Hot-rolled plate coil multi-process collaborative scheduling method and system based on uncertainty

Abstract

The embodiment of the application discloses a kind of based on uncertainty hot-rolled plate coil multi-process collaborative scheduling method and system, the method includes: the energy coupling relationship model between hot-rolled each process is built, heating, rough rolling, finishing and coiling process are abstracted as node, the directed weighted relationship of energy transmission intensity and delay characteristic is established;Based on the process parameters of real-time acquisition, the energy deviation of each process node is calculated;Propagation attenuation factor and time lag parameter are included in the disturbance propagation function, and energy deviation is introduced into disturbance propagation function as input, to carry out cascading propagation calculation between each process node to the disturbance, obtain the disturbance influence of each process node;Based on the disturbance influence of each process node and current process state, construct multi-process disturbance risk index;The processing order and rhythm of hot-rolled plate coil between each process are dynamically adjusted, realize multi-process collaborative scheduling optimization.The stability and efficiency of the application are improved hot-rolled production.

Description

Technical Field

[0001] This application relates to the field of steel production scheduling technology, and in particular to a method and system for multi-process collaborative scheduling of hot-rolled coils based on uncertainty. Background Technology

[0002] Hot-rolled coil production is one of the core processes in steel enterprises, mainly including multiple steps such as heating furnace, roughing, finishing, and coiling. These steps are closely coupled in terms of energy flow, material flow, and cycle time. In actual production, due to uncertainties such as fluctuations in raw material properties, changes in equipment status, temperature drift, and adjustments to external orders, disturbances between steps can easily propagate, causing problems such as coil quality defects, increased energy consumption, and capacity loss.

[0003] In existing technologies, hot rolling scheduling methods mostly employ static planning, heuristic algorithms, or simple robust optimization models. These methods lack precise quantification of energy deviation as a disturbance source and do not adequately consider the dynamic coupling of energy and the cascading propagation of uncertainties among multiple processes within the hot rolling process.

[0004] Therefore, there is an urgent need for a scheduling method that can accurately capture the propagation law of energy uncertainty, construct multi-process disturbance risk indicators, and achieve dynamic synergistic optimization of processing sequence and rhythm, so as to improve the stability and efficiency of hot rolling production. Summary of the Invention

[0005] This application provides a method and system for multi-process collaborative scheduling of hot-rolled coils based on uncertainty, which improves the stability and efficiency of hot-rolling production.

[0006] This application provides the following solution: According to the first aspect, a multi-process collaborative scheduling method for hot-rolled coils based on uncertainty is provided. The method includes: constructing an energy coupling relationship model between various hot-rolling processes, abstracting heating, roughing, finishing, and coiling processes as nodes, and establishing a directed weighted relationship characterizing energy transfer intensity and delay characteristics; calculating the energy deviation of each process node based on real-time acquired process parameters; constructing a disturbance propagation function including a propagation attenuation factor and a time lag parameter according to the energy coupling relationship model, and introducing the energy deviation as an input into the disturbance propagation function to perform cascade propagation calculation of disturbances between process nodes, thereby obtaining the disturbance impact of each process node; constructing a multi-process disturbance risk index based on the disturbance impact of each process node and the current process state; and dynamically adjusting the processing sequence and rhythm of hot-rolled coils between processes according to the disturbance risk index to achieve multi-process collaborative scheduling optimization.

[0007] According to one achievable method in the embodiments of this application, the weight of each directed edge in the energy coupling relationship model is jointly determined by the energy transfer efficiency between adjacent process nodes and the process cycle matching degree, which is used to characterize the transmission intensity of disturbance between processes.

[0008] According to one achievable method in the embodiments of this application, the energy deviation is the difference between the actual energy input of each process node and the expected energy input calculated based on the target process parameters. The expected energy input is determined by an energy benchmark model based on the plate and coil specification parameters and historical process data.

[0009] According to one achievable method in an embodiment of this application, constructing a disturbance propagation function including a propagation attenuation factor and a time lag parameter based on the energy coupling relationship model includes: extracting directed connection paths between each process node based on the energy coupling relationship model, and obtaining energy coupling strength parameters on the corresponding paths; determining the propagation attenuation factor corresponding to each path based on the energy coupling strength parameters, such that the propagation attenuation factor and the energy coupling strength have an inverse relationship; calculating the propagation time delay of the disturbance on the path based on the cycle time difference between adjacent process nodes, and obtaining the time lag parameter; and introducing the propagation attenuation factor and the time lag parameter into a preset propagation function structure to construct a disturbance propagation function for describing the propagation process of the disturbance along the path.

[0010] According to one achievable method in an embodiment of this application, the preset propagation function structure is a combined function that simultaneously includes a path attenuation term and a time-delay response term, wherein: the path attenuation term is used to characterize the cumulative attenuation effect of the disturbance as the path length increases when it is propagated along multi-level process nodes, and is calculated by weighting the propagation attenuation factors corresponding to each path; the time-delay response term is used to characterize the dynamic delay effect of the disturbance propagation between different process nodes, and the disturbance input is subjected to time-series offset processing based on the time lag parameter; the path attenuation term and the time-delay response term are coupled to form a joint characterization of the disturbance propagation process to obtain the disturbance response results of each process node.

[0011] According to one achievable method in the embodiments of this application, when calculating the cascading propagation of disturbances between process nodes, the disturbance effects from multiple upstream process nodes are comprehensively considered, and the disturbance effect of the target process node is obtained by superposition or weighted fusion.

[0012] According to one achievable method in this application embodiment, the construction of a multi-process disturbance risk index based on the disturbance impact of each process node and the current process state includes: obtaining the disturbance impact of each process node and normalizing the disturbance impact to obtain a standardized disturbance characterization quantity; extracting the current process state parameters of each process node, wherein the process state parameters include at least one of temperature deviation, rolling force fluctuation, or tension stability index, and performing dimensional unification processing on the process state parameters; merging the standardized disturbance characterization quantity and the process state parameters based on a preset coupling mapping relationship to obtain the local risk value of each process node; and weighting and aggregating the local risk values ​​of each process node to obtain a global disturbance risk index characterizing the multi-process collaborative state.

