Mechanical equipment state monitoring method and device based on dynamic different-period weighting index

Abstract

The invention discloses a mechanical equipment state monitoring method and device based on a dynamic different-period weighting index. The method comprises the following steps: acquiring current vibration data of equipment; based on the current vibration data, according to weighted superposition of waveform factors corresponding to the vibration data in two adjacent time periods, obtaining an early warning index; if the early warning index is larger than a preset early warning threshold value, an early warning signal is sent out; wherein the calculation parameter of the early warning index is determined by historical vibration data of the equipment and a preset fitness function. According to the invention, early warning can be given out in time at the early stage of equipment failure, and the method has high adaptability and high accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment condition monitoring, and in particular to a mechanical equipment condition monitoring method and device based on dynamic heterocyclic weighted indicators. Background Art

[0002] With the development of science and technology, mechanical equipment is widely used in all areas of modern life, work, and production. Currently, mechanical equipment is developing towards high-precision and sophisticated technology, and its operating environment is becoming increasingly complex and changeable. As mechanical equipment continues to operate, factors such as long-term operation, frequently changing working conditions, and harsh operating environments will affect the health of mechanical equipment, thereby reducing its operating efficiency. Therefore, it is necessary to monitor the status of mechanical equipment to promptly identify and resolve equipment problems.

[0003] Existing methods for monitoring the condition of mechanical equipment are mainly divided into two categories: direct observation and information monitoring. The direct observation method relies on the experience and judgment of technicians, and has problems such as strong subjectivity and poor accuracy, making it difficult to achieve comprehensive and accurate real-time monitoring. Information monitoring methods mainly include vibration analysis, oil sample analysis, temperature monitoring, and acoustic emission. Among them, the vibration analysis method is easily affected by noise interference and has difficulty in accurately identifying early faults at low speeds or intermittent operation; the oil sample analysis method has a time lag and cannot achieve real-time monitoring; the temperature monitoring method is insensitive to minor faults and has a response lag; although the acoustic emission method can detect and monitor small cracks, it is easily affected by environmental noise and is relatively expensive. Existing methods have problems with real-time performance, accuracy, and adaptability. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a mechanical equipment status monitoring method and device based on dynamic heterocyclic weighted indicators, which can issue early warnings in the early stages of equipment failures and has strong adaptability and high accuracy.

[0005] An embodiment of the present invention provides a method for monitoring the condition of mechanical equipment based on a dynamic heterocyclic weighted index, comprising: collecting current vibration data of the equipment; Based on the current vibration data, a warning indicator is calculated by weighted superposition of waveform factors corresponding to vibration data in two adjacent time periods; If the warning indicator is greater than the preset warning threshold, a warning signal is issued; The calculation parameters of the early warning indicator are determined by the historical vibration data of the equipment and a preset fitness function.

[0006] As an improvement to the above solution, the calculation parameters of the warning indicator include: a weighted coefficient of the first time parameter, the second time parameter and the waveform factor; The method for determining the calculation parameters includes: Obtaining historical vibration data of the device; Based on the historical vibration data and a preset fitness function, with the goal of minimizing the fitness function, the calculation parameters of the early warning indicator are optimized to obtain optimized calculation parameters.

[0007] As an improvement to the above solution, the early warning indicator is calculated based on the current vibration data and by weighted superposition of the waveform factors corresponding to the vibration data in two adjacent time periods, including: Based on the current vibration data, the warning indicator at the current moment is calculated according to the following formula: F(t1,t2,t,α)=α×f(t2,t1)+(1-α)×f(t1,t) Where F(t1, t2, t, α) is the warning indicator at the current time t, t1 is the first time parameter, t2 is the second time parameter, t ≥ t2 > t1 > 1, and α is the weighting coefficient of the waveform factor; f(t2, t1) and f(t1, t) are the waveform factors of the vibration data collected in the first time period [t-t2, t-t1] and the second time period [t-t1, t], respectively; The calculation formula of the shape factor is: Where x={x1,x2,...,x N}, x represents the vibration data collected during the set time period; N is the total number of data points in the time period.

[0008] As an improvement to the above solution, the value range of the weighting coefficient α is:

[0009] As an improvement to the above solution, the formula of the fitness function Zf is: Among them, x is the first warning time; is the average warning time; σ is the standard deviation of the warning time; y is the warning index value at the first warning; the warning time is determined according to the warning index.

