Electrical automation equipment state prediction method and device based on artificial intelligence

Abstract

The invention relates to the technical field of data processing, and particularly discloses an electrical automation equipment state prediction method and device based on artificial intelligence, and the method can achieve the real-time evaluation of the heat dissipation efficiency through the precise collection and analysis of the operation environment parameters of the equipment, effectively monitors the thermal management state of the electrical automation equipment, and improves the reliability of the electrical automation equipment. An advanced artificial intelligence algorithm is utilized to quickly identify heat management abnormity and timely warn potential faults, the risk of production interruption of the electrical automation equipment caused by sudden faults is reduced, in addition, through intelligent analysis of operation state parameters of the electrical automation equipment, a control strategy can be dynamically optimized, and the production efficiency of the electrical automation equipment is improved. The electrical automation equipment is ensured to be in the optimal operation state, meanwhile, the operation precision grade of the electrical automation equipment can be accurately predicted, a scientific basis is provided for accurate control, and the operation precision of the electrical automation equipment is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and specifically to an electrical automation equipment state prediction method and device based on artificial intelligence. Background Art

[0002] With the rapid development of intelligent manufacturing, automation equipment plays an increasingly important role in fields such as production manufacturing, energy distribution, and transportation. However, during long-term operation, these devices often experience performance degradation or failures due to reasons such as wear, aging, environmental factors, or improper operation. This not only affects production efficiency but may also pose safety hazards. Therefore, achieving accurate prediction and timely maintenance of the state of automation equipment has become one of the key technologies for improving equipment operation reliability and reducing maintenance costs.

[0003] For example, the invention patent with the publication number CN119025841A discloses an electrical equipment state monitoring method and system, which relates to the technical field of electrical equipment monitoring. It includes collecting data according to the monitored electrical equipment collection items and performing outlier removal; setting an initial collection frequency and performing linear interpolation and spline interpolation based on the collection items respectively to fill in the collection item data; constructing a long short-term memory network (LSTM) model for time series prediction.

[0004] For example, the invention patent with the publication number CN113760992A discloses a prediction method, device, equipment, and storage medium for the operating state of electrical equipment, which relates to the technical field of computers, especially artificial intelligence technologies such as deep learning and big data. The specific implementation solution is as follows: obtaining the historical operating state parameters of the target electrical equipment; obtaining a reference data set according to the type to which the target electrical equipment belongs, where the reference data set includes the operating state parameters of multiple reference electrical equipment in each period; determining the operating state of the target electrical equipment according to the historical operating state parameters of the target electrical equipment and the operating state parameters of multiple reference electrical equipment in each period.

[0005] However, during the implementation of the embodiments of the present application, it is found that the above technologies have at least the following technical problems: When predicting the performance state of automation equipment, the prior art generally only analyzes the operating parameters of the automation equipment itself, making it impossible for the performance prediction model to comprehensively capture all the key factors affecting equipment performance. This limitation restricts the depth and breadth of the prediction results, making the prediction results inaccurate and incomplete. Summary of the Invention

[0006] In view of the deficiencies of the prior art, the present invention provides an electrical automation equipment state prediction method and device based on artificial intelligence, which can effectively solve the problems involved in the above background art.

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions: In the first aspect of the present invention, a method for predicting the state of electrical automation equipment based on artificial intelligence is provided, including: Step 1: A data collection device collects the operating environment parameters of the electrical automation equipment, and a data processing device uses the first artificial intelligence method to evaluate the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs; Step 2: The data collection device obtains the thermal management state parameters of the electrical automation equipment, and the data processing device uses the second artificial intelligence method to analyze the thermal management anomaly index of the electrical automation equipment, and determines whether to optimize the preset control set of the operating state parameters of the electrical automation equipment based on the thermal management anomaly index of the electrical automation equipment; Step 3: A control device controls the electrical automation equipment through the control set of the operating state parameters of the electrical automation equipment, the data collection device collects the operating state parameters of the electrical automation equipment, the data processing device uses the third artificial intelligence method to determine the operating accuracy factor of the electrical automation equipment, predicts the operating accuracy level of the electrical automation equipment based on the operating accuracy factor of the electrical automation equipment, and a feedback device controls and feedbacks the state of the electrical automation equipment based on the operating accuracy level of the electrical automation equipment.

[0008] As a further method, the control of the electrical automation equipment through the control set of the operating state parameters of the electrical automation equipment is specifically as follows: If it is determined not to optimize the preset control set of the operating state parameters of the electrical automation equipment, the electrical automation equipment is directly controlled through the preset control set of the operating state parameters of the electrical automation equipment; If it is determined to optimize the preset control set of the operating state parameters of the electrical automation equipment, the optimized control set of the operating state parameters of the electrical automation equipment is recorded as the first updated control set of the operating state parameters of the electrical automation equipment, and the electrical automation equipment is controlled through the first updated control set of the operating state parameters of the electrical automation equipment.

[0009] As a further method, the prediction of the operating accuracy level of the electrical automation equipment is specifically as follows: The operating accuracy factor of the electrical automation equipment is compared with the first operating accuracy factor interval, the second operating accuracy factor interval, and the third operating accuracy factor interval stored in the electrical database; If the operating accuracy factor of the electrical automation equipment belongs to the first operating accuracy factor interval, the predicted operating accuracy level of the electrical automation equipment is the first level; If the operating accuracy factor of the electrical automation equipment belongs to the second operating accuracy factor interval, the predicted operating accuracy level of the electrical automation equipment is the second level; If the operating accuracy factor of the electrical automation equipment belongs to the third operating accuracy factor interval, the predicted operating accuracy level of the electrical automation equipment is the third level.

[0010] As a further method, the control feedback on the state of the electrical automation equipment is as follows. The specific control feedback process is as follows: If the operation accuracy level of the electrical automation equipment is the first level, continuously obtain the thermal management state parameters of the electrical automation equipment; if the operation accuracy level of the electrical automation equipment is the second level, match the second optimization control set from the electrical database according to the operation accuracy factor of the electrical automation equipment, and optimize the operation state parameter control set of the electrical automation equipment updated for the first time to obtain the operation state parameter control set of the electrical automation equipment updated for the second time, and control the electrical automation equipment through the operation state parameter control set of the electrical automation equipment updated for the second time; if the operation accuracy level of the electrical automation equipment is the third level, generate a warning log for feedback.

[0011] The second aspect of the present invention provides a state prediction device for electrical automation equipment based on artificial intelligence, including: a data collection device, a data processing device, a control device, and a feedback device; the data collection device is used to collect the operation environment parameters of the electrical automation equipment, obtain the thermal management state parameters of the electrical automation equipment, and collect the operation state parameters of the electrical automation equipment; the data processing device is used to evaluate the heat dissipation efficiency coefficient of the operation environment to which the electrical automation equipment belongs by using the first artificial intelligence method, analyze the thermal management anomaly index of the electrical automation equipment by using the second artificial intelligence method, and determine the operation accuracy factor of the electrical automation equipment by using the third artificial intelligence method; the control device is used to control the electrical automation equipment through the operation state parameter control set of the electrical automation equipment; the feedback device is used to perform control feedback on the state of the electrical automation equipment based on the operation accuracy level of the electrical automation equipment.

[0012] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention provides a state prediction method and device for electrical automation equipment based on artificial intelligence. By accurately collecting and analyzing the operation environment parameters of the equipment, this method can evaluate the heat dissipation efficiency in real time, effectively monitor the thermal management state of the electrical automation equipment, use advanced artificial intelligence algorithms to quickly identify thermal management anomalies, and timely warn of potential faults, thus greatly shortening the time window for equipment maintenance and reducing the risk of production interruption of electrical automation equipment caused by sudden failures. In addition, through the intelligent analysis of the operation state parameters of the electrical automation equipment, the control strategy can be dynamically optimized to ensure that the electrical automation equipment is in the best operation state. At the same time, it can accurately predict the operation accuracy level of the electrical automation equipment, providing a scientific basis for precise control and further improving the operation accuracy of the electrical automation equipment. This method not only significantly enhances the reliability and stability of the electrical automation equipment, but also realizes the efficient automation management of the electrical automation equipment through an intelligent prediction and control feedback mechanism.

