A Smart Control Method for Preventing Bedsores Based on Multi-Sensor Fusion

Abstract

This invention discloses an intelligent control method for preventing bedsores based on multi-sensor fusion, belonging to the field of intelligent nursing technology. The method includes: real-time acquisition of body surface pressure, temperature, and humidity data through an array of sensor units; normalization and weighting of the multi-source data; calculation of the real-time risk index (RI) using the formula RI=αP_norm+βT_norm+γ*H_norm; comparison of the RI with preset low and high risk thresholds to trigger tiered response operations, including different combinations of weak ventilation, strong ventilation, and heating; and continuous monitoring based on a "monitoring-assessment-intervention-feedback" closed loop, automatically stopping intervention after the risk is eliminated. This invention integrates multiple parameters to achieve accurate risk assessment, achieves intelligent and adaptive proactive prevention through tiered response and closed-loop control, and introduces time-series trend analysis to improve early warning foresight, effectively solving the problems of one-sided assessment, crude intervention, and lack of closed-loop feedback in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of intelligent nursing technology, specifically to an intelligent control method for preventing bedsores based on multi-sensor fusion. Background Technology

[0002] Pressure ulcers, also known as bedsores, are serious complications caused by prolonged pressure on localized tissues in bed-bound or wheelchair-bound patients, leading to impaired blood circulation and subsequent damage to the skin and subcutaneous tissues. They not only cause immense suffering for patients but also significantly increase medical costs and the burden of care. Prevention is the most effective way to manage pressure ulcers.

[0003] Traditional methods of preventing bedsores mainly rely on caregivers to turn patients over regularly, use pressure-reducing mattresses, and keep the skin clean and dry.

[0004] These methods have obvious limitations: Manual turning over is labor-intensive and makes it difficult to guarantee the continuity and precision of nighttime and long-term care. Ordinary pressure-reducing mattresses can only passively distribute pressure and cannot sense or respond to the deterioration of the microenvironment caused by the combined effects of pressure, temperature, and humidity, lacking proactive intervention capabilities. With the development of sensor technology, some smart monitoring mattresses have emerged, but existing solutions often have the following problems: monitoring parameters are singular, usually focusing only on pressure and ignoring the important impact of temperature and humidity on skin tolerance, resulting in incomplete risk assessment; intervention methods are simple and crude, mostly single threshold alarms or single ventilation / pressure reduction responses, unable to make differentiated and refined adjustments according to risk levels; control logic is mostly open-loop, lacking a dynamic adjustment mechanism based on effect evaluation after response, which may lead to insufficient or excessive intervention; in addition, most systems lack the ability to predict risk trends, and the response is lagging. Summary of the Invention

[0005] The technical problem to be solved by this invention is to overcome the above-mentioned technical defects and provide an intelligent control method for preventing bedsores based on multi-sensor fusion.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A smart control method for preventing bedsores based on multi-sensor fusion includes the following steps: S1. Through multiple sensing units arranged on the bed, pressure data, temperature data and humidity data of the area in contact between the user's body surface and the bed are collected in real time. S2. Based on the pressure data, temperature data, and humidity data, calculate the real-time risk index using a preset risk assessment model; S3. Compare the real-time risk index with at least two preset risk thresholds, and trigger the corresponding graded response operation based on the comparison result; the graded response operation includes at least one or more combinations of: starting ventilation with a first wind speed, starting ventilation with a second wind speed, and starting heating function. S4. During and after the execution of the graded response operation, continuously return to the execution steps S1-S3 for closed-loop monitoring and feedback until the real-time risk index is lower than the preset relief threshold, then automatically stop the currently executed graded response operation.

[0007] The present invention discloses an intelligent control method for preventing bedsores based on multi-sensor fusion. This method achieves a comprehensive and accurate assessment of bedsore risk through multi-parameter fusion, and performs graded and proactive closed-loop intervention based on the assessment results, effectively improving the intelligence and effectiveness of prevention.

[0008] In addition, the intelligent control method for preventing bedsores based on multi-sensor fusion proposed in the above application may also have the following additional technical features: Specifically, in step S1, the multiple sensing units are arranged in an array to collect pressure distribution maps, temperature distribution maps, and humidity distribution maps.

