Medical equipment energy consumption measurement data management control method and intelligent early warning system

Abstract

The invention relates to the technical field of medical equipment energy consumption management, and discloses a medical equipment energy consumption metering data management control method and an intelligent early warning system, which are used for solving the problem that when medical equipment energy consumption management is carried out, which equipment is not actually used for a long time is difficult to accurately identify. The method comprises the following steps: acquiring historical data of medical equipment for analysis to obtain a preliminary prediction quantity, acquiring state data of the medical equipment in real time, evaluating to obtain a necessary index for adjustment, judging whether to perform prediction quantity adjustment or not, if so, calculating to obtain an actual prediction quantity, performing equipment overload early warning according to the actual prediction quantity, and if not, performing equipment overload early warning according to the actual prediction quantity. If so, carrying out early warning reminding; if it is judged that the equipment is not overloaded, early warning reminding is not carried out, the equipment idle index of each time period is calculated according to the time period pre-measurement of the adjacent time periods, and equipment management control is carried out, so that the accuracy of acquiring the state of the medical equipment is effectively improved, and the accuracy of energy consumption optimization decision is improved.

Description

Technical Field

[0001] This invention relates to the field of energy consumption management technology for medical equipment, and more specifically to a method for managing and controlling energy consumption metering data of medical equipment and an intelligent early warning system. Background Technology

[0002] In modern medical environments, the widespread use of medical equipment has greatly improved the quality and efficiency of medical services, but it has also brought about high energy costs and management challenges. Especially in large medical institutions, various medical devices (such as CT scanners, MRI machines, ultrasound equipment, and surgical instruments) need to be kept in standby mode for extended periods to ensure they are readily available. However, this prolonged standby time leads to significant energy waste.

[0003] Existing medical equipment energy management systems typically rely on statistical analysis of equipment operating time and power consumption to identify potential energy-saving optimization points. By acquiring real-time energy consumption data from the equipment and combining it with information such as equipment operating status and usage frequency, energy management can be implemented.

[0004] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems:

[0005] In practical applications, current energy management systems struggle to accurately identify which devices are in a "standby but not actually used" state, making it difficult to precisely execute energy-saving optimization strategies. Furthermore, the status of devices changes in real time, which may affect the results of energy consumption analysis, leading to inaccurate device data predictions and impacting the accuracy of energy consumption optimization decisions. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method for managing and controlling energy consumption metering data of medical equipment and an intelligent early warning system to solve the problems existing in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] The method for managing and controlling energy consumption metering data of medical equipment includes the following steps: Step 1: Collect historical data of medical equipment, analyze the historical data using time series analysis, and preliminarily predict the daily equipment usage, which is recorded as the preliminary forecast. Step 2: Collect real-time status data of medical equipment, including equipment aging data and equipment load data. An adjustment necessity index is obtained based on the medical equipment status data, and the need for forecast adjustment is determined based on the adjustment necessity index. Step 3: If the forecast adjustment is determined to be necessary, the actual forecast is calculated based on the adjustment necessity index and the preliminary forecast. Step 4: Set a maximum workload threshold for medical equipment. An overload warning is issued based on the actual forecast and the maximum workload threshold. If the equipment is determined to be overloaded, a warning reminder is issued to the operator; if the equipment is not determined to be overloaded, no warning reminder is issued. Step 5: Divide the daily time into multiple time periods according to the average time interval, obtain hospital scheduling data, and obtain the time period forecast for each time period based on the hospital scheduling data and the actual forecast. Step 6: Calculate the equipment idle index for each time period based on the time period forecasts of adjacent time periods, and manage and control the equipment based on the equipment idle index.

[0009] Preferably, the preliminary prediction step is as follows: set a detection time period, collect historical usage data of medical equipment within the detection time period, and form a data sequence that changes over time based on the historical usage data according to the time series; use the unit root test to determine whether the data sequence is stationary; if there is a unit root in the data sequence, remove the trend using the difference algorithm; use the Akaike Information Criterion to determine the model parameters and obtain the initial model; use the historical usage data to train the initial model to obtain the final prediction model; use the final prediction model to predict the equipment usage for the next day, which is recorded as the preliminary prediction.

