Moisture control method, device and equipment for silk making process and medium

Abstract

The invention discloses a moisture control method, device and equipment for a silk making process and a medium. The method comprises the following steps: acquiring a current state vector corresponding to a target production material in a target cut tobacco making process; state indexing is carried out on the current state vector based on the target state and an action mapping table, basic adjustment action information corresponding to the current state vector is determined, and corresponding historical adjustment action information is matched in a historical action set based on the current collection moment; wherein the target state and action mapping table is determined based on a target nonlinear regression model corresponding to the target production material; and performing weighted fusion on the historical adjustment action information and the basic adjustment action information to obtain target adjustment action information corresponding to the current state vector, and executing the target adjustment action information to realize moisture control of the target cut tobacco making process. According to the technical scheme of the invention, accurate, robust and autonomous control of the moisture at the outlet of the silk making process can be realized, and the production efficiency of the silk making process is improved.

Description

Technical Field

[0001] This invention relates to the field of tobacco processing technology, and in particular to a method, apparatus, equipment and medium for moisture control in the tobacco processing process. Background Technology

[0002] In the cigarette manufacturing process, the outlet moisture content is a core indicator that determines the physical properties, processing performance, and sensory quality of the final product. The precision of moisture control directly affects product homogenization, raw material consumption, and production line efficiency. Therefore, achieving accurate and stable outlet moisture control is a key objective of automating the cigarette manufacturing process.

[0003] Currently, existing moisture control methods mainly rely on the following technical approaches: One is a feedback control method based on traditional Proportional-Integral-Derivative (PID) control. This method generates a control signal by comparing the deviation between the measured outlet moisture value and the target setpoint through proportional, integral, and derivative operations. Another is a feedforward and feedback composite control method based on a fixed process model. This method uses an offline-established process model to perform feedforward compensation for major disturbances, and then combines it with feedback control for correction. A third is a predictive compensation algorithm based on a static data-driven model. This method uses historical data to train a regression model to predict outlet moisture and provides compensation suggestions accordingly.

[0004] However, the yarn drying process exhibits significant time lag, strong nonlinearity, and time-varying characteristics. Traditional linear PID controllers struggle to dynamically adapt to these complex conditions, and their control parameters often rely heavily on manual tuning based on operator experience, making it difficult to achieve ideal and stable control results. In actual production, fluctuations in raw material properties, changes in environmental temperature and humidity, and equipment state drift can all lead to a severe mismatch between the pre-established fixed process model and the actual process, resulting in decreased control accuracy or even instability. Furthermore, static data-driven models typically employ an offline training and online application model, with long update cycles. They cannot respond in real time to continuous changes in production conditions. Over long-term operation, prediction biases may accumulate due to model aging or changes in operating conditions, ultimately affecting control quality.

[0005] Therefore, how to achieve precise, robust, and autonomous control of moisture at the outlet of the silk-making process, and improve the accuracy and efficiency of moisture control in the silk-making process, so as to improve the production efficiency of the silk-making process, is an urgent problem to be solved. Summary of the Invention

[0006] This invention provides a method, apparatus, equipment, and medium for moisture control in the silk-making process, which can solve the problem of low accuracy and efficiency in moisture control during the silk-making process.

[0007] According to one aspect of the present invention, a method for controlling moisture in a yarn-making process is provided, comprising: Obtain the current state vector corresponding to the target production material in the target yarn making process; wherein, the current state vector includes the current inlet temperature, current inlet moisture, current measured outlet moisture, current steam pressure, current drum speed, current drum wall temperature, current hot air velocity, current exhaust hood negative pressure, current material flow rate and current hot air temperature at the current acquisition time; The current state vector is indexed based on the target state and action mapping table to determine the basic adjustment action information corresponding to the current state vector, and the corresponding historical adjustment action information is matched in the historical action set based on the current acquisition time; wherein, the target state and action mapping table is determined based on the target nonlinear regression model corresponding to the target production material; The historical adjustment action information and the basic adjustment action information are weighted and fused to obtain the target adjustment action information corresponding to the current state vector, and the target adjustment action information is executed to achieve moisture control in the target yarn making process.

[0008] According to another aspect of the present invention, a moisture control device for a yarn-making process is provided, comprising: The data acquisition module is used to acquire the current state vector corresponding to the target production material in the target yarn making process; wherein, the current state vector includes the current inlet temperature, current inlet moisture, current measured outlet moisture, current steam pressure, current drum speed, current drum wall temperature, current hot air velocity, current dehumidification hood negative pressure, current material flow rate and current hot air temperature at the current acquisition time; The data matching module is used to index the current state vector based on the target state and action mapping table, determine the basic adjustment action information corresponding to the current state vector, and match the corresponding historical adjustment action information in the historical action set based on the current acquisition time; wherein, the target state and action mapping table is determined based on the target nonlinear regression model corresponding to the target production material; The action determination module is used to perform weighted fusion of the historical adjustment action information and the basic adjustment action information to obtain the target adjustment action information corresponding to the current state vector, and execute the target adjustment action information to achieve moisture control in the target yarn making process.

[0009] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the moisture control method of the silk-making process according to any embodiment of the present invention.

[0010] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the moisture control method of the silk-making process according to any embodiment of the present invention.

[0011] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the moisture control method for the silk-making process described in any embodiment of the present invention.

