A lean control method for energy consumption state of a machining equipment

Abstract

The present application relates to a kind of lean control methods of machining equipment energy consumption state, belong to energy consumption intelligent management and control technical field.The method includes the following steps: S1: obtaining production scheduling scheme from production information system;S2: establishing equipment multi-source energy consumption characteristic model, energy consumption prediction model and equipment energy consumption state control model;S3: establish and train equipment fault repair time prediction model;S4: update S2 equipment energy consumption state control model;S5: according to the control scheme generated by the equipment energy consumption state control model updated in S4, the state of the device is controlled by edge computer.This application is based on the multi-source characteristics of machining equipment energy consumption, and the energy consumption of the equipment is modeled, which is beneficial to the energy consumption of the production process.Statistics;The composition of non-value-added energy consumption in the processing process is analyzed, and the state of non-value-added operation time of the equipment is controlled leanly combined with production scheduling plan, to realize the energy saving and emission reduction of machining equipment.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of energy consumption intelligent management and control, and relates to a lean control method for energy consumption state of a machining equipment. BACKGROUND

[0002] Due to the multi-source and dynamic nature of equipment energy consumption in the manufacturing process, there is a lot of waste of equipment energy consumption during non-value-added operation, which poses a challenge to energy saving and emission reduction in the manufacturing process. Therefore, a method for reducing non-value-added energy waste of equipment is urgently needed.

[0003] When energy saving and management of equipment are performed, the multi-element and dynamic nature of equipment energy consumption can easily cause the equipment energy consumption model to be inaccurate, resulting in the inability to obtain effective control strategies, which is not conducive to lean control of energy saving of equipment during non-value-added operation. In the process of realizing energy saving and management of equipment, in order to avoid this phenomenon, it is particularly important to establish a lean control method for the energy consumption state of equipment that can be self-adaptively updated. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a lean control method for the energy consumption state of a machining equipment, which solves the technical problems of large non-value-added energy consumption waste of the machining equipment and low accuracy of the control strategy of the energy consumption state of the equipment. According to the multi-source characteristics of the energy consumption of the machining equipment, the energy consumption of the equipment is modeled, which is conducive to the statistics of the energy consumption of the production and processing process; the composition of the non-value-added energy consumption in the processing process is analyzed, and the state of the non-value-added operation time of the equipment is controlled in lean mode in combination with the production scheduling plan, so as to realize energy saving and emission reduction of the machining equipment.

[0005] To achieve the above purpose, the present application provides the following technical scheme:

[0006] A lean control method for the energy consumption state of a machining equipment, comprising the following steps:

[0007] S1: obtaining a production scheduling scheme: obtaining power characteristics of each component of the machining equipment in different states from a manufacturing enterprise production process execution system MES, an enterprise resource planning system ERP, and a production and manufacturing operation management system MOM;

[0008] S2: establishing an equipment energy consumption, prediction, and control model: establishing an equipment multi-source energy consumption characteristic model and an energy consumption prediction model according to the power characteristics of each component of the equipment in different states, and establishing an equipment energy consumption state control model according to the equipment multi-source energy consumption characteristic model and the equipment energy consumption prediction model;

[0009] S3: processing dynamic interference: collecting fault information and repair information of the equipment during production to form a data set, and establishing and training an equipment fault repair time prediction model by using a deep learning algorithm;

[0010] S4: updating the device energy consumption state control model: establishing an accuracy identification model, comparing the accuracy fitting rates of the new and old energy consumption prediction models, selecting the energy consumption prediction model with a high fitting rate for reservation, and updating the device energy consumption state control model according to the reserved energy consumption prediction model;

[0011] S5: device state control: according to the updated device energy consumption state control model in S4, combining the time sequence of the workpiece arriving at and leaving the device obtained from the production scheduling scheme, obtaining a device energy-saving control scheme, and installing an edge computing gateway on the device to complete the control of the device state.

[0012] Further, in S2, the device multi-source energy consumption characteristic model:

[0013]

[0014] In the formula, E represents the total energy consumption of the device during non-value-added operation, I represents the total number of components included in the device, t i,r , t i,s , t i,su respectively represent the idle time of component i, the time length of the shutdown process of component i, and the time length of the startup process of component i, p i,r , p i,s , p i,su respectively represent the power during the idle time of component i, the power during the shutdown process of component i, and the power during the startup process of component i.

[0015] Further, combined with the historical power information of each component of the device, a weighted moving average method is used to predict the power values of each component, and an energy consumption prediction model is established according to the predicted power values of each component:

[0016]

[0017]

[0018]

[0019]

[0020] In the formula, E pri is the predicted energy consumption value, are the idle power, shutdown process power, and startup process power of component i, are the idle power at the 1st, 2nd, 3rd, and nth time points before the current time point of component i, are the shutdown process power at the 1st, 2nd, 3rd, and nth time points before the current time point of component i, are the startup process power at the 1st, 2nd, 3rd, and nth time points before the current time point of component i, w1, w2, w3, w nThe weight of the actual power of the component i at the current time point and the previous 1, 2, 3, n time points.

