Industrial electromechanical equipment management and control method and system based on artificial intelligence

Abstract

The invention discloses an artificial intelligence-based industrial electromechanical equipment management and control method and system, and particularly relates to the technical field of equipment management and control, and the method comprises the steps: collecting the operation data of industrial electromechanical equipment through a sensor and a monitoring system, and extracting the characteristics of the operation data of the industrial electromechanical equipment; performing fault diagnosis on each industrial electromechanical device by using an artificial intelligence algorithm based on the extracted features, determining a standby device of the industrial electromechanical device having the fault according to the industrial electromechanical device having the fault, and collecting historical information of the standby device according to the relative amplitude of the operation data of the standby device and the fault record of the standby device, according to records detected by the artificial intelligence algorithm of the standby equipment, confusion matrix indexes of the standby equipment are determined, artificial intelligence training information of the standby equipment is collected, and the matching degree of the standby equipment and the fault equipment is quantified. According to the method, the starting opportunity of the standby equipment can be optimized, and the minimum downtime of equipment switching in the production process is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and more specifically, to an industrial electromechanical equipment control method and system based on artificial intelligence. Background Art

[0002] During the operation and maintenance of industrial electromechanical equipment, equipment failures are a common and inevitable problem. Since equipment failures may lead to production interruptions, output value losses, and safety risks, how to quickly and accurately diagnose equipment failures and replace faulty equipment in a timely manner has become a key issue in the field of industrial automation. With the increase in the complexity and quantity of industrial equipment, traditional equipment management and maintenance methods can no longer meet the needs of modern industry;

[0003] Traditional equipment fault diagnosis relies on manual experience and rule reasoning, which has great limitations. This method is not only inefficient but also less accurate. Especially when facing complex and variable fault situations, misdiagnosis or missed diagnosis is likely to occur. In addition, it is also difficult to select and match standby equipment, especially when the number of standby equipment is limited. Therefore, it is not easy to achieve rapid response to equipment failures and automatic switching of standby equipment.

[0004] To solve the above defects, a technical solution is provided now. Summary of the Invention

[0005] In order to overcome the above defects of the prior art, embodiments of the present invention provide an industrial electromechanical equipment control method and system based on artificial intelligence to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An industrial electromechanical equipment control method based on artificial intelligence, comprising the following steps:

[0008] S1: Collect the operation data of industrial electromechanical equipment through sensors and a monitoring system, extract the characteristics of the operation data of industrial electromechanical equipment, and use an artificial intelligence algorithm to diagnose faults for each industrial electromechanical equipment based on the extracted characteristics;

[0009] S2: According to the industrial electromechanical equipment with faults, determine the standby equipment for the industrial electromechanical equipment with faults, and collect the historical information of the standby equipment according to the relative amplitude of the operation data of the standby equipment and the fault records of the standby equipment;

[0010] S3: According to the records of the standby equipment detected by the artificial intelligence algorithm, determine the confusion matrix index of the standby equipment, and collect the artificial intelligence training information of the standby equipment;

[0011] S4: Comprehensively analyze the historical information and artificial intelligence training information of the standby device, and quantify the matching degree between the standby device and the faulty device.

[0012] In a preferred embodiment, collect the historical information of the standby device, including:

[0013] Represent the historical information of the standby device through the relative fluctuation matching coefficient of features and the fault record performance coefficient;

[0014] The acquisition logic of the relative fluctuation matching coefficient of features is as follows: Determine the average value, maximum value, and minimum value of the operation feature data when the faulty industrial electromechanical equipment is working normally, the relative amplitude of the operation feature data when the faulty industrial electromechanical equipment is working normally, and mark the relative amplitude of the operation feature data when the faulty industrial electromechanical equipment is working normally as: fd n ; where N, N is a positive integer, n is the number of the operation feature data of the faulty industrial electromechanical equipment, is the maximum value of the operation feature data, is the minimum value of the operation feature data, is the average value of the operation feature data;

[0015] By performing maximum-minimum normalization on the relative amplitude of the operation feature data when the faulty industrial electromechanical equipment is working normally, represent the normalized relative amplitude of the operation feature data when the faulty industrial electromechanical equipment is working normally as a vector: GZ = [FD 1 , FD 2 , FD 3 , ……, FD N , determine the relative amplitude of the standby device, and by normalizing the relative amplitude of the standby device, represent the normalized relative amplitude of the standby device as a vector: where i = 1, 2, 3, ……, I, I is a positive integer, and i is the number of the standby device;

[0016] Calculate the relative fluctuation matching coefficient of features, and the calculation formula is: where, TZ i is the relative fluctuation matching coefficient of features of the i-th standby device, is the element in the n-th relative amplitude vector of the i-th standby device after normalization, and FDn is the element of the relative amplitude of the n-th operation feature data when the faulty industrial electromechanical equipment is working normally after normalization.