[0012] The technical solution of this invention involves acquiring the current state vector corresponding to the target production material in the target silk-making process. Then, based on a target state-action mapping table, the current state vector is indexed to determine the basic adjustment action information corresponding to the current state vector. Furthermore, based on the current acquisition time, the corresponding historical adjustment action information is matched in the historical action set. The target state-action mapping table is determined based on a target nonlinear regression model corresponding to the target production material. Finally, the historical adjustment action information and the basic adjustment action information are weighted and fused to obtain the target adjustment action information corresponding to the current state vector. This target adjustment action information is then executed to achieve moisture control in the target silk-making process. Because the target state-action mapping table is pre-determined using a target nonlinear regression model, and the historical adjustment action information is used to compensate for the initially obtained basic adjustment action information, the problem of low accuracy and efficiency in moisture control during the silk-making process is solved. This enables precise, robust, and autonomous control of the moisture content at the silk-making process outlet, improving the accuracy and efficiency of moisture control and further enhancing the production efficiency of the silk-making process.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1This is a flowchart of a moisture control method for a yarn-making process according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of a moisture control method for a yarn-making process according to Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of a moisture control device for a silk-making process according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device for implementing the moisture control method in the silk-making process according to an embodiment of the present invention. Detailed Implementation

[0016] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0017] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0018] Example 1 Figure 1 This is a flowchart of a moisture control method for a yarn-making process according to Embodiment 1 of the present invention. This embodiment is applicable to situations where automated moisture control is performed in the yarn-making process. The method can be executed by a moisture control device for the yarn-making process, which can be implemented in hardware and / or software and can be configured in an electronic device. For example... Figure 1 As shown, the method includes: S110. Obtain the current state vector corresponding to the target production material in the target yarn making process; wherein, the current state vector includes the current inlet temperature, current inlet moisture, current measured outlet moisture, current steam pressure, current drum speed, current drum wall temperature, current hot air velocity, current dehumidification hood negative pressure, current material flow rate and current hot air temperature at the current acquisition time.

[0019] The tobacco processing step refers to the complete process of transforming re-dried tobacco leaves into finished tobacco shreds that meet the requirements of cigarette formulation through a series of continuous physical and chemical treatments. The target tobacco processing step refers to a pre-selected step requiring moisture control. Typically, the target tobacco processing step can be determined based on actual application needs. It is worth noting that in this embodiment of the invention, moisture control can be applied to the leaf drying node within the target tobacco processing step after the target tobacco processing step is determined. The production material refers to the main body of tobacco substances that undergoes processing and changes in physical form, chemical composition, or sensory characteristics during the tobacco processing step. For example, the production material can be leaf shreds. The target production material refers to the production material currently being processed in the target tobacco processing step. Typically, each target production material has a corresponding type code.

[0020] The state vector refers to the set of all key process parameters that comprehensively characterize the real-time state of the material drying process within the drying drum and can predict future moisture trends. Typically, one acquisition moment corresponds to one state vector. The current acquisition moment refers to the discrete time point at which the control system synchronously triggers all sensors to perform a complete data acquisition according to a preset sampling period. The current state vector refers to the state vector corresponding to the current acquisition moment. Inlet temperature refers to the temperature of the blade material entering the drying drum. Typically, the inlet temperature reflects the thermal state of the blades after pre-processing such as cutting and feeding. The current inlet temperature refers to the inlet temperature of the target production material at the current acquisition moment. Inlet moisture refers to the moisture content of the blades entering the drying drum. Typically, the inlet moisture reflects the basic amount of moisture that needs to be removed from the material during drying. The current inlet moisture refers to the inlet moisture of the target production material at the current acquisition moment. Measured outlet moisture refers to the moisture content of the blades leaving the drying drum. Typically, the measured outlet moisture reflects the core controlled variable of the control system. The current measured outlet moisture refers to the measured outlet moisture of the target production material at the current acquisition moment. Steam pressure can refer to the steam pressure of the heat exchanger supplying hot air or the steam injection pressure inside the drum. Generally, steam pressure is a prerequisite parameter for controlling the stability of hot air temperature. Current steam pressure can refer to the steam pressure corresponding to the target production material at the current sampling time. Drum speed can refer to the rotational speed of the drying drum. Generally, the residence time of the material inside the drum can be controlled by the drum speed. Current drum speed can refer to the drum speed corresponding to the target production material at the current sampling time. Drum wall temperature can refer to the temperature of the metal surface of the inner wall of the drying drum that is in direct contact with the tobacco. Current drum wall temperature can refer to the drum wall temperature corresponding to the target production material at the current sampling time. Hot air velocity can refer to the flow velocity of the hot air medium inside the drying drum. Current hot air velocity can refer to the hot air velocity corresponding to the target production material at the current sampling time. Exhaust hood negative pressure can refer to the degree to which the gas pressure inside the exhaust hood at the outlet end of the drying drum is lower than atmospheric pressure. Current exhaust hood negative pressure can refer to the exhaust hood negative pressure corresponding to the target production material at the current sampling time. Material flow rate can refer to the mass of blades passing through the drying drum per unit time. Current material flow rate refers to the material flow rate corresponding to the target production material at the current sampling time. Hot air temperature refers to the temperature of the hot air medium entering the drying drum. Typically, hot air temperature is the primary energy source in the drying process. Current hot air temperature refers to the hot air temperature corresponding to the target production material at the current sampling time.

[0021] It is worth noting that, since the types of equipment used in the leaf drying nodes of each target filament production process are different, the current state vector in the embodiments of the present invention includes, but is not limited to, the above-mentioned parameters.

