Multi-production-line production plan scheduling system and method based on task goals
By adopting a production plan and schedule system based on task goals in a multi-production production environment, using technologies such as data acquisition, artificial intelligence and machine learning to optimize resource allocation and adjust schedules in real time, the existing system cannot respond in real time and The problem of uneven resource allocation improves production efficiency and planning accuracy.
Patent Information
- Application Number
- CN202411002825.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-08
AI Technical Summary
The existing multi-production line production planning schedule system cannot respond to production changes in real time when dealing with large-scale and dynamically changing production environments, resulting in uneven resource allocation and low production efficiency, and lack of in-depth analysis and prediction capabilities of production data, making it difficult to Identify potential production bottlenecks and optimization opportunities ahead of time.
Using a multi-production line production planning scheduling system based on task goals, the data acquisition module collects production data in real time, the data processing module uses artificial intelligence and machine learning models to predict production demand and resource usage patterns, and the advanced scheduling module determines task priority and Optimize resource allocation, adjust the optimization module dynamically adjusts the scheduling plan, and feedback to improve the module continuously optimizes the system performance.
It realizes real-time response to production changes, optimizes resource utilization, improves the accuracy and efficiency of production plans, and ensures efficient completion of production tasks.
Smart Images

Figure CN118917608A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of production planning and scheduling, and in particular to a multi-production line production planning and scheduling system based on task objectives and a method thereof. Background Art
[0002] Production scheduling refers to the development of detailed production plans and schedules based on factors such as product demand, resource availability, and production capacity during the production process to ensure that production activities proceed in an orderly manner. In a multi-line production environment, production scheduling becomes more complicated due to the involvement of multiple production lines and multiple production resources.
[0003] Existing multi-line production planning and scheduling systems usually rely on traditional scheduling algorithms and manual decision-making. These systems have some shortcomings when dealing with large-scale, dynamically changing production environments. For example, they may not be able to respond to production changes in real time, resulting in uneven resource allocation and low production efficiency. In addition, existing systems often lack the ability to deeply analyze and predict production data, making it difficult to identify potential production bottlenecks and optimization opportunities in advance.
[0004] In view of these shortcomings of the prior art, the present invention proposes a multi-production line production planning and scheduling system and method based on task objectives. Summary of the invention
[0005] The purpose of the present invention is to provide a multi-production line production planning scheduling system and method based on task objectives to solve the problems raised in the above background technology.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] A multi-line production planning and scheduling system based on task objectives, including
[0008] Data acquisition module, used to collect production data in real time through sensors and equipment deployed on the production line;
[0009] A data processing module, used to pre-process and perform real-time analysis on the data collected by the data acquisition module, and to predict production demand and resource usage patterns using artificial intelligence and machine learning models;
[0010] An advanced scheduling module is used to determine the task priority and optimize resource allocation and generate a preliminary scheduling plan based on the analysis results and task objectives of the data processing module;
[0011] A plan generation module, used to generate a detailed scheduling plan based on the preliminary scheduling plan generated by the advanced scheduling module, and publish it to the production management system;
[0012] An adjustment and optimization module, used to continuously monitor the operating status of the production line and dynamically adjust the scheduling plan generated by the advanced scheduling module according to the real-time data and prediction results of the data processing module;
[0013] The feedback improvement module is used to collect user feedback and continuously optimize the scheduling system based on the adjustment results and real-time data of the adjustment optimization module.
[0014] Furthermore, the data acquisition module includes various types of sensors for collecting real-time data on equipment status, production speed, and material consumption. The sensors include but are not limited to temperature sensors, pressure sensors, and speed sensors.
[0015] Furthermore, the data processing module includes a data cleaning unit, a formatting unit and a real-time analysis unit, which are used to ensure the data quality and the accuracy of the real-time analysis.
[0016] Furthermore, the advanced scheduling module includes a task priority sorting unit and a resource allocation optimization unit, which are used to generate a preliminary scheduling plan according to task objectives and real-time analysis results.