[0013] According to one achievable method in an embodiment of this application, the preset coupling mapping relationship is a piecewise nonlinear mapping relationship, including: when the disturbance influence is lower than a preset disturbance threshold, a first mapping function dominated by process state parameters is used to characterize the dominant role of process state on risk; when the disturbance influence is higher than the preset disturbance threshold, a second mapping function dominated by the disturbance influence is used to characterize the amplification effect of disturbance propagation on risk; wherein, the first mapping function and the second mapping function are continuous at the preset disturbance threshold, and the mapping relationship is continuously switched through a smooth transition function.

[0014] According to one achievable method in this application embodiment, the dynamic adjustment of the processing sequence and rhythm of hot-rolled coils between processes based on the disturbance risk index includes: identifying target process nodes where the disturbance risk index is higher than a preset risk threshold, and determining the corresponding high-risk propagation path; for coil tasks on the high-risk propagation path, performing processing sequence rearrangement so that coil tasks with higher disturbance risk are prioritized or delayed in entering subsequent processes, thereby reducing the cascading amplification effect of disturbances between adjacent processes; adaptively adjusting the processing rhythm of each process node based on the disturbance risk index, by increasing or decreasing the time interval between adjacent processes to suppress the speed of disturbance propagation; after completing the processing sequence rearrangement and rhythm adjustment, updating the disturbance risk index of each process node, and cyclically executing the above adjustment process until the disturbance risk index meets the preset stability condition.

[0015] According to the second aspect, a multi-process collaborative scheduling system for hot-rolled coils based on uncertainty is provided. The system includes: an energy coupling relationship construction unit, configured to construct an energy coupling relationship model between various hot-rolling processes, abstracting heating, roughing, finishing, and coiling processes as nodes, and establishing a directed weighted relationship characterizing energy transfer intensity and delay characteristics; an energy deviation calculation unit, configured to calculate the energy deviation of each process node based on real-time acquired process parameters; a disturbance influence calculation unit, configured to construct a disturbance propagation function including a propagation attenuation factor and a time lag parameter according to the energy coupling relationship model, and introduce the energy deviation as an input into the disturbance propagation function to perform cascade propagation calculation of disturbances between process nodes, obtaining the disturbance influence of each process node; a disturbance risk index construction unit, configured to construct a multi-process disturbance risk index based on the disturbance influence of each process node and the current process state; and a processing sequence rhythm adjustment unit, configured to dynamically adjust the processing sequence and rhythm of hot-rolled coils between processes according to the disturbance risk index, thereby achieving multi-process collaborative scheduling optimization.

[0016] According to the specific embodiments provided in this application, the following technical effects are disclosed: This invention constructs a directed weighted relationship model of energy coupling between hot rolling heating, roughing, finishing, and coiling processes. It uses real-time acquired process parameters to calculate the energy deviation at each process node as a disturbance source, and then constructs a disturbance propagation function including a propagation attenuation factor and a time lag parameter to achieve accurate cascading propagation calculation of uncertainties across multiple processes. Based on this, it integrates the disturbance impact with the current process state to construct a multi-process disturbance risk index, and dynamically adjusts the processing sequence and rhythm of the coil accordingly. This method overcomes the limitation of traditional scheduling methods that insufficiently consider the dynamic propagation characteristics of energy flow, effectively suppressing the cascading amplification effect of uncertainties, significantly improving the collaborative stability and robustness of the hot rolling production process, and ultimately achieving the technical effects of reducing quality defect rate, reducing energy consumption, and improving capacity utilization. It is particularly suitable for real-time optimization scheduling of multiple processes in hot-rolled coils under high uncertainty environments.

[0017] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a system architecture diagram applicable to the embodiments of this application; Figure 2 A flowchart of a multi-process collaborative scheduling method for hot-rolled coils based on uncertainty provided in this application embodiment; Figure 3 A structural block diagram of a multi-process collaborative scheduling system for hot-rolled coils based on uncertainty, provided in an embodiment of this application; Figure 4 A schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0021] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0022] To facilitate understanding of this application, the system architecture on which this application is based will be described first. Figure 1 An exemplary system architecture that can be applied to embodiments of this application is shown, such as Figure 1 As shown, the system architecture may include: user equipment and a non-deterministic multi-process collaborative scheduling system for hot-rolled coils located on the server side.

[0023] Users can input real-time collected process parameters through user equipment, which then sends them to the server-side multi-process collaborative scheduling system for hot-rolled coils based on uncertainty. The multi-process collaborative scheduling system for hot-rolled coils based on uncertainty can employ the method provided in the embodiments of this application to perform multi-process collaborative scheduling. The server can send process adjustment instructions to the user terminal, which then controls the hot-rolling equipment to perform corresponding operations.

[0024] User devices can include, but are not limited to, smart mobile terminals, wearable devices, and PCs (Personal Computers). Smart mobile devices can include devices such as mobile phones, tablets, laptops, and PDAs (Personal Digital Assistants). Wearable devices can include devices such as smartwatches and smart glasses.

[0025] A multi-process collaborative scheduling system for hot-rolled coils based on uncertainty can be configured as a standalone server, a server cluster, or a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a host product within the cloud computing service system, designed to address the management difficulties and weak service scalability inherent in traditional physical hosts and Virtual Private Servers (VPS) services. Besides... Figure 1 In addition to the architecture shown, the multi-process collaborative scheduling system for hot-rolled coils based on uncertainty can also be set up on a computer terminal with strong computing power.

[0026] Figure 2 This application provides a flowchart of a multi-process collaborative scheduling method for hot-rolled coils based on uncertainty, which can be implemented by... Figure 1 The system shown executes a multi-process collaborative scheduling system for hot-rolled coils based on uncertainty. For example... Figure 2 As shown, the method may include the following steps: Step 201: Construct an energy coupling relationship model between various hot rolling processes, abstract the heating, roughing, finishing, and coiling processes as nodes, and establish a directed weighted relationship that characterizes the energy transfer intensity and delay characteristics.

[0027] Step 202: Calculate the energy deviation of each process node based on the real-time acquired process parameters.

[0028] Step 203: Based on the energy coupling relationship model, construct a disturbance propagation function that includes a propagation attenuation factor and a time lag parameter, and introduce the energy deviation as an input into the disturbance propagation function to perform cascade propagation calculation of the disturbance between each process node, so as to obtain the disturbance influence of each process node.

