Process parameter setting system and method for engineering equipment

Abstract

The invention relates to the technical field of control systems, and discloses a process parameter setting system and method for engineering equipment, and the system comprises a parameter collection module which collects the operation parameters of the equipment in real time through a sensor; the intelligent calculation module is used for constructing an optimization objective function of the process parameters based on the operation parameters and generating an optimal parameter combination in combination with a multi-objective optimization algorithm and constraint conditions; the dynamic feedback module is used for monitoring the dynamic change of the process parameters in real time and dynamically adjusting the process parameters through a reinforcement learning algorithm; and the execution control module transmits the adjusted process parameters to an execution mechanism of the equipment. According to the method, the optimal parameter combination is generated by constructing the technological parameter optimization objective function and combining the multi-objective optimization algorithm and the constraint condition, and automatic adjustment is performed through the execution control module, so that compared with the prior art depending on manpower or simple control logic, the problems of complicated adjustment, response lag and poor adaptability are solved, and the method is suitable for large-scale popularization and application. And the equipment operation precision and efficiency are obviously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of control systems, and in particular to a process parameter setting system and method for engineering equipment. Background Art

[0002] In industrial production, equipment operating parameters (such as temperature, pressure and load) are key factors affecting process flow and product quality. Accurate control of equipment parameters is not only related to the improvement of production efficiency, but also directly affects energy utilization and equipment life. In complex process flows, there is usually a significant coupling relationship between different parameters, and they are affected by the dynamic changes of the operating environment. Therefore, the optimization and control of equipment parameters are extremely important in industrial automation and are the core means to achieve efficient, energy-saving and stable production.

[0003] However, the existing technology still has many deficiencies in the setting and optimization of process parameters. Most of them rely on manual experience or preset simple control logic, which is difficult to cope with the complexity and dynamics of the process flow. Especially in the case of multiple variables, the manual adjustment process is complicated, the response speed is slow, and the adaptability to the environment is insufficient, which in turn affects the accuracy and efficiency of equipment operation, and may even cause process instability, resulting in a decrease in yield rate. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a process parameter setting system and method for engineering equipment, which solves the problems in the prior art of complex manual adjustment process, slow response speed, and insufficient environmental adaptability, which affect the accuracy and efficiency of equipment operation, cause process instability, and lead to a decrease in yield rate.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a process parameter setting system for engineering equipment, comprising:

[0006] A parameter acquisition module collects the operating parameters of the equipment in real time through sensors, wherein the operating parameters include the temperature, pressure and load of the equipment;

[0007] Intelligent computing module, based on operating parameters, constructs the optimization objective function of process parameters, and generates the optimal parameter combination by combining multi-objective optimization algorithm and constraint conditions;

[0008] Dynamic feedback module, which monitors the dynamic changes of process parameters in real time and dynamically adjusts the process parameters through reinforcement learning algorithm;

[0009] The execution control module transmits the adjusted process parameters to the equipment's actuator to complete the automatic setting of the equipment's process parameters.

[0010] Preferably, the parameter acquisition module includes:

[0011] Temperature sensor, used to collect the operating temperature of the equipment in real time;

[0012] Pressure sensor, used to collect the pressure value of equipment operation;

[0013] Load sensor, used to collect the operating load of the equipment;

[0014] The data transmission device transmits the collected data to the intelligent computing module through the industrial data interface.

[0015] Preferably, the step of constructing the optimization objective function by the intelligent computing module includes:

[0016] Defining the operating efficiency of the process parameters, wherein the operating efficiency represents the ratio of the effective power of the equipment to the total input power;

[0017] Define the energy consumption of the process, which represents the total energy consumption per unit time;

[0018] defining the stability of the operating parameters, said stability being represented by the standard deviation of the sampled values;

[0019] The operation efficiency, energy consumption and stability are comprehensively considered to generate a multi-objective optimization function.

[0020] Preferably, the constraints of the intelligent computing module in generating the optimization objective function include:

[0021] Boundary conditions of process parameters, including upper and lower limits of temperature, pressure and load;

[0022] Safety constraints ensure that the maximum stress value of the process parameter combination does not exceed the design allowable value of the equipment.

[0023] Preferably, the optimization algorithm for generating the optimal parameter combination by the intelligent computing module includes:

[0024] Use Lagrange multiplier method to construct the joint expression of objective function and constraints;

[0025] Solve the partial derivatives and constraints of the objective function to obtain the global optimal solution;

[0026] Genetic algorithms are used to generate populations and calculate fitness for initial parameter combinations, and parameters are optimized through crossover and mutation operations.

