scheme to minimize the access time of the cargo and reduce the time consumption of the warehouse internal logistics.
2. Constraint condition function: in the smart warehouse layout, constraint functions are used to satisfy various requirements and constraints. For example, constraints on the flow path of the cargo may ensure reasonable movement and efficient access of the cargo within the warehouse. The constraint condition of the goods shelf capacity can prevent the goods shelf capacity from exceeding the bearing capacity of the goods shelf, and the goods can be safely stored. Constraints on the cargo classification requirements may ensure that different types of cargo are stored according to specific classification rules. These constraint functions will be defined and designed according to specific business needs.
3. Data analysis function: in the smart warehouse layout, data analysis functions are used to process and mine warehouse operations data to extract key information and rules. For example, the goods may be grouped by some similarity through a cluster analysis function to help determine the storage location and optimal flow path of the goods. Through the association rule mining function, the association between cargoes can be found, so that the layout scheme is optimized. The time series analysis function may then help predict the trend of the cargo flow in order to rationally adjust the warehouse layout.
4. Optimizing algorithm functions: in the smart warehouse layout, an optimization algorithm function is used to solve the optimization problem in the mathematical model to find the optimal layout scheme. For example, for genetic algorithms, it is first necessary to convert the warehouse layout strategy optimization problem to genotype, i.e., convert the entities of shelves, goods, warehouses, etc., to genes on chromosomes. Then, according to a certain crossover and mutation operator, crossover and mutation operations are carried out on the chromosome, so that a new individual is generated. And evaluating the quality degree of the individuals by calculating the fitness value, and selecting individuals with higher fitness values for reproduction to generate a new generation population. Repeating the steps until the preset stopping condition is met.
For the simulated annealing algorithm, an objective function, namely, a fitness function of the warehouse layout strategy needs to be defined to evaluate the degree of layout. Then, starting from the random initial temperature, continuously reducing the temperature according to a certain cooling strategy, and repeatedly executing the following operations: a new layout is randomly generated, the fitness value is calculated, and the new layout is used as a reference to determine whether to accept the layout. In the cooling process, along with the reduction of the temperature, the probability of receiving the inferior layout is gradually reduced, and finally the stable state is achieved, wherein the obtained layout is the local optimal solution.
For the particle swarm algorithm, the storage layout strategy optimization problem needs to be converted into the movement problem of particles in the search space. Each particle adjusts its own speed and position according to the individual extremum and the global extremum, and flies in a better direction. In each iteration, the fitness value of each particle is calculated, and the individual extremum and the global extremum are updated according to the fitness value. Repeating the steps until the preset stopping condition is met.
In practical application, a suitable algorithm can be selected according to specific requirements and scenes. For example, for simpler problems, particle swarm optimization can be used for solving, the implementation is simpler, and the solution speed is faster; for more complex problems, genetic algorithm or simulated annealing algorithm can be used for solving, the genetic algorithm or simulated annealing algorithm has stronger global searching capability or better local searching capability, and the complex warehouse layout strategy optimization problem can be solved better. Meanwhile, in the concrete implementation, the algorithm can be subjected to parameter adjustment or improvement according to actual conditions so as to obtain a better solving effect.
5. Layout evaluation function: in the smart warehouse layout, a layout evaluation function is used to evaluate the effect and performance of the optimized layout scheme. For example, the layout scheme can be simulated by a simulation method or a simulation system, and key indexes such as cargo access time, warehouse space utilization rate and the like are calculated. According to the evaluation result, the layout scheme can be adjusted and optimized to further improve the warehouse operation efficiency and accuracy
While the foregoing is directed to embodiments of the present invention, other and further details of the invention may be had by the present invention, it should be understood that the foregoing description is merely illustrative of the present invention and that no limitations are intended to the scope of the invention, except insofar as modifications, equivalents, improvements or modifications are within the spirit and principles of the invention.
Claims (7)
1. An intelligent warehouse layout method based on intelligent data analysis and algorithm optimization is characterized in that: the intelligent warehouse layout method comprises the following steps:
s1, data collection and processing: collecting warehouse related data in real time by using a sensor and an internet of things technology;
s2, intelligent data analysis: processing and analyzing warehouse data by applying a data mining and analyzing technology;
s3, constructing a data model: establishing a mathematical model of the warehouse layout based on the collected warehouse related data and the analysis result of the intelligent data;
s4, optimizing algorithm application: selecting a proper optimization algorithm to optimize the mathematical model of the built warehouse layout;
s5, layout evaluation and adjustment: evaluating the mathematical model of the optimized warehouse layout obtained in the step S4;
s6, visual display and decision support: displaying the optimized warehouse layout in the step S5 to a user through a visual interface;
s7, real-time monitoring and adjustment: setting a real-time monitoring system to collect actual operation data, and adjusting and optimizing the layout according to the actual operation data;
s8, intelligent decision support: developing an intelligent decision system by combining intelligent data analysis and an optimization algorithm;
s9, intelligent warehouse system integration: the intelligent warehouse layout method based on intelligent data analysis and algorithm optimization is applied to the existing warehouse management system for integration.