[0029] Step 204: Based on the disturbance impact of each process node and the current process status, construct a multi-process disturbance risk index.

[0030] Step 205: Based on the disturbance risk index, dynamically adjust the processing sequence and rhythm of hot-rolled coils among various processes to achieve multi-process collaborative scheduling optimization.

[0031] As can be seen from the above process, this invention constructs a directed weighted relationship model of energy coupling between hot rolling heating, roughing, finishing, and coiling processes. It uses real-time acquired process parameters to calculate the energy deviation at each process node as a disturbance source, and then constructs a disturbance propagation function including a propagation attenuation factor and a time lag parameter, achieving accurate cascading propagation calculation of uncertainties across multiple processes. Based on this, it integrates the disturbance impact with the current process state to construct a multi-process disturbance risk index, and dynamically adjusts the processing sequence and rhythm of the coil accordingly. This method overcomes the limitation of traditional scheduling methods that do not adequately consider the dynamic propagation characteristics of energy flow. It can effectively suppress the cascading amplification effect of uncertainties, significantly improve the collaborative stability and robustness of the hot rolling production process, and ultimately achieve the technical effects of reducing quality defect rate, reducing energy consumption, and improving capacity utilization. It is particularly suitable for real-time optimization scheduling of multiple processes in hot-rolled coils under high uncertainty environments.

[0032] The following describes in detail each step of the above process and the effects that can be further produced, with reference to the embodiments.

[0033] First, the above step 201, namely "constructing an energy coupling relationship model between various hot rolling processes, abstracting the heating, roughing, finishing, and coiling processes as nodes, and establishing a directed weighted relationship characterizing the energy transfer intensity and delay characteristics", will be described in detail with reference to the embodiments.

[0034] In this invention, constructing an energy coupling relationship model among the various processes in hot rolling is the core foundation of the entire scheduling method. This model takes the energy flow in the hot rolling production process as its starting point, systematically abstracting the heating, roughing, finishing, and coiling processes mathematically, thus providing a unified framework for the subsequent quantification and propagation analysis of uncertainties. Through this model, the interdependence of energy transfer among multiple processes can be clearly depicted, avoiding the problem of insufficient consideration of dynamic coupling between processes in traditional scheduling methods.

[0035] In the model construction process, the heating, roughing, finishing, and coiling processes are first abstracted into independent nodes. These nodes represent various stages in the production process with clearly defined inputs, outputs, and energy conversion functions. Each node carries real-time status information of the current process, including process parameters such as temperature, power consumption, and coil properties. This abstraction simplifies the complex hot rolling production line into a structured network, facilitating subsequent calculations and optimizations, while preserving the physical independence and interrelationships of each process.

[0036] Next, the model establishes a directed weighted relationship characterizing the intensity and delay characteristics of energy transfer. Specifically, each process node is connected by directed edges, pointing from upstream to downstream processes, reflecting the unidirectional transfer direction of energy and material flow. The weight of each directed edge is determined by two key characteristics: first, the intensity of energy transfer, i.e., the efficiency of energy conversion between adjacent processes; and second, the delay characteristic, i.e., the time lag required for energy or disturbance to transfer from one process to the next. This weighted design allows the model to not only reflect the static energy balance relationship but also dynamically capture the cycle time differences and energy losses that exist in actual production.

[0037] For example, the formula for calculating the weight of a directed edge:

[0038] Where: wij represents the weight of the directed edge from process node i to process node j; ηij represents the energy transfer efficiency between adjacent process nodes i and j, and its value ranges from [0,1]. It can be calculated from historical process data, for example... The effective energy actually received by downstream processes. (Total energy output from upstream processes). This represents the relative loss rate during energy transfer, with values ​​ranging from [0,1]. This indicates the process cycle time matching degree, calculated as follows: in These represent the average cycle times for upstream and downstream processes, respectively. This is the adjustment coefficient; This is a balance coefficient used to adjust the relative importance of energy transfer efficiency and beat matching; it can be set to 0.6.

[0039] This weighting comprehensively considers both the physical efficiency of energy transfer and the timing matching characteristics of production rhythm. Higher energy transfer efficiency and smaller cycle time differences result in larger edge weights, indicating stronger coupling between the two processes and a more significant disturbance propagation capability. Through the establishment of this energy coupling model, subsequent steps can use the real-time collected energy deviation as a disturbance source input to achieve accurate cascading propagation calculations of disturbances between nodes.

[0040] The following describes step 202, namely "calculating the energy deviation of each process node based on the real-time collected process parameters," in detail with reference to the embodiments.

[0041] The real-time acquired process parameters mainly include temperature, power consumption, fuel flow, plate and coil running speed, rolling force, current and voltage, and slab or coil specifications at each process node. These parameters are acquired in real time through sensors, PLC systems, or MES systems on the production line to ensure that the data reflects the actual operating status at the current production moment. Based on these parameters, the actual energy input of each process node is first calculated, that is, the total amount of energy actually consumed or transferred in the current process.

[0042] Meanwhile, the system calculates the expected energy input for each process node using a pre-established energy baseline model. This baseline model comprehensively considers the specifications of the currently processed coil, such as thickness, width, and steel grade, as well as a large amount of historical process data. It uses a combination of mechanistic modeling and data-driven approaches to predict the energy consumption of the coil under ideal and stable conditions. The expected energy input represents the theoretically optimal energy demand state.

[0043] The energy deviation is defined as the difference between the actual energy input and the expected energy input. When the actual energy input is higher than the expected value, the deviation is positive, indicating energy surplus or waste; when the actual energy input is lower than the expected value, the deviation is negative, indicating potential energy shortage or low temperature. This deviation directly serves as the input source for subsequent disturbance propagation functions, quantitatively characterizing the energy uncertainty in each process caused by raw material fluctuations, equipment status changes, or external disturbances.

[0044] The following describes in detail step 203, namely, "constructing a disturbance propagation function containing a propagation attenuation factor and a time lag parameter based on the energy coupling relationship model, and introducing the energy deviation as an input into the disturbance propagation function to perform cascade propagation calculation of the disturbance between each process node, and obtaining the disturbance influence of each process node," with reference to the embodiments.

