Intelligent printing process multi-parameter monitoring and optimizing system

Abstract

The invention belongs to the technical field of printing, and discloses an intelligent printing process multi-parameter monitoring and optimizing system. The method comprises the following steps: acquiring multi-parameter real-time data in a printing process, and constructing a parameter space based on the multi-parameter real-time data; constructing the multi-parameter real-time data into a weighted directed graph, and obtaining a parameter adjustment reference route in the constructed weighted directed graph; an initial solution set is generated in the parameter space, and on the basis of the initial solution set, an optimization algorithm is used for solving to obtain an optimal parameter combination; the parameter adjustment reference route is combined with the optimal parameter combination, and a dynamic adjustment strategy in the printing process is formed and sent to the monitoring optimization terminal; waste can be reduced, and the service life of equipment is prolonged; meanwhile, waste of raw materials is reduced, and waste is reduced.

Description

Technical Field

[0001] The present invention relates to the field of printing technology, and more specifically, to an intelligent printing process multi-parameter monitoring and optimization system. Background Art

[0002] The patent application with the publication number CN117575098A discloses an optimization method for printing parameters on intaglio printing equipment. It randomly generates an initial parameter dataset according to the setting range of printing parameters, encodes the initial parameter dataset using binary coding, and initializes the population. It calculates the fitness corresponding to each chromosome in the initialized population, selects excellent chromosomes in the population as parent generations, performs crossover and mutation operations to obtain a new population, and repeats the selection, crossover, and mutation operations on the new population until the stop condition is met, and outputs the individual with the smallest fitness value as the optimal solution. This printing parameter optimization method has the capabilities of automatic search and global search, automatically optimizes printing parameters, optimizes and adjusts the parameters in the printing process by simulating the evolution process in nature, realizes more precise, stable, and efficient printing control, improves printing quality, and at the same time has strong universality and flexibility.

[0003] However, in the actual printing production process, the printing quality is still affected by many parameters, and there are complex mutual influence relationships among these parameters, which need to be comprehensively weighed and adjusted. However, at present, the parameter adjustment in the printing process mainly relies on the experience of operators, lacks scientific optimization methods, and it is difficult to ensure the stability and consistency of printing quality. At the same time, the printing process is a dynamically changing process, and various parameters may fluctuate at any time. If the parameters cannot be monitored in real time and adjusted in time, it will lead to fluctuations in printing quality, produce a large number of defective products and waste products, reduce production efficiency, and increase the waste of energy and raw materials. However, the existing technology lacks a mechanism for real-time monitoring and dynamic adjustment and cannot respond in time to changes in the printing state. In addition, the existing technology mainly relies on manual visual inspection to evaluate printing quality, lacks scientific quantitative indicators, and it is difficult to accurately optimize printing parameters. At the same time, manual inspection has low efficiency, subjectivity, and uncertainty, and cannot ensure the accuracy and consistency of evaluation.

[0004] In view of this, the present invention proposes an intelligent printing process multi-parameter monitoring and optimization system to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above object, the present invention provides the following technical solution: An intelligent printing process multi-parameter monitoring and optimization system, comprising: a space construction module, configured to obtain multi-parameter real-time data in the printing process and construct a parameter space based on the multi-parameter real-time data; A reference route fitting module, which is used to construct a weighted directed graph from multi-parameter real-time data and obtain a parameter adjustment reference route in the constructed weighted directed graph; An optimal solution module, which is used to generate an initial solution set in the parameter space and solve for the optimal parameter combination using an optimization algorithm based on the initial solution set; A strategy adjustment module, which is used to combine the parameter adjustment reference route with the optimal parameter combination to form a dynamic adjustment strategy during the printing process and send it to the monitoring and optimization terminal; each module is connected by wired and / or wireless means.

[0006] Furthermore, the multi-parameter real-time data includes printing machine parameters, printing material parameters, environmental parameters, and production efficiency parameters; The printing machine parameters include printing speed, printing pressure, ink supply, drying temperature, and positioning accuracy; the printing material parameters include paper weight, ink concentration, ink viscosity, and the dosage of auxiliary materials; the environmental parameters include environmental temperature, environmental humidity, and the ventilation volume per unit time of the environment; the production efficiency parameters include the number of products produced per unit time, raw material consumption, scrap rate, and downtime.

[0007] Furthermore, the method for constructing the parameter space includes: Determine the number of dimensions required to construct the parameter space according to the parameters of the multi-parameter real-time data; for each parameter of the multi-parameter real-time data, determine its value range; for continuous parameters, perform discretization processing, that is, equally divide the continuous value range into several discrete values; Combine the value ranges of all parameters in sequence to construct a preliminary parameter space; each combination obtained corresponds to a space point in the preliminary parameter space; mark the feasible solution region of the preliminary parameter space; obtain the final parameter space.

[0008] Furthermore, the method for marking the feasible solution region of the preliminary parameter space includes: Select one from all the dimensions of the preliminary parameter space as the division dimension, and determine several division points on the division dimension; use the division points to divide the preliminary parameter space into several intervals on the division dimension, and perform the Cartesian product of the intervals on the other dimensions except the division dimension with these divided intervals to obtain several subspaces; Preset constraint conditions, and regard the subspace as a two-dimensional plane; represent all constraint conditions as geometric objects in the subspace; for each geometric object, calculate its boundary equation; the boundary equation is a straight line equation passing through a fixed point or a parameter equation of a geometric object; From all dimensions of the subspace, select one as the scanning dimension; traverse all geometric objects, for each geometric object, extract all points on its boundary equation, use these points as event points, record the coordinates of the event points and the geometric objects to which they belong; for each event point, if the event point is the starting point of the boundary equation of a certain geometric object, mark it as a starting point event, if the event point is the ending point of the boundary equation of a certain geometric object, mark it as an ending point event; Sort all event points in ascending order of the coordinate values on the scanning dimension. If more than one event point has the same coordinate value on the scanning dimension, then perform a secondary sort according to the coordinate values of other dimensions; obtain the sorted event point sequence; construct an event queue based on the sorted event point sequence; each element in the event queue contains the coordinates of the event point, the event type, and the geometric object to which it belongs; the event type includes the starting point event and the ending point event; Define a data structure as the active state structure and initialize it to be empty; take out the first event point from the event queue. If the event point is a starting point event, insert the corresponding geometric object into the active state structure. If the event point is an ending point event, delete the corresponding geometric object from the active state structure, and repeat until the event queue is empty; define a scanning line and start scanning from the scanning dimension. During the scanning process, store all geometric objects spanned by the current scanning line in the active state structure. For each point in the subspace, query whether the coordinates of the point in other dimensions except the scanning dimension fall within the intervals in the active state structure. If the coordinates in all dimensions fall within the corresponding intervals, then mark the point as being in the feasible solution region; otherwise, mark the point as being in the infeasible solution region.

