Intelligent optimization method and system for wet ball mill of coal-fired power plant

Abstract

The invention relates to the technical field of ball mill optimization, and discloses an intelligent optimization method for a wet ball mill of a coal-fired power plant, which comprises the following steps: S1, pre-checking the wet ball mill and matched equipment thereof, and accessing a distributed control system through the Internet of Things technology to obtain real-time operation parameters; the invention also discloses an intelligent optimization system for the wet ball mill of the coal-fired power plant, which comprises the following modules: a data acquisition layer module used for accessing the distributed control system through a sensor to obtain the real-time operation parameters of the wet ball mill; and the data analysis layer module is used for carrying out cleaning, feature extraction and modeling analysis on the acquired real-time operation parameters. Through the artificial intelligence Informer large model and the IoT technology, intelligent prediction and dynamic optimization of the wet ball mill are achieved, consumption of steel balls and electric energy is reduced, economic benefits are improved, the system supports multi-mode operation, the data visualization technology is combined, manual monitoring limitation is eliminated, and management efficiency and safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ball mill optimization, and in particular to an intelligent optimization method and system for a wet ball mill in a coal-fired power plant. Background Art

[0002] Wet ball mill plays a key role in the limestone-gypsum wet desulfurization system of coal-fired power plants, which meets the desulfurization requirements by grinding limestone slurry. However, the traditional steel ball addition method exposes significant deficiencies in efficiency, energy consumption and safety, which restricts the overall performance of wet ball mill.

[0003] In the traditional method, the addition of steel balls depends on the experience of the operator, and the current drop is usually used as the basis for judging whether the steel balls need to be supplemented. However, the operating environment of the wet ball mill is complex, and the current change may be caused by many factors. It is difficult to guarantee the accuracy of steel ball addition based on a single parameter. As a result, excessive or insufficient steel balls are often added. Excessive addition not only increases energy consumption, but also imposes an additional burden on the equipment; insufficient steel balls lead to substandard slurry particle size control, thereby affecting desulfurization efficiency. This human-dominated method has obvious limitations in accuracy and efficiency.

[0004] In addition, the wet ball mill consumes a high proportion of energy during operation, and its operating efficiency is closely related to the amount and timing of steel ball addition. Traditional manual adjustments cannot dynamically optimize the steel ball replenishment strategy according to real-time working conditions, and it is often difficult to find a balance between energy consumption and efficiency. For example, excessive steel ball input has limited efficiency improvement, but energy consumption surges; insufficient steel balls lead to low efficiency, which directly affects the realization of production goals. This contradiction has not been effectively resolved for a long time, making it difficult for wet ball mills to achieve economical operation.

[0005] At the same time, the traditional method of adding steel balls requires frequent manual intervention, which not only interrupts the continuous operation of the equipment, but also increases safety hazards. During the steel ball delivery process, operators need to work in a high temperature and high humidity environment, which may cause equipment damage or other unexpected risks. In addition, frequent downtime operations also reduce production efficiency and further increase operation and maintenance costs.

[0006] It can be seen that the traditional steel ball adding method faces major challenges in terms of precision control, energy consumption optimization and safety assurance. This method not only fails to meet the requirements of modern coal-fired power plants for high efficiency and low consumption, but also limits the room for improvement of wet ball mills in terms of environmental protection and economic goals. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention provides an intelligent optimization method and system for a wet ball mill in a coal-fired power plant, which solves the problems of low efficiency, excessive energy consumption, frequent manual intervention and safety hazards in the traditional steel ball addition method of the wet ball mill in a coal-fired power plant.

[0008] To achieve the above objectives, the present invention is implemented by the following technical scheme: an intelligent optimization method for a wet ball mill in a coal-fired power plant, comprising the following steps: S1. Preliminary inspection of the wet ball mill and its supporting equipment, and access to the distributed control system through the Internet of Things technology to obtain real-time operating parameters, including but not limited to limestone consumption, limestone slurry volume, wet ball mill operating current, wet ball mill power consumption and wet ball mill operating time; S2. Based on big data analysis, the collected data is cleaned, features are extracted and integrated for analysis to identify the complex relationship between limestone consumption and wet ball mill operating current, steel ball weight and steel ball specifications; S3. Use the artificial intelligence Informer large model to calculate the optimal working state of the wet ball mill, including the optimal current range and steel ball addition strategy; S4. Dynamically adjust the operating parameters of the wet ball mill according to the optimization decision, control the current of the wet ball mill within the optimal range, and automatically perform the steel ball adding operation, including the adding time and quantity of the steel balls.

