A power consumption optimization control system and method for a powder dry pressing servo press

Abstract

This invention relates to the field of powder dry pressing technology, specifically to an energy consumption optimization control system and method for a powder dry pressing servo press. The method includes the following steps: determining the target powder to be pressed, and determining the corresponding dry pressing parameters of the target powder based on a cloud server; constructing an energy consumption optimization model, and optimizing the dry pressing parameters based on the energy consumption optimization model to determine the optimal combination of control parameters; establishing a transmission channel between the cloud server and the control terminal, wherein the transmission channel includes two transmission channels and a connection chain between the two transmission channels; transmitting the optimal combination of control parameters to the control terminal based on the transmission channel, and the control terminal adjusting the servo press through the optimal combination of control parameters, which can ensure the safety of the optimal combination of control parameters during the transmission process, thereby improving the accuracy of servo press control for powder dry pressing.

Description

Technical Field

[0001] This invention relates to the field of powder dry pressing technology, specifically to an energy consumption optimization control system and method for a powder dry pressing servo press. Background Technology

[0002] Powder dry pressing technology is widely used in manufacturing fields such as powder metallurgy, ceramics, and cemented carbide. Its forming quality directly depends on the accuracy of the servo press control parameters. In the servo press control system, to achieve high-precision pressing, an optimal combination of control parameters (such as pressing force, pressing speed, and holding time) is typically determined based on process requirements, material properties, and equipment status. This optimal control parameter combination needs to be transmitted from the upper-level control system (such as a process optimization system, host computer, or cloud server) to the servo press's execution controller via a transmission channel. In actual industrial settings, it is difficult to guarantee the safety of the optimized control parameter combination during transmission, leading to the servo press executing unexpected control commands, thus affecting the accuracy of servo press control and consequently the stability of powder dry pressing quality.

[0003] To address these issues, we propose an energy consumption optimization control system and method for a powder dry pressing servo press. Summary of the Invention

[0004] The purpose of this invention is to provide an energy consumption optimization control system and method for a powder dry pressing servo press, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a power consumption optimization control system and method for a powder dry pressing servo press, the method comprising the following steps: The target powder to be pressed and molded is determined, and the corresponding dry pressing parameters of the target powder are determined based on the cloud server. Construct an energy consumption optimization model, and optimize the dry pressing parameters based on the energy consumption optimization model to determine the optimal combination of control parameters; Establish a transmission channel between the cloud server and the control terminal, wherein the transmission channel includes two transmission channels and a connection link between the two transmission channels; The optimal combination of control parameters is transmitted to the control terminal based on the transmission zone, and the control terminal adjusts the servo press according to the optimal combination of control parameters.

[0006] Preferably, the step of determining the target powder to be processed and the corresponding dry pressing parameters of the target powder includes: Multiple powders to be pressed are identified, and corresponding dry pressing parameters are set for each powder. The dry pressing parameters are then mapped to the corresponding powders and stored in a cloud server. The powder currently undergoing the pressing process is identified as the target powder, and the corresponding dry pressing parameters are matched based on the cloud server.

[0007] Preferably, the step of building an energy consumption optimization model based on a cloud server includes: The operation data of the servo press under different combinations of dry pressing parameters are collected. The dry pressing parameters include pressing speed, holding pressure, holding time and demolding speed. The operation data includes actual energy consumption value and molding quality index. Using dry pressing parameters as input variables and molding energy consumption as output variables, an initial model reflecting the mapping relationship between dry pressing parameters and molding energy consumption is constructed. The initial model is trained based on the operational data, and the internal parameters of the model are adjusted so that the energy consumption prediction error and the satisfaction of quality constraints reach the preset standards, thus obtaining the energy consumption optimization model.

