A method and system for auxiliary generation of operation and maintenance strategy based on digital twin

Abstract

The present application provides a method and system for auxiliary generation of operation and maintenance strategies based on digital twins, which relates to the field of intelligent operation and maintenance technology of industrial equipment. The method includes: constructing a digital twin model and the initial abnormality index of each collaborative operation device according to the real-time operation data of multiple collaborative operation devices; generating an impact transfer sequence according to the digital twin model; combining the historical operation data and device characteristics of each collaborative operation device, predicting the performance degradation index of each collaborative operation device after a preset time; thereby adjusting the initial abnormality index and generating an abnormality index to be adjusted; determining the impact index according to the impact transfer sequence, adjusting the abnormality index to be adjusted according to the impact index, and generating a target abnormality index; when there is a target device whose target abnormality index is greater than a preset abnormality threshold, generating an operation and maintenance strategy for the target device. The technical effect of the present application is: making the generated operation and maintenance strategy forward-looking, thereby effectively preventing the transmission and spread of abnormal equipment status.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent operation and maintenance of industrial equipment, and specifically to a method and system for auxiliary generation of operation and maintenance strategies based on digital twins. Background Art

[0002] As the intelligence and complexity of industrial equipment continue to increase, the interaction and linkage effects between multiple collaboratively operated devices have put forward higher requirements on the operational reliability and efficiency of the overall system. In actual operation, the degradation of equipment performance, the accumulation of uncertainties, and the complexity of collaborative effects may lead to the transmission and amplification of abnormalities between devices, thereby affecting the normal operation of the entire system. Therefore, how to build an operation and maintenance strategy for collaboratively operated equipment in advance and prevent the transmission and spread of abnormal equipment status in a timely manner has become a technical problem that needs to be solved in the current field of industrial operation and maintenance management.

[0003] In the prior art, the above problems are usually solved based on the monitoring and data analysis methods of a single device, for example, using the real-time operation data and historical operation data of the device to evaluate the health status of the device and predict the performance degradation trend. Although the above method can effectively monitor the status of a single device and formulate an operation and maintenance strategy for a single device, it ignores the correlation between devices, making it impossible to accurately predict the transmission effect of the abnormal status of the device in the system, resulting in the formulated operation and maintenance strategy being unable to prevent the transmission and spread of the abnormal status of the device in a timely manner. Summary of the invention

[0004] The present application provides a method and system for auxiliary generation of operation and maintenance strategies based on digital twins, which are used to make the generated operation and maintenance strategies forward-looking, thereby effectively preventing the transmission and spread of abnormal equipment conditions.

[0005] In the first aspect, the present application provides a method for assisting in generating operation and maintenance strategies based on digital twins, the method comprising: obtaining real-time operation data of multiple collaborative operation devices, constructing digital twin models corresponding to the multiple collaborative operation devices based on the real-time operation data, and generating an initial abnormality index for each of the collaborative operation devices; generating an impact transfer sequence between the collaborative operation devices based on the digital twin model; obtaining historical operation data of each of the collaborative operation devices and device characteristics of each of the collaborative operation devices, and predicting the performance degradation index of each of the collaborative operation devices after a preset period of time by combining the historical operation data and the device characteristics; adjusting the initial abnormality index based on the performance degradation index to generate an abnormality index to be adjusted for each of the collaborative operation devices; determining the impact index between the collaborative operation devices based on the impact transfer sequence, adjusting the abnormality index to be adjusted based on the impact index, and generating a target abnormality index for each of the collaborative operation devices; when there is a target device whose target abnormality index is greater than a preset abnormality threshold, generating an operation and maintenance strategy for the target device, the target device being at least one of the multiple collaborative operation devices.

[0006] By adopting the above technical solution, a digital twin model is constructed by acquiring real-time operation data of collaboratively operated equipment and generating an initial abnormality index. The performance degradation index is predicted by combining the impact transfer sequence, historical operation data and equipment characteristics, and then the abnormality index to be adjusted and the target abnormality index are generated. Finally, an operation and maintenance strategy is generated for the target equipment whose target abnormality index exceeds the preset abnormality threshold. Not only the performance degradation trend of a single device is taken into account, but also the impact transfer effect between devices is combined, so that the generated operation and maintenance strategy is forward-looking, thereby effectively preventing the transmission and spread of abnormal equipment status.

[0007] Optionally, the real-time operation data includes temperature parameters and vibration parameters, and generating an initial abnormality index for each of the collaborative operation devices based on the real-time operation data includes: calculating the temperature difference between the temperature parameters of each of the collaborative operation devices and the standard temperature parameters, and the vibration parameter difference between the vibration parameters and the standard vibration parameters; arithmetically multiplying the temperature difference by a preset temperature weight coefficient to generate a temperature abnormality index for each of the collaborative operation devices, and arithmetically multiplying the vibration parameter difference by a preset vibration weight coefficient to generate a vibration abnormality index for each of the collaborative operation devices; and arithmetically adding the temperature abnormality index and the vibration abnormality index to generate an initial abnormality index for each of the collaborative operation devices.

[0008] By adopting the above technical solution, the differences between the temperature parameters and vibration parameters and their standard values ​​are calculated respectively, and the temperature anomaly index and vibration anomaly index are generated in combination with the corresponding weight coefficients. The two are then arithmetically added to obtain the initial anomaly index. This not only takes into account the influence of the two key operating parameters, temperature and vibration, on the equipment status, but also realizes differentiated processing of the influence degrees of different parameters through the weight coefficients, so that the generated initial anomaly index can more accurately reflect the actual operating status of the equipment.

[0009] Optionally, combining the historical operation data and the device characteristics to predict the performance degradation index of each of the collaborative operation devices after a preset period of time includes: determining the number of historical failures of each of the collaborative operation devices and the average value of the historical failure intervals based on the historical operation data; determining the standard failure interval and standard service life of each of the collaborative operation devices based on the device characteristics; substituting the number of historical failures, the average value of the historical failure intervals, the standard failure interval and the standard service life into a preset formula to predict the performance degradation index of each of the collaborative operation devices after a preset period of time; wherein,

[0010] The preset formula is: ; In the formula, For the The performance degradation index of the coordinated operation equipment, is the weight coefficient of the historical fault impact factor, For the The historical failure times of the coordinated operation equipment, For the The average value of the historical failure interval time of the coordinated operation equipment, For the The historical operating time of the coordinated operation equipment, For the The standard service life of a coordinated operation equipment, is the weight coefficient of the remaining life impact factor, For the preset duration, For the The standard time between failures of the coordinated operation equipment, is the weight coefficient of the factor affecting future degradation trend.

[0011] By adopting the above technical solution, by substituting multi-dimensional parameters such as the number of historical failures, the average value of historical failure intervals, the standard failure interval and the standard service life into the preset formula, and combining the weight coefficients of the historical failure influencing factors, the remaining life influencing factors and the future degradation trend influencing factors, a comprehensive evaluation and prediction of the equipment performance degradation trend is achieved. This not only takes into account the historical operating conditions of the equipment, but also combines the standard life characteristics of the equipment, so that the predicted performance degradation index can more accurately reflect the performance status of the equipment after a preset period of time.