[0027] Preferably, the reinforcement learning algorithm comprises the following steps:

[0028] Define the current process parameter state as the state variable of reinforcement learning;

[0029] Generate reinforcement learning actions by adjusting the increase and decrease of process parameters;

[0030] Calculate the impact value of the adjusted process parameters on the optimization target and generate a reward signal based on the value;

[0031] Update the value function of reinforcement learning and dynamically adjust the optimization strategy.

[0032] Preferably, the execution control module is connected to the actuator of the equipment through an industrial control bus, quickly transmits the optimized process parameters to the equipment, and monitors the response of the equipment in real time through a feedback mechanism.

[0033] Preferably, the intelligent computing module and the dynamic feedback module are combined with a dynamic simulation tool to verify the optimization parameters, and the simulation includes:

[0034] Simulate the impact of parameter adjustments on operating efficiency, energy consumption and stability through equipment mathematical models;

[0035] The optimization objectives are verified and adjusted based on the simulation results.

[0036] Preferably, the system supports multi-device linkage optimization and uses a multi-objective optimization algorithm to generate a global optimal parameter combination between devices to meet the overall process requirements of the production line.

[0037] A method for setting process parameters of engineering equipment comprises the following steps:

[0038] Collecting operating parameters of the equipment in real time, including temperature, pressure and load of the equipment;

[0039] Constructing an optimization objective function of process parameters based on the operating parameters, wherein the objective function is used to comprehensively describe the operating efficiency, energy consumption and stability of the equipment, and combines boundary conditions and safety constraints;

[0040] Based on the optimization objective function, the optimal process parameter combination is generated by combining the multi-objective optimization algorithm;

[0041] Based on the optimal process parameter combination, the reinforcement learning algorithm is used to dynamically adjust the process parameters through the real-time operating parameter feedback of the equipment;

[0042] The dynamically adjusted process parameters are transmitted to the equipment's actuators, and the equipment's automatic adjustment is completed. At the same time, the equipment's operating status is monitored through a feedback mechanism to form a closed-loop optimization.

[0043] The present invention provides a system and method for setting process parameters of engineering equipment, which has the following beneficial effects:

[0044] 1. The present invention constructs an optimization objective function of process parameters according to the collected parameters, generates an optimal parameter combination by using a multi-objective optimization algorithm and constraints, and automatically adjusts the parameters by executing a control module. Compared with the prior art method that relies on manual or simple control logic, the present invention solves the problems of complex adjustment process, slow response speed, and insufficient environmental adaptability, and greatly improves the accuracy and efficiency of equipment operation.

[0045] 2. The present invention uses a dynamic feedback module to dynamically adjust the operating parameters collected in real time using a reinforcement learning algorithm. The module generates an adjustment strategy based on the current state and updates the process parameter optimization effect through real-time feedback. The present invention solves the problem that the prior art relies on static rules and is difficult to adapt to complex dynamic working conditions, enabling the equipment to dynamically adapt to process requirements during operation, greatly improving the system response speed and operating stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the system architecture of the present invention;

[0047] Figure 2 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In order to better understand the present invention, the above contents are described in detail below in conjunction with specific embodiments.

[0050] Example 1

[0051] Please see attached Figure 1 , an embodiment of the present invention provides a process parameter setting system for engineering equipment, comprising:

[0052] A parameter acquisition module collects the operating parameters of the equipment in real time through sensors, wherein the operating parameters include the temperature, pressure and load of the equipment;

[0053] In this embodiment, the parameter acquisition module collects key parameters in the equipment operation process in real time through the sensor network. By collecting these operating parameters, reliable data support is provided for subsequent process parameter optimization, ensuring the overall coordination of the system and real-time data.

[0054] Specifically, the parameter acquisition module is used to collect the operating parameters of the equipment, including but not limited to the temperature, pressure and load of the equipment. Generally, these operating parameters can be collected by dedicated sensors and transmitted to the intelligent computing module through a data interface.

[0055] Specifically, temperature collection can be achieved through thermocouple sensors or infrared temperature sensors. These sensors can monitor local temperature changes of the equipment in real time and output linear signals. The temperature data is represented by T in units of K. As an option, thermocouple sensors can be arranged in areas where heat sources are more concentrated during the operation of the equipment to capture more accurate data.

[0056] Pressure is usually collected using a pressure transmitter, whose output signal can be an analog signal or a digital signal. The pressure parameter is represented by P, and the unit is Pa. In a possible implementation, the installation position of the pressure transmitter can be selected at a part where the pressure gradient is significant during the operation of the equipment, so as to more accurately reflect the load changes of the equipment operation.

[0057] Load collection can be achieved through strain gauges or force sensors. Force sensors can monitor the stress state of the equipment during operation, and the collected data is represented by L, in N. As an alternative, sensors with a high dynamic range can be used to adapt to large changes in equipment load.

