Intelligent health state assessment method for building electromechanical equipment

Abstract

The invention provides an intelligent health state assessment method for building electromechanical equipment, and relates to the technical field of equipment state assessment, and the method comprises the steps: building a temperature model through obtaining temperature curves of monitored equipment at different powers, obtaining a predicted temperature curve according to a next task, and carrying out the analysis to obtain a predicted temperature score; acquiring a previous vibration curve of the monitored equipment, analyzing the previous vibration curve, acquiring a current vibration score, acquiring a historical task similar to a next task, acquiring a historical temperature score and a historical vibration score, acquiring a health score in combination with an intermediate task, and analyzing the health degree; according to the method, the next task is associated with the actual physical state and the historical state of the equipment to generate the health score, so that the accuracy of equipment health state assessment is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment status evaluation, and specifically to an intelligent health status evaluation method for building mechanical and electrical equipment. Background Technique

[0002] Building mechanical and electrical equipment plays an indispensable role in modern buildings and covers multiple key subsystems. The efficient operation of these equipment not only directly affects the comfort and safety of buildings, but also has an important impact on energy consumption and operating costs. With the development of intelligent building and Internet of Things technologies, the demand for automated monitoring and management of building mechanical and electrical equipment is increasing day by day to achieve real-time monitoring, early warning and optimal control of the equipment operation status, thereby improving the overall building management efficiency and user experience.

[0003] Currently, the health status evaluation of building mechanical and electrical equipment mainly relies on the monitoring and analysis of basic parameters such as temperature and vibration. However, traditional methods have certain limitations in dealing with multi-dimensional and dynamically changing operation data and are difficult to comprehensively and accurately reflect the actual operation status of the equipment. Especially at different operating powers and task durations, the temperature curves and vibration characteristics of the equipment are complex and variable, and a single state or simple model is difficult to effectively predict and evaluate the health status of the equipment.

[0004] The above information disclosed in the background technique section is only used to enhance the understanding of the background of the present disclosure, so it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent health status evaluation method for building mechanical and electrical equipment to solve the problems raised in the above background technique.

[0006] To achieve the above purpose, the present invention provides the following technical solutions: An intelligent health status evaluation method for building mechanical and electrical equipment, the specific steps include: Step 1: Obtain the temperature curves of the monitored equipment at different operating powers, use the operating power and the task duration of the temperature curve as the training set, train with the corresponding temperature curve labels to obtain a temperature model, obtain the required operating power and task duration of the monitored equipment and input them into the temperature model to obtain the predicted temperature curve; Step 2: Analyze the predicted temperature curve, obtain the over-temperature rate through the temperature threshold, obtain the temperature change rate through the reference temperature change rate, obtain the volatility and the cumulative heat load, and form a predicted temperature score; Step 3: Obtain the vibration curve during the last task and the vibration curve during normal tasks of the monitored device. Obtain the vibration curve during normal tasks of the device, and combine the vibration curve during normal tasks to obtain the amplitude deviation, stable volatility, proportion of stable time, and shock attenuation degree of the vibration curve during the last task. The shock attenuation degree is obtained through the average change rate to form the current vibration score; Step 4: Obtain historical tasks similar to the next task. The similarity is judged by the similarity degree, and obtain the temperature curve and vibration curve of the historical tasks. Refer to the construction method of the predicted temperature score and combine the temperature curve of the historical tasks to construct the historical temperature score. Refer to the current vibration score construction method and combine the vibration curve of the historical tasks to construct the historical vibration score; Step 5: Obtain the power and task duration of each intermediate task experienced by the device from the historical task to the previous task, obtain the device health score, set a health threshold, and judge the ability of the next task according to the health status.

[0007] Further, obtain the temperature curves of the monitored device at different operating powers. The horizontal axis of the temperature curve is time, and the vertical axis is temperature. The time is the moment between the start of the task and the end of the task when the device starts. The temperature is the temperature obtained by the temperature monitor equipped on the device itself. The temperature curves at different operating powers are obtained through experiments on the same model devices of the monitored device; Take the domain length of the power and temperature curves as the training set. The domain length is the task duration required by the device, and take the corresponding temperature curve as the label, and input it into the linear regression model for training to obtain the temperature model.

[0008] Further, obtain the operating power and task duration required for the next task, and input the operating power and task duration into the temperature model to obtain the predicted temperature curve.

[0009] Further, analyze the predicted temperature curve, obtain the temperature threshold of the monitored device, and obtain the over-temperature rate. The basis formula is as follows:

[0010] Among them, is the value of the over-temperature rate, is the highest value of the predicted temperature curve, is the temperature threshold, is the coefficient, ; Obtain the volatility. The logic is as follows: Obtain the average value and standard deviation of the predicted temperature curve to obtain the volatility. The basis formula is as follows:

[0011] Among them, is the value of volatility, is the standard deviation of the predicted temperature curve, is the average value of the predicted temperature curve, is the task duration of the next task, is the high-temperature duration; The high-temperature duration is the duration when the value of the predicted temperature curve exceeds 80% of the temperature threshold.

[0012] Furthermore, obtain the temperature change rate, and the logic is as follows: Obtain the change rate curve and the average change rate curve of the predicted temperature curve, obtain the reference temperature change rate of the monitored device, judge the maximum value of its absolute value according to the change rate curve, and construct the temperature change rate. The formula is as follows:

[0013] where, is the value of the temperature change rate, represents the maximum value selection function, is the maximum value of the absolute value of the change rate curve, is the average change rate, is the reference temperature change rate; Obtain the cumulative heat load, and the logic is as follows:

[0014] where, is the cumulative heat load, is the predicted temperature curve, is the temperature threshold, is the duration of the next task; Construct the predicted temperature score, and the formula is as follows:

[0015] where, is the predicted temperature score, is the over-temperature rate, is the volatility, is the temperature change rate, is the cumulative heat load, , , and are coefficients, .

