AI-based facility digital monitoring analysis pre-training system
By dividing the target time area into sub-time areas, collecting and analyzing relevant parameters and calculating the abnormal index, the problems of low data processing efficiency and different standards in the existing technology are solved, efficient data analysis and early warning are achieved, and manual labor is improved Intelligent performance and security.
Patent Information
- Application Number
- CN202411024738.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-29
AI Technical Summary
The existing digital monitoring and analysis pre-training system for AI-based facilities is inefficient in data acquisition, analysis and processing, resulting in data redundancy and error, and has different standards and data silos, which limits the performance of artificial intelligence.
By dividing the target time area into multiple sub-time areas, collecting and analyzing learning efficiency fluctuation parameters, batch fluctuation parameters, training fluctuation parameters and optimizing fluctuation parameters, using mathematical models to calculate abnormal indexes, real-time data processing and early warning, and improving data analysis accuracy and completeness.
It improves the accuracy and completeness of data processing, can promptly detect and deal with abnormal situations in pre-training, avoid system accidents, reduce industrial costs and losses, and improve the performance of artificial intelligence.
Smart Images

Figure CN118981407A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of AI-based facility digitization technology, and more specifically, to an AI-based facility digitization monitoring and analysis pre-training system. Background Art
[0002] With the development of the times, artificial intelligence (AI) is an important driving force for a new round of scientific and technological revolution and industrial transformation. It attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. AI technology has a wide range of applications in language recognition, image recognition, natural language processing, etc., and with the maturity of theory and the advancement of technology, its application areas are constantly expanding.
[0003] The existing AI-based digital monitoring and analysis pre-training system for facilities can fully utilize the advantages of AI technology to conduct all-round monitoring and analysis of facilities. Through data pre-collection modules, data pre-processing modules, pre-training modules, and early warning modules, the system can automatically identify and predict the operating status of facilities, promptly discover potential problems and hidden dangers, and provide strong guarantees for the safe operation of facilities. The system automatically analyzes, identifies, and understands content through computer vision and deep learning algorithms, and can detect abnormal situations in pre-training in real time and issue an alarm immediately.
[0004] However, in actual use, the existing monitoring and analysis pre-training systems are still insufficient in data collection, analysis and processing, and still have some shortcomings. For example, for large amounts of real-time data, traditional data processing methods cannot process them in a timely manner, resulting in data redundancy. When testing the data, errors will occur in the results, which leads to low efficiency and quality of data processing. The construction standards of existing monitoring and analysis pre-training systems are inconsistent, and the data island phenomenon is serious, which limits the performance of artificial intelligence. Summary of the invention
[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an AI-based facility digital monitoring and analysis pre-training system, which solves the problems raised in the above-mentioned background technology through AI-based facility digitization.
[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solution: an AI-based facility digital monitoring and analysis pre-training system, comprising:
[0007] Monitoring time division module: used to determine the monitoring time of target pre-training as the target time area, divide the target time area into various sub-time areas by equal time division, and mark them as 1, 2...n in sequence;
[0008] Data collection module: used to collect the pre-trained learning efficiency fluctuation parameters, batch fluctuation parameters, training fluctuation parameters, and optimization fluctuation parameters of each sub-time zone;
[0009] Data analysis and processing module: used to analyze and process the data collected in the data analysis and processing module in real time to obtain the learning efficiency fluctuation coefficient, batch fluctuation coefficient, training fluctuation coefficient, and optimization fluctuation coefficient;
[0010] Sub-time region anomaly calculation module: used to import the learning efficiency fluctuation coefficient value, batch fluctuation coefficient value, training fluctuation coefficient value, and optimization fluctuation coefficient value into the mathematical model of the sub-time region anomaly index to obtain the sub-time region anomaly value;
[0011] Target time anomaly calculation module: used to import the sub-time area anomaly index into the mathematical model of the target time area anomaly index to obtain the target time anomaly value;
[0012] Target time anomaly discrimination module: used to accurately compare the target time anomaly value with the preset target time anomaly value, calculate the difference between the target time anomaly value and the preset target time anomaly value, and when the difference is greater than the preset difference, transmit the difference to the target time warning module for feedback;
[0013] Target time warning module: used to transmit the received data to the system, and then the system transmits the data obtained after intelligent processing to the target time optimization module, and at the same time, the corresponding warning reminder is made according to the received data warning instruction;
[0014] Target time optimization module: used to import abnormal data in the target time warning module into the optimizer, and obtain optimized data through fine-tuning and integration.
