An intelligent PLC data analysis and optimization control system

Abstract

The present invention relates to the field of PLC control technology, and in particular, to an intelligent PLC data analysis and optimization control system. It includes: a data collection unit for collecting production and consumption data generated during the operation of the equipment; a control algorithm unit based on the production and consumption data collected by the data collection unit, and through a PID control algorithm to process the input data and generate corresponding control instructions, and introduce the equipment temperature and failure rate into the PID control algorithm to improve the accuracy of the control instructions; an optimization decision unit uses a simulated annealing algorithm to adjust the control instructions received from the control algorithm unit; and an adaptive control unit automatically adjusts the control strategy through a K-means clustering algorithm. The present invention is designed to dynamically adjust various parameters in the production process, including workload and production line speed, using a PID control algorithm, which helps to maximize production efficiency and energy efficiency while ensuring product quality.

Description

Technical Field

[0001] The present invention relates to the technical field of PLC control, in particular to an intelligent PLC data analysis and optimization control system. Background Art

[0002] Modern industrial equipment is usually equipped with a large number of sensors that can collect a large amount of data in real time. However, these data are often only used for basic monitoring, and their potential value is not fully explored. The raw data is not processed and analyzed, and it is difficult to extract valuable information from it, and it is impossible to provide a basis for optimizing the control strategy. Traditional PLC control systems are usually based on fixed control logic, which is difficult to cope with changes in environmental conditions. When the production environment or equipment status changes, the fixed control strategy may no longer be applicable, resulting in low efficiency or even failure. In different production stages or equipment states, energy consumption may be unreasonable, resulting in energy waste. There is a lack of effective energy management and optimization mechanisms, and the energy use strategy cannot be dynamically adjusted according to actual needs. Therefore, an intelligent PLC data analysis and optimization control system is designed. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent PLC data analysis and optimization control system to solve the problems of low data utilization, inflexible control strategy and low energy management efficiency proposed in the above background technology.

[0004] To achieve the above object, the present invention provides an intelligent PLC data analysis and optimization control system, comprising:

[0005] A data collection unit, the data collection unit is used to collect production and consumption data generated during the operation of the equipment;

[0006] A control algorithm unit, which processes the input data based on the production and consumption data collected by the data collection unit and generates corresponding control instructions through a PID control algorithm, and introduces the equipment temperature and failure rate into the PID control algorithm to improve the accuracy of the control instructions;

[0007] An optimization decision unit, wherein the optimization decision unit uses a simulated annealing algorithm to adjust the control instruction received from the control algorithm unit;

[0008] An adaptive control unit, wherein the adaptive control unit automatically adjusts the control strategy through a K-means clustering algorithm.

[0009] As a further improvement of the technical solution, the production and consumption data generated during the operation of the equipment collected by the data collection unit includes:

[0010] Equipment energy consumption, equipment capacity, equipment temperature and equipment failure rate.

[0011] As a further improvement of the technical solution, the control algorithm unit processes the input data through the PID control algorithm and generates corresponding control instructions, including the following steps:

[0012] S1.1. Preprocess the collected production and consumption data;

[0013] S1.2. Use the pre-processed production and consumption data to monitor the current state of the system, and analyze the production and consumption data to determine the deviation between the current state and the expected target;

[0014] S1.3, using the PID control algorithm to calculate the error between the current measured value and the set value, where the measured value represents the actual measured value of the production and consumption data, and the set value represents the target value that the production and consumption data is expected to reach;

[0015] S1.4. Improve the control quantity calculated by the PID control algorithm and convert it into specific control instructions. The control instructions include reducing the workload of the equipment, adjusting the speed of the production line, and introducing the equipment temperature and failure rate into the PID control algorithm to improve the accuracy of the control instructions.

[0016] As a further improvement of the technical solution, in S1.3, the PID control algorithm is specifically:

[0017] ;

[0018] The device temperature and failure rate are introduced into the PID control algorithm, specifically:

[0019] ;

[0020] in, Indicates the control instructions applied to the device to be controlled; Indicates the control instruction applied to the device to be controlled after the device temperature and failure rate are introduced; Indicates time; Represents the time from the initial moment to the current moment Any time within the time interval; Represents the time from the initial moment to the current moment The error at any time within the time interval; Represents the proportional gain, which is used to directly respond to the current error size; Represents the integral gain, which is used to accumulate past errors; Represents the differential gain, which is used to predict the changing trend of the error; Indicates the error between the actual frequency and the target frequency; represents the temperature coefficient; Indicates the current temperature of the device; Indicates ideal temperature; represents the failure rate coefficient; The failure rate of the equipment over time changes.