[0013] (2) By collecting and analyzing the operating environment parameters of electrical automation equipment, this method can comprehensively insight into various key factors affecting the performance of electrical automation equipment, thus overcoming the limitations of traditional performance prediction models and effectively solving the problem that the prediction results of previous prediction methods are inaccurate and incomplete due to the inability to comprehensively capture all key factors. By deeply mining the complex relationship between environmental parameters and the performance of electrical automation equipment, not only the accuracy of the prediction results is improved, but also the depth and breadth of the prediction are greatly expanded, providing a more reliable scientific basis for the condition monitoring and maintenance of electrical automation equipment.

[0014] (3) By accurately determining the operating precision factor of electrical automation equipment, this method realizes personalized control feedback on the state of electrical automation equipment, effectively avoiding over-maintenance or under-maintenance, and significantly improving the operating precision of electrical automation equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the following drawings without creative efforts.

[0016] Figure 1 It is a schematic flow chart of the method steps of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0018] Referring to Figure 1 As shown, the first aspect of the present invention provides a method for predicting the state of electrical automation equipment based on artificial intelligence, including: Step 1, a data collection device collects the operating environment parameters of electrical automation equipment, and a data processing device uses the first artificial intelligence method to evaluate the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs.

[0019] The above-mentioned first artificial intelligence method represents a specific evaluation method for the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs.

[0020] In a specific embodiment, by collecting and analyzing the operating environment parameters of electrical automation equipment, the method can comprehensively understand various key factors affecting the performance of electrical automation equipment, thus overcoming the limitations of traditional performance prediction models and effectively solving the problem that the prediction results of previous prediction methods are inaccurate and incomplete because they cannot comprehensively capture all key factors. By deeply exploring the complex relationship between environmental parameters and the performance of electrical automation equipment, not only the accuracy of the prediction results is improved, but also the depth and breadth of the prediction are greatly expanded, providing a more reliable scientific basis for the condition monitoring and maintenance of electrical automation equipment.

[0021] Specifically, the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs is evaluated. The specific evaluation process is as follows: The operating environment parameters of the electrical automation equipment include the average temperature of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, the average air flow velocity of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, and the average thermal radiation intensity of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period. The above environmental monitoring period refers to the time point for monitoring and analyzing the operating environment of the electrical automation equipment, and the specific duration is formulated by the equipment administrator. The average temperature of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period represents the average level of the temperature of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, which can be measured in real time by each temperature sensor installed in the operating environment, and the average value of all the measured values is obtained through averaging. The above average air flow velocity represents the average value of the air flow velocity in the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, which can be measured in real time by each anemometer installed in the operating environment, and the average value of all the measured values is obtained through averaging. The above average thermal radiation intensity represents the average value of the thermal radiation intensity received in the operating environment to which the electrical automation equipment belongs during the environmental monitoring period. The thermal radiation intensity refers to the energy passing through a unit area per unit time, which reflects the strength of the thermal radiation in the environment and can be measured in real time by each thermal radiometer installed in the operating environment, and the average value of all the measured values is obtained through averaging.

[0022] Obtain the average temperature of the surface detection part of the electrical automation equipment within the environmental monitoring period, perform a difference process with the average temperature of the operating environment of the electrical automation equipment within the environmental monitoring period, and perform a ratio process on the processing result with the average temperature of the operating environment of the electrical automation equipment within the environmental monitoring period to finally obtain the heat dissipation efficiency value of the operating environment of the electrical automation equipment within the environmental monitoring period; the average temperature of the surface detection part of the electrical automation equipment within the environmental monitoring period represents the average value of the temperature of the surface detection part of the electrical automation equipment within the environmental monitoring period, which can be obtained through monitoring and analysis by infrared imaging technology (such as an infrared thermal imager). During the environmental monitoring period, the infrared thermal imager will scan the surface detection part of the electrical automation equipment multiple times at a predetermined time interval, record the temperature data obtained from each scan, and calculate the average temperature of the surface detection part within the monitoring period by statistically processing and averaging these temperature data, where the surface detection part refers to the surface area of the electrical automation equipment that can be monitored by infrared imaging technology; the above heat dissipation efficiency value is used to quantify the efficiency of the electrical automation equipment in dissipating heat to the operating environment through its surface within the environmental monitoring period.

[0023] Comprehensively evaluate the heat dissipation efficiency value of the operating environment of the electrical automation equipment within the environmental monitoring period, the average air flow velocity of the operating environment of the electrical automation equipment within the environmental monitoring period, and the average thermal radiation intensity of the operating environment of the electrical automation equipment within the environmental monitoring period to obtain the heat dissipation effectiveness coefficient of the operating environment of the electrical automation equipment. The heat dissipation effectiveness coefficient of the operating environment of the electrical automation equipment is used to comprehensively quantify the heat dissipation ability of the operating environment of the electrical automation equipment.

[0024] The specific evaluation method for the heat dissipation effectiveness coefficient of the operating environment of the electrical automation equipment is as follows: ; In the formula, is the heat dissipation effectiveness coefficient of the operating environment of the electrical automation equipment, is the heat dissipation efficiency value of the operating environment of the electrical automation equipment within the environmental monitoring period, is the average air flow velocity of the operating environment of the electrical automation equipment within the environmental monitoring period, is the average thermal radiation intensity of the operating environment of the electrical automation equipment within the environmental monitoring period, is the defined heat dissipation efficiency value preset in the electrical database, is the defined average air flow velocity preset in the electrical database, is the defined average thermal radiation intensity preset in the electrical database, is the influence weight of the heat dissipation efficiency value preset in the electrical database, is the preset influence weight of the average air flow velocity in the electrical database, is the preset influence weight of the average heat radiation intensity in the electrical database, and e is the natural constant.

[0025] The above-defined heat dissipation efficiency value represents the minimum allowable value of the heat dissipation efficiency value of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period; the above-defined average air flow velocity represents the minimum allowable value of the average air flow velocity of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period; the above-defined average heat radiation intensity represents the maximum allowable value of the average heat radiation intensity of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period.

[0026] The above heat dissipation efficiency value influence weight represents the value of the influence degree of the unit value of the heat dissipation efficiency value on the heat dissipation effectiveness coefficient; the above average air flow velocity influence weight represents the value of the influence degree of the unit value of the average air flow velocity on the heat dissipation effectiveness coefficient; the above average heat radiation intensity influence weight represents the value of the influence degree of the unit value of the average heat radiation intensity on the heat dissipation effectiveness coefficient. The electrical database stores the corresponding relationships between the heat dissipation efficiency value and its corresponding influence weight, the average air flow velocity and its corresponding influence weight, and the average heat radiation intensity and its corresponding influence weight. For example, when the heat dissipation efficiency value, the average air flow velocity, and the average heat radiation intensity are input into the electrical database, the electrical database can match the heat dissipation efficiency value influence weight, the average air flow velocity influence weight, and the average heat radiation intensity influence weight, and their value ranges are all between 0 and 1.

