Intelligent control system and method for Bluetooth sound box production line

Abstract

The invention discloses an intelligent control system and method for a Bluetooth loudspeaker box production line, relates to the technical field of intelligent manufacturing, and is used for solving the problems that the Bluetooth loudspeaker box production line is uneven in process distribution, unstable in rhythm and difficult to dispatch under the condition of lacking people. The method comprises the following steps: firstly, carrying out current situation analysis on a Bluetooth loudspeaker box production line, collecting data such as an assembly process, workstation operation information and personnel distribution, and identifying production bottlenecks by using a man-hour determination method; the process is optimized and recombined, and an improved scheme based on process rhythm coordination and load balancing is designed; furthermore, a mathematical model is constructed, a genetic algorithm is introduced, and optimal process allocation is completed by taking maximization of a production balance rate and minimization of a load index as targets. And finally, station replacement and operation dynamic adjustment under the emergency situation are achieved. The method can effectively improve the flexibility and beat stability of the production line, and is suitable for the multi-process collaborative optimization requirement in an intelligent manufacturing scene.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology, and more specifically, to an intelligent control system and method for a Bluetooth speaker production line. Background Art

[0002] As the manufacturing industry moves towards flexibility and intelligence, more and more production lines are adopting a multi-variety, small-batch production model to meet customer demand for customized products. Under this model, production rhythms change frequently, and process paths are flexible and varied, placing higher demands on the skill structure and job matching of operators. However, most manufacturing enterprises currently still use static scheduling or experience-based manual allocation methods for manpower scheduling, lacking a comprehensive evaluation mechanism for personnel skills, process complexity, and job priority. This makes it difficult to quickly respond to personnel changes and process switches, leading to low production efficiency, frequent bottlenecks, and even production interruptions.

[0003] In addition, existing human resource scheduling systems are mostly driven by fixed templates and lack in-depth integration and analysis of actual production line cycle time, task load and personnel resume data. It is difficult to dynamically adjust the matching relationship between people and positions. Especially when there is a shortage of operators in key processes, inefficient means such as overtime or temporary replacement are often used to solve the problem, which affects the stability of production plans and the ability to deliver on time.

[0004] To address the above problems, this invention proposes a solution. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an intelligent control system and method for a Bluetooth speaker production line to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: In a preferred embodiment, it includes: Step 1: Draw a process sequence diagram of the Bluetooth speaker production line and determine the production data of the Bluetooth speaker production line before the improvement; Step 2: Optimize and balance the production data of the Bluetooth speaker production line, and conduct correlation analysis and compensation optimization of workstations, workers and production operations; Step 3: Establish assessment standards for the optimized Bluetooth speaker production line and implement cyclical management.

[0007] In a preferred embodiment, in step 1, the production characteristics, production problems and current status of the assembly process of the current Bluetooth speaker production line are identified, the production data of the Bluetooth speaker production line before improvement is obtained, and anomalies are detected.

[0008] In a preferred embodiment, in step 2, the Bluetooth speaker production line is optimized based on industrial engineering methods, and the specific steps are as follows: Determine the design principles of the optimization scheme, optimize the process and procedures of the Bluetooth speaker production line, and improve the production data of the Bluetooth speaker production line.

[0009] In a preferred embodiment, in step 2, the Bluetooth speaker production line is optimized based on a genetic algorithm, and the specific steps are as follows: Step B1: Mathematical model expression of the Bluetooth speaker production line; Define variable parameters, constraints, and construct the optimization objective function; Step B2: Bluetooth speaker production line algorithm design; Generate an initial feasible solution that conforms to the priority relationship, which is used as the encoding gene sequence. Arrange the processes in a row according to the work priority order of the production line, and stipulate that the number of each process is equal to a gene. Then encode each work unit according to the order number of the processes. Translate each number of chromosome genes into the form of the production line equilibrium problem solution according to the genetic coding method, and construct a fitness function. Change the internal structure of the population according to the fitness value.