[0021] As a further improvement of the technical solution, the optimization decision unit adjusts the control instruction, including the following steps:

[0022] S2.1, initially set PID control parameters and define the objective function;

[0023] Among them, PID control parameters include proportional gain, integral gain, differential gain, temperature coefficient and failure rate coefficient, and the objective function includes maximizing production capacity and minimizing energy consumption. A weighted combination of equipment aging rate and failure rate is introduced into the objective function.

[0024] S2.2, using simulated annealing algorithm to adjust PID control parameters to minimize the objective function;

[0025] S2.3. During the optimization process, continuously monitor changes in equipment temperature and failure rate, and use them as the basis for adjusting the control strategy.

[0026] As a further improvement of the technical solution, in S2.1, the objective function body is:

[0027] ;

[0028] The weighted combination of equipment aging rate and failure rate introduced into the objective function is as follows:

[0029] ;

[0030] in, represents the objective function; represents the objective function after introducing the weighted combination of equipment aging rate and failure rate; represents the trade-off factor for balancing capacity; represents the trade-off factor for balancing energy consumption; Represents a set of PID control parameters; Indicates Capacity at the moment; represents the number of time steps; Indicates PID control parameters at each moment resulting in energy consumption; Indicates the weight coefficient of the equipment aging rate. The larger the value of, the greater the proportion of the equipment aging rate in the optimization process; Indicates the degree of aging of the equipment over a certain period of time; Indicates the weight coefficient of equipment failure rate. The larger the value of , the greater the proportion of equipment failure rate in the optimization process; Indicates the frequency of equipment failures within a certain period of time; Indicated in The actual measured value of the monitored process at any given moment; Indicated in The expected process value at a given moment; Represents a time index.

[0031] As a further improvement of the technical solution, in S2.2, the PID control parameters are adjusted by using a simulated annealing algorithm, comprising the following steps:

[0032] S2.21, generate a new PID control parameter group from the vicinity of the current PID control parameters, and calculate the objective function value of the new PID control parameter group;

[0033] S2.22, calculate the objective function value under the current PID control parameters and the objective function value under the new PID control parameters, and compare them;

[0034] S2.23. If the objective function value under the new PID control parameters is less than the objective function value under the current PID control parameters, the objective function value under the new PID control parameters is accepted;

[0035] If the objective function value under the new PID control parameters is greater than the objective function value under the current PID control parameters, then the probability Accept the objective function value under the new PID control parameters.

[0036] As a further improvement of the technical solution, the adaptive control unit automatically adjusts the control strategy through a K-means clustering algorithm, comprising the following steps:

[0037] S3.1. Select characteristic data related to the control strategy, the characteristic data including equipment energy consumption, equipment temperature and equipment failure rate;

[0038] S3.2, based on the feature data, the silhouette coefficient method is used to determine the optimal number of clusters K. After determining the optimal number of clusters K, the feature data is clustered using the K-means clustering algorithm to group similar data points together to obtain K different clusters;

[0039] S3.3. Analyze the characteristics of each cluster and understand the environmental conditions represented by each cluster;

[0040] S3.4. Design corresponding PID control parameters for each environmental condition;

[0041] S3.5, associating each cluster with a PID control parameter set, and if the system detects that it is currently in an environmental condition corresponding to a cluster, the PID control parameter set of the cluster is applied;

[0042] S3.6. Regularly re-evaluate feature data and adjust control strategies based on the latest clustering results.

[0043] As a further improvement of the technical solution, in S3.2, the optimal number of clusters K is determined using the silhouette coefficient method, comprising the following steps:

[0044] S3.21. Select a series of different K values. For each K value, use the K-means algorithm to cluster. For each data point , calculate its silhouette coefficient ;

[0045] S3.22, calculate the average value S of the silhouette coefficients of all data points;

[0046] S3.23. For each K value, record its corresponding average silhouette coefficient S, and select the K value that maximizes the average silhouette coefficient S as the optimal number of clusters.