[0012] Optionally, the initial abnormality index is adjusted according to the performance degradation index to generate the abnormality index to be adjusted for each of the collaboratively operated devices, including: matching the performance degradation index with multiple preset intervals to obtain the target interval to which the performance degradation index belongs; obtaining the adjustment coefficient corresponding to the target interval, arithmetically multiplying the adjustment coefficient by the initial abnormality index to generate the abnormality index to be adjusted for each of the collaboratively operated devices.

[0013] By adopting the above technical solution, the target interval is determined by matching the performance degradation index with the preset interval, and the initial abnormal index is adjusted based on the adjustment coefficient corresponding to the target interval to generate the abnormal index to be adjusted, thereby realizing the hierarchical adjustment of the current abnormal state of the equipment, so that the abnormal index to be adjusted can simultaneously reflect the real-time operating status and performance degradation trend of the equipment, thereby improving the accuracy of abnormal state assessment.

[0014] Optionally, determining the influence index between each of the collaboratively operating devices according to the influence transfer sequence includes: determining the upstream and downstream hierarchical relationship between each of the collaboratively operating devices according to the influence transfer sequence; establishing an influence transfer matrix between multiple collaboratively operating devices according to the upstream and downstream hierarchical relationship, wherein the rows of the influence transfer matrix represent upstream devices, the columns of the influence transfer matrix represent downstream devices, and the matrix elements in the influence transfer matrix have a value range of 0 to 1, which is used to characterize the influence intensity of the upstream device on the downstream device; multiplying each of the matrix elements in the influence transfer matrix with a preset hierarchical weight coefficient, and accumulating the multiplication results to obtain the influence index between each of the collaboratively operating devices, and the influence index is used to characterize the degree of association between each of the collaboratively operating devices.

[0015] By adopting the above technical solution, by determining the upstream and downstream hierarchical relationships between devices according to the impact transfer sequence and establishing an impact transfer matrix, the impact index is calculated by combining the matrix elements and the hierarchical weight coefficients. This not only quantifies the impact intensity between collaboratively operating devices, but also considers the transmission effect of devices at different levels. The resulting impact index can more accurately reflect the degree of correlation between devices, providing a reliable basis for the subsequent transmission evaluation of abnormal conditions.

[0016] Optionally, adjusting the abnormal index to be adjusted according to the impact index to generate a target abnormal index for each of the collaboratively operated devices includes: accumulating the impact index of each of the collaboratively operated devices to generate an impact cumulative value of each of the collaboratively operated devices; arithmetically multiplying the impact cumulative value with a preset adjustment factor to generate an impact adjustment coefficient; arithmetically multiplying the impact adjustment coefficient with the abnormal index to be adjusted to generate a target abnormal index for each of the collaboratively operated devices.

[0017] By adopting the above technical scheme, the impact accumulated value is obtained by accumulating the impact index of each collaboratively operated device, and the impact adjustment coefficient is generated in combination with the preset adjustment factor. Then, the abnormal index to be adjusted is adjusted to obtain the target abnormal index, thereby realizing a global evaluation of the abnormal state of the equipment. The target abnormal index finally generated not only reflects the operating state of the equipment itself, but also takes into account the degree of influence of the equipment in the entire system, thereby providing a more comprehensive and accurate basis for the formulation of operation and maintenance strategies.

[0018] Optionally, after generating the operation and maintenance strategy of the target device, it also includes: applying the operation and maintenance strategy to the digital twin model to generate simulated operation data of the target device; calculating the simulated abnormality index of the target device based on the simulated operation data; when the simulated abnormality index is greater than the preset abnormality threshold, adjusting the operation and maintenance strategy; when the simulated abnormality index is not greater than the preset abnormality threshold, outputting the operation and maintenance strategy.

[0019] By adopting the above technical solution, the operation and maintenance strategy is applied to the digital twin model for simulation verification, the simulated anomaly index is calculated according to the simulated operation data and compared with the preset anomaly threshold, so as to achieve pre-evaluation and optimization adjustment of the operation and maintenance strategy, avoid the risks that may be caused by directly applying the operation and maintenance strategy to the actual equipment, and at the same time ensure that the final output operation and maintenance strategy can effectively reduce the abnormal state of the equipment and improve the reliability of the operation and maintenance decision.

[0020] In a second aspect, the present application provides an operation and maintenance strategy auxiliary generation system based on digital twins, the system comprising: a first acquisition module, a generation module, a second acquisition module, a first adjustment module, a second adjustment module and an output module; wherein,

[0021] The first acquisition module is used to acquire the real-time operation data of multiple collaborative operation devices, construct digital twin models corresponding to the multiple collaborative operation devices according to the real-time operation data, and generate an initial abnormality index for each of the collaborative operation devices; the generation module is used to generate an impact transfer sequence between the collaborative operation devices according to the digital twin model; the second acquisition module is used to acquire the historical operation data of each of the collaborative operation devices and the device characteristics of each of the collaborative operation devices, and predict the performance degradation index of each of the collaborative operation devices after a preset time period in combination with the historical operation data and the device characteristics; the first adjustment module is used to adjust the initial abnormality index according to the performance degradation index and generate an abnormality index to be adjusted for each of the collaborative operation devices; the second adjustment module is used to determine the impact index between the collaborative operation devices according to the impact transfer sequence, adjust the abnormality index to be adjusted according to the impact index, and generate a target abnormality index for each of the collaborative operation devices; the output module is used to generate an operation and maintenance strategy for a target device when there is a target device whose target abnormality index is greater than a preset abnormality threshold, and the target device is at least one device among the multiple collaborative operation devices.

[0022] In the third aspect, the present application provides an electronic device, adopting the following technical solution: including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a computer program such as any one of the above-mentioned operation and maintenance strategy auxiliary generation methods based on digital twins.

[0023] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: storing a computer program that can be loaded by a processor and execute any of the above-mentioned digital twin-based operation and maintenance strategy auxiliary generation methods.

[0024] In summary, the present application includes at least one of the following beneficial technical effects:

[0025] By acquiring the real-time operation data of collaboratively operated equipment, a digital twin model is constructed and an initial abnormality index is generated. The performance degradation index is predicted by combining the impact transfer sequence, historical operation data and equipment characteristics, and then the abnormality index to be adjusted and the target abnormality index are generated. Finally, an operation and maintenance strategy is generated for the target equipment whose target abnormality index exceeds the preset abnormality threshold. Not only the performance degradation trend of a single device is taken into account, but also the impact transfer effect between devices is combined, so that the generated operation and maintenance strategy is forward-looking, thereby effectively preventing the transmission and spread of abnormal equipment status. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1It is a flowchart of a method for assisting in generating an operation and maintenance strategy based on digital twins provided in an embodiment of the present application;

[0027] Figure 2 It is a structural schematic diagram of an operation and maintenance strategy auxiliary generation system based on digital twins provided in an embodiment of the present application;

[0028] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0029] Description of reference numerals: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0031] In the description of the embodiments of the present application, words such as "illustrative", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "illustrative", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "illustrative", "for example" or "for example" is intended to present related concepts in a concrete way.

[0032] Figure 1 Schematic diagram of a method for assisting in generating an operation and maintenance strategy based on digital twins provided in an embodiment of the present application. Figure 1 As shown, the method includes S101-S106:

[0033] S101, obtaining real-time operation data of multiple collaborative operation devices, constructing digital twin models corresponding to the multiple collaborative operation devices based on the real-time operation data, and generating an initial abnormality index for each collaborative operation device.