[0017] In a preferred embodiment, the acquisition logic of the fault record performance coefficient is as follows:

[0018] According to the historical failure repair records of standby devices, obtain the number of times of failure repair of standby devices, and mark the number of times of failure repair of standby devices as: CS i , obtain the historical operation duration of standby devices, and mark the historical operation duration of standby devices as: SC i , obtain the average value of the number of times of repair of all standby devices, and mark the average value of the number of times of repair of all standby devices as: CS, obtain the average historical operation duration of all standby devices, and mark the average historical operation duration of all standby devices as: SC;

[0019] Calculate the failure record performance coefficient, and the calculation formula is: Among them, BX i is the failure record performance coefficient.

[0020] In a preferred embodiment, collect the artificial intelligence training information of standby devices, including:

[0021] The acquisition logic of the failure recognition accuracy coefficient is: based on the usage history records of standby devices, determine the number of true positive cases detected by the artificial intelligence algorithm for standby devices, and mark the number of true positive cases detected by the artificial intelligence algorithm for standby devices as: TP i , determine the number of true negative cases detected by the artificial intelligence algorithm for standby devices, and mark the number of true negative cases detected by the artificial intelligence algorithm for standby devices as: TN i , determine the number of false positive cases detected by the artificial intelligence algorithm for standby devices, and mark the number of false positive cases detected by the artificial intelligence algorithm for standby devices as: FP i , determine the number of false negative cases detected by the artificial intelligence algorithm for standby devices, and mark the number of false negative cases detected by the artificial intelligence algorithm for standby devices as: FN i

[0022] Calculate the failure recognition accuracy coefficient, and the calculation formula is: Among them, JZ i is the failure recognition accuracy coefficient.

[0023] In a preferred embodiment, comprehensively analyze the historical information and artificial intelligence training information of standby devices, including:

[0024] Comprehensively analyze the feature relative fluctuation matching coefficient, the failure record performance coefficient and the failure recognition accuracy coefficient, and generate a standby device evaluation coefficient. The calculation formula is: Among them, pg i is the standby device evaluation coefficient of the i-th standby device, α 1 , α 2 , α 3Proportionality coefficients which are the characteristic relative fluctuation matching coefficient, the fault record performance coefficient, and the fault identification accuracy coefficient, respectively, α 1 and α 2 and α 3 are all greater than 0.

[0025] In a preferred embodiment, quantifying the matching degree between the standby device and the faulty device includes:

[0026] Set the standby device evaluation coefficient threshold, compare the standby device evaluation coefficient of each standby device with the standby device evaluation coefficient threshold. If the standby device evaluation coefficient of the standby device is greater than the standby device evaluation coefficient threshold, generate a warning signal. If the standby device evaluation coefficient of the standby device is less than the standby device evaluation coefficient threshold, generate a passing signal. Sort the standby device evaluation coefficients of the standby devices with passing signals from largest to smallest, and use the standby device with the highest ranking as the replacement device.

[0027] In a preferred embodiment, an industrial electromechanical equipment control system based on artificial intelligence includes a fault judgment module, a standby device acquisition module, a data acquisition module, an evaluation module, and a signal generation module, with signal connections between the modules;

[0028] The fault judgment module is used to collect the real-time operation data of industrial electromechanical equipment through sensors and monitoring systems, and diagnose potential faults of industrial electromechanical equipment;

[0029] The standby device acquisition module is used to determine the standby device of the faulty industrial electromechanical equipment according to the faulty industrial electromechanical equipment;

[0030] The data acquisition module is used to collect historical data of the standby device and analyze it according to the collected data to obtain historical information and artificial intelligence training information of the standby device;

[0031] The evaluation module is used to comprehensively analyze the historical information and artificial intelligence training information of the standby device to quantify the compatibility between the standby device and the faulty device;

[0032] The signal generation module is used to generate a signal for starting the standby device according to the selection priority of the standby device to guide the switching operation of the device.