[0015] Preferably, the AI-based facility digital monitoring and analysis pre-training system is characterized in that the data acquisition module is used to collect pre-trained learning efficiency fluctuation parameters, batch fluctuation parameters, training fluctuation parameters, and optimization fluctuation parameters of each sub-time zone.
[0016] Preferably, the learning efficiency fluctuation parameters include the weight update step size, weight step size, weight maximum step size, weight change rate, and training speed, which are respectively denoted as S1, S2, S max , S3, and S v The batch fluctuation parameters include the number of iterations, the maximum memory storage, the storage loss, and the rate of change of iterations, which are denoted as N1, N max , N2, and N3; the training fluctuation parameters include the number of pre-training iterations, the maximum number of pre-training rounds, the pre-training speed, and the gradient change rate of the rounds, which are denoted as J1, Jmax , J v , and J2; the optimized fluctuation parameters include the current data loss, the maximum allowed data loss, the data momentum, and the optimized gradient change rate, which are denoted as H1, H max , M, and H0, where data momentum is used to update the current data, which can help the model accelerate in the relevant direction and suppress oscillations.
[0017] Preferably, the data analysis and processing module is used to perform real-time analysis and processing on the data collected in the data analysis and processing module to obtain a learning efficiency fluctuation coefficient, a batch fluctuation coefficient, a training fluctuation coefficient, and an optimization fluctuation coefficient.
[0018] Preferably, the data analysis and processing module includes a learning efficiency fluctuation coefficient calculation unit, a batch fluctuation coefficient calculation unit, a training fluctuation coefficient calculation unit, and an optimization fluctuation coefficient calculation unit.
[0019] Preferably, the learning efficiency fluctuation coefficient calculation unit imports the learning efficiency fluctuation parameter into the mathematical model of the learning efficiency fluctuation coefficient to obtain the learning efficiency fluctuation coefficient value; the batch fluctuation coefficient calculation unit imports the batch fluctuation parameter into the mathematical model of the learning batch fluctuation coefficient to obtain the batch fluctuation coefficient value; the training fluctuation coefficient calculation unit imports the training fluctuation parameter into the mathematical model of the training fluctuation coefficient to obtain the training fluctuation coefficient value; the optimization fluctuation coefficient calculation unit imports the optimization fluctuation parameter into the mathematical model of the optimization fluctuation coefficient to obtain the optimization fluctuation coefficient value.
[0020] Preferably, the mathematical model of the learning efficiency fluctuation coefficient of each sub-time is:
[0021]
[0022] La i represents the learning efficiency fluctuation coefficient of the ith sub-time region, represents the training speed of the ith sub-time zone, represents the step size of the weight update of the ith sub-time region, represents the weight step of the ith sub-time region, S max Indicates the maximum step length of the target time region weight, It represents the rate of change of the weight of the ith sub-time zone; the mathematical model of the fluctuation coefficient of each sub-time batch is:
[0023]
[0024] Ma i represents the batch fluctuation coefficient of the ith sub-time zone, Indicates the number of iterations of the ith sub-time region, N maxIndicates the maximum memory storage capacity of the target time zone. represents the amount of loss stored in the i-th sub-time zone, The rate of change of the iteration of the i-th sub-time region; the mathematical model of the fluctuation coefficient of each sub-time training is:
[0025]
[0026] XA i represents the training fluctuation coefficient of the ith sub-time region, represents the number of times the i-th sub-time region traverses the pre-training, J max Indicates the maximum number of rounds of pre-training in the target time region, represents the pre-training speed of the ith sub-time region, It represents the gradient change rate of the round number in the ith sub-time region. The mathematical model of the optimized fluctuation coefficient of each sub-time is:
[0027]
[0028] Ya i represents the optimized volatility coefficient of the ith sub-time zone, represents the current data loss in the ith sub-time zone, H max Indicates the maximum amount of data loss allowed in the target time zone, M i represents the data momentum of the ith sub-time region, represents the optimization gradient change rate of the i-th sub-time region, where i=1,2,...,n, and i represents the number of the i-th detection sub-region.
[0029] Preferably, the analysis method of the abnormal value of the sub-time region is: i =(La i +Ma i +Xa i +Ya i )*υ, where ξ i represents the sub-time region anomaly index, and υ represents the weight of the target region anomaly.