[0045] Constructing a disturbance propagation function, incorporating propagation attenuation factors and time lag parameters, based on an energy coupling model is the core step in achieving accurate cascading propagation calculations of uncertainty across multiple processes. This step, grounded in an established directed weighted relationship model, transforms the static energy coupling network into a mathematical function capable of dynamically describing the disturbance propagation pattern. This provides a quantifiable propagation mechanism for subsequent calculations of disturbance impact and the construction of risk indicators. Through this construction process, the system can effectively capture the attenuation and delay characteristics of disturbances propagating from upstream process nodes to downstream nodes, avoiding the problem of insufficient description of the dynamic propagation process between processes in traditional scheduling methods.

[0046] First, the system extracts directed connection paths between process nodes based on an energy coupling relationship model and obtains the energy coupling strength parameters on the corresponding paths. Specifically, the system employs a graph theory path search algorithm, starting from any upstream process node and traversing all complete directed paths that can reach downstream nodes. Simultaneously, for each extracted path, the system calculates the energy coupling strength parameters of all directed edges on the path. This parameter can be obtained through the accumulation or product of the edge weights on the path, reflecting the overall coupling strength when the disturbance propagates along the path, providing a direct basis for determining the subsequent attenuation factor.

[0047] Next, based on the extracted energy coupling strength parameters, the propagation attenuation factor for each path is determined, and the propagation attenuation factor is made to have an inverse relationship with the energy coupling strength. When the energy coupling strength is higher, the propagation attenuation factor is smaller, indicating that the disturbance attenuates more slowly on strongly coupled paths, and vice versa. This inverse relationship conforms to the physical law that higher energy transfer efficiency leads to longer disturbance persistence in actual production. The propagation attenuation factor can be achieved using the following formula:

[0048] in, This represents the propagation attenuation factor of path p. This represents the energy coupling strength parameter of path p. This formula ensures that the attenuation factor ranges from 0 to 1, possessing a clear physical meaning and computational stability.

[0049] Then, based on the cycle time difference between adjacent process nodes, the propagation time delay of the disturbance along the path is calculated to obtain the time lag parameter. The cycle time difference is quantified by the absolute difference in the average processing time of two adjacent process nodes and accumulated segment by segment along the path to finally form the total time lag parameter for that path. This parameter directly reflects the time delay characteristic required for the disturbance to propagate from one process to the next, and can accurately describe the timing offset caused by the mismatch in production rhythm.

[0050] Finally, the propagation attenuation factor and time lag parameter are introduced into the predefined propagation function structure to construct a disturbance propagation function that describes the path propagation process of the disturbance. The predefined propagation function structure includes both path attenuation terms and time lag response terms, which, through coupled operations, form a joint representation of the disturbance propagation process. For example, the disturbance propagation function can take the following implementable combinational form:

[0051] in, Input the energy deviation of the upstream node. This represents the disturbance response of downstream node j at time t. This refers to the time lag parameter of the path. This is an adjustable time-delay response coefficient. This function can accurately characterize the dynamic propagation process of disturbances between multi-level process nodes, providing a reliable foundation for subsequent multi-source disturbance fusion calculations and risk indicator construction.

[0052] in, The path attenuation term characterizes the cumulative attenuation effect of a disturbance propagating along multiple process nodes as the path length increases. It is calculated by weighting the propagation attenuation factors corresponding to each path. When a disturbance originates from an upstream process node and reaches a downstream node via a path composed of multiple directed edges, its influence gradually weakens as the path length increases. This cumulative attenuation effect conforms to the law that energy transfer efficiency decreases with distance in actual production. The propagation attenuation factor is determined by the energy coupling strength parameter of the path and exhibits an inverse relationship with the coupling strength.

[0053] The time-delay response term characterizes the dynamic delay effect of disturbance propagation between different process nodes and performs time-series offset processing on the disturbance input based on the time lag parameter. In actual hot rolling production, due to the difference in cycle time between adjacent processes, disturbances do not arrive at downstream nodes instantaneously but have a certain propagation delay. The time-delay response term, by introducing a time lag parameter, offsets the disturbance input on the time axis, thereby accurately describing the dynamic process of disturbances "arriving with a delay and then gradually taking effect." This term can effectively capture the timing effects caused by mismatched production rhythms, ensuring that the model is highly consistent with the actual process cycle time.

[0054] As an feasible approach, the time-delay response coefficient It can be a non-fixed constant, and an adaptive adjustment mechanism that dynamically fuses multi-source uncertainty intensity and path criticality can be adopted to achieve... Online intelligent adjustment.

[0055] Specifically, the system calculates the standard deviation and maximum value of the energy deviation of all upstream process nodes in real time, and then integrates them to obtain the global uncertainty intensity. : in, The standard deviation of all energy deviations. The maximum deviation is N, where N is the number of upstream nodes.

[0056] For each propagation path, define the path criticality. This is the ratio of the sum of the weights of the critical process nodes along the path, such as the finishing rolling process, to the total path length. Critical processes can be pre-assigned weights based on their process importance; for example, a weight of 0.6 for the finishing rolling node and 0.3 for the coiling node.

[0057] The final time-delay response coefficients are obtained by applying a nonlinear mapping to the two factors mentioned above: in, The base time delay coefficient can be determined by historical data, for example, 30~120 seconds; To adjust the sensitivity coefficient; This serves as a current global disturbance risk indicator. This serves as the risk benchmark threshold.

[0058] When the production process has significant uncertainties or the path passes through critical processes... The value automatically increases, slowing down the decay of the time-delay response term, making the system's memory of disturbance propagation more durable, and preventing the risk of cascading missed detections. When the global risk is already high, the exponential term will... Appropriately reducing the time delay can enhance the sensitivity of the response time delay, prompting the scheduling system to make rhythm adjustments more quickly.

[0059] Next, the energy deviation is used as an input to the disturbance propagation function to perform cascade propagation calculations of the disturbance between each process node, thereby obtaining the disturbance impact of each process node.

[0060] Specifically, the energy deviation at each process node is first used directly as the input to the disturbance propagation function. This input represents the disturbance source at the current moment caused by the difference between the actual and expected energy input at that node. Following the constructed disturbance propagation function structure, the system sequentially substitutes this input into each extraction path from the upstream node to the target node. The propagation function simultaneously considers the effects of path attenuation and time-delay response terms, performing spatial attenuation and temporal delay offset processing on the input energy deviation, thereby simulating the propagation process of disturbances under real production cycle time.