[0010] Preferably, the step of obtaining the necessary adjustment index based on the medical equipment status data includes: real-time collection of equipment aging data, which includes the equipment's service life, cumulative operating time, and energy consumption data, where the energy consumption data is the energy consumption of the equipment per unit time during the detection period; evaluation of the equipment energy consumption change value based on the equipment energy consumption data; normalization of the equipment's service life, cumulative operating time, and energy consumption change value, and obtaining the equipment aging coefficient based on the normalized equipment service life, cumulative operating time, and energy consumption change value; real-time collection of equipment load data, which includes current operating time, task queue length, data processing throughput, and equipment temperature data; normalization of the current operating time, task queue length, data processing throughput, and equipment temperature data, and evaluation of the equipment load coefficient based on the normalized current operating time, task queue length, data processing throughput, and equipment temperature data, specifically obtaining the following steps: In the formula, This is expressed as the equipment load factor. This represents the current running time. This is represented as the length of the task queue. Represented as equipment temperature data, This is expressed as data processing throughput; the equipment aging factor and equipment load factor are normalized, and the necessary adjustment index is calculated based on the normalized equipment aging factor and equipment load factor. The specific steps for obtaining this index are as follows: In the formula, This indicates that adjustments are necessary to the index. This is expressed as the equipment aging factor. This is expressed as the equipment load factor. , This is represented by the weighting coefficients of the equipment aging coefficient and the equipment load coefficient.

[0011] Preferably, the step of obtaining the device energy consumption change value is as follows: Obtain the device's energy consumption per unit time within the detection period to form a time series; convert the time series into a matrix form using a sliding window to obtain a data matrix; standardize the data matrix to obtain a standardized matrix; perform singular value decomposition on the standardized matrix to obtain the singular values ​​of the standardized matrix; obtain the total number of singular values ​​and the number of non-zero singular values; and calculate the degree of energy consumption fluctuation based on the singular values ​​of the standardized matrix. The specific steps are as follows: In the formula, This is expressed as the degree of energy consumption fluctuation. Let be the i-th non-zero singular value, k be the number of non-zero singular values, and q be the total number of singular values. It is represented as the j-th singular value; calculate the average increase in energy consumption of the equipment per unit time, denoted as the degree of energy consumption increase, normalize the degree of energy consumption fluctuation and the degree of energy consumption increase, and calculate the change in energy consumption based on the normalized degree of energy consumption fluctuation and the degree of energy consumption increase.

[0012] Preferably, the step of determining whether to adjust the forecast based on the necessary adjustment index is as follows: compare the necessary adjustment index with the necessary threshold; if the necessary adjustment index is greater than or equal to the necessary threshold, it is determined that the current equipment status change has an impact on the forecast and the forecast needs to be adjusted; if the necessary adjustment index is less than the necessary threshold, it is determined that the current equipment status change has no impact on the forecast and the forecast does not need to be adjusted.

[0013] Preferably, the step of calculating the actual predicted amount based on the necessary adjustment index and the preliminary predicted amount is as follows: the necessary threshold is calculated as a ratio to the necessary adjustment index to obtain the adjustment factor; the adjustment factor is multiplied by the preliminary predicted amount to obtain the actual predicted amount.

[0014] Preferably, the step of providing equipment overload warning based on the actual predicted quantity and the maximum workload threshold is as follows: the actual predicted quantity is compared with the maximum workload threshold, which is obtained by an adaptive threshold method. If the actual predicted quantity is greater than or equal to the maximum workload threshold, the equipment is determined to be overloaded; if the actual predicted quantity is less than the maximum workload threshold, the equipment is determined not to be overloaded.

[0015] Preferably, the step of obtaining the equipment idle index is as follows: Calculate the ratio of the maximum workload threshold to the number of time periods to obtain the maximum workload of each time period; obtain the predicted time period values ​​of two adjacent time periods for each time period, and calculate the average predicted time period value; obtain the equipment idle index based on the average predicted time period value and the maximum workload of each time period. The specific steps are as follows: In the formula, This is expressed as the equipment idle index. This is expressed as the average forecast value over a given time period. This represents the maximum workload over a given time period.

[0016] Preferably, the step of managing and controlling the equipment based on the equipment idle index is as follows: using an adaptive threshold method to obtain an idle threshold, comparing the equipment idle index with the idle threshold; if the equipment idle index is greater than or equal to the idle threshold, it is determined that the equipment will not be used during this time period, and the operator is prompted to turn off the equipment; if the equipment idle index is less than the idle threshold, it is determined that the equipment will be used during this time period, and the operator is not prompted to turn off the equipment.