[0034] In the industrial production process, multiple devices often need to work together to complete specific production tasks. In order to promptly detect equipment operation anomalies and take corresponding operation and maintenance measures, this embodiment provides an auxiliary generation method of operation and maintenance strategy based on digital twins.

[0035] First, the real-time operation data of the equipment is collected through sensors deployed on each collaborative operation equipment, and the real-time operation data includes but is not limited to temperature parameters and vibration parameters. Among them, the temperature parameter is used to reflect the heating condition during the operation of the equipment, and the vibration parameter is used to characterize the vibration state of the equipment during operation. These parameters can intuitively reflect the operation status of the equipment.

[0036] After obtaining the real-time operation data, the pre-trained deep learning model is used to process the real-time operation data and build the digital twin model of each collaborative operation device. The digital twin model is a virtual mapping of the physical device, which can reflect the operating status and performance changes of the device in real time. Specifically, by establishing a mathematical model that includes the geometric features, physical characteristics and operating parameters of the device, the mapping of the physical device to the virtual space is realized. The construction of the digital twin model makes it possible to simulate and predict the operating status of the device in a virtual environment, providing a basis for the subsequent formulation and verification of operation and maintenance strategies.

[0037] While building the digital twin model, the initial abnormality index of each collaboratively operated device is generated based on real-time operating data. Specifically, by calculating the temperature difference between the temperature parameter and the standard temperature parameter, and the vibration parameter difference between the vibration parameter and the standard vibration parameter, and multiplying these differences by the preset temperature weight coefficient and vibration weight coefficient, the temperature abnormality index and vibration abnormality index are obtained. Among them, the standard temperature parameter and the standard vibration parameter are reference values ​​obtained based on historical data statistics under normal operating conditions of the equipment. By adding the temperature abnormality index and the vibration abnormality index, the initial abnormality index reflecting the overall operating status of the equipment can be obtained.

[0038] Based on the above embodiment, as an optional implementation, in S101, the real-time operation data includes temperature parameters and vibration parameters, and generating the initial abnormality index of each cooperative operation device according to the real-time operation data specifically includes S11-S13:

[0039] S11, calculating the temperature difference between the temperature parameter of each cooperatively operated device and the standard temperature parameter, and the vibration parameter difference between the vibration parameter and the standard vibration parameter.

[0040] S12, arithmetically multiplying the temperature difference with the preset temperature weight coefficient to generate the temperature anomaly index of each cooperatively operated device, and arithmetically multiplying the vibration parameter difference with the preset vibration weight coefficient to generate the vibration anomaly index of each cooperatively operated device.

[0041] S13, arithmetically adding the temperature anomaly index and the vibration anomaly index to generate an initial anomaly index of each cooperatively operated device.

[0042] During the operation of industrial equipment, temperature and vibration are the two most direct and important parameters that reflect the operating status of the equipment. Through real-time monitoring and analysis of these two key parameters, abnormal conditions in equipment operation can be discovered in a timely manner, providing basic data support for the coordinated control of equipment.

[0043] In the specific implementation, first obtain the real-time operating data of temperature parameters and vibration parameters from the equipment monitoring system. Each equipment has its corresponding standard operating parameters, which are the optimal working state parameters determined based on equipment design specifications, operating experience and process requirements. By comparing the real-time operating data with the standard parameters, the temperature difference and vibration parameter difference are calculated. These differences intuitively reflect the degree of deviation between the current operating state of the equipment and the ideal state.

[0044] Take an axial flow pump in an industrial device as an example. Its standard operating temperature is 45°C and its standard vibration value is 2.5mm / s. When real-time monitoring shows that the bearing temperature of the pump reaches 52°C and the vibration value is 3.8mm / s, it can be calculated that the temperature difference is 7°C and the vibration parameter difference is 1.3mm / s. These differences indicate that the equipment operation has deviated to a certain extent.

[0045] Considering the different degrees of influence of temperature and vibration parameters on the equipment status, it is necessary to introduce corresponding weight coefficients for weighted calculation. The temperature weight coefficient and vibration weight coefficient are set based on equipment characteristics and historical operating experience. Usually, the temperature weight coefficient is set to 0.6 and the vibration weight coefficient is set to 0.4. Multiply the difference by the corresponding weight coefficient to obtain the temperature anomaly index and vibration anomaly index. In the above example, the temperature anomaly index is 4.2 (7×0.6) and the vibration anomaly index is 0.52 (1.3×0.4).

[0046] Finally, the temperature anomaly index and the vibration anomaly index are arithmetically added to obtain the initial anomaly index of the equipment. For example, the initial anomaly index of the axial flow pump in the above example is 4.72 (4.2 + 0.52). This index comprehensively reflects the degree of abnormality of the equipment in terms of temperature and vibration, providing a reliable data basis for subsequent performance degradation analysis and coordinated control.

[0047] It should be noted that the determination of the weight coefficient can be verified and corrected by using historical fault data. Analyze the correlation between temperature anomalies and vibration anomalies in historical equipment failure cases and actual failures. For example, statistical analysis shows that before a certain type of pump fails, 80% of the cases have obvious vibration anomalies, while 60% of the cases have temperature anomalies. Based on this, it can be preliminarily determined that the vibration weight coefficient of this type of equipment is 0.6 and the temperature weight coefficient is 0.4.

[0048] S102: Generate an influence transfer sequence between collaboratively operating devices based on the digital twin model.

[0049] In an industrial production environment, there is a close relationship between multiple collaboratively operated devices. The abnormal operation of a device may affect the operating status of other associated devices, resulting in the transmission and spread of faults between devices. In order to accurately evaluate the impact relationship between devices, it is necessary to generate an impact transmission sequence based on the constructed digital twin model. The impact transmission sequence refers to an ordered sequence that describes the fault transmission path and impact relationship between devices, which is used to characterize how faults are transmitted between collaboratively operated devices.

[0050] Specifically, the process connection relationship and material flow of each collaboratively operated equipment are first analyzed through the digital twin model. Based on the physical connection mode of the equipment, such as pipeline connection, transmission connection, etc., the direct correlation relationship between the equipment is determined. At the same time, the historical operation data in the digital twin model is used to identify the correlation pattern between the equipment operation parameters through the time series correlation analysis method. For example, when the temperature of the upstream equipment A rises abnormally, after a certain time delay, the vibration parameters of the downstream equipment B connected to it may change abnormally. The time series characteristics of this parameter change can reflect the influence transfer relationship between the equipment.

[0051] After determining the association between devices, the graph theory method is used to construct the device impact transfer network. Each collaborative device is used as a network node, and the impact relationship between devices is used as a directed edge. Through the depth-first search algorithm, starting from each device node, possible impact transfer paths are explored. During the search process, factors such as the physical distance between devices and the sequence of process links are considered to determine the priority and importance of impact transfer. Finally, all possible paths obtained by the search are sorted according to the degree of impact to form an impact transfer sequence.

[0052] For example, in a production line consisting of equipment A, B, and C, if the impact transfer relationship between the equipment is: the abnormality of equipment A will directly affect the operation of equipment B, and the abnormality of equipment B will affect the operation of equipment C, and equipment A may also indirectly affect equipment C through other channels, then the possible impact transfer sequence includes: A→B→C and A→C. In this way, various possible impact transfer paths between equipment can be fully described.

[0053] S103, obtaining historical operation data of each collaborative operation device and device characteristics of each collaborative operation device, and predicting the performance degradation index of each collaborative operation device after a preset period of time by combining the historical operation data and the device characteristics.