[0009] Preferably, the cleaning of the collected data in step S2 comprises the following steps: The operating current and power consumption signals of the wet ball mill are smoothed by the sliding window method. Detect outliers in operational data and mark or remove them; Interpolation algorithms are used to fill in missing data to generate a complete data set.

[0010] Preferably, the optimization decision in S4 is based on the following contents: Use time series prediction model to predict the future trend of wet ball mill operating current; Determine the optimal time and quantity of adding steel balls through big data analysis, which is dynamically calculated based on limestone consumption, wet ball mill power consumption, and current steel ball consumption rate; Dynamically adjust the operating current of the wet ball mill so that it can be stabilized within the preset minimum operating current range while meeting the best grinding efficiency.

[0011] Preferably, the optimal steel ball adding strategy in step S3 is determined according to the following steps: Calculate the relationship between limestone consumption and steel ball consumption per unit time; Optimize the calculation of the number of steel balls to be added based on the maximum ball loading capacity of the equipment, steel ball specifications and wear rate; According to the load and working status of the wet ball mill predicted by big data, the specific time point for adding steel balls is determined.

[0012] An intelligent optimization system for wet ball mills in coal-fired power plants, including the following modules: The data acquisition layer module is used to obtain the real-time operating parameters of the wet ball mill through the sensor access to the distributed control system; The data analysis layer module is used to clean, extract features and conduct modeling analysis on the collected real-time operating parameters; A decision-making layer module, which is used to generate the optimal working state of the wet ball mill based on the analysis results, including the current range and steel ball addition strategy; The execution control layer module is used to dynamically adjust the operating parameters of the wet ball mill and control the steel ball adding equipment to perform corresponding operations according to the output of the decision layer A data storage module, used for storing real-time parameters and historical operation data of the wet ball mill; An alarm module is used to trigger an alarm to notify relevant personnel when the current of the wet ball mill exceeds the set range or an abnormality occurs; Data visualization module for displaying wet ball mill operation trends and ball addition statistics in graphical form.

[0013] Preferably, the data acquisition layer module includes: a sensor interface unit for receiving operating parameters of the wet ball mill, including limestone consumption, wet ball mill operating current, and wet ball mill power consumption; A data transmission unit for transmitting real-time data to a distributed control system via industrial wireless communication technology or wired Ethernet; The security encryption unit is used to encrypt the collected and transmitted data to ensure data security.

[0014] Preferably, the data analysis layer module includes: A data cleaning unit is used to smooth the noise data in the wet ball mill operating parameters and to interpolate and complete the missing values; Feature extraction unit, used to extract the core feature parameters of limestone consumption, wet ball mill operating current and steel ball addition; The time series analysis unit is used to predict the future operating status of the wet ball mill based on the Informer model.

[0015] Preferably, the decision-making layer module includes: A rule generation unit for developing the optimal current range and ball addition strategy for wet ball mill operation; Optimization calculation unit for dynamically adjusting the operating current and steel ball addition time according to the limestone consumption and wet ball mill operating load; The decision output unit is used to send the optimization results to the execution control layer module.

[0016] Preferably, the execution control layer module includes: An operating parameter adjustment unit is used to dynamically adjust the operating current of the wet ball mill and control it to be stable within an optimal range; A steel ball adding control unit, used to automatically perform the steel ball adding operation according to the optimization results; Interlock protection unit is used to ensure that steel balls are added only when the wet ball mill and related equipment are in operation.

[0017] The present invention provides an intelligent optimization method and system for a wet ball mill in a coal-fired power plant, which has the following beneficial effects: 1. The present invention introduces the artificial intelligence Informer large model and IoT technology to achieve intelligent prediction and dynamic adjustment of the operating parameters of the wet ball mill, successfully controls the current of the wet ball mill within the minimum threshold range that meets production needs, optimizes the steel ball addition strategy, and greatly reduces the consumption of steel balls and electricity. Compared with the traditional operation method that relies on manual experience, the present invention avoids the problem of untimely or excessive steel ball replenishment, significantly reduces the operating cost, and solves the difficult problems of traditional technology in energy waste and insufficient economic efficiency.

