Production line real-time optimization control method, device, system, equipment and storage medium

Abstract

The application provides a production line real-time optimization control method and device, system, equipment and storage medium, wherein the method comprises the following steps: determining operation variables and control variables of a DCS, and determining operation variable running values of the operation variables, control variable predicted values of the control variables, and control variable target values of the control variables; and adjusting the operation variable running values of the DCS to make the control variable predicted values approach the control variable target values. The method is mainly based on a data-driven modeling method, has low requirements on raw materials and equipment precision, can adapt to different production line state conditions, and can make the production line maintain an optimal economic state for a long time under the premise of guaranteeing product production quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial control, and in particular, relates to a production line real-time optimization control method and device, system, equipment and storage medium. BACKGROUND

[0002] Cement clinker production is a complex process industry production process. In order to ensure that the quality of the cement clinker meets the requirements, it is necessary to adjust the operation variables of the production line in real time, so that the temperature, pressure and other values of the production process meet the needs of clinker production. In the process of real-time adjustment, due to the strong nonlinearity, multivariable strong coupling, uncertainty, unclear mechanism and the like of the dynamic characteristics between the control variables and the operation variables, it is difficult to establish a mathematical model for production process simulation, and many times it is necessary to rely on the manual experience of the central control operator to implement adjustment.

[0003] The cement production line is generally adjusted and controlled by multiple central control operators, and the experience and adjustment methods of different central control operators are generally different, so that the cement production line is long-term operated in a non-economic optimal state, resulting in high energy consumption and large resource consumption. SUMMARY

[0004] The embodiments of the present application provide a production line real-time optimization control method, so as to enable the production line to be operated in the most economic state.

[0005] Correspondingly, the embodiments of the present application also provide a production line real-time optimization control device, a production line real-time optimization control system, an electronic device and a computer readable storage medium, to ensure the implementation and application of the above method.

[0006] In order to solve the above problems, the embodiments of the present application disclose a production line real-time optimization control method, which is used for real-time optimization control of a distributed control system (DCS) of a production line, and the method comprises the following steps:

[0007] determining operation variables and control variables of the DCS, and determining operation variable running values of the operation variables, control variable predicted values of the control variables, and control variable target values of the control variables;

[0008] adjusting the operation variable running values of the DCS to make the control variable predicted values approach the control variable target values.

[0009] Optionally, the step of determining the operation variables and the control variables of the DCS, and determining the operation variable running values of the operation variables, the control variable predicted values of the control variables, and the control variable target values of the control variables comprises the following steps:

[0010] obtaining operation variable running values of the operation variables and cement raw material quality inspection data from the DCS of the cement production line;

[0011] determining a control variable predicted value of the control variable according to the operation variable running value;

[0012] determining a control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data.

[0013] Optionally, the determining the control variable predicted value of the control variable according to the operation variable running value comprises:

[0014] obtaining an energy consumption prediction model, the energy consumption prediction model comprising a corresponding relationship between the operation variable and the control variable;

[0015] determining the control variable predicted value according to the operation variable running value and the energy consumption prediction model.

[0016] Optionally, the determining the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data comprises:

[0017] obtaining a quality prediction model, the quality prediction model comprising a corresponding relationship between the operation variable, the cement raw material quality inspection data and the cement clinker predicted data, and further comprising a corresponding relationship between the cement clinker predicted data within a quality inspection requirement range of the cement clinker and the operation variable;

[0018] determining the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data through the quality prediction model.

[0019] Optionally, the method further comprises:

[0020] when a preset condition is met, obtaining historical running data of the DCS, the historical running data comprising an operation variable historical value of the operation variable and a control variable historical value of the control variable;

[0021] training the energy consumption prediction model according to the operation variable historical value and the control variable historical value.

[0022] Optionally, the method further comprises:

[0023] when a preset condition is met, obtaining historical running data of the DCS and historical quality inspection data of the cement raw material and historical quality inspection data of the cement clinker corresponding to the historical running data, the historical running data comprising an operation variable historical value of the operation variable and a control variable historical value of the control variable;

[0024] training the quality prediction model according to the operation variable historical value, the control variable historical value, the historical quality inspection data of the cement raw material and the historical quality inspection data of the cement clinker.

[0025] Optionally, the adjusting the operation variable running value of the DCS to make the control variable predicted value approach the control variable target value comprises:

[0026] determining an adjustment direction of the control variable according to the control variable predicted value, the control variable target value, the operation variable running value, and a preset optimization algorithm; the adjustment direction comprises increasing the operation variable running value and decreasing the operation variable running value;

[0027] adjusting the operation variable running value according to the adjustment direction to make the control variable predicted value approach the control variable target value.

[0028] Optionally, the method further comprises:

[0029] when an abnormal working condition occurs, determining an adjustment parameter of the operation variable running value according to the abnormal working condition;

[0030] adjusting the operation variable running value according to the adjustment parameter.

[0031] Optionally, before the when an abnormal working condition occurs, determining an adjustment parameter of the operation variable running value according to the abnormal working condition, the method further comprises:

[0032] acquiring a point feature of the production line;

[0033] determining whether an abnormal working condition occurs according to the point feature.

[0034] Optionally, the method further comprises:

[0035] when an abnormal working condition occurs, locking a control loop of the adjusting the operation variable running value of the DCS to make the control variable predicted value approach the control variable target value.

[0036] Embodiments of the present application also disclose a production line real-time optimization control device, which is used for performing real-time optimization control on a distributed control system (DCS) of a production line, and comprises:

[0037] a determining module, which is used for determining operation variables and control variables of the DCS, and determining an operation variable running value of the operation variables, a control variable predicted value of the control variables, and a control variable target value of the control variables;

[0038] an adjusting module, which is used for adjusting the operation variable running value of the DCS to make the control variable predicted value approach the control variable target value.

[0039] Optionally, the determining module comprises:

[0040] The first obtaining module is configured to obtain an operation variable running value of an operation variable and cement raw material quality inspection data from a DCS of a cement production line.

[0041] The first determining module is configured to determine a control variable predicted value of the control variable according to the operation variable running value.

[0042] The second determining module is configured to determine a control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data.

[0043] Optionally, the first determining module comprises:

[0044] The second obtaining module is configured to obtain an energy consumption prediction model, wherein the energy consumption prediction model comprises a corresponding relationship between the operation variable and the control variable.

[0045] The predicted value determining module is configured to determine the control variable predicted value according to the operation variable running value and the energy consumption prediction model.

[0046] Optionally, the second determining module comprises:

[0047] The third obtaining module is configured to obtain a quality prediction model, wherein the quality prediction model comprises a corresponding relationship between the operation variable and the cement raw material quality inspection data and a predicted data of the cement clinker, and further comprises a corresponding relationship between the predicted data of the cement clinker within a quality inspection requirement range of the cement clinker and the operation variable.

[0048] The target value determining module is configured to determine the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data by using the quality prediction model.

[0049] Optionally, the device further comprises:

[0050] The fourth obtaining module is configured to obtain historical running data of the DCS when a preset condition is met, wherein the historical running data comprises an operation variable historical value of the operation variable and a control variable historical value of the control variable.