[0030] Preferably, the target time abnormal value is obtained in the following specific manner: Where η is the target time anomaly value, Where μ is the mean value of the target time anomaly, λ is other influencing factors of the target time anomaly, and i = 1, 2, ..., n, i represents the number of the i-th detection sub-region.
[0031] Technical effects and advantages of the present invention:
[0032] 1. The present invention determines the target time abnormal value by dividing the target time area into learning efficiency fluctuation coefficient values, batch fluctuation coefficient values, training fluctuation coefficient values, and optimization fluctuation coefficient values of each sub-time area, thereby ensuring the comprehensiveness of data use and further ensuring the rationality of target time abnormality judgment;
[0033] 2. The present invention uses the AI technology facility digital monitoring and analysis pre-training system to divide the system into multiple modules, accurately divide the target time zone into various sub-zones, and mark them in sequence, providing a basis for subsequent data collection and improving the accuracy and completeness of data analysis and processing;
[0034] 3. The present invention can handle potential problems arising in pre-training through the early warning module, avoid the occurrence of system accidents, improve the performance of artificial intelligence, and reduce industrial costs and losses;
[0035] 4. The present invention can accurately detect abnormal situations of pre-training through data analysis and trends. Through the discrimination module of the system, there is a scientific basis for detecting abnormal situations of pre-training. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 It is the overall flow chart of the present invention. DETAILED DESCRIPTION
[0037] 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.
[0038] The following is an explanation of the terms involved in the embodiments of the present application.
[0039] Large pre-trained models: Large pre-training uses specific deep learning algorithms to learn the inherent connections in the data through self-supervised learning on large-scale data. Large pre-trained models can be transferred through fine-tuning and other methods to adapt to new specific needs and specialized fields. Various branches of deep learning, such as computer vision, speech processing, natural language processing, and video processing, have corresponding large pre-trained models.
[0040] Fine-tuning: Based on the pre-trained model, further training is performed on a small amount of data to adapt to new specific needs and specialized fields. Fine-tuning is a transfer learning technology that can greatly reduce the time and resource consumption of pre-training and reduce the corresponding industry costs.
[0041] As attached Figure 1 Shown in the figure is an AI-based facility digital monitoring and analysis pre-training system, including a monitoring time division module, a data acquisition module, a data analysis and processing module, a sub-time area anomaly calculation module, a target time anomaly calculation module, a target time anomaly discrimination module, a target time warning module, and a target time optimization module.
[0042] The output end of the monitoring time division module is connected to the input end of the data acquisition module, the output end of the data acquisition module is connected to the input end of the data analysis and processing module, the output end of the data analysis and processing module is connected to the input end of the sub-time area anomaly calculation module, the output end of the sub-time area anomaly calculation module is connected to the input end of the target time anomaly calculation module, the output end of the target time anomaly calculation module is connected to the input end of the target time anomaly discrimination module, the output end of the target time anomaly discrimination module is connected to the input end of the target time early warning module, and the output end of the target time early warning module is connected to the input end of the target time optimization module.
[0043] The monitoring time division module is used to determine the monitoring time of the target pre-training as the target time area, divide the target time area into various sub-time areas by equal time division, and mark them as 1, 2...n in sequence.
[0044] The data collection module is used to collect the pre-trained learning efficiency fluctuation parameters, batch fluctuation parameters, training fluctuation parameters, and optimization fluctuation parameters of each sub-time zone.
[0045] In this embodiment, it should be specifically explained that the pre-trained learning efficiency fluctuation parameters, batch fluctuation parameters, training fluctuation parameters, and optimization fluctuation parameters are detected using a GPU server and an optimizer, wherein the models and manufacturers of the GPU servers are: NVIDIA DGX Station and NVIDIA.
[0046] In this embodiment, it should be specifically explained that the learning efficiency fluctuation parameters include the step size of weight update, the weight step size, the maximum weight step size, the weight change rate, and the training speed, which are respectively denoted as S1, S2, S max , S3, and S v The batch fluctuation parameters include the number of iterations, the maximum memory storage, the storage loss, and the rate of change of iterations, which are denoted as N1, N max , N2, and N3; the training fluctuation parameters include the number of pre-training iterations, the maximum number of pre-training rounds, the pre-training speed, and the gradient change rate of the rounds, which are denoted as J1, J max , J v, and J2; the optimized fluctuation parameters include the current data loss, the maximum allowed data loss, the data momentum, and the optimized gradient change rate, which are denoted as H1, H max , M, and H0, where data momentum is used to update the current data, which can help the model accelerate in the relevant direction and suppress oscillations.