[0017] Furthermore, the plan generation module includes a schedule plan generation unit and a publishing unit, which are used to notify relevant personnel and equipment of the generated schedule plan.
[0018] Furthermore, the adjustment and optimization module includes a real-time monitoring unit and a dynamic adjustment unit, which are used to adjust the scheduling plan according to the real-time monitoring results and the prediction results.
[0019] Furthermore, the feedback improvement module includes a user feedback collection unit and a continuous improvement unit, which are used to optimize system performance according to user feedback and real-time data.
[0020] A method for a multi-production line production planning and scheduling system based on task objectives includes the following steps
[0021] Step S1, data acquisition, sensors deployed on the production line read physical quantities in real time, including temperature, pressure and speed, and convert these physical quantities into electrical signals. The sensors transmit the electrical signals to the data acquisition module via wired or wireless means;
[0022] Step S2, signal conversion, the data acquisition module receives the electrical signal from the sensor, and the data acquisition module converts the electrical signal into a digital signal;
[0023] Step S3, data storage, the digital signal is temporarily stored in the system's cache, waiting for further processing, and the digital signal is stored in the system's memory to form an original data record;
[0024] Step S4, data analysis, the processor cleans the stored raw data, removes noise and erroneous data, and processes the cleaned data to extract useful information, including production speed and equipment status, and then uses artificial intelligence and machine learning models to analyze the processed data to predict production demand and resource usage patterns;
[0025] Step S5, scheduling decision, the processor determines the priority of the task according to the analysis results and task objectives, and calculates the optimal resource allocation plan to ensure efficient use of resources, and then generates a detailed scheduling plan, including the start time, end time and required resources of each task;
[0026] Step S6, plan release, the processor generates a control signal to instruct the device controller to perform the corresponding operation, the control signal is transmitted to the device controller via wired or wireless means, the device controller receives the control signal and controls the device to perform the task according to the schedule plan;
[0027] Step S7, real-time adjustment, the sensor continuously monitors the running status of the equipment and transmits the status information to the data acquisition module. The processor dynamically adjusts the schedule according to the real-time status information and analysis results, and generates a new control signal. The new control signal is transmitted to the equipment controller via wired or wireless means to update the execution plan of the equipment;
[0028] Step S8, feedback and continuous improvement, the system collects equipment operation data and user feedback information, and stores them in the memory. The processor optimizes the scheduling algorithm and system parameters based on the collected data and feedback information.
[0029] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method of the multi-production line production planning and scheduling system based on task objectives.
[0030] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the method of the multi-production line production planning and scheduling system based on task objectives.
[0031] Compared with the prior art, the present invention has the following beneficial effects:
[0032] By integrating advanced data acquisition, processing and analysis modules, as well as advanced scheduling and planning modules, the present invention can collect and analyze production data in real time, predict production demand and resource usage patterns, and dynamically adjust scheduling plans according to task objectives. In this way, the system can effectively solve the problems of insufficient real-time response capability, uneven resource allocation and low production efficiency in the prior art, improve the accuracy and efficiency of production plans, optimize resource utilization, and ensure the efficient completion of production tasks. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 A method flow chart of a multi-production line production planning and scheduling system based on task objectives according to the present invention;
[0034] Figure 2 This is a schematic diagram of module connections of a multi-production line production planning and scheduling system based on task objectives of the present invention;
[0035] Figure 3 This is a schematic diagram of the connection of data acquisition modules of a multi-production line production planning and scheduling system based on task objectives of the present invention;
[0036] Figure 4 This is a schematic diagram of the connection of data processing modules of a multi-production line production planning and scheduling system based on task objectives of the present invention;
[0037] Figure 5 It is a schematic diagram of the connection of the advanced scheduling module of a multi-production line production planning and scheduling system based on task objectives of the present invention;
[0038] Figure 6 It is a schematic diagram of the connection of a plan generation module of a multi-production line production plan scheduling system based on task objectives of the present invention;
[0039] Figure 7 It is a connection diagram of an adjustment and optimization module of a multi-production line production planning and scheduling system based on task objectives of the present invention;
[0040] Figure 8 It is a connection diagram of a feedback improvement module of a multi-production line production planning and scheduling system based on task objectives of the present invention. DETAILED DESCRIPTION
[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.