[0008] Preferably, the steps for optimizing the dry pressing parameters based on the energy consumption optimization model to determine the optimal combination of control parameters include: Obtain the dry pressing parameters corresponding to the target powder, and use the initial dry pressing parameters as input variables to input the pre-constructed and trained energy consumption optimization model; The energy consumption optimization model takes minimizing molding energy consumption as the optimization objective and powder molding quality index as the constraint. It iteratively optimizes within the adjustable range of dry pressing parameters to generate multiple sets of candidate parameter combinations. The optimal control parameter combination is selected from multiple candidate parameter combinations that satisfy all quality constraints and have the lowest molding energy consumption.

[0009] Preferably, the step of establishing a transmission channel between the cloud server and the control terminal includes: Two transmission channels are set up between the cloud server and the control terminal. Multiple transmission nodes are set up for each transmission channel. The communication relationship between the transmission nodes corresponding to the two transmission channels is temporarily established to obtain the connection chain. Configure a transformation area for any transmission channel, wherein the transformation area includes multiple interconnected storage points; A transmission channel is obtained by connecting a transmission channel with a conversion zone to another transmission channel via a connection chain.

[0010] Preferably, the configuration of a transformation area for any transmission channel includes multiple interconnected storage packets: Multiple storage packets are set in the transmission channel. A storage packet is configured for any storage point. The storage packet includes multiple data points. The multiple data points are divided into two groups, and the multiple data points in the same group are connected to obtain two data chains. Configure connection lines for multiple data points in one data chain, and configure connection ports for multiple data points in another data chain; The correspondence between data points in two data chains is established by connecting lines; the transformation area is obtained by communicating between multiple storage packets with established correspondence.

[0011] Preferably, the steps of transmitting the optimal control parameter combination to the control terminal based on the transmission zone, and the control terminal regulating the servo press using the optimal control parameter combination, include: Obtain the optimal combination of control parameters from the cloud server and store it in a storage package; The transformation area is transmitted through various transmission nodes in the transmission channel. Based on the changes in the transmission nodes, the optimal control parameters are combined and stored in different storage points. The optimal control parameters combination that has undergone storage transformation is then transmitted to the control terminal via the transmission channel. When the storage point where the storage packet is located is accessed, a temporary connection link is established between the two transmission channels through the transmission node. Based on the connection link, the storage packet is transmitted to another transmission channel to continue transmission until it is transmitted to the control end.

[0012] Preferably, the step of storing the optimal control parameter combination in any one of the storage packets in the transformation region includes: The optimal combination of control parameters is divided into multiple data segments. Based on the parameter values ​​and parameter types, the multiple data segments are grouped into type groups and parameter groups. The type groups and parameter groups are stored on different data chains in the storage package respectively. Based on the correspondence between parameter values ​​and parameter types in the optimal control parameter combination, a corresponding chain is established between corresponding data points. The corresponding chain is obtained by connecting lines and connection ports.

[0013] Preferably, the step of storing the optimal control parameter combination between different storage packets based on changes in transmission nodes includes: Obtain the current transmission node of the transformation zone and the storage point where the storage packet in the transformation zone is located; When the transmission node where the transformation area is located changes, the storage packet is transferred from the current storage point to another storage point. At the same time, the connection port of the data point where the parameter value is located is changed, and the movement path of the connection line between multiple connection ports is recorded. After transmitting the optimal combination of control parameters to the control terminal via the storage packet, the correspondence between the connection line and the connection port is restored according to the movement path.

[0014] A powder dry pressing servo press energy consumption optimization control system, applied to any one of the above-described powder dry pressing servo press energy consumption optimization control methods, includes: The initial setup module is used to determine the target powder to be pressed and molded, and determines the dry pressing parameters corresponding to the target powder based on the cloud server. The model building module is used to build an energy consumption optimization model, and based on the energy consumption optimization model, the dry pressing parameters are optimized to determine the optimal combination of control parameters; The channel establishment module is used to establish a transmission channel between the cloud server and the control terminal. The transmission channel includes two transmission channels and a connection chain between the two transmission channels. The press control module is used to transmit the optimal combination of control parameters to the control terminal based on the transmission zone. The control terminal then controls the servo press using the optimal combination of control parameters.