[0017] Preferably, the intelligent early warning system for medical equipment energy consumption metering data includes: a preliminary usage prediction module, used to collect historical data of medical equipment, and based on the historical data, use time series analysis to make a preliminary prediction of the equipment usage for the day, which is recorded as the preliminary prediction amount, and transmits the preliminary prediction amount to the usage adjustment module; an equipment status assessment module, used to collect medical equipment status data in real time, use a neural network model to assess the necessary adjustment index based on the equipment status data, and determine whether to adjust the preliminary prediction amount based on the necessary adjustment index, and transmit the necessary adjustment index to the usage adjustment module; a usage adjustment module, if it determines that the prediction amount needs to be adjusted, obtains the actual prediction amount based on the necessary adjustment index and the preliminary prediction amount, and transmits the actual prediction amount to the overload early warning module; and an overload early warning module, used to issue an equipment overload early warning based on the actual prediction amount.

[0018] The technical effects and advantages of this invention are as follows:

[0019] Historical data from medical equipment is collected and analyzed to obtain preliminary forecasts. Real-time status data of medical equipment is collected to assess the necessity of adjustments and determine whether to adjust the forecast. If adjustment is required, the actual forecast is calculated, and an overload warning is issued based on the actual forecast. If the equipment is determined to be overloaded, a warning is issued; otherwise, no warning is issued. Based on the forecasts for adjacent time periods, the equipment idle index for each time period is calculated for equipment management and control. This effectively improves the accuracy of acquiring the status of medical equipment and enhances the precision of energy consumption optimization decisions. Attached Figure Description

[0020] Figure 1 A flowchart illustrating the medical equipment energy consumption metering data management and control method provided in this application embodiment.

[0021] Figure 2 This is a structural diagram of an intelligent early warning system for medical equipment energy consumption metering data provided in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The medical equipment energy consumption metering data management and control method and intelligent early warning system involved in the present invention are not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] This invention provides a method for managing and controlling energy consumption metering data of medical equipment, such as... Figure 1 As shown, it includes the following steps:

[0024] Step 1: Collect historical data of medical equipment, analyze the historical data using time series analysis, and make a preliminary prediction of the equipment usage for the day, which is recorded as the preliminary prediction. It should be noted that the medical equipment in this embodiment refers to any single medical device.

[0025] Time series analysis is a data modeling and prediction method based on time sequence. It analyzes historical usage data of medical equipment to identify trends, periodic fluctuations, and random changes, thereby predicting future equipment usage. By learning past usage patterns and combining them with hospital work patterns, it can make preliminary predictions of daily or different time periods of equipment usage, providing data support for intelligent control, optimizing equipment operating efficiency, and reducing energy waste.

[0026] In this embodiment, it should be specifically explained that the preliminary prediction amount acquisition step is as follows:

[0027] Set a detection period, which can be changed according to the actual situation. For example, the detection period can be one year or half a year. Collect historical usage data of medical equipment within the detection period. The historical usage data includes the number of times the equipment is used and the running time of each day within the detection period. The historical usage data is then divided into a data sequence that changes over time according to the time series, providing a basis for subsequent predictions.

[0028] Because equipment usage can fluctuate over time, such as decreasing during holidays and increasing during flu season, it's necessary to check if the data exhibits a stable pattern before making predictions. The unit root test is used to determine if the data series is stationary. If a unit root exists in the data series, it indicates excessive data volatility. In this case, the difference algorithm is used to remove the trend, making the data more suitable for prediction.

[0029] The unit root test is a method used to determine whether time series data is stationary. If time series data has a unit root, it means that the data will fluctuate significantly over time, failing to maintain a stable mean and variance, leading to a decrease in the accuracy of the predictive model. The most commonly used unit root test is the augmented Dickey-Fowler test, which uses statistical tests to determine whether a unit root exists in the data.

[0030] Difference operations are a method used to eliminate trends in time series data, making the data more stable and suitable for predictive modeling. Time series data are often affected by long-term trends; for example, the usage of medical devices may gradually increase over time, and this trend can interfere with the accuracy of predictions. The core idea of ​​difference operations is to calculate the amount of data change between adjacent time points to eliminate the overall upward or downward trend.