[0042] Embodiment 1
[0043] like Figure 2-8 As shown, the present invention provides a technical solution:
[0044] A multi-line production planning and scheduling system based on task objectives, including
[0045] Data acquisition module, used to collect production data in real time through sensors and equipment deployed on the production line;
[0046] Preferably, the data acquisition module includes various types of sensors for collecting real-time data on equipment status, production speed, and material consumption, and the sensors include but are not limited to temperature sensors, pressure sensors, and speed sensors.
[0047] A data processing module, used to pre-process and perform real-time analysis on the data collected by the data acquisition module, and to predict production demand and resource usage patterns using artificial intelligence and machine learning models;
[0048] Preferably, the data processing module includes a data cleaning unit, a formatting unit and a real-time analysis unit, which are used to ensure data quality and accuracy of real-time analysis.
[0049] An advanced scheduling module is used to determine the task priority and optimize resource allocation and generate a preliminary scheduling plan based on the analysis results and task objectives of the data processing module;
[0050] Preferably, the advanced scheduling module includes a task priority sorting unit and a resource allocation optimization unit, which are used to generate a preliminary scheduling plan according to task objectives and real-time analysis results.
[0051] A plan generation module, used to generate a detailed scheduling plan based on the preliminary scheduling plan generated by the advanced scheduling module, and publish it to the production management system;
[0052] Preferably, the plan generation module includes a schedule generation unit and a release unit, which are used to notify relevant personnel and equipment of the generated schedule.
[0053] An adjustment and optimization module, used to continuously monitor the operating status of the production line and dynamically adjust the scheduling plan generated by the advanced scheduling module according to the real-time data and prediction results of the data processing module;
[0054] Preferably, the adjustment and optimization module includes a real-time monitoring unit and a dynamic adjustment unit, which are used to adjust the scheduling plan according to the real-time monitoring results and the prediction results.
[0055] A feedback improvement module, used to collect user feedback and continuously optimize the scheduling system based on the adjustment results and real-time data of the adjustment optimization module;
[0056] Preferably, the feedback improvement module includes a user feedback collection unit and a continuous improvement unit, which are used to optimize system performance according to user feedback and real-time data.
[0057] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method of the multi-production line production planning and scheduling system based on task objectives.
[0058] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the method of the multi-production line production planning and scheduling system based on task objectives.
[0059] like Figure 1 As shown, a method for a multi-line production planning and scheduling system based on task objectives includes the following steps
[0060] Step S1, data acquisition, sensors deployed on the production line read physical quantities in real time, including temperature, pressure and speed, and convert these physical quantities into electrical signals. The sensors transmit the electrical signals to the data acquisition module via wired or wireless means;
[0061] Step S2, signal conversion, the data acquisition module receives the electrical signal from the sensor, and the data acquisition module converts the electrical signal into a digital signal;
[0062] Step S3, data storage, the digital signal is temporarily stored in the system's cache, waiting for further processing, and the digital signal is stored in the system's memory to form an original data record;
[0063] Step S4, data analysis, the processor cleans the stored raw data, removes noise and erroneous data, and processes the cleaned data to extract useful information, including production speed and equipment status, and then uses artificial intelligence and machine learning models to analyze the processed data to predict production demand and resource usage patterns;
[0064] Data cleaning uses mean filtering to remove random noise. The expression is as follows:
[0065] y_i=\frac{1}{N}\sum_{j=iN / 2}^{i+N / 2}x_j
[0066] Where y_i is the i-th filtered data point, x_j is the original data point, and N is the window size.
[0067] Data processing moving average is used to smooth data. The expression is as follows:
[0068] \text{MA}_i=\frac{1}{M}\sum_{j=i-M+1}^{i}x_j
[0069] Where \text{MA}_i is the i-th moving average, x_j is the original data point, and M is the window size.