[0015] Compared with the prior art, the beneficial effects of the present invention are: By changing the storage location and the correspondence between parameter types and values ​​during transmission through the transmission channel, the security of the optimal control parameter combination during transmission can be guaranteed, preventing external access, interception, and tampering with the optimal control parameter combination. This improves the accuracy of servo press control for powder dry pressing, and consequently improves the quality of powder dry pressing. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the 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.

[0017] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a system structure block diagram of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0019] For examples, please refer to Figures 1 to 2This invention provides a technical solution for an energy consumption optimization control system and method for a powder dry pressing servo press: an energy consumption optimization control method for a powder dry pressing servo press includes the following steps: S1: Determine the target powder to be pressed and molded, and determine the corresponding dry pressing parameters of the target powder based on the cloud server; The steps for determining the target powder to be processed and the corresponding dry pressing parameters of the target powder include: determining multiple powders to be pressed and molded, setting corresponding dry pressing parameters for each powder to be pressed and molded, mapping the dry pressing parameters to the corresponding powders and storing them in a cloud server; determining the powder currently in the pressing process as the target powder, and matching the corresponding dry pressing parameters of the target powder based on the cloud server. S2: Construct an energy consumption optimization model, and optimize the dry pressing parameters based on the energy consumption optimization model to determine the optimal combination of control parameters; The steps for building an energy consumption optimization model based on a cloud server include: collecting operating data of a servo press under different combinations of dry pressing parameters, whereby the dry pressing parameters include pressing speed, holding pressure, holding time, and demolding speed; and the operating data includes actual energy consumption values ​​and molding quality indicators. Using the dry pressing parameters as input variables and molding energy consumption as output variables, an initial model reflecting the mapping relationship between the dry pressing parameters and molding energy consumption is constructed. Based on the operating data, the initial model is trained, and the internal parameters are adjusted to ensure that the energy consumption prediction error and quality constraint satisfaction meet preset standards, thus obtaining the energy consumption optimization model. The steps for optimizing dry pressing parameters and determining the optimal control parameter combination based on the energy consumption optimization model include: obtaining the dry pressing parameters corresponding to the target powder; using the initial dry pressing parameters as input variables and inputting them into a pre-constructed and trained energy consumption optimization model; the energy consumption optimization model takes minimizing molding energy consumption as the optimization objective and powder molding quality indicators as constraints, and iteratively optimizes within the adjustable range of the dry pressing parameters to generate multiple sets of candidate parameter combinations; from the multiple sets of candidate parameter combinations, the set that satisfies all quality constraints and has the lowest molding energy consumption is selected as the optimal control parameter combination. Specifically, during the iterative optimization process, the energy consumption optimization model automatically adjusts the parameter search direction based on the predicted energy consumption and quality constraint satisfaction of the current parameter combination; when selecting the optimal parameter combination, if the energy consumption values ​​of multiple parameter combinations are within a preset threshold, the combination with the shortest pressing cycle or the least equipment wear is selected first; multiple servo presses are connected to the cloud server via industrial Ethernet or wireless communication. The system collects operational data of a servo press under different combinations of dry pressing parameters, including pressing speed, holding pressure, holding time, and demolding speed. The operational data includes actual energy consumption and molding quality indicators. Actual energy consumption is collected via a built-in power sensor or an independent meter, recording the total energy consumption within a single pressing cycle. Molding quality indicators include molding density, compressive strength, and dimensional accuracy, obtained through online testing equipment or offline quality inspection. The collected data is timestamped and uploaded to a cloud server via a data acquisition channel, stored in a time-series database. The cloud server uses dry pressing parameters as input variables and molding energy consumption as output variables to construct an initial model reflecting the mapping relationship between dry pressing parameters and molding energy consumption. This initial model is constructed by building a feedforward neural network containing an input layer, hidden layers, and an output layer. Input layer nodes correspond to dry pressing parameters, and output layer nodes correspond to molding energy consumption. The collected operational data is divided into training and validation sets. The initial model is trained using the training set data. The least squares method is used to adjust the model's internal parameters, gradually reducing the root mean square error between the model's predicted energy consumption and the actual energy consumption. During model training, quality constraints are embedded simultaneously: the qualified thresholds of molding quality indicators (molding density, compressive strength, dimensional accuracy) are used as constraint boundaries. Energy consumption data corresponding to parameter combinations that do not meet quality requirements in the training samples are marked to ensure that the model can identify whether parameter combinations meet quality requirements while predicting energy consumption. When the model's energy consumption prediction error on the validation set is less than a preset threshold (e.g., relative error ≤ 5%) and the accuracy of quality constraint judgment reaches a preset standard (e.g., ≥ 95%), the model training is complete, and the energy consumption optimization model is obtained. The trained energy consumption optimization model is deployed on a cloud server, providing an API interface for downstream systems to call. Through the cloud server's API interface, based on the powder type, the dry pressing parameters corresponding to the target powder are matched and read from the powder-parameter mapping library stored on the cloud server.The acquired dry pressing parameters are used as initial input variables and fed into the deployed energy consumption optimization model. The model aims to minimize molding energy consumption and uses powder molding quality indicators as constraints, iteratively optimizing within the adjustable range of the dry pressing parameters. After iteration, the model outputs multiple sets of candidate parameter combinations that meet the quality constraints. First, the set with the lowest molding energy consumption is selected. Second, if the energy consumption differences among multiple parameter combinations are within a preset threshold (e.g., energy consumption difference ≤ 2%), the pressing cycle length is further compared, prioritizing the combination with the shortest pressing cycle to improve production efficiency; or prioritizing the combination where the parameter values ​​deviate less from the equipment limits to reduce equipment wear. The optimal control parameter combination obtained is then sent to the press control system via the cloud server's API interface. The press control system automatically adjusts the servo press's speed curve, pressure setting, and action timing based on the received parameter combination to execute the powder dry pressing molding operation.