[0022] S120. Based on the target state and action mapping table, the current state vector is indexed to determine the basic adjustment action information corresponding to the current state vector, and the corresponding historical adjustment action information is matched in the historical action set based on the current acquisition time; wherein, the target state and action mapping table is determined based on the target nonlinear regression model corresponding to the target production material.

[0023] The state-action mapping table refers to a table used to record the expected value of each adjustment action under different operating conditions. For example, the state-action mapping table can be a two-dimensional table. Rows can represent discretized states, with each state corresponding to an index value. Columns can represent possible actions. Typically, for the same state (i.e., the same row), each action (i.e., each column) has a corresponding value, representing the expected long-term return of taking that action in that state. The nonlinear regression model refers to a model used to learn the nonlinear mapping relationship between input and output. For example, nonlinear regression models can include neural networks, support vector machines, and decision trees. The target nonlinear regression model refers to a pre-trained model used to learn the nonlinear mapping relationship between the state vector and the predicted outlet moisture value. Typically, different types of coded target production materials correspond to different target nonlinear regression models. The target state-action mapping table refers to the state-action mapping table obtained based on the output of the target nonlinear regression model. Adjustment action information refers to the content of the adjustment actions to be performed. For example, the adjustment action information can be +1L / min or -2L / min. Basic adjustment action information can refer to the adjustment action information obtained from the initial indexing of the target state and action mapping table.

[0024] The historical action set refers to the set of adjustment actions performed on production materials with the same type code as the target production material in the historical production batches of the target yarn-making process. Typically, one type code corresponds to one historical action set. One historical production batch corresponds to one historical action array, which stores the adjustment actions performed on that historical production batch at various times. The historical action set stores the historical action arrays corresponding to each historical production batch. Historical adjustment action information refers to the adjustment action information in the historical action set that matches the current acquisition time.

[0025] S130. The historical adjustment action information and the basic adjustment action information are weighted and fused to obtain the target adjustment action information corresponding to the current state vector, and the target adjustment action information is executed to achieve moisture control in the target yarn making process.

[0026] Among them, the target adjustment action information can refer to the final determined moisture adjustment action information.

[0027] The technical solution of this invention involves acquiring the current state vector corresponding to the target production material in the target silk-making process. Then, based on a target state-action mapping table, the current state vector is indexed to determine the basic adjustment action information corresponding to the current state vector. Furthermore, based on the current acquisition time, the corresponding historical adjustment action information is matched in the historical action set. The target state-action mapping table is determined based on a target nonlinear regression model corresponding to the target production material. Finally, the historical adjustment action information and the basic adjustment action information are weighted and fused to obtain the target adjustment action information corresponding to the current state vector. This target adjustment action information is then executed to achieve moisture control in the target silk-making process. Because the target state-action mapping table is pre-determined using a target nonlinear regression model, and the historical adjustment action information is used to compensate for the initially obtained basic adjustment action information, the problem of low accuracy and efficiency in moisture control during the silk-making process is solved. This enables precise, robust, and autonomous control of the moisture content at the silk-making process outlet, improving the accuracy and efficiency of moisture control and further enhancing the production efficiency of the silk-making process.

[0028] Example 2 Figure 2 This is a flowchart of a moisture control method for a yarn-making process provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Specifically, this embodiment refines the step of "weighting and fusing the historical adjustment action information and the basic adjustment action information to obtain the target adjustment action information corresponding to the current state vector." Specifically, this may include: obtaining the historical forgetting factor and learning factor corresponding to the target production material; weighting and fusing the first adjustment action information, the second adjustment action information, and the basic adjustment action information based on the historical forgetting factor and learning factor to obtain the target adjustment action information corresponding to the current state vector; the first adjustment action information is the adjustment action information corresponding to the collection time point that is consistent with the current collection time within a first time period in the historical action set; the second adjustment action information is the adjustment action information corresponding to the collection time point that is consistent with the current collection time within a second time period in the historical action set; the second time period is the previous production time period of the production time period to which the current collection time belongs; the first time period is the previous production time period of the second time period. Figure 2 As shown, the method includes: S210. Obtain the current state vector corresponding to the target production material in the target yarn making process; wherein, the current state vector includes the current inlet temperature, current inlet moisture, current measured outlet moisture, current steam pressure, current drum speed, current drum wall temperature, current hot air velocity, current dehumidification hood negative pressure, current material flow rate and current hot air temperature at the current acquisition time.

[0029] Specifically, when controlling moisture content in the target yarn-making process, the current inlet temperature can be collected using an infrared measuring instrument installed above the roller feed inlet or a contact thermocouple installed on the inner wall of the feed chute. The current inlet moisture content can be collected using a near-infrared online moisture meter or a microwave moisture meter. The current hot air temperature can be collected using a thermocouple, resistance temperature detector (RTD), or infrared thermal imager. The current steam pressure can be collected using a pressure transmitter, smart pressure gauge, or differential pressure transmitter. The current roller rotation speed can be collected using an encoder, frequency converter, or laser tachometer. The current measured outlet moisture content can be collected using an online near-infrared moisture meter or a microwave resonant cavity moisture meter installed above the roller outlet belt.

[0030] S220. Obtain the target nonlinear regression model corresponding to the target production material and the first state vector corresponding to the first acquisition time; wherein, the first acquisition time is the acquisition time before the current acquisition time.