[0027] It should be noted that the increase in the average air flow velocity significantly enhances the convective heat dissipation effect of heat in the operating environment. This increase enables the ambient temperature to be lower than the temperature of the electrical automation equipment, thereby directly improving the heat dissipation efficiency value. The reason lies in that the air flow accelerates the heat transfer rate from the surface of the electrical automation equipment to the surrounding environment, effectively preventing the accumulation of surface temperature of the equipment in the environment. At the same time, the air flow also promotes the extensive diffusion of heat, further reducing the thermal radiation intensity in the operating environment, resulting in a corresponding decrease in the average thermal radiation intensity, thus improving the heat dissipation capacity of the operating environment where the electrical automation equipment is located. However, when the heat dissipation efficiency value increases abnormally significantly, this strongly indicates that within the established environmental monitoring period, the average temperature recorded at the surface detection part of the electrical automation equipment is abnormally high compared to the average temperature of its operating environment. This abnormal phenomenon deeply reveals the too-low state of the operating environment temperature. Such a low-temperature environment not only directly leads to a significant reduction in the thermal radiation intensity, thereby weakening the effects of heat conduction and convective heat dissipation, but also in this situation, the average air flow velocity also slows down accordingly. This series of chain reactions jointly contribute to the abnormal increase in the heat dissipation efficiency coefficient in the operating environment of the electrical automation equipment. The excessive increase in this coefficient also has an adverse impact on the operating accuracy of the electrical automation equipment. The electronic components and mechanical parts inside the electrical automation equipment are designed to have a certain temperature operating range. When the ambient temperature is too low, the performance of these components and parts may change. For example, the thermal expansion and contraction of materials cause dimensional changes, which in turn affect the clearance between precision parts; the viscosity of the lubricating oil increases, reducing the operating efficiency of mechanical parts; and the electrical conductivity of electronic components may be affected by the low temperature, resulting in signal transmission delays or distortions, etc. The electrical automation equipment is difficult to maintain the best working state and performance. The too-low heat dissipation efficiency coefficient of the operating environment where the electrical automation equipment is located clearly indicates poor heat dissipation effect. This directly causes the heat accumulated inside the electrical automation equipment to be difficult to effectively discharge, accelerating the aging process of electronic components and even possibly directly triggering component failures, resulting in a sharp drop or complete failure of the performance of the electrical automation equipment. Therefore, it is necessary to control the heat dissipation efficiency coefficient of the operating environment where the electrical automation equipment is located within a reasonable range.

[0028] The electrical database is a database used to store the parameters involved in the method and device for predicting the state of electrical automation equipment based on artificial intelligence.

[0029] Step 2: The data collection device obtains the thermal management state parameters of the electrical automation equipment, and the data processing device analyzes the thermal management anomaly index of the electrical automation equipment using the second artificial intelligence method, and determines whether to optimize the preset control set of the operating state parameters of the electrical automation equipment based on the thermal management anomaly index of the electrical automation equipment.

[0030] The above-mentioned second artificial intelligence method represents a specific analysis method for the thermal management anomaly index of electrical automation equipment.

[0031] Specifically, the determination of whether to optimize the preset control set of the operating state parameters of the electrical automation equipment is as follows: Extract the thermal management anomaly threshold of the electrical automation equipment from the electrical database and compare it with the thermal management anomaly index of the electrical automation equipment. If the thermal management anomaly index of the electrical automation equipment is less than or equal to the thermal management anomaly threshold of the electrical automation equipment, it is determined not to optimize the preset control set of the operating state parameters of the electrical automation equipment; the above-mentioned thermal management anomaly threshold of the electrical automation equipment represents the maximum value of the reasonable range of the thermal management anomaly index of the electrical automation equipment.

[0032] If the thermal management anomaly index of the electrical automation equipment is greater than the thermal management anomaly threshold of the electrical automation equipment, it is determined to optimize the preset control set of the operating state parameters of the electrical automation equipment. The specific optimization process is as follows: Compare the temperature coefficient of the electrical automation equipment with the reference temperature coefficient to obtain a comparison result. Based on the comparison result, match the first optimization control set from the electrical database, and update the preset control set of the operating state parameters of the electrical automation equipment once to obtain the updated control set of the operating state parameters of the electrical automation equipment once; the above-mentioned comparison results include comparison result one (that is, the temperature coefficient of the electrical automation equipment is greater than the reference temperature coefficient), comparison result two (that is, the temperature coefficient of the electrical automation equipment is equal to the reference temperature coefficient), and comparison result three (that is, the temperature coefficient of the electrical automation equipment is less than the reference temperature coefficient); the specific matching process of the above-mentioned first optimization control set is as follows: The first optimization control sets corresponding to each comparison result are stored in the electrical database. Query the comparison result of the temperature coefficient of the electrical automation equipment and the reference temperature coefficient. The first optimization control set corresponding to this comparison result is the first optimization control set matched by the comparison result of the temperature coefficient of the electrical automation equipment and the reference temperature coefficient. The specific values in the first optimization control set are determined by the thermal management anomaly index of the electrical automation equipment. In an exemplary embodiment, assume that the thermal management anomaly index of the electrical automation equipment is G, the thermal management anomaly threshold of the electrical automation equipment is GY, and the comparison result of the temperature coefficient of the electrical automation equipment and the reference temperature coefficient is comparison result one. Then the first optimization control set includes: reducing the operating power in the control set of the operating state parameters of the electrical automation equipment to the original ( ) times, reducing the operating speed in the control set of the operating state parameters of the electrical automation equipment to the original ( ) times, and keeping the remaining parameters in the control set of the operating state parameters of the electrical automation equipment unchanged.

[0033] Specifically, the specific analysis method for the thermal management anomaly index of the electrical automation equipment is as follows: ; ; ; wherein, is the thermal management anomaly index of the electrical automation equipment, is the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs, is the reference heat dissipation efficiency coefficient preset in the electrical database, is the temperature coefficient of the electrical automation equipment, is the reference temperature coefficient preset in the electrical database, is the temperature growth deviation coefficient of the electrical automation equipment, is the average heat flux density of the surface detection part to which the electrical automation equipment belongs during the equipment monitoring period, is the reference average heat flux density preset in the electrical database, is the power density of the electrical automation equipment during the equipment monitoring period, is the reference power density preset in the electrical database, is the weight value of the heat dissipation efficiency coefficient preset in the electrical database, is the weight value of the temperature coefficient preset in the electrical database, is the weight value of the temperature growth deviation coefficient preset in the electrical database, is the weight value of the average heat flux density preset in the electrical database, is the weight value of the power density preset in the electrical database, is the average temperature of the surface detection part to which the electrical automation equipment belongs during the equipment monitoring period, is the average temperature of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period, is the first average temperature influence value preset in the electrical database, is the second average temperature influence value preset in the electrical database, is the temperature growth deviation rate of the surface detection part to which the electrical automation equipment belongs during the equipment monitoring period, is the temperature growth deviation rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period, is the first temperature growth deviation rate influence value preset in the electrical database, is the second temperature growth deviation rate influence value preset in the electrical database.

[0034] The above heat dissipation efficiency coefficient weight represents the value of the influence degree of the unit value of the heat dissipation efficiency coefficient on the thermal management anomaly index; the above temperature coefficient weight represents the value of the influence degree of the unit value of the temperature coefficient on the thermal management anomaly index; the above temperature growth deviation coefficient weight represents the value of the influence degree of the unit value of the temperature growth deviation coefficient on the thermal management anomaly index; the above average heat flux density weight represents the value of the influence degree of the unit value of the average heat flux density on the thermal management anomaly index; the above power density weight represents the value of the influence degree of the unit value of the power density on the thermal management anomaly index. The electrical database stores the corresponding relationships between the heat dissipation efficiency coefficient and its corresponding weight, the temperature coefficient and its corresponding weight, the temperature growth deviation coefficient and its corresponding weight, the average heat flux density and its corresponding weight, and the power density and its corresponding weight. For example, when the heat dissipation efficiency coefficient, temperature coefficient, temperature growth deviation coefficient, average heat flux density, and power density are input into the electrical database, the electrical database can match the heat dissipation efficiency coefficient weight, temperature coefficient weight, temperature growth deviation coefficient weight, average heat flux density weight, and power density weight, and their value ranges are all between 0 and 1.