[0051] The first training module is configured to train the energy consumption prediction model according to the operation variable historical value and the control variable historical value.

[0052] Optionally, the device further comprises:

[0053] The fifth obtaining module is configured to obtain historical running data of the DCS and historical quality inspection data of the cement raw material and historical quality inspection data of the cement clinker corresponding to the historical running data when a preset condition is met, wherein the historical running data comprises an operation variable historical value of the operation variable and a control variable historical value of the control variable.

[0054] a second training module configured to train the quality prediction model according to the operation variable historical values, the control variable historical values, the historical quality inspection data of the cement raw material, and the historical quality inspection data of the cement clinker.

[0055] Optionally, the adjusting module comprises:

[0056] an adjusting direction determining module configured to determine an adjusting direction of the control variable according to the control variable predicted value, the control variable target value, the operation variable running value, and a preset optimization algorithm; the adjusting direction comprises increasing the operation variable running value and decreasing the operation variable running value;

[0057] an adjusting control module configured to adjust the operation variable running value according to the adjusting direction, so that the control variable predicted value approximates to the control variable target value.

[0058] Optionally, the device further comprises:

[0059] a parameter determining module configured to determine an adjusting parameter of the operation variable running value according to the abnormal working condition when the abnormal working condition occurs;

[0060] a second adjusting module configured to adjust the operation variable running value according to the adjusting parameter.

[0061] Optionally, the device further comprises:

[0062] a point feature acquiring module configured to acquire point features of the production line;

[0063] an abnormal working condition judging module configured to judge whether an abnormal working condition occurs according to the point features.

[0064] Optionally, the device further comprises:

[0065] an interlocking module configured to lock a control loop of adjusting the operation variable running value so that the control variable predicted value approximates to the control variable target value when the abnormal working condition occurs.

[0066] Embodiments of the present application further disclose a production line real-time optimization control system, which comprises a distributed control system (DCS) of a production line, an optimization recommendation model module, and an optimization control model module; the optimization recommendation model module is in communication connection with the DCS, and the optimization control model module is in communication connection with the optimization recommendation model module and the DCS respectively;

[0067] the optimization recommendation model module is configured to determine operation variables and control variables of the DCS, and determine operation variable running values of the operation variables, control variable predicted values of the control variables, and control variable target values of the control variables.

[0068] The optimization control model module is configured to obtain the operation variable running value determined by the optimization recommendation model module, the control variable prediction value of the control variable, and the control variable target value of the control variable, and adjust the operation variable running value of the DCS to make the control variable prediction value approach the control variable target value.

[0069] Optionally, the optimization recommendation model module is specifically configured to:

[0070] obtain the operation variable running value of the operation variable and the cement raw material quality inspection data from the DCS of the cement production line; determine the control variable prediction value of the control variable according to the operation variable running value; and determine the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data.

[0071] Optionally, the optimization recommendation model includes a quality prediction model module and an energy consumption prediction model module, wherein the energy consumption prediction model module includes:

[0072] a second obtaining module configured to obtain an energy consumption prediction model, the energy consumption prediction model including a corresponding relationship between the operation variable and the control variable;

[0073] a prediction value determination module configured to determine the control variable prediction value according to the operation variable running value and the energy consumption prediction model.

[0074] The quality prediction model module includes:

[0075] a third obtaining module configured to obtain a quality prediction model, the quality prediction model including a corresponding relationship between the operation variable and the cement raw material quality inspection data and the predicted data of the cement clinker, and a corresponding relationship between the predicted data of the cement clinker within a quality inspection requirement range of the cement clinker and the operation variable;

[0076] a target value determination module configured to determine the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data through the quality prediction model.

[0077] Optionally, the system further includes a model online evaluation and update module, the model online evaluation and update module being in communication connection with the DCS, and the model online evaluation and update module being in communication connection with the quality prediction model module and the energy consumption prediction model module, the model online evaluation and update module including:

[0078] a fourth obtaining module configured to obtain historical running data of the DCS when a preset condition is met, the historical running data including operation variable historical values of the operation variable and control variable historical values of the control variable;

[0079] The first training module is configured to train the energy consumption prediction model according to the operation variable historical values and the control variable historical values.

[0080] Optionally, the model online evaluation and update module comprises:

[0081] The fifth acquisition module is configured to acquire historical operation data of the DCS and historical quality inspection data of the cement raw material and historical quality inspection data of the cement clinker corresponding to the historical operation data when a preset condition is met, wherein the historical operation data comprises operation variable historical values of the operation variables and control variable historical values of the control variables.

[0082] The second training module is configured to train the quality prediction model according to the operation variable historical values, the control variable historical values, the historical quality inspection data of the cement raw material and the historical quality inspection data of the cement clinker.

[0083] Optionally, the optimization control model module comprises:

[0084] The adjustment direction determination module is configured to determine an adjustment direction of the control variable according to the control variable predicted value, the control variable target value, the operation variable running value and a preset optimization algorithm, wherein the adjustment direction comprises increasing the operation variable running value and reducing the operation variable running value.

[0085] The adjustment control module is configured to adjust the operation variable running value according to the adjustment direction, so that the control variable predicted value approximates to the control variable target value.

[0086] Optionally, the system further comprises a dynamic control model module, which is in communication connection with the DCS, and the dynamic control model module comprises:

[0087] The parameter determination module is configured to determine an adjustment parameter of the operation variable running value according to the abnormal working condition when the abnormal working condition occurs.

[0088] The second adjustment module is configured to adjust the operation variable running value according to the adjustment parameter.

[0089] Optionally, the system further comprises a real-time data acquisition and processing module, which is in communication connection with the dynamic control model module and the DCS respectively, and the real-time data acquisition and processing module comprises:

[0090] The point feature acquisition module is configured to acquire point features of the production line.

[0091] The abnormal working condition judgment module is configured to judge whether an abnormal working condition occurs according to the point features.

[0092] Optionally, the system further comprises an interlocking module, which is in communication connection with the dynamic control model module and the optimization control model module respectively, and is used for locking the control loop of adjusting the operation variable running value of the operation variable to make the control variable predicted value approach the control variable target value when an abnormal working condition occurs.

[0093] An electronic device comprises a processor, a memory, and a computer program stored on the memory and capable of running on the processor, and the computer program, when executed by the processor, implements the steps of the production line real-time optimization control method as described above.

[0094] A computer readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the production line real-time optimization control method as described above.