[0031] Here, the first acquisition time can refer to an acquisition time prior to the current acquisition time. That is, the first acquisition time and the current acquisition time are in the same production batch. For example, if the current acquisition time is t, then the first acquisition time can be t-1. The first state vector can refer to the state vector composed of the various state parameters acquired at the first acquisition time.

[0032] In an optional implementation, before obtaining the target nonlinear regression model corresponding to the target production material, the method further includes: Step a1: Obtain the set of historical state vectors and the basic nonlinear regression model corresponding to the target production material.

[0033] Here, "historical state vector" refers to the state vector obtained after data collection of production materials with the same type code as the target production material in the historical production batches of the target silk-making process. Typically, the historical state vectors of the same batch of production materials in the same production process are stored in the same historical state vector array. "Historical state vector set" refers to the set used to store the historical state vector arrays corresponding to different historical production batches. Typically, one type code corresponds to one historical state vector set. It is worth noting that the historical production batches corresponding to the historical state vector set need to be updated periodically to ensure that the historical state vector set retains the historical state vector arrays corresponding to the most recent historical production batches. "Basic nonlinear regression model" refers to the initially constructed, untrained nonlinear regression model.

[0034] Step a2: Based on the aforementioned basic nonlinear regression model, predict the moisture value of the first historical state vector in the historical state vector set to obtain the historical moisture value prediction result.

[0035] Here, the first historical state vector can refer to a randomly selected historical state vector from the set of historical state vectors. The moisture content prediction result can refer to the predicted outlet moisture content at the next sampling time obtained after inputting the state vector into the nonlinear regression model. The historical moisture content prediction result can refer to the predicted outlet moisture content at the next sampling time obtained after inputting the first historical state vector into the nonlinear regression model.

[0036] Step a3: Determine the historical prediction deviation corresponding to the basic nonlinear regression model based on the historical moisture value prediction results and the second historical state vector; wherein, the collection time corresponding to the second historical state vector is the collection time after the collection time corresponding to the first historical state vector.

[0037] The second historical state vector can refer to the state vector corresponding to the next acquisition time after the acquisition time corresponding to the first historical state vector. Typically, the first and second historical state vectors are stored in the same historical state vector array. For example, taking the acquisition time corresponding to the first historical state vector as 'a', the corresponding historical state vector array can be determined based on the first historical state vector. Then, the historical state vector with acquisition time a+1 is matched in this array and used as the second historical state vector. Prediction bias can refer to the difference between the predicted moisture value and the measured outlet moisture value corresponding to the next acquisition time. Historical prediction bias can refer to the difference between the predicted historical moisture value corresponding to the first historical state vector and the measured outlet moisture value in the second historical state vector.

[0038] Step a4: Optimize the basic nonlinear regression model based on the historical prediction deviation to obtain the optimized target nonlinear regression model.

[0039] Specifically, before controlling the moisture content of the target silk-making process, a set of historical state vectors and a basic nonlinear regression model corresponding to the target production material can be obtained. Then, the first historical state vector from the set is input into the basic nonlinear regression model to obtain the predicted historical moisture content corresponding to the first historical state vector. Further, the historical prediction deviation between the predicted historical moisture content and the measured outlet moisture content in the second historical state vector is calculated. Finally, this historical prediction deviation is used as a loss function to optimize the basic nonlinear regression model, update the network weights, accelerate network convergence, reduce oscillations during convergence, and improve model accuracy. This yields a well-trained target nonlinear regression model, providing a solid foundation for subsequent operations.

[0040] In an optional implementation, after optimizing the basic nonlinear regression model based on the historical prediction bias to obtain the optimized target nonlinear regression model, the method further includes: adding the current state vector to the historical state vector set to obtain an updated historical state vector set. The target nonlinear regression model is then optimized online based on the updated historical state vector set to obtain an online optimized target nonlinear regression model.

[0041] Specifically, after acquiring the current state vector of a new production batch, the current state vector can be added to the historical state vector set. The historical state vector set is then updated to obtain an updated historical state vector set. This updated historical state vector set is then used to continuously update the target nonlinear regression model, resulting in a secondary optimized target nonlinear regression model, thus ensuring the accuracy of the prediction results output by the target nonlinear regression model.

[0042] S230. Based on the target nonlinear regression model, the moisture value of the first state vector is predicted to obtain the first moisture value prediction result, and the first prediction deviation corresponding to the first collection time is determined based on the first moisture value prediction result and the current state vector.

[0043] The first moisture content prediction result can refer to the predicted outlet moisture content at the current sampling time obtained after inputting the first state vector into the target nonlinear regression model. The first prediction deviation can refer to the difference between the first moisture content prediction result and the current measured outlet moisture content in the current state vector. For example, with the current measured outlet moisture content as W_actual, the first moisture content prediction result is W. pred Taking {t-1} as an example, the first prediction bias can be expressed as: ΔM_{t-1}=W_pred_{t-1}-W_actual.

[0044] S240. Based on the first prediction deviation, update the basic state and action mapping table to obtain the target state and action mapping table.

[0045] The basic state-action mapping table can refer to the state-action mapping table that has not been updated at the current moment.