[0009] Furthermore, the construction method of the weighted directed graph includes: Initialize a directed graph; regard each parameter in the multi-parameter real-time data as a state variable, the value range of each state variable constitutes the state space of the corresponding state variable, and take the Cartesian product of the state spaces of all state variables as the state space of the entire directed graph; define the state at each time point in the state space of the entire directed graph as a multi-dimensional vector, and each component in the multi-dimensional vector corresponds to the value of a parameter at the corresponding time point; For each time step t, record the current state and the next state ; use a counter to track the number of times of transferring from the state to the next state . Each time an observation of a transfer from the state to the next state is made, increment the counter by 1; Set a Dirichlet prior distribution , is a priori positive vector; for each time step t, obtain the current state from the Dirichlet prior distribution and the corresponding a priori positive vector, denoted as ; Define the prior probability of transferring from the current state to the next state at time step t; where is a preset attenuation factor, and ; Based on the prior probability, for the current state and the next state , define the posterior distribution ; where is the transfer probability to be estimated from the current state to the next state ; take the mean of the posterior distribution as the transfer probability of the current state transferring to the next state ; represents the Dirichlet distribution; Create a state transition matrix, where the rows of the state transition matrix represent the current state, the columns of the state transition matrix represent the next state, and the values of the elements of the state transition matrix are the corresponding transfer probabilities; Define the state cost function ; calculate the function value of the state cost function for each state, denoted as the cost value; in the directed graph, define the nodes to represent the states, and if there is a non-zero transfer probability between two states, then connect a directed edge and between the corresponding two nodes ; define the weight of the corresponding directed edge ; where is the transfer probability between the two states corresponding to the two nodes and ; is the cost value of the state corresponding to the node , is the cost value of the state corresponding to the node ; is the balance coefficient, and ; thus, the weighted directed graph G is obtained.

[0010] Furthermore, the formula of the state cost function is: ; where , , , and are the corresponding weight coefficients; is the production efficiency index; is the energy consumption; is the printing contrast, is the printing color deviation; is the raw material utilization rate; ; where is the number of color channels to be considered; is the th weight of the color channel; is the th actual value of the th color channel in state is the th target value of the th color channel in state ; where is the reference target value; is the ink concentration or color concentration in state ; is the th standard deviation of the th color channel in state , and are correction parameters.

[0011] Furthermore, the method for obtaining the parameter adjustment reference route includes: Based on the original weighted directed graph G, create a new extended graph G'. Define a source point s and a sink point e on the extended graph G'. They are respectively connected to all nodes with in-degree 0 and out-degree 0 in the weighted directed graph G. For each node u with in-degree 0 in G, connect a directed edge with weight 0 from the source point s to u in G'. For each node v with out-degree 0 in G, connect a directed edge with weight 0 from v to the sink point e in G'; For each node u in G', define its node label q(u) as the length of the longest path from u to the sink node e; define a queue, add all nodes with in-degree 0 to the queue, initialize the values of their node labels to 0, and then continuously take out the node v with in-degree 0 from the queue. For each predecessor node v' of v, calculate its node label q(v') = max(q(v'), q(v) + w(v', v)); where w(v', v) is the weight of the directed edge from v' to v, until the values of the node labels of all nodes are calculated; based on the calculated node labels, calculate the net weight for each edge in G'. The calculation formula for the net weight is as follows: ; where is the net weight of the directed edge between node u and node v, is the weight of the directed edge between node u and node v; is node to the length of the longest path of the sink node e; Use Dijkstra's algorithm in G' starting from the source node s to find a path P from the source node s to the sink node e, where the sum of the net weights of the edges is equal to ; The path P contains a sequence of nodes in G' forming a sequence, denoted as the node sequence; project this node sequence back to the original weighted directed graph G, that is, obtain a path in G, and the corresponding series of states of this path are the parameter adjustment reference route.

[0012] Furthermore, the step of generating the initial solution set in the parameter space is as follows: Step 1: Discretize the parameter space, divide the value range of each parameter into discrete values, that is, the parameter space is divided into small grids; is the dimensionality of the parameter space; is an integer greater than 1; Step 2: Initialize a dimensional boolean matrix A, and set the initial values of all elements in the boolean matrix A to 0; Step 3: Randomly select a small grid, set the corresponding element in the boolean matrix A to 1, and use it as the initial solidified area; randomly select a dimension in all dimensions of the parameter space as the expansion direction; in the expansion direction, starting from the boundary of the solidified area, randomly select an adjacent small grid; if the corresponding element in the boolean matrix A of this small grid is 0, it means that this small grid is not occupied, occupy it, and add it to the solidified area; repeat until the solidified area reaches the preset area size threshold M1; obtain the comprehensive solidified area. Step 4: Randomly select a small grid within the comprehensive curing area; set the corresponding element in the Boolean matrix A to 0; repeat until the number of melted ones reaches the preset melting threshold M2, and M2 is less than M1; obtain the initial solution area; the combination of parameters corresponding to the small grids within the initial solution area is an initial solution. Step 5: Repeat Step 3 - 4 until a preset number of initial solutions are generated to form an initial solution set.