[0047] The data analysis and processing module is used to perform real-time analysis and processing on the data collected in the data analysis and processing module to obtain a learning efficiency fluctuation coefficient, a batch fluctuation coefficient, a training fluctuation coefficient, and an optimization fluctuation coefficient.
[0048] In this embodiment, it should be specifically explained that the data analysis and processing module includes a learning efficiency fluctuation coefficient calculation unit, a batch fluctuation coefficient calculation unit, a training fluctuation coefficient calculation unit, and an optimization fluctuation coefficient calculation unit; the learning efficiency fluctuation coefficient calculation unit imports the learning efficiency fluctuation parameter into the mathematical model of the learning efficiency fluctuation coefficient to obtain the learning efficiency fluctuation coefficient value; the batch fluctuation coefficient calculation unit imports the batch fluctuation parameter into the mathematical model of the learning batch fluctuation coefficient to obtain the batch fluctuation coefficient value; the training fluctuation coefficient calculation unit imports the training fluctuation parameter into the mathematical model of the training fluctuation coefficient to obtain the training fluctuation coefficient value; the optimization fluctuation coefficient calculation unit imports the optimization fluctuation parameter into the mathematical model of the optimization fluctuation coefficient to obtain the optimization fluctuation coefficient value.
[0049] In this embodiment, it should be specifically explained that the mathematical model of the learning efficiency fluctuation coefficient of each sub-time is: La i represents the learning efficiency fluctuation coefficient of the ith sub-time region, represents the training speed of the ith sub-time zone, represents the step size of the weight update of the ith sub-time region, represents the weight step of the ith sub-time region, S max Indicates the maximum step length of the target time region weight, It represents the rate of change of the weight of the ith sub-time zone; the mathematical model of the fluctuation coefficient of each sub-time batch is:
[0050]
[0051] Ma i represents the batch fluctuation coefficient of the ith sub-time zone, Indicates the number of iterations of the ith sub-time region, N max Indicates the maximum memory storage capacity of the target time zone. represents the amount of loss stored in the i-th sub-time zone, The rate of change of the iteration of the i-th sub-time region; the mathematical model of the fluctuation coefficient of each sub-time training is:
[0052]
[0053] XA i represents the training fluctuation coefficient of the ith sub-time region, represents the number of times the i-th sub-time region traverses the pre-training, J max Indicates the maximum number of rounds of pre-training in the target time region, represents the pre-training speed of the ith sub-time region, It represents the gradient change rate of the round number in the ith sub-time region. The mathematical model of the optimized fluctuation coefficient of each sub-time is:
[0054]
[0055] Ya i represents the optimized volatility coefficient of the ith sub-time zone, represents the current data loss in the ith sub-time zone, H max Indicates the maximum amount of data loss allowed in the target time zone, M i represents the data momentum of the ith sub-time region, represents the optimization gradient change rate of the i-th sub-time region, where i=1,2,...,n, and i represents the number of the i-th detection sub-region.
[0056] The sub-time region anomaly calculation module is used to import the learning efficiency fluctuation coefficient value, the batch fluctuation coefficient value, the training fluctuation coefficient value, and the optimization fluctuation coefficient value into the mathematical model of the sub-time region anomaly index to obtain the sub-time region anomaly value.
[0057] In this embodiment, it should be specifically explained that the analysis method of the abnormal value of the sub-time region is: ξ i =(La i +Ma i +Xa i +Ya i )*υ, where ξ i represents the sub-time region anomaly index, and υ represents the weight of the target region anomaly.
[0058] The target time anomaly calculation module is used to import the sub-time region anomaly index into the mathematical model of the target time region anomaly index to obtain the target time anomaly value.
[0059] In this embodiment, it should be specifically explained that the specific method for obtaining the target time anomaly value is: Where η is the target time anomaly value, Where μ is the mean value of the target time anomaly, λ is other influencing factors of the target time anomaly, and i = 1, 2, ..., n, i represents the number of the i-th detection sub-region.
[0060] The target time anomaly discrimination module is used to accurately compare the target time anomaly value with the preset target time anomaly value, calculate the difference between the target time anomaly value and the preset target time anomaly value, and when the difference is greater than the preset difference, transmit the difference to the target time warning module for feedback.