[0054] In industrial production, the performance of equipment will gradually deteriorate as the use time increases. This degradation process will affect the equipment's operating reliability and production efficiency. In order to proactively prevent equipment failures, it is necessary to predict the performance degradation trend of the equipment. This step predicts the degree of performance degradation of the equipment in the future by analyzing the equipment's historical operating data and equipment characteristics.

[0055] First, the historical operation data of each collaborative operation device is obtained from the equipment management system, including the equipment's operating time, historical fault records, maintenance records and other information. Through statistical analysis of historical operation data, the average number of historical faults and historical fault intervals of each device are determined. Among them, the number of historical faults reflects the reliability level of the equipment, and the average fault interval represents the stable operation capability of the equipment. At the same time, the historical operating time of the equipment is calculated. This parameter represents the cumulative operating time of the equipment from the time it was put into use to the present.

[0056] Secondly, the equipment characteristics of each collaborative equipment are obtained from the equipment archive, mainly including the standard failure interval and standard service life. The standard failure interval refers to the expected failure interval of the equipment under normal use conditions, and the standard service life is the expected service life provided by the equipment manufacturer. These equipment characteristic parameters reflect the design performance and expected reliability of the equipment.

[0057] After obtaining the above data, a preset formula is used to predict the performance degradation index of each collaborative operation device after a preset time. The preset formula is: ; In the formula, For the The performance degradation index of the coordinated operation equipment, is the weight coefficient of the historical fault impact factor, For the The historical failure times of the coordinated operation equipment, For the The average value of the historical failure interval time of the coordinated operation equipment, For the The historical operating time of the coordinated operation equipment, For the The standard service life of a coordinated operation equipment, is the weight coefficient of the remaining life impact factor, For the preset duration, For the The standard time between failures of the coordinated operation equipment, is the weight coefficient of the factor affecting future degradation trend.

[0058] The formula consists of three parts, the first part is: , reflecting the impact of the equipment’s historical operating conditions on its future performance.

[0059] This section will record the number of historical failures. Mean Time Between Failures The ratio of is taken as the basic index. This design fully considers the time distribution characteristics of fault occurrence. The ratio form not only eliminates the influence of time scale, making the indicators between different devices comparable, but also reflects the frequency of fault occurrence per unit time. The introduction of provides an adjustment mechanism, so that the contribution of this influencing factor can be flexibly adjusted according to the device type and application scenario.

[0060] When the equipment has a history of frequent failures, the value of this item will increase accordingly, indicating that the equipment has poor reliability and a high risk of performance degradation in the future. It is suitable for evaluating equipment with a clear failure record and can make reasonable predictions about future performance based on historical data.

[0061] The second part is: , reflecting the impact of equipment life consumption on performance. This part is based on historical operating time Standard service life The ratio of is based on the addition of 1 to ensure that even new equipment has a basic risk of degradation. This design reflects the objective law that equipment performance will naturally decay over time. It intuitively shows the degree of consumption of equipment life. The design concept of adding 1 operation is based on the consideration that even brand new equipment may have performance degradation, making this influencing factor more universal. Weight coefficient The setting allows the influence of this factor to be adjusted according to the life characteristics of different devices. This part of the index will increase monotonically with the increase of device usage time, which conforms to the natural law of device aging and reflects the impact of device life consumption on performance degradation.

[0062] The third part is: , predicting the performance degradation trend of the equipment in the future period. This part will predict the duration Time between failures and standard The ratio of is used as a basic indicator, reflecting the degree of degradation that may occur within the prediction period. The introduction of the standard failure interval time realizes the normalization processing between different devices, making the prediction results comparable. The setting allows the adjustment of the influence weight of future trend prediction, making the prediction more flexible and accurate. The influence of the prediction time span on the degradation degree is considered, and the dimension is unified through the standard failure interval, while reflecting the cumulative effect of time extension on performance degradation.

[0063] Assume there is a centrifugal pump with the following operating parameters and characteristic data:

[0064] Historical failure times = 5 times (number of failures in the past two years), average failure interval time =120 days, historical running time =1080 days (about 3 years), standard service life =1825 days (5 years), standard failure interval =180 days, forecast duration =90 days (predicting performance degradation over the next 3 months).

[0065] Weight coefficient: α=0.4, β=0.3, γ=0.3 (set according to the characteristics of this type of equipment). The setting of weight coefficients α, β, and γ is a dynamic optimization process, which requires comprehensive consideration of multiple factors such as equipment type, operating environment, and maintenance strategy. The specific setting method is as follows:

[0066] In the initial stage, a judgment matrix is ​​first established to compare the three factors of historical failure impact, remaining life impact and future degradation trend in pairs. The scoring standard adopts a 1-9 scale: 1 means that the two factors are equally important, 3 means that one factor is slightly more important than the other, 5 means obviously important, 7 means strongly important, 9 means extremely important, and 2, 4, 6, and 8 are the middle values ​​of adjacent judgments.

[0067] Taking rotating equipment (such as centrifugal pumps, compressors, etc.) as an example, the judgment matrix may be as follows: historical failures and remaining life: 2 (historical failures are slightly important), historical failures and future trends: 3 (historical failures are more important), remaining life and future trends: 1.5 (remaining life is slightly important).

[0068] By calculating the eigenvector of the judgment matrix, the initial weight values ​​are obtained: α≈0.4, β≈0.35, γ≈0.25.

[0069] Then, adjust the weights according to the specific characteristics of the equipment: For high-speed rotating equipment (such as high-speed centrifugal pumps): Since this type of equipment is more sensitive to failure, increase α to 0.45-0.5, the impact on life is relatively minor, reduce β to 0.3-0.35, and keep γ in the range of 0.2-0.25.

[0070] For static equipment (such as heat exchangers): Failures occur less frequently, reducing α to 0.2-0.25, with a significant impact on service life, increasing β to 0.45-0.5, and increasing γ to 0.3-0.35, as material degradation trends are more important.

[0071] For key equipment (such as main process compressors): maintain a high α value (0.4-0.45) to fully consider the impact of failures, appropriately increase the β value (0.35-0.4) to focus on life factors, and correspondingly reduce the γ value (0.2-0.25).

[0072] Finally, the performance degradation index is calculated part by part:

[0073] The first part (historical failure impact factor): = 0.4 × (5 / 120) = 0.0167, this value indicates that the pump has a relatively high historical failure frequency. Through calculation, it can be seen that an average failure occurs every 120 days, which is shorter than the standard failure interval of 180 days, indicating that the reliability of the equipment is lower than expected.

[0074] The second part (life remaining impact factor): = 0.3 × (1 + 1080 / 1825) = 0.477. The calculation results show that the pump has used about 59% of its design life. A value greater than 0.3 (i.e., β value) indicates that the equipment has entered a more obvious aging stage and needs to be paid more attention.

[0075] The third part (factor affecting future degradation trend): =0.3×(90 / 180)=0.15, which means that in the next 90 days, considering only the time factor, the equipment will generate a degradation contribution of 0.15, which is equivalent to half of the standard failure interval.

[0076] The final performance degradation index: =0.0167+0.477+0.15=0.6437.

[0077] S104: According to the performance degradation index, the initial abnormality index is adjusted to generate an abnormality index to be adjusted for each cooperatively operated device.