[0010] As an improvement to the above solution, the calculation parameters of the early warning indicators are optimized with the goal of minimizing the fitness function, specifically including: With the goal of minimizing the fitness function, the Hippo optimization algorithm is used to optimize the calculation parameters of the early warning indicators.

[0011] As an improvement to the above solution, the Hippo optimization algorithm specifically includes: Initializing the positions of a plurality of hippopotamus individuals, where the position of each hippopotamus individual is composed of the first time parameter, the second time parameter, and a weighted coefficient of the waveform factor; By simulating the behavior of a hippopotamus searching for food in water, the position is adjusted to perform a global search; Dynamically adjusting said locations to enhance population diversity by simulating the behavior of hippos in defending against predators; Fine-tune the location by conducting a local search, simulating the behavior of a hippopotamus fleeing a predator; When the number of iterations reaches the set maximum number of iterations, the globally optimal parameter combination is output.

[0012] As an improvement to the above solution, the warning threshold is determined according to the Laida criterion.

[0013] The embodiment of the present invention further provides a mechanical equipment condition monitoring device based on a dynamic heterocyclic weighted index, comprising: Data acquisition module, used to collect current vibration data of the equipment; An indicator calculation module, configured to calculate an early warning indicator based on the current vibration data and by weighted superposition of waveform factors corresponding to vibration data in two adjacent time periods; An early warning module is configured to issue an early warning signal if the early warning indicator is greater than a preset early warning threshold; The calculation parameters of the early warning indicator are determined by the historical vibration data of the equipment and a preset fitness function.

[0014] Furthermore, the calculation parameters of the early warning indicator include: a weighted coefficient of the first time parameter, the second time parameter and the waveform factor; The device is also used for: Obtaining historical vibration data of the device; Based on the historical vibration data and a preset fitness function, with the goal of minimizing the fitness function, the calculation parameters of the early warning indicator are optimized to obtain optimized calculation parameters.

[0015] Compared with the prior art, the beneficial effects of the mechanical equipment status monitoring method and device based on dynamic hetero-periodic weighted indicators provided by the embodiment of the present invention are: based on the current vibration data, according to the weighted superposition of the waveform factors corresponding to the vibration data in two adjacent time periods, an early warning indicator is calculated, and an early warning signal is issued when the early warning indicator is greater than the preset early warning threshold, which can timely issue an early warning in the early stage of equipment failure; by designing a fitness function and using an improved optimization algorithm for parameter optimization, the calculation parameters of the early warning indicator can be adjusted according to different equipment and working conditions, thereby improving the adaptability and accuracy of equipment status monitoring. The embodiment of the present invention effectively improves the operational safety and reliability of the equipment by adopting dynamic hetero-periodic weighted indicators to perform mechanical equipment status monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a method for monitoring the condition of mechanical equipment based on dynamic heterocyclic weighted indicators provided by an embodiment of the present invention; Figure 2 It is a time series diagram of early warning indicators of the training set provided by an embodiment of the present invention; Figure 3 This is a fitness function optimization effect diagram provided by an embodiment of the present invention; Figure 4 A time domain diagram corresponding to a training set generated according to the national standard method provided in an embodiment of the present invention; Figure 5 A time domain graph corresponding to a training set generated according to a dynamic hetero-periodic weighted index provided in an embodiment of the present invention; Figure 6 It is a structural diagram of a mechanical equipment condition monitoring device based on dynamic heterocyclic weighted indicators provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0018] See also Figure 1 , Figure 1 The present invention provides a flow chart of a method for monitoring the condition of mechanical equipment based on a dynamic heterocyclic weighted index. The method for monitoring the condition of mechanical equipment based on a dynamic heterocyclic weighted index comprises: S1: collecting current vibration data of the equipment; S2: Based on the current vibration data, calculate the early warning indicator by weighted superposition of the waveform factors corresponding to the vibration data in two adjacent time periods; S3: If the warning indicator is greater than a preset warning threshold, a warning signal is issued; The calculation parameters of the early warning indicator are determined by the historical vibration data of the equipment and a preset fitness function.