[0047] As a further improvement of the technical solution, in S3.2, the K-means algorithm is specifically:

[0048] ;

[0049] in, represents the within-cluster sum of squares, Indicates the number of clusters; Indicates All data points of a cluster; Indicates The centroid of each cluster; represents a data point in a cluster; Represents the index of the cluster.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. In this intelligent PLC data analysis and optimization control system, through the integrated data collection and control algorithm unit, the system can monitor the operating status of the equipment in real time, including key indicators such as energy consumption, production capacity, temperature and failure rate. The PID control algorithm is used to dynamically adjust various parameters in the production process, including workload, production line speed, etc., which helps to maximize production efficiency and energy utilization efficiency while ensuring product quality. In addition, by incorporating equipment temperature and failure rate into the PID control algorithm, the system can more finely balance energy consumption and production capacity, thereby achieving more economical and efficient production operations.

[0052] 2. In the intelligent PLC data analysis and optimization control system, the simulated annealing algorithm is used to optimize the control strategy. Combined with the K-means clustering technology of the adaptive control unit, the system can automatically adjust the control strategy according to different production environment conditions. This method can not only effectively respond to various changes in the production process, such as production and consumption differences caused by different shifts, seasonal changes or raw material fluctuations, but also adapt to long-term equipment aging and performance degradation by regularly re-evaluating and adjusting the control strategy, thereby enhancing the adaptability and robustness of the entire system and reducing the risk of production interruptions. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is the overall flow chart of the present invention;

[0054] The meaning of each number in the figure is:

[0055] 1. Data collection unit; 2. Control algorithm unit; 3. Optimization decision unit; 4. Adaptive control unit. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments 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.

[0057] See also Figure 1 As shown, an intelligent PLC data analysis and optimization control system is provided, including:

[0058] The data collection unit 1 is used to collect the production and consumption data generated during the operation of the equipment;

[0059] In this embodiment, the production and consumption data generated during the operation of the equipment includes:

[0060] Equipment energy consumption, equipment capacity (product quantity, yield rate), equipment temperature, and equipment failure rate.

[0061] The control algorithm unit 2 processes the input data based on the production and consumption data collected by the data collection unit 1 and generates corresponding control instructions through the PID control algorithm;

[0062] In this embodiment, the PID control algorithm adjusts the control quantity through three parts: proportional, integral and differential. The proportional term directly responds to the error and provides a fast response; the integral term eliminates the steady-state error so that the system eventually reaches the set value; the differential term predicts the changing trend of the error, adjusts the control quantity in advance, and reduces overshoot. The combination of the three can largely ensure the accuracy and stability of the system. The PID control algorithm can achieve real-time control because it only needs the error information at the current moment to calculate the control signal. This feature makes it very suitable for applications that require a fast response; the PID control algorithm processes the input data and generates corresponding control instructions, including the following steps:

[0063] S1.1. Pre-process the collected production and consumption data, including data cleaning, formatting, and outlier detection, to ensure data quality;

[0064] S1.2. Use the pre-processed production and consumption data to monitor the current state of the system, and analyze the production and consumption data to determine the deviation between the current state and the expected target;

[0065] S1.3, using the PID control algorithm to calculate the error between the current measured value and the set value, where the measured value represents the actual measured value of the production and consumption data, and the set value represents the target value that the production and consumption data is expected to reach;

[0066] S1.4. Improve the control quantity calculated by the PID control algorithm and convert it into specific control instructions. The control instructions include reducing the workload of the equipment, adjusting the speed of the production line, and introducing the equipment temperature and failure rate into the PID control algorithm to improve the accuracy of the control instructions;

[0067] Among them, the PID control algorithm is specifically:

[0068] ;