[0021] Further, in the S2, the device energy consumption state control model is established, that is, the energy consumption model of each component in different time periods is calculated according to the power data of each component in different states, as shown in formula (6), and the value of M(i, t) is calculated as the target of minimizing E(i, t) to obtain the state control model of the component i, and the device energy consumption state control model of the device is established, as shown in formula (7):

[0022]

[0023]

[0024] In the formula, E(i, t) represents the energy consumption of the component i in the non-value-added operation time of t, M represents the device energy consumption state control model, represents the control strategy of the i-th component of the device, is the time point when the i-th component is turned on, is the time point when the i-th component is turned off.

[0025] Further, in the S3, the data style required for establishing the device fault repair time prediction model in the prediction of dynamic interference is as follows:

[0026] Data fau ={i, ft, rt} (8)

[0027] In the formula, Data fau represents a device fault data set, i represents the fault component number, ft represents the fault type, and rt represents the time required for fault repair.

[0028] Further, in the S4, the precision identification model is:

[0029]

[0030] In the formula, represents the precision fitting rate of the energy consumption prediction model, E mea represents the actual power of the device monitored, represents the predicted power obtained by the energy consumption prediction model, μ E represents the average measured energy consumption.

[0031] Further, in the S4, the updated device energy consumption state control model is:

[0032]

[0033] In the formula, M * ​representing an updated device energy consumption state control model, representing a new control strategy of the i-th component of the device, representing a new start time point of the i-th component, representing a new stop time point of the i-th component.

[0034] Further, in the S5, the device energy saving control scheme is:

[0035] F(k)={f1(k),f2(k),...,f i (k),...,f I (k)} (11)

[0036] F * (k)={f1 * (k),f2 * (k),...,f i * (k),...,f I * (k)} (12)

[0037] In the formula, F(k), F * (k) represent the old and new control schemes of the device at the time point k, f i (k), f i *(k) represent the old and new control schemes of the i-th component of the device at the time point k.

[0038] The present application has the following advantages:

[0039] First, the present application combines deep learning to establish a device fault repair time prediction algorithm and a device component power fluctuation adaptive update device energy consumption state lean control model to improve the precision of the model.

[0040] Second, the present application integrates the prediction model and the control strategy model in the microcomputer system of the edge computing gateway installed on each device, generates a device energy consumption state lean control scheme in combination with the device scheduling information of the production scheduling scheme, and completes the energy consumption state lean control of the device component level in step S5 through the connection of the edge computing gateway and the device control system, which helps to reduce the energy consumption of non-value-added operation of the device.

[0041] Other advantages, objects, and features of the present application will be in part apparent and in part pointed out hereinafter in the specification, and will be observed by those skilled in the art upon examination of the following specification, or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by the means recited in the following specification. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to make the objects, technical solutions and advantages of the present application clearer, the preferred embodiments of the present application will be described in detail below with reference to the drawings, in which:

[0043] Fig. 1 The overall solution diagram for providing the preferred embodiments of the present application is shown in the figure;

[0044] Fig. 2 The diagram for obtaining the production scheduling scheme of the present application is shown in the figure;

[0045] Fig. 3 The diagram for establishing the device energy consumption, prediction and control model of the present application is shown in the figure;

[0046] Fig. 4 The diagram for processing the dynamic interference of the present application is shown in the figure;

[0047] Fig. 5 The diagram for updating the device energy consumption state control model of the present application is shown in the figure;

[0048] Fig. 6 The schematic diagram for updating the device energy consumption state control model of the present application is shown in the figure. DETAILED DESCRIPTION

[0049] The embodiments of the present application are described below through specific examples, and other advantages and effects of the present application can be easily understood by those skilled in the art from the disclosure of the present specification. The present application can also be implemented or applied through other different embodiments, and each detail in the present specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0050] The drawings are only used for exemplary illustration, and the representation is only a schematic diagram, not a physical diagram, and should not be understood as a limitation of the present application. In order to better illustrate the embodiments of the present application, some components in the drawings may be omitted, enlarged or reduced, and do not represent the actual size of the product. It is understandable for those skilled in the art that some well-known structures and their descriptions in the drawings may be omitted.

[0051] The same or similar reference numerals in the drawings of the embodiments of the present application correspond to the same or similar components; in the description of the present application, it is understood that if the orientations or positional relationships indicated by the terms "upper", "lower", "left", "right", "front", "back", etc. are based on the orientations or positional relationships shown in the drawings, they are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, therefore the terms describing the positional relationships in the drawings are only used for exemplary illustration and cannot be understood as a limitation on the present application, for those skilled in the art, the specific meanings of the above terms can be understood according to the specific circumstances.