[0070] Linear regression is used to predict production demand, and the expression is as follows:
[0071] y=\beta_0+\beta_1x_1+\beta_2x_2+\cdots+\beta_nx_n+\epsilon
[0072] Where y is the predicted production demand, x_1, x_2, \ldots, x_n are input variables, including but not limited to historical production data and order quantity, \beta_0, \beta_1, \ldots, \beta_n are regression coefficients, and \epsilon is the error term.
[0073] Time series analysis is used to predict resource usage patterns, as expressed below:
[0074] y_t=\mu+\sum_{i=1}^{p}\phi_iy_{ti}+\sum_{j=1}^{q}\theta_j\epsilon_{tj}
[0075] +\epsilon_t
[0076] Among them, y_t is the predicted value at time t, \mu is the mean, \phi_i is the autoregressive coefficient, \theta_j is the moving average coefficient, and \epsilon_t is the error term.
[0077] Step S5, scheduling decision, the processor determines the priority of the task according to the analysis results and task objectives, and calculates the optimal resource allocation plan to ensure efficient use of resources, and then generates a detailed scheduling plan, including the start time, end time and required resources of each task;
[0078] The weighted scoring method is used to determine the priority of tasks, and the expression is as follows:
[0079] P_i=\sum_{j=1}^{m}w_jf_{ij}
[0080] Among them, P_i is the priority score of the i-th task, w_j is the weight of the j-th evaluation indicator, and f_{ij} is the score of the i-th task on the j-th evaluation indicator.
[0081] Linear programming is used to optimize resource allocation, and the expression is as follows:
[0082] \text{Maximize}\quadZ=\sum_{i=1}^{n}c_ix_i
[0083] \text{Subjectto}\quad\sum_{i=1}^{n}a_{ij}x_i\leqb_j\quad\forallj
[0084] x_i\geq0\quad\foralli
[0085] Where Z is the objective function, c_i is the coefficient of the i-th variable, x_i is the value of the i-th variable, a_{ij} is the coefficient of the i-th variable in the j-th constraint, and b_j is the right-hand side value of the j-th constraint.
[0086] Step S6, plan release, the processor generates a control signal to instruct the device controller to perform the corresponding operation, the control signal is transmitted to the device controller via wired or wireless means, the device controller receives the control signal and controls the device to perform the task according to the schedule plan;
[0087] Step S7, real-time adjustment, the sensor continuously monitors the running status of the equipment and transmits the status information to the data acquisition module. The processor dynamically adjusts the schedule according to the real-time status information and analysis results, and generates a new control signal. The new control signal is transmitted to the equipment controller via wired or wireless means to update the execution plan of the equipment;
[0088] The heuristic algorithm is used to dynamically adjust the schedule, and the expression is as follows:
[0089] \text{Minimize}\quadC_{\text{max}}=\max_{i=1}^{n}(C_i)
[0090] \text{Subjectto}\quad\sum_{j=1}^{m}p_{ij}x_{ij}\leqd_i\quad\foralli
[0091] Where C_{\text{max}} is the maximum completion time, C_i is the completion time of the i-th task, p_{ij} is the processing time of the i-th task on the j-th resource, x_{ij} is the allocation of the i-th task on the j-th resource, and d_i is the deadline of the i-th task.
[0092] Step S8, feedback and continuous improvement, the system collects equipment operation data and user feedback information, and stores them in the memory. The processor optimizes the scheduling algorithm and system parameters based on the collected data and feedback information.
[0093] Gradient descent is used to optimize system parameters, and the expression is as follows:
[0094] \theta_{t+1}=\theta_t\alpha\nablaJ(\theta_t)
[0095] Among them, \theta_{t+1} is the parameter of the t+1th iteration, \theta_t is the parameter of the tth iteration, \alpha is the learning rate, and \nablaJ(\theta_t) is the gradient of the objective function J at \theta_t.
[0096] Embodiment 2
[0097] Using a set of physical quantity values collected by a hypothetical sensor, and scheduling according to the system and method of the first embodiment;
[0098] Assume that the physical values collected by the sensor are as follows:
[0099] Temperature: 25℃;
[0100] Pressure: 100kPa;
[0101] Speed: 50m / s;
[0102] Step S1: Data collection
[0103] The sensor converts these physical quantities into electrical signals and transmits them to the data acquisition module via wired or wireless means.
