Intelligent factory production process real-time monitoring and optimizing system

Abstract

The invention discloses a real-time monitoring and optimizing system for the production process of an intelligent factory, and belongs to the field of production management of the intelligent factory, and the real-time monitoring and optimizing system specifically comprises the following steps: obtaining technological parameters and production action sequence data of a pipe fitting forming process by using an industrial Internet of Things, and transmitting the technological parameters and the production action sequence data to a data processing center; on the basis of the Markov chain theory, an action waste analysis model is built according to action sequence data, action waste is recognized by calculating the state transition probability and steady state distribution and comparing with a standard action process, and a result is fed back to a production management system; the production management system constructs a dynamic bottleneck station identification model by using the queuing theory and the operational research in combination with the process parameters and the action waste identification result, calculates the probability that each station becomes a bottleneck in real time, and judges the dynamic bottleneck station in combination with the stacking number of products being processed and the production efficiency; the production takt is adjusted according to the dynamic bottleneck station recognition result, real-time monitoring and optimization of the production process are achieved, and the production efficiency and quality are improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent factory production management, and specifically relates to a real-time monitoring and optimization system for an intelligent factory production process. Background Art

[0002] Smart factory production processes present numerous challenges, including improper material stacking leading to wasted space, unnecessary steps leading to time-consuming production processes, difficulty accurately identifying bottleneck workstations on the production line, and the inability to adaptively adjust production rhythms to meet actual conditions. These issues impact production efficiency and business profitability. Traditional production monitoring and optimization methods struggle to comprehensively, accurately, and in real time address these issues, failing to meet the efficient, lean production demands of smart factories.

[0003] For example, the Chinese patent application with publication number CN109360118A discloses a factory status monitoring method, apparatus, system, equipment and storage medium, including: obtaining the status of factory change items, and setting scores for the status of the factory change items to obtain factory change item status scores, wherein the factory change items include at least production changes, inventory changes and production and sales balance changes, and the status of the factory change items includes at least four states: normal, attention, abnormal, and warning; calculating the factory status score according to the factory change item status score, and judging the factory status according to the factory status score. This invention monitors the status of various factory change items in the production process in real time, and monitors whether the factory status is normal by digitally processing the status of each factory change item, so as to achieve the purpose of real-time monitoring of production conditions, detect production errors in a timely manner, and make factory operations more efficient.

[0004] The above existing technologies have the following problems: they mainly focus on factory change items such as production changes, inventory changes, and production and sales balance changes, and focus on macro-status monitoring at the overall factory operation level; they only set scores for the status of factory change items and then calculate the factory status score to judge the factory status. The analysis method is relatively simple and lacks in-depth exploration of the inherent laws of the production process; there is no detailed feedback and adjustment mechanism for specific problems. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention proposes a real-time monitoring and optimization system for the production process of an intelligent factory, which uses the industrial Internet of Things to obtain the process parameters and production action sequence data of the pipe forming process and transmits them to the data processing center; based on the Markov chain theory, a motion waste analysis model is constructed according to the action sequence data, and by calculating the state transition probability and steady-state distribution, the motion waste is identified by comparing with the standard action process, and the results are fed back to the production management system; the production management system combines the process parameters of the pipe forming process with the motion waste identification results, uses queuing theory and operations research to construct a dynamic bottleneck station identification model, calculates the probability of each station becoming a bottleneck in real time, and judges the dynamic bottleneck station based on the number of work-in-progress accumulation and production efficiency; adjusts the production rhythm according to the dynamic bottleneck station identification results, realizes real-time monitoring and optimization of the production process, and improves production efficiency and quality.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A real-time monitoring and optimization system for the production process of an intelligent factory, comprising: a data acquisition module, a motion waste analysis module, a bottleneck workstation identification module, and a production rhythm adjustment module;

[0008] The motion waste analysis module constructs a motion waste analysis model based on the motion sequence data collected by the data collection module and the Markov chain theory, and identifies motion waste by calculating the state transition probability and the steady-state distribution of the Markov chain;

[0009] The bottleneck workstation identification module constructs a dynamic bottleneck workstation identification model based on the received motion waste identification results and the process parameters of the pipe forming process collected by the data acquisition module, and quantitatively evaluates the probability value of each workstation evolving into a bottleneck workstation at different time nodes;

[0010] The production rhythm adjustment module adjusts the production rhythm according to the identification result of the dynamic bottleneck station.

[0011] Specifically, the motion waste analysis module constructs a motion waste analysis model based on the motion sequence data and Markov chain theory to identify motion waste situations, including:

[0012] A1: Obtain action sequence data during the pipe fitting production process and perform preprocessing;

[0013] A2: Based on the pipe fitting production process, a unique discrete state code is defined for each action. A mapping rule from action to discrete state is formulated. Mapping is performed based on the action name. By traversing the preprocessed action sequence data, each action is converted into its corresponding discrete state code according to the mapping rule.

[0014] A3: Analyze the discretized action sequence data, classify the actions into different categories based on their types, and combine K actions into an action state based on their execution order. The action state includes raw material classification and screening, processing technology, quality inspection, and finished product classification and handling.