[0061] During the cascading propagation calculation, the system transmits disturbances level by level among the process nodes. For any target process node, the calculation traverses all possible upstream directed connection paths and independently executes the propagation function operation along each path. This means that the disturbance is not simply diffused in one go, but rather achieves a cumulative effect through layer-by-layer transmission between multiple nodes. When a disturbance arrives at the same target node simultaneously from multiple upstream process nodes, the system comprehensively considers the disturbance effects from different upstream nodes and obtains the final disturbance impact on the target node through superposition or weighted fusion.

[0062] The impact of the disturbance can be calculated using the following feasible formula:

[0063] in, This represents the disturbance impact on the target process node j at time t. Let j be the set of all paths leading to node j. Input the energy deviation of the starting node of path p. The path decay factor, This is the path time lag parameter. This is the dynamically adjustable time-delay response coefficient. This formula achieves precise fusion of multi-source disturbances through a weighted summation of multi-path results.

[0064] The following describes in detail step 204, namely "constructing a multi-process disturbance risk index based on the disturbance impact of each process node and the current process status", with reference to the embodiments.

[0065] This step achieves a complete assessment of risks ranging from local disturbances to global collaborative risks by integrating the dynamic impact of disturbance propagation with the actual operating status of the process.

[0066] First, the system acquires the disturbance impact of each process node and normalizes these impacts to obtain a standardized disturbance characterization. The disturbance impact is the result of the previous cascade propagation calculation, and its value may vary considerably due to differences in process location and path. Normalization maps the disturbance impact of all nodes to a uniform interval, thus eliminating magnitude differences and facilitating subsequent fusion calculations. The standardized disturbance characterization can be calculated using the following formula:

[0067] in, Let be the standardized perturbation characterization quantity for process node j. This represents the amount of disturbance impact at that node. and These are the minimum and maximum values ​​of the disturbance impact on all nodes at the current time. This processing ensures that the disturbance characterization values ​​range from zero to one, providing good comparability.

[0068] Next, the system extracts the current process state parameters for each process node and performs dimensional unification processing on these parameters. The current process state parameters include at least one of the following: temperature deviation, rolling force fluctuation, or tension stability index. These parameters directly reflect the operational quality and stability of each process in actual production. Since the physical units and numerical ranges of different state parameters differ, dimensional unification processing is necessary. Typically, the minimum-maximum normalization method is used to map them to the zero-to-one range. The processed state parameters can be fused and calculated with the standardized perturbation characterization quantity on the same scale, avoiding evaluation bias caused by dimensional inconsistencies.

[0069] Then, based on a pre-defined coupling mapping relationship, the standardized disturbance characterization quantity and process state parameters are fused and calculated to obtain the local risk value of each process node. This mapping relationship is a pre-defined nonlinear coupling function that can dynamically adjust the dominant role of the two according to different disturbance levels. When the disturbance is small, the process state parameters play a dominant role; when the disturbance is large, the disturbance characterization quantity is amplified to reflect cascading risks. The result of the fusion calculation is the local risk value of each node, reflecting the degree of disturbance threat faced by that process individually.

[0070] As a feasible approach, the pre-defined coupling mapping relationship employs a piecewise nonlinear mapping function, which can adaptively switch the dominant factor according to the disturbance level. Under low disturbance conditions, process state parameters are dominant, while under high disturbance conditions, standardized disturbance characteristics are dominant, achieving a smooth and continuous transition at the threshold. The specific mapping relationship is as follows: Let S be the standardized disturbance characteristic, ranging from 0 to 1, and Q be the normalized process state parameter, ranging from 0 to 1. This is the final calculated local risk value. The preset disturbance threshold is... It can be calibrated based on historical data, for example, 0.35~0.45.

[0071] when At that time, the first mapping function, which is dominated by process state parameters, is adopted:

[0072] when A second mapping function dominated by the perturbation characterization quantity is adopted:

[0073] Where a, b, and c are adjustment coefficients, and the possible values ​​are: a = 0.6, b = 0.4, and c = 1.2.

[0074] Ensure that the two functions are within the threshold For continuous and smooth transitions, a sigmoid smooth switching function is introduced:

[0075] Among them, switching weight Defined as:

[0076] K is the transition steepness coefficient, which can be selected from 15 to 25 and is used to control the smoothness of the transition.

[0077] Finally, the local risk values ​​of each process node are weighted and aggregated to obtain a global disturbance risk index characterizing the collaborative state of multiple processes. The weighted aggregation considers the importance of different processes in the hot rolling production line; for example, the weights of finishing rolling and coiling processes can be appropriately increased. The global disturbance risk index can be calculated using the following feasible formula:

[0078] in, This serves as a global disturbance risk indicator. Let be the local risk value of node j. The weight coefficient of this node and satisfying N represents the total number of process nodes. This indicator can comprehensively characterize the collaborative risk level of the entire hot rolling multi-process, providing a quantitative basis from a global perspective for dynamically adjusting the processing sequence and pace.

[0079] The multi-process disturbance risk indicators obtained through the above complete construction process have both local precision and global coordination, laying a solid foundation for real-time optimized scheduling of hot-rolled coil production process.

[0080] The following describes in detail step 205, namely, "dynamically adjusting the processing sequence and rhythm of hot-rolled coils among various processes based on the disturbance risk index, to achieve multi-process collaborative scheduling optimization," with reference to the embodiments.

[0081] This step uses global disturbance risk indicators as the basis for decision-making, directly transforming risk assessment results into actionable production instructions, thereby effectively suppressing the cascading amplification effect of uncertainty across multiple processes. It breaks through the limitations of traditional scheduling methods that only perform static planning or single rescheduling, forming a complete dynamic closed loop of risk identification, sequence and rhythm adjustment, and iterative updates, significantly improving the stability and collaborative optimization capabilities of hot rolling production.

[0082] First, the system identifies target process nodes whose disturbance risk indicators exceed a preset risk threshold and determines the corresponding high-risk propagation paths. Specifically, by traversing all process nodes, the global disturbance risk indicator is compared with the preset risk threshold, and nodes with risks exceeding the threshold are selected. Subsequently, for these high-risk nodes, the system traces back the directed paths in the energy coupling relationship model to extract all upstream propagation paths that may lead to an increase in the risk of that node. These high-risk propagation paths are marked as key intervention targets, providing precise path-level guidance for subsequent sequence rearrangement and cycle time adjustment.