[0104] Step S2: Signal conversion
[0105] The data acquisition module receives the electrical signal from the sensor and converts the electrical signal into a digital signal.
[0106] Step S3: Data storage
[0107] The digital signal is temporarily stored in the system's buffer, awaiting further processing, and the digital signal is stored in the system's memory to form a raw data record.
[0108] Step S4: Data analysis
[0109] The processor cleans the stored raw data, removes noise and erroneous data, and processes the cleaned data to extract useful information, including production speed and equipment status. It then uses artificial intelligence and machine learning models to analyze the processed data to predict production demand and resource usage patterns.
[0110] Assume that the original data is recorded as follows:
[0111] Temperature: [24,25,26,27,28];
[0112] Pressure: [98,100,102,104,106];
[0113] Speed: [48,50,52,54,56];
[0114] Use mean filtering to remove random noise:
[0115] Temperature: y_i=\frac{1}{5}\sum_{j=i-2}^{i+2}x_j y_1=\frac{1}{5}(24+25+26+27+28)=26y_2=\frac{1}{5}(24+25+26+27+28)=26y_3=\frac{1}{5}(24+25+26+27+28)=26y_ 4=\frac{1}{5}(24+25+26+27+28)=26y_5=\frac{1}{5}(24+25+26+27+28)=26 Pressure: y_i=\frac{1}{5}\sum_{j=i-2}^{i+2}x_j y_1=\frac{1}{5}(98+100+102+104+106)=102y_2=\frac{1}{5}(98+100+102+104+106)=102y_3=\frac{1}{5}(98+100+102+104+106)=102 y_4=\frac{1}{5}(98+100+102+104+106)=102y_5=\frac{1}{5}(98+100+102+104+106)=102 Speed: y_i=\frac{1}{5}\sum_{j=i-2}^{i+2}x_j y_1=\frac{1}{5}(48+50+52+54+56)=52y_2=\frac{1}{5}(48+50+52+54+56)=52y_3=\frac{1}{5}(4 8+50+52+54+56)=52y_4=\frac{1}{5}(48+50+52+54+56)=52y_5=\frac{1}{5}(48+50+52+54+56)=52
[0116] Use a moving average to smooth the data:
[0117] Temperature: \text{MA}i=\frac{1}{3}\sum{j=i-1}^{i+1}x_j\text{MA}_2=\frac{1}{3}(25+26+27)=26
[0118] \text{MA}_3=\frac{1}{3}(25+26+27)=26
[0119] \text{MA}_4=\frac{1}{3}(25+26+27)=26
[0120] Pressure: \text{MA}i=\frac{1}{3}\sum{j=i-1}^{i+1}x_j
[0121] \text{MA}_2=\frac{1}{3}(100+102+104)=102
[0122] \text{MA}_3=\frac{1}{3}(100+102+104)=102
[0123] \text{MA}_4=\frac{1}{3}(100+102+104)=102
[0124] Speed: \text{MA}i=\frac{1}{3}\sum{j=i-1}^{i+1}x_j
[0125] \text{MA}_2=\frac{1}{3}(50+52+54)=52
[0126] \text{MA}_3=\frac{1}{3}(50+52+54)=52
[0127] \text{MA}_4=\frac{1}{3}(50+52+54)=52
[0128] Use linear regression to forecast production demand;
[0129] Assume that the input variables include historical production data and order volume:
[0130] Historical production data: [100,110,120,130,140]
[0131] Order quantity: [50,55,60,65,70]
[0132] Using linear regression model: y = \beta_0+\beta_1x_1+\beta_2x_2+\epsilon
[0133] Assume the regression coefficients are:
[0134] \beta_0=10
[0135] \beta_1=0.5
[0136] \beta_2 = 0.8
[0137] Forecast production demand: y = 10 + 0.5 * 120 + 0.8 * 60 = 10 + 60 + 48 = 118
[0138] Predict resource usage patterns through time series analysis;
[0139] Using the time series model: y_t=\mu+\sum_{i=1}^{p}\phi_i y_{ti}+\sum_{j=1}^{q}\theta_j\epsilon_{tj}+\epsilon_t
[0140] Assume the parameters are:
[0141] \mu=50
[0142] \phi_1=0.5
[0143] \theta_1=0.3
[0144] Predict resource usage patterns:
[0145] y_t=50+0.5*52+0.3*2=50+26+0.6=76.6
[0146] Step S5: Scheduling decision
[0147] The processor determines the priority of the task based on the analysis results and task objectives, calculates the optimal resource allocation plan to ensure efficient use of resources, and then generates a detailed scheduling plan, including the start time, end time and required resources of each task.