[0035] The above-mentioned first average temperature influence value represents the value of the influence degree of the average temperature unit value of the surface detection part to which the electrical automation equipment belongs on the temperature coefficient within the equipment monitoring period; the above-mentioned second average temperature influence value represents the value of the influence degree of the average temperature unit value of the internal detection part to which the electrical automation equipment belongs on the temperature coefficient within the equipment monitoring period; the above-mentioned first temperature growth deviation rate influence value represents the value of the influence degree of the temperature growth deviation rate unit value of the surface detection part to which the electrical automation equipment belongs on the temperature growth deviation coefficient within the equipment monitoring period; the above-mentioned second temperature growth deviation rate influence value represents the value of the influence degree of the temperature growth deviation rate unit value of the internal detection part to which the electrical automation equipment belongs on the temperature growth deviation coefficient within the equipment monitoring period. In the electrical database, the corresponding relationships between the average temperature of the surface detection part to which the electrical automation equipment belongs and its corresponding influence value, the average temperature of the internal detection part to which the electrical automation equipment belongs and its corresponding influence value, the temperature growth deviation rate of the surface detection part to which the electrical automation equipment belongs and its corresponding influence value, and the temperature growth deviation rate of the internal detection part to which the electrical automation equipment belongs and its corresponding influence value within the equipment monitoring period are stored. For example, by inputting the average temperature of the surface detection part to which the electrical automation equipment belongs, the average temperature of the internal detection part to which the electrical automation equipment belongs, the temperature growth deviation rate of the surface detection part to which the electrical automation equipment belongs, and the temperature growth deviation rate of the internal detection part to which the electrical automation equipment belongs within the equipment monitoring period into the electrical database, the electrical database can match the first average temperature influence value, the second average temperature influence value, the first temperature growth deviation rate influence value, and the second temperature growth deviation rate influence value, and their value ranges are all between 0 and 1.

[0036] The temperature coefficient of the above-mentioned electrical automation equipment is used to comprehensively quantify the temperature level of the electrical automation equipment within the equipment monitoring period; the temperature growth deviation coefficient of the above-mentioned electrical automation equipment is used to comprehensively quantify the temperature growth deviation degree of the electrical automation equipment within the equipment monitoring period; the above-mentioned reference heat dissipation efficiency coefficient represents the reference value of the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs; the above-mentioned reference temperature coefficient represents the reference value of the temperature coefficient of the electrical automation equipment; the above-mentioned reference average heat flux density represents the reference value of the average heat flux density of the surface detection part to which the electrical automation equipment belongs within the equipment monitoring period; the above-mentioned reference power density represents the reference value of the power density of the electrical automation equipment within the equipment monitoring period.

[0037] It should be noted that the heat dissipation efficiency coefficient is a key indicator for measuring the heat dissipation capacity of the operating environment of electrical automation equipment. By comparing it with the reference heat dissipation efficiency coefficient preset in the electrical database, it can reflect whether the heat dissipation conditions of the current environment meet the standards. When the heat dissipation efficiency coefficient significantly deviates from the corresponding reference value, it may lead to abnormal increase in the temperature of the electrical automation equipment due to the inability of the temperature to dissipate, or it may also cause the electrical automation equipment to fail to operate normally, resulting in the temperature of the electrical automation equipment being abnormally low. At this time, the temperature coefficient will change and significantly deviate from the corresponding reference value. The temperature growth deviation coefficient further refines the abnormal situation of temperature change. It calculates the deviation degree of the temperature growth of the electrical automation equipment and is closely related to the stable operating state of the electrical automation equipment. When the temperature growth deviation coefficient increases, it indicates that the temperature growth of the electrical automation equipment exceeds the normal range, which may be the result of the combined action of various factors such as decreased heat dissipation efficiency and internal heat accumulation. The average heat flux density is an important parameter for evaluating the heat dissipation performance of the equipment surface. By comparing it with the reference average heat flux density preset in the electrical database, it can reflect whether the heat dissipation on the equipment surface is uniform and effective. When the actual average heat flux density significantly deviates from the corresponding reference value, it means that there may be problems with the heat dissipation of the electrical automation equipment. The change in the average heat flux density will directly affect the temperature distribution and heat dissipation efficiency coefficient of the electrical automation equipment, and thus affect the temperature coefficient and temperature growth deviation coefficient. The power density reflects the energy consumption of the electrical automation equipment during operation and is closely related to the heat generation of the electrical automation equipment because the heat generation of the electrical automation equipment is usually proportional to its power. When the power density increases, the heat generation of the electrical automation equipment will also increase correspondingly, which will put higher requirements on the heat dissipation system. If the heat dissipation system cannot dissipate the heat in a timely and effective manner, it will cause the temperature of the electrical automation equipment to rise. Therefore, when the power density significantly deviates from the corresponding reference value, it will cause abnormal heat generation of the electrical automation equipment, thus exacerbating the degree of deviation of the temperature coefficient from the corresponding reference value, and then triggering a series of thermal management problems. In summary, the parameters such as the heat dissipation efficiency coefficient, temperature coefficient, temperature growth deviation coefficient, average heat flux density, and power density are interrelated. Abnormal heat dissipation efficiency will directly lead to abnormal temperature coefficient and temperature growth deviation coefficient; while the change in the average heat flux density will affect the heat dissipation efficiency coefficient and temperature coefficient of the equipment; the increase in power density will increase the heat generation of the equipment, posing a greater challenge to the thermal management of electrical automation equipment. The changes in these parameters will ultimately affect the calculation result of the thermal management abnormality index through complex interaction mechanisms, thus reflecting the performance state of the electrical automation equipment in terms of thermal management.

[0038] Furthermore, the thermal management anomaly index of the electrical automation equipment is analyzed as follows: The thermal management state parameters of the electrical automation equipment include the average temperature of the surface detection parts of the electrical automation equipment during the equipment monitoring period, the average temperature of the internal detection parts of the electrical automation equipment during the equipment monitoring period, the temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period, the temperature growth rate of each internal detection part of the electrical automation equipment during the equipment monitoring period, the average heat flux density of the surface detection parts of the electrical automation equipment during the equipment monitoring period, and the power density of the electrical automation equipment during the equipment monitoring period.

[0039] The above-mentioned equipment monitoring period refers to the time period for detecting the thermal management performance of the electrical automation equipment, and the specific duration is determined by the equipment administrator; the average temperature of the surface detection parts of the electrical automation equipment during the equipment monitoring period represents the average level of the temperature of the surface detection parts of the electrical automation equipment during the equipment monitoring period, and the acquisition method is the same as that of the average temperature of the surface detection parts of the electrical automation equipment during the environmental monitoring period; the average temperature of the internal detection parts of the electrical automation equipment during the equipment monitoring period represents the average level of the temperature of the internal detection parts of the electrical automation equipment during the equipment monitoring period. The real-time temperature of each internal detection part during the equipment monitoring period is monitored by temperature sensors installed at each internal detection part, and all data are integrated and averaged to obtain the average temperature of the internal detection parts of the electrical automation equipment during the equipment monitoring period. Each internal detection part includes, but is not limited to, the center position point of the reducer and each detection position point set by the equipment management personnel on the surface of the motor. The specific parts of each internal detection part can be determined by the equipment administrator.

[0040] The temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period represents the temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period. The temperature at the end time point of the equipment monitoring period of the surface detection parts of the electrical automation equipment is subtracted from the temperature at the start time point of the equipment monitoring period of the surface detection parts of the electrical automation equipment, and the processing result is averaged with the duration corresponding to the equipment monitoring period to finally obtain the temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period; the temperature at the end time point of the equipment monitoring period of the surface detection parts of the electrical automation equipment and the temperature at the start time point of the equipment monitoring period of the surface detection parts of the electrical automation equipment can both be monitored and analyzed through infrared imaging technology (such as an infrared thermal imager).

[0041] The temperature growth rate of each internal detection part of the above-mentioned electrical automation equipment within the equipment monitoring period, which represents the temperature growth rate of each internal detection part of the electrical automation equipment within the equipment monitoring period. The temperature of each internal detection part of the electrical automation equipment at the end time point of the equipment monitoring period is subtracted from the temperature of the corresponding internal detection part of the electrical automation equipment at the start time point of the equipment monitoring period, and the processing result is averaged with the duration corresponding to the equipment monitoring period, finally obtaining the temperature growth rate of each internal detection part of the electrical automation equipment within the equipment monitoring period. The temperature of each internal detection part of the electrical automation equipment at the end time point of the equipment monitoring period and the temperature of the corresponding internal detection part of the electrical automation equipment at the start time point of the equipment monitoring period can both be measured by temperature sensors.