[0031] The Akaike Information Criterion is used to determine the optimal model parameters, such as the autoregressive term, the difference order, and the moving average term, to obtain the initial model.

[0032] The Akaike Information Criterion is a metric used to measure the quality of statistical models, primarily for model selection. It selects the optimal model from multiple candidate models by comprehensively considering both the model's goodness of fit (its ability to interpret data) and complexity (the number of parameters). The core idea of ​​the Akaike Information Criterion is to ensure a good model fit while avoiding overfitting caused by introducing too many parameters.

[0033] The initial model is trained using historical usage data to obtain the final prediction model. The final prediction model is then used to predict the device usage for the next day, which is recorded as the initial prediction.

[0034] Step 2: Collect medical equipment status data in real time. The medical equipment status data includes equipment aging data and equipment load data. Based on the medical equipment status data, an adjustment necessity index is obtained. Based on the adjustment necessity index, it is determined whether to make a predictive adjustment.

[0035] In this embodiment, it should be specifically explained that the step of obtaining the necessary adjustment index based on the medical device status data is as follows:

[0036] Real-time collection of equipment aging data, including equipment service life, cumulative equipment runtime, and equipment energy consumption data, with the equipment energy consumption data being the energy consumption of the equipment per unit time during the detection period.

[0037] The change in equipment energy consumption is assessed based on the equipment energy consumption data.

[0038] The equipment's service life, cumulative operating time, and energy consumption changes are normalized. The equipment aging factor is then calculated based on these normalized values. The specific steps for obtaining this factor are as follows:

[0039] ;

[0040] In the formula, This is expressed as the equipment aging factor. This indicates the equipment's service life. This is expressed as the cumulative operating time of the device. This is expressed as a change in equipment energy consumption;

[0041] Real-time acquisition of device load data, including current running time, task queue length, data processing throughput, and device temperature data. Current running time is the continuous running time after the device is powered on, task queue length is the number of tasks currently waiting for the device to process, and data processing throughput is the amount of images, signals, or data processed by the device per unit time.

[0042] The current runtime, task queue length, data processing throughput, and device temperature data are normalized. Based on the normalized current runtime, task queue length, data processing throughput, and device temperature data, the device load factor is evaluated. The specific steps for obtaining this factor are as follows:

[0043] ;

[0044] In the formula, This is expressed as the equipment load factor. This represents the current running time. This is represented as the length of the task queue. Represented as equipment temperature data, This is expressed as data processing throughput;

[0045] The equipment aging factor and equipment load factor are normalized. The necessary adjustment index is then calculated based on the normalized equipment aging factor and equipment load factor. The specific steps for obtaining this index are as follows:

[0046] ;

[0047] In the formula, This indicates that adjustments are necessary to the index. This is represented by the equipment aging factor. Equipment aging reduces operating efficiency, increases the risk of failure, and can even disrupt normal medical procedures. Therefore, when the aging factor is high, the system needs to take more proactive adjustment measures to ensure equipment safety and stability, thereby improving overall operating efficiency and reducing the impact of unexpected failures. This is expressed as the equipment load factor, which reflects the real-time operating pressure of the equipment. If equipment operates under high load for extended periods, it may lead to performance degradation, increased energy consumption, and even equipment failure or a shortened lifespan. Therefore, when the load factor is high, appropriate adjustment measures need to be taken to ensure stable equipment operation, improve work efficiency, and reduce the risk of sudden failures. , This represents the weighting coefficients of the equipment aging factor and the equipment load factor, and... , , The analytic hierarchy process (AHP) is used to determine the relative importance of multiple factors, particularly when it's difficult to directly quantify weights. AHP constructs a hierarchical model to break down complex problems into multiple levels and assesses the importance of different factors using pairwise comparison matrices. Then, eigenvalue decomposition or consistency checks are used to calculate the weight coefficients of each factor, ensuring reasonable and consistent weights. Finally, a weighted summation method is used to comprehensively calculate the influence of each factor, thus aiding in scientific decision-making.