[0058] In some embodiments, the parameter acquisition module can also be extended to collect other environmental parameters of the equipment operation, such as humidity, equipment vibration frequency, etc. These environmental parameters can provide a more comprehensive description of the operating status and ensure the accuracy of the input value intelligent computing module data. The parameter acquisition module and the intelligent computing module are connected through an industrial data interface, and commonly used interface protocols include MODBUS, PROFINET or EtherCAT. In a possible implementation, the collected parameter data is transmitted to the intelligent computing module in real time through an industrial communication protocol, and a timestamp is attached to ensure the synchronization and validity of the data.

[0059] The collected operating parameters such as temperature, pressure and load can be further digitally processed by the following formula to eliminate signal noise and improve data quality:

[0060]

[0061] Among them, x i ′ represents the smoothed data of the i-th sampling point; n is the number of sampling points in the time window; x ij is the jth sampling value of the ith acquisition point in the time window.

[0062] Generally, the above smoothing method can effectively eliminate high-frequency noise and improve the stability of parameters. As an option, the size of the time window n can be dynamically adjusted according to the actual operation requirements of the device to balance the sampling accuracy and calculation efficiency.

[0063] In another embodiment, the collected data can also be used to generate real-time monitoring curves. These curves can intuitively show the changing trend of the equipment operation status, such as the function of temperature change over time and the function of pressure change over time.

[0064] And through high-frequency sampling and data transmission optimization, the acquisition module can transmit data with a delay of milliseconds, ensuring that subsequent modules can make decisions based on the latest operating status in optimization calculations.

[0065] Therefore, the data acquisition module ensures the accuracy and real-time nature of the collected data through sensor configuration and flexible data processing mechanism, providing a solid foundation for the subsequent optimization and dynamic adjustment of process parameters. The design of this module can be flexibly expanded according to actual needs and adapt to the operating environment of different types of equipment.

[0066] Intelligent computing module, based on operating parameters, constructs the optimization objective function of process parameters, and generates the optimal parameter combination by combining multi-objective optimization algorithm and constraint conditions;

[0067] In this embodiment, the intelligent computing module constructs a process parameter optimization objective function that can reflect the operating status of the equipment based on the operating parameters of the equipment. By introducing a multi-objective optimization algorithm and constraints, a set of optimal process parameter combinations is generated. These process parameters can not only improve the operating efficiency of the equipment, but also reduce energy consumption and maintain stability under complex conditions.

[0068] Generally, the intelligent computing module obtains data from the parameter acquisition module. After preprocessing, these data are input into the mathematical model to calculate the optimization objective function of the process parameters. The objective function needs to accurately describe the characteristics of the equipment operation and meet the actual operation constraints. By solving this objective function, a set of global optimal process parameters is finally generated.

[0069] Specifically, the core of the optimization objective function lies in the comprehensive balance of three major indicators: operating efficiency, energy consumption and stability. These indicators have a decisive influence on the operating performance of the equipment.

[0070] Operation efficiency is used to evaluate the energy utilization rate E of the equipment during operation. It is defined as the ratio of the effective output power of the equipment to the total input power. For the sake of calculation simplicity, this goal can be expressed by the following formula:

[0071]

[0072] Among them, W out Indicates the effective output power of the device, W in Indicates the total input power of the device, high efficiency means less energy loss.

[0073] Energy consumption is another key indicator. It represents the total energy consumed by the device when it is running. Energy consumption is calculated as follows:

[0074] C=∫0 T P(t)dt

[0075] Where C represents the total energy consumption of the device in the time interval, P(t) represents the instantaneous power of the device at time t, T represents the upper limit of the time interval, that is, the time range from t = 0 to t = T, and t represents the time variable. If higher calculation efficiency is required, the discretization method can be used for approximate calculation:

[0076]

[0077] Where C represents the total energy consumption of the device in the time interval, i represents the index of the current sampling point, ranging from i = 1 to n, and P i represents the power value of the i-th sampling point, and Δt represents the sampling time interval.

[0078] Stability is used to measure the fluctuation of the equipment's operating status. The standard deviation of the parameter is usually used to describe stability:

[0079]

[0080] Among them, S represents the standard deviation, which is used to measure the fluctuation degree of the sampled data, n represents the total number of sampling points, and x i Represents the value of the i-th sampling point. Represents the average value of all sampling points.

[0081] In order to optimize these indicators simultaneously, the comprehensive objective function is constructed as follows:

[0082]

[0083] Among them, F represents the value of the comprehensive optimization objective function, and w1, w2, and w3 represent the weight coefficients of each optimization objective.