[0042] The average heat flux density of the surface detection part of the above-mentioned electrical automation equipment within the equipment monitoring period, which represents the average value of the heat flux density of the surface detection part of the equipment within the monitoring period. The heat flux density refers to the amount of heat passing through a unit area per unit time and can be measured by a heat flux density sensor; the power density of the above-mentioned electrical automation equipment within the equipment monitoring period, which represents the average output power per unit volume of the electrical automation equipment within the equipment monitoring period. The volume of the electrical automation equipment can be obtained from the specification manual, and the average output power of the electrical automation equipment within the equipment monitoring period can be measured by a power meter. Dividing the average output power of the electrical automation equipment within the equipment monitoring period by the volume of the electrical automation equipment gives the power density of the electrical automation equipment within the equipment monitoring period.

[0043] The temperature growth rates of each internal detection part of the electrical automation equipment within the equipment monitoring period are averaged to obtain the average temperature growth rate of the internal detection parts of the electrical automation equipment within the equipment monitoring period, which represents the average value of the temperature growth rates of the internal detection parts of the electrical automation equipment within the equipment monitoring period.

[0044] According to the power density of the electrical automation equipment during the equipment monitoring period, match the reference average temperature growth rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period from the electrical database. Perform difference and absolute value processing on the reference average temperature growth rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period and the average temperature growth rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period in sequence. Process the processing result by taking the ratio with the reference average temperature growth rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period, and finally obtain the temperature growth deviation rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period; the specific matching process of the reference average temperature growth rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period is as follows: the electrical database stores the reference average temperature of the internal detection part corresponding to each power density interval during the equipment monitoring period. Query the power density interval stored in the electrical database to which the power density of the electrical automation equipment belongs during the equipment monitoring period. The reference average temperature of the internal detection part corresponding to this power density interval during the equipment monitoring period is the reference average temperature growth rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period; the temperature growth deviation rate of the internal detection part to which the electrical automation equipment belongs during the equipment monitoring period is used to quantify the abnormal degree of temperature growth of the internal detection part of the electrical automation equipment during the equipment monitoring period.

[0045] According to the average temperature growth rate of the internal detection part of the electrical automation equipment during the equipment monitoring period, match the reference temperature growth rate of the surface detection part of the electrical automation equipment during the equipment monitoring period from the electrical database. Perform difference and absolute value processing on the temperature growth rate of the surface detection part of the electrical automation equipment during the equipment monitoring period and the reference temperature growth rate of the surface detection part of the electrical automation equipment during the equipment monitoring period in sequence. Process the processing result by taking the ratio with the reference temperature growth rate of the surface detection part of the electrical automation equipment during the equipment monitoring period, and finally obtain the temperature growth deviation rate of the surface detection part of the electrical automation equipment during the equipment monitoring period. The specific matching process of the above-mentioned reference temperature growth rate of the surface detection part of the electrical automation equipment during the equipment monitoring period is as follows: The electrical database stores the reference temperature growth rate of the surface detection part corresponding to the average temperature growth rate interval of each internal detection part during the equipment monitoring period. Query the average temperature growth rate interval of the internal detection part stored in the electrical database where the average temperature growth rate of the internal detection part of the electrical automation equipment during the equipment monitoring period belongs. The reference temperature growth rate of the surface detection part corresponding to the average temperature growth rate interval of this internal detection part during the equipment monitoring period is the reference temperature growth rate of the surface detection part of the electrical automation equipment during the equipment monitoring period. The above-mentioned temperature growth deviation rate of the surface detection part of the electrical automation equipment during the equipment monitoring period is used to quantify the abnormal degree of temperature growth of the surface detection part of the electrical automation equipment during the equipment monitoring period.

[0046] Comprehensively analyze the heat dissipation efficiency coefficient of the operating environment of the electrical automation equipment, the average temperature of the surface detection part of the electrical automation equipment during the equipment monitoring period, the average temperature of the internal detection part of the electrical automation equipment during the equipment monitoring period, the temperature growth deviation rate of the surface detection part of the electrical automation equipment during the equipment monitoring period, the temperature growth deviation rate of the internal detection part of the electrical automation equipment during the equipment monitoring period, the average heat flux density of the surface detection part of the electrical automation equipment during the equipment monitoring period, and the power density of the electrical automation equipment during the equipment monitoring period to obtain the thermal management anomaly index of the electrical automation equipment. The thermal management anomaly index of the electrical automation equipment is used to comprehensively quantify the abnormal degree of thermal management of the electrical automation equipment.

[0047] Step 3: The control device controls the electrical automation equipment through the operation status parameter control set of the electrical automation equipment. The data collection device collects the operation status parameters of the electrical automation equipment. The data processing device uses the third artificial intelligence method to determine the operation precision factor of the electrical automation equipment, predicts the operation precision level of the electrical automation equipment based on the operation precision factor of the electrical automation equipment, and the feedback device controls and feedbacks the status of the electrical automation equipment based on the operation precision level of the electrical automation equipment.

[0048] The above-mentioned third artificial intelligence method refers to the specific determination method of the operation precision factor of the electrical automation equipment. The above-mentioned control of the electrical automation equipment through the operation status parameter control set of the electrical automation equipment means that the control device packages the operation status parameter control set of the electrical automation equipment into an instruction that the electrical automation equipment can recognize and receive, marks it as the operation status parameter control set instruction of the electrical automation equipment, and sends the operation status parameter control set instruction of the electrical automation equipment to the electrical automation equipment through network transmission. After receiving the operation status parameter control set instruction of the electrical automation equipment, the electrical automation equipment will immediately parse and execute it.

[0049] In a specific embodiment, this method realizes personalized control feedback on the status of the electrical automation equipment by accurately determining the operation precision factor of the electrical automation equipment, effectively avoiding the situation of over-maintenance or under-maintenance, and significantly improving the operation precision of the electrical automation equipment.

[0050] Specifically, the control of the electrical automation equipment through the operation status parameter control set of the electrical automation equipment is specifically as follows: If it is determined that the operation status parameter control set of the preset electrical automation equipment is not optimized, the electrical automation equipment is directly controlled through the operation status parameter control set of the preset electrical automation equipment; if it is determined that the operation status parameter control set of the preset electrical automation equipment is optimized, the optimized operation status parameter control set of the electrical automation equipment is recorded as the operation status parameter control set of the electrical automation equipment updated once, and the electrical automation equipment is controlled through the operation status parameter control set of the electrical automation equipment updated once.

[0051] Specifically, the operation accuracy level of the electrical automation equipment is predicted as follows: The operation accuracy factor of the electrical automation equipment is compared with the first operation accuracy factor range, the second operation accuracy factor range, and the third operation accuracy factor range stored in the electrical database. If the operation accuracy factor of the electrical automation equipment belongs to the first operation accuracy factor range, the operation accuracy level of the electrical automation equipment is predicted to be the first level. If the operation accuracy factor of the electrical automation equipment belongs to the second operation accuracy factor range, the operation accuracy level of the electrical automation equipment is predicted to be the second level. If the operation accuracy factor of the electrical automation equipment belongs to the third operation accuracy factor range, the operation accuracy level of the electrical automation equipment is predicted to be the third level. It should be noted that all the operation accuracy factors corresponding to the first operation accuracy factor range are greater than all the operation accuracy factors corresponding to the second operation accuracy factor range, and all the operation accuracy factors corresponding to the second operation accuracy factor range are greater than all the operation accuracy factors corresponding to the third operation accuracy factor range. In an exemplary embodiment, the first level represents excellent, the second level represents good, and the third level represents poor.