[0148] Assume that the task priority evaluation indicators and weights are as follows:
[0149] Evaluation indicators: urgency, importance
[0150] Weights: w_1 = 0.6, w_2 = 0.4
[0151] The task scores are as follows:
[0152] Task 1: Urgency = 8, Importance = 7
[0153] Task 2: Urgency = 6, Importance = 9
[0154] Calculate task priority:
[0155] Task 1: P_1 = 0.6*8 + 0.4*7 = 4.8 + 2.8 = 7.6
[0156] Task 2: P_2 = 0.6*6 + 0.4*9 = 3.6 + 3.6 = 7.2
[0157] Assume that the resource allocation constraints are as follows:
[0158] Resource 1: a_{11}=2, a_{21}=3, b_1=10
[0159] Resource 2: a_{12}=4, a_{22}=2, b_2=12
[0160] Optimizing resource allocation using linear programming:
[0161] \text{Maximize}\quad Z=7.6x_1+7.2x_2
[0162] \text{Subject to}\quad 2x_1+3x_2\leq 10
[0163] \quad 4x_1+2x_2\leq 12
[0164] \quad x_1,x_2\geq 0
[0165] The solution is: x_1 = 2, x_2 = 2;
[0166] Generate a schedule:
[0167] Task 1: Start time = 0, End time = 2, Required resources = 2;
[0168] Task 2: Start time = 2, End time = 4, Required resources = 2;
[0169] Step S6: Plan for release
[0170] The processor generates a control signal to instruct the device controller to perform a corresponding operation. The control signal is transmitted to the device controller via wired or wireless means. The device controller receives the control signal and controls the device to perform tasks according to the schedule.
[0171] Step S7: Real-time adjustment
[0172] The sensor continuously monitors the operating status of the equipment and transmits the status information to the data acquisition module. The processor dynamically adjusts the schedule based on the real-time status information and analysis results, and generates new control signals. The new control signals are transmitted to the equipment controller via wired or wireless means to update the equipment's execution plan.
[0173] Assume that the real-time status information is as follows:
[0174] Task 1: Completion time = 3
[0175] Task 2: Completion time = 5
[0176] Use heuristic algorithms to dynamically adjust the schedule:
[0177] \text{Minimize}\quad C_{\text{max}}=\max(3,5)=5
[0178] Update schedule:
[0179] Task 1: Start time = 0, End time = 3, Required resources = 2
[0180] Task 2: Start time = 3, End time = 5, Required resources = 2
[0181] The above method starts from the physical value collected by the sensor, and goes through the steps of data collection, signal conversion, data storage, data analysis, scheduling decision, plan release and real-time adjustment, and finally generates and adjusts the scheduling plan.
[0182] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0183] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A multi-line production planning and scheduling system based on task objectives, characterized by: include Data acquisition module, used to collect production data in real time through sensors and equipment deployed on the production line; A data processing module, used to pre-process and perform real-time analysis on the data collected by the data acquisition module, and to predict production demand and resource usage patterns using artificial intelligence and machine learning models; An advanced scheduling module is used to determine the task priority and optimize resource allocation and generate a preliminary scheduling plan based on the analysis results and task objectives of the data processing module; A plan generation module, used to generate a detailed scheduling plan based on the preliminary scheduling plan generated by the advanced scheduling module, and publish it to the production management system; An adjustment and optimization module, used to continuously monitor the operating status of the production line and dynamically adjust the scheduling plan generated by the advanced scheduling module according to the real-time data and prediction results of the data processing module; The feedback improvement module is used to collect user feedback and continuously optimize the scheduling system based on the adjustment results and real-time data of the adjustment optimization module.