[0084] Constraints

[0085] During the optimization process, the process parameters need to meet certain boundary conditions and safety constraints. Boundary conditions limit the range of parameter values, for example:

[0086] T min ≤T≤T max

[0087] P min ≤P≤P max

[0088] L min ≤L≤L max

[0089] Among them, T, P, L represent temperature, pressure and load respectively, and min and max represent upper and lower limits.

[0090] Safety constraints ensure that process parameters do not cause the equipment to exceed design stresses:

[0091] g(T,P,L)≤c max

[0092] Where g(T,P,L) is the calculation function of equipment stress, c max It is the maximum stress value allowed in equipment design.

[0093] Multi-objective optimization algorithm

[0094] In this embodiment, a variety of optimization algorithms are used to solve the objective function and constraint condition problems.

[0095] First, the objective function and constraints are combined through the Lagrangian method:

[0096]

[0097] in, It is a Lagrangian function, which is used to combine the objective function and the constraints together and find the optimal solution by solving its extreme value.

[0098] By taking partial derivatives of L(T,P,L,λ), we can find the necessary conditions for the optimal solution:

[0099]

[0100] It means that the partial derivative with respect to temperature T is zero, and the optimal value of the optimization objective F with respect to T is solved while satisfying the constraints;

[0101]

[0102] It means that the partial derivative with respect to pressure P is zero, and the optimal value of the optimization objective F with respect to P is solved while satisfying the constraints;

[0103]

[0104] It means that the partial derivative with respect to the load L is zero, and the optimal value of the optimization objective F with respect to L is solved while satisfying the constraints;

[0105]

[0106] It means that the partial derivative of the Lagrange multiplier λ is zero, and the optimal value of the optimization objective F with respect to T is solved while satisfying the constraint g(T,P,L)-c max =0 is satisfied;

[0107] For complex nonlinear problems, genetic algorithms are used for further optimization. The steps of genetic algorithms include:

[0108] Population initialization: randomly generate several parameter combinations;

[0109] Fitness evaluation: calculate the objective function value;

[0110] Crossover and mutation: generate new parameter combinations;

[0111] Convergence judgment: When the objective function value is stable, the optimal solution is output.

[0112] Therefore, the intelligent computing module can significantly improve the operating efficiency of the equipment, reduce energy consumption, and ensure the stability of equipment operation. More importantly, the optimization results of this module can be fed back to subsequent modules in real time, supporting dynamic adjustment and closed-loop control, ensuring the accuracy and real-time optimization of process parameters.

[0113] In some embodiments, the intelligent computing module can also be combined with historical operation data to dynamically adjust the optimization model using machine learning algorithms. This adaptive optimization method further enhances the flexibility of the system, enabling it to adapt to different equipment and complex process conditions.

[0114] In addition, the intelligent computing module also integrates the process algorithm library, historical operation data and equipment model internally to provide a reliable analysis basis. The process algorithm library contains a large number of mathematical models and optimization methods related to equipment processes, which are used to describe the complex coupling relationship between process parameters (such as temperature, pressure and load). Historical operation data provides prior knowledge of actual working conditions. By analyzing historical data, the potential relationship between process parameters and equipment performance can be discovered. The equipment model provides constraints and process boundaries for optimization calculations in the form of physical or numerical simulation.

[0115] At the same time, in the data processing process, the intelligent computing module uses machine learning or expert system algorithms. These algorithms can analyze the impact of process parameters from multiple dimensions through training and reasoning capabilities. For example, machine learning algorithms (such as support vector machines, random forests, or neural networks) can predict the impact of specific process parameters on equipment performance based on historical operating data, thereby quickly finding the optimal parameter combination. As an option, expert system algorithms make logical judgments and decisions on complex process scenarios based on rule bases and reasoning mechanisms, which are particularly suitable for process problems with strong nonlinearity and multivariable coupling.

[0116] Specifically, the optimal process parameter combination is generated through the following steps:

[0117] First, select the optimization goal (such as maximizing efficiency, minimizing energy consumption, or optimizing stability) according to the user's needs. Users can adjust the parameter weights through the interface provided by the module to customize the priority of the optimization goal.

[0118] Then, the potential impact of process parameters is modeled and predicted by combining the currently collected operating parameters with historical data. For example, the following relationship model is established through machine learning algorithms:

[0119] y=f(T,P,L)

[0120] Where y represents the optimization target (such as efficiency or energy consumption); T, P, and L represent temperature, pressure, and load, respectively.