[0046] Specifically, after acquiring the current state vector corresponding to the target production material in the target silk-making process, the first state vector corresponding to the previous acquisition time can be obtained. Then, this first state vector is input into the target nonlinear regression model, which predicts the moisture content of the first state vector, yielding a first moisture content prediction result. The first prediction deviation between the first moisture content prediction result and the currently measured outlet moisture content in the current state vector is then calculated. Finally, the first prediction deviation is used to update the basic state-action mapping table, resulting in the target state-action mapping table. This ensures the accuracy of the target state-action mapping table, providing a solid foundation for subsequent moisture control processes.

[0047] In an optional implementation, updating the base state-action mapping table based on the first prediction deviation to obtain the target state-action mapping table includes: Step b1: Weight the first prediction deviation, the current measured outlet moisture content, and the target outlet moisture content to obtain the control effect score corresponding to the first acquisition time.

[0048] The target outlet moisture value can refer to a pre-set outlet moisture value. Typically, one target outlet moisture value corresponds to one target yarn-making process, which can be determined based on process requirements. The control effect score can refer to a numerical value used to quantitatively evaluate the effectiveness of a control system performing a specific action under a specific state. For example, taking a first prediction deviation of ΔM_{t-1}, a target outlet moisture value of W_target, a current measured outlet moisture value of W_actual, an adjustment action information corresponding to the first acquisition time of A_{t-1}, and an adjustment action information corresponding to the previous acquisition time of A_{t-2}, the control effect score can be expressed as: R_{t}=α×(-|W_actual-W_target|)+β×(-|A_{t-1}-A_{t-2}|)+γ×(-|ΔM_{t-1}|). Here, α, β, and γ are weights, respectively encouraging target tracking, smooth action, and conformity to model prediction trends.

[0049] Step b2: Calculate the error of the current state vector and the control effect score based on the preset time difference calculation rules, and determine the time difference error corresponding to the first acquisition time.

[0050] The preset time difference calculation rule refers to a pre-defined rule used to limit the error calculation process. For example, the preset time difference calculation rule can be expressed as: TD = η × [R_{t} + λ × max_{a}Q(S_{t},a) - Q(S_{t-1},A_{t-1})]. Here, η can represent the learning rate, used to control the learning speed. λ can represent the discount factor, used to weigh the importance of current rewards against future returns. max_{a}Q(S_{t},a) can represent potential future action adjustment information, i.e., the action adjustment information that may correspond to time t. Typically, this potential future action adjustment information can be obtained by querying the base state and action mapping table, i.e., the maximum value among all possible actions in the next state S_{t}. Q(S_{t-1},A_{t-1}) can represent the table value corresponding to the first acquisition time in the base state and action mapping table. The time difference error refers to the result obtained after calculating the error of the current state vector and control effect score using the preset time difference calculation rule.

[0051] Step b3: Update the basic state and action mapping table based on the time difference error to obtain the target state and action mapping table.

[0052] Specifically, after obtaining the first prediction deviation, the first prediction deviation, the current measured outlet moisture content, and the target outlet moisture content value can be weighted to obtain the control effect score corresponding to the first acquisition time. Then, using a preset time difference calculation rule, the error of the current state vector and the control effect score is calculated to obtain the time difference error corresponding to the first acquisition time. Finally, according to the formula: Q(S_{t-1},A_{t-1})←Q(S_{t-1},A_{t-1})+TD, the basic state-action mapping table is updated to obtain the target state-action mapping table.

[0053] S250. Based on the target state and action mapping table, the current state vector is indexed to determine the basic adjustment action information corresponding to the current state vector, and the corresponding historical adjustment action information is matched in the historical action set based on the current acquisition time; wherein, the historical adjustment action information includes: first adjustment action information and second adjustment action information; the target state and action mapping table is determined based on the target nonlinear regression model corresponding to the target production material.

[0054] In an optional implementation, the first adjustment action information is the adjustment action information corresponding to the collection time point within a first time period in the historical action set that coincides with the current collection time; the second adjustment action information is the adjustment action information corresponding to the collection time point within a second time period in the historical action set that coincides with the current collection time; the second time period is the production time period preceding the production time period to which the current collection time belongs; and the first time period is the production time period preceding the second time period. For example, taking the current collection time as 9:15, the production time period (i.e., production batch from 9:00 to 10:00), the second time period as 8:00 to 9:00, and the first time period as 7:00 to 8:00 as an example, then the second adjustment action information can be the adjustment action information corresponding to 8:15 in the historical action set, and the first adjustment action information can be the adjustment action information corresponding to 7:15 in the historical action set.

[0055] Specifically, after obtaining the current state vector, data processing can be performed on the current state vector through state normalization or discretization to obtain the current state corresponding to the current state vector. Then, the current state is used to perform state indexing in the target state-action mapping table to obtain the corresponding basic adjustment action information. For example, assuming the outlet moisture content W is a continuous value ranging from [0%, 15%], it can be discretized into: State 0: [0%, 5%), State 1: [5%, 10%), and State 2: [10%, 15%), where State 0 represents a low moisture state, State 1 represents a normal moisture state, and State 3 represents a high moisture state. Taking the current measured outlet moisture content in the current state vector as 3%, and the target state-action mapping table as shown in Table 1 below, W = 3% can be mapped to State 0. Under State 0, the +1L / min action has the highest value. This means that, based on historical experience, increasing the water addition by 1L / min under low moisture conditions yields the greatest long-term benefit. Therefore, increasing the water addition by 1L / min can be used as the basic adjustment action information. At the same time, the corresponding historical adjustment action information is matched with the historical action set using the current collection time point, providing an effective basis for subsequent operations.