[0010] In a preferred embodiment, in step 2, the online status, workstation distribution, and on-duty time of the workers during the production process are obtained; the number of processes completed by each worker per unit time is counted, and the process completion rate, work time ratio, and work achievement rate of the workers during the production process are calculated. Calculate the substitutability score between workstations; calculate the interaction intensity index between workstations; calculate the interaction coefficient between worker workstations by weighted summing of the substitutability score and the interaction intensity index between workstations. By treating the staff status index data as graph nodes and the interaction coefficient as the edge weight, the effective connection ratio between the currently active nodes in the graph is calculated to determine the real-time workstation coupling degree of the current Bluetooth speaker production line. Calculate the standard deviation of the beat and the frequency of abrupt changes to determine the local beat disturbance index of the current Bluetooth speaker production line. Combine the workstation coupling degree and the local beat disturbance index to compensate and correct the current fitness value.

[0011] In a preferred embodiment, in step 2, the genetic algorithm model is applied to the Bluetooth speaker production line optimized by industrial engineering methods. The multiple feasible solutions output by the genetic algorithm are classified to determine the standard production data for the Bluetooth speaker production line. An optimization function is then constructed based on the compensated fitness value to further optimize the production data for the Bluetooth speaker production line.

[0012] In a preferred embodiment, in step 3, a standard operating procedure (SOP) is established, and the Bluetooth speaker production line is continuously improved using the PDCA cycle management.

[0013] In a preferred embodiment, it includes: a job criticality assessment module, a personnel competency feature extraction and matching module, a dynamic personnel and job scheduling optimization module, and a data storage module, with signal connections between the modules; The job criticality assessment module is mainly used to identify critical workstations by analyzing the task process path, the position of the workstation in the Bluetooth speaker production line and its impact on the overall cycle time, and to assess the sensitivity of each workstation to production efficiency. The personnel capability feature extraction and matching module is mainly used to extract capability features based on factors such as staff resume data, skill level, and task completion quality, and to perform multi-factor matching with work position requirements to build a work position-staff adaptation model. The dynamic personnel and job scheduling optimization module is mainly used to combine the criticality of the job with the suitability of the personnel, and take into account the current status of the Bluetooth speaker production line, to dynamically optimize the scheduling plan, realize the priority matching of key work positions, ensure rapid response when personnel change or task switching, and ensure production stability and efficiency. The data storage module is mainly used to store all data during the processing.

[0014] The technical effects and advantages of the intelligent control system and method for a Bluetooth speaker production line of the present invention are as follows: This invention achieves intelligent optimization of production scheduling under conditions of multi-variety, small-batch production and fluctuating human resources by introducing process cycle time data analysis, personnel capability coefficient quantification, and process characteristic matching models. Compared with traditional experience-based allocation methods, this method can dynamically adjust the matching relationship between processes and personnel, effectively improving process execution efficiency and personnel utilization. The system can maintain high cycle time stability even in situations of staff shortages or temporary staff replacements, significantly reducing process bottlenecks and stagnation. In addition, the model can quickly adapt to different process flows, possessing strong versatility and scalability, improving the overall flexibility and intelligence level of the production line. Attached Figure Description

[0015] Figure 1 This is an operation flowchart of an intelligent control method for a Bluetooth speaker production line according to the present invention.

[0016] Figure 2 This is a schematic diagram of the intelligent control system for a Bluetooth speaker production line according to the present invention.

[0017] Figure 3 This is a diagram analyzing the current status of a Bluetooth speaker production line. Detailed Implementation

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] This invention is achieved through the collection.