[0016] Further, obtain the vibration curve of the monitored device during a single task, and obtain the vibration curve of the device during normal tasks. The normal tasks refer to the operation process at a specific operating power and for a specific working duration calibrated by the merchant. Obtain the amplitude range of the device during normal tasks. The horizontal axis of the vibration curve is time, and the vertical axis is amplitude. Construct the current vibration score according to the following formula:

[0017] Among them, is the current vibration score, is the amplitude deviation degree, is the stable volatility, is the proportion of stable time, is the impact attenuation degree; The acquisition logic of the amplitude deviation degree is as follows:

[0018] Among them, is the amplitude deviation degree, represents the maximum selection function, is the maximum amplitude of the vibration curve during the previous task, is the maximum value of the amplitude range during normal tasks; The acquisition logic of the stable volatility is as follows:

[0019] Among them, is the stable volatility, represents the maximum selection function, is the standard deviation of the vibration curve during the previous task, is the standard deviation of the vibration curve during normal tasks.

[0020] Further, the acquisition logic of the proportion of stable time is as follows:

[0021] Among them, is the proportion of stable time, is the reasonable time, is the task duration; The reasonable time is the duration during which the amplitude of the vibration curve during the previous task is within the amplitude range during normal tasks; The acquisition logic of the impact attenuation degree is as follows:

[0022] Among them, is the impact attenuation degree, represents the maximum selection function, is the number of shock events detected in the vibration curve during the previous task, is the reference shock number during normal tasks; The logic for obtaining the number of shock events is as follows: The vibration curve is segmented at equal time intervals to obtain multiple curve segments. The average rate of change of each curve segment is obtained according to the following formula:

[0023] where, is the rate of change of amplitude of the th curve segment, is the amplitude at the end of the th curve segment, is the initial amplitude of the th curve segment, is the time length of the curve segment, is the time retrieval variable of the curve segment, , , is the number of curve segments; Obtain the rate-of-change threshold, and obtain the number of curve segments whose amplitude rate of change exceeds the rate-of-change threshold, which is the number of shock events.

[0024] Furthermore, obtain historical tasks similar to the next task. The historical tasks are obtained through work logs, and the similarity is judged by the operating power and task duration. The formula for similarity is as follows:

[0025] where, is the similarity, is the operating power during the next task, is the operating power of the historical task, is the task duration of the next task, is the task duration of the historical task; Select the historical task with the highest similarity, and obtain the temperature curve and vibration curve of this historical task. Refer to the construction method of the predicted temperature score and combine the temperature curve of the historical task to construct the historical temperature score. Refer to the current vibration score construction method and combine the vibration curve of the historical task to construct the historical vibration score.

[0026] Furthermore, obtain the power and task duration of each intermediate task experienced from the historical task to the previous task. The intermediate tasks are obtained through work logs, and a health score is constructed according to the following formula:

[0027] where, is the health score, For predicting the temperature score, For the historical temperature score, For the current vibration score, For the historical vibration score, Indicates the operating power of the Indicates the task duration of the intermediate task number retrieval variable, , , is the total number of director tasks; Set the health threshold and compare the health score with the health threshold: When the health score is less than the health threshold, it means that the status of the currently monitored device can meet the next task; When the health score is greater than or equal to the health threshold, adjust the power and task duration of the device participating in this task, obtain a new predicted temperature curve, repeat steps 2 to 5 again and judge whether the health score is less than the health threshold. If the health score is less than the health threshold, it means that the currently monitored device can meet the next task. When the power and task duration of this task are adjusted 5 times and the health score still cannot be less than the health threshold, an alarm is issued.

[0028] Compared with the prior art, the beneficial effects of the present invention are: The present invention obtains the required power and task duration according to the next task volume and inputs them into the trained temperature model to obtain a predicted temperature curve, analyzes the predicted temperature curve to obtain a predicted temperature score, obtains the vibration curve of the device's previous task and analyzes it to obtain the current vibration score, obtains similar historical tasks according to the next task, and judges the temperature curve and vibration curve of the historical tasks to obtain the historical temperature score and historical vibration score, obtains the work history from the historical tasks to the previous task, generates a health score and guides the operation. By connecting the next task with the actual physical state of the device and referring to similar historical tasks at the same time, comparing the states of the historical tasks, the previous task and the next task, and generating a health score, the present invention ensures the accuracy of the device health status evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0030] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0031] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. Words such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Upper", "lower", "left", "right", etc. are only used to represent relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0032] Embodiment:

[0033] Please refer to Figure 1 , the present invention provides a technical solution: Step 1: Obtain the temperature curves of the monitored device at different operating powers. Use the operating power and the task duration of the temperature curve as the training set, and train with the corresponding temperature curve labels to obtain a temperature model. Obtain the required operating power and task duration of the monitored device and input them into the temperature model to obtain the predicted temperature curve; The said Step 1 includes the following contents: Step 101: Obtain the temperature curves of the monitored device at different operating powers. The horizontal axis of the temperature curve is time, and the vertical axis is temperature. The time is the moment between the start of the task and the end of the task when the device starts. The temperature is the temperature obtained by the temperature monitor equipped with the device itself. The temperature curves at different operating powers are obtained through experiments on the same model devices of the monitored device; Use the domain length of the power and temperature curve as the training set. The domain length is the task duration required by the device. Use the corresponding temperature curve as the label and input it into a linear regression model for training to obtain a temperature model.

[0034] In this step, the temperature curves of the device at different operating powers are obtained through experiments, which can comprehensively reflect the temperature change of the device in each power state. The accurate acquisition of the temperature curve provides high-quality basic data for the subsequent training of the temperature model, ensuring that the model can accurately capture the thermal characteristics of the device at different powers. In addition, the data obtained through standardized experimental methods enhances the generality and reliability of the model, facilitating effective prediction in practical applications.

[0035] Step 102: Obtain the operating power and task duration required for the next task, input the operating power and task duration into the temperature model, and obtain the predicted temperature curve.

