Internet of Things control method and system for digital factory

Abstract

The present invention relates to the field of factory control technology, and discloses an Internet of Things control method and system for a digital chemical plant. The method includes obtaining each resource consumption sequence of the chemical plant during the production process, determining the stationarity results of each resource consumption sequence through autocorrelation analysis, thereby calculating the degree of fluctuation of each resource consumption sequence, obtaining the correlation degree value between each resource consumption sequence, and determining the set of related resource consumption sequences between the resource consumption sequences by comparing with the difference between the maximum correlation degrees, and then obtaining each resource consumption sequence that may fail and calculating the stable decline data of each resource consumption sequence that may fail, and finally using a genetic algorithm to optimize the resource allocation of the chemical plant. This method has the following effects: it can timely determine the core factors of problems in the Internet of Things control of the chemical plant and achieve optimal resource allocation.

Description

Technical Field

[0001] The present invention relates to the field of factory control technology, and in particular to an Internet of Things control method and system for a digital factory. Background Art

[0002] Currently, common control methods within IoT include: rule-based control, which uses predefined rules and logic to control device operation; feedback-based control, which uses sensor data to adjust device operation in real time; and model-based control, which uses mathematical models to predict optimal control strategies for devices. Key application areas for IoT control include smart homes, smart manufacturing, smart grids, smart transportation, and smart cities. In these areas, IoT control enables remote monitoring, automated control, and fault detection of equipment, improving system efficiency and reliability. For chemical plants, IoT control can effectively monitor and manage various resources in the production process, enabling real-time monitoring and control. This allows chemical plants to optimize resource utilization, increase production efficiency, and better maintain the stability of equipment and systems.

[0003] In existing technologies, most studies focus on setting a single threshold for target parameters, without considering adaptive parameter threshold settings. This makes it difficult to ensure production stability. Furthermore, the core factors influencing production cannot be accurately identified during the production process, limiting resource allocation.

[0004] The existing technology has the problem of being unable to promptly identify the core factors of problems arising in the Internet of Things control of chemical plants, resulting in the inability to optimize resource allocation. Summary of the Invention

[0005] The present invention provides an Internet of Things control method and system for a digital chemical plant, so as to timely determine the core factors of problems arising in the Internet of Things control of a chemical plant and achieve optimal allocation of resources.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides an IoT control method for a digital factory, comprising:

[0007] Obtain the resource consumption sequence of each chemical plant during the production process;

[0008] Determining the stationarity results of each resource consumption sequence through autocorrelation analysis according to each resource consumption sequence;

[0009] Calculating the fluctuation degree of each resource consumption sequence according to the stationarity results of each resource consumption sequence to obtain the correlation degree values ​​between each resource consumption sequence;

[0010] Determining a set of correlated resource consumption sequences between the resource consumption sequences by comparing the correlation values ​​between the resource consumption sequences with the difference between the maximum correlation values;

[0011] According to the set of related resource consumption sequences, obtaining each resource consumption sequence that may fail and calculating stable decrease degree data of each resource consumption sequence that may fail;

[0012] According to the stable decline degree data, a genetic algorithm is used to optimize resource allocation of the chemical plant.

[0013] In an optional implementation, determining the stationarity results of the resource consumption sequences by autocorrelation analysis according to the resource consumption sequences includes:

[0014] Obtaining the initial mean value of each resource consumption sequence;

[0015] Comparing the initial mean value with the final mean values ​​of the resource consumption sequences at all different time points within each resource consumption sequence to obtain difference values ​​of each resource consumption sequence;

[0016] According to the difference values ​​of the various resource consumption sequences, the inverse of the sum of all the difference values ​​is used as the stationarity result of the various resource consumption sequences.

[0017] In an optional embodiment, calculating the fluctuation degree of each resource consumption sequence based on the stationarity results of each resource consumption sequence to obtain the correlation degree values ​​between the resource consumption sequences includes:

[0018] According to the stationarity results of the resource consumption sequences, the fluctuation degree of the resource consumption sequences is calculated by the following formula:

[0019] ;

[0020] in, Indicates the degree of fluctuation of resource consumption sequence, represents the mean of the resource consumption series, Represents the time index of each data in the resource consumption sequence, Indicates that the resource consumption sequence is The consumption of time, The index identifier of the resource consumption sequence, Indicates that the resource consumption sequence is and The relevance of the data at the moment The larger the value, the higher the resource consumption sequence. and The greater the correlation of the data at each moment, σ represents the standard deviation;

[0021] dividing a plurality of resource consumption sequences with similar fluctuation degrees of the resource consumption sequences into a new resource consumption sequence group;

[0022] Aggregation is performed based on correlation coefficient values ​​between any two resource consumption sequences in the new resource consumption sequence group to obtain correlation degree values ​​between the resource consumption sequences.