[0020] In this embodiment, the present invention discloses an intelligent control method for a Bluetooth speaker production line, such as... Figure 1 As shown, it includes: Step 1: Current Status Analysis of Bluetooth Speaker Production Line; First, clarify the current production characteristics, production problems, and assembly process status of the Bluetooth speaker production line; including the overall assembly process of the Bluetooth speaker production line, core links such as motherboard assembly, battery welding, shell fixing, functional testing, and packaging. Furthermore, use flowchart modeling tools such as Visio, AutoCAD, or BPMN to draw the production flow chart and process sequence diagram of the current Bluetooth speaker production line, such as... Figure 3 As shown, the Work Analysis Method (MTM) is applied to record the motion units involved in each process, and the workstation, operation content, equipment used, and number of personnel for each process are marked. Next, the working hours of the Bluetooth speaker production line were determined using a measurement method. Specifically, the current number of observations was selected based on experience, and then the error limit method was used to determine the number of observations for the operation measurement, based on the following formula: Where N represents the actual ideal number of observations, Xi represents the stopwatch reading, and n represents the current number of observations; Outliers were removed from the observation time data of the Bluetooth speaker production line obtained after operational observation using the three-standard-deviation method, specifically based on the following formula: Where n represents the number of observations, Xi represents the value of each observation, and X- represents the average value of the observations; After calculating the average X- after n observations, the standard deviation of the observed values ​​is then calculated using the following formula: Furthermore, based on the calculated standard deviation of the observed values, the control limits of the measured values ​​are normally distributed to obtain the observation threshold Yg. When the observed value is less than the observation threshold Yg, it indicates that the observed value is a normal value and can be used normally; when the observed value is greater than or equal to the observation threshold Yg, it indicates that the observed value is an outlier and cannot be used normally, and needs to be removed.

[0021] Based on the collected observation data, the standard operating time, time utilization rate, production line balance rate, and smoothing index of each workstation were calculated, which are the production data of the Bluetooth speaker production line before the improvement.

[0022] Step 2: Balance optimization analysis of the Bluetooth speaker production line; The optimization analysis of the Bluetooth speaker production line based on industrial engineering methods is as follows: Step A1: Based on the production characteristics, production problems, and current status of the assembly process of the Bluetooth speaker production line obtained in Step 1, determine the design principles of the optimization scheme; Specifically, we first analyze the product structure and production cycle characteristics of Bluetooth speakers, identify the bottleneck processes on the Bluetooth speaker production line, and clarify the process optimization goals: reduce ineffective operations, reduce handling distance, reduce temporary storage time, and improve overall cycle coordination. Furthermore, based on the process optimization objectives, the design principles for the optimization scheme are determined: "coordinated cycle time, reasonable path, and balanced workstations" are the core design standards, and an evaluation index system is established for subsequent optimization.

[0023] Step A2: Optimize the process and workflow of the Bluetooth speaker production line to improve the production data of the Bluetooth speaker production line, denoted as D (modified), including: current process - workstation allocation, load, resource usage, etc.; First, based on the "5W1H" method in industrial engineering, we continuously ask questions about the work processes, methods, personnel and equipment, work locations, work time arrangements, and work objectives of the Bluetooth speaker production line to find the optimal work method. At the same time, we conduct node analysis on the handling and temporary storage behaviors between processes to construct a "material flow diagram" to quantitatively assess the proportion of non-value-added activities and identify problems such as inappropriate arrangement of work processes and excessive temporary storage time.

[0024] Furthermore, the Bluetooth speaker production line was streamlined and reorganized using the four optimization principles of "ECRS", and improvement suggestions that should be followed for the optimization of the Bluetooth speaker production line process were summarized. It should be noted that due to various practical limitations, there is no absolute production balance; we can only strive for relative balance. Therefore, we need to further optimize the improvement suggestions based on the actual situation of the Bluetooth speaker production line to arrive at the final process improvement recommendations.

[0025] Step A3: Optimize the Bluetooth speaker production line using a genetic algorithm. The specific steps are as follows: Step B1: Mathematical model expression of the Bluetooth speaker production line; Define variable parameters: The number of workstations is m, the workstation number is k (k=1,2,3...m); the production cycle time is CT; the number of operation steps is n; the set of all operation steps on the k-th workstation is represented by Sk; i and j are the sequence numbers of each operation step (ij=1,2,3...n); the operation time of the i-th operation step is Ti; the total operation time on the k-th workstation is T(Sk); the operation priority relationship matrix is ​​r[i][j], (where i=1,2,3...n; j=1,2,3...n); Define constraints: The division of each process on the production line into workstations must satisfy the priority relationships between the processes. Each process can only be assigned to one workstation, and its production time cannot exceed the total operating time of the workstation to which it is assigned. When there are n processes on the production line, the process association matrix is ​​represented as an n*n matrix, and the process priority constraint is expressed as: r[i][j] = (1 indicates that process i is the immediate predecessor of process j; 0 indicates that process i is not the immediate predecessor of process j). Optimization goal: Given the production cycle time CT and the number of workstations m, the various processes on each workstation are rationally allocated and adjusted to achieve the maximum production balance rate and the minimum production load SI. The optimization objective function is as follows: Objective function 1: ; Requirements: Given the number of workstations m, maximize the production line balance rate while meeting the production cycle time requirements.