[0020] S3: Establish a transmission channel between the cloud server and the control terminal. The transmission channel includes two transmission channels and a connection link between the two transmission channels. The steps to establish a transmission channel between the cloud server and the control terminal include: setting up two transmission channels between the cloud server and the control terminal; setting up multiple transmission nodes for each transmission channel; temporarily establishing communication relationships between the transmission nodes corresponding to the two transmission channels to obtain a connection chain; configuring a transformation area for any one transmission channel, wherein the transformation area includes multiple interconnected storage points; and connecting the transmission channel with the transformation area to another transmission channel based on the connection chain to obtain a transmission channel. A transformation area is configured for any transmission channel, wherein the transformation area includes multiple interconnected storage packets: multiple storage packets are set in the transmission channel, and a storage packet is configured for any storage point. The storage packet includes multiple data points. The multiple data points are divided into two groups, and multiple data points in the same group are connected to form two data chains. A connection line is set for multiple data points in any data chain, and a connection port is configured for multiple data points in the other data chain. The correspondence between each data point in the two data chains is established through the connection line. The multiple storage packets with the established correspondence are connected for communication to form the transformation area. It's important to note that a storage point is a unit for data storage and processing. It can be considered a relatively independent entity with certain computing and storage capabilities. In cloud server-controller communication scenarios, it's a fundamental component for constructing the transformation zone, used to carry storage packets and participate in data transformation operations. Storage points can be virtual machines; multiple virtual machines can be created on a physical server as storage points. These virtual machines are isolated from each other but can communicate and interact via a network. A storage packet is a collection of data stored in a storage point. It contains multiple data points and is organized and divided according to specific rules to enable data transformation and processing during transmission. A storage packet is the basic unit for data transformation operations in the transmission channel. A storage packet can be viewed as a file or data block stored on a virtual machine disk. These files or data blocks contain data information that needs to be transmitted and processed, managed through a file system or specific data structure. When transferring data between virtual machines, storage packets can be copied or moved between different virtual machine disks. The transmission channel is a logical channel for data transmission between the cloud server and the control terminal. It consists of multiple transmission nodes, providing path and bandwidth support for data transmission. Transmission channels can be unidirectional or bidirectional, used to enable data flow in different directions; they can be based on network connections. For example, a physical link can be established between the cloud server and the control terminal through physical network media such as Ethernet or Fibre Channel; at the network layer, a logical transmission channel can be constructed using the TCP / IP protocol stack, identifying different channel endpoints through IP addresses and port numbers to achieve reliable data transmission. A connection chain is a set of communication relationships temporarily established to connect corresponding transmission nodes in two transmission channels; it defines the path and order of data transmission between the two channels, ensuring that data can be transmitted from one channel to another in a predetermined manner. Transmission nodes are key points on the transmission channel, responsible for receiving, forwarding, and processing data. They are components of the transmission channel, achieving reliable data transmission between the cloud server and the control terminal through cooperation with other transmission nodes. Transmission nodes can be devices such as servers, routers, or switches in the network. The transformation zone can consist of a group of virtual machines interconnected through an internal network. Specific data processing programs run in each virtual machine to perform transformation operations on the data in the storage packet. When data enters the transformation area, it is first stored in a storage packet at one of the storage points (virtual machines), and then transferred and processed between different storage points according to predetermined rules. A data point is a data storage unit within a storage packet, and data links can be implemented by establishing a pointer chain in memory or using a linked list in a data structure.