[0095] Compared with the prior art, the embodiments of the present application have the following advantages:

[0096] In the embodiments of the present application, by determining the operation variable and the control variable of the DCS, and determining the operation variable running value of the operation variable, the control variable predicted value of the control variable, and the control variable target value of the control variable, the operation variable running value of the DCS is adjusted to make the control variable predicted value approach the control variable target value, so that the production line can be kept in an optimal economic state for a long time under the premise of ensuring product production quality. BRIEF DESCRIPTION OF DRAWINGS

[0097] Figure 1 A step flowchart of a production line real-time optimization control method provided for Embodiment One of the present application;

[0098] Figure 2 A step flowchart of a production line real-time optimization control method provided for Embodiment Two of the present application;

[0099] Figure 3 An application scenario schematic diagram of a production line real-time optimization control method provided for the embodiments of the present application;

[0100] Figure 4 A structural block diagram of a production line real-time optimization control device provided for Embodiment Three of the present application;

[0101] Figure 5 A structural block diagram of a production line real-time optimization control device provided for Embodiment Four of the present application. DETAILED DESCRIPTION

[0102] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0103] Cement clinker production is a complex process industry production process, in order to ensure that the quality of cement clinker to meet the requirements, the need to adjust the operating variables of the production line in real time, so that the temperature, pressure and other values of the production process meet the needs of clinker production. In the process of real-time adjustment, due to the dynamic characteristics between the control variables and the operating variables have strong nonlinearity, multivariable strong coupling, uncertainty, mechanism is not clear, etc., it is difficult to establish a mathematical model for production process simulation, many times are dependent on the experience of the control operator to implement adjustment, the dependence on people is large. And the same cement production line is generally adjusted and controlled by multiple control operators, and the experience and adjustment method of different control operators are generally different, so that the cement production line is running in a non-economic optimal state for a long time, resulting in high energy consumption and large resource consumption.

[0104] Individual cement manufacturers will use expert control systems to control the cement production process, wherein the expert control system uses expert experience to summarize the control mechanism and control rules in the clinker production process to form a knowledge base about the clinker production process. The commonly used knowledge in the expert control system is the production rule, which is written in the form of IF…THEN… in the knowledge base. In the actual production control process, the real-time collected data are matched with the expert knowledge in the knowledge base, and if the condition matching is successful, the corresponding action in the rule is executed for control. That is, the expert system is a program system with a large amount of specialized knowledge and experience, and the knowledge base is used to store the knowledge provided by experts.

[0105] The disadvantages of this control system are as follows: first, the precision of the raw materials and equipment of the production line is required to be high, and once the precision of the raw materials or equipment fluctuates, the previously set expert rules will be invalid; second, it cannot adapt to long-time automatic control of the production line, because the characteristics of the equipment will change over time, but the expert system cannot adaptively update the control parameters, resulting in that the expert rules will be invalid after a long time of operation of the production line.

[0106] In view of this, the embodiments of the present application provide a production line real-time optimization control method to solve the defects of the existing production line control system.

[0107] Reference Figure 1 , a step flowchart of a production line real-time optimization control method provided by an embodiment of the present application is shown, and the method is used for real-time optimization control of a distributed control system (DCS) of a production line. The method can include the following steps:

[0108] Step 101, determining the operating variables and control variables of the DCS, and determining the operating variable running value of the operating variables, the control variable predicted value of the control variables, and the control variable target value of the control variables.

[0109] Specifically, variables that can be directly adjusted in the DCS are defined as operation variables, and variables that cannot be directly adjusted in the DCS are defined as control variables; and when the operation variables in the DCS are adjusted or changed, the control variables in the DCS are affected. At some time, the data of the operation variables at a certain time may not affect the data of the control variables at the time, but may affect the future data of the control variables.

[0110] In the embodiments of the present application, the operation variable running value can be considered as the current value of the operation variable, the control variable prediction value can be considered as the value of the control variable related to the operation variable running value, which is calculated or predicted by the operation variable running value; and the control variable target value can be considered as the value of the control variable corresponding to the optimal economic state of the production line under the premise that the product meets the production requirements.

[0111] In an optional embodiment of the present application, when the above-mentioned real-time optimization control method of the production line is specifically used for real-time optimization control of the DCS of the cement clinker production line, the above-mentioned determination of the operation variables and the control variables of the DCS, and the determination of the operation variable running value of the operation variable, the control variable prediction value of the control variable, and the control variable target value of the control variable include:

[0112] obtaining the operation variable running value of the operation variable and the cement raw material quality inspection data from the DCS of the cement production line;

[0113] determining the control variable prediction value of the control variable according to the operation variable running value;

[0114] determining the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data.

[0115] The production process of cement includes: adding lime raw materials, clay raw materials and correction raw materials (such as silicon correction raw materials, aluminum correction raw materials, iron correction raw materials, etc.) into a mill, and grinding these raw materials into raw materials, i.e. cement raw materials, by the mill; then calcining the cement raw materials in a cement kiln to partial melting to obtain a silicate cement clinker with calcium silicate as the main component; finally, grinding the cement clinker and gypsum together to obtain cement.

[0116] Generally, the quality of cement raw materials input into a cement production line is uneven, but the cement clinker output from the cement production line is required to have a uniform quality, for example, the content of free calcium oxide f-CaO in the cement clinker is required to be within a specified content range, the 3d strength of the cement clinker is required to be within a specified strength range, and the like. Therefore, it is necessary to properly control the operating variables of the DCS of the cement production line in real time to ensure that the output is the cement clinker meeting the quality requirements. At the same time, the production line is required to be operated in an optimal economic state to improve production efficiency. Exemplarily, the optimal economic state can refer to a state in which the energy consumption (including power consumption and coal consumption) corresponding to the production of a unit of cement clinker meeting the quality requirements is the lowest.

[0117] By obtaining the operating variable running value of the DCS, the control variable predicted value of the corresponding control variable can be calculated or predicted according to the operating variable running value. According to the operating variable running value and the cement raw material quality inspection data, the predicted data of the cement clinker corresponding to the cement raw material under the control of the operating variable running value can be predicted; and then, in combination with the quality inspection requirements of the cement clinker, the adjustable value of the operating variable is determined. The adjustable value of the operating variable generally has multiple values, and the control variable predicted value of the control variable corresponding to each operating variable adjustable value can be calculated or predicted, and the control variable target value corresponding to the optimal economic state of the production line is selected from the multiple control variable predicted values corresponding to the multiple operating variable adjustable values.

[0118] In an optional embodiment of the present application, the process of determining the control variable predicted value of the control variable according to the operating variable running value can specifically include:

[0119] obtaining an energy consumption prediction model, the energy consumption prediction model including a corresponding relationship between the operating variable and the control variable;

[0120] determining the control variable predicted value according to the operating variable running value and the energy consumption prediction model.

[0121] In the embodiment, the control variable predicted value is determined by the energy consumption prediction model. Specifically, the energy consumption prediction model can be constructed in advance, the energy consumption prediction model including a corresponding relationship between the operating variable and the control variable of the DCS, and being used to predict the value of the corresponding control variable based on the value of the operating variable. In order to improve the prediction accuracy of the energy consumption prediction model, the energy consumption prediction model needs to be trained before being used. Specifically, the historical running data of the DCS in a preset historical time period can be obtained, and the energy consumption prediction model is trained by using the historical running data.

[0122] After obtaining the running value of the operation variable of the DCS, the running value of the operation variable can be input into the energy consumption prediction model, and the corresponding control variable prediction value is output through the energy consumption prediction model, so as to determine the control variable prediction value corresponding to the running value of the operation variable. Optionally, the prediction period of the energy prediction model can be 60 seconds, or can be adaptively adjusted according to the actual situation of the production line.