[0048] In this embodiment, it should be specifically explained that the steps for obtaining the device energy consumption change value are as follows:

[0049] The energy consumption of the equipment per unit time during the detection period is obtained to form a time series. A sliding window is used to convert the time series into matrix form, resulting in a data matrix. For example, if the sliding window size is 3, the data matrix can be represented as follows: Each row represents a local time window;

[0050] The data matrix is ​​standardized to obtain the standardized matrix. Eliminate the influence of individual differences;

[0051] Singular value decomposition is performed on the normalized matrix to obtain its singular values. The total number of singular values ​​and the number of non-zero singular values ​​are obtained. The degree of energy consumption fluctuation is then calculated based on the singular values ​​of the normalized matrix. The specific steps are as follows:

[0052] ;

[0053] In the formula, This is expressed as the degree of energy consumption fluctuation. Let be the i-th non-zero singular value, k be the number of non-zero singular values, and q be the total number of singular values. Represented as the j-th singular value;

[0054] Calculate the average increase in equipment energy consumption per unit time, denoted as the energy consumption rise rate. Based on the energy consumption fluctuation rate and the energy consumption rise rate, calculate the energy consumption change value. The specific steps are as follows:

[0055] ;

[0056] In the formula, Expressed as a change in energy consumption, This is expressed as the degree of energy consumption fluctuation. This indicates the degree of increase in energy consumption.

[0057] Singular Value Decomposition (SVD) is a mathematical method used to break down complex data matrices into simpler structures, helping to extract the key features of the data. It decomposes a matrix into three parts, containing the core patterns of the data, the degree of influence, and information on variations in different directions. In energy consumption analysis, SVD can help identify the main patterns of energy consumption variation in equipment and quantify the degree of fluctuation, thereby optimizing energy management strategies.

[0058] In this embodiment, it should be specifically explained that the step of determining whether to adjust the forecast based on the necessary adjustment index is as follows:

[0059] The necessary adjustment index is compared with the necessary threshold, which is obtained through an adaptive thresholding method. If the necessary adjustment index is greater than or equal to the necessary threshold, it is determined that the change in the current equipment status has a significant impact on the forecast, and the forecast needs to be adjusted. If the necessary adjustment index is less than the necessary threshold, it is determined that the change in the current equipment status has no impact on the forecast, and the forecast does not need to be adjusted.

[0060] Step 3: If it is determined that the forecast needs to be adjusted, the actual forecast is calculated based on the necessary adjustment index and the initial forecast.

[0061] In this embodiment, it should be specifically explained that the steps for calculating the actual forecast based on the necessary adjustment index and the preliminary forecast are as follows:

[0062] The adjustment factor is obtained by calculating the ratio of the necessary threshold to the necessary adjustment index;

[0063] The actual predicted value is obtained by multiplying the adjustment factor by the preliminary prediction.

[0064] Step 4: Set the maximum workload threshold for medical equipment. The maximum workload threshold is calculated based on the equipment capacity and departmental needs. Based on the actual predicted workload and the maximum workload threshold, an overload warning is issued for the equipment. If the equipment is determined to be overloaded, an early warning is issued to the operator, reminding them that the equipment is under heavy load and to take timely measures, such as using other equipment to divert the workload. If the equipment is determined not to be overloaded, no early warning is issued.

[0065] In this embodiment, it should be specifically explained that the steps for providing equipment overload early warning based on the actual predicted quantity and the maximum workload threshold are as follows:

[0066] The actual predicted quantity is compared with the maximum workload threshold, which is obtained through an adaptive thresholding method. If the actual predicted quantity is greater than or equal to the maximum workload threshold, the equipment is determined to be overloaded; if the actual predicted quantity is less than the maximum workload threshold, the equipment is determined not to be overloaded.

[0067] Step 5: Divide the daily time into multiple time periods on average according to the time interval. The time interval can be changed according to the actual situation. For example, the time interval can be one hour or two hours. Obtain the hospital's shift schedule data, and obtain the predicted amount for each time period based on the hospital's shift schedule data and the actual predicted amount.

[0068] In this embodiment, it should be specifically explained that the steps for obtaining the predicted amount for each time period based on hospital scheduling data and actual predicted amount are as follows:

[0069] The demand for medical equipment in each department during each time period is obtained based on the hospital's scheduling data. The demand is the total duration of use of the medical equipment.