[0019] Specifically, the embodiments of the present invention design a dynamic heterocyclic weighted index, or early warning index. Furthermore, by collecting vibration acceleration data of mechanical equipment in real time and calculating the current early warning index value based on this vibration acceleration data, when the early warning index value is detected to be greater than a preset early warning threshold, it indicates that the equipment vibration is abnormal, and an early warning signal is issued to prompt technicians to promptly maintain the equipment. The calculation parameters of the early warning index are adjustable parameters, which are adaptively adjusted according to different equipment or different working conditions.

[0020] As one of the optional embodiments, the calculation parameters of the early warning indicator include: a weighted coefficient of a first time parameter, a second time parameter and a waveform factor.

[0021] As one of the optional embodiments, the early warning indicator is calculated based on the current vibration data according to the weighted superposition of the waveform factors corresponding to the vibration data in two adjacent time periods, including: Based on the current vibration data, the warning indicator at the current moment is calculated according to the following formula: F(t1,t2,t,α)=α×f(t2,t1)+(1-α)×f(t1,t) Where F(t1, t2, t, α) is the warning indicator at the current time t, t1 is the first time parameter, t2 is the second time parameter, t ≥ t2 > t1 > 1, and α is the weighting coefficient of the waveform factor; f(t2, t1) and f(t1, t) are the waveform factors of the vibration data collected in the first time period [t-t2, t-t1] and the second time period [t-t1, t], respectively; The calculation formula of the shape factor is: Where x={x1, x2, ..., x N}, x represents the vibration data collected during the set time period; N is the total number of data points in the time period.

[0022] As one of the optional embodiments, the value range of the weighting coefficient α is:

[0023] By setting the value range of the weighting coefficient α, sufficient freedom can be provided to adjust the weighting strategy, and when using the fitness function for optimization, the convergence process can be accelerated and unnecessary calculations can be reduced, avoiding redundant search processes caused by an excessively large parameter space.

[0024] As one of the optional embodiments, the method for determining the calculation parameters includes: Obtaining historical vibration data of the device; Based on the historical vibration data and a preset fitness function, with the goal of minimizing the fitness function, the calculation parameters of the early warning indicator are optimized to obtain optimized calculation parameters.

[0025] Specifically, based on the historical vibration data corresponding to the mechanical equipment, the early warning indicators corresponding to the historical vibration data are calculated, and a fitness function is set. Then, the early warning indicators and the fitness function are combined, and the optimization algorithm is used to optimize the parameters to obtain the optimized early warning indicator calculation formula for real-time monitoring of the equipment status and fault warning.

[0026] As an optional embodiment, the fitness function Z f The formula is: Among them, x is the first warning time; is the average warning time; σ is the standard deviation of the warning time; y is the warning index value at the first warning; the warning time is determined according to the warning index.

[0027] Specifically, the first warning time is the time when a potential fault is detected and a warning is issued; the average warning time is the average of all warning times recorded in a series of tests (i.e., historical vibration data); and the standard deviation of the warning time is used to measure the dispersion of the warning time in a series of tests.

[0028] The first part of the fitness function formula: It is used to amplify the situation where the first warning time is later than the average warning time, thereby improving the value of the fitness function; when the first warning time is significantly longer than the average warning time, exponential growth can impose heavy penalties, accelerate the growth of the fitness function value, and prompt the optimization function to avoid this situation.

[0029] The second part of the fitness function formula, -log(y+1), encourages high early warning indicator values. When y is large, the growth rate of the logarithmic function slows down, but the overall growth remains negative, causing the fitness function value to decrease. This design encourages early warnings when more serious anomalies are detected, thereby enabling early identification of potential major problems. The y+1 prevents the logarithmic function from failing to calculate when y is zero, while also ensuring that the logarithmic input is positive.

[0030] As one of the optional embodiments, the optimization of the calculation parameters of the early warning indicator with the goal of minimizing the fitness function specifically includes: With the goal of minimizing the fitness function, the Hippo optimization algorithm is used to optimize the calculation parameters of the early warning indicators.

[0031] As one of the optional embodiments, the Hippo optimization algorithm specifically includes: Initializing the positions of a plurality of hippopotamus individuals, where the position of each hippopotamus individual is composed of the first time parameter, the second time parameter, and a weighted coefficient of the waveform factor; By simulating the behavior of a hippopotamus searching for food in water, the position is adjusted to perform a global search; Dynamically adjusting said locations to enhance population diversity by simulating the behavior of hippos in defending against predators; Fine-tune the location by conducting a local search, simulating the behavior of a hippopotamus fleeing a predator; When the number of iterations reaches the set maximum number of iterations, the globally optimal parameter combination is output.