[0023] In an optional embodiment, determining a set of correlated resource consumption sequences between the resource consumption sequences by comparing the correlation values ​​between the resource consumption sequences with a difference between the maximum correlation values ​​includes:

[0024] Obtaining a maximum correlation value among the correlations between the resource consumption sequences;

[0025] Subtracting the correlation values ​​between the resource consumption sequences from the maximum correlation value to obtain a correlation difference value;

[0026] According to the correlation degree difference, a set of related resource consumption sequences between the resource consumption sequences is determined by the following method:

[0027] When the correlation difference is greater than β, all resource consumption sequences are determined to be the same resource consumption sequence set;

[0028] When the correlation degree difference is less than or equal to β, it is determined that the resource consumption sequence does not belong to any resource consumption sequence set;

[0029] Among them, β is the stable correlation value completed in advance.

[0030] In an optional implementation, obtaining each resource consumption sequence that may fail and calculating stable decrease degree data of each resource consumption sequence that may fail according to the set of related resource consumption sequences includes:

[0031] Obtaining a mutation degree of a resource consumption sequence in the resource consumption sequence set;

[0032] Perform anomaly detection based on the mutation degree to generate resource consumption sequences that may cause failures;

[0033] Predicting consumption parameters based on the resource consumption sequences that may cause failures;

[0034] According to the predicted consumption parameters, the stable decrease degree data of each of the resource consumption sequences that may fail is calculated using the following formula:

[0035] ;

[0036] in, is the stable descent data, It is The number of data points in a resource consumption series, Indicates the A resource consumption sequence at time point and The difference between .

[0037] In an optional embodiment, the optimizing resource allocation of the chemical plant using a genetic algorithm based on the stable decrease degree data includes:

[0038] comparing the stable decrease degree data with the determined stable decrease threshold value to determine the resource consumption units that may fail corresponding to all resource consumption sequences that may fail;

[0039] When the total production consumption of the resource-consuming units that may fail and other resource-consuming units that are unlikely to fail is the lowest, the genetic algorithm is used to optimize the allocation of resources in the chemical plant.

[0040] In an optional implementation, obtaining the mutation degree of the resource consumption sequence in the resource consumption sequence set includes:

[0041] According to the consumption trend and the actual consumption trend change slope, normalizing the actual consumption trend change slope to obtain a mutation degree of the resource consumption sequence in the resource consumption sequence set;

[0042] The standardization includes:

[0043] ;

[0044] in, Indicates the mutation degree of the resource consumption sequence in the resource consumption sequence set, The proportional coefficient representing the degree of mutation is used to adjust the sensitivity of the degree of mutation. represents the actual consumption trend change slope of the resource consumption sequence in the resource consumption sequence set, Indicates the standard consumption trend change slope of the resource consumption sequence in the resource consumption sequence set.

[0045] In a second aspect, the present invention provides an Internet of Things control system for a digital factory, comprising:

[0046] The data acquisition module is used to obtain the resource consumption sequence of each chemical plant during the production process;

[0047] a stationarity determination module, configured to determine the stationarity results of each resource consumption sequence through autocorrelation analysis based on each resource consumption sequence;

[0048] a fluctuation degree calculation module, configured to calculate the fluctuation degree of each resource consumption sequence according to the stationarity results of each resource consumption sequence, and obtain the correlation degree values ​​between the resource consumption sequences;

[0049] a resource consumption sequence set determining module, configured to determine a set of correlated resource consumption sequences between the resource consumption sequences by comparing the correlation values ​​between the resource consumption sequences with the difference between the maximum correlation values;

[0050] a stability descent degree calculation module, configured to obtain, based on the set of related resource consumption sequences, each resource consumption sequence that may have a failure and calculate stability descent degree data of each resource consumption sequence that may have a failure;

[0051] The optimization allocation module is used to optimize the resource allocation of the chemical plant by using a genetic algorithm according to the stable decline data.

[0052] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the Internet of Things control method for a digital factory described in any one of the above.