[0026] Objective function 2: ; Requirements: Given the number of workstations m, minimize the production line workload index SI as much as possible while satisfying the production cycle time.

[0027] Since we have two objective functions, and we need to ensure that the production line balance rate Maxη and the production line conforms to the balance index MinSI, we use the adaptive weighting method to transform the multi-objective optimization problem into a single-objective optimization problem, constructing a new function F as shown in the equation: ; Where α represents the weight value of Fmaxn and β represents the weight value of Fminsl.

[0028] Step B2: Bluetooth speaker production line algorithm design; First, topological sorting is used to generate an initial feasible solution that conforms to the priority relationship, which serves as the encoding gene sequence. Then, the processes are arranged in a row according to the work priority order of the production line, and each process number is assigned a gene. Finally, each work unit is encoded according to the sequence number of the processes.

[0029] The genetic coding scheme is used to translate the individual chromosome gene numbers into solutions to the production line balancing problem. The decoding process is as follows: Step Y1: Generate the initial production cycle CT'=T / m.

[0030] Where CT' represents the production cycle time, T represents the total working time, and m represents the number of workstations.

[0031] Step Y2: Based on the production cycle time CT', allocate tasks to m workstations according to their priority. The operation time of the k-th workstation is denoted by T(Sk) (k=1,2,3...m). If T(Sk)≤CT', then MinCT=CT', and the search operation stops; otherwise, proceed to step Y3.

[0032] Step Y3: Randomly assign workstations on the production line. Let ΔSk ​​represent the time of the first work unit of the (k+1)th workstation. Then CT' = Min(TS(Sk) + ΔSk).

[0033] Step Y4: Set CT = MaxT(Sk). If CT > CT', then CT' is the new production line cycle time, and the value is returned to step Y2 to complete the reallocation; otherwise, the search stops. CT is the production cycle time under the current sorting.

[0034] Furthermore, to achieve the optimization objective, function F is used as the fitness function to change the internal structure of the population and to determine the quality of individuals in the population. In this way, the population will continuously adjust towards the optimization objective. Specifically, objective function 1 is used as the fitness function established when the production line cycle time is minimized, where Fmaxn represents the fitness value when the production line cycle time is minimized; objective function 2 is used as the fitness function established when the production line load is most balanced, where Fminsl represents the fitness value when the production line load reaches the most balanced state.

[0035] It should be noted that when unforeseen operational disruptions occur on the production line, such as sudden equipment failures or absences of key personnel, the original optimization results based on the genetic algorithm become invalid due to the discrepancy between the actual situation and the input model. This leads to significant fluctuations in production cycle time, a sharp drop in the balance rate, and consequently, the current optimal process allocation scheme becomes inapplicable. Therefore, in this embodiment, the status index data of the workers during the production process are first obtained, as follows: During the production process, the system locates workers' current workstations by equipping them with RFID badges, UWB positioning tags, and smart workwear wristbands. It determines whether workers are on duty and engaged in work by recognizing their movements and the duration of their stillness, and obtains data on workers' online status, workstation distribution, and on-duty time. By integrating MES with a barcode scanning process reporting device and PLC cycle signals, the system counts the number of processes completed by each worker per unit of time, and calculates the workers' process completion rate, work time percentage, and work achievement rate during the production process. Furthermore, the standard operating procedures and workstation instructions are analyzed to construct a three-dimensional matrix of workstation-process-skill. The executable processes and required skills for each workstation are extracted, the skill overlap between workstations is identified, and the substitutability score between workstations is calculated. Next, by integrating MES (Manufacturing Execution System), the collaborative work records of workers at different workstations in past actual production processes are analyzed, such as job transfer records and events of assisting in completing processes. The frequency and success rate of mutual assistance between workstations under abnormal conditions are statistically analyzed, and the interaction intensity index between workstations is calculated. Finally, the substitutability score between workstations and the interaction intensity index between workstations are weighted and summed to calculate the interaction coefficient between worker workstations.