[0033] The technical effects and advantages of the present invention:

[0034] The present invention integrates sensors and a monitoring system to monitor the operating status of industrial electromechanical equipment in real time, extracts relevant operating characteristics, and uses advanced artificial intelligence algorithms such as deep learning, support vector machine (SVM), and decision tree, combined with historical equipment data for fault diagnosis to determine the industrial electromechanical equipment with faults. By combining the historical data and fault records of standby equipment, the most suitable standby equipment is intelligently selected to ensure that the standby equipment can replace the faulty equipment as soon as possible and maintain the stability of the production process. The present invention helps to optimize the timing of enabling standby equipment and ensure the minimum downtime for equipment switching during the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0036] Figure 1 It is a schematic flow chart of a method for controlling industrial electromechanical equipment based on artificial intelligence according to the present invention;

[0037] Figure 2 It is a schematic structural diagram of a system for controlling industrial electromechanical equipment based on artificial intelligence according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with 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 of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0039] Embodiment 1

[0040] Figure 1 A schematic flow chart of a method for controlling industrial electromechanical equipment based on artificial intelligence is given, which specifically includes the following steps:

[0041] S1: Collect the operating data of industrial electromechanical equipment through sensors and a monitoring system, extract the characteristics of the operating data of industrial electromechanical equipment, and use artificial intelligence algorithms to perform fault diagnosis on each industrial electromechanical equipment based on the extracted characteristics;

[0042] S2: According to the industrial electromechanical equipment with faults, determine the standby equipment for the industrial electromechanical equipment with faults, and collect the historical information of the standby equipment according to the relative amplitude of the operating data of the standby equipment and the fault records of the standby equipment;

[0043] S3: Determine the confusion matrix index of the standby equipment according to the records of the standby equipment detected by the artificial intelligence algorithm, and collect the artificial intelligence training information of the standby equipment;

[0044] S4: Comprehensively analyze the historical information and AI training information of the standby equipment to quantify the matching degree between the standby equipment and the faulty equipment.

[0045] Industrial electromechanical equipment usually collects the operating data of the equipment through sensors and monitoring systems. Sensor data is the basis for fault diagnosis, predictive maintenance, and optimizing equipment operation. By monitoring various operating states of the equipment in real time, potential fault problems can be detected in a timely manner, thereby improving the reliability of the equipment, reducing downtime, and lowering maintenance costs.

[0046] Collect the operating data of the equipment through sensors and monitoring systems, and transmit the collected data to the central monitoring system through a wireless network or a wired network (such as industrial Ethernet, Modbus, etc. protocols), and store it in the historical database of each industrial electromechanical equipment;

[0047] After preprocessing the transmitted data, such as denoising and normalization, extract the characteristics of the operating data of industrial electromechanical equipment, and perform fault diagnosis on each industrial electromechanical equipment based on the extracted characteristics using machine learning or deep learning algorithms.

[0048] For industrial electromechanical equipment, there are standby equipment to handle equipment failures or maintenance. The standby equipment can replace the original equipment during a failure, and there is a certain degree of compatibility between the standby equipment. When the standby equipment replaces the faulty equipment, it can ensure that the characteristics of the operating data of the industrial electromechanical equipment meet the working conditions, and ensure that no additional risks are added during the actual replacement process.

[0049] When artificial intelligence (AI) algorithms predict faults, the success rate of fault prediction for different standby equipment may vary. The differences are mainly affected by the following factors:

[0050] The working characteristics of the standby equipment (such as workload, working environment, service life, etc.) may be different from those of the faulty equipment, which will affect the prediction accuracy of the AI model. For example:

[0051] Equipment health status: If the standby equipment is in good working condition and has good maintenance records, the AI model can usually accurately predict the possible faults. On the contrary, if there are potential faults or long-term lack of maintenance for the standby equipment, the prediction may be affected.

[0052] Workload differences: The load changes of the standby equipment during operation may be different from those of the faulty equipment. If the operating parameters such as the workload, ambient temperature, and vibration of the standby equipment are significantly different from those of the faulty equipment, the AI algorithm may face higher uncertainty during prediction.