[0123] Optionally, after obtaining the energy consumption prediction model, the energy consumption prediction model can also be trained periodically or aperiodically; the process can include:

[0124] When the preset condition is met, the historical running data of the DCS is obtained, and the historical running data includes the operation variable historical value of the operation variable and the control variable historical value of the control variable.

[0125] The energy consumption prediction model is trained according to the operation variable historical value and the control variable historical value.

[0126] The preset condition can refer to a condition preset for triggering training of the energy consumption prediction model, and the preset condition can be a training time, which can be a specific time specified by a user, for example, a certain time in the future is specified as the time of the next training; or a user-set preset training period to periodically train the energy consumption prediction model, etc.

[0127] Taking periodic training of the energy consumption prediction model as an example. The user can pre-set the periodic training period, specifically, by receiving the periodic training period set by the user, when the periodic training period is reached, the historical running data is obtained, and the historical running data at least includes the historical running data within the periodic training period. Generally, the periodic training period is between 1 and 15. Illustratively, when the periodic training period is 10 days, the historical running data of the DCS is obtained 10 days away from the last training of the energy consumption prediction model, and the historical running data at least includes the historical running data 10 days away from the last training of the energy consumption prediction model.

[0128] The energy consumption prediction model is trained according to the historical running data, and after the training is completed, the prediction accuracy of the new energy consumption prediction model after the training and the current energy consumption prediction model before the training is evaluated, when the prediction accuracy of the new energy consumption prediction model is higher than that of the current energy consumption prediction model, the new energy consumption prediction model is used to update the current energy consumption prediction model, so that the energy consumption prediction model used can continuously adapt to the changes of the production line equipment and working conditions, and the control effect is improved. Optionally, the prediction period of the quality prediction model can be 30 minutes, or can be adaptively adjusted according to the actual situation of the production line.

[0129] In an optional embodiment of the present application, the process of determining the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data can specifically include:

[0130] obtaining a quality prediction model, the quality prediction model including a corresponding relationship between the operation variable and the cement raw material quality inspection data and the predicted data of the cement clinker, and a corresponding relationship between the predicted data of the cement clinker and the operation variable within the quality inspection requirement range of the cement clinker;

[0131] determining the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data through the quality prediction model.

[0132] In the embodiment, the control variable target value is determined through the quality prediction model. Specifically, the quality prediction model can be constructed in advance, the quality prediction model including a corresponding relationship between the operation variable of the DCS and the cement raw material quality inspection data and the predicted data of the cement clinker, and a corresponding relationship between the predicted data of the cement clinker and the operation variable within the quality inspection requirement range of the cement clinker, for predicting the control variable target value of the corresponding control variable based on the cement raw material quality inspection data, the numerical value of the operation variable, and the quality inspection requirement of the cement clinker. The predicted data of the cement clinker is calculated or predicted according to the cement raw material quality inspection data and the operation variable running value of the operation variable, i.e., the prediction of the quality of the cement clinker produced by the cement raw material under the control of the operation variable running value.

[0133] In order to improve the prediction accuracy of the quality prediction model, the quality prediction model needs to be trained before being used. Specifically, the historical running data of the DCS and the historical quality inspection data of the cement raw material and the historical quality inspection data of the cement clinker corresponding to the historical running data in a preset historical time period can be obtained, and the quality prediction model is trained by using the obtained historical running data, the historical quality inspection data of the cement raw material, and the historical quality inspection data of the cement clinker.

[0134] After obtaining the operation variable running value of the DCS and the cement raw material quality inspection data, the operation variable running value and the cement raw material quality inspection data can be input into the quality prediction model, and the corresponding control variable target value is output through the quality prediction model, so as to determine the control variable target value corresponding to the production of the cement clinker meeting the quality inspection requirement of the cement clinker under the current working condition.

[0135] Optionally, after obtaining the quality prediction model, the quality prediction model can also be trained periodically or aperiodically; the process can include:

[0136] When a preset condition is met, historical operation data of the DCS and historical quality inspection data of the cement raw material and the cement clinker corresponding to the historical operation data are acquired, the historical operation data including historical operation variable values of the operation variables and historical control variable values of the control variables;

[0137] The quality prediction model is trained according to the historical operation variable values, the historical control variable values, the historical quality inspection data of the cement raw material and the historical quality inspection data of the cement clinker.

[0138] The preset condition can refer to a condition preset for triggering training of the quality prediction model, and specifically can be a training time, which can be a specific time specified by a user, for example, a certain time in the future is specified as the time of the next training, or can be a preset training period set by the user, so as to periodically train the quality prediction model, and the like.

[0139] Taking periodic training of the quality prediction model as an example, the user can preset a periodic training period, specifically, by receiving a periodic training period set by the user, when the periodic training period is reached, the historical operation data and the historical quality inspection data of the cement raw material and the cement clinker corresponding to the historical operation data are acquired, the historical operation data at least including historical operation data within the periodic training period; generally, the periodic training period is between 1 and 15. Illustratively, when the periodic training period is 10 days, the historical operation data of the DCS and the historical quality inspection data of the cement raw material and the cement clinker corresponding to the historical operation data are acquired when 10 days have elapsed since the last training of the quality prediction model, the historical operation data at least including historical operation data within 10 days since the last training of the quality prediction model.

[0140] The quality prediction model is trained according to the historical operation data and the historical quality inspection data of the cement raw material and the cement clinker corresponding to the historical operation data, and after the training is completed, the prediction accuracy of the new quality prediction model after the training and the current quality prediction model before the training is evaluated, when the prediction accuracy of the new quality prediction model is higher than that of the current quality prediction model, the new quality prediction model is used to update the current quality prediction model, so that the quality prediction model used can continuously adapt to changes in the production line equipment and working conditions, and the control effect is improved.

[0141] By increasing the online evaluation and updating mechanism of the energy consumption prediction model and the quality prediction model, the model can be retrained, evaluated and updated based on the current actual running data, and the updating process is completely online and automatic, without human intervention; through the evaluation process, it can be ensured that the updated model is better than the previous model.

[0142] Step 102, adjusting the operation variable running value of the DCS to make the control variable predicted value approach the control variable target value.

[0143] After determining the control variable predicted value and the control variable target value, when the control variable predicted value is different from the control variable target value, or the difference between the control variable predicted value and the control variable target value exceeds the prediction difference threshold, the operation variable of the DCS can be adjusted to make the control variable predicted value approach the control variable target value. Preferably, the control variable predicted value is equal to the control variable target value by adjusting the operation variable of the DCS. Thus, it is ensured that the production line is kept running in the optimal economic state. Alternatively, the period of adjusting the operation variable running value can be 60 seconds, or can be adaptively adjusted according to the actual situation of the production line.