[0036] Based on the obtained staff status index data and the interaction coefficients between staff workstations, a graph structure modeling method is adopted. The staff status index data is regarded as graph nodes, and the interaction coefficients are edge weights. A dynamic graph is constructed in combination with the current staff status. According to graph traversal and network connectivity analysis, the effective connection ratio between currently active nodes in the graph is calculated. Furthermore, the real-time workstation coupling degree of the current Bluetooth speaker production line is calculated, which indicates whether other workstations can fill the gap in time after a workstation fails under the current staff status, and the strength of the filling ability.

[0037] Furthermore, by integrating MES to monitor the status of each process in real time, including: in progress, abnormal, delayed, completed, etc., it records whether there are any abnormalities such as waiting, backlog, or stoppage in each process. Based on the recorded process status data, the sliding window method is used to statistically analyze the process cycle time changes over the past N1 cycles, calculate the cycle time standard deviation and mutation frequency, identify workstations with unstable cycle time, and analyze the trend of change. Then, the exponential weighted average time series prediction model is used to predict whether the process cycle time will change in the short term, and determine the local cycle time disturbance index of the current Bluetooth speaker production line. The higher the local cycle time disturbance index, the greater the risk of the current Bluetooth speaker production line.

[0038] Based on the fitness function in the original genetic algorithm, and incorporating the workstation coupling degree and local cycle time perturbation index, the current fitness value is compensated and corrected as follows: Define the compensation factor: The lower the workstation coupling, the higher the risk, and the lower the suitability. A higher local beat disturbance index leads to production instability and a decrease in adaptability. A multi-factor weighted compensation model is constructed based on the basic fitness degree F, the workstation coupling degree K, and the local cycle disturbance index D. The compensation formula is: Fnew=D×(1-Aa(1-K))×(1-Bb×D), where Aa and Bb represent empirical weight factors, which are set according to the difficulty of historical anomaly recovery.

[0039] Step B3: Apply a genetic algorithm to solve the balancing problem of the Bluetooth speaker production line; The genetic algorithm model was applied to a Bluetooth speaker production line optimized by industrial engineering methods. Using the roulette wheel selection principle in genetic algorithms, individuals were placed one-to-one into a continuous interval. The probability of an individual being selected was calculated as follows: Where Fmaxn(p) represents the fitness of an individual, Fminsl(p) represents the fitness of any individual, and pop-size represents the total number of individuals in the population.

[0040] Furthermore, a two-point crossover method is used for the crossover operation. Two chromosomes are randomly selected from the population as parents, and two unequal random numbers C1 and C2 are randomly generated in the interval [1, n-1] as crossover points. After the individuals are divided into three parts, the gene order of the chromosomes in the head and tail of the parents remains unchanged. The duplicate genes in the head and tail of parents 1 and parents 2 are deleted, while the order of the remaining genes remains unchanged. These genes are then inserted into parents 2, thus forming a completely new chromosome offspring. The offspring chromosomes after the crossover operation inherit the gene relationships of the parents' chromosomes and still conform to the priority order of production and processing.

[0041] Furthermore, through population evolution, multiple feasible solution sets with different numbers of workstations and different allocation strategies are generated, yielding balance rates, load indices, and process distribution schemes under multiple allocation methods. Cluster analysis is then performed on the operating results under various workstations, classifying the multiple feasible solutions output by the genetic algorithm to determine the standard production data for the Bluetooth speaker production line, as detailed below: First, we collected the core characteristic indicators of various workstation solutions, including: process allocation method, balance rate, maximum load, load balance index, and number of workstations, and established an indicator matrix.