[0052] Please refer to Figs. 1-6 A lean control method for energy consumption state of a machining equipment, the specific steps are as follows:

[0053] Step 1: Obtain a production scheduling scheme.

[0054] In actual production, the production scheduling scheme will give the production scheduling plan of the equipment, through which the sequence of the workpieces to be produced by the equipment and the approximate time of each workpiece to arrive at the equipment can be determined, so that the range of each non-value-added working time of the equipment can be determined. Therefore, before controlling the state of the equipment, the production scheduling scheme of the equipment needs to be obtained first, and the specific steps are as follows:

[0055] Connect the interface of the production informatization system: access the interface of the MES, ERP, MOM and other production informatization management systems through the edge gateway.

[0056] Export the production scheduling scheme: export the production scheduling scheme from the interface of the connected production informatization system.

[0057] Extract the machining time sequence of the equipment: extract data from the exported production scheduling scheme to obtain the machining time sequence of the target equipment, and the data format is: {workpiece name, machining equipment, arrival time, departure time}.

[0058] Step 2: Establish an equipment energy consumption, prediction and control model module

[0059] Before controlling the state of the equipment, an equipment energy consumption state control model needs to be established according to the energy consumption characteristics of the equipment, so as to determine which control scheme can maximize the reduction of non-value-added energy consumption of the equipment in the non-machining time period at different production time intervals, including the following specific steps:

[0060] Dig up the energy consumption characteristics of the equipment: by detecting the power information and state of each component of the equipment, the energy consumption characteristics of each component of the equipment in different states are dug up, laying a foundation for establishing the multi-dormant state energy consumption model of the equipment.

[0061] Establishing a device energy consumption prediction model: combining the historical power information of each component of the device, using the weighted moving average method to predict the power value of each component, and establishing an energy consumption prediction model according to the predicted power value of each component, providing predicted power information of each component under different states for establishing a device state control strategy model.

[0062] Establishing a device energy consumption state control model: according to the established energy consumption characteristic model and energy consumption prediction model, solving the state control model of the device. This control model can solve the optimal control scheme under different production conditions to achieve the purpose of reducing non-value-added energy consumption.

[0063] Determining the device control scheme: combining the established device energy consumption state control model and the estimated workpiece arrival time, determining the device control scheme. This scheme can control the state of each component of the device during non-value-added operation time to achieve the purpose of energy saving.

[0064] Step 3: Predicting dynamic disturbance processing.

[0065] In actual production process, production disturbance is inevitable, and the device may have interference events mainly caused by failure. Through the deep learning framework, a device repair time prediction model is established to predict the repair time of the device according to the failure characteristics of the device. The specific steps are as follows:

[0066] Establishing a device failure feature library: collecting various failure information of the device in the production process, including device number, failure type, repair time, etc., and putting it into the device failure feature library.

[0067] Establishing a device repair time prediction model: using deep learning framework, training a device repair time prediction model through device failure feature library. This model can predict the repair time of the device according to the failure characteristics of the device. The failure and maintenance of the device will affect the original production arrangement, and the estimated repair time is to better arrange the subsequent production tasks.

[0068] Step 4: Updating the device energy consumption state control model.

[0069] In actual production, the device may have power fluctuations in each state due to long-term work of the device and components. The power characteristics of each component of the device in each state are the basis for establishing the device state control model. When the power characteristics of the device change, the state control model should also be updated. The specific method is as follows:

[0070] Energy consumption data collection: using collection and prediction methods to obtain real energy consumption data and predicted energy consumption data.

[0071] Energy consumption data prediction: using new and old models to predict energy consumption data combined with control instructions.

[0072] Prediction model update: compare the prediction accuracy of new and old models using the precision identification model, and select the model with higher prediction accuracy for retention.

[0073] Step 5: Equipment state control

[0074] By connecting the edge computing gateway with the numerical control system of the device, and according to the latest device energy consumption state control model obtained in the previous steps, the state control scheme of the device is generated by combining the production scheduling information, and the components of the device are accurately controlled to achieve the purpose of reducing non-value-added energy consumption. Specifically, the strategy is divided into the following methods:

[0075] Connect the numerical control system of the device: the edge gateway is connected with the numerical control system and sensor of the device, which is used to transmit control instructions to the numerical control system to realize the control and monitoring of the device.

[0076] Equipment state control: during the non-value-added operation time, according to the device energy consumption state control model, the device is accurately controlled, including entering the sleep state, standby state and normal working state. When the device enters the sleep state, the state of the device is converted according to the device energy consumption state control model, to ensure that the energy consumption of the device is minimized.