[0013] Furthermore, the solution method for the optimal parameter combination includes: Define the optimization function ; where is the registration accuracy score, is the glossiness score of the imprint surface, and are the weight parameters of the corresponding items, and their values are greater than 0 and less than 1; Randomly select N2 initial solutions from the initial solution set to form an initial hunter group, where N2 is the preset number of hunters; perform iterative optimization based on the initial hunter group. For each iteration step of the iterative optimization, calculate the value of the optimization function corresponding to each hunter; record it as the hunting value of the corresponding hunter. Sort the hunters from largest to smallest according to the hunting value, and denote the first n3 hunters as candidate preys, and the remaining hunters as irrelevant hunters; n3 is an integer greater than 1. Calculate the average distance from each candidate prey to all other candidate preys; calculate the difference between the distance from each candidate prey to the hunter and its average distance, and denote it as the hunting difference df; calculate the weight of each candidate prey according to the hunting difference df, and this weight is the hunting difference df divided by the sum of all differences. Take the candidate prey with the largest weight as the tracked prey Y, and calculate the displacement vector V of the hunter X towards the direction of the tracked prey as V = ra×(Y - X); where ra is a random number between (0, 1); update the new position X_new of the hunter X based on the displacement vector V as X_new = X + V. Calculate the hunting value corresponding to the new position X_new. If this hunting value is greater than the hunting value of the original hunter X, then update the position of the hunter X to X_new; obtain the optimal hunter group. Preset the exchange probability PR. Randomly select one irrelevant hunter A from all the irrelevant hunters, and randomly select one hunter B from the hunters after position update. With the probability of PR, use the combination of A and B to form a new hunter C to replace the irrelevant hunter A; repeat until all the remaining irrelevant hunters are replaced to obtain a new generation of hunter groups; merge the optimal hunter group and the new generation of hunter groups to form a new hunter group; repeat to form a new hunter group until the preset maximum number of iterations is reached; select the hunter with the highest hunting value from the final new hunter group, and the combination of its corresponding parameters is the optimal parameter combination obtained by solving.

[0014] Further, the registration accuracy score ; where is the registration error of the th measurement point, is the preset maximum registration error threshold, and are both adjustment parameters greater than 0; is the distance from the th measurement point to the edge of the printed matter; dmax is the maximum value of the distances from all measurement points to the edge of the printed matter; is a penalty coefficient greater than 0; Imprint surface gloss score ; where is the weight of the th measurement point, is the gloss value of the th measurement point, is the gloss gradient value of the th measurement point; is the gradient adjustment parameter, and its value is greater than or equal to 0; is the distribution penalty coefficient, and ; is the standard deviation of the gloss values of all measurement points; is the preset reference gloss standard deviation.

[0015] Technical effects and advantages of a multi-parameter monitoring and optimization system for an intelligent printing process according to the present invention: The present invention realizes the intelligence and automation of the printing process, greatly reduces the uncertainty and subjectivity of manual operations, and ensures the stability and consistency of printing quality; through real-time monitoring and dynamic adjustment, it can adaptively respond to changes in the printing state, correct deviations in a timely manner, eliminate fluctuations, greatly reduce the production of defective and waste products, and improve the qualified product rate; secondly, by using scientific optimization algorithms and quantitative evaluation indicators, it can search for the global optimal solution in the high-dimensional solution space of multi-parameters, realize the precise optimization of printing parameters, fully explore the performance potential of printing equipment, maximize the improvement of printing quality, and make various indicators such as the clarity, contrast, and color reproduction of printed matter reach the ideal level; in addition, through parameter optimization, it can effectively reduce the energy consumption and raw material consumption in the printing process, improve the resource utilization efficiency; the optimized parameter combination can reduce waste and extend the service life of the equipment; at the same time, reduce the waste of raw materials and the generation of waste, thereby reducing production costs and achieving a win-win situation of economic and environmental benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of a multi-parameter monitoring and optimization system for an intelligent printing process according to the present invention; Figure 2 Schematic diagram of a multi-parameter monitoring and optimization method for an intelligent printing process of the present invention. Specific implementation manners

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment 1 Please refer to Figure 1 As shown, a multi-parameter monitoring and optimization system for an intelligent printing process in this embodiment includes: A space construction module, configured to obtain real-time multi-parameter data during the printing process and construct a parameter space based on the real-time multi-parameter data; A reference route fitting module, configured to construct the real-time multi-parameter data into a weighted directed graph, and obtain a parameter adjustment reference route in the constructed weighted directed graph; An optimal solution module, configured to generate an initial solution set in the parameter space and solve for the optimal parameter combination using an optimization algorithm based on the initial solution set; A strategy adjustment module, configured to combine the parameter adjustment reference route with the optimal parameter combination to form a dynamic adjustment strategy during the printing process and send it to the monitoring and optimization terminal; each module is connected by wired and / or wireless means to achieve data transmission between modules.

[0019] The real-time multi-parameter data includes printing machine parameters, printing material parameters, environmental parameters, and production efficiency parameters; the printing machine parameters include printing speed, printing pressure, ink supply amount, drying temperature, and positioning accuracy (the offset degree of the printed image relative to the paper edge, which affects the appearance effect of the printed matter), and are obtained by real-time monitoring through various sensors installed on the printing machine, such as encoders, pressure sensors, flow meters, etc.

[0020] The printing material parameters include paper weight, ink concentration, ink viscosity, and the usage amounts of auxiliary materials (such as curing agents, thickeners, etc.); the ink concentration and viscosity can be obtained by real-time measurement using an on-line color densitometer and a viscometer.

[0021] The environmental parameters include ambient temperature, ambient humidity, and the ventilation volume per unit time of the environment; the production efficiency parameters include the production quantity per unit time, raw material consumption, scrap rate, and downtime; the production quantity per unit time is obtained by real-time statistics using a counter or an encoder; the raw material consumption is obtained by real-time monitoring using a flow meter or a weighing sensor; the scrap rate is obtained by real-time statistics through manual inspection; the downtime is obtained by real-time recording using a timer or an encoder.

[0022] The methods for constructing the parameter space include: Based on the parameters of the multi-parameter real-time data (such as printing speed, printing pressure, ink supply volume, etc.), determine the number of dimensions required for constructing the parameter space; for each parameter (data type) of the multi-parameter real-time data, determine its value range; for example, the printing speed may be between 1000 - 5000 sheets per minute, and the printing pressure may be between 50 - 200 N, etc.; for continuous parameters, perform discretization processing on them, that is, divide the continuous value range into several discrete values; for example, the printing speed may be a continuous value.