[0042] Next, Z-score or min-max normalization is used to make the dimensions of each indicator consistent, unify the measurement standard, and prevent certain indicators from dominating the clustering results; Using K-means, which is suitable for cases with a preset number of clusters, or DBSCAN, which is suitable for cases without a preset number of clusters, different process allocation schemes are divided into several classes according to similarity. The representative solution with high balance rate and uniform load in each class is selected as the standard production data for the Bluetooth speaker production line of that class, denoted as Do.

[0043] Next, the fitness value at which the compensated new production load reaches its optimal equilibrium is input into the genetic algorithm, and the genetic algorithm is run again to obtain the optimal fitness solution, which corresponds to the optimal fitness value representing the most balanced state index of the Bluetooth speaker production line under the new load: Furthermore, an optimization function is constructed based on standard production data and optimal fitness values ​​from the Bluetooth speaker production line: The first term represents the degree of difference from the standard production data, the second term represents the difference between the current standard production data and the optimal fitness under the current load, and λ1 and λ2 represent the weighting coefficients. Finally, the output shows the production data of the Bluetooth speaker production line, which further optimizes coordination and resource utilization.

[0044] Step 3: Post-production management of the Bluetooth speaker production line; Establish SOPs (Standard Operating Procedures), specifically: From the optimized Bluetooth speaker production data, process sequences and corresponding key control points are extracted, and each process is written as a Standard Operating Procedure (SOP) template. All SOPs are imported into the MES system or deployed on workstations in tablet / PDA form. Regular training and assessments are conducted, with assessment content including: SOP accuracy rate; Operation time target rate; Quality spot check pass rate.

[0045] Furthermore, implement PDCA cycle management, and formulate improvement plans based on production data (capacity, yield, and time), such as: increasing the yield of the welding process to 98%; reducing the average time of the sound cavity assembly process by 10 seconds; at the same time, implement Do: SOP adjustments and put them into trial, such as: adjusting SOPs, optimizing process paths or tooling within a small batch range; finally, compare the actual yield with the target through MES or periodic spot checks to determine whether the optimization measures are effective and establish a data analysis report.

[0046] If the trial results are good, the improvements will be written into the SOP and implemented across the entire Bluetooth speaker production line; if it fails, the failure plan and reasons will be recorded, a new improvement plan will be formulated, and the next round of PDCA cycle management will begin, so that the production line has a continuous improvement mechanism to adapt to actual scenarios such as order changes, process optimization, and quality backtracking.

[0047] This invention also proposes an intelligent control system for a Bluetooth speaker production line, such as... Figure 2 As shown, it includes: a job key assessment module, a personnel competency feature extraction and matching module, a dynamic personnel and job scheduling optimization module, and a data storage module, with signal connections between each module; The job criticality assessment module is mainly used to identify critical workstations by analyzing the task process path, the position of the workstation in the Bluetooth speaker production line and its impact on the overall cycle time, and to assess the sensitivity of each workstation to production efficiency. The personnel capability feature extraction and matching module is mainly used to extract capability features based on factors such as staff resume data, skill level, and task completion quality, and to perform multi-factor matching with work position requirements to build a work position-staff adaptation model. The dynamic personnel and job scheduling optimization module is mainly used to combine the criticality of the job with the suitability of the personnel, and take into account the current status of the Bluetooth speaker production line, to dynamically optimize the scheduling plan, realize the priority matching of key work positions, ensure rapid response when personnel change or task switching, and ensure production stability and efficiency. The data storage module is mainly used to store all data during the processing.

[0048] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0049] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0050] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and inventive constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0051] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0052] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0053] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for intelligent control of a Bluetooth speaker production line. Its characteristics include: Step 1: Draw a process sequence diagram for the Bluetooth speaker production line and determine the production data of the Bluetooth speaker production line before the improvement; Step 2: Optimize and balance the production data of the Bluetooth speaker production line, and conduct correlation analysis and compensation optimization of workstations, workers and production operations; Step 3: Establish assessment standards for the optimized Bluetooth speaker production line and implement cyclical management.