[0032] Specifically, the Hippopotamus Optimization (HO) algorithm is inspired by the behavior of hippos in their natural environments. It simulates their movements in rivers or ponds and uses global and local search strategies to find the optimal solution. The Hippopotamus Optimization algorithm mainly includes the following stages: Initialization: During the initialization phase, the HO algorithm randomly generates a certain number of individuals (i.e., search agents) and assigns them positions. The parameters t1, t2, and α of these individuals are initialized to a range. For example, t1 might be between 1 and 5, t2 between 2 and 6, and α between 1 / 10 and 1 (depending on the upper and lower bounds set). Each individual's parameters may be different, representing a different candidate solution. The positions of the randomly generated hippopotamus individuals serve as the initial population.

[0033] Exploration Phase: During the exploration phase, the algorithm simulates the behavior of a hippopotamus searching for food in a body of water, conducting a global search process that explores the entire search space. For optimization tasks, the exploration phase helps avoid being trapped in local optima. During this phase, the algorithm fully explores the search space by randomly adjusting parameters—specifically, by varying t1, t2, and α. For example, individual hippos, guided by "food," move to new areas, representing the exploration of parameters t1, t2, and α within the search space. The goal of this phase is to ensure that the initial parameter selection covers as wide a range as possible, thereby identifying potential excellent solutions.

[0034] Defense Phase: During the defense phase, the algorithm simulates the behavior of a hippopotamus defending itself against predators. The algorithm enhances the diversity of the population and its global search capabilities, introducing more randomness so that the search is not confined to a specific area. Specifically, this phase improves the robustness of the algorithm by dynamically adjusting the parameters t1, t2, and α of each individual. For example, certain parameters may be increased or decreased in certain individuals, allowing the algorithm to remain stable in the face of a more complex search space and thus avoid premature convergence. The defense phase is a key part of the algorithm in avoiding being trapped in local optima.

[0035] Escape Phase: During the escape phase, the algorithm simulates the behavior of a hippopotamus fleeing a predator, adjusting parameters more precisely and conducting a local search to ensure a more accurate solution. During this phase, fine-tuning t1, t2, and α ensures a more precise optimal parameter combination. By reducing the magnitude of parameter changes during the escape phase, the algorithm gradually approaches the optimal solution.

[0036] Through the synergy of the above stages, the Hippo optimization algorithm can efficiently balance exploration and exploitation in the search space, thereby finding the global optimal solution to the optimization problem.

[0037] As an optional embodiment, the warning threshold is determined according to the Laida criterion.

[0038] Specifically, the Laida criterion, also known as the 3σ criterion, is used to determine the warning threshold. The warning threshold is calculated by summing the mean and standard deviation of the historical vibration data. It's important to note that the warning thresholds obtained for different datasets will vary, but these differences are minimal and can be further adjusted and optimized by optimizing the fitness function.

[0039] In a specific example, for bearing condition monitoring, two PCB 352C33 unidirectional accelerometers were used to acquire vibration data over the entire bearing lifecycle. These sensors were magnetically fixed to the horizontal and vertical positions of the test bearing. Signal acquisition was performed using a DT9837 portable dynamic signal collector, with a sampling frequency of 25.6 kHz, a sampling interval of 1 minute, and each sampling period lasting 1.28 seconds. The collected bearing vibration data is shown in Table 1.

[0040] Table 1 bearings Damage location Total number of samples life Bearing1-2 outer ring 161 2h41min Bearing1-3 outer ring 158 2h38min Bearing2-2 outer ring 161 2h41min Bearing3-4 Inner ring 1515 25h15min The vibration data of Bearing1-3 bearings are used as training sets, and the vibration data of the other three bearings are used as test sets. First, according to the initial calculation parameters of the set early warning indicators, t1 = 2, t2 = 4 and Calculate the early warning indicators corresponding to the training set, and the calculation results are as follows Figure 2 As shown, from Figure 2As can be seen in the figure, the indicator curve is relatively stable for the first 50 minutes, but after 55 minutes, it begins to fluctuate dramatically. With this indicator, the time when the fluctuation begins represents the onset of the fault. To eliminate the subjectivity of manually defining the fluctuation location, a unified early warning standard is needed to locate the fluctuation point and effectively monitor the equipment status. To determine the fluctuation location, the Laida criterion is used to set the early warning threshold. By calculating the sum of the mean and standard deviation of the training set data, the alarm threshold is 1.3.