[0018] 2. The present invention adopts multi-mode operation support, combines deep learning algorithms with data visualization technology, and provides three flexible options: intelligent mode, automatic mode, and manual mode. The system can not only analyze data trends in real time, but also automatically adjust the operating status of the equipment. In traditional methods, operations rely on manual monitoring and cannot respond in real time. The present invention effectively eliminates the limitations of manual intervention and solves the problem of single operation mode and difficulty in adapting to complex working conditions in the prior art, greatly improving management efficiency and production safety.

[0019] 3. The present invention realizes fully automated operation from equipment operation monitoring to steel ball addition through complete data collection, analysis, decision-making and execution closed-loop control. It has breakpoint resumption and multiple fault-tolerant mechanisms. The TLS encryption protocol and identity authentication are introduced in the data transmission process to ensure communication security and data integrity. Traditional technologies are insufficient in handling data loss and network failures. The present invention not only enhances the stability and security of the system, but also improves the reliability of equipment operation, solving the hidden dangers of downtime or reduced efficiency due to equipment failure in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the method flow of the present invention; Figure 2 It is the overall system architecture diagram of the present invention; Figure 3 A network topology diagram of the present invention; Figure 4It is a system framework diagram of the present invention; Figure 5 It is the data acquisition layer module of the present invention; Figure 6 The data analysis layer module of the present invention; Figure 7 It is the decision-making layer module of the present invention; Figure 8 It is the execution control layer module of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Please see attached Figure 1 The embodiment of the present invention provides an intelligent optimization method for a wet ball mill in a coal-fired power plant, comprising the following steps: S1. Conduct a preliminary inspection of the wet ball mill and its supporting equipment, and access the distributed control system through the Internet of Things technology to obtain real-time operating parameters, including but not limited to limestone consumption, limestone slurry volume, wet ball mill operating current, wet ball mill power consumption and wet ball mill operating time; In this embodiment, a comprehensive inspection is first performed on the wet ball mill and its supporting equipment to ensure that the equipment is in normal operation. This step includes the integrity inspection of the equipment's mechanical system, electrical system, and sensors. Specifically: Check the ball storage bin, motor, reducer, sprocket and transmission mechanism to see if their connections are firm and if they are in normal wear condition.

[0023] Check whether accessories such as protective covers and vibrators are working properly to avoid affecting the accuracy of subsequent sensor acquisition.

[0024] Verify the status of sensors to ensure they are accurately sensing key parameters such as current, voltage, limestone consumption, etc.

[0025] Generally, sensor inspection also includes regular calibration to ensure the accuracy of data collection. For example, the sensor output value is verified to be in compliance with the specification by inputting a standard signal.

[0026] After confirming that the equipment is in a normal state, the DCS system is accessed through the Internet of Things technology to collect and transmit the equipment's operating data. Specifically, this embodiment uses a variety of industrial protocols and data transmission methods to ensure the comprehensiveness and stability of data collection.

[0027] In some embodiments, the real-time operation data of the wet ball mill is connected to the distributed control system via ModbusTCP or UDP protocol. As an option, data access can also be achieved by directly connecting to the DPU control cabinet board. Such protocols can achieve efficient field device communication.

[0028] In general, data transmission can be carried out through industrial wireless communication technologies (such as LoRaWAN or NB-IoT) or wired Ethernet. In specific implementation, the appropriate communication method is selected according to the infrastructure conditions of the power plant. For example, when the wet ball mill is located in an area far away from the control room, LoRaWAN is preferred to provide long-distance wireless communication.

[0029] The data is encrypted using TLS or SSL protocols during transmission to prevent data tampering or leakage. As an implementation method, identity authentication can also be implemented on the devices connected to the sensor to ensure that only authorized devices can send or receive data.

[0030] In this embodiment, the collected operating parameters cover a variety of key process and equipment data of the wet ball mill, including but not limited to the following categories: Equipment working parameters: Working current of wet ball mill (Unit: Ampere).