2. The intelligent warehouse layout method based on intelligent data analysis and algorithm optimization as claimed in claim 1, wherein: in step S1, the warehouse-related data includes warehouse size, cargo type, demand, and storage location.
3. The intelligent warehouse layout method based on intelligent data analysis and algorithm optimization as claimed in claim 2, wherein: in step S2: classifying cargoes by using a cluster analysis method, and finding out the similarity and the difference between cargoes; using an association rule mining method to find the association relation between cargoes; and establishing a prediction model to predict the demand and storage position of the goods.
4. A smart warehouse layout method based on intelligent data analysis and algorithm optimization as claimed in claim 3, wherein: in step S3, the mathematical model of the warehouse layout contains an objective function and constraints, the objective function comprising a minimum time for goods access; the constraints include cargo flow path constraints, shelf capacity constraints, and cargo classification requirements constraints.
5. The intelligent warehouse layout method based on intelligent data analysis and algorithm optimization as claimed in claim 4, wherein: in step S4, the warehouse layout is optimized using a genetic algorithm, and an optimal solution is found, which specifically includes:
s4-1, coding: representing the goods placement position on the goods shelf by binary codes;
s4-2, initializing population: randomly generating a certain number of individuals as an initial population;
s4-3, evaluation: calculating the fitness value of each individual, evaluating the quality of the goods shelf layout or goods placement scheme represented by the chromosome, and calculating the fitness according to the characteristics of the goods and the limitation conditions of the warehouse;
s4-4, selecting: selecting according to the fitness of the individual, wherein a selection operator adopts roulette selection or tournament selection;
s4-5, crossing: randomly pairing selected individuals, performing cross operation on the paired individuals according to a certain probability to form new individuals, wherein a single-point cross or multi-point cross is adopted by a cross operator;
s4-6, changing the gene value of one or a plurality of genes into the allele value according to a certain mutation probability for each individual in the population, wherein a mutation operator adopts basic position mutation or uniform mutation;
s4-7, loop iteration: repeating the steps S4-3 to S4-6 until the preset iteration times are reached or convergence conditions are met;
s4-8, decoding: and decoding the optimal solution individuals in the final population to obtain an optimal solution or an approximate optimal solution.
6. The intelligent warehouse layout method based on intelligent data analysis and algorithm optimization as claimed in claim 5, wherein: in step S4, the warehouse layout is optimized using a simulated annealing algorithm, an optimal solution is found,
1) Initializing: defining parameters of a warehouse layout problem, including an initial state S, an initial temperature T, a termination temperature tf, a cooling constant c and a Markov chain length L;
2) Searching: at each temperature, an L-round search was performed, for each round of search the following operations were performed:
A. randomly perturbing the current state S to generate a new state S';
B. calculating a fitness value f (S ') of the new state S ', wherein the fitness value f (S ') is the degree of merit of calculating the new layout, and the degree of merit includes space utilization and access efficiency;
C. judging whether to accept the new state S': if f (S ') > f (S), accepting the new state S ' with probability min {1, exp (f (S ') -f (S)/T) }; otherwise, the new state S' is not accepted;
D. and (3) cooling: multiplying the current temperature T by a cooling constant c;
E. judging whether the temperature is lower than the termination temperature tf: if the solution is lower than the preset threshold, ending the algorithm and outputting an optimal solution; otherwise, returning to the step B.
7. The intelligent warehouse layout method based on intelligent data analysis and algorithm optimization as claimed in claim 6, wherein: in step S4, the warehouse layout is optimized using a particle swarm algorithm, finding the optimal solution: the method comprises the following specific steps:
(1) Initializing: setting the number N of particles, the dimension D of a search space, acceleration constants c1 and c2, an inertia weight w, the maximum iteration number MaxIter and a modulus M of modular operation;
(2) Randomly generating N particles, each particle having a position and a velocity in a D-dimensional space, and a minimum and a maximum in each dimension;
(3) Calculating the fitness value of each particle, and updating the individual extremum and the global extremum according to the fitness value;
(4) The following steps are repeated until the maximum number of iterations is reached:
a. updating the speed and the position of each particle according to a speed updating formula, specifically:
i. for each dimension, if the absolute value of the particle velocity is greater than the range of the dimension search space, limiting the velocity to be within the range;
if the modulus of particle velocity is greater than M, limiting its velocity between [ -M, M ];
b. limiting the position of the particles to be within the search space, and reinitializing if the position exceeds the range;
c. updating the individual extremum and the global extremum;