[0121] Next, the optimization algorithm is used to search for the optimal parameter combination that achieves the optimization goal while satisfying the constraints of the device model:

[0122]

[0123] Among them, F(T,P,L) represents the comprehensive optimization objective function, which includes the trade-offs of efficiency, energy consumption and stability.

[0124] Indicates the minimum value of T, P, and L.

[0125] Therefore, on this basis, according to the comprehensive objective function, users can adjust the weight of the objective function according to specific process requirements. For example, when the production process pays more attention to energy saving, the value of the energy consumption weight w2 can be increased, and the efficiency weight w1 and stability weight w3 can be reduced accordingly. Therefore, the module can automatically re-optimize according to the weight adjustment to generate the best parameter combination that meets user needs.

[0126] In one possible implementation, the intelligent computing module also supports switching between multiple optimization algorithms, such as genetic algorithm, particle swarm optimization or simulated annealing, to adapt to process optimization problems of different complexity.

[0127] In addition, the optimization scheme of the intelligent computing module will be stored and combined with historical data to form an iterative optimization process. By continuously updating the algorithm's training data, the module can gradually adapt to the actual operating characteristics of the device and achieve precise optimization. For example, during long-term operation, the module can use the real-time feedback of the device to adjust the algorithm parameters, thereby improving the optimization accuracy.

[0128] And when the production line includes multiple devices, the intelligent computing module can coordinate and optimize the parameters of each device based on the global process requirements. For example, when the load of one device increases, the module can adjust the process parameters of other devices in a coordinated manner to ensure the overall stability and efficiency of the production line.

[0129] Therefore, through the deep integration of process algorithm library, historical data and equipment model, as well as intelligent analysis of machine learning or expert system, powerful process parameter optimization capability is provided for equipment operation. This design not only meets the multi-objective optimization requirements in complex process scenarios, but also can continuously improve equipment performance and resource utilization in actual operation.

[0130] Dynamic feedback module, which monitors the dynamic changes of process parameters in real time and dynamically adjusts the process parameters through reinforcement learning algorithm;

[0131] In this embodiment, the dynamic feedback module monitors the dynamic changes of the process parameters in real time, and uses the reinforcement learning algorithm to dynamically adjust the process parameters according to the real-time feedback of the equipment operation status. Through this module, the operating parameters of the equipment can always be kept in an optimized state in actual working conditions, ensuring the continuous improvement of the overall performance.

[0132] In general, the dynamic feedback module works in conjunction with the intelligent computing module and the execution control module. It not only monitors the optimized process parameters, but also adjusts the parameters according to the changes in the equipment operating status, making the optimization plan more real-time and adaptable. Under complex operating conditions, the module can autonomously explore the best adjustment strategy through reinforcement learning algorithms to adapt to changing operating conditions.

[0133] Specifically, the dynamic feedback module first obtains the current value of the process parameter in real time. For example, through the real-time data such as temperature T, pressure P, load L transmitted by the sensor, the dynamic feedback module can evaluate the current operating status of the equipment.

[0134] Specifically, the dynamic feedback module uses a reinforcement learning algorithm to dynamically optimize and adjust the process parameters. The basic elements of reinforcement learning include state s, action a, reward r and strategy α. In the present invention, these elements are defined as follows:

[0135] Status s: The current values ​​of process parameters and feedback data on the equipment operating status, such as the current values ​​of temperature, pressure, and load.

[0136] Action a: Adjustment of process parameters, such as increasing temperature, reducing pressure or adjusting load.

[0137] Reward r: The degree of improvement in the equipment performance caused by the adjustment operation, such as improvement in operating efficiency, reduction in energy consumption, etc.

[0138] In general, the dynamic feedback module is based on the current state s t Select an action t , and adjust the equipment process parameters. The adjusted process parameters will affect the operating status of the equipment. The system calculates the reward value r through a real-time feedback mechanism. t , and update the value function of reinforcement learning.

[0139] Value function Q(s t ,a t ) is updated as:

[0140]

[0141] Among them, Q(s t ,a t ) means in state s t Next, perform action a t The expected cumulative reward value that can be obtained, r t Indicates execution of action a t After the current state s t The reward value obtained under the condition is used to evaluate the quality of the action, α is the learning rate, γ is the discount factor, which indicates the influence weight of future rewards. Indicates that in the next state s t+1 Next, represents the future expected reward of the best policy starting from the next state.

[0142] As an option, the dynamic feedback module can use deep reinforcement learning technology to replace the traditional value function table with a neural network, so as to more efficiently handle process parameter adjustment problems in complex working conditions.

[0143] In one possible implementation, the action set of the dynamic feedback module can be further expanded. For example, not only can the basic process parameters such as temperature, pressure, and load be adjusted, but the weight of the collected data can also be dynamically corrected to make the optimization results more in line with actual operation requirements.