[0052] Specifically, the control feedback on the state of the electrical automation equipment is as follows: If the operation accuracy level of the electrical automation equipment is the first level, the thermal management state parameters of the electrical automation equipment are continuously obtained. If the operation accuracy level of the electrical automation equipment is the second level, the second optimization control set is matched from the electrical database according to the operation accuracy factor of the electrical automation equipment, and the operation state parameter control set of the electrical automation equipment is optimized for the first time to obtain the operation state parameter control set of the electrical automation equipment after the second optimization, and the electrical automation equipment is controlled by the operation state parameter control set of the electrical automation equipment after the second optimization. If the operation accuracy level of the electrical automation equipment is the third level, a warning log is generated for feedback. The specific matching process of the above second optimization control set is as follows: The second optimization control set corresponding to each operation accuracy factor range is stored in the electrical database. Query the operation accuracy factor range in the electrical database to which the operation accuracy factor of the electrical automation equipment belongs, and the second optimization control set corresponding to the operation accuracy factor range in the electrical database to which the operation accuracy factor of the electrical automation equipment belongs is the second optimization control set matched according to the operation accuracy factor of the electrical automation equipment.

[0053] Further, the determination of the operation accuracy factor of the electrical automation equipment is as follows: The operation state parameters of the electrical automation equipment include the action trajectory curves of the electrical automation equipment in each operation monitoring period, the average vibration amplitude of the electrical automation equipment in the operation monitoring period, and the real-time acceleration of the electrical automation equipment in the operation monitoring period. The above operation monitoring period refers to the time period for analyzing the operation accuracy of the electrical automation equipment, and the specific duration is formulated by the equipment administrator. The above action trajectory curve describes the movement path of a preset first position point on the electrical automation equipment in space during the operation monitoring period, usually presented in the form of a curve graph, which can intuitively reflect the movement law, speed change, and possible errors of the electrical automation equipment. A position sensor (such as a laser rangefinder or an optical sensor, etc.) is installed at the preset first position point of the electrical automation equipment to record the movement position of the electrical automation equipment in real time. The position data collected by the position sensor is imported into data analysis software (such as MATLAB), and the action trajectory curve of the robotic arm is obtained through curve processing. Among them, recording a complete movement process of the electrical automation equipment from the starting position point to the ending position point can be expressed as an action trajectory curve of the electrical automation equipment in the operation monitoring period. Recording a complete movement process of the electrical automation equipment from the ending position point to the starting position point can also be expressed as an action trajectory curve of the electrical automation equipment in the operation monitoring period. If the action trajectory curve is incomplete, this action trajectory curve may not be included in the subsequent analysis. The starting position point represents the static position point of the preset first position point before the electrical automation equipment starts to execute a certain action or task, and the ending position point represents the target position point that the preset first position point should reach after the electrical automation equipment completes a specific action or task. Both the starting position point and the ending position point are marked by the user of the electrical automation equipment. The above average vibration amplitude represents the average level of the vibration amplitude of the electrical automation equipment in the operation monitoring period, which can be monitored by a vibration sensor installed by the equipment administrator, and the unit is millimeter. The above real-time acceleration represents the acceleration of a preset second position point on the electrical automation equipment at any moment during the operation monitoring period, which can be measured by an acceleration sensor.

[0054] Both the above preset first position point and the preset second position point are formulated by the equipment administrator. The preset first position point needs to be able to reflect the movement law of the electrical automation equipment. The first position point should be located on the moving parts of the electrical automation equipment, and its movement state can represent or reflect the typical movement characteristics of the electrical automation equipment. The preset second position point needs to be able to reflect the acceleration law of the electrical automation equipment. The second position point may be located at the joints of the electrical automation equipment, the ends of the moving parts, or other key positions, so as to deeply understand the dynamic performance of the electrical automation equipment by measuring the acceleration of the second position point.

[0055] Extract the reference action trajectory curve of the electrical automation equipment from the electrical database, and compare the action trajectory curves of the electrical automation equipment during the operation monitoring period with the reference action trajectory curve of the electrical automation equipment. Comprehensively obtain the deviation value of the action trajectory curve of the electrical automation equipment during the operation monitoring period, which is used to quantify the deviation degree of the action trajectory curve of the electrical automation equipment during the operation monitoring period relative to the reference action trajectory curve. The specific acquisition method is as follows: Output the action trajectory curves of the electrical automation equipment during the operation monitoring period and the reference action trajectory curve of the electrical automation equipment to data processing software (such as MATLAB). Through the data processing software, compare each position point on the action trajectory curves of the electrical automation equipment during the operation monitoring period with the corresponding position point on the reference action trajectory curve of the electrical automation equipment in sequence, calculate the shortest straight-line distance between each position point on the action trajectory curves of the electrical automation equipment during the operation monitoring period and the corresponding position point on the reference action trajectory curve of the electrical automation equipment, obtain the deviation distance of each position point of the action trajectory curves of the electrical automation equipment during the operation monitoring period, integrate all the deviation distances in the deviation distances of each position point of the action trajectory curves of the electrical automation equipment during the operation monitoring period, and perform accumulation to obtain the deviation value of the action trajectory curve of the electrical automation equipment during the operation monitoring period.

[0056] Perform standard deviation processing on the real-time operation acceleration of the electrical automation equipment during the operation monitoring period to obtain the operation acceleration fluctuation value of the electrical automation equipment during the operation monitoring period, which is used to quantify the operation acceleration fluctuation degree of the electrical automation equipment during the operation monitoring period.

[0057] Comprehensively determine the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs, the thermal management abnormal index of the electrical automation equipment, the deviation value of the action trajectory curve of the electrical automation equipment during the operation monitoring period, the average vibration amplitude of the electrical automation equipment during the operation monitoring period, and the operation acceleration fluctuation value of the electrical automation equipment during the operation monitoring period to obtain the operation precision factor of the electrical automation equipment. The operation precision factor of the electrical automation equipment is used to comprehensively quantify the operation precision degree of the electrical automation equipment.

[0058] The specific determination method of the operation precision factor of the electrical automation equipment is as follows: ; ; In the formula, is the operation precision factor of the electrical automation equipment, is the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs, is the preset reference heat dissipation efficiency coefficient in the electrical database, is the thermal management anomaly index of the electrical automation device, is the operation precision index of the electrical automation device, is the weight of the heat dissipation efficiency coefficient preset in the electrical database, is the weight of the thermal management anomaly index preset in the electrical database, is the weight of the operation precision index preset in the electrical database, is the deviation value of the action trajectory curve of the electrical automation device during the operation monitoring period, is the average vibration amplitude of the electrical automation device during the operation monitoring period, is the operation acceleration fluctuation value of the electrical automation device during the operation monitoring period, is the defined action trajectory curve deviation value preset in the electrical database, is the defined average vibration amplitude preset in the electrical database, is the defined operation acceleration fluctuation value preset in the electrical database, is the influence coefficient of the action trajectory curve deviation value preset in the electrical database, is the influence coefficient of the average vibration amplitude preset in the electrical database, is the influence coefficient of the operation acceleration fluctuation value preset in the electrical database.

[0059] The above-mentioned operation precision index of the electrical automation device is used to quantify the operation precision of the electrical automation device itself and is part of the operation precision factor of the electrical automation device.

[0060] The above-mentioned weight of the heat dissipation efficiency coefficient represents the proportion of the heat dissipation efficiency coefficient in the operation precision factor; the above-mentioned weight of the thermal management anomaly index represents the proportion of the thermal management anomaly index in the operation precision factor; the above-mentioned weight of the operation precision index represents the proportion of the operation precision index in the operation precision factor. The electrical database stores the corresponding relationships between the heat dissipation efficiency coefficient and its corresponding weight, the thermal management anomaly index and its corresponding weight, and the operation precision index and its corresponding weight. For example, when the heat dissipation efficiency coefficient, the thermal management anomaly index, and the operation precision index are input into the electrical database, the electrical database can match the weights of the heat dissipation efficiency coefficient, the thermal management anomaly index, and the operation precision index, and their value ranges are all between 0 and 1.