[0023] Combine the value ranges of all parameters in sequence to construct a preliminary parameter space; each obtained combination corresponds to a space point in the preliminary parameter space; due to possible mutual constraint relationships between different parameters, some parameter combinations may be infeasible. According to the actual process limitations, mark the feasible solution region of the preliminary parameter space; obtain the final parameter space.

[0024] Specifically, select one from all the dimensions of the preliminary parameter space as the partitioning dimension. On the partitioning dimension, determine several partition points, which can be selected according to heuristic strategies such as equal division, density-based, etc.; use the partition points to divide the preliminary parameter space into several intervals on the partitioning dimension, and perform the Cartesian product of the intervals on other dimensions except the partitioning dimension with these divided intervals to obtain several subspaces.

[0025] Preset constraint conditions. Specifically, the constraint conditions are parameterized according to specific printing processes, equipment, materials, and quality requirements; the constraint conditions are equations, inequalities, logical expressions, etc. between parameters; regard the subspace as a two-dimensional plane (coordinate system); represent all constraint conditions as geometric objects (such as line segments, polygons, etc.) in the subspace; for each geometric object, calculate its boundary equation; the boundary equation is a straight line equation passing through a fixed point or a parametric equation of a geometric object.

[0026] Select one from all the dimensions of the subspace as the scanning dimension; traverse all geometric objects. For each geometric object, extract all the points on its boundary equation, regard these points as event points, and record the coordinates of the event points and the geometric objects to which they belong.

[0027] For each event point, if the event point is the starting point of the boundary equation of a geometric object, it is marked as a starting event; if the event point is the ending point of the boundary equation of a geometric object, it is marked as an ending event. All event points are sorted in ascending order according to their coordinate values in the scanning dimension. If more than one event point has the same coordinate value in the scanning dimension, secondary sorting is performed according to the coordinate values in other dimensions, obtaining a sorted sequence of event points. Based on the sorted sequence of event points, an event queue is constructed. Each element in the event queue contains the coordinates of the event point, the event type, and the geometric object to which it belongs. The event types include starting events and ending events.

[0028] Define a data structure as the active state structure, such as a red-black tree, a segment tree, etc., and initialize this data structure to be empty. Take the first event point from the event queue. If the event point is a starting event, insert the corresponding geometric object into the active state structure; if the event point is an ending event, delete the corresponding geometric object from the active state structure, and repeat until the event queue is empty.

[0029] Define a scanning line and start scanning from the scanning dimension. During the scanning process, store all the geometric objects crossed by the current scanning line in the active state structure. For each point in the subspace, query whether the coordinates of the point in the dimensions other than the scanning dimension fall within the intervals in the active state structure. If the coordinates in all dimensions fall within the corresponding intervals, the point is located in the feasible solution region and is marked as the feasible solution region; otherwise, the point is located in the infeasible solution region and is marked as the infeasible solution region. Construct the corresponding parameter space based on the multi-parameter real-time data to prepare for subsequent optimization calculations. The finer the parameter space, the better the optimization effect may be, but more computing resources are also required.

[0030] The construction method of the weighted directed graph includes: Initialize a directed graph. Consider each parameter in the multi-parameter real-time data as a state variable. The value range of each state variable constitutes the state space of the corresponding state variable. Take the Cartesian product of the state spaces of all state variables as the state space of the entire directed graph. Define the state at each time point in the state space of the entire directed graph as a multi-dimensional vector, and each component in the multi-dimensional vector corresponds to the value of a parameter at the corresponding time point.

[0031] For each time step t, record the current state and the next state ; Use a counter to track the number of times of transferring from the state to the next state . Each time an observation of a transfer from the state to the next state Upon the transfer, increment the counter by 1.

[0032] Set a Dirichlet prior distribution , where is a prior positive vector reflecting the prior knowledge of the state transition probability; specifically, cluster the multi-dimensional parameter data at the current time step to obtain several clusters, each cluster representing a parameter state, count the transition frequencies from each cluster to other clusters, and normalize these transition frequencies as the prior positive vector corresponding to the state; the Dirichlet prior distribution is a matrix distributed according to time steps, which contains each state and its corresponding positive vector.

[0033] For each time step t, obtain the current state and the corresponding prior positive vector from the Dirichlet prior distribution , denoted as ; define the prior probability of transferring from the current state to the next state at time step t; where is a preset attenuation factor, and ; newly observed transfers have a greater impact on prior knowledge.

[0034] Based on the prior probability, for the current state and the next state , define the posterior distribution ; where is the transfer probability to be estimated from the current state to the next state ; take the mean of the posterior distribution as the transfer probability of the current state transferring to the next state ; represents the Dirichlet distribution.

[0035] Create a state transition matrix, where the rows of the state transition matrix represent the current state, the columns of the state transition matrix represent the next state, and the values of the elements of the state transition matrix are the corresponding transfer probabilities; Define the state cost function ; ; where , , , and are the corresponding weight coefficients, reflecting the importance of each cost function; is the production efficiency index, specifically the number of products produced per unit time, obtained by multiplying the printing speed by the actual running time ratio; is the energy consumption, which is the sum of the electrical energy consumption and other energy consumptions; the electrical energy consumption is the power multiplied by the running time, and the power and other energy consumptions can be modeled and measured according to the parameters set under the corresponding conditions, such as printing speed, temperature, etc.; is the printing contrast ratio (the ratio between the maximum brightness value and the minimum brightness value), is the printing color deviation; is the raw material utilization rate. Specifically, the raw material utilization rate is the actual output quantity divided by the sum of the theoretical output quantity and the waste quantity; the theoretical output quantity is the quantity that should be output under the corresponding conditions in an ideal situation; the waste quantity is the quantity of waste products generated during the actual production process.