[0069] Furthermore, by introducing the equipment temperature as a control variable, the PID controller can better adapt to the impact of temperature changes on equipment performance, and can adjust the control output more accurately to maintain ideal temperature conditions and ensure the stability of the production process and the consistency of product quality; using the failure rate as one of the control variables can make the control system more intelligent. By monitoring the failure rate of the equipment and incorporating it into the PID control algorithm, the system can take preventive measures before the failure occurs, such as adjusting operating parameters to reduce the burden on the equipment, or triggering maintenance plans in advance. This method helps to extend the life of the equipment, reduce unplanned downtime, and improve overall production efficiency; Traditional PID control usually only controls a single variable (such as temperature, pressure, etc.); however, in modern complex production environments, multiple factors (such as temperature, load, wear, etc.) will work together on equipment performance. By introducing more relevant variables (such as equipment temperature and failure rate) in the PID algorithm, a more comprehensive control strategy can be achieved, thereby better balancing the relationship between different control objectives, including the balance between energy consumption and production capacity; introducing equipment temperature and failure rate into the PID control algorithm, specifically:

[0070] ;

[0071] in, Indicates the control instructions applied to the device to be controlled; Indicates the control instruction applied to the device to be controlled after the device temperature and failure rate are introduced; Indicates time; Represents the time from the initial moment to the current moment Any time within the time interval; Represents the time from the initial moment to the current moment The error at any time within the time interval; Represents the proportional gain, which is used to directly respond to the current error size; Represents the integral gain, which is used to accumulate past errors; Represents the differential gain, which is used to predict the changing trend of the error; Indicates the error between the actual frequency and the target frequency; Indicates the temperature coefficient, that is, when the device temperature deviates from the ideal temperature by 1 degree, the control output the extent of the impact; Indicates the current temperature of the device; Indicates ideal temperature; It represents the failure rate coefficient, that is, the effect of each unit increase in the failure rate on the control output. the extent of the impact; The failure rate of the equipment over time changes, , Indicates at time The number of times the internal equipment fails; is the length of the time window.

[0072] The optimization decision unit 3 uses a simulated annealing algorithm to adjust the control instruction received from the control algorithm unit 2;

[0073] In this embodiment, the optimization decision unit 3 adjusts the control instruction, including the following steps:

[0074] S2.1, initially set PID control parameters and define the objective function;

[0075] Among them, PID control parameters include proportional gain, integral gain, differential gain, temperature coefficient and failure rate coefficient, and the objective function includes maximizing production capacity and minimizing energy consumption. A weighted combination of equipment aging rate and failure rate is introduced into the objective function.

[0076] The specific objective function is:

[0077] ;

[0078] Furthermore, by including equipment aging rate and failure rate in the objective function, it can be ensured that the optimization is not just about maximizing / minimizing cost or production capacity, but takes into account the full life cycle management of the equipment. As a result, the system not only pursues short-term production efficiency, but also pays attention to the long-term health of the equipment, thereby achieving a more comprehensive performance optimization; incorporating equipment aging rate and failure rate into the optimization target helps to detect the trend of equipment performance degradation early and take preventive maintenance measures. This can avoid production interruptions caused by sudden failures and reduce unplanned downtime caused by equipment maintenance, thereby improving the overall availability and reliability of the production system; considering the equipment aging rate, the system can adjust the control parameters more intelligently to slow down the aging process of the equipment. By properly arranging the workload, the wear caused by excessive use of the equipment can be reduced, the service life of the equipment can be extended, and the cost of replacing new equipment can be reduced; the weighted combination of the aging rate and failure rate of the equipment introduced into the objective function is specifically as follows:

[0079] ;

[0080] in, represents the objective function; represents the objective function after introducing the weighted combination of equipment aging rate and failure rate; represents the trade-off factor for balancing capacity; represents the trade-off factor for balancing energy consumption; Represents a set of PID control parameters; Indicates Capacity at the moment; represents the number of time steps; Indicates PID control parameters at each moment resulting in energy consumption; Indicates the weight coefficient of the equipment aging rate. The larger the value of , the greater the proportion of the equipment aging rate in the optimization process; Indicates the degree of aging of the equipment over a certain period of time; Indicates the weight coefficient of equipment failure rate. The larger the value of , the greater the proportion of equipment failure rate in the optimization process; Indicates the frequency of equipment failures within a certain period of time. The failure frequency is defined as the number of equipment failures within a certain time window divided by the length of the time window. Indicated in The actual measured value of the monitored process at any given moment; Indicated in The expected process value at a given moment; Represents a time index.