[0021] S4: Based on the transmission zone, the optimal control parameter combination is transmitted to the control terminal, and the control terminal adjusts the servo press according to the optimal control parameter combination; The steps for transmitting the optimal control parameter combination to the control end based on the transmission zone, and for the control end to regulate the servo press using the optimal control parameter combination, include: obtaining the optimal control parameter combination from the cloud server and storing the optimal control parameter combination in a storage packet; transmitting the transformation zone through various transmission nodes in the transmission channel, and performing storage transformation of the optimal control parameter combination between different storage points based on the changes in transmission nodes (here, storage transformation refers to changing the storage point where the storage packet containing the optimal control parameter combination is located); transmitting the optimal control parameter combination that has undergone storage transformation to the control end via the transmission channel; when accessing the storage point where the storage packet is located, temporarily establishing a connection link between the two transmission channels through the transmission node, and transmitting the storage packet to another transmission channel based on the connection link to continue transmission until it is transmitted to the control end; The steps of storing the optimal control parameter combination in any storage packet in the transformation area include: dividing the optimal control parameter combination into multiple data segments; grouping the multiple data segments into type groups and parameter groups based on parameter values ​​and parameter types; storing the type groups and parameter groups into different data chains in the storage packet; and establishing a corresponding chain between corresponding data points according to the correspondence between parameter values ​​and parameter types in the optimal control parameter combination. The corresponding chain is obtained by connecting lines and connection ports. The steps for storing the optimal control parameter combination between different storage packets based on changes in transmission nodes include: obtaining the transmission node where the transformation area is currently located and the storage point where the storage packet in the transformation area is located; when the transmission node where the transformation area is located changes (here, "change" refers to a transmission channel composed of multiple transmission nodes. When the transformation area is transmitted in the transmission channel, it needs to pass through different transmission nodes. When it is on different transmission nodes, it means that the transmission node where the transformation area is located has changed. For example, if the transformation area is transmitted from transmission node A to transmission node B, it means that the transmission node where the transformation area is located has changed from transmission node A to transmission node B). If the storage packet is moved from the current storage point to another storage point (the other storage point refers to any storage point in the transformation area that is not the current storage point of the storage packet; for example, if there are storage points 1, 2, and 3, and the storage packet is at storage point 1, then the other storage point refers to any one of storage points 2 or 3), the connection port of the data point corresponding to the parameter value of the data point in the storage point will be changed, and the movement path of the connection line between multiple connection ports will be recorded. After the optimal control parameter combination is transmitted to the control terminal through the storage packet, the correspondence between the connection line and the connection port will be restored according to the movement path. Specifically, the optimal control parameter combination is first divided according to parameter type and parameter value, and the correspondence between the two is recorded at the same time. Based on the correspondence, the connection line of the data point where the parameter type is located is connected to the connection port of the data point where the parameter value is located, as a correspondence chain. The connection line is used to correspond between parameter type and parameter value.The optimal control parameter combination is stored in a storage packet, which is located in a storage point. The storage packet is like a virtual machine, capable of storing the optimal control parameter combination according to a correspondence. The storage point is like the storage address of the storage packet, capable of changing the correspondence between parameter types and parameter values ​​when the location of the storage packet changes. (A change in the location of a storage packet refers to the movement of the storage packet between multiple storage points. When the transformation area passes through a transmission node, a change in the location of the storage packet occurs. For example, the correspondence between data points in two sets of data chains can be arbitrarily changed. For instance, one set of data chains stores data types 1, 2, and 3, while the other set stores parameters.) The original