[0015] A4: All the action states obtained by the division in A3 are aggregated after removing the duplicate action states, and the aggregated action states form the state space of the Markov chain ,in, represents the nth action state, where n represents the number of action states;

[0016] A5: Starting from the first action state of the preprocessed action sequence data, check the two adjacent action states in sequence and ;

[0017] If two adjacent action states are different, it is determined that a state transition has occurred, that is, from one action state to another Transfer to another action state ;

[0018] A6: Use the initialized counter to count the number of state transitions in the preprocessed action sequence data to obtain the transition frequency ;

[0019] A7: By calculating the transfer frequency With Transfer to all non The ratio of the total number of action states itself to obtain the state transition probability ;

[0020] A8: Create a The state transition probability calculated in A7 is Assign to the matrix to get the action transfer matrix .

[0021] Specifically, the motion waste analysis module constructs a motion waste analysis model based on the Markov chain theory according to the motion sequence data to identify motion waste situations, and further includes:

[0022] A9: According to the properties of the steady-state distribution, establish the Markov chain equilibrium equation and use the linear equation system to solve the Markov chain equilibrium equation to obtain the steady-state distribution vector ;

[0023] A10: According to the steady-state distribution vector , determine the frequency of occurrence of each action state in the actual production process The frequency of occurrence of each action state is the steady-state probability of each action state ,and ;

[0024] A11: According to the process requirements of pipe production, set the standard frequency range for each action state , at the same time, set a preset standard threshold for each action state ,in, and Respectively represent the minimum and maximum values ​​of the standard frequency of the i-th action state;

[0025] A12: For each action state , the action state Frequency of occurrence With standard frequency range Make a comparison;

[0026] like ,and , then determine the action state There is wasted motion;

[0027] A13: Feedback the motion waste identification results to the production management system through the data interface.

[0028] Specifically, the Markov chain equilibrium equation satisfies:

[0029] The system transitions from all previous action states to the action state The sum of the weighted state transition probabilities is equal to the system being in the action state The steady-state probability of

[0030] The sum of the steady-state probabilities of the system being in all action states is 1.

[0031] Specifically, the specific steps of A10 include:

[0032] A10.1: Obtaining the Steady-State Distribution Vector and the state space of the Markov chain ;

[0033] A10.2: Traversal The index of each action state in , from the steady-state distribution vector Extract the element value at the corresponding position, and the element value is the steady-state probability of the action state.

[0034] Specifically, the bottleneck workstation identification module constructs a dynamic bottleneck workstation identification model based on the received motion waste identification results and the process parameters of the pipe forming process collected by the data acquisition module, and quantitatively evaluates the probability of each workstation evolving into a bottleneck workstation at different time nodes, including:

[0035] B1: Obtaining motion waste identification results and process parameters of the pipe forming process, while simultaneously monitoring the amount of work-in-progress (WIP) accumulation and production efficiency at each workstation in real time; the motion waste identification results include wasteful motions and waste levels;

[0036] B2: Assign a unique identifier to each workstation, treat each workstation as a queuing system, and the WIP as a customer. Based on the process parameters of the tube forming process and the results of motion waste identification, determine the arrival rate and service rate of each queuing system. The arrival rate is the rate at which the WIP arrives at the workstation; the service rate is the rate at which the workstation processes the WIP.

[0037] B3: Combine the M / M / 1 model and apply dynamic programming methods to establish a dynamic bottleneck workstation identification model;

[0038] B4: Integrate the obtained motion waste identification results, pipe forming process parameters, and real-time monitoring of the number of work-in-progress accumulation and production efficiency of each workstation to form pipe fitting data. The pipe fitting data is input into the dynamic bottleneck workstation identification model, and the dynamic bottleneck workstation identification model is used to calculate in real time the probability value of each workstation evolving into a bottleneck workstation at different time nodes.

[0039] Specifically, the bottleneck workstation identification module constructs a dynamic bottleneck workstation identification model based on the received motion waste identification results and the process parameters of the pipe forming process collected by the data acquisition module, and quantitatively evaluates the probability of each workstation evolving into a bottleneck workstation at different time nodes, and also includes:

[0040] B5: Monitor the WIP accumulation quantity and production efficiency of each workstation in real time, and set the WIP accumulation quantity threshold;

[0041] If the number of work-in-process products accumulated at any workstation exceeds the threshold, and its production efficiency is lower than the demand efficiency of the downstream workstation, the workstation is determined to be the current dynamic bottleneck workstation based on the probability value calculated by the dynamic bottleneck workstation identification model.

[0042] B6: Output the identification results of dynamic bottleneck workstations in the form of charts and feed them back to the production management system.

[0043] Specifically, the specific steps of B2 include:

[0044] B2.1: Develop identifier rules based on the characteristics of the workstations. The identifier rules use a combination of letters and numbers, with letters representing work sections and numbers representing the sequence number of the workstations within the section.

[0045] B2.2: Assign a unique identifier to each workstation according to the established identifier rules and create a workstation information table; the workstation information table includes the name, function, and identifier information of the workstation;

[0046] B2.3: Perform concept mapping, treating each workstation as a queuing system, the WIP as the customer, and the processing equipment and operators at the workstation as the service desk. Also, define the queueing rules for the WIP in front of the workstation as first-come, first-served.