2. The multi-production line production planning and scheduling system based on task objectives according to claim 1 is characterized by: The data acquisition module includes various types of sensors for collecting real-time data on equipment status, production speed, and material consumption. The sensors include but are not limited to temperature sensors, pressure sensors, and speed sensors.
3. The multi-production line production planning and scheduling system based on task objectives according to claim 1 is characterized by: The data processing module includes a data cleaning unit, a formatting unit and a real-time analysis unit, which are used to ensure the data quality and the accuracy of the real-time analysis.
4. The multi-production line production planning and scheduling system based on task objectives according to claim 1 is characterized by: The advanced scheduling module includes a task priority sorting unit and a resource allocation optimization unit, which are used to generate a preliminary scheduling plan according to task objectives and real-time analysis results.
5. The multi-production line production planning and scheduling system based on task objectives according to claim 1 is characterized by: The plan generation module includes a schedule plan generation unit and a release unit, which are used to notify relevant personnel and equipment of the generated schedule plan.
6. The multi-production line production planning and scheduling system based on task objectives according to claim 1 is characterized by: The adjustment and optimization module includes a real-time monitoring unit and a dynamic adjustment unit, which are used to adjust the scheduling plan according to the real-time monitoring results and the prediction results.
7. The multi-production line production planning and scheduling system based on task objectives according to claim 1 is characterized by: The feedback improvement module includes a user feedback collection unit and a continuous improvement unit, which are used to optimize system performance according to user feedback and real-time data.
8. A method for a multi-production line production planning and scheduling system based on task objectives according to any one of claims 1 to 7, characterized in that: The following steps are included Step S1, data acquisition, sensors deployed on the production line read physical quantities in real time, including temperature, pressure and speed, and convert these physical quantities into electrical signals. The sensors transmit the electrical signals to the data acquisition module via wired or wireless means; Step S2, signal conversion, the data acquisition module receives the electrical signal from the sensor, and the data acquisition module converts the electrical signal into a digital signal; Step S3, data storage, the digital signal is temporarily stored in the system's cache, waiting for further processing, and the digital signal is stored in the system's memory to form an original data record; Step S4, data analysis, the processor cleans the stored raw data, removes noise and erroneous data, and processes the cleaned data to extract useful information, including production speed and equipment status, and then uses artificial intelligence and machine learning models to analyze the processed data to predict production demand and resource usage patterns; Step S5, scheduling decision, the processor determines the priority of the task according to the analysis results and task objectives, and calculates the optimal resource allocation plan to ensure efficient use of resources, and then generates a detailed scheduling plan, including the start time, end time and required resources of each task; Step S6, plan release, the processor generates a control signal to instruct the device controller to perform the corresponding operation, the control signal is transmitted to the device controller via wired or wireless means, the device controller receives the control signal and controls the device to perform the task according to the schedule plan; Step S7, real-time adjustment, the sensor continuously monitors the running status of the equipment and transmits the status information to the data acquisition module. The processor dynamically adjusts the schedule according to the real-time status information and analysis results, and generates a new control signal. The new control signal is transmitted to the equipment controller via wired or wireless means to update the execution plan of the equipment; Step S8, feedback and continuous improvement, the system collects equipment operation data and user feedback information, and stores them in the memory. The processor optimizes the scheduling algorithm and system parameters based on the collected data and feedback information.
9. A computer device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method of the multi-production line production planning and scheduling system based on task objectives as described in claim 8.
10. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor executes the method of a multi-production line production planning and scheduling system based on task objectives as described in claim 8.
Citation Information
Cited By
Multi-target factory scheduling method considering machine limitation
CN119204611A