[0056] Table 1 Target State and Action Mapping Table It is worth noting that, in the embodiments of the present invention, in the process of "indexing the current state vector based on the target state and action mapping table to determine the basic adjustment action information corresponding to the current state vector", the action corresponding to the maximum value can be selected as the basic adjustment action information, or the basic adjustment action information can be determined according to the ε-greedy exploration-exploitation (ε-greedy) strategy. The embodiments of the present invention do not specifically limit this.

[0057] S260. Obtain the historical forgetting factor and learning factor corresponding to the target production material.

[0058] The historical forgetting factor refers to a parameter used to control the decay rate of the first and second adjustment action information. Typically, the historical forgetting factor determines the system's weighting of recent and long-term experiences. The learning factor refers to a parameter used to control the influence of basic adjustment action information in the final output. Typically, the learning factor determines the system's openness to innovative strategies and the speed of adoption.

[0059] S270. Based on the historical forgetting factor and the learning factor, the first adjustment action information, the second adjustment action information and the basic adjustment action information are weighted and fused to obtain the target adjustment action information corresponding to the current state vector.

[0060] Specifically, after obtaining the first adjustment action information, the second adjustment action information, and the basic adjustment action information, the first adjustment action information, the second adjustment action information, and the basic adjustment action information can be weighted and fused according to the formula: A_final_t=θ×A_q_t+(1-θ)×[ω×A_final_{T-1}+(1-ω)×A_final_{T-2}]. This yields the target adjustment action information corresponding to the current state vector. Here, θ can represent the learning factor, A_q_t can represent the basic adjustment action information, ω can represent the historical forgetting factor, A_final_{T-1} can represent the second adjustment action information, A_final_{T-2} can represent the first adjustment action information, and T can represent the production batch to which the current acquisition time belongs.

[0061] S280. Execute the target adjustment action information to achieve moisture control in the target silk-making process.

[0062] Specifically, the target adjustment action information is sent to the water addition actuator, i.e., the regulating valve. In this way, the moisture control of the target silk-making process is achieved.

[0063] The technical solution of this invention involves obtaining the current state vector corresponding to the target production material in the target silk-making process. Then, it obtains the target nonlinear regression model corresponding to the target production material and the first state vector corresponding to the first acquisition time. Based on the target nonlinear regression model, it predicts the moisture value of the first state vector to obtain a first moisture value prediction result, and determines the first prediction deviation corresponding to the first acquisition time based on the first moisture value prediction result and the current state vector. Based on the first prediction deviation, it updates the basic state-action mapping table to obtain the target state-action mapping table. Further, it indexes the current state vector based on the target state-action mapping table to determine the basic adjustment action information corresponding to the current state vector, and matches the corresponding historical adjustment action information in the historical action set based on the current acquisition time. Finally, it obtains the historical forgetting factor and learning factor corresponding to the target production material. Based on the historical forgetting factor and learning factor, it performs a weighted fusion of the first adjustment action information, the second adjustment action information, and the basic adjustment action information to obtain the target adjustment action information corresponding to the current state vector. Finally, it executes the target adjustment action information to achieve moisture control in the target silk-making process. By deeply integrating the decision-making framework with the data-driven nonlinear process prediction model in the rolling optimization closed loop, and by constructing a multi-objective reward function that integrates moisture deviation, motion change rate, and model prediction deviation, the problem of low accuracy and efficiency of moisture control in the silk-making process is solved. This enables precise, robust, and autonomous control of the moisture at the silk-making process outlet, improving the accuracy and efficiency of moisture control in the silk-making process, and further enhancing the production efficiency of the silk-making process.

[0064] Example 3 Figure 3 This is a schematic diagram of a moisture control device for a yarn-making process provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a data acquisition module 310, a data matching module 320, and an action determination module 330; The data acquisition module 310 is used to acquire the current state vector corresponding to the target production material in the target yarn making process; wherein, the current state vector includes the current inlet temperature, current inlet moisture, current measured outlet moisture, current steam pressure, current drum speed, current drum wall temperature, current hot air velocity, current dehumidification hood negative pressure, current material flow rate and current hot air temperature at the current acquisition time. The data matching module 320 is used to index the current state vector based on the target state and action mapping table, determine the basic adjustment action information corresponding to the current state vector, and match the corresponding historical adjustment action information in the historical action set based on the current acquisition time; wherein, the target state and action mapping table is determined based on the target nonlinear regression model corresponding to the target production material; The action determination module 330 is used to perform weighted fusion of the historical adjustment action information and the basic adjustment action information to obtain the target adjustment action information corresponding to the current state vector, and execute the target adjustment action information to achieve moisture control in the target yarn making process.

[0065] The technical solution of this invention involves acquiring the current state vector corresponding to the target production material in the target silk-making process. Then, based on a target state-action mapping table, the current state vector is indexed to determine the basic adjustment action information corresponding to the current state vector. Furthermore, based on the current acquisition time, the corresponding historical adjustment action information is matched in the historical action set. The target state-action mapping table is determined based on a target nonlinear regression model corresponding to the target production material. Finally, the historical adjustment action information and the basic adjustment action information are weighted and fused to obtain the target adjustment action information corresponding to the current state vector. This target adjustment action information is then executed to achieve moisture control in the target silk-making process. Because the target state-action mapping table is pre-determined using a target nonlinear regression model, and the historical adjustment action information is used to compensate for the initially obtained basic adjustment action information, the problem of low accuracy and efficiency in moisture control during the silk-making process is solved. This enables precise, robust, and autonomous control of the moisture content at the silk-making process outlet, improving the accuracy and efficiency of moisture control and further enhancing the production efficiency of the silk-making process.