[0047] B2.4: Collect historical data on the arrival of work-in-progress at each workstation during pipe fitting production, record the timestamps of the work-in-progress arrivals, and calculate the time interval between two adjacent work-in-progress arrivals based on the timestamps. ;

[0048] B2.5: Calculating time intervals Average value , and the average value Find the reciprocal to get the arrival rate of each queue system ;

[0049] B2.6: Analyze the results of motion waste identification, evaluate the impact of wasteful motions on the WIP arrival rate, and revise the calculated arrival rate based on the degree of impact;

[0050] B2.7: Determine the standard processing time for each station based on the process parameters of the pipe forming process , analyze the results of motion waste identification, evaluate the impact of wasteful motion on the efficiency of work-in-process at the workstation, and correct the standard processing time according to the degree of impact to obtain the actual processing time ;

[0051] B2.8: Yes Find the reciprocal and get the service rate of each queuing system .

[0052] Specifically, the specific steps of B3 include:

[0053] B3.1: Determine the decision to be taken in each action state and load the pre-trained M / M / 1 model. At the same time, the obtained arrival rate and service rate As M / M / 1 model parameters;

[0054] B3.2: Set minimizing the production cycle as the objective function and derive the state transition equation based on the M / M / 1 model and decision rules;

[0055] B3.3: Based on the objective function and state transition equation, establish the Bellman equation and use the value iteration method to solve the Bellman equation;

[0056] B3.4: By solving the Bellman equation, we can obtain the optimal decision for each action state, i.e. the optimal strategy. , and obtain the dynamic bottleneck workstation identification model.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] 1. The present invention proposes a real-time monitoring and optimization system for the production process of an intelligent factory, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.

[0059] 2. The present invention proposes a real-time monitoring and optimization system for the production process of an intelligent factory. By collecting process parameters and motion sequence data of the pipe forming process through the Industrial Internet of Things, and using Markov chain theory to construct a motion waste analysis model, the system can accurately identify motion waste. This process achieves a deep insight into the details of the production process and quantifies the waste situation, which helps to optimize the production process from the source of operation, reduce unnecessary motion consumption, and improve production efficiency.

[0060] 3. The present invention proposes a real-time monitoring and optimization system for the production process of an intelligent factory. In terms of bottleneck station identification and production rhythm adjustment, the production management system combines the process parameters of the pipe forming process with the motion waste identification results, and uses queuing theory and operations research to construct a dynamic bottleneck station identification model. It can judge the bottleneck station in real time and adjust the production rhythm in a timely manner based on this, effectively avoiding the accumulation of work-in-progress, so that the production rhythm of each station is coordinated and matched, ensuring the smooth and efficient production process, thereby improving the overall production quality, reducing production costs, and enhancing the lean production level of the intelligent factory. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is an architecture diagram of a real-time monitoring and optimization system for the production process of an intelligent factory according to the present invention;

[0062] Figure 2 This is a principle flow chart of a real-time monitoring and optimization system for an intelligent factory production process according to the present invention;

[0063] Figure 3 This is a flowchart of the motion waste identification of a real-time monitoring and optimization system for the production process of an intelligent factory of the present invention;

[0064] Figure 4This is a flow chart of dynamic bottleneck station judgment of a real-time monitoring and optimization system for production processes in an intelligent factory according to the present invention. DETAILED DESCRIPTION

[0065] Example 1:

[0066] See also Figure 1 and Figure 2 The present invention provides an embodiment of a smart factory production process real-time monitoring and optimization system, comprising:

[0067] Data collection module, motion waste analysis module, bottleneck workstation identification module, production rhythm adjustment module;

[0068] The data acquisition module is used to collect process parameters of the pipe forming process and action sequence data during the pipe fitting production process, and transmit the data to the data processing center; the pipe forming process parameters include temperature, pressure, and speed; the action sequence data includes the action sequence of workers operating the equipment and the operation data of the equipment itself;

[0069] The motion waste analysis module is used to analyze the motion sequence data in the production process based on Markov chain theory, identify motion waste, and feed the results back to the production management system;

[0070] The bottleneck station identification module is used to combine the motion waste identification results and the process parameters of the pipe forming process to build a dynamic bottleneck station identification model, monitor the status of each station in real time, and determine the current dynamic bottleneck station;

[0071] The production rhythm adjustment module is used to adjust the production rhythm according to the identification results of dynamic bottleneck workstations to optimize the production process and improve production efficiency.

[0072] The motion waste analysis module includes: a model building unit, a model calculation unit, and a motion waste identification unit;

[0073] A model building unit, for building a motion waste analysis model using the collected motion sequence data according to Markov chain theory;

[0074] A model calculation unit is used to process and calculate the action sequence data, determine the state transition probability from one action state to another, and calculate the steady-state distribution of the Markov chain;

[0075] The motion waste identification unit is used to analyze the frequency of occurrence of each motion state in the actual production process based on the steady-state distribution and state transition probability of the Markov chain, compare it with the standard motion process, and identify motion waste.