[0061] The above-mentioned influence coefficient of the action trajectory curve deviation value represents the value of the influence degree of the unit value of the action trajectory curve deviation value on the operation precision index; the above-mentioned influence coefficient of the average vibration amplitude represents the value of the influence degree of the unit value of the average vibration amplitude on the operation precision index; the above-mentioned influence coefficient of the operation acceleration fluctuation value represents the value of the influence degree of the unit value of the operation acceleration fluctuation value on the operation precision index. The electrical database stores the corresponding relationships between the action trajectory curve deviation value and its corresponding influence coefficient, the average vibration amplitude and its corresponding influence coefficient, and the operation acceleration fluctuation value and its corresponding influence coefficient. For example, when the action trajectory curve deviation value, the average vibration amplitude, and the operation acceleration fluctuation value are input into the electrical database, the electrical database can match the influence coefficient of the action trajectory curve deviation value, the influence coefficient of the average vibration amplitude, and the influence coefficient of the operation acceleration fluctuation value, and their value ranges are all between 0 and 1.

[0062] The above-defined action trajectory curve deviation value represents the maximum allowable value of the action trajectory curve deviation value of the electrical automation equipment during the operation monitoring period; the above-defined average vibration amplitude represents the maximum allowable value of the average vibration amplitude of the electrical automation equipment during the operation monitoring period; the above-defined operation acceleration fluctuation value represents the maximum allowable value of the operation acceleration fluctuation value of the electrical automation equipment during the operation monitoring period.

[0063] It should be noted that when the heat dissipation efficiency coefficient of the operating environment where the electrical automation equipment is located significantly deviates from its preset reference value, the thermal management system of the electrical automation equipment will be significantly affected by the environment and then present an abnormal state. This abnormal state is specifically manifested as a significant increase in the abnormal level of the thermal management of the electrical automation equipment. The abnormality of the thermal management will directly affect the normal working conditions of each component inside the electrical automation equipment. Under normal circumstances, these components can maintain stable performance and expected functions within a specific temperature range. However, once the thermal management is abnormal, the working environment temperature of the components inside the electrical automation equipment will deviate from the optimal range, resulting in a decline in component performance and even possible failures. Therefore, by comprehensively analyzing the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs, the thermal management abnormal index of the electrical automation equipment, and the operation precision index of the electrical automation equipment, the operation precision of the electrical automation equipment and the key factors affecting the operation precision of the electrical automation equipment can be accurately identified.

[0064] It should also be explained that if the average vibration amplitude of the electrical automation equipment shows an upward trend, this usually means that the vibration state of the electrical automation equipment exceeds the normal range, manifested as too large a vibration amplitude. Such an abnormal vibration state will directly affect the motion stability and accuracy of the electrical automation equipment. Specifically, excessive vibration will cause the deviation value of the action trajectory curve to increase when the electrical automation equipment performs tasks. This is because the vibration will interfere with the motion control of the electrical automation equipment, causing a deviation between the actual motion trajectory and the expected trajectory of the electrical automation equipment, thus resulting in the problem of discontinuous motion. At the same time, the increase in the average vibration amplitude will also lead to an increase in the fluctuation value of the operating acceleration. Under the influence of vibration, the acceleration sensor of the electrical automation equipment will detect frequent acceleration changes, indicating that the dynamic performance of the electrical automation equipment has been affected. The fluctuation of acceleration will not only affect the motion smoothness of the electrical automation equipment, but may also cause additional stress on the mechanical structure and electronic components of the electrical automation equipment, accelerating their aging and wear. Therefore, by comprehensively analyzing these three parameters: the average vibration amplitude, the deviation value of the action trajectory curve, and the fluctuation value of the operating acceleration, the operating precision status of the electrical automation equipment itself can be evaluated.

[0065] In a specific embodiment, the present invention provides a method for predicting the state of an electrical automation equipment based on artificial intelligence. By accurately collecting and analyzing the operating environment parameters of the equipment, this method can evaluate the heat dissipation efficiency in real time, effectively monitor the thermal management state of the electrical automation equipment, use advanced artificial intelligence algorithms to quickly identify thermal management anomalies, and timely warn of potential faults, thus greatly shortening the time window for equipment maintenance and reducing the risk of production interruption of the electrical automation equipment caused by sudden failures. In addition, through the intelligent analysis of the operating state parameters of the electrical automation equipment, the control strategy can be dynamically optimized to ensure that the electrical automation equipment is in the best operating state. At the same time, it can accurately predict the operating precision level of the electrical automation equipment, providing a scientific basis for precise control and further improving the operating precision of the electrical automation equipment. This method not only significantly enhances the reliability and stability of the electrical automation equipment, but also realizes the efficient automation management of the electrical automation equipment through an intelligent prediction and control feedback mechanism.

[0066] In the second aspect of the present invention, a state prediction device for electrical automation equipment based on artificial intelligence is provided, including: a data collection device, a data processing device, a control device, and a feedback device; the data collection device is used to collect the operating environment parameters of the electrical automation equipment, obtain the thermal management state parameters of the electrical automation equipment, and collect the operating state parameters of the electrical automation equipment; the data processing device is used to evaluate the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs by using the first artificial intelligence method, analyze the thermal management anomaly index of the electrical automation equipment by using the second artificial intelligence method, and determine the operating precision factor of the electrical automation equipment by using the third artificial intelligence method; the control device is used to control the electrical automation equipment through the operating state parameter control set of the electrical automation equipment; the feedback device is used to perform control feedback on the state of the electrical automation equipment based on the operating precision level of the electrical automation equipment.

[0067] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of the present technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A method for predicting the state of electrical automation equipment based on artificial intelligence, characterized in that Including: Step 1: The data collection device collects the operating environment parameters of the electrical automation equipment, and the data processing device uses the first artificial intelligence method to evaluate the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs. Step 2: The data collection device obtains the thermal management status parameters of the electrical automation equipment, and the data processing device uses the second artificial intelligence method to analyze the thermal management anomaly index of the electrical automation equipment. Based on the thermal management anomaly index of the electrical automation equipment, it is determined whether to optimize the preset control set of the operating status parameters of the electrical automation equipment. Step 3: The control device controls the electrical automation equipment through the control set of the operating status parameters of the electrical automation equipment. The data collection device collects the operating status parameters of the electrical automation equipment. The data processing device uses the third artificial intelligence method to determine the operating accuracy factor of the electrical automation equipment. Based on the operating accuracy factor of the electrical automation equipment, the operating accuracy level of the electrical automation equipment is predicted. The feedback device performs control feedback on the status of the electrical automation equipment based on the operating accuracy level of the electrical automation equipment.

2. The method for predicting the state of an electrical automation device based on artificial intelligence according to claim 1, wherein: The specific evaluation process of the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs is as follows: The operating environment parameters of the electrical automation equipment include the average temperature of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, the average air flow velocity of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, and the average thermal radiation intensity of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period. Obtain the average temperature of the surface detection part to which the electrical automation equipment belongs during the environmental monitoring period, and perform a difference process with the average temperature of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period. The processing result is subjected to a ratio process with the average temperature of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, and finally the heat dissipation efficiency value of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period is obtained. Comprehensively evaluate the heat dissipation efficiency value of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, the average air flow velocity of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, and the average thermal radiation intensity of the operating environment to which the electrical automation equipment belongs during the environmental monitoring period, and obtain the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs. The heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs is used to comprehensively quantify the heat dissipation capacity of the operating environment to which the electrical automation equipment belongs.