[0066] Optionally, the moisture control device for the silk-making process may further include: a mapping table update module, used to acquire the target nonlinear regression model corresponding to the target production material and the first state vector corresponding to the first acquisition time; wherein, the first acquisition time is the acquisition time preceding the current acquisition time; based on the target nonlinear regression model, the moisture value of the first state vector is predicted to obtain a first moisture value prediction result, and based on the first moisture value prediction result and the current state vector, a first prediction deviation corresponding to the first acquisition time is determined; based on the first prediction deviation, the basic state and action mapping table is updated to obtain the target state and action mapping table.

[0067] Optionally, the moisture control device in the silk-making process may further include: a model training module, used to acquire a set of historical state vectors and a basic nonlinear regression model corresponding to the target production material before acquiring the target nonlinear regression model corresponding to the target production material; predict the moisture value of the first historical state vector in the set of historical state vectors based on the basic nonlinear regression model to obtain a historical moisture value prediction result; determine the historical prediction deviation corresponding to the basic nonlinear regression model based on the historical moisture value prediction result and the second historical state vector; wherein the acquisition time corresponding to the second historical state vector is the next acquisition time after the acquisition time corresponding to the first historical state vector; and optimize the basic nonlinear regression model based on the historical prediction deviation to obtain an optimized target nonlinear regression model.

[0068] Optional, the mapping table update module can be used for: The first prediction deviation, the current measured outlet moisture content, and the target outlet moisture content are weighted and processed to obtain the control effect score corresponding to the first acquisition time. Based on the preset time difference calculation rules, the error of the current state vector and the control effect score is calculated to determine the time difference error corresponding to the first acquisition time. The basic state-action mapping table is updated based on the time difference error to obtain the target state-action mapping table.

[0069] Optionally, the historical adjustment action information includes: first adjustment action information and second adjustment action information; the first adjustment action information is the adjustment action information corresponding to the collection time point that is consistent with the current collection time within a first time period in the historical action set; the second adjustment action information is the adjustment action information corresponding to the collection time point that is consistent with the current collection time within a second time period in the historical action set; the second time period is the production time period preceding the production time period to which the current collection time belongs; the first time period is the production time period preceding the second time period; The action determination module 330 can be used specifically for: Obtain the historical forgetting factor and learning factor corresponding to the target production material; The first adjustment action information, the second adjustment action information, and the basic adjustment action information are weighted and fused based on the historical forgetting factor and the learning factor to obtain the target adjustment action information corresponding to the current state vector.

[0070] Optionally, the moisture control device in the silk-making process may further include: a model optimization module, used to add the current state vector to the historical state vector set after optimizing the basic nonlinear regression model based on the historical prediction deviation to obtain the optimized target nonlinear regression model, thereby obtaining an updated historical state vector set; and to perform online optimization of the target nonlinear regression model based on the updated historical state vector set to obtain an online optimized target nonlinear regression model.

[0071] The moisture control device for the silk-making process provided in the embodiments of the present invention can execute the moisture control method for the silk-making process provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0072] Example 4 Figure 4 A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0073] like Figure 4 As shown, the electronic device 410 includes at least one processor 420 and a memory, such as a read-only memory (ROM) 430 or a random access memory (RAM) 440, communicatively connected to the at least one processor 420. The memory stores computer programs executable by the at least one processor. The processor 420 can perform various appropriate actions and processes based on the computer program stored in the ROM 430 or loaded into the RAM 440 from storage unit 490. The RAM 440 may also store various programs and data required for the operation of the electronic device 410. The processor 420, ROM 430, and RAM 440 are interconnected via a bus 450. An input / output (I / O) interface 460 is also connected to the bus 450.

[0074] Multiple components in electronic device 410 are connected to I / O interface 460, including: input unit 470, such as keyboard, mouse, etc.; output unit 480, such as various types of monitors, speakers, etc.; storage unit 490, such as disk, optical disk, etc.; and communication unit 4100, such as network card, modem, wireless transceiver, etc. Communication unit 4100 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0075] Processor 420 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 420 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 420 performs the various methods and processes described above, such as moisture control methods in the silk-making process.

[0076] The method includes: Obtain the current state vector corresponding to the target production material in the target yarn making process; wherein, the current state vector includes the current inlet temperature, current inlet moisture, current measured outlet moisture, current steam pressure, current drum speed, current drum wall temperature, current hot air velocity, current exhaust hood negative pressure, current material flow rate and current hot air temperature at the current acquisition time; The current state vector is indexed based on the target state and action mapping table to determine the basic adjustment action information corresponding to the current state vector, and the corresponding historical adjustment action information is matched in the historical action set based on the current acquisition time; wherein, the target state and action mapping table is determined based on the target nonlinear regression model corresponding to the target production material; The historical adjustment action information and the basic adjustment action information are weighted and fused to obtain the target adjustment action information corresponding to the current state vector, and the target adjustment action information is executed to achieve moisture control in the target yarn making process.