[0076] The bottleneck workstation identification module includes: probability calculation unit, status monitoring unit, and bottleneck judgment unit;

[0077] A probability calculation unit is used to calculate in real time the probability of each workstation becoming a bottleneck workstation at different times using a dynamic bottleneck workstation identification model constructed based on motion waste identification results and process parameters of the pipe forming process;

[0078] The status monitoring unit is used to monitor the number of work-in-progress accumulation and production efficiency of each workstation in real time and obtain the actual operating status of the workstation;

[0079] The bottleneck judgment unit is used to judge that any work-in-process accumulation quantity at any workstation exceeds the set work-in-process accumulation quantity threshold and its production efficiency is lower than the demand efficiency of the downstream workstation, based on the model calculation results, and the workstation is judged as the current dynamic bottleneck workstation.

[0080] The production rhythm adjustment module includes: adjustment decision unit and adjustment execution unit;

[0081] The adjustment decision-making unit is used to formulate production rhythm adjustment strategies and plans based on the identification results of dynamic bottleneck workstations, and determine the magnitude and direction of the adjustment;

[0082] The adjustment execution unit is used to perform production rhythm adjustment operations according to the plan formulated by the adjustment decision unit. For example, it adjusts the operating speed and operation rhythm of the equipment to make the production process smoother and reduce the impact of bottleneck stations on production.

[0083] Specifically, the overall process of a real-time monitoring and optimization system for smart factory production processes includes:

[0084] S1: Obtain the process parameters of the pipe forming process and the action sequence data of the pipe production process, and transmit them to the data processing center through the industrial Internet of Things;

[0085] S2: Based on the motion sequence data from the pipe fitting production process, a motion waste analysis model is constructed based on Markov chain theory. By processing and calculating the motion sequence data, the state transition probability from one motion state to another is determined, and the steady-state distribution of the Markov chain is calculated. Based on the steady-state distribution and state transition probability of the Markov chain, the frequency of occurrence of each motion state in the actual production process is analyzed. By comparing it with the standard motion process, motion waste is identified, and the motion waste identification results are fed back to the production management system.

[0086] S3: After receiving the motion waste identification results, the production management system combines the process parameters of the pipe forming process and the motion waste identification results to build a dynamic bottleneck station identification model. It calculates in real time the probability of each station becoming a bottleneck station at different times. At the same time, it monitors the WIP accumulation and production efficiency of each station in real time. When the WIP accumulation of any station exceeds the set product accumulation threshold and its production efficiency is lower than the demand efficiency of the downstream station, the station is determined to be the current dynamic bottleneck station based on the model calculation results.

[0087] S4: Adjust the production rhythm based on the identification results of the dynamic bottleneck workstation.

[0088] Example 2:

[0089] See also Figure 3 In this embodiment, the motion waste analysis module constructs a motion waste analysis model based on the motion sequence data and Markov chain theory to identify motion waste situations, including:

[0090] A1: Obtain action sequence data during the pipe fitting production process and perform preprocessing;

[0091] A2: Based on the pipe fitting production process, a unique discrete state code is defined for each action. A mapping rule from action to discrete state is formulated. Mapping is performed based on the action name. By traversing the preprocessed action sequence data, each action is converted into its corresponding discrete state code according to the mapping rule.

[0092] For example, if the action name contains the word "screening", it is mapped to the state code corresponding to "raw material classification screening".

[0093] A3: Analyze the discretized action sequence data, classify the actions into different categories based on their type, and combine K actions into an action state based on their execution order. The action state includes raw material classification and screening, processing technology, multi-dimensional quality inspection, and finished product classification and handling.

[0094] Each action state is formed by a combination of continuous actions with the same function.

[0095] Exemplarily, all series of raw material screening actions can be combined into a "raw material classification screening" state.

[0096] A4: All the action states obtained by the division in A3 are aggregated after removing the duplicate action states, and the aggregated action states form the state space of the Markov chain ,in, represents the nth action state, where n represents the number of action states;

[0097] A5: Starting from the first action state of the preprocessed action sequence data, check the two adjacent action states in sequence and ;

[0098] If two adjacent action states are different, it is determined that a state transition has occurred, that is, from one action state to another Transfer to another action state ;

[0099] A6: Use the initialized counter to count the number of state transitions in the preprocessed action sequence data to obtain the transition frequency ;

[0100] A7: By calculating the transfer frequency With Transfer to all non The ratio of the total number of action states itself to obtain the state transition probability ,in, Indicates from Transfer to non The frequency of transition of its own action state;

[0101] A8: Create a The state transition probability calculated in A7 is Assign to the matrix to get the action transfer matrix ;

[0102] A9: According to the properties of the steady-state distribution, establish the Markov chain equilibrium equation and use the linear equation system to solve the Markov chain equilibrium equation to obtain the steady-state distribution vector ;

[0103] The Markov chain equilibrium equation in A9 satisfies the following conditions:

[0104] The system transitions from all possible previous action states to the action state The sum of the weighted state transition probabilities is equal to the system being in the action state The steady-state probability of

[0105] The sum of the steady-state probabilities of the system being in all action states is 1.