[0083] For plate rolling tasks on the high-risk propagation path, the system performs processing order rearrangement, prioritizing or delaying plate rolling tasks with higher disturbance risk into subsequent processes to reduce the cascading amplification effect of disturbances between adjacent processes. The rearrangement strategy ranks the plate rolling tasks on each path based on their overall risk contribution. Higher-risk plate rolling tasks can be inserted earlier into low-risk paths or temporarily postponed to a lower-risk time period. This rearrangement process can be implemented using the following priority formula:

[0084] in, Adjusting the priority for the k-th roll task. The risk value of the high-risk path where the task is located. This represents the task weighting coefficient. By rearranging the processing sequence in ascending or descending order of priority, the pressure of disturbance propagation can be effectively dispersed, reducing the accumulation of cascading risks.

[0085] Based on the aforementioned disturbance risk index, the system adaptively adjusts the processing cycle time of each process node by increasing or decreasing the time interval between adjacent processes to suppress the disturbance propagation speed. When the risk index is high, the system appropriately increases the interval time between adjacent processes to slow down the disturbance transmission rate; when the risk decreases, the interval is appropriately reduced to maintain the production rhythm. This adaptive adjustment can be achieved through the following formula:

[0086] in, The time interval between processes i and j after adjustment. For adjustment coefficients, This serves as the baseline risk level. This adjustment ensures that the beat rate change is positively correlated with the risk level, achieving dynamic suppression of disturbance propagation speed.

[0087] After completing the rearrangement of the processing sequence and adjustment of the cycle time, the system updates the disturbance risk indicators of each process node and repeats the above adjustment process until the disturbance risk indicators meet the preset stability conditions. During the update process, real-time process parameters are re-acquired, and the energy deviation, disturbance impact, and global risk indicators are recalculated.

[0088] If the risk index remains above the stability threshold, the process returns to the step of identifying high-risk nodes and continues iterating. When the global disturbance risk index falls below the preset stability condition or the maximum number of iterations is reached, the adjustment process terminates. This iterative closed-loop mechanism ensures that the scheduling scheme can continuously respond to changes in the production environment, ultimately achieving a dynamic balance in the collaborative scheduling optimization of multiple processes in hot-rolled coils.

[0089] To further illustrate the technical effects of this application, a specific implementation method and the test results of this implementation method are given below.

[0090] This embodiment uses a 2250mm hot-rolling production line of a steel company as the application object. The processed coil specifications are 2.0-16.0mm thick, 900-2100mm wide, and the steel grades are low-carbon steel and medium-carbon steel. The production line includes four process nodes: heating furnace, roughing rolling, finishing rolling, and coiling. The system first constructs an energy coupling relationship model based on historical process data and real-time collected parameters such as temperature, power, and flow rate. The weight of each directed edge is determined by the energy transfer efficiency and cycle time matching degree. Subsequently, the energy deviation of each process node is calculated as the disturbance source input, and cascade propagation calculation is performed through a disturbance propagation function that includes propagation attenuation factor and time lag parameter to obtain the disturbance influence of each node. Based on this, the disturbance impact and current process status parameters, including temperature deviation, rolling force fluctuation, and tension stability indicators, are integrated to construct a multi-process disturbance risk index. The processing sequence and rhythm of the coil are dynamically adjusted according to this risk index: after identifying high-risk nodes and paths, high-risk coil tasks are prioritized or postponed, while the time interval between adjacent processes is adaptively increased or decreased until the global disturbance risk index falls below a preset stability threshold of 0.25. This implementation method operates entirely in real-time on the MES system, with a calculation cycle controlled within 2 seconds, ensuring online dynamic optimization.

[0091] To verify the practical effectiveness of the invention, simulation and industrial field tests were conducted. The tests were compared with the traditional static scheduling method, running 1000 coil production cycles under the same coil order and the introduction of typical uncertainty disturbances, including raw material temperature fluctuations of ±30℃, random equipment cycle delays of ±15 seconds, and power fluctuations of ±8%.

[0092] The results show that the method of this invention reduces the global disturbance risk index by an average of 42.6%, improves the temperature uniformity of the hot-rolled coil by 13.8%, and reduces the standard deviation of rolling force fluctuation by 11.2%. Compared with traditional methods, the quality defect rate, such as poor sheet shape and uneven performance, decreases from 4.7% to 2.9%, energy consumption per unit decreases by 7.9%, capacity utilization increases by 9.4%, and cycle time fluctuation coefficient decreases by 18.7%. In the field industrial verification, no major cascading disturbances caused by shutdowns occurred during 72 hours of continuous operation, fully demonstrating the significant optimization effect of this solution on the multi-process collaborative scheduling of hot-rolled coils under high uncertainty environments.

[0093] The method provided in this application can be applied to various scenarios, including but not limited to: in large steel enterprises' 2250mm or 1580mm hot rolling production lines, when raw material temperature fluctuates, equipment status changes randomly, or emergency orders frequently occur, this method can quantify disturbance propagation in real time through an energy coupling model, dynamically adjust the processing sequence and rhythm of coils, and significantly reduce quality problems such as uneven temperature and plate shape defects. In flexible production scenarios with multiple varieties and small batches, such as when frequently switching between different specifications of coils for the production of high-strength steel, automotive panels, and pipeline steel, this invention can effectively suppress the cascading amplification of disturbances between processes, maintain a stable production rhythm, and improve capacity utilization.

[0094] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0095] According to another embodiment, a multi-process collaborative scheduling system for hot-rolled coils based on uncertainty is provided. Figure 3 A schematic block diagram of a multi-process collaborative scheduling system for hot-rolled coils based on uncertainty is shown according to one embodiment. Figure 3 As shown, the device 300 includes: Energy coupling relationship construction unit 301 is configured to construct an energy coupling relationship model between various hot rolling processes, abstracting the heating, roughing, finishing and coiling processes as nodes, and establishing a directed weighted relationship characterizing the energy transfer intensity and delay characteristics.

[0096] The energy deviation calculation unit 302 is configured to calculate the energy deviation of each process node based on the real-time acquired process parameters.