[0053] Degree of equipment aging: The aging status or historical failure situation of standby equipment will affect its reliability, and thus affect the accuracy of the AI failure prediction model. The model usually makes predictions based on the operating history and performance of the equipment. Equipment aging may make it more difficult for the model to predict its future failures.

[0054] Differences in training data: The prediction accuracy of AI algorithms depends on the historical data of the equipment, especially the failure history of the equipment. If the data of the standby equipment is less or varies greatly from that of the failed equipment, the model may not be able to adapt well to the characteristics of the standby equipment. This will result in a lower prediction success rate.

[0055] Differences in equipment type and characteristics: The working characteristics of different standby equipment may result in different failure modes and failure prediction characteristics. If the training data of the AI model mainly comes from failed equipment, and the characteristics and working conditions of the standby equipment are not exactly the same as those of the failed equipment, the success rate of predicting failures may be affected.

[0056] After a failure of a specific industrial electromechanical equipment is located, determine the standby equipment of the industrial electromechanical equipment. To ensure that the failed industrial electromechanical equipment can be replaced in a timely manner and can operate normally after replacement, collect the historical information and artificial intelligence training information of the standby equipment, represent the historical information of the standby equipment through the relative fluctuation matching coefficient of features and the failure record performance coefficient, and represent the artificial intelligence training information through the failure identification precision coefficient.

[0057] The acquisition logic of the relative fluctuation matching coefficient of features is as follows: Determine the average value, maximum value, and minimum value of the operating characteristic data when the failed industrial electromechanical equipment is working normally, and the relative amplitude of the operating characteristic data when the failed industrial electromechanical equipment is working normally, and mark the relative amplitude of the operating characteristic data when the failed industrial electromechanical equipment is working normally as: fd n ; where N, N is a positive integer, n is the number of the operating characteristic data of the failed industrial electromechanical equipment, is the maximum value of the operating characteristic data, is the minimum value of the operating characteristic data, is the average value of the operating characteristic data;

[0058] It should be noted that the operating characteristic data includes data such as power, speed, temperature, and vibration that reflect the operation of industrial electromechanical equipment, and is specifically set by the staff in the professional field according to the type of industrial electromechanical equipment.

[0059] By performing maximum-minimum normalization on the relative amplitude of the operating characteristic data when the failed industrial electromechanical equipment is working normally, represent the relative amplitude of the operating characteristic data when the failed industrial electromechanical equipment is working normally after normalization as a vector: GZ = [FD 1 , FD2 , FD 3 , ……, FD N , determine the relative amplitude of the standby device. By normalizing the relative amplitude of the standby device, the normalized relative amplitude of the standby device is represented as a vector: where \(i = 1, 2, 3, \ldots, I\), \(I\) is a positive integer, and \(i\) is the number of the standby device;

[0060] Calculate the characteristic relative fluctuation matching coefficient. The calculation formula is: where \(TZ\) i is the characteristic relative fluctuation matching coefficient of the \(i\)-th standby device, is the element in the \(n\)-th relative amplitude vector of the \(i\)-th standby device after normalization, and \(FD_n\) is the element of the relative amplitude of the \(n\)-th operating characteristic data when the faulty industrial electromechanical equipment operates normally after normalization.

[0061] As can be seen from the formula, the larger the characteristic relative fluctuation matching coefficient, the greater the deviation between the operating data of the standby device and the faulty device during normal operation. That is, it is possible that the operating data of the faulty device changes within a small range, while the relative amplitude of the operating characteristic data of the standby device may be large, the operating range of the device is limited, and there may be some damages that cause it to be unable to effectively respond to load changes, or even fail to reach the optimal performance. If such a device is replaced with a standby device with a wider operating range, it may lead to performance mismatch, thereby affecting the overall stability and efficiency of the system. That is, the larger the characteristic relative fluctuation matching coefficient, the less likely it is to maintain the same operating performance as the faulty device in the system.

[0062] The acquisition logic of the faulty record performance coefficient is as follows: According to the historical fault repair records of the standby device, obtain the number of times of fault repair of the standby device, and mark the number of times of fault repair of the standby device as: \(CS\) i , obtain the historical operating duration of the standby device, and mark the historical operating duration of the standby device as: \(SC\) i , obtain the average value of the number of times of repair of all standby devices, and mark the average value of the number of times of repair of all standby devices as: \(CS\), obtain the average historical operating duration of all standby devices, and mark the average historical operating duration of all standby devices as: \(SC\);

[0063] Calculate the faulty record performance coefficient. The calculation formula is: where \(BX\) i is the faulty record performance coefficient.