[0106] Among them, the steady-state distribution is a stable state reached by the Markov chain after a long period of operation, and the probability of each state no longer changes with time; the steady-state distribution vector is usually a one-dimensional array with the same number of elements as the number of action states.

[0107] For example, suppose there is a Markov chain with a state space of , the state transition probability matrix is ;

[0108] ·Assume that the steady-state distribution vector is , according to the specific formula of the Markov chain equilibrium equation , we can get the following system of equations: By solving this set of equations, we can obtain the steady-state distribution vector , which means that after a long period of operation, the system is in an action state The steady-state probability is , in action The steady-state probability is .

[0109] A10: According to the steady-state distribution vector , determine the frequency of occurrence of each action state in the actual production process The frequency of occurrence of each action state is the steady-state probability of each action state ,and ;

[0110] A11: According to the process requirements of pipe production, set the standard frequency range for each action state , at the same time, set a preset standard threshold for each action state ,in, and Respectively represent the minimum and maximum values ​​of the standard frequency of the i-th action state;

[0111] A12: For each action state , the action state Frequency of occurrence With standard frequency range Make a comparison;

[0112] like ,and , then determine the action state There is wasted motion;

[0113] A13: Feedback the motion waste identification results to the production management system through the data interface.

[0114] The specific steps of A10 include:

[0115] A10.1: Obtaining the Steady-State Distribution Vector and the state space of the Markov chain ;

[0116] A10.2: Traversal The index of each action state in , from the steady-state distribution vector Extract the element value at the corresponding position, which is the steady-state probability of the action state.

[0117] Example 3:

[0118] See also Figure 4 In this embodiment, the bottleneck workstation identification module constructs a dynamic bottleneck workstation identification model based on the received motion waste identification results and the process parameters of the pipe forming process collected by the data collection module, and quantitatively evaluates the probability of each workstation evolving into a bottleneck workstation at different time points, including:

[0119] B1: Obtaining motion waste identification results and process parameters of the pipe forming process, while simultaneously monitoring the amount of work-in-progress (WIP) accumulation and production efficiency at each workstation in real time; the motion waste identification results include wasteful motions and waste levels;

[0120] B2: Assign a unique identifier to each workstation, treat each workstation as a queuing system and the WIP as a customer. Based on the process parameters of the tube forming process and the results of motion waste identification, determine the arrival rate and service rate of each queuing system. The arrival rate is the rate at which the WIP arrives at the workstation; the service rate is the rate at which the WIP is processed by the workstation.

[0121] B3: Combine the M / M / 1 model and apply dynamic programming methods to establish a dynamic bottleneck workstation identification model;

[0122] B4: Integrate the acquired motion waste identification results, pipe forming process parameters, and real-time monitoring of the WIP accumulation and production efficiency of each workstation to form pipe data. This data is then input into a dynamic bottleneck workstation identification model. The dynamic bottleneck workstation identification model is used to calculate in real time the probability of each workstation becoming a bottleneck workstation at different time points.

[0123] Furthermore, the specific steps of B4 include:

[0124] B4.1: Integrate the motion waste identification results, pipe forming process parameters, WIP accumulation, and production efficiency to generate pipe data containing multiple features. This data can be organized into a data table, where each row represents the data for a workstation at a certain point in time, and each column corresponds to a different feature, such as workstation number, motion waste indicator, process parameter value, WIP accumulation, and production efficiency.

[0125] B4.2: Input the integrated pipe fitting data into the dynamic bottleneck workstation identification model. Based on the input data, combined with its own algorithms and parameters, calculate the probability of each workstation evolving into a bottleneck workstation at different time points. Specifically, the following are included:

[0126] (1) Check the integrated pipe fitting data, remove missing values ​​and outliers, and perform standardization. For example, if the number of work-in-progress accumulation is negative or the production efficiency is an unreasonable maximum value, it needs to be corrected or eliminated;

[0127] (2) Load the trained dynamic bottleneck workstation identification model and set the parameters required for model operation, such as discount factor and time step;

[0128] (3) Determine the initial state of the model based on the input pipe fitting data, where the initial state usually includes information such as the number of work-in-progress at each workstation and the current time;

[0129] (4) Based on the input pipe data and the state transition equation of the dynamic bottleneck station identification model, calculate the probability and result of the system transitioning from the current state to the next state at each time node;

[0130] (5) Calculate the objective function value in each state based on the state transition results. The objective function is usually to minimize the production cycle or maximize production efficiency.

[0131] (6) By solving the Bellman equation, we can obtain the probability value of each workstation evolving into a bottleneck workstation at different time nodes.

[0132] B5: Monitor the WIP accumulation quantity and production efficiency of each workstation in real time, and set the WIP accumulation quantity threshold;

[0133] If the number of work-in-process products accumulated at any workstation exceeds the work-in-process product accumulation threshold and its production efficiency is lower than the required efficiency of the downstream workstation, the workstation is determined to be the current dynamic bottleneck workstation based on the probability value calculated by the dynamic bottleneck workstation identification model. Specifically, the following are included:

[0134] (1) The number of work-in-progress at each workstation is collected in real time by sensors installed at the workstations;

[0135] (2) Monitor the production efficiency of each workstation, such as recording the number of products completed or the amount of work processed per unit time. At the same time, determine the demand efficiency of downstream workstations based on their production capacity, production rhythm, and order requirements.