[0036] In this step, by inputting the required operating power and task duration into the trained temperature model, the temperature change trend of the device in the next task can be predicted in advance. This prediction not only helps the operation and maintenance personnel identify potential overheating risks in advance, but also provides estimated data for subsequent temperature analysis and scoring, optimizing the feedforward control ability of the entire monitoring process and ensuring the safety and efficiency of the device during operation.

[0037] Step 2: Analyze the predicted temperature curve, obtain the over-temperature rate through the temperature threshold, obtain the temperature change rate through the baseline temperature change rate, obtain the volatility and cumulative heat load, and form a predicted temperature score; The said Step 2 includes the following contents: Step 201: Analyze the predicted temperature curve, obtain the temperature threshold of the monitored device, and obtain the over-temperature rate. The basis formula is as follows:

[0038] Wherein, is the value of the over-temperature rate, is the highest value of the predicted temperature curve, is the temperature threshold, is the coefficient, .

[0039] By reasonably defining and adjusting the relationships between various variables, the over-temperature risk of the device can be accurately quantified, providing a scientific basis for the assessment of the device's thermal health status, ensuring that potential overheating problems can be identified and prevented in a timely manner in subsequent steps, and guaranteeing the safe and stable operation of the device. As increases, grows exponentially, meaning that the closer or higher the device temperature is to the threshold, the over-temperature rate rises significantly, reflecting a higher overheating risk. On the contrary, if increases, that is, the safe temperature upper limit of the device is raised. Under the same , will decrease, indicating that the device is still considered to be operating safely at a higher temperature. In addition, the existence of makes more sensitive to changes in the temperature ratio, enhancing the response ability of the formula to over-temperature situations.

[0040] By analyzing the predicted temperature curve and calculating the over-temperature rate, it is possible to accurately assess whether there is a risk of exceeding the safe temperature threshold during the mission of the device. Obtaining this indicator helps to promptly detect potential overheating problems and prevent damage or performance degradation of the device caused by excessive temperature. At the same time, the calculation of the over-temperature rate provides a necessary reference for subsequent volatility and temperature change rate, ensuring that the temperature score can comprehensively reflect the thermal stress state of the device. As an important part of the temperature score, the over-temperature rate enhances the sensitivity and accuracy of the overall evaluation system, effectively guaranteeing the safety and reliability of the device operation.

[0041] Step 202: Obtain the volatility, with the logic as follows: Obtain the mean and standard deviation of the predicted temperature curve to obtain the volatility, based on the following formula:

[0042] Where, is the value of the volatility, is the standard deviation of the predicted temperature curve, is the mean of the predicted temperature curve, is the mission duration of the next mission, is the high-temperature duration; By combining the amplitude of temperature fluctuations and the duration of high temperature, it is possible to comprehensively evaluate the temperature stability of the device and potential thermal instability factors during operation. It not only helps to identify potential temperature fluctuation risks during device operation but also provides important data support for subsequent predicted temperature scoring, ensuring higher accuracy and reliability in the overall solution for evaluating the thermal health state of the device, thereby enhancing the operation safety and efficiency of the device.

[0043] Specifically reflects the degree of temperature fluctuation of the device during the predicted mission, comprehensively considering the relative volatility of the temperature curve and the duration of the high-temperature state. represents the standard deviation of the predicted temperature curve, measuring the severity of temperature changes; is the mean of the predicted temperature curve, used to standardize the fluctuation amplitude and reflect the overall temperature stability; represents the duration when the temperature exceeds 80% of the temperature threshold, is the total mission duration, measuring the proportion of the high-temperature state in the entire mission. As increases, increases linearly, indicating enhanced temperature volatility; conversely, an increase in will cause to decrease linearly, indicating that at a higher average temperature, the relative volatility decreases. An increase in , reflecting the prolongation of the duration of the high-temperature state, while the increase of will linearly decrease , meaning that the proportion of the high-temperature state in a longer task duration decreases.

[0044] The high-temperature duration is the duration when the predicted temperature curve value exceeds 80% of the temperature threshold.

[0045] By measuring the stability of the temperature curve, the volatility provides information on the consistency of the temperature change of the device during the task. High volatility may indicate unstable factors during the operation of the device, and measures need to be taken in a timely manner to ensure the stable control of the device temperature. The acquisition of volatility not only reflects the temperature stability of the device, but also provides an important quantitative indicator for the comprehensive temperature score. The introduction of this indicator enables the temperature score to more comprehensively evaluate the thermal dynamic characteristics of the device and improve the scientific nature of the overall evaluation. At the same time, the data support of volatility helps in the calculation of the health score in subsequent steps to ensure the stable operation and healthy state of the device in various tasks.

[0046] Step 203: Obtain the temperature change rate, the logic is as follows: Obtain the change rate curve and the average change rate curve of the predicted temperature curve, obtain the reference temperature change rate of the monitored device, judge the maximum value of its absolute value according to the change rate curve, and construct the temperature change rate. The formula is as follows:

[0047] Wherein, is the value of the temperature change rate, represents the maximum value selection function, is the maximum value of the absolute value of the change rate curve, is the average change rate, is the reference temperature change rate.

[0048] Specifically, it reflects the degree of the temperature change rate of the device during the predicted task, and measures the severity of the temperature fluctuation and the overall change trend of the device. represents the maximum value of the absolute value of the temperature change rate curve, is the average value of the temperature change rate, is the reference temperature change rate, which is used for the calculation of the standardized temperature change rate. The function is used to select the larger of the two calculated values to ensure that the temperature change rate can comprehensively reflect the most extreme situation during the temperature change process of the device. depends on the larger of the ratio of the maximum absolute value of the temperature change rate to the reference temperature change rate and the ratio of its average change rate to the reference temperature change rate. When the peak value of the temperature change rate is significantly higher than the reference temperature change rate, It will be mainly determined by the peak, and vice versa. As increases, increases linearly, indicating that more drastic temperature changes occur during the operation of the device, and the potential thermal stress risk also increases accordingly. On the contrary, if increases, and the growth rate is not large, will also increase correspondingly, but the amplitude depends on relative to change. As the reference temperature change rate, it plays a role in standardizing the temperature change rate. Increasing value will decrease and , thus reducing , and vice versa. The temperature change rate can be flexibly adjusted according to the specific operating characteristics and safety standards of the device, improving the accuracy and applicability of the evaluation.