[0081] Furthermore, ; Indicates The actual energy consumption of the equipment at a point in time;

[0082] ; Indicates The actual capacity of the equipment at a point in time;

[0083] ; In the formula, is the aging rate based on time; is the aging rate based on usage; It is The weights of the used parameters; It is The intensity of use of each usage parameter; represents the number of time steps; and Represents an index variable; is the coefficient of influence of maintenance on aging; It is The weight of the maintenance parameters; It is The maintenance degree of each maintenance parameter;

[0084] ; In the formula, Indicates at time The number of times the internal equipment fails; is the length of the time window, for example 24 hours.

[0085] S2.2, using simulated annealing algorithm to adjust PID control parameters to minimize the objective function;

[0086] Among them, the simulated annealing algorithm is a heuristic search method that imitates the annealing phenomenon during the cooling process of metals. During the optimization process, the algorithm allows acceptance of results that are worse than the current solution under certain conditions, which helps to jump out of the local optimal solution and find the global optimal solution. This is particularly important for the optimization of PID parameters, because the optimization space of PID parameters may be multidimensional and complex, with multiple local minima; the simulated annealing algorithm allows the "temperature" to be gradually reduced during the optimization process, which is equivalent to gradually reducing the probability of accepting a worse solution. Such a mechanism enables the algorithm to explore the solution space extensively in the early stages, and to focus more on improving the current best solution in the later stages, thereby achieving more flexible parameter adjustment; the simulated annealing algorithm allows the "temperature" to be gradually reduced during the optimization process, which is equivalent to gradually reducing the probability of accepting a worse solution, thereby achieving more flexible parameter adjustment; the simulated annealing algorithm allows the "temperature" to be gradually reduced during the optimization process, which is equivalent to gradually reducing the probability of accepting a worse solution, thereby achieving more flexible parameter adjustment; the simulated annealing algorithm allows the "temperature" to be gradually reduced during the optimization process, which is equivalent to gradually reducing the probability of accepting a worse solution, thereby achieving more flexible parameter adjustment; the adjustment of PID control parameters using the simulated annealing algorithm includes the following steps:

[0087] S2.21, generate a new PID control parameter group from the vicinity of the current PID control parameters, and calculate the objective function value of the new PID control parameter group;

[0088] S2.22, calculate the objective function value under the current PID control parameters and the objective function value under the new PID control parameters, and compare them;

[0089] S2.23. If the objective function value under the new PID control parameters is less than the objective function value under the current PID control parameters, the objective function value under the new PID control parameters is accepted;

[0090] If the objective function value under the new PID control parameters is greater than the objective function value under the current PID control parameters, then the probability Accept the objective function value under the new PID control parameters, where: , It represents the difference between the objective function value under the new PID control parameters and the objective function value under the current PID control parameters. Indicates the current temperature parameter;

[0091] S2.3. During the optimization process, continuously monitor changes in equipment temperature and failure rate, and use them as the basis for adjusting the control strategy.

[0092] The adaptive control unit 4 automatically adjusts the control strategy through the K-means clustering algorithm;

[0093] In this embodiment, the K-means clustering algorithm can automatically identify data sets with similar characteristics based on historical data. This means that by clustering the data collected during the operation of the equipment (such as energy consumption, temperature, failure rate, etc.), different operating modes or environmental conditions can be automatically identified; the K-means algorithm can dynamically identify the current operating status and adjust the control strategy based on these states. This means that the system can automatically adapt to different operating conditions without human intervention. For example, when it is detected that the device is in a high-energy consumption but stable mode, the system can automatically switch to PID control parameters suitable for this mode to ensure the best control effect in any case; automatically adjusting the control strategy through the K-means clustering algorithm includes the following steps:

[0094] S3.1. Select characteristic data related to the control strategy, the characteristic data including equipment energy consumption, equipment temperature and equipment failure rate;

[0095] S3.2, based on the feature data, the silhouette coefficient method is used to determine the optimal number of clusters K. After determining the optimal number of clusters K, the feature data is clustered using the K-means clustering algorithm to group similar data points together to obtain K different clusters;