[0136] (3) Compare the collected WIP accumulation quantity of each workstation with the pre-set WIP accumulation quantity threshold, compare the production efficiency of the workstation with the demand efficiency of the downstream workstation, and determine whether the production efficiency is lower than the demand efficiency of the downstream workstation;

[0137] (4) When any workstation simultaneously satisfies the two conditions that the number of work-in-progress accumulation exceeds the threshold number of work-in-progress accumulation and the production efficiency is lower than the efficiency required by the downstream workstation, the probability value of the workstation evolving into a bottleneck workstation at the current time node calculated by the dynamic bottleneck workstation identification model is checked. In the present invention, the probability value of the bottleneck workstation is obtained by processing and calculating data such as process parameters of the pipe forming process and motion waste identification results through the dynamic bottleneck workstation identification model;

[0138] (5) Make a comprehensive judgment based on the set rules and probability values. For example, if the probability value exceeds the set critical value, the workstation is determined to be the current dynamic bottleneck workstation; if the probability value does not reach the critical value, continue to observe and monitor, and do not determine it as a bottleneck workstation.

[0139] B6: Output the identification results of dynamic bottleneck workstations in the form of charts and feed them back to the production management system.

[0140] The specific steps of B2 include:

[0141] B2.1: Develop a set of identifier rules based on the characteristics of the workstations. The identifier rules use a combination of letters and numbers, where letters represent work sections and numbers represent the sequence number of the workstations within the section.

[0142] B2.2: Assign a unique identifier to each workstation according to the established identifier rules and create a workstation information table; the workstation information table includes the name, function, and identifier information of the workstation;

[0143] B2.3: Perform concept mapping, treating each workstation as a queuing system, the WIP as the customer, and the processing equipment and operators at the workstation as the service desk. Also, define the queueing rules for the WIP in front of the workstation as first-come, first-served.

[0144] B2.4: Collect historical data on the arrival of work-in-progress at each workstation during pipe fitting production, record the timestamps of the work-in-progress arrivals, and calculate the time interval between two adjacent work-in-progress arrivals based on the timestamps. ;

[0145] B2.5: Calculating time intervals Average value , and the average value Find the reciprocal to get the arrival rate of each queue system ;

[0146] B2.6: Analyze the results of motion waste identification, assess the impact of wasteful motions on the WIP arrival rate, and revise the calculated arrival rate based on the degree of impact. For example, if any motion waste causes the WIP to remain in the production process for too long, it will affect its arrival rate at subsequent workstations. Repeated handling may cause delays or damage to the WIP during handling, affecting its timely arrival at the next workstation.

[0147] Furthermore, by analyzing historical data, we can determine how much the rate at which the work-in-process arrives at the next workstation decreases for every minute of waiting time, so as to quantify the impact of wasteful actions on the arrival rate. Based on the quantified impact, the originally calculated work-in-process arrival rate can be revised, taking into account the impact of different wasteful actions to obtain a revised arrival rate.

[0148] B2.7: Determine the standard processing time for each station based on the process parameters of the pipe forming process , analyze the results of motion waste identification, evaluate the impact of wasteful motion on the efficiency of work-in-process at the workstation, and correct the standard processing time according to the degree of impact to obtain the actual processing time ,For example, wasted motion may lead to equipment failure, operator errors, etc., ,thus reducing the processing efficiency of the workstation;

[0149] Furthermore, the specific steps of B2.7 include:

[0150] B2.71: Obtain the process parameters of the pipe forming process and calculate the standard processing time based on the process parameters. The calculation of the standard processing time varies depending on the specific process of different stations. For example, for a simple machining station, if the machine processes the pipe at a fixed speed v, the processing length is X, and each clamping and removal of the pipe requires a fixed time , then the standard processing time ;

[0151] B2.72: Analyze operators' actions at workstations to identify wasteful actions, such as unnecessary movement, unnecessary waiting, and repetitive operations. Record the frequency and duration of each wasteful action. Excessive movement refers to movement other than station switching, and unnecessary waiting refers to non-work waiting.

[0152] B2.73: Analyze the impact of wasteful actions on workstation WIP processing efficiency based on their characteristics and frequency. For example, frequent movement can cause worker fatigue, reducing work speed; unnecessary waiting can idle equipment and extend overall processing time. Expert assessment methods can be used to determine the extent to which each wasteful action affects workstation WIP processing efficiency.

[0153] B2.74: Modify the standard processing time based on the impact of the assessed wasteful actions on the work-in-process efficiency of the workstation;

[0154] If a wasteful action leads to reduced efficiency , then the actual processing time .

[0155] B2.8: Yes Find the mean and then the reciprocal to get the service rate of each queue system .