[0049] The temperature change rate evaluates the smoothness and response ability of the device's temperature change during the mission by analyzing the rate of temperature change. A higher temperature change rate may indicate a potential overheating risk during rapid temperature changes of the device, and measures need to be taken to avoid failures caused by excessive temperature fluctuations of the device. The evaluation of the temperature change rate not only improves the fineness of the temperature score but also provides more specific guidance for the thermal management of the device. The introduction of this index makes the temperature scoring system more comprehensive, can more accurately reflect the performance of the device under different temperature change conditions, and promotes the optimization and improvement of the device during actual operation.

[0050] Step 204: Obtain the cumulative heat load, the logic is as follows:

[0051] Among them, is the cumulative heat load, is the predicted temperature curve, is the temperature threshold, is the duration of the next mission; Specifically reflects the total heat accumulation degree that the device bears during the entire mission, and measures the thermal accumulation level suffered by the device during long-term operation. As as a whole increases, the heat accumulated by the device during the mission increases, resulting in increasing, reflecting that the thermal load borne by the device increases, and the potential thermal risk also rises accordingly. On the other hand, the increase of means that the device can withstand a higher temperature without being regarded as overheating, so under the same heat accumulation situation, will decrease, indicating that the thermal load pressure of the device is relatively reduced. At the same time, The increase will dilute the impact of heat accumulation because the total task duration becomes longer, and the heat accumulation is spread over a longer time, resulting in decreasing, which means that at a longer task duration, the device bears a relatively lower heat load per unit time. The calculation of

[0052] can not only reflect the heat accumulation situation of the device during long-term operation, but also provide a key quantitative basis for device state prediction. This index plays an important role in connecting the temperature curve and the device health score in the overall scheme, ensuring that the device can effectively manage the heat load during continuous operation, preventing device failures or performance degradation caused by cumulative overheating, and thus improving the operation safety and reliability of the device.

[0053] Step 205: Construct the predicted temperature score, based on the following formula:

[0054] where is the predicted temperature score, is the over-temperature rate, is the volatility, is the temperature change rate, is the cumulative heat load, , , and are coefficients, .

[0055] Specifically reflects the overall temperature health status of the device. By comprehensively considering four temperature-related indicators: over-temperature rate, volatility, temperature change rate, and cumulative heat load, it quantifies the temperature performance and health status of the device during operation. , , and and their sum is 1, respectively representing the relative importance of each indicator in the temperature score. The setting of these weight coefficients ensures that the contribution degree of different indicators to the final score can be flexibly adjusted according to actual needs. When , , or When the value of any one of these metrics increases, the value of the weighted sum also increases, thus causing to decrease exponentially. This means that the temperature health status of the device deteriorates as these metrics worsen, and vice versa. When , , or decreases, the weighted sum decreases, resulting in increasing, indicating an improvement in the temperature health status of the device. , , or is negatively correlated with , and an exponential function is used. is , , or non-linearly sensitive to changes. can capture subtle changes in temperature metrics more delicately, thus providing a more accurate and dynamic temperature score. For example, a higher indicates a higher risk of overheating, which will significantly reduce , reflecting the serious overheating problem that the device may face; while a higher indicates that the device performs well in temperature management and has a lower risk.

[0056] By integrating the overheating rate, volatility, temperature change rate, and cumulative heat load, a predicted temperature score is constructed to achieve a multi-dimensional and all-round assessment of the device's thermal health. The predicted temperature score can not only reflect the overall temperature state of the device during the mission, but also identify potential thermal risks and unstable factors. The establishment of this scoring mechanism makes the operation assessment of the device more quantitative and systematic, providing a reliable basis for subsequent health scoring and mission ability judgment. At the same time, the introduction of the comprehensive score ensures the coordinated consideration of various temperature metrics, improves the scientificity and accuracy of the overall assessment system, and promotes the organic connection and coordinated operation among the various steps of the entire solution.

[0057] Step 3: Obtain the vibration curve of the monitored device during the last mission and the vibration curve during normal missions. Obtain the vibration curve of the device during normal missions, and combine the vibration curve during normal missions to obtain the amplitude deviation, stable volatility, proportion of stable time, and shock attenuation degree of the vibration curve during the last mission. The shock attenuation degree is obtained through the average change rate to form the current vibration score; By comparing the vibration curve of the last task with that of the normal task, the current operating state and stability of the equipment can be comprehensively evaluated. The construction of the vibration score not only reflects the vibration characteristics of the equipment in the actual task, but also can identify potential mechanical abnormalities and failure risks. This scoring mechanism provides a quantitative basis for the vibration monitoring and health assessment of the equipment, ensuring dynamic monitoring and timely maintenance during the operation of the equipment. At the same time, the data support of the vibration score provides supplementary information for the subsequent health score and task ability judgment, promotes the synergistic effect of dual monitoring of temperature and vibration in the overall solution, and improves the comprehensive efficiency of equipment management.

[0058] Step 3 includes the following content: Step 301: Obtain the vibration curve of the monitored equipment during a single task, obtain the vibration curve of the equipment during normal tasks, where the normal tasks are the operation processes under specific operating powers and specific working durations calibrated by the merchant, obtain the amplitude range of the equipment during normal tasks, the horizontal axis of the vibration curve is time, and the vertical axis is amplitude, and construct the current vibration score according to the following formula:

[0059] Where, is the current vibration score, is the amplitude deviation degree, is the stable volatility, is the proportion of stable time, is the shock attenuation degree; reflects the overall vibration health state of the equipment during the current task. By calculating the average value of the four vibration indicators, the vibration performance of the equipment during operation is quantified. This means that each indicator has the same importance in the final score. It ensures the balanced contribution of different vibration characteristics to the overall score and avoids the excessive influence of a single indicator on the score result. The amplitude deviation degree is positively correlated with When increases, that is, the vibration amplitude of the equipment deviates from the normal range more, also increases, reflecting an increase in the risk of abnormal vibration of the equipment. is also positively correlated with A higher indicates that the vibration fluctuation is unstable, and there are more irregular vibrations during the operation of the equipment, which will lead to to increase, indicating that the equipment may have unstable operation or potential failures. is also positively correlated with When increases, it means that the equipment maintains a stable vibration state for a longer time, therefore increases, reflecting a higher stability of the equipment operation. is positively correlated with . A higher indicates that the device can more effectively reduce vibration shock, increases, showing that the device has good anti-vibration ability and operates more reliably.