[0053] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned Internet of Things control methods for digital factories.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention discloses an Internet of Things control method for a digital chemical plant, the method comprising obtaining each resource consumption sequence of the chemical plant during the production process, determining the stationarity results of each resource consumption sequence through autocorrelation analysis, thereby calculating the degree of fluctuation of each resource consumption sequence, obtaining the correlation degree values ​​between the resource consumption sequences, and determining the set of related resource consumption sequences between the resource consumption sequences by comparing with the difference between the maximum correlation degrees, thereby obtaining each resource consumption sequence that may fail and calculating the stable decline data of each resource consumption sequence that may fail, and finally using a genetic algorithm to optimize the resource allocation of the chemical plant. This method has the following effects: it can promptly determine the core factors of problems in the Internet of Things control of the chemical plant and achieve optimal resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of the IoT control method for a digital factory provided by the first embodiment of the present invention;

[0057] Figure 2 This is a schematic diagram of the structure of the Internet of Things control system of the digital factory provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0059] Currently, common control methods within IoT include: rule-based control, which uses predefined rules and logic to control device operation; feedback-based control, which uses sensor data to adjust device operation in real time; and model-based control, which uses mathematical models to predict optimal control strategies for devices. Key application areas for IoT control include smart homes, smart manufacturing, smart grids, smart transportation, and smart cities. In these areas, IoT control enables remote monitoring, automated control, and fault detection of equipment, improving system efficiency and reliability. For chemical plants, IoT control can effectively monitor and manage various resources in the production process, enabling real-time monitoring and control. This allows chemical plants to optimize resource utilization, increase production efficiency, and better maintain the stability of equipment and systems.

[0060] In existing technologies, most studies focus on setting a single threshold for target parameters, without considering adaptive parameter threshold settings. This makes it difficult to ensure production stability. Furthermore, the core factors causing problems in chemical plant IoT control cannot be identified in a timely manner, resulting in an inability to optimize resource allocation.

[0061] To solve the above problems, refer to Figure 1 The first embodiment of the present invention provides an Internet of Things control method for a digital factory, comprising the following steps:

[0062] S11, obtaining the resource consumption sequence of each chemical plant during the production process;

[0063] S12, determining the stationarity results of each resource consumption sequence through autocorrelation analysis according to each resource consumption sequence;

[0064] S13, calculating the fluctuation degree of each resource consumption sequence according to the stationarity results of each resource consumption sequence, and obtaining the correlation degree values ​​between each resource consumption sequence;

[0065] S14, determining a set of correlated resource consumption sequences between the resource consumption sequences by comparing the correlation values ​​between the resource consumption sequences with the difference between the maximum correlation values;

[0066] S15, obtaining, based on the set of related resource consumption sequences, each resource consumption sequence that may fail and calculating stable decrease degree data of each resource consumption sequence that may fail;

[0067] S16, optimizing resource allocation of the chemical plant using a genetic algorithm based on the stable decrease degree data.

[0068] The present invention discloses an Internet of Things control method for a digital chemical plant, the method comprising obtaining each resource consumption sequence of the chemical plant during the production process, determining the stationarity results of each resource consumption sequence through autocorrelation analysis, thereby calculating the degree of fluctuation of each resource consumption sequence, obtaining the correlation degree values ​​between the resource consumption sequences, and determining the set of related resource consumption sequences between the resource consumption sequences by comparing with the difference between the maximum correlation degrees, thereby obtaining each resource consumption sequence that may fail and calculating the stable decline data of each resource consumption sequence that may fail, and finally using a genetic algorithm to optimize the resource allocation of the chemical plant. This method has the following effects: it can promptly determine the core factors of problems in the Internet of Things control of the chemical plant and achieve optimal resource allocation.

[0069] In step S11, each resource consumption sequence of the chemical plant during the production process is obtained.

[0070] It should be noted that resource consumption sequences generally refer to the changes over time in the use of various resources, such as raw materials, energy, and water, by chemical plants during the production process. Resource consumption sequences are generally composed of raw material consumption, energy consumption, water consumption, waste generation, and equipment usage. Resource consumption sequences include energy consumption data, raw material consumption data, and production process data; each resource consumption status sequence corresponding to the resource consumption data includes resource consumption indicator data corresponding to multiple different time points; and multiple historical resource consumption status sequences include historical resource consumption indicator data corresponding to multiple different time points. The use of various resources can usually be monitored and recorded using automated data collection systems and manual recording methods.

[0071] In step S12, the stationarity results of the resource consumption sequences are determined through autocorrelation analysis based on the resource consumption sequences.