[0078] As a quantitative indicator that comprehensively reflects the equipment's historical failures, service life, and future degradation trends, the value of the performance degradation index directly affects the adjustment range of the abnormality index. For equipment with a high degree of performance degradation, even if the current operating parameters are within the normal range, it is necessary to appropriately increase its abnormality index to reflect the higher potential risk. On the contrary, for equipment with good performance, the adjustment range of its abnormality index is relatively small. This adjustment mechanism ensures that the abnormal status assessment can fully consider the historical performance and potential risks of the equipment.

[0079] In the specific implementation process, it is necessary to determine the degradation impact adjustment coefficient based on the type and importance of the equipment. This coefficient is a key parameter to measure the impact of performance degradation on the abnormal state of the equipment. Its value needs to comprehensively consider factors such as the sensitivity of the equipment, reliability requirements, and operating environment. For equipment that is sensitive to performance degradation, such as precision instruments, a larger adjustment coefficient should be used; while for insensitive equipment such as simple valves, a smaller adjustment coefficient can be used. At the same time, the importance of the equipment in the production process will also affect the value of the adjustment coefficient. Key equipment usually requires a larger adjustment coefficient to reflect more stringent evaluation standards.

[0080] After the abnormal index is adjusted, the abnormal index to be adjusted will serve as an important basis for subsequent collaborative control. When the abnormal index to be adjusted of the equipment exceeds the preset threshold, the system will take corresponding control measures, such as adjusting operating parameters or starting backup equipment, to prevent possible failures. This dynamic adjustment mechanism based on performance degradation makes the abnormal state assessment more comprehensive and accurate, and can better guide the collaborative operation control of the equipment.

[0081] Take a key pump group in an industrial device as an example. Assuming that the current operating parameters of the main pump fluctuate slightly, the initial abnormal index shows a slight abnormality. However, considering that the pump has been in operation for many years and has experienced frequent failures recently, its performance degradation index is relatively high. After adjusting the abnormal index, the abnormal index to be adjusted increases significantly, indicating that it is necessary to strengthen the monitoring of the pump or consider using a backup pump.

[0082] Based on the above embodiment, as an optional implementation, in S104, adjusting the initial abnormality index according to the performance degradation index and generating the abnormality index to be adjusted of each coordinated operation device specifically includes S41-S42:

[0083] S41, matching the performance degradation index with a plurality of preset intervals to obtain a target interval to which the performance degradation index belongs.

[0084] In the specific implementation, it is first necessary to set the preset range of the performance degradation index. Based on the operating experience and expert knowledge of the equipment throughout its life cycle, the performance degradation index is divided into four ranges: slight degradation range [0, 0.3), moderate degradation range [0.3, 0.6), severe degradation range [0.6, 0.8) and dangerous degradation range [0.8, 1.0]. The division of these ranges takes into account the general laws of equipment performance degradation and the actual needs of equipment management.

[0085] Taking a centrifugal compressor as an example, when its running time reaches 5000 hours, by analyzing its comprehensive indicators such as efficiency, power consumption, and vibration, the performance degradation index is calculated to be 0.45. By matching this value with the preset interval, it can be determined that the compressor is currently in the moderate degradation interval [0.3, 0.6]. This matching result intuitively reflects the performance status of the equipment and provides a basis for subsequent abnormal index adjustment.

[0086] S42, obtaining an adjustment coefficient corresponding to the target interval, and arithmetically multiplying the adjustment coefficient by the initial abnormality index to generate an abnormality index to be adjusted for each collaboratively operated device.

[0087] According to equipment operation experience and expert knowledge, a corresponding adjustment coefficient is set for each performance degradation interval: the adjustment coefficient for the slightly degraded interval [0, 0.3) is 1.1, the adjustment coefficient for the moderately degraded interval [0.3, 0.6) is 1.2, the adjustment coefficient for the severely degraded interval [0.6, 0.8) is 1.3, and the adjustment coefficient for the dangerously degraded interval [0.8, 1.0] is 1.4. The setting of the adjustment coefficient follows the principle of "the more severe the degradation, the greater the adjustment range", because the more severe the performance degradation of the equipment, the greater the potential risk of its abnormal state.

[0088] Take a centrifugal pump as an example. Assume that its initial abnormality index is 0.5 and its performance degradation index is 0.45 (belonging to the moderate degradation interval [0.3, 0.6)). According to the interval matching result, the corresponding adjustment coefficient 1.2 is obtained. Multiply the initial abnormality index 0.5 by the adjustment coefficient 1.2 to obtain the abnormality index to be adjusted as 0.6. This adjusted value more accurately reflects the actual abnormality degree of the equipment under the influence of performance degradation.

[0089] S105, determining the influence index between the collaboratively operated devices according to the influence transfer sequence, adjusting the abnormality index to be adjusted according to the influence index, and generating a target abnormality index for each collaboratively operated device.

[0090] In the industrial production process, there are complex relationships between equipment. The abnormal state of one equipment often affects the operating state of other related equipment through process parameters, material flow, energy flow, etc. In order to accurately assess the actual abnormality of the equipment, it is necessary to further consider the mutual influence between equipment on the basis of the abnormal index to be adjusted. This requires determining the influence index between equipment through the influence transfer sequence, and adjusting the abnormal index to be adjusted accordingly, so as to finally obtain a more accurate target abnormal index.

[0091] The influence transfer sequence is a directed graph structure that describes the influence relationship between equipment, where nodes represent equipment and edges represent influence transfer paths. By analyzing process flow charts, equipment layout diagrams, and operating data, direct influence relationships between equipment can be identified. For example, in a chemical plant, abnormal temperature of the reactor will directly affect the performance of the downstream heat exchanger, and the heat exchange effect of the heat exchanger will affect the process parameters of subsequent equipment. This chain effect can be clearly expressed through the influence transfer sequence.

[0092] Based on the influence transmission sequence, the influence index Iij between devices can be calculated, which indicates the degree of influence of the abnormal state of device i on device j. The calculation of the influence index needs to consider multiple factors: first, the process correlation, which reflects the degree of process coupling between devices; second, the physical distance, which indicates the distance relationship between devices in space; third, the response time, which reflects the speed of abnormal state transmission; and finally, the control correlation, which describes the degree of correlation between devices in control strategy. These factors are combined in a weighted combination to form the final influence index.

[0093] After determining the impact index, the abnormal index to be adjusted needs to be adjusted. The adjustment process takes into account the cumulative impact of abnormal conditions of upstream equipment, especially those associated equipment with large impact indexes. For example, when an abnormality occurs in the upstream equipment of a pump, even if the abnormal index to be adjusted of the pump itself is low, considering the potential impact of the abnormality of the upstream equipment, its final target abnormal index will be increased accordingly. This adjustment mechanism ensures that the abnormal state assessment can fully reflect the associated impact between equipment.

[0094] Take a chemical production line as an example, assuming there is a process chain including a reactor, a heat exchanger and a separator. When the reactor experiences temperature fluctuations, its abnormal index to be adjusted is 0.4. Through the influence transfer sequence analysis, it is found that the influence index of the reactor on the heat exchanger is 0.8, and the influence index on the separator is 0.5. After considering this influence relationship, even if the current operating parameters of the heat exchanger and separator are normal, their target abnormal index will increase accordingly, prompting operators to strengthen the monitoring of these equipment.

[0095] Based on the above embodiment, as an optional implementation, in S105, determining the influence index between the coordinated operation devices according to the influence transfer sequence specifically includes S51-S53:

[0096] S51, determining the upstream and downstream hierarchical relationship between the collaboratively operated devices according to the impact transfer sequence.