[0060] By obtaining the vibration curves of the previous task and the normal task, a comparison benchmark is provided for the construction of the vibration score. This comparative analysis can effectively identify vibration anomalies in the device during the previous task and timely detect potential mechanical failures or performance degradation. The setting of the reference vibration curve ensures the objectivity and standardization of the scoring system, making the vibration score highly comparable and reliable. In addition, the acquisition of the vibration curve provides the necessary data support for the calculation of subsequent vibration indicators, ensuring the accuracy and comprehensiveness of the overall vibration score and improving the refinement level of device vibration monitoring.

[0061] Step 302: The logic for obtaining the amplitude deviation degree is as follows:

[0062] where is the amplitude deviation degree, represents the maximum selection function, is the maximum amplitude of the vibration curve during the previous task, is the maximum value of the amplitude range during the normal task; reflects the degree of deviation of the vibration amplitude of the device during the current task relative to the reference amplitude range and measures the abnormality of the device's vibration performance. The function ensures that is not negative, thus maintaining the non-negativity of the deviation degree. By comparing the maximum amplitude of the current task with the maximum value of the reference amplitude, the deviation of the device's vibration amplitude is quantified. When the vibration amplitude of the device significantly deviates from the reference range, will approach 0, reflecting a higher risk of vibration anomaly; while when is only slightly higher than or lower than the reference value, will remain at a relatively high value, indicating a small vibration deviation and the device operating relatively stably.

[0063] The amplitude deviation can directly reflect whether there is abnormal vibration during the operation of the equipment by comparing the maximum amplitude of the current task vibration curve with the reference amplitude. This indicator helps to detect early signs of equipment performance degradation or mechanical component wear in a timely manner, preventing major failures caused by abnormal vibration. The acquisition of the amplitude deviation not only enhances the sensitivity of the vibration score but also provides an important quantitative basis for the comprehensive vibration score. The introduction of this indicator enables the vibration score to more accurately evaluate the operation stability of the equipment, ensuring the health status and reliability of the equipment during long-term operation and providing strong support for the health assessment of the overall solution.

[0064] Step 303: The logic for obtaining the stable volatility is as follows:

[0065] Where, is the stable volatility, represents the maximum selection function, is the standard deviation of the vibration curve during the previous task, is the standard deviation of the vibration curve during the normal task.

[0066] reflects the consistency and stability of the equipment vibration data. The higher the value, the more stable the vibration fluctuation of the equipment during operation, the closer the fluctuation amplitude is to the reference state, and the smoother the operation. The standard deviation of the current task reflects the vibration fluctuation of the equipment in this task, while the reference standard deviation represents the vibration fluctuation level of the equipment under normal task conditions. and and have an inverse relationship. When the vibration standard deviation of the current task increases, the score increases, resulting in decreasing, and thus decreases, indicating that the vibration volatility of the equipment becomes worse. On the contrary, when decreases, decreases, increases, resulting in increasing, reflecting that the vibration volatility of the equipment is more stable. In addition, if is greater than or equal to 1, then is negative, and the function ensures that is not negative, with a minimum of 0. This ensures that the value of is within a reasonable range and accurately reflects the operation stability of the equipment. The stable volatility provides a quantitative assessment of the equipment operation stability by comparing the vibration fluctuation amplitudes of the current task and the reference task, helping to identify whether there are unstable vibration factors during the equipment operation, thus ensuring the reliable operation of the equipment.

[0067] The stable volatility evaluates the stability of the equipment operation by comparing the standard deviation of the vibration curves of the current task and the benchmark task. A lower stable volatility indicates that the equipment maintains good smoothness during operation, reducing the probability of potential failures. This indicator not only reflects the vibration characteristics of the equipment under normal operating conditions but also can identify unstable factors in the equipment during specific tasks. The introduction of stable volatility improves the comprehensiveness and accuracy of the vibration score, enabling the scoring system to more comprehensively reflect the operating state of the equipment. The acquisition of this indicator provides a basis for stability evaluation for subsequent health scoring and task ability judgment, ensuring the continuous and stable operation of the equipment in various tasks.

[0068] Step 304: The logic for obtaining the proportion of stable time is as follows:

[0069] Where, is the proportion of stable time, is the reasonable time, is the task duration; reflects the degree to which the equipment maintains a stable operating state throughout the task. The higher the value, the more the equipment maintains the vibration amplitude within the normal range for a larger proportion of the time, and the smoother the operation. The reasonable time is calculated as the ratio of the reasonable time to the total duration, which can evaluate the effectiveness of the equipment in maintaining a stable vibration state during the task. The longer the reasonable time, the more the equipment operates stably for a larger proportion of the time, and vice versa, indicating that the equipment has abnormal vibrations for more time. When the reasonable time increases, also increases, indicating that the equipment maintains a stable vibration state for a longer time and operates more smoothly. On the contrary, when the total task duration increases while the reasonable time remains unchanged, will decrease, indicating that the equipment is in a stable state for a relatively shorter time during the longer task period and may have more vibration abnormalities. In addition, if and increase simultaneously, but grows faster than , then will still increase, and vice versa. Ensure that the value of can accurately reflect the operating stability of the equipment during the task and its performance in the time dimension. Comparing the ratio of the time the equipment maintains a stable vibration during the task to the total task time provides a quantitative evaluation of the equipment's operating stability. Helps identify whether the equipment can continuously maintain a good operating state during the task, thus ensuring the reliability and performance of the equipment and avoiding potential failures or performance degradation caused by unstable vibrations.