[0041] Furthermore, according to the fitness function, the Hippo optimization algorithm is used to iteratively optimize the parameters, where the number of Hippo individuals is set to 50 and the maximum number of iterations is set to 100. The optimization effect of the fitness function is as follows Figure 3 As shown in Figure 2, by applying the Hippo optimization algorithm, the algorithm successfully avoided the dilemma of falling into the local optimal solution and reached the optimal fitness value in the sixth generation. During the optimization process, the Hippo optimization algorithm effectively enhanced the early warning indicators, and the final optimization parameters were: t1 = 1, t2 = 5 and

[0042] In order to verify the effect of the dynamic heterogeneous period weighted index (i.e., early warning index) of the embodiment of the present invention, please refer to Figure 4 and Figure 5 , Figure 4 The time domain diagram corresponding to the training set generated according to the national standard method provided in the embodiment of the present invention, Figure 5 The time domain diagram corresponding to the training set generated according to the dynamic hetero-periodic weighted index provided in the embodiment of the present invention. It can be seen that after the training set data is re-expressed using the dynamic hetero-periodic weighted index, the obtained warning time is 116 minutes. According to relevant national standards, the prescribed warning time is 150 minutes. Compared with the standard value, the optimized warning time is advanced by 34 minutes, fully demonstrating the significant effect of the dynamic hetero-periodic weighted index in optimizing the warning time.

[0043] Verification was performed using a test set, as shown in Table 2, which demonstrates the effectiveness of the test set. It can be seen that the warning time derived from the dynamic heterogeneous weighted index of the present invention can be as early as 27 minutes earlier than that of traditional methods, thereby providing early warning of potential risks. This present invention not only improves the timeliness of warnings but also effectively enhances the responsiveness of the equipment monitoring system, providing more time to prevent potential risks. The early warning indicator in the embodiment of the present invention comprehensively evaluates the overall characteristics of the vibration data by combining the time series data in different time periods. The two time periods in the formula cover the earlier and more recent time series data respectively, so that the indicator can simultaneously reflect the long-term trend and recent changes, which helps to fully understand the operating status of the equipment and identify potential anomalies and faults. The indicator can quantify the degree of extreme fluctuations in the time series data. Extreme fluctuations are often early signs of equipment failure, such as bearing wear, breakage or poor lubrication. After combining data from different time periods, the weighted waveform factor can more sensitively capture these abnormal fluctuations and improve the accuracy and timeliness of fault monitoring and detection. The weighting coefficient in the indicator controls the contribution ratio of historical data and current data in the final waveform factor, so that the dynamic heterocyclic weighted indicator can not only retain the useful information in the historical data, but also quickly respond to changes in the current data. By optimizing and adjusting the indicator parameters through the optimization algorithm, the influence of historical data and current data can be dynamically balanced according to the specific working conditions and monitoring targets of the equipment, so that the dynamic heterocyclic weighted indicator can be widely used in various mechanical equipment and their changing operating environments, significantly improving the accuracy and adaptability of monitoring.

[0044] The embodiments of this invention can effectively monitor vibration fluctuations in equipment and promptly identify potential fault hazards. They are applicable not only to specific types of mechanical equipment but also to a wide range of mechanical equipment for vibration status analysis. By accurately analyzing equipment vibration signals, this invention can provide early warning of faults during operation, effectively improving the safety and reliability of equipment operation.

[0045] Correspondingly, the present invention also provides a mechanical equipment state monitoring device based on dynamic heterocyclic weighted indicators, which can implement all processes of the mechanical equipment state monitoring method based on dynamic heterocyclic weighted indicators in the above embodiment.

[0046] See also Figure 6 , Figure 6 The structure diagram of a mechanical equipment condition monitoring device based on a dynamic heterocyclic weighted index provided by an embodiment of the present invention is as follows. The mechanical equipment condition monitoring device based on a dynamic heterocyclic weighted index comprises: a data acquisition module 601 for acquiring current vibration data of the equipment; An indicator calculation module 602 is configured to calculate an early warning indicator based on the current vibration data and by weighted superposition of waveform factors corresponding to vibration data in two adjacent time periods; The warning module 603 is configured to issue a warning signal if the warning indicator is greater than a preset warning threshold; The calculation parameters of the early warning indicator are determined by the historical vibration data of the equipment and a preset fitness function.