[0036] ; among them, is the number of color channels to be considered, usually 3 (RGB) or 4 (CMYK); is the th weight of the color channel, reflecting the importance of this channel to the overall color; is the actual value of the th color channel under the state , is the target value of the th color channel under the state ; ; Among them, is the reference target value, which can be a standard color value, such as RGB(255, 255, 255) representing pure white, or a theoretical target value set according to the types and concentrations of inks used, etc.; is the ink concentration or color concentration under the state ; is the standard deviation of the th color channel under the state ; , and are correction parameters, fitted according to the measured data; they can effectively eliminate the color deviation caused by changes in environmental and material conditions.

[0037] Calculate the function value of the state cost function for each state, denoted as the cost value, representing the quality of this state; in a directed graph, define nodes to represent states. If there is a non - zero transition probability between two states, then connect a directed edge and between the corresponding two nodes ; define the weight of the corresponding directed edge ; among them, is for the two nodes and the transition probability between two corresponding states; is the cost value of the state corresponding to node ; is the cost value of the state corresponding to node ; is the balance coefficient, and , which is used to balance the influence degrees of the transition probability and the cost value; thus, a weighted directed graph G is obtained.

[0038] The method for obtaining the parameter adjustment reference route includes: Based on the original weighted directed graph G, a new extended graph G' is created. A source point s and a sink point e are defined on the extended graph G', and they are respectively connected to all the nodes with in-degree 0 and out-degree 0 in the weighted directed graph G; for each node u with in-degree 0 in G, a directed edge with a weight of 0 is connected from the source point s to u in G', and for each node v with out-degree 0 in G, a directed edge with a weight of 0 is connected from v to the sink point e in G'; for a node u, the number of directed edges starting from the node u is called the out-degree of the node, and the number of directed edges pointing to the node u is called the in-degree of the node.

[0039] For each node u in G', its node label q(u) is defined as the length of the longest path from u to the sink point e; a queue is defined, and all the nodes with in-degree 0 (including e) are added to the queue, and the values of their node labels are initialized to 0. Then, the node v with in-degree 0 is continuously taken out from the queue, and for each predecessor node v' of v, its node label q(v') = max(q(v'), q(v) + w(v', v)) is calculated; more specifically, for each node u, a predecessor node is maintained, which records who the previous node of u is on the shortest path from the starting point to u; by continuously tracking the predecessor nodes, the shortest path from the starting point to any node can be reconstructed; where w(v', v) is the weight of the directed edge from v' to v (inherited from the weighted directed graph G), until the values of the node labels of all nodes are calculated; based on the calculated node labels, the net weight of each edge in G' is calculated.

[0040] It should be explained that G' not only includes the source point s, the sink point e, and the nodes connected to them, but also includes the topological structure of the original weighted directed graph G.

[0041] The calculation formula for the net weight is: ; where, is the net weight of the directed edge between node u and node v, is the weight of the directed edge between node u and node v (inherited from the weighted directed graph G); is the length of the longest path from the node to the sink node e.

[0042] Using the Dijkstra algorithm in G', starting from the source node s, find a path P from the source node s to the sink node e, where the sum of the net weights of the edges is equal to ; The path P contains a sequence of nodes in G', denoted as the node sequence; Project this node sequence back to the original weighted directed graph G, and a path in G is obtained. The corresponding series of states of this path are the parameter adjustment reference route.

[0043] The steps to generate the initial solution set in the parameter space are as follows: Step 1: Discretize the parameter space. Divide the value range of each parameter into discrete values, that is, the parameter space is divided into small grids (hypercubes); is the number of dimensions of the parameter space; is an integer greater than 1.

[0044] Step 2: Initialize a -dimensional boolean matrix A, and set the initial value of all elements in the boolean matrix A to 0.

[0045] Step 3: Randomly select a small grid, set the corresponding element in the boolean matrix A to 1, and use it as the initial solidified area; Randomly select one dimension in all dimensions of the parameter space as the expansion direction ( expansion directions); In the expansion direction, starting from the boundary of the solidified area, randomly select an adjacent small grid; If the corresponding element in the boolean matrix A of this small grid is 0, it means that this small grid is not occupied, occupy it (set the element to 1), and add it to the solidified area; Repeat until the solidified area reaches the preset area size threshold M1; Obtain the comprehensive solidified area.

[0046] Step 4: Randomly select a small grid within the comprehensive solidified area; Melt it, that is, set the corresponding element in the boolean matrix A to 0; Repeat until the number of melted reaches the preset melting threshold M2, and M2 is less than M1; Obtain the initial solution area; The combination of parameters corresponding to the small grids within the initial solution area is an initial solution.

[0047] Step 5: Repeat steps 3-4 until the preset number of initial solutions are generated to form the initial solution set.

[0048] The solution methods for the optimal parameter combination include: Define the optimization function ; where, is the registration accuracy score, is the imprint surface glossiness score, and are the weight parameters of the corresponding items, and their values are greater than 0 and less than 1; Registration accuracy score ; where is the registration error of the th measurement point, is the preset maximum registration error threshold, and are both adjustment parameters greater than 0; is the th distance from the measurement point to the edge of the printed matter; dmax is the maximum value of the distances from all measurement points to the edge of the printed matter; is a penalty coefficient greater than 0, used to adjust the penalty degree.

[0049] Imprint surface gloss score ; where is the weight (preset) of the th measurement point, reflecting the importance of this point to the overall gloss, is the gloss value of the th measurement point, is the gloss gradient value of the th measurement point, reflecting the change rate of the gloss near this point; is the gradient adjustment parameter, and its value is greater than or equal to 0; when the gloss gradient value is large, increasing the weight of the area with drastic gloss change can increase the weight of the gloss transition area; is the distribution penalty coefficient, and ; is the standard deviation of the gloss values of all measurement points, reflecting the degree of dispersion of the gloss distribution; is the preset reference gloss standard deviation.

[0050] Randomly select N2 initial solutions from the initial solution set to form an initial hunter group, where N2 is the preset number of hunters; based on the initial hunter group, perform iterative optimization. For each iteration step of the iterative optimization, calculate the value of the optimization function corresponding to each hunter (combination of parameters); denote it as the hunting value of the corresponding hunter.