[0070] The reasonable time is the duration during which the amplitude of the vibration curve at the time of the previous task is within the amplitude range of the normal task; The proportion of stable time is obtained by calculating the proportion of time during which the equipment vibration is within the normal range, and it evaluates the operation stability and reliability of the equipment during the task. A higher proportion of stable time indicates that the equipment has maintained a good operation state for a longer time, reducing the possibility of failures. This indicator not only reflects the continuous stability of the equipment during the task, but also provides an evaluation basis for vibration scoring from the time dimension. The introduction of the proportion of stable time makes the vibration scoring more comprehensive and detailed, and can more accurately reflect the operation status of the equipment. The acquisition of this indicator helps in the calculation of subsequent health scores and the judgment of task capabilities, ensuring the continuous efficient and stable operation of the equipment in various tasks.

[0071] Step 305: The logic for obtaining the shock attenuation degree is as follows:

[0072] Among them, is the shock attenuation degree, represents the maximum selection function, is the number of shock events detected in the vibration curve at the time of the previous task, is the reference shock number during normal tasks; reflects the relationship between the number of sudden vibrations (i.e., shock events) encountered by the equipment during operation and the number of shock events in the reference task. The higher the value, the stronger the attenuation ability of the equipment to shock events, that is, the fewer shock events occur in the current task, indicating that the equipment has good anti-vibration performance and rapid recovery ability. When increasing, it means that more shock events are detected in the current task, resulting in increasing, thereby decreasing, and finally decreasing. This indicates that the equipment has a weak attenuation ability to shock events in the current task. When decreases, decreases, increases, resulting in increasing. This indicates that the equipment has a strong attenuation ability to shock events in the current task. Through the function, it ensures that always remains within the non-negative range, providing a stable and reliable evaluation basis. Plays a key role in the equipment health score, helping to identify whether the equipment has sufficient anti-vibration performance and preventing the risk of mechanical damage or failures caused by excessive vibration.

[0073] The logic for obtaining the number of shock events is as follows: The vibration curve is segmented at equal time intervals to obtain multiple curve segments, and the average rate of change of each curve segment is obtained respectively. The formula is as follows:

[0074] where is the amplitude change rate of the th curve segment, is the end amplitude of the th curve segment, is the initial amplitude of the th curve segment, is the time length of the curve segment, is the time retrieval variable of the curve segment, , , is the number of curve segments; reflects the severity of vibration fluctuations and the dynamic characteristics of the equipment response. A higher value indicates a larger amplitude change in a shorter time, which may indicate that the equipment has experienced significant vibration shocks or dynamic loads during this period.

[0075] Obtain the change rate threshold, and obtain the number of curve segments whose amplitude change rate exceeds the change rate threshold, which is the number of impact events.

[0076] The impact attenuation degree evaluates the response and mitigation ability of the equipment to sudden vibrations during operation by analyzing the number of impact events in the vibration curve. A higher impact attenuation degree indicates that the equipment has good anti-vibration ability and can effectively reduce the potential damage of vibrations to the equipment structure. This indicator not only reflects the dynamic response characteristics of the equipment but also can identify potential vibration control problems during the operation of the equipment. The introduction of the impact attenuation degree enriches the dimension of vibration scoring, enabling the scoring system to more comprehensively evaluate the performance of the equipment under different vibration conditions. The acquisition of this indicator provides key data support for the comprehensive evaluation of vibration scoring, ensuring that the equipment can maintain good operating conditions under various working conditions and providing an important basis for the health assessment of the overall solution and the judgment of task capabilities.

[0077] Step 4: Obtain historical tasks similar to the next task. The similarity is judged by the similarity degree, and obtain the temperature curve and vibration curve of the historical tasks. Refer to the construction method of the predicted temperature score and construct the historical temperature score in combination with the temperature curve of the historical tasks. Refer to the current vibration score construction method and construct the historical vibration score in combination with the vibration curve of the historical tasks; The content of Step 4 is as follows: Obtain historical tasks similar to the next task. The historical tasks are obtained through work logs, and the similarity is judged by operating power and task duration. The formula for similarity is as follows:

[0078] Wherein, is the similarity, is the operating power at the next task, is the operating power of the historical task, is the task duration of the next task, is the task duration of the historical task; reflects the degree of closeness of the next task to past tasks in terms of power and duration. The higher the value, the more similar the two tasks are in these two key parameters, and the stronger the relevance and effectiveness of the selected historical task as a reference.

[0079] and respectively measure the relative differences between the next task and the historical task in terms of operating power and task duration. Comprehensively represents the similarity degree in these two dimensions. Ensures that the similarity evaluation takes into account both the consistency of power and the matching of task duration, thus comprehensively reflecting the similarity of tasks. Close to When, tends to 1, Close to When, also tends to 1. When the operating power and task duration of the next task are highly close to those of the historical task, both ratios are close to 1, also approaches 100%, indicating that the tasks are highly similar. When or increases or decreases, responds proportionally to the corresponding changes. The increase or decrease of the ratio directly affects 's increase or decrease. By taking the average of the ratios, extreme changes in a single dimension are mitigated by the relative stability of the other dimension. Quantifies the similarity degree of the two tasks in these two key parameters. The selection of similar historical tasks in step 4 provides a quantitative basis, ensuring the relevance and effectiveness of the reference data, thereby optimizing the construction process of equipment temperature and vibration scores.

[0080] Select the historical task with the highest similarity, and obtain the temperature curve and vibration curve of this historical task. Refer to the construction method of the predicted temperature score and combine it with the temperature curve of the historical task to construct the historical temperature score. Refer to the current vibration score construction method and combine it with the vibration curve of the historical task to construct the historical vibration score.