[0070] The demand for medical equipment in each department within a given time period is summed to obtain the total demand for medical equipment within that time period. The total demand for medical equipment within a given time period is then compared with the length of the time period. If the total demand for medical equipment within a given time period is less than or equal to the length of the time period, no correction is made. If the total demand for medical equipment within a given time period is greater than the length of the time period, the total demand is corrected using an equipment sharing model.

[0071] The equipment sharing model describes and manages situations where multiple departments or users share the same equipment. The goal of this model is to optimize equipment utilization efficiency, avoid resource waste, and ensure that each department can access the equipment promptly when needed. The equipment sharing model considers equipment availability and concurrent usage, and rationally schedules and allocates resources based on factors such as demand priority, equipment usage duration, and departmental scheduling, thereby achieving efficient utilization of equipment resources.

[0072] Calculate the total demand for medical equipment in each time period, sum the total demand for medical equipment in each time period to obtain the total demand for medical equipment in a day, and then multiply the ratio of the total demand for medical equipment in each time period to the total demand for medical equipment in a day by the actual predicted quantity to obtain the predicted quantity of medical equipment in each time period.

[0073] The steps to obtain the medical equipment demand of each department in different time periods based on hospital scheduling data are as follows:

[0074] Obtain hospital appointment data, and based on the hospital appointment data, obtain the number of patients booked by each department in each time period, and obtain the average examination time using medical equipment;

[0075] By combining hospital scheduling data, the number of patients that a department can receive in each time period is calculated. The total time that the department needs to use medical equipment in each time period is calculated by multiplying the number of patients by the average examination time.

[0076] When calculating the total demand from multiple departments within each time period, it is assumed that each department's equipment demand is independent and that all departments can use the equipment at the same time. However, in practice, equipment may be shared by multiple departments simultaneously, which may lead to excessively high demand and inaccurate time period predictions. This makes it impossible to accurately predict the total duration of medical equipment use by departments within each time period. Using an equipment sharing model to correct the data can reduce this situation.

[0077] Step 6: Calculate the equipment idle index for each time period based on the predicted volume of adjacent time periods, and perform equipment management and control based on the equipment idle index.

[0078] Adaptive thresholding is a method for dynamically adjusting thresholds. Based on historical data analysis and real-time equipment status, it optimizes thresholds over time or as the environment changes, rather than using fixed values. In medical equipment energy management, adaptive thresholding first calculates equipment load distribution over different time periods using historical data, and then dynamically adjusts idle thresholds based on real-time equipment operating conditions.

[0079] Equipment management and control based on forecasts of adjacent time periods can smooth out short-term fluctuations and avoid the influence of random data from a single time period on decision-making. By combining workloads from multiple time periods, it is possible to more accurately determine equipment usage trends, reduce the risk of premature or excessive equipment shutdowns, and ensure rapid response to sudden short-term demands. This optimizes equipment management, improves resource utilization, avoids unnecessary equipment downtime or overuse, and ultimately enhances hospital operational efficiency and service quality.

[0080] In this embodiment, it should be specifically explained that the step of obtaining the device idle index is as follows:

[0081] The maximum workload threshold is calculated by dividing it by the number of time periods to obtain the maximum workload for a time period.

[0082] To obtain the time-period forecast of two adjacent time periods for each time period, the average time-period forecast is calculated. The specific steps are as follows:

[0083] ;

[0084] In the formula, This is expressed as the average forecast value over a given time period. This represents the time-period prediction for the t-th time period. and These represent the predicted time intervals of two adjacent time intervals before and after the t-th time interval;

[0085] The equipment idle index is obtained by combining the average predicted workload over the time period with the maximum workload over the time period. The specific steps for obtaining this index are as follows:

[0086] ;

[0087] In the formula, This is expressed as the equipment idle index. This is expressed as the average forecast value over a given time period. This represents the maximum workload over a given time period.

[0088] In this embodiment, it should be specifically explained that the equipment management and control steps based on the equipment idle index are as follows:

[0089] An adaptive threshold method is used to obtain the idle threshold. The device idle index is compared with the idle threshold. If the device idle index is greater than or equal to the idle threshold, it is determined that the device will not be used during this time period, and the operator is prompted to turn off the device, reminding the operator that they can choose to turn off the device. If the device idle index is less than the idle threshold, it is determined that the device will be used during this time period, and the operator is not prompted to turn off the device.