[0072] Obtaining the initial mean value of each resource consumption sequence;

[0073] Comparing the initial mean value with the final mean values ​​of the resource consumption sequences at all different time points within each resource consumption sequence to obtain difference values ​​of each resource consumption sequence;

[0074] According to the difference values ​​of the various resource consumption sequences, the inverse of the sum of all the difference values ​​is used as the stationarity result of the various resource consumption sequences.

[0075] It should be noted that autocorrelation analysis is a statistical method that can discover the periodic patterns of resource consumption sequences. Autocorrelation analysis can also reveal the trend changes of resource consumption sequences over time, helping managers understand the changing trends of resource utilization efficiency and take corresponding measures to optimize them.

[0076] To obtain the initial mean of each resource consumption sequence, it is necessary to first collect the resource consumption sequences within a certain time range and remove some outliers. For each resource consumption sequence, the initial mean of the resource consumption sequence within the time range can be calculated using Excel or Python tools.

[0077] The initial mean is compared with the final mean of the resource consumption sequences at all different time points within each resource consumption sequence to obtain a difference value for each resource consumption sequence. For each time point, the mean of the resource consumption sequence at that time point is compared with the initial mean and the difference value is calculated.

[0078] Stationarity of a resource consumption series refers to the fact that its temporal characteristics do not change over time. In other words, the series' statistical properties, such as mean, variance, and autocorrelation, remain constant over time. In resource consumption analysis, stationarity implies that the long-term mean and volatility of resource consumption are stable, which aids long-term planning and resource allocation.

[0079] In step S13, the fluctuation degree of each resource consumption sequence is calculated according to the stationarity result of each resource consumption sequence, and the correlation degree value between each resource consumption sequence is obtained.

[0080] According to the stationarity results of the resource consumption sequences, the fluctuation degree of the resource consumption sequences is calculated by the following formula:

[0081] ;

[0082] in, Indicates the degree of fluctuation of resource consumption sequence, represents the mean of the resource consumption series, Represents the time index of each data in the resource consumption sequence, Indicates that the resource consumption sequence is The consumption of time, The index identifier of the resource consumption sequence, Indicates that the resource consumption sequence is and The relevance of the data at the moment The larger the value, the higher the resource consumption sequence. and The greater the correlation of the data at each moment, σ represents the standard deviation;

[0083] dividing a plurality of resource consumption sequences with similar fluctuation degrees of the resource consumption sequences into a new resource consumption sequence group;

[0084] Aggregation is performed based on correlation coefficient values ​​between any two resource consumption sequences in the new resource consumption sequence group to obtain correlation degree values ​​between the resource consumption sequences.

[0085] It's important to note that the temporal volatility of a resource consumption series generally refers to the degree of dispersion of the series values ​​around its mean. This volatility can be measured using variance, standard deviation, coefficient of variation, range, and interquartile range. The volatility of a resource consumption series reflects the stability and predictability of resource consumption over time. Understanding the volatility of a resource consumption series can help companies with resource planning and inventory management, helping to avoid resource shortages or surpluses.

[0086] Mean of resource consumption series Calculated by the following formula:

[0087] ;

[0088] in, Indicates that the resource consumption sequence is The consumption of time, is the total number of data points in the resource consumption series.

[0089] Standard deviation It is an important concept in statistics. It is used to measure the degree of dispersion of a set of data, that is, the degree of deviation between the data values ​​and their average value (mean). Specifically, the standard deviation is defined as the square root of the arithmetic mean (variance) of the squares of the deviations of all data values ​​from their mean. The standard deviation can be calculated by the following steps: :

[0090] S131. Calculate the average value (mean) of all data;

[0091] S132. For each data value, calculate its difference (deviation) from the mean and square the difference;

[0092] S133. Calculate the average of these squared differences, i.e., the variance;

[0093] S134. Calculate the square root of the variance to get the standard deviation .

[0094] Standard deviation Quantifies the variability or dispersion of the data. A smaller standard deviation means that the data points are more closely distributed around the mean, while a larger standard deviation means that the data points are more dispersed around the mean. In a normal distribution, the standard deviation It also depends on the percentage distribution of the data. For example, about 68% of the data falls within one standard deviation of the mean. Within the range, about 95% of the data falls within two standard deviations Within the range, about 99.7% of the data falls within three standard deviations Inside.

[0095] The correlation coefficient values ​​between each pair of resource consumption sequences in the new resource consumption sequence group are aggregated to obtain the correlation values ​​between the resource consumption sequences. First, for each pair of resource consumption sequences in the new resource consumption sequence group, the characteristics and distribution of their data are observed, and the correlation coefficient between them is calculated using the Pearson correlation coefficient, Spearman rank correlation coefficient, or Kendall rank correlation coefficient. For all resource consumption sequences in the new resource consumption sequence group, the correlation coefficients between them are aggregated using the average, median, or weighted average to obtain the correlation values ​​between the resource consumption sequences.