[0097] The influence transfer sequence refers to the order of equipment connection determined by the direction of material or energy flow in the process. For example, in a chemical plant, the raw materials are first fed into the reactor by a transfer pump, and the reaction products are then cooled by a heat exchanger and then enter the separation tower. In this process, the transfer pump → reactor → heat exchanger → separation tower constitutes a basic influence transfer sequence. Based on this sequence, it can be clearly identified that the transfer pump is upstream, the reactor is in the middle, and the heat exchanger and separation tower are downstream.

[0098] When determining the hierarchical relationship, you first need to build a device association matrix. The element values ​​in the matrix represent the direct impact relationship between the devices, 1 indicates that there is a direct impact, and 0 indicates that there is no direct impact. By analyzing the connectivity of the matrix, the complete impact transfer path can be identified. For example, in a process, device A → device B → device C → device D constitutes an impact transfer chain, then device A is at the most upstream level, and device D is at the most downstream level.

[0099] At the same time, the situation of parallel equipment also needs to be considered. For example, two parallel coolers provide services to downstream equipment at the same time, and they are in the same hierarchical position. By analyzing the process flow diagram and equipment operation logic, this parallel relationship can be identified to ensure the accuracy of the hierarchical division.

[0100] Take a refrigeration system as an example. The refrigerant circulates through the compressor, condenser, throttle valve and evaporator in sequence. By analyzing the impact transmission sequence, it can be determined that the compressor is the first level (upstream), the condenser is the second level, the throttle valve is the third level, and the evaporator is the fourth level (downstream). When an abnormality occurs in a device in the system, this hierarchical relationship helps to predict and evaluate the transmission path and impact range of the abnormal state.

[0101] S52, based on the upstream and downstream hierarchical relationship, establish an influence transfer matrix between multiple collaboratively operating devices, wherein the rows of the influence transfer matrix represent upstream devices, the columns of the influence transfer matrix represent downstream devices, and the matrix elements in the influence transfer matrix range from 0 to 1, which are used to characterize the intensity of the influence of upstream devices on downstream devices.

[0102] The construction of the impact transfer matrix is ​​based on the determined upstream and downstream hierarchical relationship, in the form of an n×n matrix (n is the total number of devices), where the matrix element aij represents the impact intensity of the i-th device (upstream) on the j-th device (downstream). The impact intensity value ranges from 0 to 1, where 0 represents no impact, 1 represents full impact, and the intermediate values ​​represent partial impacts of varying degrees.

[0103] Taking the process chain of "transfer pump-heat exchanger-reactor-separation tower" in a chemical plant as an example, a 4×4 influence transfer matrix can be constructed. Assume that the influence intensity of the transfer pump on the heat exchanger is 0.8 (indicating that the abnormality of the transfer pump will significantly affect the operation of the heat exchanger), the influence intensity of the heat exchanger on the reactor is 0.6 (indicating that the abnormality of the heat exchanger has a more obvious impact on the reactor), and the influence intensity of the reactor on the separation tower is 0.7 (indicating that the abnormality of the reactor will greatly affect the operation of the separation tower). For non-adjacent equipment, such as the transfer pump on the separation tower, the influence intensity may be 0.3 (indicating that there is an indirect impact but the intensity is weak).

[0104] The determination of the impact intensity requires consideration of multiple factors: first, the degree of process correlation. The impact intensity between directly connected equipment is usually greater; second, the criticality of material or energy transfer. For example, equipment that controls flow usually has a greater impact on the downstream; and finally, historical operating data analysis. The impact intensity is determined by statistically analyzing the correlation between upstream equipment anomalies and downstream equipment performance changes.

[0105] The construction of the matrix follows the following rules: the influence intensity of the upstream device on the downstream device is greater than 0, the influence intensity between devices of the same level is 0, the influence intensity of the downstream device on the upstream device is 0, and the influence intensity of the device on itself is 1.

[0106] For example, for the four devices mentioned above, the impact transfer matrix may be as follows:

[0107] P H R S P 1 0.8 0.5 0.3 H 0 1 0.6 0.4 R 0 0 1 0.7 S 0 0 0 1

[0108] (Where P is the delivery pump, H is the heat exchanger, R is the reactor, and S is the separation tower).

[0109] S53, multiplying each matrix element in the influence transfer matrix by a preset hierarchical weight coefficient, and accumulating the multiplication results to obtain an influence index between each collaborative operation device, where the influence index is used to characterize the degree of association between each collaborative operation device.

[0110] The layer weight coefficient is a correction factor determined based on the layer position of the equipment, which is used to adjust the impact intensity between different layers. Generally, the weight coefficient between adjacent layers is large, and the larger the layer gap, the smaller the weight coefficient. For example, the weight coefficient of adjacent layers can be set to 0.9, the weight coefficient of one layer can be set to 0.7, the weight coefficient of two layers can be set to 0.5, and so on. This decreasing weight setting conforms to the objective law of abnormal state transmission attenuation in industrial production.

[0111] Taking the above chemical plant as an example, the hierarchical weight coefficient is set as follows: adjacent hierarchical levels are 0.9, one hierarchical level is 0.7, two hierarchical levels are 0.5, and three hierarchical levels are 0.3. Then the influence index of P→H is calculated as: 0.8×0.9=0.72; the influence index of P→R is calculated as: 0.5×0.7=0.35; the influence index of P→S is calculated as: 0.3×0.5=0.15. Similarly, the influence indexes between other equipment pairs can be calculated.

[0112] By adding up all the impact indices, we can get the comprehensive impact index between each pair of equipment. For example, the comprehensive impact index between the delivery pump and the separation tower is 0.15 (direct impact) + 0.72 × 0.6 × 0.9 (indirect impact through the heat exchanger) + 0.35 × 0.7 × 0.9 (indirect impact through the reactor). This cumulative calculation takes into account the combined effects of direct impact and various indirect impact paths.

[0113] S106, when there is a target device whose target abnormality index is greater than a preset abnormality threshold, generating an operation and maintenance strategy for the target device, where the target device is at least one device among the multiple collaboratively operated devices.

[0114] In the industrial production process, when the target abnormality index of a target device exceeds a preset abnormality threshold, a targeted operation and maintenance strategy needs to be generated, and the target device is at least one device among multiple collaboratively operated devices.

[0115] The specific implementation process is to first obtain the target anomaly index and preset anomaly threshold of the target device. The preset anomaly threshold is divided into three levels: the mild anomaly threshold is set to 0.6, the moderate anomaly threshold is set to 0.7, and the severe anomaly threshold is set to 0.8. When the target anomaly index exceeds any threshold, the operation and maintenance strategy generation mechanism is triggered.

[0116] The generation of operation and maintenance strategies is based on the equipment type, abnormality level, fault characteristics and operating environment of the target equipment. The system extracts the typical failure mode and corresponding maintenance plan of this type of equipment from the operation and maintenance knowledge base, and identifies the most likely cause of the failure in combination with the current abnormal indicator characteristics. At the same time, the operating environment of the equipment, including the status of upstream and downstream equipment, production plan requirements and maintenance resources, is considered to determine the priority and implementation timing of the operation and maintenance measures.