[0061] In this embodiment, it should be specifically explained that the preset target time anomaly value is the average of the target time anomaly values in previous years, where the average removes the maximum and minimum values, and the maximum and minimum values are both extreme values of external factors. The preset difference value is the difference between the theoretical target time anomaly value and the actual target time anomaly value.
[0062] The target time warning module is used to transmit the received data to the system, and then the system transmits the data obtained after intelligent processing to the target time optimization module. At the same time, corresponding warning reminders are made according to the received data warning instructions.
[0063] In this embodiment, it should be specifically explained that the early warning reminder is: when the difference value is greater than the preset difference value, it indicates that an abnormality occurs in the pre-training, and the system will perform corresponding optimization.
[0064] The target time optimization module is used to import abnormal data in the target time warning module into the optimizer, and obtain optimized data through fine-tuning and integration.
[0065] The present invention uses an AI facility digital monitoring and analysis pre-training system to divide the system into multiple modules, accurately divides the target time area and other times into various sub-areas, and marks them in sequence, providing a basis for subsequent data collection and improving the accuracy and completeness of data analysis and processing; through data analysis and trends, the pre-training abnormalities can be accurately detected, and the discrimination module of the system has a good scientific basis for detecting the pre-training abnormalities; the early warning module can handle potential problems arising in the pre-training, avoid the occurrence of system accidents, improve the performance of artificial intelligence, and reduce production costs and losses.
[0066] Secondly, in the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;
[0067] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. An AI-based facility digital monitoring and analysis pre-training system, comprising: Monitoring time division module: used to determine the monitoring time of target pre-training as the target time area, divide the target time area into various sub-time areas by equal time division, and mark them as 1, 2...n in sequence; Data collection module: used to collect the pre-trained learning efficiency fluctuation parameters, batch fluctuation parameters, training fluctuation parameters, and optimization fluctuation parameters of each sub-time zone; Data analysis and processing module: used to analyze and process the data collected in the data analysis and processing module in real time to obtain the learning efficiency fluctuation coefficient, batch fluctuation coefficient, training fluctuation coefficient, and optimization fluctuation coefficient; Sub-time region anomaly calculation module: used to import the learning efficiency fluctuation coefficient value, batch fluctuation coefficient value, training fluctuation coefficient value, and optimization fluctuation coefficient value into the mathematical model of the sub-time region anomaly index to obtain the sub-time region anomaly value; Target time anomaly calculation module: used to import the sub-time area anomaly index into the mathematical model of the target time area anomaly index to obtain the target time anomaly value; Target time anomaly discrimination module: used to accurately compare the target time anomaly value with the preset target time anomaly value, calculate the difference between the target time anomaly value and the preset target time anomaly value, and when the difference is greater than the preset difference, transmit the difference to the target time warning module for feedback; Target time warning module: used to transmit the received data to the system, and then the system transmits the data obtained after intelligent processing to the target time optimization module, and at the same time, the corresponding warning reminder is made according to the received data warning instruction; Target time optimization module: used to import abnormal data in the target time warning module into the optimizer, and obtain optimized data through fine-tuning and integration.
2. According to claim 1, the AI-based facility digital monitoring and analysis pre-training system is characterized by: The data collection module is used to collect the pre-trained learning efficiency fluctuation parameters, batch fluctuation parameters, training fluctuation parameters, and optimization fluctuation parameters of each sub-time zone.
3. The AI-based facility digital monitoring and analysis pre-training system according to claim 1, characterized in that: The learning efficiency fluctuation parameters include the weight update step size, weight step size, weight maximum step size, weight change rate, and training speed, which are denoted as S1, S2, S max , S3, and S v The batch fluctuation parameters include the number of iterations, the maximum memory storage, the storage loss, and the rate of change of iterations, which are denoted as N1, N max , N2, and N3; The training fluctuation parameters include the number of pre-training iterations, the maximum number of pre-training rounds, the pre-training speed, and the gradient change rate of the number of rounds, which are denoted as J1 and J2, respectively. max , J v , and J2; the optimized fluctuation parameters include the current data loss, the maximum allowed data loss, the data momentum, and the optimized gradient change rate, which are denoted as H1, H max , M, and H0, where data momentum is used to update the current data, which can help the model accelerate in the relevant direction and suppress oscillations.