[0144] In an optional embodiment of the present application, the process of adjusting the operation variable running value of the DCS to make the control variable predicted value approach the control variable target value can include:

[0145] According to the control variable predicted value, the control variable target value, the operation variable running value, and a preset optimization algorithm, the adjustment direction of the control variable is determined; the adjustment direction includes increasing the operation variable running value and reducing the operation variable running value;

[0146] The operation variable running value is adjusted according to the adjustment direction to make the control variable predicted value approach the control variable target value.

[0147] In this embodiment, the adjustment direction of the control variable can be determined by a preset optimization algorithm according to the control variable predicted value, the control variable target value, and the operation variable running value. The adjustment direction includes increasing the operation variable running value or reducing the operation variable running value. Then, the operation variable running value is adjusted according to the adjustment direction to make the control variable predicted value approach the control variable target value.

[0148] Alternatively, the upper limit value and the lower limit value of the operation variable and the single-step limit value of each adjustment can be preset according to the process mechanism. During the process of adjusting the operation variable running value according to the adjustment direction, it is ensured that the operation variable running value is between the preset upper limit value and the lower limit value, and the step of each adjustment conforms to the preset single-step limit value.

[0149] When adjusting the operation variable running value each time, the control variable predicted value corresponding to the adjusted operation variable running value and the corresponding control variable target value can be calculated or predicted in real time, and the control variable predicted value and the control variable target value are compared to determine whether to perform the next adjustment, and when it is determined that the next adjustment is needed, the direction of the next adjustment is determined.

[0150] The embodiment of the application determines the operation variable and the control variable of the DCS, and determines the operation variable running value of the operation variable, the control variable predicted value of the control variable, and the control variable target value of the control variable; the operation variable running value of the DCS is adjusted to make the control variable predicted value approach the control variable target value; the method mainly models based on a data-driven method, has low requirements on raw materials and equipment precision, can adapt to the state conditions of different production lines, and enables the production line to maintain the optimal economic state for a long time under the premise of ensuring the product production quality.

[0151] Referring to Figure 2 , a step flow chart of a production line real-time optimization control method provided by the embodiment two is shown, and the method is used for real-time optimization control of a distributed control system DCS of a production line. The method can include the following steps:

[0152] Step 201, determining the operation variable and the control variable of the DCS, and determining the operation variable running value of the operation variable, the control variable predicted value of the control variable, and the control variable target value of the control variable.

[0153] The step 201 can refer to the description of the step 101 in the foregoing, and will not be described here.

[0154] Step 202, adjusting the operation variable running value of the DCS to make the control variable predicted value approach the control variable target value.

[0155] The step 202 can refer to the description of the step 102 in the foregoing, and will not be described here.

[0156] Step 203, when an abnormal working condition occurs, determining the adjustment parameter of the operation variable running value according to the abnormal working condition.

[0157] Step 204, adjusting the operation variable running value according to the adjustment parameter.

[0158] In the embodiment of the application, the adjustment of the operation variable can include two loops, one loop is used for real-time adjustment of the operation variable to make the control variable predicted value approach the control variable target value, to realize that the running state of the production line approaches the optimal running state, and finally reaches the optimal running state of the production line. The other loop is used for adjusting the operation variable in the abnormal working condition to ensure the stability of the running state of the production line in the production process. Through the double-loop design, the economic operation and the emergency of the sudden abnormality can be considered, the production line is controlled to be in the optimal running state in the normal operation condition, the sudden condition is handled in time in the sudden abnormal condition, and the abnormality is solved.

[0159] When the abnormal working condition occurs, an adjustment parameter of the operation variable running value is determined according to the abnormal working condition, the adjustment parameter including an adjustment direction, or the adjustment direction and an adjustment step, and the operation variable running value is adjusted according to the adjustment parameter to solve the abnormal working condition. Optionally, the sensing period of the dynamic control module for processing the abnormal working condition is generally shorter, usually less than 1 / 10 of the period of the optimization control module for adjusting the operation variable in real time.

[0160] Specifically, before the above-mentioned step of determining the adjustment parameter of the operation variable running value according to the abnormal working condition when the abnormal working condition occurs, the method can further include:

[0161] Obtaining point features of the production line;

[0162] Determining whether the abnormal working condition occurs according to the point features.

[0163] In the embodiment, the dynamic control module for adjusting the operation variable loop under the abnormal working condition can be based on a PID (proportional-integral-derivative control) control module and be set in combination with a process mechanism. Through a real-time data sampling server, point features in a production process are obtained from a DCS system in real time. Taking cement clinker production as an example, the point features can include kiln head cover negative pressure of a rotary kiln, outlet pressure of a grate cooler fan, current of the grate cooler fan, pushing pressure under the grate, current and rotating speed of a kiln main motor, secondary air temperature, tertiary air temperature, etc. The point features can also include current of a raw mill main motor, pressure difference of a vertical mill, vertical mill vibration, and current of a circulating hopper, etc. Whether the abnormal working condition occurs can be determined according to the point features.

[0164] Specifically, whether the abnormal working condition occurs can be determined according to the point features by comparing the currently obtained point features with the point features obtained last time to determine whether the working condition is normal according to the difference between the point features obtained at adjacent two times. Generally, when the point features are abnormal, the production line will also correspondingly show abnormality. For example, when the point features of the rotary kiln are abnormal, it can be identified that the kiln skin is off, etc. For another example, when the point features of the raw mill are abnormal, it can be identified that the mill is full, etc. Therefore, in other embodiments, whether the abnormal working condition occurs can also be determined by identifying the working condition of the production line.

[0165] Exemplarily, when the kiln head cover negative pressure of the rotary kiln obtained at a moment is lower than the kiln head cover negative pressure obtained at a previous moment, and the decrease amplitude exceeds a preset value, according to the process mechanism, the rotating speed of the kiln head exhaust fan is rapidly increased by using a PID controller, so that the kiln head cover negative pressure is restored to a normal level.

[0166] Further, in an optional embodiment of the application, the above-mentioned method can further include:

[0167] When an abnormal condition occurs, the control loop adjusting the operating variable to make the control variable predicted value approach the control variable target value is locked.

[0168] In the embodiment, the two control loops (optimization control module and dynamic control module) adjusting the operating variable can be interlocked, specifically, the two control loops can be interlocked through the interlocking module to realize online dynamic switching of emergency control and optimization control. Moreover, the control priority of the dynamic control module can be set to be higher than the control priority of the optimization control module, that is, when an abnormal condition is sent, the control loop adjusting the operating variable to make the control variable predicted value approach the control variable target value is locked to ensure that when the dynamic control module perceives an emergency abnormal condition in the real-time optimization control process, the operating variable value for emergency disposal will not be covered by the operating variable value in the control cycle of the optimization control module.

[0169] To make the person skilled in the art better understand the embodiments of the present application, refer to Figure 3 The following describes a production line real-time optimization control method in the embodiments of the present application through specific examples.

[0170] Figure 3 An application scenario schematic diagram of a production line real-time optimization control method in the embodiments of the present application is shown. The application scenario is mainly used to realize optimal economic operation of the production line, while taking into account emergency control of unexpected events.