[0031] Power consumption of the device (Unit: kilowatt-hour).

[0032] Run time (Unit: one hour).

[0033] Speed R (Unit: revolutions per minute).

[0034] Process indicators: Limestone consumption (Unit: tons).

[0035] Limestone slurry volume (Unit: cubic meter).

[0036] Device configuration parameters: Steel ball weight (Unit: tons).

[0037] Ball Specifications (Unit: mm).

[0038] Maximum ball loading (Unit: tons).

[0039] Rated Power (Unit: kilowatt).

[0040] System frequency f (Unit: Hertz).

[0041] In one possible implementation, the collected data is transmitted to the distributed control system in real time and stored in a central database in a structured manner. The data at each sampling time point contains multiple fields, including equipment status information, real-time operating indicators, and environmental parameters.

[0042] For example, at a certain point in time t The running status of the data can be represented as a multidimensional vector:

[0043] This multidimensional data format facilitates the subsequent data analysis phase to extract key features and input them into the optimization model.

[0044] In order to ensure the timeliness of the data, in general, the data sampling frequency is set to 1 second / time in this embodiment, that is, the key operating parameters of the wet ball mill are collected once per second. As an option, when the equipment operating conditions are relatively stable, the sampling frequency can be adjusted to 5 seconds / time or a longer time interval to reduce the burden of data transmission.

[0045] In another embodiment, a dynamic sampling strategy may also be set. For example: When the wet ball mill is running When the change in current exceeds the set threshold, the system will automatically increase the sampling frequency to capture the details of the current fluctuation.

[0046] When the device is not in operation, only static status data of the device is collected to save storage resources.

[0047] In some embodiments, to ensure the integrity of collected data, this embodiment adopts the following mechanism: After each sampling, the communication between the sensor and DCS will return a confirmation signal to avoid data loss.

[0048] If the operating data at certain time points is missing, the system will mark these time points as invalid and notify the relevant maintenance personnel.

[0049] For sudden network interruptions, a breakpoint-resume mechanism is used to resume data collection.

[0050] In addition, the system also regularly calibrates the sensor to check whether its measurement error is within the allowable range. In this way, data deviation caused by sensor aging is avoided.

[0051] S2. Based on big data analysis, the collected data is cleaned, features are extracted and integrated for analysis to identify the complex relationship between limestone consumption and wet ball mill operating current, steel ball weight and steel ball specifications; In this embodiment, data cleaning first smoothes the noise signal. To ensure the stability of the wet ball mill operation data, the sliding window average method is used to smooth the collected current, voltage and other parameters. The calculation formula is:

[0052] in, is the smoothed data value, n is the window size, k=(n−1) / 2 The selection of the window is dynamically adjusted according to the operating characteristics of the wet ball mill. In one possible implementation, for the operating stage with large current fluctuations, a smaller window n=5 is selected; while for the stable operating stage, the window size can be increased to n=10 to further smooth the data.

[0053] In some embodiments, possible outliers are also marked or removed. Specifically, the Z-score standardization method is used to calculate the degree of dispersion of each data point:

[0054] in, x is the current data point, μ is the mean of the data, σ is the standard deviation. , then the data point is considered an outlier and marked as invalid. In another possible implementation, the outlier point is replaced by the mean of its neighboring data points to ensure data continuity.

[0055] In some implementations, outliers are replaced with the mean of nearby data points:

[0056] To ensure data continuity.

[0057] In the case of missing data, linear interpolation is used to complete the data. Assuming that the current data at time point t is missing, it is calculated using the following formula:

[0058] in: is the time of adjacent known data points; 、 are known values ​​at adjacent time points.

[0059] In this embodiment, after data cleaning is completed, feature extraction is performed on the processed data. Generally, the goal of feature extraction is to mine key indicators of wet ball mill operating parameters to provide a scientific basis for subsequent optimization models.

[0060] Specifically, the extracted features include but are not limited to: Limestone consumption rate , and its calculation formula is:

[0061] in, is the consumption of limestone per unit time, and ΔT is the sampling time interval.

[0062] Ball wear rate , and its calculation formula is:

[0063] in, is the reduction in weight of the steel ball per unit time.