4. The AI-based facility digital monitoring and analysis pre-training system according to claim 1, characterized in that: The data analysis and processing module is used to perform real-time analysis and processing on the data collected in the data analysis and processing module to obtain a learning efficiency fluctuation coefficient, a batch fluctuation coefficient, a training fluctuation coefficient, and an optimization fluctuation coefficient.
5. The AI-based facility digital monitoring and analysis pre-training system according to claim 1, characterized in that: The data analysis and processing module includes a learning efficiency fluctuation coefficient calculation unit, a batch fluctuation coefficient calculation unit, a training fluctuation coefficient calculation unit, and an optimization fluctuation coefficient calculation unit.
6. The AI-based facility digital monitoring and analysis pre-training system according to claim 5, characterized in that: The learning efficiency fluctuation coefficient calculation unit imports the learning efficiency fluctuation parameter into the mathematical model of the learning efficiency fluctuation coefficient to obtain the learning efficiency fluctuation coefficient value; the batch fluctuation coefficient calculation unit imports the batch fluctuation parameter into the mathematical model of the learning batch fluctuation coefficient to obtain the batch fluctuation coefficient value; the training fluctuation coefficient calculation unit imports the training fluctuation parameter into the mathematical model of the training fluctuation coefficient to obtain the training fluctuation coefficient value; the optimization fluctuation coefficient calculation unit imports the optimization fluctuation parameter into the mathematical model of the optimization fluctuation coefficient to obtain the optimization fluctuation coefficient value.
7. The AI-based facility digital monitoring and analysis pre-training system according to claim 1, characterized in that: The mathematical model of the learning efficiency fluctuation coefficient of each sub-time is: La i represents the learning efficiency fluctuation coefficient of the ith sub-time region, represents the training speed of the ith sub-time zone, represents the step size of the weight update of the ith sub-time region, represents the weight step of the ith sub-time region, S max Indicates the maximum step length of the target time region weight, It represents the rate of change of the weight of the ith sub-time zone; the mathematical model of the fluctuation coefficient of each sub-time batch is: Ma i represents the batch fluctuation coefficient of the ith sub-time zone, Indicates the number of iterations of the ith sub-time region, N max Indicates the maximum memory storage capacity of the target time zone. represents the amount of loss stored in the i-th sub-time zone, The rate of change of the iteration of the i-th sub-time region; the mathematical model of the fluctuation coefficient of each sub-time training is: XA i represents the training fluctuation coefficient of the ith sub-time zone, represents the number of times the i-th sub-time region traverses the pre-training, J max Indicates the maximum number of rounds of pre-training in the target time region, represents the pre-training speed of the ith sub-time region, It represents the gradient change rate of the round number in the ith sub-time region. The mathematical model of the optimized fluctuation coefficient of each sub-time is: Ya i represents the optimized volatility coefficient of the ith sub-time zone, represents the current data loss in the ith sub-time zone, H max Indicates the maximum amount of data loss allowed in the target time zone, M i represents the data momentum of the ith sub-time region, represents the optimization gradient change rate of the i-th sub-time region, where i=1,2,...,n, and i represents the number of the i-th detection sub-region.
8. The AI-based facility digital monitoring and analysis pre-training system according to claim 1, characterized in that: The analysis method of the abnormal value of the sub-time region is: i =(La i +Ma i +Xa i +Ya i )*υ, where ξ i represents the sub-time region anomaly index, and υ represents the weight of the target region anomaly.
9. The AI-based facility digital monitoring and analysis pre-training system according to claim 1, characterized in that: The specific method for obtaining the target time abnormal value is: Where η is the target time anomaly value, Where μ is the mean value of the target time anomaly, λ is other influencing factors of the target time anomaly, and i = 1, 2, ..., n, i represents the number of the i-th detection sub-region.
10. The AI-based facility digital monitoring and analysis pre-training system according to claim 1, characterized in that: The warning reminder is: when the difference value is greater than the preset difference value, it means that there is an abnormality in the pre-training, and the system will perform corresponding optimization.
Citation Information
Patent Citations
Multi-target identification monitoring method and system based on intelligent learning
CN116524422A
Food storage supervision system based on artificial intelligence
CN116843236A
Intelligent environment monitoring system based on Internet of Things
CN117629314A
Intelligent mold management and control system based on data analysis
CN117807398A
Pre-training model fine tuning method, crop monitoring method, device and equipment
CN118313431A