[0171] The application scenario mainly includes six modules, which are a quality prediction model module, an energy consumption prediction model module, an optimization control model module, a dynamic control model module, an interlocking module, and a model online evaluation and update module. The following describes the modules.

[0172] The quality prediction model module predicts the 3d strength and f-CaO of the cement clinker based on the cement raw material quality inspection data, the cement clinker quality inspection data, and the DCS real-time operation data, that is, predicts the prediction data of the cement clinker, and at the same time, in combination with the business mechanism knowledge, constrains the unit clinker power consumption and coal consumption targets to provide the allowable fluctuation range of the control variable for the energy consumption optimization model module, that is, the control variable optimization space (control variable target value). It is ensured that within the control variable optimization space, the generated cement clinker can meet the related requirements of the cement clinker quality in the process mechanism. Optionally, the prediction cycle of the quality prediction model module is 30 minutes.

[0173] The energy consumption prediction model module is based on the historical operation data of the DCS to establish a corresponding relationship between the unit clinker energy consumption value and each operation variable in the cement production process. According to the feedback value (operation variable running value) of each operation variable, the unit energy consumption is predicted in real time (to obtain the control variable prediction value), which provides a basis for the optimization control model module to optimize the operation variable, that is, to provide a basis for the optimization control model module to adjust the operation variable.

[0174] The optimization control model module is based on the prediction result of the energy consumption prediction model module to adjust the operation variable of the DCS in real time, so that the control variable prediction value predicted by the energy consumption prediction model module can continuously approach the control variable target value obtained by the quality prediction model module, thereby enabling the cement production line to continuously and real-time adjust the running state to approach the optimal running state, so as to achieve the purpose of the optimal economic running state of the production line. Optionally, the control period of the optimization control model module is 60 seconds.

[0175] The dynamic control model module is mainly used for quickly sensing and processing the sudden emergency abnormal working conditions in the cement production process to ensure the stability of the running state in the cement production process. The dynamic control model module is usually based on the PID control module and is set in combination with the process mechanism. Through the real-time data acquisition server, the point feature in the production process is obtained from the DCS system. When the abnormal working conditions such as full grinding or kiln skin falling are identified, the dynamic control model module will quickly modify the related operation variables of the DCS to meet the timeliness of system stable control. The dynamic control model module will only take corresponding control actions when it senses the emergency abnormal working conditions of the system, and will not control under normal circumstances, but will be controlled by the optimization control model module. Optionally, the sensing period of the dynamic control model module is generally shorter, usually less than 1 / 10 of the control period of the optimization control model module.

[0176] The interlocking module, in the real-time optimization control process, when the dynamic control model module senses the emergency abnormal working conditions, in order to ensure that the operation variable running value of the operation variable for emergency disposal will not be covered by the operation variable running value in the control period of the optimization control model module, the operation variable setting of the two control loops is interlocked to prioritize the control right of the dynamic control model module.

[0177] The model online evaluation and update module is mainly used for online evaluation and update of the quality prediction model module and the energy consumption prediction model module. The model online evaluation and update module uses historical operation data of the DCS and the quality inspection system to periodically retrain the quality prediction model module and the energy consumption prediction model module, and obtains a new quality prediction model module and a new energy consumption prediction model module after training. The new quality prediction model module is compared with the current quality prediction model module before training, and the new energy consumption prediction model module is compared with the current energy consumption prediction model module before training, to evaluate the prediction accuracy of the new model module and the corresponding current model module. When the accuracy of the new model module is higher than that of the corresponding current model module, the current model module is updated online, so that the overall real-time optimization control system can continuously adapt to changes in equipment and working conditions. The update cycle of the model online evaluation and update module is determined according to the actual production line, and can be set to 1-15 days.

[0178] The embodiment of the application determines the operation variable and the control variable of the DCS, and determines the operation variable running value of the operation variable, the control variable prediction value of the control variable, and the control variable target value of the control variable. The operation variable running value of the DCS is adjusted to make the control variable prediction value approach the control variable target value. When an abnormal working condition occurs, the adjustment parameter of the operation variable running value is determined according to the abnormal working condition. The operation variable running value is adjusted according to the adjustment parameter. The method can take into account economic operation and emergency response to sudden abnormalities. In normal operation, the production line is controlled to be in an optimal operating state. In the case of sudden abnormality, the sudden situation is handled in time to solve the abnormality.

[0179] It should be noted that, for the method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the application embodiments are not limited to the action order described, because according to the application embodiments, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions involved are not necessarily necessary for the application embodiments.

[0180] Corresponding to the first embodiment of the application, the third embodiment of the application provides a production line real-time optimization control device, which refers to Figure 4 , which shows the structure block diagram of an embodiment of a production line real-time optimization control device of the application. The device is used for real-time optimization control of the distributed control system DCS (Distributed Control System) of the production line. The device can include the following modules:

[0181] The determining module 401 is configured to determine an operation variable and a control variable of the DCS, and determine an operation variable running value of the operation variable, a control variable predicted value of the control variable, and a control variable target value of the control variable.

[0182] The first adjusting module 402 is configured to adjust the operation variable running value of the DCS so as to make the control variable predicted value approximate to the control variable target value.

[0183] In an optional embodiment of the present application, the determining module 401 comprises:

[0184] The first obtaining module is configured to obtain the operation variable running value of the operation variable and the cement raw material quality inspection data from the DCS of the cement production line.

[0185] The first determining module is configured to determine the control variable predicted value of the control variable according to the operation variable running value.

[0186] The second determining module is configured to determine the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data.

[0187] In an optional embodiment of the present application, the first determining module comprises:

[0188] The second obtaining module is configured to obtain an energy consumption prediction model, wherein the energy consumption prediction model comprises a corresponding relationship between the operation variable and the control variable.

[0189] The predicted value determining module is configured to determine the control variable predicted value according to the operation variable running value and the energy consumption prediction model.

[0190] In an optional embodiment of the present application, the second determining module comprises:

[0191] The third obtaining module is configured to obtain a quality prediction model, wherein the quality prediction model comprises a corresponding relationship between the operation variable and the cement raw material quality inspection data and a predicted data of the cement clinker, and further comprises a corresponding relationship between the predicted data of the cement clinker within a quality inspection requirement range of the cement clinker and the operation variable.

[0192] The target value determining module is configured to determine the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data by using the quality prediction model.

[0193] In an optional embodiment of the present application, the device further comprises:

[0194] The fourth obtaining module is configured to obtain historical running data of the DCS when a preset condition is met, wherein the historical running data comprises an operation variable historical value of the operation variable and a control variable historical value of the control variable.

[0195] The first training module is configured to train the energy consumption prediction model according to the operation variable historical value and the control variable historical value.

[0196] In an optional embodiment of the present application, the device further comprises:

[0197] The fifth obtaining module is configured to obtain historical running data of the DCS and historical quality inspection data of the cement raw material and historical quality inspection data of the cement clinker corresponding to the historical running data when a preset condition is met, wherein the historical running data comprises an operation variable historical value of the operation variable and a control variable historical value of the control variable.