[0096] In step S14, a set of correlated resource consumption sequences between the resource consumption sequences is determined by comparing the correlation values ​​between the resource consumption sequences with the difference between the maximum correlation values.

[0097] Obtaining a maximum correlation value among the correlations between the resource consumption sequences;

[0098] Subtracting the correlation values ​​between the resource consumption sequences from the maximum correlation value to obtain a correlation difference value;

[0099] According to the correlation degree difference, a set of related resource consumption sequences between the resource consumption sequences is determined by the following method:

[0100] When the correlation difference is greater than β, all resource consumption sequences are determined to be the same resource consumption sequence set;

[0101] When the correlation degree difference is less than or equal to β, it is determined that the resource consumption sequence does not belong to any resource consumption sequence set;

[0102] Among them, β is the stable correlation value completed in advance.

[0103] It should be noted that the maximum correlation value among the correlations between the resource consumption sequences is obtained by observing the correlation values ​​of all resource consumption sequences and selecting the one with the largest correlation value as the maximum correlation value.

[0104] Stable correlation refers to the relatively constant correlation between two or more variables over a certain timeframe. This correlation does not fluctuate significantly over time. In resource consumption series analysis, stable correlation typically refers to the long-term stability of correlations between different resource consumption indicators. This provides insights into the stable correlations between different resource consumption series and can help companies optimize resource allocation. β is a pre-trained stable correlation value, which can be 0.8, 0.85, or 0.9.

[0105] In step S15, each resource consumption sequence that may fail is obtained according to the set of related resource consumption sequences, and stable decrease degree data of each resource consumption sequence that may fail is calculated.

[0106] Obtaining a mutation degree of a resource consumption sequence in the resource consumption sequence set;

[0107] Perform anomaly detection based on the mutation degree to generate resource consumption sequences that may cause failures;

[0108] Predicting consumption parameters based on the resource consumption sequences that may cause failures;

[0109] According to the predicted consumption parameters, the stable decrease degree data of each of the resource consumption sequences that may fail is calculated using the following formula:

[0110] ;

[0111] in, is the stable descent data, It is The number of data points in a resource consumption series, Indicates the A resource consumption sequence at time point and The difference between .

[0112] It's important to note that mutation level describes the degree or magnitude of a dramatic change in a system, process, or variable at a specific point in time or over a specific period of time, often significantly different from the system's normal behavior or historical trends. The mutation level can be used to identify sudden changes in resource consumption and inefficiencies in the production process, allowing for operational optimization and improved resource utilization. It can also serve as an early indicator of equipment failure or performance degradation, helping to predict whether a device is experiencing a malfunction.

[0113] Anomaly detection is the process of identifying points in a data set where the degree of change does not conform to expected patterns or deviates from normal behavior. In the context of resource consumption sequences, anomaly detection can help identify sequences that may indicate failures or inefficiencies. For example, anomaly detection methods can employ statistical methods such as Z-scores and IQR scores; machine learning methods such as isolation forests, local outlier factors (LOFs), and autoencoders can also be employed, although this disclosure is not limited to these methods.

[0114] Stable decline describes the degree to which a variable or indicator steadily decreases over time. It encompasses the following: trend stability, which refers to an indicator exhibiting a steady downward trend over a period of time, rather than fluctuating or unstable changes; rate of decline, which refers to a relatively stable rate or magnitude of decline, without sharp increases or decreases; and predictability, which generally indicates that future changes are predictable. In resource management, stable decline can mean reduced resource consumption, contributing to sustainable resource utilization.

[0115] Furthermore, obtaining the mutation degree of the resource consumption sequence in the resource consumption sequence set includes:

[0116] Obtaining the consumption trend and actual consumption trend change slope of the resource consumption sequence in the relevant resource consumption sequence set;

[0117] According to the consumption trend and the actual consumption trend change slope, normalizing the actual consumption trend change slope to obtain a mutation degree of the resource consumption sequence in the resource consumption sequence set;

[0118] The standardization includes:

[0119] ;

[0120] in, Indicates the mutation degree of the resource consumption sequence in the resource consumption sequence set, The proportional coefficient representing the degree of mutation, which can be a constant or a variable, is used to adjust the sensitivity of the degree of mutation. represents the actual consumption trend change slope of the resource consumption sequence in the resource consumption sequence set, Indicates the standard consumption trend change slope of the resource consumption sequence in the resource consumption sequence set.