data point correspondence for value 1, parameter value 2, and parameter value 3 is: data type 1 corresponds to parameter value 1, data type 2 corresponds to parameter value 2, and data type 3 corresponds to parameter value 3. However, when the storage packet is transferred from the current storage point to another storage point, the correspondence between parameter values ​​and data types changes to: data type 1 corresponds to parameter value 2, data type 2 corresponds to parameter value 3, and data type 3 corresponds to parameter value 1. The movement path of the connection line for each parameter type between multiple connection ports is recorded (here, the movement path refers to the connection order between the connection line and each connection port). The change pattern of the correspondence is not restricted, but it must be ensured that after each change, all data types and parameter values ​​are consistent with... The original correspondence is completely different. Completely different means that no parameter value and parameter type correspondence is the same as its correspondence in the optimal control parameter combination. This ensures that the data correspondence changes according to the location of the storage packet. Therefore, even when an external access captures a storage packet, it is difficult to match the parameter value with the corresponding parameter type, and the acquired data is garbled, thus increasing data transmission security. Simultaneously, the connection order of the connecting line and each connecting port is recorded as the moving path of the connecting line (a connecting line is formed by two interconnected communication nodes, one end of which is fixed to the data point where the parameter type is located, while the other end can change to connect to different...). The connection port and communication node are the data points corresponding to both ends of the connection line. According to the movement path, the connection line is used to connect to the original connection port. After the storage packet is transmitted to the control end, the connection line is moved in the reverse direction of the movement path to restore the original correspondence between parameter type and parameter value (the original correspondence here refers to the correspondence between parameter type and parameter value in the optimal control parameter combination, and this correspondence is also the correspondence stored in the storage packet at the beginning. However, during the subsequent transmission of the storage packet, the correspondence changes to prevent external access. Therefore, the correspondence is restored by moving the path to improve the security of data during transmission).The transformation area is analogous to a virtual machine. When the optimal control parameter combination is stored in the transformation area (the optimal control parameter combination is stored in a storage packet within a storage point in the transformation area), multiple transmission nodes form a transmission channel. When the transformation area is transmitted through the transmission channel, it passes through the transmission nodes. A trigger point is set for each storage point. When the transmission node corresponding to the transformation area changes, the trigger point where the storage packet is located is activated. The trigger point then triggers the storage packet to move to any other storage point. (For example, if the transmission channel includes transmission nodes 1, 2, 3, and 4, and the storage points in the transformation area are storage points 1, 2, and 3, and the storage packet is located at storage point 2 when the transformation area is at node 1, then when the transformation area continues to be transmitted to node 2 in the transmission channel, it indicates that the transmission node of the transformation area has changed. Therefore, the trigger point is used to activate the movement of the storage packet in storage point 2, moving the storage packet to any other storage point, which can be either storage point 1 or storage point 3, as long as it is not located at storage point 2.) This allows for real-time changes to the storage location of the storage package, reducing the probability of external access to the storage point and improving the security of the optimal control parameter combination during transmission. When data in the storage package is transmitted to the control terminal, a transmission connection is established between the storage point and the control terminal. The optimal control parameter combination is then transmitted to the control terminal via this connection. After transmission to the control terminal, the transformation area is destroyed, and the optimal control parameter combination continues to be carried in the cloud server through the transformation area. The transformation area, as a transmission carrier, securely transmits the optimal control parameter combination to the control terminal. By changing the storage location and the correspondence between parameter types and values ​​during transmission, the security of the optimal control parameter combination during transmission is ensured, preventing external access, interception, and tampering with the optimal control parameter combination. This improves the accuracy of servo press control for powder dry pressing, thereby enhancing the quality of powder dry pressing.