[0090] In this embodiment, it should be specifically explained that, as Figure 2 As shown, the intelligent early warning system for medical equipment energy consumption metering data includes:

[0091] The preliminary usage forecast module is used to collect historical data of medical equipment, and based on the historical data, it uses time series analysis to make a preliminary forecast of the equipment usage for the day, which is recorded as the preliminary forecast. The preliminary forecast is then transmitted to the usage adjustment module.

[0092] The equipment status assessment module is used to collect medical equipment status data in real time. Through a neural network model, it assesses the necessary adjustment index based on the equipment status data, and determines whether to adjust the preliminary forecast based on the necessary adjustment index. The necessary adjustment index is then transmitted to the usage adjustment module.

[0093] If the usage adjustment module determines that the forecast quantity needs to be adjusted, it obtains the actual forecast quantity based on the adjustment necessity index and the preliminary forecast quantity, and transmits the actual forecast quantity to the overload warning module.

[0094] The overload warning module is used to provide equipment overload warnings based on actual predicted loads.

[0095] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0096] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for managing and controlling metering data of energy consumption of medical equipment, characterized in that, The method comprises the following steps: Step 1: collecting historical data of medical equipment, analyzing the historical data by time series analysis method, preliminarily predicting the equipment usage amount of the day, and recording the preliminary prediction amount; Step 2: collecting medical equipment state data in real time, the medical equipment state data including equipment aging data and equipment load data, and evaluating the adjustment necessity index according to the medical equipment state data to determine whether to adjust the prediction amount; Step 3: if it is determined that the prediction amount needs to be adjusted, calculating the actual prediction amount according to the adjustment necessity index and the preliminary prediction amount; Step 4: setting a maximum workload threshold of the medical equipment, performing equipment overload warning according to the actual prediction amount and the maximum workload threshold, and warning and reminding the operator if it is determined that the equipment is overloaded; if it is determined that the equipment is not overloaded, no warning and reminding is performed; Step 5: dividing the daily time into multiple time periods according to time intervals, obtaining hospital scheduling data, and obtaining the time period prediction amount of each time period according to the hospital scheduling data and the actual prediction amount; Step 6: calculating the equipment idle index of each time period according to the time period prediction amount of adjacent time periods, and performing equipment management control according to the equipment idle index.

2. The medical equipment energy metering data management control method according to claim 1, characterized by: The preliminary prediction amount obtaining step is: setting a detection time period, collecting historical use data of medical equipment in the detection time period, and forming a data sequence changing with time according to the time sequence of the historical use data; using unit root test method to determine whether the data sequence is stable, if there is a unit root in the data sequence, removing the trend through difference operation method; using Akaike information criterion to determine model parameters to obtain an initial model; training the initial model using historical use data to obtain a final prediction model, and using the final prediction model to predict the equipment usage amount of the next day, which is recorded as the preliminary prediction amount.

3. The medical equipment energy metering data management control method according to claim 1, wherein, The adjustment necessity index evaluation step according to the medical equipment state data is: collecting equipment aging data in real time, the aging data including equipment service life, equipment cumulative running time and equipment energy consumption data, the equipment energy consumption data being the energy consumption amount of the equipment per unit time in the detection time period; evaluating the equipment energy consumption change value according to the equipment energy consumption data; normalizing the equipment service life, the equipment cumulative running time and the equipment energy consumption change value, and obtaining an equipment aging coefficient according to the normalized equipment service life, the equipment cumulative running time and the equipment energy consumption change value; collecting equipment load data in real time, the equipment load data including current running time, task queue length, data processing throughput and equipment temperature data; normalizing the current running time, the task queue length, the data processing throughput and the equipment temperature data, and evaluating an equipment load coefficient according to the normalized current running time, the task queue length, the data processing throughput and the equipment temperature data, the specific obtaining steps being: ； wherein, denoted as device load coefficient, denoted as current run time, denoted as task queue length, denoted as device temperature data, denoted as data processing throughput; normalizing the equipment aging coefficient and the equipment load coefficient, and calculating the adjustment necessity index according to the normalized equipment aging coefficient and the equipment load coefficient, the specific obtaining steps being: ； In the formula, is expressed as an adjustment necessary index, is expressed as a device aging coefficient, is expressed as a device load coefficient, , is expressed as a weight coefficient of the device aging coefficient and a weight coefficient of the device load coefficient.