[0081] By obtaining historical task data similar to the next task and constructing corresponding historical temperature scores and historical vibration scores, valuable reference basis can be provided for the upcoming task of the device. This process not only ensures the relevance and effectiveness of the reference data through similarity judgment, but also optimizes the prediction and evaluation of the current task by using the temperature and vibration scores in the historical data. The introduction of the historical temperature score enables the comparison of the temperature score and vibration score of the current task with the historical performance, identifying trends and potential problems in the device operation. The implementation of this step enhances the prediction ability and evaluation depth of the overall solution, ensuring that the operating parameters and health status of the device in the new task can be more accurately predicted and optimized, improving the scientific and forward-looking nature of device management.

[0082] Step 5: Obtain the power and task duration of each intermediate task experienced from the historical task to the previous task, obtain the device health score, set the health threshold, and judge the next task ability according to the health status.

[0083] The said Step 5 includes the following contents: Obtain the power and task duration of each intermediate task experienced from the historical task to the previous task, the intermediate task is obtained through the work log, and construct the health score, the basis formula is as follows:

[0084] Wherein, is the health score, is the predicted temperature score, is the historical temperature score, is the current vibration score, is the historical vibration score, represents the th running power of the intermediate task, represents the th task duration of the intermediate task, is the intermediate task number retrieval variable, , , is the total number of director tasks; By combining the temperature score and vibration score, and combining with the running power and task duration of the intermediate task, the health status of the device is quantified. A high health score indicates that the device performs well in terms of temperature and vibration, and operates with a low thermal load in the historical task, and vice versa. This score provides a scientific basis for subsequent judgment on whether the device is suitable for performing the next task, ensuring that the device is in good health status before continuing to operate and avoiding potential failure risks. Indicates the ratio of the predicted temperature score of the next task to the historical task temperature score. If is higher than , the ratio is greater than 1, indicating that the temperature health status of the next task is lower than that of the historical task, and vice versa. Indicates the ratio of the vibration score of the last task to the vibration score of the historical task. If is higher than , the ratio is greater than 1, indicating that the vibration health status of the current task is lower than that of the historical task, and vice versa. Indicates the consumption degree of each intermediate task on the device health status. The more tasks, the greater the operating power and the longer the working hours, the greater the consumption of the device health status. Indicates the reduction of the intermediate task data to avoid the denominator value being too large, making too small. By comparing the ratio of the numerator to the denominator, the numerator reflects the deviation degree of the health status of the next task and the last task compared to the historical task, and the numerator reflects the consumption of the intermediate task on the device health. When the deviation degree of the health status is greater than the consumption of the device health, will increase, indicating that the current device health status is declining. When the deviation degree of the health status is less than the consumption of the device health, will decrease, indicating that the current device health status still remains at a relatively high level.

[0085] Set a health threshold and compare the health score with the health threshold: When the health score is less than the health threshold, it represents that the status of the currently monitored device can meet the next task; When the health score is greater than or equal to the health threshold, adjust the power and task duration of the device participating in this task, obtain a new predicted temperature curve, and repeat steps 2 to 5 again and judge whether the health score is less than the health threshold. If the health score is less than the health threshold, it represents that the currently monitored device can meet the next task. When the power and task duration of this task are adjusted 5 times and the health score still cannot be less than the health threshold, an alarm is issued.

[0086] By analyzing the operating power and task duration of each intermediate task during the historical task up to the previous task, calculating the device health score can comprehensively evaluate the long-term operating status and health trend of the device. The calculation of the health score comprehensively considers the temperature score and vibration score, reflecting the health status of the device in multiple dimensions. Setting a health threshold and making comparisons ensure that the device is in good health before the next task, avoiding operating risks caused by device fatigue or wear. When the health score is greater than or equal to the threshold, by adjusting the operating parameters or performing maintenance, ensure that the device can continuously and stably participate in the task. This step not only provides a scientific basis for the predictive maintenance of the device, but also improves the intelligent management level of the overall solution through the introduction of the health score. Through the dynamic monitoring and evaluation of the health status, ensure the efficient and safe operation of the device in various tasks, optimize the device management process, and improve the overall operation efficiency.

[0087] By fusing the temperature, voltage, and vibration scores through the cube root, construct a comprehensive health score to achieve multi-dimensional status evaluation. A significant decrease in any score will result in a decrease in the comprehensive score, triggering the threshold judgment logic.

[0088] The above formulas are all calculated by taking the numerical value without dimension. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0090] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application.

Claims

1. An intelligent health status assessment method for building electromechanical equipment, characterized in that: The specific steps include: Step 1: Obtain the temperature curve of the monitored device under different operating powers, use the task duration of the operating power and temperature curve as the training set, train with the corresponding temperature curve label, obtain the temperature model, obtain the required operating power and task duration of the monitored device and input them into the temperature model to obtain the predicted temperature curve; Step 2: Analyze the predicted temperature curve, obtain the over-temperature rate through the temperature threshold, obtain the temperature change rate through the reference temperature change rate, obtain the fluctuation rate and the accumulated heat load, and form a predicted temperature score; Step 3: Obtain the vibration curve of the monitored device during the last task and the vibration curve during the normal task, obtain the vibration curve of the device during the normal task, and obtain the amplitude deviation, stable volatility, stable time proportion and impact attenuation of the vibration curve during the last task in combination with the vibration curve during the normal task. The impact attenuation is obtained by the average change rate to form the current vibration score; Step 4: Obtain historical tasks similar to the next task, the similarity is judged by similarity, and the temperature curve and vibration curve of the historical tasks are obtained. The historical temperature score is constructed by referring to the construction method of the predicted temperature score combined with the temperature curve of the historical tasks, and the historical vibration score is constructed by referring to the construction method of the current vibration score combined with the vibration curve of the historical tasks; Step 5: Obtain the power and task duration of each intermediate task from the historical task to the previous task, obtain the device health score, set the health threshold, and determine the next task capability based on the health status.