[0097] The disturbance impact calculation unit 303 is configured to construct a disturbance propagation function including a propagation attenuation factor and a time lag parameter based on the energy coupling relationship model, and to introduce the energy deviation as an input into the disturbance propagation function to perform cascade propagation calculation of the disturbance between each process node, so as to obtain the disturbance impact of each process node.

[0098] The disturbance risk index construction unit 304 is configured to construct multi-process disturbance risk indicators based on the disturbance impact of each process node and the current process status.

[0099] The processing sequence rhythm adjustment unit 305 is configured to dynamically adjust the processing sequence and rhythm of hot-rolled coils between processes based on the disturbance risk index, thereby achieving multi-process collaborative scheduling optimization.

[0100] As an implementable approach, the weights of each directed edge in the energy coupling relationship model of the energy coupling relationship construction unit 301 are jointly determined by the energy transfer efficiency between adjacent process nodes and the process cycle matching degree, which are used to characterize the transmission intensity of disturbances between processes.

[0101] As an feasible approach, the energy deviation in the energy deviation calculation unit 302 is the difference between the actual energy input of each process node and the expected energy input calculated based on the target process parameters. The expected energy input is determined by the energy benchmark model based on the plate and coil specification parameters and historical process data.

[0102] As an implementable approach, the disturbance impact calculation unit 303, when constructing a disturbance propagation function containing a propagation attenuation factor and a time lag parameter based on the energy coupling relationship model, can be configured as follows: based on the energy coupling relationship model, extract the directed connection paths between each process node and obtain the energy coupling strength parameters on the corresponding paths; based on the energy coupling strength parameters, determine the propagation attenuation factor corresponding to each path, so that the propagation attenuation factor and the energy coupling strength have an inverse relationship; based on the cycle time difference between adjacent process nodes, calculate the propagation time delay of the disturbance on the path to obtain the time lag parameter; and introduce the propagation attenuation factor and the time lag parameter into a preset propagation function structure to construct a disturbance propagation function for describing the propagation process of the disturbance along the path.

[0103] As an implementable approach, the disturbance impact calculation unit 303, when the preset propagation function structure is a combination function that simultaneously includes a path attenuation term and a time-delay response term, can be configured as follows: the path attenuation term is used to characterize the cumulative attenuation effect of the disturbance as it propagates along multi-level process nodes, and is calculated by weighting the propagation attenuation factors corresponding to each path; the time-delay response term is used to characterize the dynamic delay effect of the disturbance propagation between different process nodes, and the disturbance input is processed by time-series offset based on the time lag parameter; the path attenuation term and the time-delay response term are coupled to form a joint characterization of the disturbance propagation process, so as to obtain the disturbance response results of each process node.

[0104] As an feasible approach, the disturbance impact calculation unit 303 comprehensively considers the disturbance impact from multiple upstream process nodes when calculating the cascading propagation of disturbances between process nodes, and obtains the disturbance impact of the target process node through superposition or weighted fusion.

[0105] As an implementable approach, the disturbance risk index construction unit 304, when constructing a multi-process disturbance risk index based on the disturbance impact of each process node and the current process state, can be configured as follows: acquiring the disturbance impact of each process node and normalizing the disturbance impact to obtain a standardized disturbance characterization; extracting the current process state parameters of each process node, wherein the process state parameters include at least one of temperature deviation, rolling force fluctuation, or tension stability indicators, and performing dimensional unification processing on the process state parameters; based on a preset coupling mapping relationship, fusing the standardized disturbance characterization and the process state parameters to obtain the local risk value of each process node; and weighted aggregating the local risk values ​​of each process node to obtain a global disturbance risk index characterizing the multi-process collaborative state.

[0106] As an implementable approach, the preset coupling mapping relationship in the disturbance risk index construction unit 304 is a piecewise nonlinear mapping relationship, including: when the disturbance impact is lower than the preset disturbance threshold, a first mapping function dominated by process state parameters is used to characterize the dominant role of process state on risk; when the disturbance impact is higher than the preset disturbance threshold, a second mapping function dominated by the disturbance impact is used to characterize the amplification effect of disturbance propagation on risk; wherein, the first mapping function and the second mapping function are continuous at the preset disturbance threshold, and the continuous switching of the mapping relationship is achieved through a smooth transition function.

[0107] As an implementable approach, the processing sequence rhythm adjustment unit 305, when dynamically adjusting the processing sequence and rhythm of hot-rolled coils between processes based on the disturbance risk index, can be configured to: identify target process nodes where the disturbance risk index is higher than a preset risk threshold, and determine the corresponding high-risk propagation path; for coil tasks on the high-risk propagation path, perform processing sequence rearrangement, so that coil tasks with higher disturbance risk are prioritized or delayed to enter subsequent processes, thereby reducing the cascading amplification effect of disturbances between adjacent processes; based on the disturbance risk index, adaptively adjust the processing rhythm of each process node by increasing or decreasing the time interval between adjacent processes to suppress the speed of disturbance propagation; after completing the processing sequence rearrangement and rhythm adjustment, update the disturbance risk index of each process node, and repeatedly execute the above adjustment process until the disturbance risk index meets the preset stability condition.

[0108] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. Components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0109] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0110] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0111] And an electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.

[0112] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0113] in, Figure 4An exemplary architecture of an electronic device is shown, which may include a processor 410, a video display adapter 411, a disk drive 412, an input / output interface 413, a network interface 414, and a memory 420. The processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, and memory 420 can communicate with each other via a communication bus 430.

[0114] The processor 410 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to achieve the technical solution provided in this application.

[0115] The memory 420 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 420 can store the operating system 421 for controlling the operation of the electronic device 400, and the basic input / output system (BIOS) 422 for controlling the low-level operations of the electronic device 400. Additionally, it can store a web browser 423, a data storage management system 424, and a multi-process collaborative scheduling system 425 based on uncertainty for hot-rolled coils, etc. The aforementioned multi-process collaborative scheduling system 425 based on uncertainty for hot-rolled coils can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 420 and executed by the processor 410.

[0116] Input / output interface 413 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0117] Network interface 414 is used to connect a communication module (not shown in the figure) to enable communication and interaction between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0118] Bus 430 includes a pathway for transmitting information between various components of the device, such as processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, and memory 420.