[0121] It's important to note that mutation level describes the degree or magnitude of a dramatic change in a system, process, or variable at a specific point in time or over a specific period of time, often significantly different from the system's normal behavior or historical trends. The mutation level can be used to identify sudden changes in resource consumption and inefficiencies in the production process, allowing for operational optimization and improved resource utilization. It can also serve as an early indicator of equipment failure or performance degradation, helping to predict whether a device is experiencing a malfunction.

[0122] Obtain the consumption trend and actual consumption trend change slope of the resource consumption sequences in the relevant resource consumption sequence set. The resource consumption sequences in the collected relevant resource consumption sequence set are cleaned and preprocessed, the resource consumption trend is analyzed using linear regression or time series analysis methods, and the actual consumption trend change slope is calculated by observing the consumption trend.

[0123] The slope of the actual consumption trend change of the resource consumption sequence in the resource consumption sequence set can be calculated by the following formula:

[0124] ;

[0125] in, Indicates time The resource consumption, is the total number of data points in the resource consumption series.

[0126] The slope of the standard consumption trend change of the resource consumption sequence in the resource consumption sequence set can be calculated by the following formula:

[0127] ;

[0128] in, Indicates the The slope of the actual consumption trend change of a resource consumption sequence, The total number of sequences in the resource consumption sequence set. The slope of the actual consumption trend of a resource consumption sequence can help monitor resource consumption efficiency in real time. A positive slope indicates that resource consumption is increasing over time, while a negative slope indicates that resource consumption is decreasing. The magnitude of the slope reflects the speed and trend of resource consumption changes.

[0129] In step S16, the resource allocation of the chemical plant is optimized using a genetic algorithm according to the stable decrease degree data.

[0130] comparing the stable decrease degree data with the determined stable decrease threshold value to determine the resource consumption units that may fail corresponding to all resource consumption sequences that may fail;

[0131] When the total production consumption of the resource-consuming units that may fail and other resource-consuming units that are unlikely to fail is the lowest, the genetic algorithm is used to optimize the allocation of resources in the chemical plant.

[0132] It should be noted that the stable decline threshold can be determined by analyzing historical resource consumption data to determine the consumption range under normal operating conditions. A threshold is then set, and when resource consumption falls below this value, it is considered to be steadily declining. Statistical methods, such as standard deviation and coefficient of variation, can also be used to determine the reasonable range of consumption changes. Thus, the stable decline threshold can be set as the average consumption level minus several times the standard deviation. Setting a stable decline threshold can help optimize resource allocation, improve resource utilization efficiency, and reduce production costs by identifying downward trends in resource consumption.

[0133] Genetic algorithms are heuristic search algorithms that mimic the process of natural selection and are used to solve optimization and search problems. In the optimal allocation of resources in chemical plants, genetic algorithms can be used to find the optimal allocation of resource consumption to improve efficiency and reduce costs.

[0134] Specifically, the implementation process of using genetic algorithms to optimize resource allocation in chemical plants includes:

[0135] First, the optimization goal is defined as the minimum total production consumption of resource-consuming units that may fail and other resource-consuming units that are unlikely to fail, and key parameters of the genetic algorithm, such as population size, are set; a binary coding scheme is designed to represent the resource allocation scheme, where each binary bit represents whether a resource-consuming unit is assigned to a specific task or production process, and then an initial population is randomly generated, where each individual represents a possible resource allocation scheme; a fitness function is defined based on the minimum total production consumption of resource-consuming units to evaluate the performance of each resource allocation scheme; based on the results evaluated by the fitness function, the individual with the highest fitness is selected from the final population, decoded into a resource allocation scheme, and implemented in actual production, thereby achieving optimal resource allocation in the chemical plant.

[0136] Through the optimal allocation of resources, we can ensure that resources are used efficiently in every step of the production process, reduce waste, and improve overall production efficiency; ensuring that the resource needs of key production links are met can prevent production accidents caused by resource shortages, ensure the safety of workers and the continuity of production; reasonable optimal allocation of resources can avoid equipment overload, thereby extending the service life of equipment, reducing maintenance costs and replacement frequency.

[0137] The following describes the working process of the present invention using a common scenario as an example. Figure 1 Schematic diagram of the working scenario of the method.