[0144] Specifically, the dynamic feedback module can achieve dynamic optimization and adjustment of process parameters through the following steps:

[0145] In some embodiments, the dynamic feedback module can also be used in combination with a dynamic simulation tool. For example, before adjusting the process parameters, the possible impact of the adjustment is simulated, and then the adjustment is decided based on the simulation results. This approach can further reduce the risk of adjustment and improve the stability of the system.

[0146] In general, the introduction of dynamic feedback modules can significantly improve the robustness and adaptability of the system. Through the dynamic adjustment of the reinforcement learning algorithm, the process parameters can be automatically optimized according to the actual operating status without human intervention. This not only improves the operating efficiency of the equipment, but also reduces energy consumption and operating fluctuations.

[0147] This module can also be combined with historical operation data to improve the quality of the initial strategy of reinforcement learning through data analysis. For example, the initial value function can be generated based on the historical operation parameters of the device, thereby reducing the cold start time of learning.

[0148] The execution control module transmits the adjusted process parameters to the equipment's actuator to complete the automatic setting of the equipment's process parameters.

[0149] In this embodiment, the execution control module transmits the adjusted process parameters output by the dynamic feedback module to the equipment actuator to complete the automatic setting of the equipment. Through the execution control module, the optimization results of the system can directly act on the equipment, thereby realizing the precise adjustment of the process parameters and the real-time optimization of the equipment operation status.

[0150] Generally, the execution control module maintains real-time communication with the dynamic feedback module and the equipment actuator. It not only receives the optimization parameters, but also transmits them to the equipment control system in an adaptive format. At the same time, the execution control module can monitor the response of the equipment actuator to ensure that the optimization parameters can be correctly executed and provide timely feedback on possible abnormal situations.

[0151] Specifically, the execution control module is connected to the equipment actuator via an industrial control bus (such as EtherCAT or PROFINET). The optimized process parameters are packaged as standardized control signals and transmitted to the equipment actuator.

[0152] Specifically, the transfer of optimization parameters can be achieved according to the following process:

[0153] The setting of temperature T is transmitted to the temperature control system by the execution control module, and the target temperature is automatically adjusted by adjusting the heating or cooling equipment.

[0154] The pressure P is adjusted by controlling the pneumatic or hydraulic system. The actuator can automatically adjust the pressure valve according to the transmitted target value.

[0155] The load L is adjusted by the load control system, which adjusts the power output of the drive motor to make the load reach the target value.

[0156] Generally, the transmission of process parameters needs to take into account the response delay of the equipment and the nonlinear characteristics of the actual operation. To this end, in this embodiment, the execution control module includes a real-time monitoring and feedback mechanism while sending the optimization parameters.

[0157] As an option, the execution control module can achieve closed-loop control in the following way: after the optimized parameters are transmitted to the device, the actual response value of the actuator is collected again by the sensor and compared with the target value. If the deviation exceeds the set threshold, the execution control module will compensate for the deviation by adjusting the signal until the device response value reaches the target value.

[0158] In a possible implementation, the feedback mechanism of the execution control module can adopt a proportional-integral-derivative (PID) control algorithm. The adjustment formula of PID control is as follows:

[0159]

[0160] Among them, u(t) is the control signal, which represents the adjustment value of the actuator, such as valve opening, motor speed, etc. e(t) is the deviation value, which represents the difference between the current measurement value and the target value, and is defined as e(t) = r(t) - y(t), where r(t) is the target value and y(t) is the actual measurement value. K p is the proportional coefficient, which is used to control the deviation e(t) and the direct contribution to the control signal u(t). The larger its value, the faster the response, but it may cause system instability. i K is the integral coefficient, which is used to accumulate the influence of deviation over time and eliminate the static error of deviation. d is the differential coefficient, used to control the rate of change of deviation The impact on the control signal can improve the system's ability to respond to rapid changes and reduce overshoot. is the cumulative value of the deviation e(τ) from time 0 to t. The integral term reflects the cumulative effect of long-term deviation.

[0161] In some embodiments, the execution control module can also support the joint control of multiple devices. For example, on a production line, the actuators of multiple devices need to adjust different process parameters at the same time. The execution control module can distribute the optimized parameters to each device and coordinate their execution order to ensure the smooth operation of the entire production line.

[0162] Specifically, the linkage of multiple devices can adopt a distributed control architecture. The actuator of each device has an independent control unit, and the execution control module acts as a central coordinator, communicating with multiple devices through the bus protocol, distributing optimization parameters and synchronizing the operating status of each device.