[0051] Sort the hunters from largest to smallest according to the hunting value, and denote the first n3 hunters as candidate prey, and the remaining hunters as irrelevant hunters; n3 is an integer greater than 1; calculate the average distance from each candidate prey to all other candidate preys, and the average distance is the average of the differences in hunting values; calculate the difference between the distance from each candidate prey to the hunter (difference in hunting values) and its average distance, and denote it as the hunting difference df; calculate the weight of each candidate prey according to the hunting difference df, and this weight is the hunting difference df divided by the sum of all differences.

[0052] Take the candidate prey with the largest weight as the tracked prey Y, and calculate the displacement vector V of hunter X towards the direction of the tracked prey: V = ra × (Y - X); where ra is a random number between (0, 1); update the new position of hunter X based on the displacement vector V: X_new = X + V; calculate the hunting value corresponding to the new position X_new. If this hunting value is greater than the hunting value of the original hunter X, then update the position of hunter X to X_new; obtain the optimal hunter group.

[0053] Preset an exchange probability PR. Randomly select one irrelevant hunter A from all the irrelevant hunters, and randomly select one hunter B from the hunters after position update. With a probability of PR, form a new hunter C using the combination of A and B to replace the irrelevant hunter A; repeat until all the remaining irrelevant hunters are replaced, obtaining a new generation of hunter groups.

[0054] Merge the optimal hunter group and the new generation of hunter groups to form a new hunter group; repeat to form a new hunter group until the preset maximum number of iterations is reached; from the final new hunter group, select the hunter with the highest hunting value, and the combination of its corresponding parameters is the optimal parameter combination obtained by the solution.

[0055] In the above process, it is necessary to encode the combination of parameters. In addition, some hyperparameters need to be set and tuned through cross-validation; perform an efficient global search in the solution space to avoid falling into local optima, thereby finding the global optimal solution.

[0056] The optimal parameter combination corresponds to a point (multi-dimensional vector) in the parameter space. On the parameter adjustment reference route, find the node (state) closest to the optimal parameter combination, denoted as node S*. Calculate the Euclidean distance dist (between vectors) between the optimal parameter combination and the state corresponding to node S*. If dist is less than the preset distance threshold, then take S* as the starting point; otherwise, add the optimal parameter combination as a new starting point to the parameter adjustment reference route; starting from the starting point, along the parameter adjustment reference route, determine the combination of parameters at each time step to form a state sequence; for the state at each time step of the state sequence, calculate the cost value of this state according to the established state cost function; set two cost thresholds, namely the ideal cost threshold and the warning cost threshold, and the ideal cost threshold is less than the warning cost threshold. If the cost value of the current state is lower than the ideal cost threshold, then maintain the current state and enter the next time step; if the cost value of the current state is higher than the warning cost threshold, then according to the previously established weighted directed graph, find a new optimal path to transfer to a new state as the state of the next time step; if the cost value of the current state is between the ideal cost threshold and the warning cost threshold, then there is a certain probability (preset) to transfer to a new state, and the new state is determined by the previous weighted directed graph, which is the dynamic adjustment strategy.

[0057] During the printing process, the current printing parameter data is monitored in real time and mapped to the corresponding state. If the current state deviates from the expected state of the dynamic adjustment strategy, the corresponding parameters are automatically adjusted according to the rules of the dynamic adjustment strategy to gradually return to the trajectory of the expected state sequence.

[0058] While maintaining the overall adjustment direction, it also has a certain degree of self - adaptability and robustness, and can make dynamic adjustments according to the real - time state, thereby improving the stability of the printing process and product quality. At the same time, two thresholds, namely ideal and warning, are set. When the cost value is within a reasonable range, a certain inertia is maintained to avoid overly frequent parameter adjustments.

[0059] In this embodiment, the intelligence and automation of the printing process are realized, greatly reducing the uncertainty and subjectivity of manual operations, and ensuring the stability and consistency of printing quality. Through real - time monitoring and dynamic adjustment, it can adaptively respond to changes in the printing state, correct deviations in a timely manner, eliminate fluctuations, greatly reduce the generation of defective and waste products, and improve the qualified product rate. Secondly, by adopting scientific optimization algorithms and quantitative evaluation indicators, it can search for the global optimal solution in the high - dimensional solution space of multiple parameters, realize the precise optimization of printing parameters, fully tap the performance potential of printing equipment, maximize the improvement of printing quality, and make various indicators such as the clarity, contrast, and color restoration degree of printed matter reach the ideal level. In addition, through parameter optimization, the energy consumption and raw material consumption in the printing process can be effectively reduced, and the resource utilization efficiency can be improved. The optimized parameter combination can reduce waste and extend the service life of the equipment. At the same time, it reduces the waste of raw materials and the generation of waste, thereby reducing production costs and achieving a win - win situation of economic and environmental benefits.

[0060] Embodiment 2 Please refer to Figure 2 As shown, for the parts not described in detail in this embodiment, refer to the description content of Embodiment 1. A multi - parameter monitoring and optimization method for an intelligent printing process is provided, including: S1. Obtain the multi - parameter real - time data during the printing process and construct a parameter space based on the multi - parameter real - time data; S2. Construct the multi - parameter real - time data into a weighted directed graph, and in the constructed weighted directed graph, obtain the parameter adjustment reference route; S3. Generate an initial solution set in the parameter space, and use an optimization algorithm to solve for the optimal parameter combination based on the initial solution set; S4. Combine the parameter adjustment reference route with the optimal parameter combination to form a dynamic adjustment strategy in the printing process and send it to the monitoring and optimization terminal.

[0061] Embodiment 3 This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the operation mode of the above-provided multi-parameter monitoring and optimization method for an intelligent printing process.

[0062] Since the electronic device introduced in this embodiment is the electronic device adopted for implementing a multi-parameter monitoring and optimization method for an intelligent printing process in an embodiment of the present application, based on the multi-parameter monitoring and optimization method for an intelligent printing process introduced in an embodiment of the present application, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in an embodiment of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device adopted for a multi-parameter monitoring and optimization method for an intelligent printing process in an embodiment of the present application, it falls within the scope of protection of the present application.