2. The intelligent control method for a Bluetooth speaker production line according to claim 1, characterized in that: In step 1, the production characteristics, production problems and current status of the assembly process of the Bluetooth speaker production line are identified, the production data of the Bluetooth speaker production line before improvement is obtained, and anomalies are detected.

3. The intelligent control method for a Bluetooth speaker production line according to claim 2, characterized in that: In step 2, the Bluetooth speaker production line is optimized based on industrial engineering methods. The specific steps are as follows: Determine the design principles of the optimization scheme, optimize the process and procedures of the Bluetooth speaker production line, and improve the production data of the Bluetooth speaker production line.

4. The intelligent control method for a Bluetooth speaker production line according to claim 3, characterized in that; In step 2, the Bluetooth speaker production line is optimized based on a genetic algorithm. The specific steps are as follows: Step B1: Mathematical model expression of the Bluetooth speaker production line; Define variable parameters, constraints, and construct the optimization objective function; Step B2: Bluetooth speaker production line algorithm design; Generate an initial feasible solution that conforms to the priority relationship, which is used as the encoding gene sequence. Arrange the processes in a row according to the work priority order of the production line, and stipulate that the number of each process is equal to a gene. Then encode each work unit according to the order number of the processes. Translate each number of chromosome genes into the form of the production line equilibrium problem solution according to the genetic coding method, and construct a fitness function. Change the internal structure of the population according to the fitness value.

5. The intelligent control method for a Bluetooth speaker production line according to claim 4, characterized in that: In step 2, the online status, workstation distribution, and on-duty time of the workers during the production process are obtained; the number of processes completed by each worker per unit time is counted, and the process completion rate, work time ratio, and work achievement rate of the workers during the production process are calculated. Calculate the substitutability score and the interaction intensity index between workstations; calculate the interaction coefficient between worker workstations by weighted summation of the substitutability score and the interaction intensity index between workstations. By treating the staff status index data as graph nodes and the interaction coefficient as the edge weight, the effective connection ratio between the currently active nodes in the graph is calculated to determine the real-time workstation coupling degree of the current Bluetooth speaker production line. Calculate the standard deviation of the beat and the frequency of abrupt changes to determine the local beat disturbance index of the current Bluetooth speaker production line. Combine the workstation coupling degree and the local beat disturbance index to compensate and correct the current fitness value.

6. The intelligent control method for a Bluetooth speaker production line according to claim 5, characterized in that: In step 2, the genetic algorithm model is applied to the Bluetooth speaker production line optimized by industrial engineering methods; The multiple feasible solutions output by the genetic algorithm are classified to determine the standard production data for the Bluetooth speaker production line. An optimization function is then constructed based on the compensated fitness value to further optimize the production data for the Bluetooth speaker production line.

7. The intelligent control method for a Bluetooth speaker production line according to claim 6, characterized in that: In step 3, a standard operating procedure (SOP) is established, and the Bluetooth speaker production line is continuously improved using the PDCA cycle management.

8. An intelligent control system for a Bluetooth speaker production line, characterized in that, include: The module includes a job key assessment module, a personnel competency feature extraction and matching module, a dynamic personnel and job scheduling optimization module, and a data storage module, as well as signal connections between these modules. The job criticality assessment module is mainly used to identify critical workstations by analyzing the task process path, the position of the workstation in the Bluetooth speaker production line and its impact on the overall cycle time, and to assess the sensitivity of each workstation to production efficiency. The personnel capability feature extraction and matching module is mainly used to extract capability features based on factors such as staff resume data, skill level, and task completion quality, and to perform multi-factor matching with work position requirements to build a work position-staff adaptation model. The dynamic personnel and job scheduling optimization module is mainly used to combine the criticality of the job with the suitability of the personnel, and take into account the current status of the Bluetooth speaker production line, to dynamically optimize the scheduling plan, realize the priority matching of key work positions, ensure rapid response when personnel change or task switching, and ensure production stability and efficiency. The data storage module is mainly used to store all data during the processing.

Images