[0009] Specifically, in step S2, the risk assessment model includes: The pressure data, temperature data, and humidity data are normalized respectively. Weighting coefficients were assigned to the normalized pressure, temperature, and humidity values, respectively. The real-time risk index RI is calculated according to the following formula: RI = α * P_norm + β * T_norm + γ * H_norm Where P_norm is the normalized pressure value, T_norm is the normalized temperature value, H_norm is the normalized humidity value, α, β, and γ are the corresponding weighting coefficients, and α+β+γ=1.

[0010] Specifically, in step S3, the at least two risk thresholds include a low-risk threshold and a high-risk threshold; When the real-time risk index is greater than or equal to the low-risk threshold but less than the high-risk threshold, a first-level response operation is triggered. When the real-time risk index is greater than or equal to the high-risk threshold, a second-level response operation is triggered.

[0011] Specifically, the first-level response operation is to start ventilation with the first wind speed, and the second wind speed is greater than the first wind speed; The second-level response operation is to simultaneously activate ventilation with the second wind speed and activate the heating function.

[0012] Specifically, in step S3, the graded response operation further includes triggering an alarm prompt corresponding to the response level, wherein the alarm prompt includes visual prompts, auditory prompts, and / or sending notification information to a remote terminal.

[0013] Specifically, in step S3, the corresponding hierarchical response operation is triggered based on the comparison result, including: The risk area is determined based on the location of the sensing unit whose real-time risk index exceeds the risk threshold; Control the local ventilation device corresponding to the risk area to perform the ventilation operation in the graded response operation, and / or control the local heating device corresponding to the risk area to perform the heating operation.

[0014] Specifically, after step S2, step S2a is also included: S2a. Analyze the collected continuous time-series data, calculate the trend parameters of pressure, temperature and / or humidity, and use the trend parameters as additional input to the risk assessment model to correct the real-time risk index.

[0015] Specifically, in step S4, the release threshold is lower than the risk threshold corresponding to triggering the graded response operation.

[0016] The advantages of this invention compared to existing technologies are: 1. By integrating multi-dimensional sensor information such as pressure, temperature, and humidity, and using a weighted risk assessment model (RI=αP_norm+βT_norm+γ*H_norm) for comprehensive analysis, the one-sidedness of single-parameter assessment is overcome, and a more comprehensive and accurate quantitative assessment of pressure ulcer risk is achieved.

[0017] 2. By adopting a multi-level risk threshold and graded response mechanism, differentiated intervention strategies can be automatically matched according to the risk level, realizing the precision and intelligence of intervention, and improving energy efficiency and comfort while effectively mitigating risks.

[0018] 3. A closed-loop control logic of "monitoring-evaluation-intervention-re-monitoring" was established. The effectiveness of intervention measures is continuously monitored and fed back for control decisions. Intervention is automatically stopped when the risk is eliminated, achieving adaptive and precise regulation and avoiding insufficient or excessive intervention.

[0019] 4. Time-series data analysis is introduced to correct the risk index by calculating the changing trends of pressure, temperature and humidity, enabling the system to have forward-looking early warning capabilities and to initiate intervention in advance before the risk index reaches the static threshold, transforming passive response into proactive prevention. Attached Figure Description

[0020] Figure 1 This is the core control flowchart of the present invention; Figure 2 This is a flowchart of the risk assessment model of the present invention; Figure 3 This is a flowchart of the hierarchical response of the present invention; Figure 4 This is a partial control flowchart of the present invention; Figure 5 This is a flowchart of the trend analysis process of the present invention. Detailed Implementation

[0021] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings. Identical components are indicated by the same reference numerals.

[0022] It should be noted that the terms “front,” “back,” “left,” “right,” “up,” and “down” used in the following description refer to the directions shown in the attached diagram, while the terms “inside” and “outside” refer to the directions toward or away from the geometric center of a specific component, respectively.

[0023] To make the content of this invention easier to understand, the technical solutions in the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings.

[0024] like Figures 1 to 5 As shown, the technical solution of this invention is: a smart control method for preventing bedsores based on multi-sensor fusion, the core process of which begins with step S1: multi-parameter data acquisition. Multiple integrated sensing units are arranged in a grid array under the smart mattress or sheet. Each unit includes a thin-film pressure sensor, a digital temperature sensor, and a capacitive humidity sensor. The system synchronously scans all sensing units at a preset frequency (e.g., 1Hz), continuously and in real-time acquiring comprehensive pressure, temperature, and humidity data of the area in contact between the user's body and the bed, and generating corresponding pressure, temperature, and humidity distribution maps, providing a spatially refined data foundation for risk assessment.