[0156] The specific steps of B3 include:

[0157] B3.1: Determine the decisions that can be taken in each action state and load the pre-trained M / M / 1 model , and at the same time, the arrival rate and service rate As the M / M / 1 model parameters, where represents the average number of work-in-progress in the system, and the M / M / 1 model is the prior art in this field and is not an inventive solution of the present application, so it will not be described in detail here;

[0158] For example, whether to increase the number of operators at a certain workstation or adjust the processing speed of the equipment, the decision space includes all possible decision options.

[0159] It should be noted that the M / M / 1 model is a classic and basic queuing model in queuing theory, which belongs to a single-server queuing model. In this model, M represents a Markov process, that is, the customer arrival process follows a Poisson distribution, the service time follows an exponential distribution, and 1 means that there is only one server in the system.

[0160] B3.2: Set minimizing the production cycle as the objective function and derive the state transition equation based on the M / M / 1 model and decision rules;

[0161] Furthermore, the derivation process of the state transfer equation includes: assuming is the current action state, For current decision-making, is the next action state, then the state transition probability Describes the action state Make a decision Then transfer to the action state probability.

[0162] B3.3: Based on the objective function and the state transition equation, establish the Bellman equation and use the value iteration method to solve the Bellman equation. The specific form of the Bellman equation is: , Indicates that it is in action state Make a decision The instant cost, min represents the minimum function, D represents the decision space, and Respectively indicate the action state and action status The optimal value function under the action state or action state Initially, the optimal value of the long-term cumulative reward or cost that can be obtained by adopting the optimal strategy;

[0163] B3.4: By solving the Bellman equation, we can obtain the optimal decision for each action state, i.e. the optimal strategy. , and then a dynamic bottleneck workstation identification model is obtained, wherein the value iteration method is used to solve the Bellman equation. The value iteration method is the existing technology content in this field and is not the creative solution of this application, so it will not be described here.

[0164] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific embodiments. The above-mentioned specific embodiments are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention. These are all protected by the present invention.

Claims

1. A real-time monitoring and optimization system for the production process of an intelligent factory, characterized in that: include: Data collection module, motion waste analysis module, bottleneck workstation identification module, production rhythm adjustment module; The motion waste analysis module constructs a motion waste analysis model based on the motion sequence data collected by the data collection module and the Markov chain theory, and identifies motion waste by calculating the state transition probability and the steady-state distribution of the Markov chain; The bottleneck workstation identification module constructs a dynamic bottleneck workstation identification model based on the received motion waste identification results and the process parameters of the pipe forming process collected by the data acquisition module, and quantitatively evaluates the probability value of each workstation evolving into a bottleneck workstation at different time nodes; The production rhythm adjustment module adjusts the production rhythm according to the identification result of the dynamic bottleneck station.

2. A smart factory production process real-time monitoring and optimization system as claimed in claim 1, characterized in that: The motion waste analysis module constructs a motion waste analysis model based on the motion sequence data and Markov chain theory to identify motion waste situations, including: A1: Obtain action sequence data during the pipe fitting production process and perform preprocessing; A2: Based on the pipe fitting production process, a unique discrete state code is defined for each action. A mapping rule from action to discrete state is formulated. Mapping is performed based on the action name. By traversing the preprocessed action sequence data, each action is converted into its corresponding discrete state code according to the mapping rule. A3: Analyze the discretized action sequence data, classify the actions into different categories based on their types, and combine K actions into an action state based on their execution order. The action state includes raw material classification and screening, processing technology, quality inspection, and finished product classification and handling. A4: All the action states obtained by the division in A3 are aggregated after removing the duplicate action states, and the aggregated action states form the state space of the Markov chain ,in, represents the nth action state, where n represents the number of action states; A5: Starting from the first action state of the preprocessed action sequence data, check the two adjacent action states in sequence and ; If two adjacent action states are different, it is determined that a state transition has occurred, that is, from one action state to another Transfer to another action state ; A6: Use the initialized counter to count the number of state transitions in the preprocessed action sequence data to obtain the transition frequency ; A7: By calculating the transfer frequency With Transfer to all non The ratio of the total number of action states itself to obtain the state transition probability ; A8: Create a The state transition probability calculated in A7 is Assign to the matrix to get the action transfer matrix .

3. A real-time monitoring and optimization system for production processes in an intelligent factory according to claim 2, characterized in that: The motion waste analysis module constructs a motion waste analysis model based on the Markov chain theory according to the motion sequence data to identify motion waste, and further includes: A9: According to the properties of the steady-state distribution, establish the Markov chain equilibrium equation and use the linear equation system to solve the Markov chain equilibrium equation to obtain the steady-state distribution vector ; A10: According to the steady-state distribution vector , determine the frequency of occurrence of each action state in the actual production process The frequency of occurrence of each action state is the steady-state probability of each action state ,and ; A11: According to the process requirements of pipe production, set the standard frequency range for each action state , at the same time, set a preset standard threshold for each action state ,in, and Respectively represent the minimum and maximum values ​​of the standard frequency of the i-th action state; A12: For each action state , the action state Frequency of occurrence With standard frequency range Make a comparison; like ,and , then determine the action state There is wasted motion; A13: Feedback the motion waste identification results to the production management system through the data interface.