[0064] Power consumption per unit time , whose expression is:

[0065] in, is the power consumption of the wet ball mill, is the running time.

[0066] In a possible implementation, statistical features within the rolling window, such as mean, standard deviation, maximum value, and minimum value, can also be constructed. These statistics are helpful in capturing the local variation trend during the operation of the wet ball mill.

[0067] As an option, you can also perform feature screening based on the correlation between the feature and the target variable. Specific methods include calculating the Pearson correlation coefficient, ranking the feature importance, etc. For example, when using the random forest model for feature screening, you can retain the top 10% of key features by calculating the contribution of each feature to the target output (such as the optimal current range).

[0068] In this embodiment, after feature extraction, a deep learning algorithm is used to analyze the intrinsic relationship between the operating parameters of the wet ball mill. Specifically, multiple groups of relationship models are constructed using regression models, time series models, and machine learning models.

[0069] In the regression model, predicting limestone consumption With wet ball mill current And steel ball weight The relationship between:

[0070] in, a, b, c is the regression coefficient, obtained by fitting the historical data.

[0071] In time series models, predicting future current In general, the LSTM network is used to capture the time-dependent characteristics of the current, and its state update formula is:

[0072] in, is the hidden state at the current moment, For input data, are the network weights and biases.

[0073] In the machine learning model, XGBoost or LightGBM was used for feature importance analysis and to optimize the operating parameters of the wet ball mill.

[0074] S3. Use the artificial intelligence Informer large model to calculate the optimal working state of the wet ball mill, including the optimal current range and steel ball addition strategy; In this embodiment, the operating conditions of the wet ball mill are first analyzed using the trained Informer large model. The Informer model is a time series prediction model based on deep learning, which can efficiently process large-scale time series data. Specifically, the model is mainly composed of an encoder, a decoder, and a self-attention mechanism.

[0075] In one possible implementation, the features input to the model include limestone consumption , Working current of wet ball mill , Steel ball weight , Steel ball specifications The model predicts the future operating status of the wet ball mill based on the input characteristics and outputs the optimal current range and optimal steel ball addition strategy.

[0076] As an option, the encoder is used to capture long-term dependencies in the time series and extract features by stacking multiple layers of self-attention mechanisms; the decoder generates prediction results for future time points based on the output of the encoder. The role of the attention mechanism is to filter the input features that have the greatest impact on the prediction target to improve the accuracy of the prediction.

[0077] In this embodiment, the model prediction results are used to determine the optimal operating current range of the wet ball mill. The following conditions are met: Current In this range, the grinding efficiency of the wet ball mill is the highest.

[0078] The current fluctuation is small and can be stably maintained at the minimum value within the set range.

[0079] Through historical operation data, the grinding efficiency of the wet ball mill under different currents is calculated, and then the functional relationship between current and efficiency is fitted:

[0080] in, η is the grinding efficiency of the wet ball mill, is the working current. The maximum value of the function is found by taking the derivative, and reasonable upper and lower limits are set based on industry experience to obtain the optimal current range.

[0081] Specifically, assuming the function It is in parabolic form, with the maximum point at ,but:

[0082] in, is the allowable current fluctuation range.

[0083] In this embodiment, on the basis of determining the optimal working current range, a steel ball adding strategy is further formulated. Generally, the steel ball adding strategy includes two aspects: adding time point and quantity.

[0084] Number of steel balls added The calculation is based on the following formula:

[0085] in, is the consumption of limestone, k is the grinding efficiency coefficient of the steel ball, is the specification (diameter) of the steel ball.

[0086] As a way to achieve this, you can add time points to the steel ball Set as the most recent time point when limestone consumption reaches a certain threshold. Use the time series model to predict the trend of limestone consumption and find the time point that meets the following conditions:

[0087] in, is the limestone consumption when the steel balls were added last time, is the critical value of limestone consumption.

[0088] In this embodiment, the operating parameters of the wet ball mill are optimized by dynamically adjusting the algorithm in combination with the optimal operating current range and the steel ball adding strategy. Generally, the goal of the adjustment is to ensure that the current is stable at the lowest value within the range, while adding steel balls on time to ensure grinding efficiency.