[0077] In some embodiments, the moisture control method for the yarn-making process can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 490. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 410 via ROM 430 and / or communication unit 4100. When the computer program is loaded into RAM 440 and executed by processor 420, one or more steps of the moisture control method for the yarn-making process described above can be performed. Alternatively, in other embodiments, processor 420 can be configured to perform the moisture control method for the yarn-making process by any other suitable means (e.g., by means of firmware).

[0078] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0079] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0080] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0082] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0083] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0084] This application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the moisture control method for the silk-making process provided in any embodiment of this application. This program product and the moisture control methods for the silk-making process disclosed in the embodiments of this application belong to the same inventive concept, and therefore will not be described in detail here.

[0085] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0086] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for controlling moisture in a silk-making process, characterized in that, include: Obtain the current state vector corresponding to the target production material in the target yarn making process; wherein, the current state vector includes the current inlet temperature, current inlet moisture, current measured outlet moisture, current steam pressure, current drum speed, current drum wall temperature, current hot air velocity, current exhaust hood negative pressure, current material flow rate and current hot air temperature at the current acquisition time; The current state vector is indexed based on the target state and action mapping table to determine the basic adjustment action information corresponding to the current state vector, and the corresponding historical adjustment action information is matched in the historical action set based on the current acquisition time; wherein, the target state and action mapping table is determined based on the target nonlinear regression model corresponding to the target production material; The historical adjustment action information and the basic adjustment action information are weighted and fused to obtain the target adjustment action information corresponding to the current state vector, and the target adjustment action information is executed to achieve moisture control in the target yarn making process.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the target nonlinear regression model corresponding to the target production material and the first state vector corresponding to the first acquisition time; wherein, the first acquisition time is the acquisition time preceding the current acquisition time; The moisture content of the first state vector is predicted based on the target nonlinear regression model to obtain the first moisture content prediction result. Based on the first moisture content prediction result and the current state vector, the first prediction deviation corresponding to the first collection time is determined. Based on the first prediction deviation, the basic state-action mapping table is updated to obtain the target state-action mapping table.

3. The method according to claim 2, characterized in that, Before obtaining the target nonlinear regression model corresponding to the target production material, the method further includes: Obtain the set of historical state vectors and the basic nonlinear regression model corresponding to the target production material; Based on the aforementioned fundamental nonlinear regression model, the moisture value of the first historical state vector in the historical state vector set is predicted, and the historical moisture value prediction result is obtained. Based on the historical moisture value prediction results and the second historical state vector, the historical prediction deviation corresponding to the basic nonlinear regression model is determined; wherein, the collection time corresponding to the second historical state vector is the collection time after the collection time corresponding to the first historical state vector. Based on the historical prediction bias, the basic nonlinear regression model is optimized to obtain the optimized target nonlinear regression model.

4. The method according to claim 2, characterized in that, The step of updating the base state-action mapping table based on the first prediction deviation to obtain the target state-action mapping table includes: The first prediction deviation, the current measured outlet moisture content, and the target outlet moisture content are weighted and processed to obtain the control effect score corresponding to the first acquisition time. Based on the preset time difference calculation rules, the error of the current state vector and the control effect score is calculated to determine the time difference error corresponding to the first acquisition time. The basic state-action mapping table is updated based on the time difference error to obtain the target state-action mapping table.

5. The method according to claim 1, characterized in that, The historical adjustment action information includes: first adjustment action information and second adjustment action information; the first adjustment action information is the adjustment action information corresponding to the collection time point that is consistent with the current collection time within a first time period in the historical action set; the second adjustment action information is the adjustment action information corresponding to the collection time point that is consistent with the current collection time within a second time period in the historical action set; the second time period is the production time period preceding the production time period to which the current collection time belongs; the first time period is the production time period preceding the second time period; The step of weightedly fusing the historical adjustment action information and the basic adjustment action information to obtain the target adjustment action information corresponding to the current state vector includes: Obtain the historical forgetting factor and learning factor corresponding to the target production material; The first adjustment action information, the second adjustment action information, and the basic adjustment action information are weighted and fused based on the historical forgetting factor and the learning factor to obtain the target adjustment action information corresponding to the current state vector.

6. The method according to claim 3, characterized in that, After optimizing the basic nonlinear regression model based on the historical prediction bias to obtain the optimized target nonlinear regression model, the method further includes: The current state vector is added to the historical state vector set to obtain the updated historical state vector set; The target nonlinear regression model is optimized online based on the updated set of historical state vectors to obtain the optimized target nonlinear regression model.

7. A moisture control device for a silk-making process, characterized in that, include: The data acquisition module is used to acquire the current state vector corresponding to the target production material in the target yarn making process; wherein, the current state vector includes the current inlet temperature, current inlet moisture, current measured outlet moisture, current steam pressure, current drum speed, current drum wall temperature, current hot air velocity, current dehumidification hood negative pressure, current material flow rate and current hot air temperature at the current acquisition time; The data matching module is used to index the current state vector based on the target state and action mapping table, determine the basic adjustment action information corresponding to the current state vector, and match the corresponding historical adjustment action information in the historical action set based on the current acquisition time; wherein, the target state and action mapping table is determined based on the target nonlinear regression model corresponding to the target production material; The action determination module is used to perform weighted fusion of the historical adjustment action information and the basic adjustment action information to obtain the target adjustment action information corresponding to the current state vector, and execute the target adjustment action information to achieve moisture control in the target yarn making process.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the moisture control method of the silk-making process according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the moisture control method of the silk-making process according to any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements a moisture control method for a silk-making process according to any one of claims 1-6.

Images