[0064] As can be seen from the formula, the larger the faulty record performance coefficient, the higher the frequency of faults of the standby device per unit time, that is, the lower the reliability of the standby device.

[0065] The acquisition logic of the fault identification accuracy coefficient is as follows: Based on the usage history records of the standby device, determine the number of true positives detected by the artificial intelligence algorithm for the standby device, and mark the number of true positives detected by the artificial intelligence algorithm for the standby device as: TP i , determine the number of true negatives detected by the artificial intelligence algorithm for the standby device, and mark the number of true negatives detected by the artificial intelligence algorithm for the standby device as: TN i , determine the number of false positives detected by the artificial intelligence algorithm for the standby device, and mark the number of false positives detected by the artificial intelligence algorithm for the standby device as: FP i , determine the number of false negatives detected by the artificial intelligence algorithm for the standby device, and mark the number of false negatives detected by the artificial intelligence algorithm for the standby device as: FN i

[0066] It should be noted that the number of true positives, true negatives, false positives, and false negatives of the standby device are obtained through a large number of historical records and tests, which can reflect the adaptability between the faulty device and the artificial intelligence algorithm. The number of true positives of the standby device indicates the number of times that the artificial intelligence algorithm correctly predicts that the standby device has a fault and the standby device actually has a fault. The number of true negatives of the standby device indicates that the algorithm correctly predicts that the standby device is normal and the standby device is indeed normal. The number of false positives of the standby device indicates the number of normal standby devices that the algorithm incorrectly predicts as faulty devices. The number of false negatives of the standby device indicates the number of faulty standby devices that the algorithm incorrectly predicts as normal devices.

[0067] Calculate the fault identification accuracy coefficient, and the calculation formula is: where, JZ i is the fault identification accuracy coefficient.

[0068] It can be seen from the formula that the larger the fault identification accuracy coefficient, the higher the adaptability between the standby device and the artificial intelligence algorithm, that is, the algorithm can more accurately identify faulty devices and effectively recommend or enable appropriate standby devices, thereby reducing production downtime and improving system reliability.

[0069] Conduct a comprehensive analysis of the feature relative fluctuation matching coefficient, the fault record performance coefficient, and the fault identification accuracy coefficient to generate a standby device evaluation coefficient. The calculation formula is: where, pg i is the standby device evaluation coefficient of the i-th standby device, α 1 、α 2 、α 3 are the proportionality coefficients of the feature relative fluctuation matching coefficient, the fault record performance coefficient, and the fault identification accuracy coefficient respectively, α1 and α 2 and α 3 are all greater than 0.

[0070] As can be seen from the formula, the larger the characteristic relative fluctuation matching coefficient and the fault record performance coefficient, the smaller the fault recognition precision coefficient, and the larger the standby equipment evaluation coefficient, indicating that the standby equipment is less likely to replace the faulty equipment. On the contrary, the smaller the characteristic relative fluctuation matching coefficient and the fault record performance coefficient, the larger the fault recognition precision coefficient, and the smaller the standby equipment evaluation coefficient, indicating that the standby equipment is more likely to replace the faulty equipment.

[0071] Set the threshold of the standby equipment evaluation coefficient, and compare the standby equipment evaluation coefficients of each standby equipment with the threshold of the standby equipment evaluation coefficient. If the standby equipment evaluation coefficient of a standby equipment is greater than the threshold of the standby equipment evaluation coefficient, an early warning signal is generated, indicating that the standby equipment cannot replace the faulty equipment. If the standby equipment evaluation coefficient of a standby equipment is less than the threshold of the standby equipment evaluation coefficient, a passing signal is generated, indicating that the standby equipment can replace the faulty equipment. Sort the standby equipment evaluation coefficients of the standby equipment with passing signals from largest to smallest, and use the standby equipment with the highest ranking as the replacement equipment.