[0022] A powder dry pressing servo press energy consumption optimization control system, applied to any one of the above-described powder dry pressing servo press energy consumption optimization control methods, includes: The initial setup module is used to determine the target powder to be pressed and molded, and determines the dry pressing parameters corresponding to the target powder based on the cloud server. The model building module is used to build an energy consumption optimization model, and based on the energy consumption optimization model, the dry pressing parameters are optimized to determine the optimal combination of control parameters; The channel establishment module is used to establish a transmission channel between the cloud server and the control terminal. The transmission channel includes two transmission channels and a connection chain between the two transmission channels. The press control module is used to transmit the optimal combination of control parameters to the control terminal based on the transmission zone. The control terminal then controls the servo press using the optimal combination of control parameters.

[0023] This invention dynamically changes the storage format and correspondence of the parameter combination itself during transmission, effectively preventing tampering after the parameters are intercepted, protecting the security of the transmission of the optimal control parameter combination, thereby ensuring the integrity and authenticity of the optimal control parameter combination throughout the transmission process, and thus improving the control accuracy of the servo press and the stability of the powder dry pressing quality.

[0024] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0025] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing energy consumption control of a servo press for powder dry pressing, characterized in that, Includes the following steps: The target powder to be pressed and molded is determined, and the corresponding dry pressing parameters of the target powder are determined based on the cloud server. Construct an energy consumption optimization model, and optimize the dry pressing parameters based on the energy consumption optimization model to determine the optimal combination of control parameters; Establish a transmission channel between the cloud server and the control terminal, wherein the transmission channel includes two transmission channels and a connection link between the two transmission channels; The optimal combination of control parameters is transmitted to the control terminal based on the transmission zone, and the control terminal adjusts the servo press according to the optimal combination of control parameters.

2. The energy consumption optimization control method for a powder dry pressing servo press according to claim 1, characterized in that: The steps of determining the target powder to be processed and the corresponding dry pressing parameters of the target powder include: Multiple powders to be pressed are identified, and corresponding dry pressing parameters are set for each powder. The dry pressing parameters are then mapped to the corresponding powders and stored in a cloud server. The powder currently undergoing the pressing process is identified as the target powder, and the corresponding dry pressing parameters are matched based on the cloud server.

3. The energy consumption optimization control method for a powder dry pressing servo press according to claim 1, characterized in that: The steps for building an energy consumption optimization model based on a cloud server include: The operation data of the servo press under different combinations of dry pressing parameters are collected. The dry pressing parameters include pressing speed, holding pressure, holding time and demolding speed. The operation data includes actual energy consumption value and molding quality index. Using dry pressing parameters as input variables and molding energy consumption as output variables, an initial model reflecting the mapping relationship between dry pressing parameters and molding energy consumption is constructed. The initial model is trained based on the operational data, and the internal parameters of the model are adjusted so that the energy consumption prediction error and the satisfaction of quality constraints reach the preset standards, thus obtaining the energy consumption optimization model.

4. The energy consumption optimization control method for a powder dry pressing servo press according to claim 3, characterized in that: The steps for optimizing dry pressure parameters and determining the optimal combination of control parameters based on the energy consumption optimization model include: Obtain the dry pressing parameters corresponding to the target powder, and use the initial dry pressing parameters as input variables to input the pre-constructed and trained energy consumption optimization model; The energy consumption optimization model takes minimizing molding energy consumption as the optimization objective and powder molding quality index as the constraint. It iteratively optimizes within the adjustable range of dry pressing parameters to generate multiple sets of candidate parameter combinations. The optimal control parameter combination is selected from multiple candidate parameter combinations that satisfy all quality constraints and have the lowest molding energy consumption.