[0096] Among them, the silhouette coefficient is an indicator used to measure the quality of clustering. It provides each data point with a score between -1 and 1. This score reflects the similarity of the data point to its cluster and the distance from other clusters. A high silhouette coefficient indicates that the data point is very similar to other members of its cluster and is far away from data points of other clusters. Therefore, by calculating the silhouette coefficient, the effect of clustering can be quantitatively evaluated; the silhouette coefficient provides an intuitive way to evaluate the quality of clustering. A higher average silhouette coefficient means that the data points are tightly clustered in their own clusters and are well separated from other clusters; using the silhouette coefficient method to determine the optimal number of clusters K includes the following steps:

[0097] S3.21. Select a series of different K values. For each K value, use the K-means algorithm to cluster. For each data point , calculate its silhouette coefficient , , Represents each data point The average distance to all other data points in its cluster, Represents each data point The average distance to all data points in the nearest cluster except its own cluster;

[0098] S3.22, calculate the average value S of the silhouette coefficients of all data points;

[0099] S3.23. For each K value, record its corresponding average silhouette coefficient S, and select the K value that maximizes the average silhouette coefficient S as the optimal number of clusters;

[0100] Furthermore, the K-means algorithm is specifically:

[0101] ;

[0102] in, represents the within-cluster sum of squares, Indicates the number of clusters; Indicates All data points of a cluster; Indicates The centroid of each cluster; represents a data point in a cluster; Represents the index of the cluster;

[0103] S3.3. Analyze the characteristics of each cluster, understand the environmental conditions represented by each cluster, analyze the common characteristics of the data points in each cluster, such as high energy consumption, low failure rate, high temperature, etc., and identify that one cluster may represent a high energy consumption but stable operation mode, and another cluster may represent a low energy consumption but potential failure mode;

[0104] S3.4. Design corresponding PID control parameters for each environmental condition. Adjust PID parameters according to the characteristics of each cluster. For clusters with high energy consumption but stable, increase the to respond faster to deviations, while for low-energy but potentially faulty clusters, it may be necessary to increase To reduce long-term bias;

[0105] S3.5, associating each cluster with a PID control parameter set, if the system detects that it is currently in an environmental condition corresponding to a cluster, the PID control parameter set of the cluster is applied, if the system detects that it is currently in a high energy consumption but stable environmental condition, the PID control parameter set of the high energy consumption cluster is applied;

[0106] S3.6. Regularly re-evaluate feature data and adjust control strategies based on the latest clustering results.

[0107] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only preferred examples of the present invention, and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. An intelligent PLC data analysis and optimization control system, characterized in that: include: A data collection unit (1), the data collection unit (1) being used to collect production and consumption data generated during operation of the equipment; A control algorithm unit (2), wherein the control algorithm unit (2) processes the input data based on the production and consumption data collected by the data collection unit (1) through a PID control algorithm and generates corresponding control instructions, and introduces the equipment temperature and failure rate into the PID control algorithm to improve the accuracy of the control instructions; An optimization decision unit (3), wherein the optimization decision unit (3) uses a simulated annealing algorithm to adjust the control instruction received from the control algorithm unit (2); An adaptive control unit (4), wherein the adaptive control unit (4) automatically adjusts the control strategy through a K-means clustering algorithm; The control algorithm unit (2) processes the input data through the PID control algorithm and generates corresponding control instructions, including the following steps: S1.

1. Preprocess the collected production and consumption data; S1.

2. Use the pre-processed production and consumption data to monitor the current state of the system, and analyze the production and consumption data to determine the deviation between the current state and the expected target; S1.3, using the PID control algorithm to calculate the error between the current measured value and the set value, where the measured value represents the actual measured value of the production and consumption data, and the set value represents the target value that the production and consumption data is expected to reach; S1.