[0072] The present invention integrates sensors and a monitoring system to monitor the operating status of industrial electromechanical equipment in real time, extracts relevant operating characteristics, uses advanced artificial intelligence algorithms such as deep learning, support vector machine (SVM), and decision tree, combines historical equipment data for fault diagnosis, determines industrial electromechanical equipment with faults, combines historical data and fault records of standby equipment, and intelligently selects the most suitable standby equipment to ensure that the standby equipment can replace the faulty equipment as soon as possible and maintain the stability of the production process. The present invention helps to optimize the timing of enabling standby equipment and ensure the minimum downtime for equipment switching during production.

[0073] Embodiment 2

[0074] Figure 2 A structural schematic diagram of an industrial electromechanical equipment control system based on artificial intelligence is given, specifically including a fault judgment module, a standby equipment acquisition module, a data acquisition module, an evaluation module, and a signal generation module, with signal connections between the modules;

[0075] The fault judgment module is used to collect real-time operating data of industrial electromechanical equipment through sensors and a monitoring system, and diagnose potential faults of the industrial electromechanical equipment;

[0076] The standby equipment acquisition module is used to determine the standby equipment of the faulty industrial electromechanical equipment according to the faulty industrial electromechanical equipment;

[0077] A data acquisition module, configured to acquire historical data of a standby device, and analyze the acquired data to obtain historical information of the standby device and artificial intelligence training information;

[0078] An evaluation module, configured to comprehensively analyze the historical information of the standby device and the artificial intelligence training information to quantify the adaptability between the standby device and the faulty device;

[0079] A signal generation module, configured to generate a signal for starting the standby device according to the selection priority of the standby device to guide the switching operation of the device.

[0080] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0081] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a server, or a data center to another website, a computer, a server, or a data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0082] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0083] Those of ordinary skill in the art will appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0084] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0085] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings, direct couplings, or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0086] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0087] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An industrial electromechanical equipment control method based on artificial intelligence, characterized in that: The following steps are involved: S1: Collect the operating data of industrial electromechanical equipment through sensors and monitoring systems, extract the characteristics of the operating data of industrial electromechanical equipment, and use artificial intelligence algorithms to diagnose faults of various industrial electromechanical equipment based on the extracted characteristics; S2: Determine the backup equipment of the faulty industrial electromechanical equipment according to the faulty industrial electromechanical equipment, and collect historical information of the backup equipment according to the relative amplitude of the operation data of the backup equipment and the fault record of the backup equipment; S3: Determine the confusion matrix index of the standby device based on the record of the standby device being tested by the artificial intelligence algorithm, and collect the artificial intelligence training information of the standby device; S4: Comprehensively analyze the historical information and artificial intelligence training information of the backup equipment to quantify the matching degree between the backup equipment and the faulty equipment.

2. The method for controlling industrial electromechanical equipment based on artificial intelligence according to claim 1 is characterized in that: Collect historical information of backup devices, including: The historical information of the standby equipment is represented by the characteristic relative fluctuation matching coefficient and the fault record performance coefficient; The acquisition logic of the characteristic relative fluctuation matching coefficient is: determine the average value, maximum value and minimum value of the operating characteristic data of the faulty industrial electromechanical equipment when it is working normally, the relative amplitude of the operating characteristic data of the faulty industrial electromechanical equipment when it is working normally, and mark the relative amplitude of the operating characteristic data of the faulty industrial electromechanical equipment when it is working normally as: fd n ;in, N is a positive integer, n is the number of the operating characteristic data of the faulty industrial electromechanical equipment, is the maximum value of the running characteristic data, is the minimum value of the running characteristic data, is the average value of the running characteristic data; By normalizing the relative amplitude of the operating characteristic data of the faulty industrial electromechanical equipment when it is working normally to the maximum and minimum, the normalized relative amplitude of the operating characteristic data of the faulty industrial electromechanical equipment when it is working normally is expressed by a vector: GZ = [FD1, FD2, FD3, ..., FD N ], determine the relative amplitude of the standby device, and normalize the relative amplitude of the standby device. The normalized relative amplitude of the standby device is expressed as a vector: Wherein, i = 1, 2, 3, ..., I, I is a positive integer, and i is the number of the spare equipment; Calculate the feature relative volatility matching coefficient, the calculation formula is: Among them, TZ i is the characteristic relative fluctuation matching coefficient of the ith backup device, is the element in the normalized nth relative amplitude vector of the ith standby equipment, and FDn is the element in the normalized relative amplitude of the nth operating characteristic data when the faulty industrial electromechanical equipment works normally.