[0089] In one possible implementation, the system monitors the operating current of the wet ball mill in real time. .like Out of optimal range , the system automatically adjusts the operating parameters of the wet ball mill (such as speed or feed amount) to return them to the set range.

[0090] In addition, parameters can be continuously optimized based on actual operating data. For example, using reinforcement learning algorithms, key parameters of current ranges and adding strategies can be dynamically updated based on historical adjustment result feedback.

[0091] In this embodiment, in order to verify the accuracy and optimization effect of the model, a variety of evaluation indicators can be used, including mean square error (MSE), mean absolute error (MAE) and root mean square error (RMSE). Taking mean square error as an example, its calculation formula is: in, is the actual value, is the predicted value, n is the number of samples.

[0092] In some embodiments, the actual effect of the model can also be evaluated by comparing the wet ball mill operation data before and after optimization (such as limestone consumption per unit time, power consumption, etc.). Specifically, the power consumption reduction before and after optimization can be statistically analyzed:

[0093] in, is the power consumption before optimization, For optimized power consumption.

[0094] S4. Dynamically adjust the operating parameters of the wet ball mill according to the optimization decision, control the current of the wet ball mill within the optimal range, and automatically perform the steel ball adding operation, including the adding time and quantity of the steel balls.

[0095] In this embodiment, the operation current regulation of the wet ball mill is the core of the optimized operation. ,The system realizes real-time monitoring and dynamic adjustment of working current through intelligent regulation algorithm.

[0096] Specifically, the running current collected in real time Compare with the interval range. If the current exceeds the preset range, the control module will automatically adjust the operating parameters of the wet ball mill, including equipment speed, feed rate, etc., until the current returns to the preset range.

[0097] In a possible implementation, the adjustment parameter is calculated by the following control logic:

[0098] in: is the adjusted power input; is the target current value; are the proportional, integral and differential control parameters.

[0099] Generally speaking, this PID (proportional-integral-differential) control method is suitable for the rapid fluctuation response of the current in the operation of the wet ball mill. For the operation stage with slow current changes, the weights to reduce the frequency of unnecessary adjustments.

[0100] In this embodiment, the steel ball adding operation is automatically completed under the control of the intelligent ball adding machine based on the optimization strategy of step S3. and quantity to perform the operation.

[0101] In a possible implementation, the number of steel balls added is It is calculated by the following formula:

[0102] in: is the consumption of limestone per unit time; k is the grinding efficiency coefficient of the steel ball; is the steel ball specification (diameter).

[0103] As an option, the system can also dynamically adjust the number of steel balls added. For example, when the wet ball mill is running at a low current When abnormal fluctuations occur, the ball adding operation can be temporarily suspended and resumed after the current is restored.

[0104] The execution process of steel ball addition involves the following specific steps: The ball adding machine takes out a set number of steel balls from the ball storage bin; The steel balls are fed into the wet ball mill through a chain conveyor; After adding balls, the system records the ball adding log, including time point, quantity and other information.

[0105] In this embodiment, in order to ensure the accuracy and safety of the ball adding process, the system supports three operation modes: intelligent mode, automatic mode and manual mode.

[0106] Specifically: Intelligent mode: The system automatically executes according to the optimization results output by the decision-making layer, including current regulation and steel ball adding operations.

[0107] Automatic mode: The ball addition operation is controlled by preset rules, for example, the ball addition is performed at fixed time intervals or after reaching a set threshold.

[0108] Manual mode: The user manually triggers the ball adding operation through the touch screen or remote control interface, which is used in special working conditions or equipment debugging stage.

[0109] In a possible implementation, the system automatically monitors the working status of the ball adding machine, including the chain operation status, the remaining steel balls in the ball storage bin, etc., to ensure the continuity and reliability of the ball adding process.

[0110] In this embodiment, in order to prevent equipment damage caused by misoperation or abnormal conditions, the system is equipped with a multiple interlocking protection mechanism.

[0111] Specifically: During the ball adding process, the system detects the operating status of the wet ball mill and the weighing belt feeder. If it is found that both are in the shutdown state, the ball adding operation is prohibited and an alarm is triggered.

[0112] For abnormal situations such as long ball blocking time and no ball time, the system automatically suspends operation and records relevant logs for reference by maintenance personnel.