(5) And returning the global optimal solution and the fitness value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310819180.5A CN116934220A (en) | 2023-07-05 | 2023-07-05 | Intelligent warehouse layout method based on intelligent data analysis and algorithm optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310819180.5A CN116934220A (en) | 2023-07-05 | 2023-07-05 | Intelligent warehouse layout method based on intelligent data analysis and algorithm optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116934220A true CN116934220A (en) | 2023-10-24 |
Family
ID=88374845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310819180.5A Pending CN116934220A (en) | 2023-07-05 | 2023-07-05 | Intelligent warehouse layout method based on intelligent data analysis and algorithm optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116934220A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117193926A (en) * | 2023-11-03 | 2023-12-08 | 江苏卓铭电子科技有限公司 | Computer-aided counting instrument human-computer interface generation method and system |
| CN117313978A (en) * | 2023-11-29 | 2023-12-29 | 深圳市海淇展示文化有限公司 | Method and system for assisting in setting of display position based on path planning |
| CN117391593A (en) * | 2023-12-13 | 2024-01-12 | 广东精工智能系统有限公司 | Intelligent warehouse article scheduling management method and system based on Internet of things |
| CN117557199A (en) * | 2024-01-03 | 2024-02-13 | 福州冰宇科技有限公司 | Intelligent warehousing method, system and storage medium based on mathematical model |
| CN117670187A (en) * | 2023-11-10 | 2024-03-08 | 翼瀚齐创科技(杭州)有限公司 | Storage classification associated management system for intelligent logistics |
-
2023
- 2023-07-05 CN CN202310819180.5A patent/CN116934220A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117193926A (en) * | 2023-11-03 | 2023-12-08 | 江苏卓铭电子科技有限公司 | Computer-aided counting instrument human-computer interface generation method and system |
| CN117193926B (en) * | 2023-11-03 | 2024-02-02 | 江苏卓铭电子科技有限公司 | Computer-aided counting instrument human-computer interface generation method and system |
| CN117670187A (en) * | 2023-11-10 | 2024-03-08 | 翼瀚齐创科技(杭州)有限公司 | Storage classification associated management system for intelligent logistics |
| CN117313978A (en) * | 2023-11-29 | 2023-12-29 | 深圳市海淇展示文化有限公司 | Method and system for assisting in setting of display position based on path planning |
| CN117313978B (en) * | 2023-11-29 | 2024-03-01 | 深圳市海淇展示文化有限公司 | Method and system for assisting in setting of display position based on path planning |
| CN117391593A (en) * | 2023-12-13 | 2024-01-12 | 广东精工智能系统有限公司 | Intelligent warehouse article scheduling management method and system based on Internet of things |
| CN117391593B (en) * | 2023-12-13 | 2024-05-03 | 广东精工智能系统有限公司 | Intelligent warehouse article scheduling management method and system based on Internet of things |
| CN117557199A (en) * | 2024-01-03 | 2024-02-13 | 福州冰宇科技有限公司 | Intelligent warehousing method, system and storage medium based on mathematical model |
| CN117557199B (en) * | 2024-01-03 | 2024-03-12 | 福州冰宇科技有限公司 | Intelligent warehousing method, system and storage medium based on mathematical model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116934220A (en) | Intelligent warehouse layout method based on intelligent data analysis and algorithm optimization | |
| Tan et al. | Differential evolution with adaptive mutation strategy based on fitness landscape analysis | |
| Wang et al. | Stochastic economic emission load dispatch through a modified particle swarm optimization algorithm | |
| Zhou et al. | Multiobjective evolutionary algorithms: A survey of the state of the art | |
| CN113704956A (en) | Urban road online microscopic simulation method and system based on digital twin technology | |
| Wu et al. | Operation optimization of natural gas transmission pipelines based on stochastic optimization algorithms: a review | |
| CN114678080B (en) | Converter end point phosphorus content prediction model, construction method and phosphorus content prediction method | |
| KR101173823B1 (en) | System and method for predicting an energy consumption of multi-family housing | |
| CN112351033B (en) | Deep learning intrusion detection method based on double-population genetic algorithm in industrial control network | |
| CN116383912B (en) | Micro motor structure optimization method and system for improving control precision | |
| CN117391641A (en) | Pilatory production flow management method and system | |
| CN114580763A (en) | Power load prediction method based on improved dragonfly and lightweight gradient lifting tree model | |
| Tian et al. | Dynamic operation optimization based on improved dynamic multi-objective dragonfly algorithm in continuous annealing process. | |
| CN112256209B (en) | Parameter configuration optimization method and optimization system of cloud storage system | |
| CN111311001B (en) | Bi-LSTM network short-term load prediction method based on DBSCAN algorithm and feature selection | |
| CN109919688B (en) | Electronic cigarette product line planning method considering market factors | |
| Mirjalili et al. | Multi-objective grey wolf optimizer | |
| CN116384244A (en) | Electromagnetic field prediction method based on physical enhancement neural network | |
| CN113837428B (en) | Sensor optimization layout and temperature and humidity prediction algorithm for raw smoke maintenance | |
| Mishra et al. | Multi-objective genetic algorithm: A comprehensive survey | |
| CN113987904A (en) | Method, device, equipment and storage medium for measuring and calculating repair cost of power transmission project | |
| Liu et al. | Large-scale evolutionary optimization: A review and comparative study | |
| CN110084376B (en) | Method and device for automatically separating data into boxes | |
| CN111783988B (en) | Multi-target gray prediction evolution method and system for solving environmental economic scheduling problem | |
| Navajas-Guerrero et al. | A novel heuristic approach for the simultaneous selection of the optimal clustering method and its internal parameters for time series data |
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 |