5. The energy consumption optimization control method for a powder dry pressing servo press according to claim 1, characterized in that: The steps for establishing a transmission channel between the cloud server and the control terminal include: Two transmission channels are set up between the cloud server and the control terminal. Multiple transmission nodes are set up for each transmission channel. The communication relationship between the transmission nodes corresponding to the two transmission channels is temporarily established to obtain the connection chain. Configure a transformation area for any transmission channel, wherein the transformation area includes multiple interconnected storage points; A transmission channel is obtained by connecting a transmission channel with a conversion zone to another transmission channel via a connection chain.

6. The energy consumption optimization control method for a powder dry pressing servo press according to claim 5, characterized in that: The configuration of a transformation area for any transmission channel, wherein the transformation area includes multiple interconnected storage packets: Multiple storage packets are set in the transmission channel. A storage packet is configured for any storage point. The storage packet includes multiple data points. The multiple data points are divided into two groups, and the multiple data points in the same group are connected to obtain two data chains. Configure connection lines for multiple data points in one data chain, and configure connection ports for multiple data points in another data chain; The correspondence between data points in two data chains is established by connecting lines; the transformation area is obtained by communicating between multiple storage packets with established correspondence.

7. The energy consumption optimization control method for a powder dry pressing servo press according to claim 6, characterized in that: The steps of transmitting the optimal control parameter combination to the control terminal based on the transmission zone, and then adjusting the servo press using the optimal control parameter combination at the control terminal, include: Obtain the optimal combination of control parameters from the cloud server and store it in a storage package; The transformation area is transmitted through various transmission nodes in the transmission channel. Based on the changes in the transmission nodes, the optimal control parameters are combined and stored in different storage points. The optimal control parameters combination that has undergone storage transformation is then transmitted to the control terminal via the transmission channel. When the storage point where the storage packet is located is accessed, a temporary connection link is established between the two transmission channels through the transmission node. Based on the connection link, the storage packet is transmitted to another transmission channel to continue transmission until it is transmitted to the control end.

8. The energy consumption optimization control method for a powder dry pressing servo press according to claim 7, characterized in that: The step of storing the optimal control parameter combination in any one of the storage packets in the transformation region includes: The optimal combination of control parameters is divided into multiple data segments. Based on the parameter values ​​and parameter types, the multiple data segments are grouped into type groups and parameter groups. The type groups and parameter groups are stored on different data chains in the storage package respectively. Based on the correspondence between parameter values ​​and parameter types in the optimal control parameter combination, a corresponding chain is established between corresponding data points. The corresponding chain is obtained by connecting lines and connection ports.

9. The energy consumption optimization control method for a powder dry pressing servo press according to claim 8, characterized in that: The step of storing the optimal control parameter combination between different storage packets based on changes in transmission nodes includes: Obtain the current transmission node of the transformation zone and the storage point where the storage packet in the transformation zone is located; When the transmission node where the transformation area is located changes, the storage packet is transferred from the current storage point to another storage point. At the same time, the connection port of the data point where the parameter value is located is changed, and the movement path of the connection line between multiple connection ports is recorded. After transmitting the optimal combination of control parameters to the control terminal via the storage packet, the correspondence between the connection line and the connection port is restored according to the movement path.

10. A powder dry pressing servo press energy consumption optimization control system, applied to the powder dry pressing servo press energy consumption optimization control method as described in any one of claims 1-9, characterized in that, include: The initial setup module is used to determine the target powder to be pressed and molded, and determines the dry pressing parameters corresponding to the target powder based on the cloud server. The model building module is used to build an energy consumption optimization model, and based on the energy consumption optimization model, the dry pressing parameters are optimized to determine the optimal combination of control parameters; The channel establishment module is used to establish a transmission channel between the cloud server and the control terminal. The transmission channel includes two transmission channels and a connection chain between the two transmission channels. The press control module is used to transmit the optimal combination of control parameters to the control terminal based on the transmission zone. The control terminal then controls the servo press using the optimal combination of control parameters.

Images