[0113] As an option, safety mechanisms also include overload protection and network communication fault detection. Exceeding the rated current of the device When the set ratio is exceeded, the system triggers an emergency stop and sends an alarm notification.

[0114] In this embodiment, after the ball adding operation is completed, the system records the relevant data into the database and displays it to the user through the data visualization interface. The recorded data includes: The time of each extra ball ; Number of balls added ; The operating status of the equipment after adding the ball (such as working current, power consumption, etc.).

[0115] Generally speaking, these data will serve as important input for subsequent model training and optimization, further improving the accuracy and adaptability of the system.

[0116] The intelligent optimization system for a wet ball mill in a coal-fired power plant described below and the intelligent optimization method for a wet ball mill in a coal-fired power plant described above can be referred to each other.

[0117] Please see attached Figure 2 -Attached Figure 4 , an intelligent optimization system for a wet ball mill in a coal-fired power plant, characterized in that it includes the following modules: The data acquisition layer module is used to obtain the real-time operating parameters of the wet ball mill through the sensor access to the distributed control system; The data analysis layer module is used to clean, extract features and conduct modeling analysis on the collected real-time operating parameters; A decision-making layer module, which is used to generate the optimal working state of the wet ball mill based on the analysis results, including the current range and steel ball addition strategy; The execution control layer module is used to dynamically adjust the operating parameters of the wet ball mill and control the steel ball adding equipment to perform corresponding operations according to the output of the decision layer A data storage module, used for storing real-time parameters and historical operation data of the wet ball mill; An alarm module is used to trigger an alarm to notify relevant personnel when the current of the wet ball mill exceeds the set range or an abnormality occurs; Data visualization module for displaying wet ball mill operation trends and ball addition statistics in graphical form.

[0118] Please see attached Figure 5 , the data acquisition layer modules include: a sensor interface unit for receiving operating parameters of the wet ball mill, including limestone consumption, wet ball mill operating current, and wet ball mill power consumption; A data transmission unit for transmitting real-time data to a distributed control system via industrial wireless communication technology or wired Ethernet; The security encryption unit is used to encrypt the collected and transmitted data to ensure data security.

[0119] Please see attached Figure 6 , the data analysis layer modules include: A data cleaning unit is used to smooth the noise data in the wet ball mill operating parameters and to interpolate and complete the missing values; Feature extraction unit, used to extract the core feature parameters of limestone consumption, wet ball mill operating current and steel ball addition; The time series analysis unit is used to predict the future operating status of the wet ball mill based on the Informer model.

[0120] Please see attached Figure 7 , the decision-making layer modules include: A rule generation unit for developing the optimal current range and ball addition strategy for wet ball mill operation; Optimization calculation unit for dynamically adjusting the operating current and steel ball addition time according to the limestone consumption and wet ball mill operating load; The decision output unit is used to send the optimization results to the execution control layer module.

[0121] Please see attached Figure 8 , the execution control layer modules include: An operating parameter adjustment unit is used to dynamically adjust the operating current of the wet ball mill and control it to be stable within an optimal range; A steel ball adding control unit, used to automatically perform the steel ball adding operation according to the optimization results; Interlock protection unit is used to ensure that steel balls are added only when the wet ball mill and related equipment are in operation.

[0122] The system of this embodiment can be used to execute the above method embodiments, and its principles and technical effects are similar, which will not be repeated here.

[0123] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent optimization method for a wet ball mill in a coal-fired power plant, characterized in that: The following steps are involved: S1. Preliminary inspection of the wet ball mill and its supporting equipment, and access to the distributed control system through the Internet of Things technology to obtain real-time operating parameters, including but not limited to limestone consumption, limestone slurry volume, wet ball mill operating current, wet ball mill power consumption and wet ball mill operating time; S2. Based on big data analysis, the collected data is cleaned, features are extracted and integrated for analysis to identify the complex relationship between limestone consumption and wet ball mill operating current, steel ball weight and steel ball specifications; S3. Use the artificial intelligence Informer large model to calculate the optimal working state of the wet ball mill, including the optimal current range and steel ball addition strategy; S4. Dynamically adjust the operating parameters of the wet ball mill according to the optimization decision, control the current of the wet ball mill within the optimal range, and automatically perform the steel ball adding operation, including the adding time and quantity of the steel balls.