4. A smart factory production process real-time monitoring and optimization system as claimed in claim 3, characterized in that: The Markov chain equilibrium equation satisfies: The system transitions from all previous action states to the action state The sum of the weighted state transition probabilities is equal to the system being in the action state The steady-state probability of The sum of the steady-state probabilities of the system being in all action states is 1.

5. A real-time monitoring and optimization system for production processes in an intelligent factory as claimed in claim 4, characterized in that: The specific steps of A10 include: A10.1: Obtaining the Steady-State Distribution Vector and the state space of the Markov chain ; A10.2: Traversal The index of each action state in , from the steady-state distribution vector Extract the element value at the corresponding position, and the element value is the steady-state probability of the action state.

6. A smart factory production process real-time monitoring and optimization system as claimed in claim 5, characterized in that: The bottleneck workstation identification module constructs a dynamic bottleneck workstation identification model based on the received motion waste identification results and the process parameters of the pipe forming process collected by the data acquisition module, and quantitatively evaluates the probability of each workstation evolving into a bottleneck workstation at different time nodes, including: B1: Obtaining motion waste identification results and process parameters of the pipe forming process, while simultaneously monitoring the amount of work-in-progress (WIP) accumulation and production efficiency at each workstation in real time; the motion waste identification results include wasteful motions and waste levels; B2: Assign a unique identifier to each workstation, treat each workstation as a queuing system, and the WIP as a customer. Based on the process parameters of the tube forming process and the results of motion waste identification, determine the arrival rate and service rate of each queuing system. The arrival rate is the rate at which the WIP arrives at the workstation; the service rate is the rate at which the workstation processes the WIP. B3: Combine the M / M / 1 model and apply dynamic programming methods to establish a dynamic bottleneck workstation identification model; B4: Integrate the obtained motion waste identification results, pipe forming process parameters, and real-time monitoring of the number of work-in-progress accumulation and production efficiency of each workstation to form pipe fitting data. The pipe fitting data is input into the dynamic bottleneck workstation identification model, and the dynamic bottleneck workstation identification model is used to calculate in real time the probability value of each workstation evolving into a bottleneck workstation at different time nodes.

7. A smart factory production process real-time monitoring and optimization system as claimed in claim 6, characterized in that: The bottleneck workstation identification module constructs a dynamic bottleneck workstation identification model based on the received motion waste identification results and the process parameters of the pipe forming process collected by the data collection module, and quantitatively evaluates the probability of each workstation evolving into a bottleneck workstation at different time nodes, and further includes: B5: Monitor the WIP accumulation quantity and production efficiency of each workstation in real time, and set the WIP accumulation quantity threshold; If the number of work-in-process products accumulated at any workstation exceeds the threshold, and its production efficiency is lower than the demand efficiency of the downstream workstation, the workstation is determined to be the current dynamic bottleneck workstation based on the probability value calculated by the dynamic bottleneck workstation identification model. B6: Output the identification results of dynamic bottleneck workstations in the form of charts and feed them back to the production management system.

8. A smart factory production process real-time monitoring and optimization system as claimed in claim 7, characterized in that: The specific steps of B2 include: B2.1: Develop identifier rules based on the characteristics of the workstations. The identifier rules use a combination of letters and numbers, with letters representing work sections and numbers representing the sequence number of the workstations within the section. B2.2: Assign a unique identifier to each workstation according to the established identifier rules and create a workstation information table; the workstation information table includes the name, function, and identifier information of the workstation; B2.3: Perform concept mapping, treating each workstation as a queuing system, the WIP as the customer, and the processing equipment and operators at the workstation as the service desk. Also, define the queueing rules for the WIP in front of the workstation as first-come, first-served. B2.4: Collect historical data on the arrival of work-in-progress at each workstation during pipe fitting production, record the timestamps of the work-in-progress arrivals, and calculate the time interval between two adjacent work-in-progress arrivals based on the timestamps. ; B2.5: Calculating time intervals Average value , and the average value Find the inverse and get the arrival rate of each queue system ; B2.6: Analyze the results of motion waste identification, evaluate the impact of wasteful motions on the WIP arrival rate, and revise the calculated arrival rate based on the degree of impact; B2.7: Determine the standard processing time for each station based on the process parameters of the pipe forming process , analyze the results of motion waste identification, evaluate the impact of wasteful motion on the efficiency of work-in-process at the workstation, and correct the standard processing time according to the degree of impact to obtain the actual processing time ; B2.8: Yes Find the reciprocal and get the service rate of each queuing system .

9. A smart factory production process real-time monitoring and optimization system as claimed in claim 8, characterized in that: The specific steps of B3 include: B3.1: Determine the decision to be taken in each action state and load the pre-trained M / M / 1 model. At the same time, the obtained arrival rate and service rate As M / M / 1 model parameters; B3.2: Set minimizing the production cycle as the objective function and derive the state transition equation based on the M / M / 1 model and decision rules; B3.3: Based on the objective function and state transition equation, establish the Bellman equation and use the value iteration method to solve the Bellman equation; B3.4: By solving the Bellman equation, we can obtain the optimal decision for each action state, i.e. the optimal strategy. , and obtain the dynamic bottleneck workstation identification model.

Images