[0119] It should be noted that although the above-described device only shows the processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, memory 420, bus 430, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0120] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer program product. This computer program product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0121] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A multi-process collaborative scheduling method for hot-rolled coils based on uncertainty, characterized in that, The method includes: A model of energy coupling relationship between various processes in hot rolling is constructed, and the heating, roughing, finishing and coiling processes are abstracted as nodes. A directed weighted relationship characterizing the energy transfer intensity and delay characteristics is established. Based on the real-time collected process parameters, the energy deviation of each process node is calculated; Based on the energy coupling relationship model, a disturbance propagation function containing a propagation attenuation factor and a time lag parameter is constructed, and the energy deviation is introduced into the disturbance propagation function as an input to perform cascade propagation calculation of the disturbance between each process node, thereby obtaining the disturbance influence of each process node. Based on the disturbance impact of each process node and the current process status, a multi-process disturbance risk index is constructed. Based on the aforementioned disturbance risk indicators, the processing sequence and rhythm of hot-rolled coils in each process are dynamically adjusted to achieve multi-process collaborative scheduling optimization.

2. The method according to claim 1, characterized in that, The weight of each directed edge in the energy coupling relationship model is determined by the energy transfer efficiency between adjacent process nodes and the process cycle matching degree, and is used to characterize the transmission intensity of disturbances between processes.

3. The method according to claim 1, characterized in that, The energy deviation is the difference between the actual energy input at each process node and the expected energy input calculated based on the target process parameters. The expected energy input is determined by an energy benchmark model based on the plate and coil specifications and historical process data.

4. The method according to claim 1, characterized in that, The step of constructing the perturbation propagation function, which includes a propagation attenuation factor and a time lag parameter, based on the energy coupling relationship model includes: Based on the energy coupling relationship model, the directed connection paths between each process node are extracted, and the energy coupling strength parameters on the corresponding paths are obtained. Based on the energy coupling strength parameter, determine the propagation attenuation factor corresponding to each path, so that the propagation attenuation factor and the energy coupling strength have an inverse relationship. Based on the difference in cycle time between adjacent process nodes, the propagation time delay of disturbances on the path is calculated to obtain the time lag parameter; The propagation attenuation factor and time lag parameter are introduced into a preset propagation function structure to construct a disturbance propagation function that describes the propagation process of the disturbance along the path.

5. The method according to claim 4, characterized in that, The preset propagation function structure is a combined function that simultaneously includes a path decay term and a time-delay response term, wherein: The path attenuation term is used to characterize the cumulative attenuation effect of disturbances as the path length increases when the disturbance is transmitted along multi-level process nodes, and is calculated by weighting the propagation attenuation factors corresponding to each path. The time delay response term is used to characterize the dynamic delay effect of disturbance transmission between different process nodes, and the disturbance input is subjected to time-series offset processing based on the time delay parameter. The path attenuation term and the time delay response term are coupled to form a joint characterization of the disturbance propagation process, so as to obtain the disturbance response results of each process node.

6. The method according to claim 1, characterized in that, When calculating the cascading propagation of disturbances between process nodes, the disturbance effects from multiple upstream process nodes are comprehensively considered, and the disturbance effect of the target process node is obtained by superposition or weighted fusion.

7. The method according to claim 1, characterized in that, The multi-process disturbance risk index is constructed based on the disturbance impact of each process node and the current process status, including: The disturbance impact of each process node is obtained, and the disturbance impact is normalized to obtain a standardized disturbance characterization quantity. Extract the current process status parameters of each process node. The process status parameters include at least one of temperature deviation, rolling force fluctuation or tension stability index, and perform dimensional unification processing on the process status parameters. Based on a preset coupling mapping relationship, the standardized disturbance characterization quantity and the process state parameter are fused and calculated to obtain the local risk value of each process node; the local risk values ​​of each process node are weighted and aggregated to obtain a global disturbance risk index characterizing the collaborative state of multiple processes.

8. The method according to claim 7, characterized in that, The preset coupling mapping relationship is a piecewise nonlinear mapping relationship, including: When the disturbance impact is below the preset disturbance threshold, a first mapping function dominated by process state parameters is adopted to characterize the dominant role of process state on risk. When the disturbance impact exceeds the preset disturbance threshold, a second mapping function dominated by the disturbance impact is used to characterize the amplification effect of disturbance propagation on risk. The first mapping function and the second mapping function are continuous at the preset disturbance threshold, and the mapping relationship is continuously switched through a smooth transition function.

9. The method according to claim 1, characterized in that, The dynamic adjustment of the processing sequence and rhythm of hot-rolled coils between various processes based on the disturbance risk index includes: Identify target process nodes where the disturbance risk index exceeds the preset risk threshold, and determine the corresponding high-risk propagation path; For plate and roll tasks on the high-risk propagation path, the processing order is rearranged so that plate and roll tasks with higher disturbance risk are prioritized or delayed to enter the subsequent process, so as to reduce the cascading amplification effect of disturbance between adjacent processes. Based on the aforementioned disturbance risk index, the processing cycle time of each process node is adaptively adjusted by increasing or decreasing the time interval between adjacent processes to suppress the speed of disturbance propagation. After completing the rearrangement of the processing sequence and the adjustment of the cycle time, the disturbance risk index of each process node is updated, and the above adjustment process is repeated until the disturbance risk index meets the preset stability condition.

10. A multi-process collaborative scheduling system for hot-rolled coils based on uncertainty, characterized in that, The system includes: The energy coupling relationship construction unit is configured to construct an energy coupling relationship model between various hot rolling processes, abstracting the heating, roughing, finishing and coiling processes as nodes, and establishing a directed weighted relationship characterizing the energy transfer intensity and delay characteristics; The energy deviation calculation unit is configured to calculate the energy deviation of each process node based on the real-time acquired process parameters. The disturbance impact calculation unit is configured to construct a disturbance propagation function containing a propagation attenuation factor and a time lag parameter based on the energy coupling relationship model, and to introduce the energy deviation as an input into the disturbance propagation function to perform cascade propagation calculation of the disturbance between each process node to obtain the disturbance impact of each process node. The disturbance risk index construction unit is configured to construct multi-process disturbance risk indicators based on the disturbance impact of each process node and the current process status. The processing sequence rhythm adjustment unit is configured to dynamically adjust the processing sequence and rhythm of hot-rolled coils between each process according to the disturbance risk index, so as to realize multi-process collaborative scheduling optimization.

Images