3. The method for predicting the state of an electrical automation device based on artificial intelligence according to claim 1, wherein: The specific analysis process of the thermal management anomaly index of the electrical automation equipment is as follows: The thermal management status parameters of the electrical automation equipment include the average temperature of the surface detection parts of the electrical automation equipment during the equipment monitoring period, the average temperature of the internal detection parts of the electrical automation equipment during the equipment monitoring period, the temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period, the temperature growth rates of the respective internal detection parts of the electrical automation equipment during the equipment monitoring period, the average heat flux density of the surface detection parts of the electrical automation equipment during the equipment monitoring period, and the power density of the electrical automation equipment during the equipment monitoring period; The temperature growth rates of the respective internal detection parts of the electrical automation equipment during the equipment monitoring period are averaged to obtain the average temperature growth rate of the internal detection parts of the electrical automation equipment during the equipment monitoring period; According to the power density of the electrical automation equipment during the equipment monitoring period, the reference average temperature growth rate of the internal detection parts of the electrical automation equipment during the equipment monitoring period is matched from the electrical database. The difference and absolute value processing are sequentially performed on the reference average temperature growth rate of the internal detection parts of the electrical automation equipment during the equipment monitoring period and the average temperature growth rate of the internal detection parts of the electrical automation equipment during the equipment monitoring period. The processing result is ratio-processed with the reference average temperature growth rate of the internal detection parts of the electrical automation equipment during the equipment monitoring period to finally obtain the temperature growth deviation rate of the internal detection parts of the electrical automation equipment during the equipment monitoring period; According to the average temperature growth rate of the internal detection parts of the electrical automation equipment during the equipment monitoring period, the reference temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period is matched from the electrical database. The difference and absolute value processing are sequentially performed on the temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period and the reference temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period. The processing result is ratio-processed with the reference temperature growth rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period to finally obtain the temperature growth deviation rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period; By comprehensively analyzing the heat dissipation efficiency coefficient of the operating environment of the electrical automation equipment, the average temperature of the surface detection parts of the electrical automation equipment during the equipment monitoring period, the average temperature of the internal detection parts of the electrical automation equipment during the equipment monitoring period, the temperature growth deviation rate of the surface detection parts of the electrical automation equipment during the equipment monitoring period, the temperature growth deviation rate of the internal detection parts of the electrical automation equipment during the equipment monitoring period, the average heat flux density of the surface detection parts of the electrical automation equipment during the equipment monitoring period, and the power density of the electrical automation equipment during the equipment monitoring period, the thermal management anomaly index of the electrical automation equipment is obtained. The thermal management anomaly index of the electrical automation equipment is used to comprehensively quantify the degree of thermal management anomaly of the electrical automation equipment.

4. The method for predicting the state of an electrical automation device based on artificial intelligence according to claim 1, characterized in that: The first artificial intelligence method represents a specific evaluation method for the heat dissipation efficiency coefficient of the operating environment to which the electrical automation device belongs; The second artificial intelligence method represents a specific analysis method for the thermal management anomaly index of the electrical automation device; The third artificial intelligence method represents a specific determination method for the operation accuracy factor of the electrical automation device.

5. The method for predicting the state of an electrical automation device based on artificial intelligence according to claim 1, wherein: The determination of whether to optimize the preset control set of the operating state parameters of the electrical automation device is as follows: Extract the thermal management anomaly threshold of the electrical automation device from the electrical database and compare it with the thermal management anomaly index of the electrical automation device. If the thermal management anomaly index of the electrical automation device is less than or equal to the thermal management anomaly threshold of the electrical automation device, it is determined not to optimize the preset control set of the operating state parameters of the electrical automation device; If the thermal management anomaly index of the electrical automation device is greater than the thermal management anomaly threshold of the electrical automation device, it is determined to optimize the preset control set of the operating state parameters of the electrical automation device. The specific optimization process is as follows: Compare the temperature coefficient of the electrical automation device with the reference temperature coefficient to obtain a comparison result. Based on the comparison result, match the first optimization control set from the electrical database, and update the preset control set of the operating state parameters of the electrical automation device once to obtain the once-updated control set of the operating state parameters of the electrical automation device.

6. The method for predicting the state of an electrical automation device based on artificial intelligence according to claim 1, wherein: The control of the electrical automation device through the control set of the operating state parameters of the electrical automation device is as follows: If it is determined not to optimize the preset control set of the operating state parameters of the electrical automation device, directly control the electrical automation device through the preset control set of the operating state parameters of the electrical automation device; If it is determined to optimize the preset control set of the operating state parameters of the electrical automation device, record the optimized control set of the operating state parameters of the electrical automation device as the once-updated control set of the operating state parameters of the electrical automation device, and control the electrical automation device through the once-updated control set of the operating state parameters of the electrical automation device.

7. The method for predicting the state of an electrical automation device based on artificial intelligence according to claim 1, characterized in that: The determination of the operation accuracy factor of the electrical automation device is as follows: The operating state parameters of the electrical automation device include the action trajectory curves of each time within the operation monitoring period of the electrical automation device, the average vibration amplitude of the electrical automation device within the operation monitoring period, and the real-time acceleration of the electrical automation device within the operation monitoring period; Extract the reference action trajectory curve of the electrical automation device from the electrical database, and perform a coincidence comparison between the action trajectory curves of each time within the operation monitoring period of the electrical automation device and the reference action trajectory curve of the electrical automation device to comprehensively obtain the action trajectory curve deviation value of the electrical automation device within the operation monitoring period; Perform standard deviation processing on the real-time operation acceleration of the electrical automation device within the operation monitoring period to obtain the operation acceleration fluctuation value of the electrical automation device within the operation monitoring period; Comprehensively determine the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs, the thermal management anomaly index of the electrical automation equipment, the deviation value of the action trajectory curve of the electrical automation equipment within the operation monitoring period, the average vibration amplitude of the electrical automation equipment within the operation monitoring period, and the operation acceleration fluctuation value of the electrical automation equipment within the operation monitoring period, and obtain the operation precision factor of the electrical automation equipment. The operation precision factor of the electrical automation equipment is used to comprehensively quantify the operation accuracy of the electrical automation equipment.

8. The method for predicting the state of an electrical automation device based on artificial intelligence according to claim 7, wherein: The operation precision level of the electrical automation equipment is predicted. The specific prediction process is as follows: Compare the operation precision factor of the electrical automation equipment with the first operation precision factor interval, the second operation precision factor interval, and the third operation precision factor interval stored in the electrical database; If the operation precision factor of the electrical automation equipment belongs to the first operation precision factor interval, it is predicted that the operation precision level of the electrical automation equipment is the first level; If the operation precision factor of the electrical automation equipment belongs to the second operation precision factor interval, it is predicted that the operation precision level of the electrical automation equipment is the second level; If the operation precision factor of the electrical automation equipment belongs to the third operation precision factor interval, it is predicted that the operation precision level of the electrical automation equipment is the third level.

9. The method for predicting the state of an electrical automation device based on artificial intelligence according to claim 5, wherein: The control feedback on the state of the electrical automation equipment is as follows. The specific control feedback process is as follows: If the operation precision level of the electrical automation equipment is the first level, continuously obtain the thermal management state parameters of the electrical automation equipment; If the operation precision level of the electrical automation equipment is the second level, match the second optimization control set from the electrical database according to the operation precision factor of the electrical automation equipment, and optimize the control set of the operation state parameters of the electrical automation equipment updated once to obtain the control set of the operation state parameters of the electrical automation equipment updated twice, and control the electrical automation equipment through the control set of the operation state parameters of the electrical automation equipment updated twice; If the operation precision level of the electrical automation equipment is the third level, generate a warning log for feedback.

10. An apparatus applying the method for predicting the state of an electrical automation device based on artificial intelligence according to any one of claims 1-9, characterized in that: It includes: A data collection device, a data processing device, a control device, and a feedback device; The data collection device is used to collect the operation environment parameters of the electrical automation equipment, obtain the thermal management state parameters of the electrical automation equipment, and collect the operation state parameters of the electrical automation equipment; The data processing device is used to evaluate the heat dissipation efficiency coefficient of the operating environment to which the electrical automation equipment belongs by using the first artificial intelligence method, analyze the thermal management anomaly index of the electrical automation equipment by using the second artificial intelligence method, and determine the operation precision factor of the electrical automation equipment by using the third artificial intelligence method; The control device is used to control the electrical automation equipment through the control set of the operation state parameters of the electrical automation equipment; The feedback device is used to perform control feedback on the state of the electrical automation equipment based on the operation precision level of the electrical automation equipment.

Images