4. The medical equipment energy metering data management control method according to claim 3, characterized by, The equipment energy consumption change value obtaining step is: Obtaining the energy consumption of the device per unit time in the detection time period, forming a time series, converting the time series into a matrix form by using a sliding window, and obtaining a data matrix; Standardizing the data matrix to obtain a standardized matrix; Performing singular value decomposition on the standardized matrix to obtain singular values of the standardized matrix, obtaining the total number of singular values and the number of non-zero singular values, and calculating the energy consumption fluctuation degree according to the singular values of the standardized matrix, the specific obtaining steps being: ； wherein is expressed as the energy consumption fluctuation degree, is expressed as the ith non-zero singular value, k is the number of non-zero singular values, and q is the total number of singular values, is expressed as the jth singular value; Calculating the average energy consumption increase value of the device per unit time, denoted as the energy consumption rise degree, normalizing the energy consumption fluctuation degree and the energy consumption rise degree, and calculating the energy consumption change value according to the normalized energy consumption fluctuation degree and the energy consumption rise degree.

5. The medical device metering data management control method of claim 1, wherein: The step of judging whether to adjust the prediction value according to the adjustment necessity index is: Comparing the adjustment necessity index with the necessity threshold value, if the adjustment necessity index is greater than or equal to the necessity threshold value, it is judged that the current device state change has an impact on the prediction value, and the prediction value needs to be adjusted; if the adjustment necessity index is less than the necessity threshold value, it is judged that the current device state change has no impact on the prediction value, and the prediction value does not need to be adjusted.

6. The medical device metering data management control method of claim 1, wherein: The step of calculating the actual prediction value according to the adjustment necessity index and the preliminary prediction value is: Calculating the adjustment factor by ratio of the necessity threshold value and the adjustment necessity index; Calculating the actual prediction value by product of the adjustment factor and the preliminary prediction value.

7. The medical device metering data management control method of claim 1, wherein: The step of performing device overload early warning according to the actual prediction value and the maximum workload threshold value is: Comparing the actual prediction value with the maximum workload threshold value, the maximum workload threshold value is obtained by the adaptive threshold method, if the actual prediction value is greater than or equal to the maximum workload threshold value, it is judged that the device is overloaded; If the actual prediction value is less than the maximum workload threshold value, it is judged that the device is not overloaded.

8. The medical device metering data management control method of claim 1, wherein: The step of obtaining the device idle index is: Calculating the time period maximum workload by ratio of the maximum workload threshold value and the number of time periods; Obtaining the time period prediction value of two adjacent time periods in each time period, and calculating the average time period prediction value; Obtaining the device idle index according to the average time period prediction value and the time period maximum workload, the specific obtaining steps being: ； wherein is expressed as a device idle index, is expressed as an average time period prediction, is expressed as a time period maximum workload.

9. The medical device metering data management control method of claim 1, wherein: The step of performing device management control according to the device idle index is: Obtaining the idle threshold value by the adaptive threshold method, comparing the device idle index with the idle threshold value, if the device idle index is greater than or equal to the idle threshold value, it is judged that the device will not be used in the time period, and a device closing prompt is given to the operator; If the device idle index is less than the idle threshold value, it is judged that the device will be used in the time period, and no device closing prompt is given to the operator.

10. A medical equipment energy consumption metering data intelligent early warning system for implementing the medical equipment energy consumption metering data management control method of any one of claims 1-7, characterized in that: The system comprises: A usage preliminary prediction module configured to collect historical data of the medical device, and to preliminarily predict the device usage of the day according to the historical data by using a time series analysis method, denoted as a preliminary prediction value, and to transmit the preliminary prediction value to a usage adjustment module; A device state evaluation module configured to collect device state data in real time, to evaluate an adjustment necessity index according to the device state data by using a neural network model, and to judge whether to adjust the preliminary prediction value according to the adjustment necessity index, and to transmit the adjustment necessity index to the usage adjustment module; The use amount adjustment module is used to obtain the actual prediction amount according to the adjustment necessary index and the preliminary prediction amount if it is judged that the prediction amount needs to be adjusted, and to transmit the actual prediction amount to the overload early warning module. The overload early warning module is used to perform device overload early warning according to the actual prediction amount.

Images