3. The method for controlling industrial electromechanical equipment based on artificial intelligence according to claim 2 is characterized in that: The acquisition logic of the fault record performance coefficient is: According to the historical fault maintenance records of the standby equipment, the number of fault maintenance of the standby equipment is obtained, and the number of fault maintenance of the standby equipment is marked as: CS i , obtain the historical operation time of the standby device, and mark the historical operation time of the standby device as: SC i , obtain the average number of times all standby equipment is repaired, and mark the average number of times all standby equipment is repaired as: CS, obtain the historical average operating time of all standby equipment, and mark the historical average operating time of all standby equipment as: SC; Calculate the fault record performance coefficient using the following formula: Among them, BX i is the fault record performance coefficient.

4. The method for controlling industrial electromechanical equipment based on artificial intelligence according to claim 3 is characterized in that: Collect AI training information for backup devices, including: The logic for obtaining the fault identification accuracy coefficient is as follows: based on the usage history of the standby device, determine the number of true positive cases detected by the standby device through the artificial intelligence algorithm, and mark the number of true positive cases detected by the standby device through the artificial intelligence algorithm as: TP i , determine the number of true negative examples detected by the backup device through the artificial intelligence algorithm, and mark the number of true negative examples detected by the backup device through the artificial intelligence algorithm as: TN i , determine the number of false positives detected by the backup device through the artificial intelligence algorithm, and mark the number of false positives detected by the backup device through the artificial intelligence algorithm as: FP i , determine the number of false negatives detected by the backup device through the artificial intelligence algorithm, and mark the number of false negatives detected by the backup device through the artificial intelligence algorithm as: FN i Calculate the fault identification accuracy coefficient, the calculation formula is: Among them, JZ i is the fault identification accuracy coefficient.

5. The method for controlling industrial electromechanical equipment based on artificial intelligence according to claim 4 is characterized in that: Comprehensively analyze the historical information of backup equipment and artificial intelligence training information, including: The characteristic relative fluctuation matching coefficient, fault record performance coefficient and fault identification accuracy coefficient are comprehensively analyzed to generate the backup equipment evaluation coefficient. The calculation formula is: Among them, pg i is the backup equipment evaluation coefficient of the i-th backup equipment, α1, α2, and α3 are the proportional coefficients of the characteristic relative fluctuation matching coefficient, the fault record performance coefficient, and the fault identification accuracy coefficient, respectively, and α1, α2, and α3 are all greater than 0.

6. The method for controlling industrial electromechanical equipment based on artificial intelligence according to claim 5 is characterized in that , quantify the degree of match between the backup equipment and the failed equipment, including: Set a standby equipment evaluation coefficient threshold, compare the standby equipment evaluation coefficient of each standby equipment with the standby equipment evaluation coefficient threshold, if the standby equipment evaluation coefficient of the standby equipment is greater than the standby equipment evaluation coefficient threshold, generate a warning signal, if the standby equipment evaluation coefficient of the standby equipment is less than the standby equipment evaluation coefficient threshold, generate a pass signal, sort the standby equipment evaluation coefficients of the standby equipment with the pass signal from large to small, and use the standby equipment with the highest sorting as the replacement equipment.

7. An industrial electromechanical equipment management and control system based on artificial intelligence, used to implement an industrial electromechanical equipment management and control method based on artificial intelligence as described in any one of claims 1 to 6, characterized in that: It includes a fault judgment module, a backup equipment acquisition module, a data acquisition module, an evaluation module and a signal generation module, and the signal connections between the modules; Fault diagnosis module, used to collect real-time operation data of industrial electromechanical equipment through sensors and monitoring systems, and diagnose potential faults of industrial electromechanical equipment; A spare equipment acquisition module is used to determine spare equipment for the faulty industrial electromechanical equipment according to the faulty industrial electromechanical equipment; A data collection module is used to collect historical data of the backup equipment and analyze the collected data to obtain historical information of the backup equipment and artificial intelligence training information; An evaluation module is used to comprehensively analyze the historical information of the backup equipment and the AI ​​training information to quantify the compatibility of the backup equipment with the faulty equipment; The signal generation module is used to generate a signal for starting the backup device according to the selection priority of the backup device to guide the switching operation of the device.

Images