[0138] In a modern chemical plant, various resource consumption sequences in the production process of the chemical plant are obtained; based on the various resource consumption sequences, the stationarity results of the various resource consumption sequences are determined through autocorrelation analysis; based on the stationarity results of the various resource consumption sequences, the fluctuation degrees of the various resource consumption sequences are calculated to obtain the correlation values ​​between the various resource consumption sequences; based on the correlation values ​​between the various resource consumption sequences, a set of related resource consumption sequences between the resource consumption sequences is determined by comparing with the difference between the maximum correlation values; based on the set of related resource consumption sequences, various resource consumption sequences that may fail are obtained and the stable decline data of the various resource consumption sequences that may fail are calculated; based on the stable decline data, a genetic algorithm is used to optimize the allocation of resources in the chemical plant.

[0139] In summary, the present invention discloses an Internet of Things control method for a digital chemical plant, the method comprising obtaining each resource consumption sequence in the production process of the chemical plant, determining the stationarity result of each resource consumption sequence through autocorrelation analysis, thereby calculating the degree of fluctuation of each resource consumption sequence, obtaining the correlation degree value between each resource consumption sequence, and determining the set of related resource consumption sequences between resource consumption sequences by comparing with the difference between the maximum correlation degrees, and then obtaining each resource consumption sequence that may fail and calculating the stable decline data of each resource consumption sequence that may fail, and finally using a genetic algorithm to optimize the allocation of resources of the chemical plant. This method has the following effects: it can timely determine the core factors of problems in the Internet of Things control of a chemical plant and achieve optimal allocation of resources.

[0140] Reference Figure 2 The second embodiment of the present invention provides an Internet of Things control system for a digital factory, including:

[0141] The data acquisition module is used to obtain the resource consumption sequence of each chemical plant during the production process;

[0142] a stationarity determination module, configured to determine the stationarity results of each resource consumption sequence through autocorrelation analysis based on each resource consumption sequence;

[0143] a fluctuation degree calculation module, configured to calculate the fluctuation degree of each resource consumption sequence according to the stationarity results of each resource consumption sequence, and obtain the correlation degree values ​​between the resource consumption sequences;

[0144] a resource consumption sequence set determining module, configured to determine a set of correlated resource consumption sequences between the resource consumption sequences by comparing the correlation values ​​between the resource consumption sequences with the difference between the maximum correlation values;

[0145] a stability descent degree calculation module, configured to obtain, based on the set of related resource consumption sequences, each resource consumption sequence that may have a failure and calculate stability descent degree data of each resource consumption sequence that may have a failure;

[0146] The optimization allocation module is used to optimize the resource allocation of the chemical plant by using a genetic algorithm according to the stable decline data.

[0147] It should be noted that the Internet of Things control system for a digital factory provided in an embodiment of the present invention is used to execute all the process steps of the Internet of Things control method for a digital factory in the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0148] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data processing terminal program. When the processor executes the computer program, the steps of the above-mentioned embodiments of the IoT control method for the digital factory are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the fluctuation degree calculation module.

[0149] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0150] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0151] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the electronic device and connects various parts of the entire electronic device using various interfaces and lines.

[0152] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0153] If the module / unit integrated into the electronic device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0154] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0155] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. An Internet of Things control method for a digital factory, characterized in that: Executed by a computer, including: Obtain the resource consumption sequence of each chemical plant during the production process; According to each resource consumption sequence, the stationarity results of each resource consumption sequence are determined through autocorrelation analysis, including: Obtaining the initial mean value of each resource consumption sequence; Comparing the initial mean value with the final mean values ​​of the resource consumption sequences at all different time points within each resource consumption sequence to obtain difference values ​​of each resource consumption sequence; According to the difference values ​​of the respective resource consumption sequences, the reciprocal of the sum of all the difference values ​​is used as the stationarity result of the respective resource consumption sequences; Calculating the fluctuation degree of each resource consumption sequence based on the stationarity results of each resource consumption sequence to obtain the correlation degree values ​​between each resource consumption sequence includes: According to the stationarity results of the resource consumption sequences, the fluctuation degree of the resource consumption sequences is calculated by the following formula: ； in, Indicates the degree of fluctuation of resource consumption sequence, is the total number of data points in the resource consumption sequence, represents the mean of the resource consumption series, Represents the time index of each data in the resource consumption sequence, Indicates that the resource consumption sequence is The consumption of time, Indicates that the resource consumption sequence is and The relevance of the data at the moment The larger the value, the higher the resource consumption sequence. and The greater the correlation of the data at each moment, σ represents the standard deviation; dividing a plurality of resource consumption sequences with similar fluctuation degrees of the resource consumption sequences into a new resource consumption sequence group; Aggregating the correlation coefficients between any two resource consumption sequences in the new resource consumption sequence group to obtain correlation values ​​between the resource consumption sequences; Determining a set of correlated resource consumption sequences between the resource consumption sequences by comparing the correlation values ​​between the resource consumption sequences with the difference between the maximum correlation values; According to the set of related resource consumption sequences, obtaining each resource consumption sequence that may fail and calculating stable decrease degree data of each resource consumption sequence that may fail, including: Obtaining a mutation degree of a resource consumption sequence in the resource consumption sequence set; Perform anomaly detection based on the mutation degree to generate resource consumption sequences that may cause failures; Predicting consumption parameters based on the resource consumption sequences that may cause failures; According to the predicted consumption parameters, the stable decrease degree data of each of the resource consumption sequences that may fail is calculated using the following formula: ； in, is the stable descent data, It is The number of data points in a resource consumption series, Indicates the A resource consumption sequence at time point and The difference between According to the stable decline degree data, a genetic algorithm is used to optimize resource allocation of the chemical plant.