4. Improve the control quantity calculated by the PID control algorithm and convert it into specific control instructions. The control instructions include reducing the workload of the equipment, adjusting the speed of the production line, and introducing the equipment temperature and failure rate into the PID control algorithm to improve the accuracy of the control instructions; In S1.3, the PID control algorithm is specifically: ； The device temperature and failure rate are introduced into the PID control algorithm, specifically: ； in, Indicates the control instructions applied to the device to be controlled; Indicates the control instruction applied to the device to be controlled after the device temperature and failure rate are introduced; Indicates time; Represents the time from the initial moment to the current moment Any time within the time interval; Represents the time from the initial moment to the current moment The error at any time within the time interval; Represents the proportional gain, which is used to directly respond to the current error size; Represents the integral gain, which is used to accumulate past errors; Represents the differential gain, which is used to predict the changing trend of the error; Indicates the error between the actual frequency and the target frequency; represents the temperature coefficient; Indicates the current temperature of the device; Indicates ideal temperature; represents the failure rate coefficient; The failure rate of the equipment over time changes; The optimization decision unit (3) adjusts the control instruction, including the following steps: S2.1, initially set PID control parameters and define the objective function; Among them, PID control parameters include proportional gain, integral gain, differential gain, temperature coefficient and failure rate coefficient, and the objective function includes maximizing production capacity and minimizing energy consumption. A weighted combination of equipment aging rate and failure rate is introduced into the objective function. S2.2, using simulated annealing algorithm to adjust PID control parameters to minimize the objective function; S2.

3. During the optimization process, continuously monitor the changes in equipment temperature and failure rate, and use them as the basis for adjusting the control strategy; In S2.1, the objective function is specifically: ； The weighted combination of equipment aging rate and failure rate introduced into the objective function is as follows: ； in, represents the objective function; represents the objective function after introducing the weighted combination of equipment aging rate and failure rate; represents the trade-off factor for balancing capacity; represents the trade-off factor for balancing energy consumption; Represents a set of PID control parameters; Indicates Capacity at the moment; represents the number of time steps; Indicates PID control parameters at each moment resulting in energy consumption; The weight coefficient representing the equipment aging rate; Indicates the degree of aging of the equipment over a certain period of time; The weight coefficient representing the equipment failure rate; Indicates the frequency of equipment failures within a certain period of time; Indicated in The actual measured value of the monitored process at any given moment; Indicated in The expected process value at the moment; Represents a time index; In S2.2, the PID control parameters are adjusted using a simulated annealing algorithm, including the following steps: S2.21, generate a new PID control parameter group from the vicinity of the current PID control parameters, and calculate the objective function value of the new PID control parameter group; S2.22, calculate the objective function value under the current PID control parameters and the objective function value under the new PID control parameters, and compare them; S2.

23. If the objective function value under the new PID control parameters is less than the objective function value under the current PID control parameters, the objective function value under the new PID control parameters is accepted; If the objective function value under the new PID control parameters is greater than the objective function value under the current PID control parameters, then the probability Accept the objective function value under the new PID control parameters; The adaptive control unit (4) automatically adjusts the control strategy through a K-means clustering algorithm, comprising the following steps: S3.

1. Select characteristic data related to the control strategy, the characteristic data including equipment energy consumption, equipment temperature and equipment failure rate; S3.2, based on the feature data, the silhouette coefficient method is used to determine the optimal number of clusters K. After determining the optimal number of clusters K, the feature data is clustered using the K-means clustering algorithm to group similar data points together to obtain K different clusters; S3.

3. Analyze the characteristics of each cluster and understand the environmental conditions represented by each cluster; S3.

4. Design corresponding PID control parameters for each environmental condition; S3.5, associating each cluster with a PID control parameter set, and if the system detects that it is currently in an environmental condition corresponding to a cluster, the PID control parameter set of the cluster is applied; S3.

6. Regularly re-evaluate feature data and adjust control strategies based on the latest clustering results; In S3.2, the optimal number of clusters K is determined using the silhouette coefficient method, including the following steps: S3.

21. Select a series of different K values. For each K value, use the K-means algorithm to cluster. For each data point , calculate its silhouette coefficient ; S3.22, calculate the average value of the silhouette coefficients of all data points, denoted as the average silhouette coefficient S; S3.

23. For each K value, record its corresponding average silhouette coefficient S, and select the K value that maximizes the average silhouette coefficient S as the optimal number of clusters; In S3.2, the K-means algorithm is specifically: ； in, represents the within-cluster sum of squares, Indicates the number of clusters; Indicates All data points of a cluster; Indicates The centroid of each cluster; represents a data point in a cluster; Represents the index of the cluster.

2. The intelligent PLC data analysis and optimization control system according to claim 1 is characterized in that: The production and consumption data generated during the operation of the equipment and collected by the data collection unit (1) include: Equipment energy consumption, equipment capacity, equipment temperature and equipment failure rate.

Images