[0025] After data collection, proceed to step S2: Real-time risk index calculation. For example... Figure 2As shown, this step is processed using a pre-defined risk assessment model. First, the raw pressure (P), temperature (T), and humidity (H) values ​​for each sensor point are normalized, for example, by linearly mapping them to the [0,1] interval, or by normalizing them based on clinical safety thresholds to obtain P_norm, T_norm, and H_norm. Next, weighting coefficients α, β, and γ are assigned to these three normalized parameters. The weights can be set according to clinical importance, for example, α=0.5 (pressure), β=0.3 (temperature), and γ=0.2 (humidity), and satisfying α+β+γ=1. Finally, the real-time risk index RI for each sensor point is calculated according to the formula RI = α * P_norm + β * T_norm + γ * H_norm. The higher the RI value, the greater the risk of pressure ulcers at that point. The system can track and output the maximum RI value or the regional average RI value for the entire contact surface for decision-making.

[0026] In a preferred embodiment, such as Figure 4 As shown, following step S2, step S2a may also be included: time-series trend analysis and risk correction. The system not only analyzes the current time-series data but also caches historical time-series data, such as the past 5 minutes. By analyzing the rate of change of RI or its component parameters (P, T, H) over a period of time, the speed of risk development is assessed. For example, even if the current RI value is 0.38, if its rate of change shows a rapid increase, the risk assessment model can adjust the final output value of RI based on this trend parameter, potentially triggering an early warning and achieving proactive intervention.

[0027] like Figure 1 and Figure 3 As shown, after calculating the real-time risk index RI, step S3 is performed: graded response triggering. The system compares the RI (usually the maximum value) with two preset risk thresholds (low-risk threshold T_low and high-risk threshold T_high). If RI < T_low, it is determined to be risk-free and returns to continuous monitoring. If T_low ≤ RI < T_high, the first-level response operation is triggered, such as starting weak ventilation (first wind speed) to promote air circulation, reduce local humidity and temperature, and may trigger a yellow warning light. If RI ≥ T_high, the second-level response operation is triggered, such as simultaneously starting strong ventilation at the second wind speed, which is greater than the first wind speed, and low-power heating function. Strong ventilation is used to quickly improve the microenvironment, and heating is used to promote local blood circulation, and a red alarm and remote notification are triggered.

[0028] The triggering of response operations can be refined to specific areas. The system identifies risk areas, such as the sacrum and coccyx, by recognizing the location of specific sensor units where the RI (Residual Energy Response) exceeds a threshold. Subsequently, control commands are executed only on the local ventilation and / or heating devices corresponding to the risk area, achieving targeted intervention, improving energy efficiency, and reducing interference with non-risk areas for users.

[0029] After the response is triggered, the system proceeds to step S4: closed-loop monitoring and feedback. The system does not stop operating but immediately returns to step S1 to continue collecting new pressure, temperature, and humidity data. The RI (Responsibility Index) is recalculated based on the new data and a judgment is made, forming a closed loop. This process continues until the recalculated RI drops below a preset release threshold. This threshold is typically slightly lower than the risk threshold corresponding to triggering this level of response; for example, if the threshold for triggering a level 1 response is 0.4, the release threshold can be set to 0.35 to prevent frequent start-ups and shutdowns. When the RI falls below the release threshold, the system automatically stops the currently executing ventilation and / or heating operations, the alarm is cleared, and the system returns to basic monitoring status. If the risk is not eliminated, the intervention level is maintained or adjusted, and the cycle continues.

[0030] The specific workflow of an intelligent control system for preventing bedsores, used to implement the above method, mainly includes the following hardware: a sensor module embedded in the mattress in an array form, consisting of pressure, temperature, and humidity sensor arrays; an embedded microprocessor as the core data processing and control module; a partitionable ventilation fan array and heating film array as the execution module; and an alarm and communication module.

[0031] The sensing module continuously collects user body pressure, skin temperature and humidity data, and uploads them to the control module.

[0032] The control module runs a risk assessment model, integrates multi-source data to calculate the real-time risk index (RI) for each region and the whole, and combines historical data to assess risk trends.