2. The IoT control method for a digital factory according to claim 1, characterized in that: The determining a set of correlated resource consumption sequences between the resource consumption sequences by comparing the correlation values ​​between the resource consumption sequences with the difference between the maximum correlation values ​​includes: Obtaining a maximum correlation value among the correlations between the resource consumption sequences; Subtracting the correlation values ​​between the resource consumption sequences from the maximum correlation value to obtain a correlation difference value; According to the correlation degree difference, a set of related resource consumption sequences between the resource consumption sequences is determined by the following method: When the correlation difference is greater than β, all resource consumption sequences are determined to be the same resource consumption sequence set; When the correlation degree difference is less than or equal to β, it is determined that the resource consumption sequence does not belong to any resource consumption sequence set; Among them, β is the stable correlation value completed in advance.

3. The IoT control method for a digital factory according to claim 1, characterized in that: The method of optimizing resource allocation of a chemical plant by using a genetic algorithm based on the stable decline degree data includes: comparing the stable decrease degree data with the determined stable decrease threshold value to determine the resource consumption units that may fail corresponding to all resource consumption sequences that may fail; When the total production consumption of the resource-consuming units that may fail and other resource-consuming units that are unlikely to fail is the lowest, the genetic algorithm is used to optimize the allocation of resources in the chemical plant.

4. The IoT control method for a digital factory according to claim 1, characterized in that: Obtaining the mutation degree of the resource consumption sequence in the resource consumption sequence set includes: Obtaining the consumption trend and actual consumption trend change slope of the resource consumption sequence in the relevant resource consumption sequence set; According to the consumption trend and the actual consumption trend change slope, normalizing the actual consumption trend change slope to obtain a mutation degree of the resource consumption sequence in the resource consumption sequence set; The standardization includes: ； in, Indicates the mutation degree of the resource consumption sequence in the resource consumption sequence set, The proportional coefficient representing the degree of mutation is used to adjust the sensitivity of the degree of mutation. represents the actual consumption trend change slope of the resource consumption sequence in the resource consumption sequence set, Indicates the standard consumption trend change slope of the resource consumption sequence in the resource consumption sequence set.

5. An Internet of Things control system for a digital factory, characterized in that: The method for implementing the Internet of Things control of a digital factory according to any one of claims 1 to 4 comprises: The data acquisition module is used to obtain the resource consumption sequence of each chemical plant during the production process; a stationarity determination module, configured to determine the stationarity results of each resource consumption sequence through autocorrelation analysis based on each resource consumption sequence; a fluctuation degree calculation module, configured to calculate the fluctuation degree of each resource consumption sequence according to the stationarity results of each resource consumption sequence, and obtain the correlation degree values ​​between the resource consumption sequences; a resource consumption sequence set determining module, configured to determine a set of correlated resource consumption sequences between the resource consumption sequences by comparing the correlation values ​​between the resource consumption sequences with the difference between the maximum correlation values; a stability descent degree calculation module, configured to obtain, based on the set of related resource consumption sequences, each resource consumption sequence that may have a failure and calculate stability descent degree data of each resource consumption sequence that may have a failure; The optimization allocation module is used to optimize the resource allocation of the chemical plant by using a genetic algorithm according to the stable decline data.

6. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the Internet of Things control method for a digital factory as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the Internet of Things control method for a digital factory as described in any one of claims 1 to 4.

Images