[0198] The second training module is configured to train the quality prediction model according to the operation variable historical value, the control variable historical value, the historical quality inspection data of the cement raw material and the historical quality inspection data of the cement clinker.

[0199] In an optional embodiment of the present application, the first adjusting module 402 comprises:

[0200] The adjusting direction determining module is configured to determine an adjusting direction of the control variable according to the control variable predicted value, the control variable target value, the operation variable running value and a preset optimization algorithm, wherein the adjusting direction comprises increasing the operation variable running value and reducing the operation variable running value.

[0201] The adjusting control module is configured to adjust the operation variable running value according to the adjusting direction, so that the control variable predicted value approximates to the control variable target value.

[0202] Corresponding to the second embodiment of the present application, the fourth embodiment of the present application provides a device for real-time optimization control of a production line. Figure 5 The fourth embodiment of the present application shows a structural block diagram of a device for real-time optimization control of a production line, which is used for performing real-time optimization control on a distributed control system (DCS) of a production line. The device can comprise the following modules:

[0203] The determining module 501 is configured to determine an operation variable and a control variable of the DCS, and determine an operation variable running value of the operation variable, a control variable predicted value of the control variable and a control variable target value of the control variable.

[0204] The first adjusting module 502 is configured to adjust the operation variable running value of the DCS so that the control variable predicted value approximates the control variable target value.

[0205] The parameter determining module 503 is configured to determine an adjustment parameter of the operation variable running value according to the abnormal working condition when the abnormal working condition occurs.

[0206] The second adjusting module 504 is configured to adjust the operation variable running value according to the adjustment parameter.

[0207] In an optional embodiment of the present application, the device further comprises:

[0208] The point feature acquisition module is configured to acquire point features of the production line.

[0209] The abnormal working condition judging module is configured to judge whether an abnormal working condition occurs according to the point features.

[0210] In an optional embodiment of the present application, the device further comprises:

[0211] The interlocking module is configured to lock the control loop of adjusting the operation variable running value of the DCS so that the control variable predicted value approximates the control variable target value when the abnormal working condition occurs.

[0212] Corresponding to the production line real-time optimization control method provided in the embodiments of the present application, the embodiments of the present application further provide a production line real-time optimization control system, which is shown in Figure 3 The system comprises a distributed control system (DCS) of a production line, an optimization recommendation model module, and an optimization control model module. The optimization recommendation model module (a combination of a quality prediction model module and an energy consumption prediction model module) is in communication connection with the DCS, and the optimization control model module is in communication connection with the optimization recommendation model module and the DCS respectively.

[0213] The optimization recommendation model module is configured to determine operation variables and control variables of the DCS, and determine an operation variable running value of the operation variables, a control variable predicted value of the control variables, and a control variable target value of the control variables.

[0214] The optimization control model module is configured to acquire the operation variable running value of the operation variables, the control variable predicted value of the control variables, and the control variable target value of the control variables determined by the optimization recommendation model module, and adjust the operation variable running value of the DCS so that the control variable predicted value approximates the control variable target value.

[0215] In an optional embodiment of the present application, the optimization recommendation model module is specifically configured to:

[0216] The operation variable running value of the operation variable and the cement raw material quality inspection data are acquired from a DCS of a cement production line; a control variable predicted value of the control variable is determined according to the operation variable running value; and a control variable target value of the control variable is determined according to the operation variable running value and the cement raw material quality inspection data.

[0217] In an optional embodiment of the present application, the optimization recommendation module comprises a quality prediction model module and an energy consumption prediction model module, wherein the energy consumption prediction model module comprises:

[0218] A second acquisition module is configured to acquire an energy consumption prediction model, the energy consumption prediction model comprising a corresponding relationship between the operation variable and the control variable;

[0219] A predicted value determination module is configured to determine the control variable predicted value according to the operation variable running value and the energy consumption prediction model.

[0220] The quality prediction model module comprises:

[0221] A third acquisition module is configured to acquire a quality prediction model, the quality prediction model comprising a corresponding relationship between the operation variable and the cement raw material quality inspection data and the cement clinker predicted data, and a corresponding relationship between the cement clinker predicted data within a quality inspection requirement range of the cement clinker and the operation variable;

[0222] A target value determination module is configured to determine the control variable target value of the control variable according to the operation variable running value and the cement raw material quality inspection data by using the quality prediction model.

[0223] In an optional embodiment of the present application, the system further comprises a model online evaluation and update module, the model online evaluation and update module being in communication connection with the DCS, and the model online evaluation and update module being in communication connection with the quality prediction model module and the energy consumption prediction model module, the model online evaluation and update module comprising:

[0224] A fourth acquisition module is configured to acquire historical running data of the DCS when a preset condition is met, the historical running data comprising operation variable historical values of the operation variable and control variable historical values of the control variable;

[0225] A first training module is configured to train the energy consumption prediction model according to the operation variable historical values and the control variable historical values.

[0226] In an optional embodiment of the present application, the model online evaluation and update module comprises:

[0227] a fifth obtaining module, configured to obtain historical operation data of the DCS and historical quality inspection data of the cement raw material and historical quality inspection data of the cement clinker corresponding to the historical operation data when a preset condition is met, the historical operation data including historical operation variable values of the operation variables and historical control variable values of the control variables;

[0228] a second training module, configured to train the quality prediction model according to the historical operation variable values, the historical control variable values, the historical quality inspection data of the cement raw material and the historical quality inspection data of the cement clinker.

[0229] In an optional embodiment of the present application, the optimization control model module comprises:

[0230] an adjustment direction determining module, configured to determine an adjustment direction of the control variable according to the control variable predicted value, the control variable target value, the operation variable running value and a preset optimization algorithm, the adjustment direction including increasing the operation variable running value and reducing the operation variable running value;

[0231] an adjustment control module, configured to adjust the operation variable running value according to the adjustment direction so as to make the control variable predicted value approach the control variable target value.

[0232] In an optional embodiment of the present application, the system further comprises a dynamic control model module, which is in communication connection with the DCS; the dynamic control model module comprises:

[0233] a parameter determining module, configured to determine an adjustment parameter of the operation variable running value according to the abnormal working condition when the abnormal working condition occurs;

[0234] a second adjustment module, configured to adjust the operation variable running value according to the adjustment parameter.

[0235] In an optional embodiment of the present application, the system further comprises a real-time data sampling and processing module, which is in communication connection with the dynamic control model module and the DCS respectively, and the real-time data sampling and processing module comprises:

[0236] a point position feature obtaining module, configured to obtain point position features of the production line;

[0237] an abnormal working condition judging module, configured to judge whether an abnormal working condition occurs according to the point position features.

[0238] In an optional embodiment of the present application, the system further comprises an interlocking module, which is in communication connection with the dynamic control model module and the optimization control model module respectively, and is used for locking the control loop of adjusting the operating variable running value to make the control variable predicted value approach the control variable target value when an abnormal working condition occurs.

[0239] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts are referred to the part of the method embodiment.

[0240] The embodiments of the present application further disclose an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and the computer program implements the steps of the production line real-time optimization control method when executed by the processor.