[0117] For example, when the target abnormality index of a centrifugal pump reaches 0.75, exceeding the moderate abnormality threshold, the system first analyzes its abnormal characteristics. By comparing the changing trends of the pump's vibration, temperature, pressure and other parameters, it is found that the main abnormalities come from increased bearing temperature and increased vibration. The system then extracts maintenance plans related to bearing failures from the knowledge base, and generates the following operation and maintenance strategies based on the current production plan and spare parts inventory:

[0118] First, reduce the equipment load and reduce the operating speed to 85% of the rated value. At the same time, increase the vibration detection frequency from once every 4 hours to once every hour. Closely monitor the bearing temperature change trend. If the temperature continues to rise and exceeds the warning value, switch to the standby pump. At the same time, arrange maintenance personnel to conduct special inspections, focusing on key parts such as bearing lubrication conditions and cooling system operation. According to the inspection results, reasonably arrange the bearing replacement time and give priority to planned parking opportunities for maintenance.

[0119] Based on the above embodiment, as an optional implementation, in S106, adjusting the abnormality index to be adjusted according to the impact index and generating the target abnormality index of each collaborative operation device specifically includes S61-S63:

[0120] S61, accumulating the impact index of each collaboratively operated device to generate an impact accumulation value of each collaboratively operated device.

[0121] S62, arithmetically multiplying the impact accumulated value by a preset adjustment factor to generate an impact adjustment coefficient.

[0122] S63, arithmetically multiplying the impact adjustment coefficient by the abnormality index to be adjusted to generate a target abnormality index for each cooperatively operated device.

[0123] Taking the "transfer pump-heat exchanger-reactor-separation tower" system in a chemical plant as an example, we first need to calculate the cumulative impact value of each device. For the heat exchanger, its cumulative impact value is equal to the sum of the impact indexes of all devices on it, including the impact index of the transfer pump on it 0.72, its own impact index 1.0, the impact index of the reactor on it 0 (no reverse impact) and the impact index of the separation tower on it 0 (no reverse impact). The cumulative impact value is 1.72. Similarly, the cumulative impact value of other equipment can be calculated.

[0124] The preset adjustment factor is a coefficient used to convert the impact accumulation value into an impact adjustment coefficient within a reasonable range. For example, if the adjustment factor is set to 0.2, the impact adjustment coefficient of the heat exchanger is 1.72×0.2=0.344. The setting of this adjustment factor needs to take into account the actual characteristics of the system, ensuring that the abnormal index after adjustment is within a reasonable range and ensuring the effectiveness of the adjustment.

[0125] Finally, the impact adjustment coefficient is multiplied by the abnormal index to be adjusted to obtain the target abnormal index. Assuming that the abnormal index to be adjusted of the heat exchanger is 0.6, its target abnormal index is 0.6×(1+0.344)=0.806. This result shows that after considering the influence of other equipment, the actual abnormality of the heat exchanger is higher than the level when it is evaluated independently.

[0126] After the operation and maintenance strategy of the target device is generated, it also includes:

[0127] Apply the operation and maintenance strategy to the digital twin model to generate simulated operation data of the target device; calculate the simulated anomaly index of the target device based on the simulated operation data; adjust the operation and maintenance strategy when the simulated anomaly index is greater than the preset anomaly threshold; output the operation and maintenance strategy when the simulated anomaly index is not greater than the preset anomaly threshold.

[0128] In the operation and maintenance management of industrial equipment, in order to verify the effectiveness of the operation and maintenance strategy and reduce the implementation risk, it is necessary to use digital twin technology to verify and optimize the strategy. The digital twin model is a mapping of the physical equipment in the digital space, which can simulate the operating status of the equipment under different operation and maintenance strategies, so as to evaluate the effect of the strategy without affecting the actual production.

[0129] Taking the heat exchanger of a chemical plant as an example, after the system generates an operation and maintenance strategy including cleaning frequency adjustment and operation parameter optimization, these strategy parameters are first input into the digital twin model of the heat exchanger. The digital twin model is built based on historical operation data and physical models, and can accurately reflect the dynamic characteristics of the equipment. The model includes the key parameters of the heat exchanger, such as heat transfer coefficient, pressure drop, flow rate, etc., and establishes the correlation between these parameters.

[0130] Through the simulation calculation of the digital twin model, simulated operation data of the equipment under the new operation and maintenance strategy can be generated. For example, when the cleaning cycle is adjusted from 30 days to 25 days, the model can simulate the impact of this change on parameters such as heat exchange efficiency and pressure loss. The simulation data includes real-time operating parameters such as temperature, pressure, flow, and the changing trend of equipment performance indicators.

[0131] Based on the simulated operation data, the system uses the same evaluation method as the actual equipment to calculate the simulated abnormality index. Assuming that the preset abnormality threshold is 0.8, when the abnormality index obtained in a simulation is 0.85, it means that the current operation and maintenance strategy may not be able to effectively control the abnormal state of the equipment. In this case, the system will automatically adjust the operation and maintenance strategy, such as further shortening the cleaning cycle or adjusting the operating parameters, and then re-simulate the verification.

[0132] After multiple rounds of optimization, if the simulated abnormality index drops to 0.75 (less than the preset threshold of 0.8), it means that the optimized operation and maintenance strategy can effectively control the abnormal state of the equipment. At this time, the system will output this set of verified operation and maintenance strategies, including specific maintenance cycles, operating parameters and control measures.

[0133] Based on the above method, the present application also discloses an operation and maintenance strategy auxiliary generation system based on digital twins, such as Figure 2 As shown, Figure 2is a structural diagram of an operation and maintenance strategy auxiliary generation system based on digital twins provided in an embodiment of the present application, the system includes: a first acquisition module, a generation module, a second acquisition module, a first adjustment module, a second adjustment module and an output module; wherein,

[0134] The first acquisition module is used to acquire the real-time operation data of multiple collaborative operation devices, construct digital twin models corresponding to the multiple collaborative operation devices based on the real-time operation data, and generate the initial abnormality index of each collaborative operation device; the generation module is used to generate the impact transfer sequence between the collaborative operation devices based on the digital twin model; the second acquisition module is used to acquire the historical operation data of each collaborative operation device and the device characteristics of each collaborative operation device, and predict the performance degradation index of each collaborative operation device after a preset time period in combination with the historical operation data and the device characteristics; the first adjustment module is used to adjust the initial abnormality index according to the performance degradation index and generate the abnormality index to be adjusted for each collaborative operation device; the second adjustment module is used to determine the impact index between the collaborative operation devices according to the impact transfer sequence, adjust the abnormality index to be adjusted according to the impact index, and generate the target abnormality index for each collaborative operation device; the output module is used to generate an operation and maintenance strategy for the target device when there is a target device whose target abnormality index is greater than the preset abnormality threshold, and the target device is at least one device among the multiple collaborative operation devices.

[0135] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0136] See also Figure 3 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0137] The communication bus 1002 is used to realize the connection and communication between these components.

[0138] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0139] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0140] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0141] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally also be at least one storage device located away from the aforementioned processor 1001. As Figure 3 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for an operation and maintenance strategy auxiliary generation method based on digital twins.

[0142] exist Figure 3 In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call an application stored in the memory 1005 for an operation and maintenance strategy auxiliary generation method based on digital twins. When executed by one or more processors, the electronic device executes one or more methods described in the above embodiments.

[0143] An electronic device readable storage medium stores instructions, which, when executed by one or more processors, enable the electronic device to execute one or more of the methods described in the above embodiments.