2. The intelligent optimization method for a wet ball mill in a coal-fired power plant according to claim 1, characterized in that: The cleaning of the collected data in step S2 includes the following steps: The operating current and power consumption signals of the wet ball mill are smoothed by the sliding window method. Detect outliers in operational data and mark or remove them; Interpolation algorithms are used to fill in missing data to generate a complete data set.

3. The intelligent optimization method for a wet ball mill in a coal-fired power plant according to claim 1, characterized in that: The optimization decision in S4 is based on the following: Use time series prediction model to predict the future trend of wet ball mill operating current; Determine the optimal time and quantity of adding steel balls through big data analysis, which is dynamically calculated based on limestone consumption, wet ball mill power consumption, and current steel ball consumption rate; Dynamically adjust the operating current of the wet ball mill so that it can be stabilized within the preset minimum operating current range while meeting the best grinding efficiency.

4. The intelligent optimization method for a wet ball mill in a coal-fired power plant according to claim 1, characterized in that: The optimal steel ball addition strategy in step S3 is determined according to the following steps: Calculate the relationship between limestone consumption and steel ball consumption per unit time; Optimize the calculation of the number of steel balls to be added based on the maximum ball loading capacity of the equipment, steel ball specifications and wear rate; According to the load and working status of the wet ball mill predicted by big data, the specific time point for adding steel balls is determined.

5. An intelligent optimization system for a wet ball mill in a coal-fired power plant, characterized in that: Includes the following modules: The data acquisition layer module is used to obtain the real-time operating parameters of the wet ball mill through the sensor access to the distributed control system; The data analysis layer module is used to clean, extract features and conduct modeling analysis on the collected real-time operating parameters; A decision-making layer module, which is used to generate the optimal working state of the wet ball mill based on the analysis results, including the current range and steel ball addition strategy; The execution control layer module is used to dynamically adjust the operating parameters of the wet ball mill and control the steel ball adding equipment to perform corresponding operations according to the output of the decision layer A data storage module, used for storing real-time parameters and historical operation data of the wet ball mill; An alarm module is used to trigger an alarm to notify relevant personnel when the current of the wet ball mill exceeds the set range or an abnormality occurs; Data visualization module for displaying wet ball mill operation trends and ball addition statistics in graphical form.

6. The intelligent optimization system for a wet ball mill in a coal-fired power plant according to claim 5, characterized in that: The data acquisition layer module includes: a sensor interface unit for receiving operating parameters of the wet ball mill, including limestone consumption, wet ball mill operating current, and wet ball mill power consumption; A data transmission unit for transmitting real-time data to a distributed control system via industrial wireless communication technology or wired Ethernet; The security encryption unit is used to encrypt the collected and transmitted data to ensure data security.

7. The intelligent optimization system for a wet ball mill in a coal-fired power plant according to claim 5, characterized in that: The data analysis layer module includes: A data cleaning unit is used to smooth the noise data in the operating parameters of the wet ball mill and to interpolate and complete the missing values; Feature extraction unit, used to extract the core feature parameters of limestone consumption, wet ball mill operating current and steel ball addition; The time series analysis unit is used to predict the future operating status of the wet ball mill based on the Informer model.

8. The intelligent optimization system for a wet ball mill in a coal-fired power plant according to claim 5, characterized in that: The decision-making layer module includes: A rule generation unit for developing the optimal current range and ball addition strategy for wet ball mill operation; Optimization calculation unit for dynamically adjusting the operating current and steel ball addition time according to the limestone consumption and wet ball mill operating load; The decision output unit is used to send the optimization results to the execution control layer module.

9. The intelligent optimization system for a wet ball mill in a coal-fired power plant according to claim 5, characterized in that: The execution control layer module includes: An operating parameter adjustment unit is used to dynamically adjust the operating current of the wet ball mill and control it to be stable within an optimal range; A steel ball adding control unit, used to automatically perform the steel ball adding operation according to the optimization results; Interlock protection unit is used to ensure that steel balls are added only when the wet ball mill and related equipment are in operation.

Images