2. The intelligent health status assessment method for building electromechanical equipment according to claim 1 is characterized in that: Obtain the temperature curve of the monitored device at different operating powers, where the horizontal axis of the temperature curve is time and the vertical axis is temperature, the time is the time from the start of the task to the end of the task, and the temperature is the temperature obtained by the temperature monitor equipped on the device itself. The temperature curve at different operating powers is obtained by conducting experiments on the same model of the monitored device; The domain length of the power and temperature curves is used as a training set, where the domain length is the task duration required by the device. The corresponding temperature curve is used as a label, and a linear regression model is input for training to obtain a temperature model.

3. The intelligent health status assessment method for building electromechanical equipment according to claim 2 is characterized in that: Obtain the operating power and task duration required for the next task, input the operating power and task duration into the temperature model, and obtain the predicted temperature curve.

4. The intelligent health status assessment method for building electromechanical equipment according to claim 3 is characterized by: Analyze the predicted temperature curve, obtain the temperature threshold of the monitored equipment, and obtain the over-temperature rate. The formula is as follows: ， in, is the value of the over-temperature rate, is the highest value of the predicted temperature curve, is the temperature threshold, is the coefficient, ; To obtain the volatility, the logic is as follows: Get the mean and standard deviation of the predicted temperature curve and the volatility according to the following formula: ， in, is the volatility value, is the standard deviation of the predicted temperature curve, is the average value of the predicted temperature curve, The duration of the next task. The duration of high temperature; The high temperature duration is the duration during which the predicted temperature curve value exceeds 80% of the temperature threshold.

5. The intelligent health status assessment method for building electromechanical equipment according to claim 4 is characterized in that: To obtain the temperature change rate, the logic is as follows: Obtain the change rate curve and average change rate curve of the predicted temperature curve, obtain the benchmark temperature change rate of the monitored equipment, determine the maximum absolute value of the change rate curve, and construct the temperature change rate. The formula is as follows: ， in, is the value of the temperature change rate, Indicates the selection of the maximum value function, is the maximum absolute value of the rate of change curve, is the average rate of change, is the base temperature change rate; Get the cumulative heat load, the logic is as follows: ， in, is the cumulative heat load, To predict the temperature curve, is the temperature threshold, The duration of the next task; The predicted temperature score is constructed based on the following formula: ， in, To score the predicted temperature, is the over-temperature rate, is the volatility, is the temperature change rate, is the cumulative heat load, , , and is the coefficient, .

6. The intelligent health status assessment method for building electromechanical equipment according to claim 5 is characterized by: Obtain the vibration curve of the monitored equipment during a task, obtain the vibration curve of the equipment during normal tasks, the normal task is the operation process of a specific working time under a specific operating power calibrated by the merchant, obtain the amplitude range of the equipment during normal tasks, the horizontal axis of the vibration curve is time, and the vertical axis is amplitude, construct the current vibration score, and the formula is as follows: ， in, Rate the current vibration, is the amplitude deviation, To stabilize volatility, is the proportion of stable time, is the impact attenuation; The logic for obtaining amplitude deviation is as follows: ， in, is the amplitude deviation, represents the maximum selection function, is the maximum amplitude of the vibration curve during the last mission, is the maximum value of the amplitude range during normal tasks; The logic of obtaining stable volatility is as follows: ， in, To stabilize volatility, represents the maximum selection function, is the standard deviation of the vibration curve during the last mission, is the standard deviation of the vibration curve during normal mission.

7. The intelligent health status assessment method for building electromechanical equipment according to claim 6 is characterized by: The logic for obtaining the stable time ratio is as follows: ， in, is the proportion of stable time, For a reasonable time, is the task duration; The reasonable time is the duration during which the amplitude of the vibration curve during the last task is within the amplitude range during the normal task; The logic for obtaining the impact attenuation is as follows: ， in, is the impact attenuation, represents the maximum selection function, is the number of impact events detected in the vibration curve during the last mission, The baseline number of impacts during normal tasks; The logic for obtaining the number of impact events is as follows: The vibration curve is divided into multiple curve segments according to equal time, and the average change rate of each curve segment is obtained respectively. The formula is as follows: ， in, For the The amplitude change rate of a curve segment, For the The end amplitude of the curve segment, For the The initial amplitude of the curve segment, is the time length of the curve segment, Retrieve variables for curve segment times, , , is the number of curve segments; The change rate threshold is obtained, and the number of curve segments whose amplitude change rate exceeds the change rate threshold is obtained, which is the number of impact events.

8. The intelligent health status assessment method for building electromechanical equipment according to claim 7 is characterized in that: Obtain historical tasks similar to the next task. The historical tasks are obtained through work logs. The similarity is determined by the running power and task duration. The formula for the similarity is as follows: ， in, is the similarity, is the operating power for the next mission, is the operating power of the historical task, The duration of the next task. The duration of the historical missions; Select the historical task with the highest similarity, and obtain the temperature curve and vibration curve of the historical task. Construct the historical temperature score by referring to the construction method of the predicted temperature score and the temperature curve of the historical task. Construct the historical vibration score by referring to the construction method of the current vibration score and the vibration curve of the historical task.

9. The intelligent health status assessment method for building electromechanical equipment according to claim 8 is characterized by: Obtain the power and task duration of each intermediate task from the historical task to the previous task. The intermediate tasks are obtained through work logs, and a health score is constructed based on the following formula: ， in, Score your health. To score the predicted temperature, Score the historical temperatures. Rate the current vibration, Score historical vibrations, Indicates The operating power of the intermediate tasks, Indicates The duration of the intermediate tasks, Retrieve variables for intermediate task numbers, , , The total number of director tasks; Set health thresholds and compare health scores to health thresholds: When the health score is less than the health threshold, it means that the current monitored device status can meet the next task; When the health score is greater than or equal to the health threshold, adjust the power and task duration of the device participating in this task, obtain a new predicted temperature curve, repeat steps 2 to 5 again and determine whether the health score is less than the health threshold. If the health score is less than the health threshold, it means that the currently monitored device can meet the next task. After adjusting the power and task duration of this task 5 times, if the health score is still not less than the health threshold, an alarm is issued.

Images