[0063] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0064] The above is only the preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the concept of the present invention belong to the protection scope of the present invention. It should be noted that for ordinary technical users in the technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. An intelligent printing process multi-parameter monitoring and optimization system, characterized in that: include: A space construction module is used to obtain multi-parameter real-time data during the printing process and construct a parameter space based on the multi-parameter real-time data; A reference route fitting module is used to construct multi-parameter real-time data into a weighted directed graph, and obtain a parameter adjustment reference route in the constructed weighted directed graph; The optimal solution module is used to generate an initial solution set in the parameter space, and obtain the optimal parameter combination by using an optimization algorithm based on the initial solution set; The strategy adjustment module is used to combine the parameter adjustment reference route with the optimal parameter combination to form a dynamic adjustment strategy in the printing process and send it to the monitoring optimization terminal; each module is connected by wired and / or wireless means.

2. According to claim 1, the intelligent printing process multi-parameter monitoring and optimization system is characterized in that: The multi-parameter real-time data includes printing machine parameters, printing material parameters, environmental parameters and production efficiency parameters; Printing machinery parameters include printing speed, printing pressure, ink supply, drying temperature and positioning accuracy; printing material parameters include paper weight, ink concentration, ink viscosity and the amount of auxiliary materials used; environmental parameters include ambient temperature, ambient humidity and ambient ventilation volume per unit time; production efficiency parameters include production quantity per unit time, raw material consumption, scrap rate and downtime.

3. The intelligent printing process multi-parameter monitoring and optimization system according to claim 2 is characterized in that: The method of constructing the parameter space includes: According to the parameters of the multi-parameter real-time data, the number of dimensions required to construct the parameter space is determined; for each parameter of the multi-parameter real-time data, its value range is determined; for continuous parameters, they are discretized, that is, the continuous value range is equally divided into several discrete values; The value ranges of all parameters are combined in sequence to construct a preliminary parameter space; each obtained combination corresponds to a spatial point in the preliminary parameter space; the feasible solution area of ​​the preliminary parameter space is marked; and the final parameter space is obtained.

4. The intelligent printing process multi-parameter monitoring and optimization system according to claim 3 is characterized in that: The method of marking the feasible solution region in the preliminary parameter space includes: From all the dimensions of the preliminary parameter space, one is selected as a partition dimension, and several partition points are determined on the partition dimension; the preliminary parameter space is partitioned into several intervals on the partition dimension by the partition points, and the intervals on other dimensions except the partition dimension are subjected to Cartesian products with the intervals obtained by the partitions to obtain several subspaces; Preset constraints and regard the subspace as a two-dimensional plane; express all constraints as geometric objects in the subspace; for each geometric object, calculate its boundary equation; the boundary equation is the equation of the line passing through the fixed point or the parametric equation of the geometric object; From all dimensions of the subspace, select one as the scanning dimension; traverse all geometric objects, and for each geometric object, extract all points on its boundary equation, take these points as event points, and record the coordinates of the event points and the geometric objects they belong to; for each event point, if the event point is the starting point of the boundary equation of a geometric object, mark it as a starting point event; if the event point is the end point of the boundary equation of a geometric object, mark it as an end point event; All event points are sorted from small to large according to the coordinate values ​​on the scanning dimension. If more than one event point has the same coordinate value on the scanning dimension, secondary sorting is performed according to the coordinate values ​​of other dimensions; a sorted event point sequence is obtained; an event queue is constructed based on the sorted event point sequence; each element in the event queue contains the coordinates of the event point, the event type, and the geometric object to which it belongs; the event type includes the start event and the end event; Define a data structure as the active state structure and initialize the data structure to be empty; take the first event point from the event queue. If the event point is a starting event, insert the corresponding geometric object into the active state structure; if the event point is an end event, delete the corresponding geometric object from the active state structure, and repeat until the event queue is empty; define a scan line and start scanning from the scan dimension. During the scanning process, store all geometric objects spanned by the current scan line in the active state structure. For each point in the subspace, query whether the coordinates of the point in dimensions other than the scan dimension fall within the interval in the active state structure. If the coordinates in all dimensions fall within the corresponding interval, mark the point in the feasible solution area; otherwise, mark the point in the infeasible solution area.

5. The intelligent printing process multi-parameter monitoring and optimization system according to claim 4, characterized in that: The weighted directed graph is constructed in the following manner: Initialize a directed graph; regard each parameter in the multi-parameter real-time data as a state variable, the value range of each state variable constitutes the state space of the corresponding state variable, and the Cartesian product of the state spaces of all state variables is used as the state space of the entire directed graph; define the state of each time point in the state space of the entire directed graph as a multidimensional vector, and each component in the multidimensional vector corresponds to the value of a parameter at the corresponding time point; For each time step t, record the current state and the next state ; Use a counter To track the status Transition to next state The number of times, each time it is observed from the state To the next state If the transfer is made, the counter is increased by 1; Set a Dirichlet prior distribution , is a prior positive vector; for each time step t, from the Dirichlet prior distribution Get the current status And the corresponding prior positive vector, denoted as ; Defined at time step t, from the current state Transition to next state The prior probability ;in, is the preset attenuation factor, and ; Based on the prior probability, for the current state and the next state , define the posterior distribution ;in, That is, the current state to be estimated Transition to next state The transition probability; take the mean of the posterior distribution as the current state Transfer to next state The transition probability of represents Dirichlet distribution; Create a state transfer matrix. The rows of the state transfer matrix represent the current state, the columns of the state transfer matrix represent the next state, and the values ​​of the elements of the state transfer matrix are the corresponding transition probabilities. Define the state cost function ; Calculate the function value of the state cost function of each state, recorded as the cost value; In the directed graph, define the node to represent the state. If there is a non-zero transition probability between two states, then the corresponding two nodes and There is a directed edge between ; Define the corresponding directed edge Weight ;in, For two nodes and The transition probability between the two corresponding states; For Node The cost value of the corresponding state, For Node The cost value of the corresponding state; is the balance coefficient, and ; Then the weighted directed graph G is obtained.