[0241] The embodiments of the present application further disclose a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program implements the steps of the production line real-time optimization control method when executed by a processor.

[0242] Each of the embodiments in the present specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0243] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a device, or a computer program product. Therefore, the embodiments of the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present application can adopt a computer program product in the form of being implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0244] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams according to the method, terminal device (system), and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the computer or other programmable data processing terminal device produce a device for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The device for implementing the functions specified in one flow or multiple flows and / or blocks Figure 1 one flow or multiple flows and / or blocks

[0245] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow Figure 1 one or more flow or block Figure 1 one or more flow or block

[0246] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 one or more flow or block Figure 1 one or more flow or block

[0247] Although preferred embodiments of the application have been described, those skilled in the art will recognize that additional modifications and changes can be made thereto without departing from the scope of the application. Accordingly, the appended claims are intended to cover all such modifications and changes as fall within the scope of the application.

[0248] Finally, it should be noted that the terms "first", "second", and the like, herein do not denote any order, quantity, combination, or importance, but rather are used to nomenclature different components to distinguish one component from another component and do not necessarily imply or require any such actual relationship or order. Also, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0249] The method and device, system and equipment and storage medium provided by the present application are described in detail above, and the principle and implementation mode of the present application are described by using specific examples in the present application; the above description of the embodiments is only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed; in conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for real-time optimization control of a production line, characterized by, The method is used for real-time optimization control of a distributed control system (DCS) of a cement production line, and comprises the following steps: obtaining operation variable running values of operation variables and cement raw material quality inspection data from a DCS of a cement production line; determining control variable predicted values of control variables according to the operation variable running values; wherein the operation variables are variables that can be directly adjusted in the DCS, and the control variables are variables that cannot be directly adjusted in the DCS; obtaining a quality prediction model, wherein the quality prediction model comprises a corresponding relationship between operation variables and predicted data of cement clinker and quality inspection data of cement raw material, and further comprises a corresponding relationship between the predicted data of cement clinker within a quality inspection requirement range of the cement clinker and the operation variables; determining control variable target values of the control variables by the quality prediction model according to the operation variable running values and the quality inspection data of the cement raw material; adjusting the operation variable running values of the DCS so as to make the control variable predicted values approach the control variable target values.

2. The method of claim 1, wherein: The step of determining the control variable predicted values according to the operation variable running values comprises the following steps: obtaining an energy consumption prediction model, wherein the energy consumption prediction model comprises a corresponding relationship between the operation variables and the control variables; determining the control variable predicted values according to the operation variable running values and the energy consumption prediction model.

3. The method of claim 2, wherein, The method further comprises the following steps: when a preset condition is met, obtaining historical running data of the DCS, wherein the historical running data comprises operation variable historical values of the operation variables and control variable historical values of the control variables; training the energy consumption prediction model according to the operation variable historical values and the control variable historical values.

4. The method of claim 1, wherein, The method further comprises the following steps: when a preset condition is met, obtaining historical running data of the DCS and historical quality inspection data of cement raw material and historical quality inspection data of cement clinker corresponding to the historical running data, wherein the historical running data comprises operation variable historical values of the operation variables and control variable historical values of the control variables; training the quality prediction model according to the operation variable historical values, the control variable historical values, the historical quality inspection data of the cement raw material and the historical quality inspection data of the cement clinker.

5. The method of claim 1, wherein, The step of adjusting the operation variable running values of the DCS so as to make the control variable predicted values approach the control variable target values comprises the following steps: determining an adjustment direction of the control variables according to the control variable predicted values, the control variable target values, the operation variable running values and a preset optimization algorithm; the adjustment direction comprises increasing the operation variable running values and decreasing the operation variable running values; adjusting the operation variable running values according to the adjustment direction so as to make the control variable predicted values approach the control variable target values.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises the following steps: when an abnormal working condition occurs, determining adjustment parameters of the operation variable running values according to the abnormal working condition; adjusting the operation variable running values according to the adjustment parameters.

7. The method of claim 6, wherein, Before the step of determining the adjustment parameters of the operation variable running values according to the abnormal working condition when the abnormal working condition occurs, the method further comprises the following step: obtaining point features of the production line. Determine whether an abnormal working condition occurs according to the point feature.

8. The method of claim 6, wherein, The method further comprises: When the abnormal working condition occurs, lock the control loop of adjusting the operating value of the operating variable to make the predicted value of the control variable approach the target value of the control variable.

9. A production line real-time optimization control apparatus characterized by comprising: The device is used for real-time optimization control of a distributed control system (DCS) of a production line, and comprises: A first acquisition module is configured to acquire an operating value of an operating variable and cement raw material quality inspection data from a DCS of a cement production line. A first determination module is configured to determine a predicted value of a control variable according to the operating value of the operating variable; wherein the operating variable is a variable that can be directly adjusted in the DCS, and the control variable is a variable that cannot be directly adjusted in the DCS. A third acquisition module is configured to acquire a quality prediction model, which comprises a corresponding relationship between the operating variable and the predicted data of the cement clinker and the quality inspection data of the cement raw material, and a corresponding relationship between the predicted data of the cement clinker and the operating variable within a quality inspection requirement range of the cement clinker. A target value determination module is configured to determine a target value of the control variable of the control variable according to the operating value of the operating variable and the quality inspection data of the cement raw material through the quality prediction model. An adjustment module is configured to adjust the operating value of the operating variable of the DCS to make the predicted value of the control variable approach the target value of the control variable.

10. A production line real-time optimization control system, characterized by, The system comprises a distributed control system (DCS) of a production line, an optimization recommendation model module, and an optimization control model module; the optimization recommendation model module is in communication connection with the DCS, and the optimization control model module is in communication connection with the optimization recommendation model module and the DCS, respectively. The optimization recommendation model module is configured to acquire an operating value of an operating variable and cement raw material quality inspection data from a DCS of a cement production line; determine a predicted value of a control variable according to the operating value of the operating variable; wherein the operating variable is a variable that can be directly adjusted in the DCS, and the control variable is a variable that cannot be directly adjusted in the DCS; acquire a quality prediction model, which comprises a corresponding relationship between the operating variable and the predicted data of the cement clinker and the quality inspection data of the cement raw material, and a corresponding relationship between the predicted data of the cement clinker and the operating variable within a quality inspection requirement range of the cement clinker; and determine a target value of the control variable of the control variable according to the operating value of the operating variable and the quality inspection data of the cement raw material through the quality prediction model. The optimization control model module is configured to acquire the operating value of the operating variable, the predicted value of the control variable of the control variable, and the target value of the control variable of the control variable determined by the optimization recommendation model module, and adjust the operating value of the operating variable of the DCS to make the predicted value of the control variable approach the target value of the control variable.

11. An electronic device, comprising: The device comprises a processor, a memory, and a computer program stored on the memory and capable of running on the processor, and the computer program is executed by the processor to implement the steps of the production line real-time optimization control method according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the production line real-time optimization control method in any one of claims 1 to 8.

Images