[0144] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0145] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0146] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0147] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0150] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for assisting in generating operation and maintenance strategies based on digital twins, characterized in that: The method comprises: Acquire real-time operation data of a plurality of collaborative operation devices, construct digital twin models corresponding to the plurality of collaborative operation devices according to the real-time operation data, and generate an initial abnormality index for each of the collaborative operation devices; Generating, according to the digital twin model, an influence transfer sequence between the collaboratively operated devices; Acquire historical operation data of each of the collaboratively operated devices and device characteristics of each of the collaboratively operated devices, and predict the performance degradation index of each of the collaboratively operated devices after a preset period of time by combining the historical operation data and the device characteristics; According to the performance degradation index, adjusting the initial abnormality index to generate an abnormality index to be adjusted for each of the cooperatively operated devices; According to the impact transfer sequence, the impact index between the collaboratively operated devices is determined, and according to the impact index, the abnormality index to be adjusted is adjusted to generate a target abnormality index of each collaboratively operated device; the impact transfer sequence refers to an ordered sequence that describes the fault transfer path and impact relationship between devices, and is used to characterize how the fault is transferred between the collaboratively operated devices; When there is a target device whose target abnormality index is greater than a preset abnormality threshold, an operation and maintenance strategy for the target device is generated, and the target device is at least one device among the multiple collaboratively operated devices.

2. The method for auxiliary generation of operation and maintenance strategies based on digital twins according to claim 1 is characterized in that: The real-time operation data includes temperature parameters and vibration parameters, and generating the initial abnormality index of each of the cooperative operation devices according to the real-time operation data includes: Calculating the temperature difference between the temperature parameter of each of the cooperatively operated devices and the standard temperature parameter, and the vibration parameter difference between the vibration parameter and the standard vibration parameter; Arithmetically multiplying the temperature difference with a preset temperature weight coefficient to generate a temperature anomaly index of each of the cooperatively operated devices, and arithmetically multiplying the vibration parameter difference with a preset vibration weight coefficient to generate a vibration anomaly index of each of the cooperatively operated devices; The temperature anomaly index and the vibration anomaly index are arithmetically added to generate an initial anomaly index for each of the cooperatively operated devices.

3. The method for auxiliary generation of operation and maintenance strategies based on digital twins according to claim 1 is characterized in that: The combining of the historical operation data and the device characteristics to predict the performance degradation index of each of the collaboratively operated devices after a preset period of time includes: Determine the number of historical failures of each of the collaboratively operated devices and the average value of the historical failure intervals according to the historical operation data; According to the equipment characteristics, the standard fault interval duration and standard service life of each of the cooperatively operated equipment are determined; the number of historical faults, the average value of the historical fault interval duration, the standard fault interval duration and the standard service life are substituted into a preset formula to predict the performance degradation index of each of the cooperatively operated equipment after the preset duration; wherein, The preset formula is: Where D i is the performance degradation index of the ith collaborative operation equipment, α is the weight coefficient of the historical fault impact factor, F i is the historical failure times of the i-th cooperative operation equipment, T int is the average value of the historical failure interval duration of the i-th cooperative operation equipment, T hist is the historical operating time of the i-th cooperative operation equipment, L std is the standard service life of the i-th collaborative operation equipment, β is the weight coefficient of the remaining life influencing factor, Δt is the preset duration, T std_int is the standard failure interval of the ith collaborative operation equipment, and γ is the weight coefficient of the influencing factor of the future degradation trend.

4. The method for assisting in generating operation and maintenance strategies based on digital twins according to claim 1 is characterized in that: The step of adjusting the initial abnormality index according to the performance degradation index to generate an abnormality index to be adjusted for each of the cooperatively operated devices includes: Matching the performance degradation index with a plurality of preset intervals to obtain a target interval to which the performance degradation index belongs; An adjustment coefficient corresponding to the target interval is obtained, and the adjustment coefficient is arithmetically multiplied by the initial abnormality index to generate an abnormality index to be adjusted for each of the collaboratively operated devices.

5. The method for assisting in generating operation and maintenance strategies based on digital twins according to claim 1 is characterized in that: Determining the influence index between the collaboratively operated devices according to the influence transfer sequence includes: Determining the upstream and downstream hierarchical relationships between the collaboratively operated devices according to the impact transfer sequence; According to the upstream and downstream hierarchical relationship, an influence transfer matrix between the multiple collaboratively operated devices is established, wherein the rows of the influence transfer matrix represent upstream devices, the columns of the influence transfer matrix represent downstream devices, and the matrix elements in the influence transfer matrix range from 0 to 1, which are used to characterize the influence strength of the upstream device on the downstream device; Each matrix element in the influence transfer matrix is ​​multiplied by a preset hierarchical weight coefficient, and the multiplication results are accumulated to obtain an influence index between each of the collaboratively operated devices, and the influence index is used to characterize the degree of association between each of the collaboratively operated devices.

6. The method for assisting in generating operation and maintenance strategies based on digital twins according to claim 1 is characterized in that: The adjusting the abnormality index to be adjusted according to the impact index to generate a target abnormality index of each of the collaborative operation devices includes: accumulating the impact index of each of the collaborative operation devices to generate an impact accumulation value of each of the collaborative operation devices; The impact accumulated value is arithmetically multiplied by a preset adjustment factor to generate an impact adjustment coefficient; The impact adjustment coefficient is arithmetically multiplied by the abnormality index to be adjusted to generate a target abnormality index for each of the cooperatively operated devices.

7. The method for assisting in generating operation and maintenance strategies based on digital twins according to claim 1 is characterized in that: After the operation and maintenance strategy of the target device is generated, the method further includes: Applying the operation and maintenance strategy to the digital twin model to generate simulated operation data of the target device; Calculating a simulated abnormality index of the target device according to the simulated operation data; When the simulated abnormality index is greater than the preset abnormality threshold, the operation and maintenance strategy is adjusted; when the simulated abnormality index is not greater than the preset abnormality threshold, the operation and maintenance strategy is output.

8. An operation and maintenance strategy auxiliary generation system based on digital twins, characterized in that: The system comprises: a first acquisition module, a generation module, a second acquisition module, a first adjustment module, a second adjustment module and an output module; wherein, The first acquisition module is used to acquire real-time operation data of multiple collaborative operation devices, construct digital twin models corresponding to the multiple collaborative operation devices according to the real-time operation data, and generate an initial abnormality index of each collaborative operation device; The generation module is used to generate an influence transfer sequence between the collaborative operation devices according to the digital twin model; the second acquisition module is used to obtain the historical operation data of each of the collaborative operation devices and the device characteristics of each of the collaborative operation devices, and combine the historical operation data and the device characteristics to predict the performance degradation index of each of the collaborative operation devices after a preset time period; The first adjustment module is used to adjust the initial abnormality index according to the performance degradation index to generate an abnormality index to be adjusted for each of the collaboratively operated devices; The second adjustment module is used to determine the influence index between the collaborative operation devices according to the influence transfer sequence, and adjust the abnormality index to be adjusted according to the influence index to generate a target abnormality index of each collaborative operation device; the influence transfer sequence refers to an ordered sequence that describes the fault transfer path and influence relationship between devices, and is used to characterize how the fault is transferred between the collaborative operation devices; The output module is used to generate an operation and maintenance strategy for a target device when there is a target device whose target abnormality index is greater than a preset abnormality threshold, and the target device is at least one device among the multiple collaboratively operated devices.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images