6. The intelligent printing process multi-parameter monitoring and optimization system according to claim 5, characterized in that: The state cost function The formula is: ； in, , , , and is the corresponding weight coefficient; It is an indicator of production efficiency; For energy consumption; is the printing contrast, For printing color deviation; is the raw material utilization rate; ;in, is the number of color channels to be considered; For the The weights of the color channels; For the status Next, The actual value of each color channel, For the status Next, Target value for each color channel; ； in, is the benchmark target value; Status The ink concentration or color density under Status Next, The standard deviation of each color channel; , and To correct the parameters.

7. The intelligent printing process multi-parameter monitoring and optimization system according to claim 6, characterized in that: The method for obtaining the parameter adjustment reference route includes: On the basis of the original weighted directed graph G, create a new extended graph G', define a source point s and a sink point e on the extended graph G', which are connected to all nodes with in-degree 0 and out-degree 0 in the weighted directed graph G respectively; for each in-degree 0 node u in G, connect a directed edge with weight 0 from the source point s to u in G', and for each out-degree 0 node v in G, connect a directed edge with weight 0 from v to the sink point e in G'; For each node u in G', define its node label q(u) as the longest path length from u to the sink e; define a queue, add all nodes with in-degree 0 to the queue, initialize their node labels to 0, and then continuously take out nodes v with in-degree 0 from the queue, and for each predecessor node v' of v, calculate its node label q(v')=max(q(v'), q(v)+w(v', v)); where w(v', v) is the weight of the directed edge from v' to v, until the values ​​of the node labels of all nodes are calculated; based on the calculated node labels, calculate the net weight of each edge in G'; The net weight is calculated as: ;in, is the net weight of the directed edge between node u and node v, is the weight of the directed edge between node u and node v; For Node The longest path length to the sink e; Use Dijkstra's algorithm to find a line from source point s to sink point e in G', where the sum of the net weights of the edges is equal to Path P; Path P contains a series of nodes in G' to form a sequence, recorded as a node sequence; This node sequence is projected back to the original weighted directed graph G, that is, a path in G is obtained, and the series of states corresponding to the path are the parameter adjustment reference route.

8. The intelligent printing process multi-parameter monitoring and optimization system according to claim 7, characterized in that: The steps of generating an initial solution set in the parameter space are: Step 1: Discretize the parameter space and divide the value range of each parameter into discrete values, that is, the parameter space is divided into A small grid; is the dimension of the parameter space; is an integer greater than 1; Step 2: Initialize a dimensional Boolean matrix A, set the initial values ​​of all elements in the Boolean matrix A to 0; Step 3: randomly select a small grid, set the element in the Boolean matrix A corresponding to it to 1, and use it as the initial solidification area; randomly select a dimension in all dimensions of the parameter space as the expansion direction; in the expansion direction, starting from the boundary of the solidification area, randomly select an adjacent small grid; if the element corresponding to the small grid in the Boolean matrix A is 0, it means that the small grid is not occupied, occupy it, and add it to the solidification area; repeat until the solidification area reaches the preset area size threshold M1; obtain the comprehensive solidification area; Step 4, randomly select a small grid in the comprehensive solidification area; set the corresponding element in the Boolean matrix A to 0; repeat until the amount of melting reaches the preset melting threshold M2, and M2 is less than M1; obtain the initial solution area; the combination of parameters corresponding to the small grid in the initial solution area is an initial solution; Step 5: Repeat steps 3-4 until a preset number of initial solutions are generated to form an initial solution set.

9. The intelligent printing process multi-parameter monitoring and optimization system according to claim 8, characterized in that: The method for solving the optimal parameter combination includes: Defining the optimization function ;in, Score the registration accuracy, Score the glossiness of the impression surface. and is the weight parameter of the corresponding item, and its value is greater than 0 and less than 1; Randomly select N2 initial solutions from the initial solution set to form an initial hunter group, where N2 is the preset number of hunters; perform iterative optimization based on the initial hunter group, and for each iterative step of iterative optimization, calculate the value of the optimization function corresponding to each hunter; record it as the hunting value of the corresponding hunter; Sort the hunters according to their hunting value from large to small, record the first n3 hunters as candidate prey, and the rest of the hunters as irrelevant hunters; n3 is an integer greater than 1; Calculate the average distance from each candidate prey to all other candidate prey; calculate the difference between the distance from each candidate prey to the hunter and its average distance, recorded as the hunting difference df; calculate the weight of each candidate prey based on the hunting difference df, which is the hunting difference df divided by the sum of all differences; The candidate prey with the largest weight is taken as the tracking prey Y, and the displacement vector V=ra×(YX) of hunter X in the direction of tracking the prey is calculated; where ra is a random number between (0, 1); based on the displacement vector V, the new position X_new=X+V of hunter X is updated; Calculate the hunting value corresponding to the new position X_new. If this hunting value is greater than the hunting value of the original hunter X, update the position of hunter X to X_new. Obtain the optimal hunter group. Preset the exchange probability PR, randomly select one of the irrelevant hunters A from all the irrelevant hunters, randomly select a hunter B from the hunters whose positions are updated, and use the combination of A and B with probability PR to form a new hunter C to replace the irrelevant hunter A; repeat until all the remaining irrelevant hunters are replaced to obtain a new generation of hunters; merge the optimal hunter group with the new generation of hunters to form a new hunter group; repeat the formation of a new hunter group until the preset maximum number of iterations is reached; from the final new hunter group, select the hunter with the highest hunting value, and the corresponding parameter combination is the optimal parameter combination obtained by solving.

10. The intelligent printing process multi-parameter monitoring and optimization system according to claim 9, characterized in that: The registration accuracy score ;in, For the The registration error of each measuring point is is the preset maximum registration error threshold, and All are adjustment parameters greater than 0; For the The distance from each measuring point to the edge of the printed part; dmax is the maximum value of the distance from all measuring points to the edge of the printed part; is a penalty coefficient greater than 0; Imprint surface gloss rating ;in, For the The weight of the measurement points, For the Gloss value of each measuring point, For the Gloss gradient value of each measuring point; is the gradient adjustment parameter, whose value is greater than or equal to 0; is the distribution penalty coefficient, and ; is the standard deviation of the gloss values ​​of all measurement points; is the preset reference gloss standard deviation.

Images