[0163] In this embodiment, the execution control module can also dynamically adjust the process parameters according to the load changes during operation. For example, when it is detected that the load L exceeds the safety range, the module will trigger the linkage adjustment of the pressure P and the temperature T to avoid overload operation of the equipment.

[0164] Therefore, by executing the control module, the optimized process parameters can be quickly and accurately applied to the equipment, forming a complete closed-loop optimization system, which can not only significantly improve the operating efficiency of the equipment, but also effectively reduce the operating cost and improve the stability of the overall process.

[0165] In addition, the interactive display module can be used to present the current operating status of the equipment, recommended parameter setting schemes and optimization results to the user in an intuitive way. Therefore, the user can understand the working conditions of the equipment in real time and manually adjust or confirm the process parameters when necessary, so as to more flexibly adapt to actual production needs.

[0166] Specifically, the information is displayed in various forms, including real-time data curves, recommended values ​​of optimization parameters, and visual models of equipment operation status. The module supports two interactive modes: touch screen interface and remote control terminal. Users can choose the appropriate operation mode according to the production environment. The touch screen interface is suitable for on-site equipment operation, while the remote control terminal is convenient for centralized monitoring or remote management.

[0167] At the same time, the core functions of the interactive display module include the following aspects:

[0168] Real-time display of equipment status

[0169] The interactive display module can dynamically present the key operating parameters of the equipment, such as temperature, pressure P, load L, etc. Specifically, the current parameter value will be displayed in real time in digital form, and combined with trend charts or bar charts to intuitively show the historical changes and current trends of the equipment operation.

[0170] For example, when the temperature of a device changes dramatically, the system will use color highlighting or alarms to remind users to pay attention to temperature anomalies, thereby reducing operational risks.

[0171] Presentation of recommended parameter settings

[0172] The system generates the recommended process parameter combinations through the intelligent calculation module and displays them in a clear manner on the interface. The target explanation of parameter optimization will be attached next to the recommended value (such as reducing energy consumption by 10% and increasing efficiency by 15%), so that users can quickly understand the meaning of the recommended parameters.

[0173] In some embodiments, the interactive display module will also provide a variety of optimization solutions, such as "high efficiency first", "low energy consumption first" or "stability first", etc., to meet the needs of different process scenarios.

[0174] Parameter adjustment and real-time feedback

[0175] The interactive display module allows users to adjust process parameters directly through the interface. Specifically, users can change the target value of temperature, pressure or load through sliders, input boxes or selection menus. The adjusted parameters will act on the equipment in real time through the dynamic feedback module, and its impact results will be dynamically updated on the display interface. For example, when the user adjusts the temperature target value, the interface will also display the predicted changes in energy consumption and stability after the adjustment, so that the user can evaluate the effect of the adjustment.

[0176] As an option, the interactive interface can also display optimized simulation prediction results, such as adjusted energy curves, efficiency curves, and fluctuation curves.

[0177] User confirmation and operation records

[0178] On the interface, users can choose to directly apply the recommended parameters, or click the confirmation button after adjustment to apply the customized parameters to the device. All user operations, including parameter adjustment records and confirmation time, will be recorded and stored by the system for subsequent analysis and optimization.

[0179] Specifically, before confirming the parameters, the interface will prompt the user of the possible impact of parameter adjustment, such as "the current settings may cause a 5% decrease in operating efficiency, please confirm whether to continue."

[0180] Scalable interface layout

[0181] In one possible implementation, the interactive display module supports a multi-screen switching function. For example, switching between the equipment operation information interface and the optimization result analysis interface allows the user to obtain more information in a limited display area. In addition, the module interface layout can be customized according to user preferences, such as adjusting the parameter display order, hiding unnecessary functions, etc.

[0182] In some embodiments, the interactive display module also supports multi-user authority management. For example, ordinary operators can view the operating status and apply recommended parameters, while advanced users can directly adjust the optimization strategy or modify the boundary range of parameters.

[0183] Example 2

[0184] Please see attached Figure 2 This embodiment provides a method for setting process parameters of engineering equipment using the above system, including the following steps:

[0185] Collect the equipment's operating parameters in real time, including the equipment's temperature, pressure, and load;

[0186] Based on the operating parameters, the optimization objective function of the process parameters is constructed. The objective function is used to comprehensively describe the operating efficiency, energy consumption and stability of the equipment, and is combined with boundary conditions and safety constraints;

[0187] Based on the optimization objective function, the optimal process parameter combination is generated by combining the multi-objective optimization algorithm;

[0188] Based on the optimal process parameter combination, the reinforcement learning algorithm is used to dynamically adjust the process parameters through the real-time operating parameter feedback of the equipment;