[0047] Preferably, the calculation parameters of the early warning indicator include: a weighted coefficient of the first time parameter, the second time parameter and the waveform factor; The device is also used for: Obtaining historical vibration data of the device; Based on the historical vibration data and a preset fitness function, with the goal of minimizing the fitness function, the calculation parameters of the early warning indicator are optimized to obtain optimized calculation parameters.

[0048] Preferably, the early warning indicator is calculated based on the current vibration data and by weighted superposition of waveform factors corresponding to vibration data in two adjacent time periods, including: Based on the current vibration data, the warning indicator at the current moment is calculated according to the following formula: F(t1,t2,t,α)=α×f(t2,t1)+(1-α)×f(t1,t) Where F(t1, t2, t, α) is the warning indicator at the current time t, t1 is the first time parameter, t2 is the second time parameter, t ≥ t2 > t1 > 1, and α is the weighting coefficient of the waveform factor; f(t2, t1) and f(t1, t) are the waveform factors of the vibration data collected in the first time period [t-t2, t-t1] and the second time period [t-t1, t], respectively; The calculation formula of the shape factor is: Where x={x1,x2,...,x N}, x represents the vibration data collected during the set time period; N is the total number of data points in the time period.

[0049] Preferably, the value range of the weighting coefficient α is:

[0050] Preferably, the fitness function Z f The formula is: Among them, x is the first warning time; is the average warning time; σ is the standard deviation of the warning time; y is the warning index value at the first warning; the warning time is determined according to the warning index.

[0051] Preferably, the optimization of the calculation parameters of the early warning indicator with the goal of minimizing the fitness function specifically includes: With the goal of minimizing the fitness function, the Hippo optimization algorithm is used to optimize the calculation parameters of the early warning indicators.

[0052] Preferably, the Hippo optimization algorithm specifically includes: Initializing the positions of a plurality of hippopotamus individuals, where the position of each hippopotamus individual is composed of the first time parameter, the second time parameter, and a weighted coefficient of the waveform factor; By simulating the behavior of a hippopotamus searching for food in water, the position is adjusted to perform a global search; Dynamically adjusting said locations to enhance population diversity by simulating the behavior of hippos in defending against predators; Fine-tune the location by conducting a local search, simulating the behavior of a hippopotamus fleeing a predator; When the number of iterations reaches the set maximum number of iterations, the globally optimal parameter combination is output.

[0053] Preferably, the warning threshold is determined according to the Laida criterion.

[0054] In the specific implementation, the working principle, control process and technical effect of the mechanical equipment status monitoring device based on dynamic hetero-periodic weighted indicators provided by the embodiment of the present invention are the same as those of the mechanical equipment status monitoring method based on dynamic hetero-periodic weighted indicators in the above embodiment, and will not be repeated here.

[0055] The embodiment of the present invention provides a method and device for monitoring the status of mechanical equipment based on dynamic heterocyclic weighted indicators, the beneficial effects of which are: by calculating the early warning indicator based on the current vibration data and the weighted superposition of the waveform factors corresponding to the vibration data in two adjacent time periods, and issuing an early warning signal when the early warning indicator is greater than the preset early warning threshold, it is possible to issue an early warning in the early stage of equipment failure; by designing a fitness function and using an improved optimization algorithm for parameter optimization, it is possible to adjust the calculation parameters of the early warning indicator according to different equipment and working conditions, thereby improving the adaptability and accuracy of equipment status monitoring. The embodiment of the present invention effectively improves the operational safety and reliability of the equipment by adopting dynamic heterocyclic weighted indicators to perform mechanical equipment status monitoring.

[0056] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A mechanical equipment condition monitoring method based on dynamic heterocyclic weighted indicators, characterized in that: include: Collect current vibration data of the equipment; Based on the current vibration data, a warning indicator is calculated by weighted superposition of waveform factors corresponding to vibration data in two adjacent time periods; If the warning indicator is greater than the preset warning threshold, a warning signal is issued; The calculation parameters of the early warning indicator are determined by the historical vibration data of the equipment and a preset fitness function.