[0077] Device energy consumption monitoring: when the device is running, the device energy consumption will be monitored in real time, when the device energy consumption anomaly and device failure are detected, the edge gateway is fed back to the device energy consumption state control model, providing data support for updating the device energy consumption state control model.

[0078] Finally, it should be pointed out that the above examples are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the purpose and scope of the present application, which should be covered by the claims of the present application.

Claims

1. A lean control method for energy consumption status of machining equipment, characterized in that: The method includes the following steps: S1: Obtain production scheduling plan: Obtain the power characteristics of each component of the machining equipment under different states from the manufacturing enterprise's production process execution system (MES), enterprise resource planning system (ERP), and manufacturing operations management system (MOM); S2: Establish equipment energy consumption, prediction, and control models: Based on the power characteristics of each component of the equipment under different states, establish a multi-source energy consumption characteristic model and an energy consumption prediction model for the equipment. Based on the multi-source energy consumption characteristic model and the equipment energy consumption prediction model, establish an equipment energy consumption state control model. The multi-source energy consumption characteristic model of the device is as follows: （1） In the formula, This indicates the total energy consumption of the equipment during non-value-added operations. This indicates the total number of components contained in the device. , , Representing components respectively Idle time, components Duration of the shutdown process, components The duration of the startup process, , , Representing components respectively Power and components during no-load period Power and components during shutdown Power consumed during startup; S3: Predictive dynamic interference processing: Collect fault information and repair information of equipment during production to form a dataset, and use deep learning algorithms to establish and train a model for predicting equipment fault repair time. S4: Update the equipment energy consumption status control model: Establish an accuracy identification model and use the monitored actual power of the equipment. Predicted power obtained from energy consumption prediction model Average measurement energy consumption By comparing the results, the accuracy fitting rate of the energy consumption prediction model was finally obtained. Select and retain the energy consumption prediction model with high accuracy fitting rate, and update the equipment energy consumption status control model based on the retained energy consumption prediction model. The accuracy recognition model is as follows: （9） In the formula, This represents the accuracy of the energy consumption prediction model's fit. This indicates the actual power of the monitored equipment. This represents the predicted power obtained from the energy consumption prediction model. Indicates average measured energy consumption; S5: Equipment Status Control: Based on the updated equipment energy consumption status control model in S4, and combined with the time series of workpiece arrival and departure from the equipment obtained from the production scheduling scheme, an equipment energy-saving control scheme is derived, and an edge computing gateway is installed on the equipment to complete the control of the equipment status.

2. The method for lean control of energy consumption status of machining equipment according to claim 1, characterized in that: In step S2, the power value of each component is predicted using a weighted moving average method, based on the historical power information of each component. An energy consumption prediction model is then established based on the predicted power values ​​of each component. （2） （3） （4） （5） In the formula, To predict energy consumption, , , Components No-load power, shutdown power, and startup power , , , For components 1, 2, 3, before the current time point No-load power at each time point , , , For components 1, 2, 3, before the current time point Power of the shutdown process at each time point , , , For components 1, 2, 3, before the current time point Power of the startup process at each time point , , , For components 1, 2, 3, before the current time point The weight of the actual power at each time point.

3. The lean control method for energy consumption status of machining equipment according to claim 2, characterized in that: In S2, establishing the equipment energy consumption state control model means calculating the energy consumption model of each component in different time periods based on the power data of each component in different states, as shown in equation (6), and using... Find the minimum as the objective The value is the component. The state control model is used to establish the equipment energy consumption state control model as shown in equation (7): (6) (7) In the formula, Representation Component Energy consumption during non-value-added operation time of duration [duration missing]. This represents the equipment energy consumption status control model. Indicates the device number Control strategies for each component For the first The time point when each component starts For the first The time point at which each component is turned off.

4. The method for lean control of energy consumption status of machining equipment according to claim 1, characterized in that: In step S3, the data format required for establishing a device fault repair time prediction model in dynamic interference processing is as follows: (8) In the formula, This represents a dataset of equipment failures. Indicates the faulty component number. Indicates the fault type. Indicates the time required to repair the fault.

5. The lean control method for energy consumption status of machining equipment according to claim 3, characterized in that: In step S4, the updated equipment energy consumption state control model is as follows: （10） In the formula, This indicates an updated device energy consumption state control model. Indicates the device number New control strategies for each component. For the first The new start time for each component. For the first A new shutdown time for each component.

6. The method for lean control of energy consumption status of machining equipment according to claim 5, characterized in that: In S5, the equipment energy-saving control scheme is as follows: （11） （12） In the formula, , Indicates the device at a certain point in time. Old and new control schemes for each moment, , Indicates in Components of a point-in-time device The old and new control schemes.

Images