[0189] The dynamically adjusted process parameters are transmitted to the equipment's actuators, and the equipment's automatic adjustment is completed. At the same time, the equipment's operating status is monitored through a feedback mechanism to form a closed-loop optimization

[0190] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A process parameter setting system for engineering equipment, characterized in that: include: A parameter acquisition module collects the operating parameters of the equipment in real time through sensors, wherein the operating parameters include the temperature, pressure and load of the equipment; Intelligent computing module, based on operating parameters, constructs the optimization objective function of process parameters, and generates the optimal parameter combination by combining multi-objective optimization algorithm and constraint conditions; Dynamic feedback module, which monitors the dynamic changes of process parameters in real time and dynamically adjusts the process parameters through reinforcement learning algorithm; The execution control module transmits the adjusted process parameters to the equipment's actuator to complete the automatic setting of the equipment's process parameters.

2. The process parameter setting system for engineering equipment according to claim 1, characterized in that: The parameter acquisition module comprises: Temperature sensor, used to collect the operating temperature of the equipment in real time; Pressure sensor, used to collect the pressure value of equipment operation; Load sensor, used to collect the operating load of the equipment; The data transmission device transmits the collected data to the intelligent computing module through the industrial data interface.

3. The process parameter setting system for engineering equipment according to claim 1, characterized in that: The steps of constructing the optimization objective function by the intelligent computing module include: Defining the operating efficiency of the process parameters, wherein the operating efficiency represents the ratio of the effective power of the equipment to the total input power; Define the energy consumption of the process, which represents the total energy consumption per unit time; defining the stability of the operating parameters, said stability being represented by the standard deviation of the sampled values; The operation efficiency, energy consumption and stability are comprehensively considered to generate a multi-objective optimization function.

4. A process parameter setting system for engineering equipment according to claim 3, characterized in that: The constraints of the intelligent computing module in generating the optimization objective function include: Boundary conditions of process parameters, including upper and lower limits of temperature, pressure and load; Safety constraints ensure that the maximum stress value of the process parameter combination does not exceed the design allowable value of the equipment.

5. A process parameter setting system for engineering equipment according to claim 4, characterized in that: The optimization algorithm for generating the optimal parameter combination by the intelligent computing module includes: Use Lagrange multiplier method to construct the joint expression of objective function and constraints; Solve the partial derivatives and constraints of the objective function to obtain the global optimal solution; Genetic algorithms are used to generate populations and calculate fitness for initial parameter combinations, and parameters are optimized through crossover and mutation operations.

6. The process parameter setting system for engineering equipment according to claim 1, characterized in that: The reinforcement learning algorithm comprises the following steps: Define the current process parameter state as the state variable of reinforcement learning; Generate reinforcement learning actions by adjusting the increase and decrease of process parameters; Calculate the impact value of the adjusted process parameters on the optimization target and generate a reward signal based on the value; Update the value function of reinforcement learning and dynamically adjust the optimization strategy.

7. The process parameter setting system for engineering equipment according to claim 1, characterized in that: The execution control module is connected to the actuator of the equipment through the industrial control bus, quickly transmits the optimized process parameters to the equipment, and monitors the equipment response in real time through the feedback mechanism.

8. The process parameter setting system for engineering equipment according to claim 1, characterized in that: The intelligent calculation module and the dynamic feedback module are combined with a dynamic simulation tool to verify the optimization parameters, and the simulation includes: Simulate the impact of parameter adjustments on operating efficiency, energy consumption and stability through equipment mathematical models; The optimization objectives are verified and adjusted based on the simulation results.

9. The process parameter setting system for engineering equipment according to claim 1, characterized in that: The system supports multi-device linkage optimization and uses a multi-objective optimization algorithm to generate a global optimal parameter combination between devices to meet the overall process requirements of the production line.

10. A method for setting process parameters of engineering equipment, based on a system for setting process parameters of engineering equipment according to any one of claims 1 to 9, characterized in that: The following steps are involved: Collecting operating parameters of the equipment in real time, including temperature, pressure and load of the equipment; Constructing an optimization objective function of process parameters based on the operating parameters, wherein the objective function is used to comprehensively describe the operating efficiency, energy consumption and stability of the equipment, and combines boundary conditions and safety constraints; Based on the optimization objective function, the optimal process parameter combination is generated by combining the multi-objective optimization algorithm; Based on the optimal process parameter combination, the reinforcement learning algorithm is used to dynamically adjust the process parameters through the real-time operating parameter feedback of the equipment; The dynamically adjusted process parameters are transmitted to the equipment's actuators, and the equipment's automatic adjustment is completed. At the same time, the equipment's operating status is monitored through a feedback mechanism to form a closed-loop optimization.

Images