2. The mechanical equipment condition monitoring method based on dynamic heterocyclic weighted index according to claim 1 is characterized in that: The calculation parameters of the early warning indicator include: a weighted coefficient of a first time parameter, a second time parameter and a waveform factor; The method for determining the calculation parameters includes: Obtaining historical vibration data of the device; Based on the historical vibration data and a preset fitness function, with the goal of minimizing the fitness function, the calculation parameters of the early warning indicator are optimized to obtain optimized calculation parameters.

3. The method for monitoring the condition of mechanical equipment based on dynamic heterocyclic weighted indicators according to claim 2, characterized in that: The early warning indicator is calculated based on the current vibration data and by weighted superposition of waveform factors corresponding to vibration data in two adjacent time periods, including: Based on the current vibration data, the warning indicator at the current moment is calculated according to the following formula: F(t1,t2,t,α)=α×f(t2,t1)+(1-α)×f(t1,t) Wherein, F(t1, t2, t, α) is the warning indicator at the current time t, t1 is the first time parameter, t2 is the second time parameter, t ≥ t2 > t1 > 1, and α is the weighting coefficient of the waveform factor; f(t2, t1) and f(t1, t) are the waveform factors of the vibration data collected in the first time period [t-t2, t-t1] and the second time period [t-t1, t], respectively; The calculation formula of the shape factor is: Where x={x1, x2, ..., x N }, x represents the vibration data collected during the set time period; N is the total number of data points in the time period.

4. The method for monitoring the condition of mechanical equipment based on dynamic heterocyclic weighted indicators according to claim 3, characterized in that: The value range of the weighting coefficient α is:

5. The method for monitoring the condition of mechanical equipment based on dynamic heterocyclic weighted indicators according to claim 1, characterized in that: The fitness function Z f The formula is: Among them, x is the first warning time; is the average warning time; σ is the standard deviation of the warning time; y is the warning index value at the first warning; the warning time is determined according to the warning index.

6. The method for monitoring the condition of mechanical equipment based on dynamic heterocyclic weighted indicators according to claim 2, characterized in that: The optimization of the calculation parameters of the early warning indicator with the goal of minimizing the fitness function specifically includes: With the goal of minimizing the fitness function, the Hippo optimization algorithm is used to optimize the calculation parameters of the early warning indicators.

7. The method for monitoring the condition of mechanical equipment based on dynamic heterocyclic weighted indicators according to claim 6, characterized in that: The Hippo optimization algorithm specifically includes: Initializing the positions of a plurality of hippopotamus individuals, where the position of each hippopotamus individual is composed of the first time parameter, the second time parameter, and a weighted coefficient of the waveform factor; By simulating the behavior of a hippopotamus searching for food in water, the position is adjusted to perform a global search; Dynamically adjusting said locations to enhance population diversity by simulating the behavior of hippos in defending against predators; Fine-tune the location by conducting a local search, simulating the behavior of a hippopotamus fleeing a predator; When the number of iterations reaches the set maximum number of iterations, the globally optimal parameter combination is output.

8. The method for monitoring the condition of mechanical equipment based on dynamic heterocyclic weighted indicators according to claim 1, characterized in that: The warning threshold is determined according to the Laida criterion.

9. A mechanical equipment condition monitoring device based on dynamic heterocyclic weighted indicators, characterized in that: include: Data acquisition module, used to collect current vibration data of the equipment; An indicator calculation module, configured to calculate an early warning indicator based on the current vibration data and by weighted superposition of waveform factors corresponding to vibration data in two adjacent time periods; An early warning module is configured to issue an early warning signal if the early warning indicator is greater than a preset early warning threshold; The calculation parameters of the early warning indicator are determined by the historical vibration data of the equipment and a preset fitness function.

10. The mechanical equipment condition monitoring device based on dynamic heterocyclic weighted index according to claim 9, characterized in that: The calculation parameters of the early warning indicator include: a weighted coefficient of a first time parameter, a second time parameter and a waveform factor; The device is also used for: Obtaining historical vibration data of the device; Based on the historical vibration data and a preset fitness function, with the goal of minimizing the fitness function, the calculation parameters of the early warning indicator are optimized to obtain optimized calculation parameters.

Images