[0033] The control module compares the risk index (RI) with preset thresholds (T_low, T_high). If a low risk is detected (e.g., RI=0.5), the instruction execution module activates low-speed ventilation for the corresponding area (e.g., the heel area). If a high risk is detected (e.g., RI=0.8), the instruction simultaneously activates high-speed ventilation and low-temperature heating (e.g., 40℃) for the corresponding area, triggering audible and visual alarms and remote notifications.

[0034] While the intervention is being performed, the system continuously returns to step 1 for monitoring. If monitoring shows that the sacrococcygeal RI drops to 0.3 due to the intervention, below the relief threshold of 0.35, the control module automatically stops ventilation and heating in that area. If the risk is not mitigated, the intervention is maintained until the risk is eliminated.

[0035] In the description of this specification, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0036] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0037] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A smart control method for preventing bedsores based on multi-sensor fusion, characterized in that, Includes the following steps: S1. Through multiple sensing units arranged on the bed, pressure data, temperature data and humidity data of the area in contact between the user's body surface and the bed are collected in real time. S2. Based on the pressure data, temperature data, and humidity data, calculate the real-time risk index using a preset risk assessment model; S3. Compare the real-time risk index with at least two preset risk thresholds, and trigger the corresponding graded response operation based on the comparison result. The graded response operation includes at least one or a combination of: activating ventilation with a first wind speed, activating ventilation with a second wind speed, and activating heating function. S4. During and after the execution of the graded response operation, continuously return to the execution steps S1-S3 for closed-loop monitoring and feedback until the real-time risk index is lower than the preset relief threshold, then automatically stop the currently executed graded response operation.

2. The intelligent control method for preventing bedsores based on multi-sensor fusion according to claim 1, characterized in that, In step S1, the multiple sensing units are arranged in an array to collect pressure distribution maps, temperature distribution maps, and humidity distribution maps.

3. The intelligent control method for preventing bedsores based on multi-sensor fusion according to claim 1, characterized in that, In step S2, the risk assessment model includes: The pressure data, temperature data, and humidity data are normalized respectively. Weighting coefficients were assigned to the normalized pressure, temperature, and humidity values, respectively. The real-time risk index RI is calculated according to the following formula: RI = α * P_norm + β * T_norm + γ * H_norm, where P_norm is the normalized pressure value, T_norm is the normalized temperature value, H_norm is the normalized humidity value, α, β, and γ are the corresponding weighting coefficients, and α + β + γ = 1.

4. The intelligent control method for preventing bedsores based on multi-sensor fusion according to claim 1, characterized in that, In step S3, the at least two risk thresholds include a low-risk threshold and a high-risk threshold; When the real-time risk index is greater than or equal to the low-risk threshold but less than the high-risk threshold, a first-level response operation is triggered. When the real-time risk index is greater than or equal to the high-risk threshold, a second-level response operation is triggered.

5. The intelligent control method for preventing bedsores based on multi-sensor fusion according to claim 4, characterized in that, The first-level response operation is to start ventilation with the first wind speed, where the second wind speed is greater than the first wind speed; The second-level response operation is to simultaneously activate ventilation with the second wind speed and activate the heating function.

6. The intelligent control method for preventing bedsores based on multi-sensor fusion according to claim 1, characterized in that, In step S3, the graded response operation further includes triggering an alarm prompt corresponding to the response level, wherein the alarm prompt includes visual prompts, auditory prompts, and / or sending notification information to a remote terminal.

7. The intelligent control method for preventing bedsores based on multi-sensor fusion according to claim 1, characterized in that, In step S3, the corresponding hierarchical response operation is triggered based on the comparison result, specifically including: The location of the sensing unit whose real-time risk index exceeds the risk threshold is used to determine the risk area. Control the local ventilation device corresponding to the risk area to perform the ventilation operation in the graded response operation, and / or control the local heating device corresponding to the risk area to perform the heating operation.

8. The intelligent control method for preventing bedsores based on multi-sensor fusion according to claim 1, characterized in that, Following step S2, step S2a is also included: S2a. Analyze the collected continuous time-series data, calculate the trend parameters of pressure, temperature and / or humidity, and use the trend parameters as additional input to the risk assessment model to correct the real-time risk index.

9. The intelligent control method for preventing bedsores based on multi-sensor fusion according to claim 1, characterized in that, In step S4, the release threshold is lower than the risk threshold corresponding to triggering the graded response operation.

10. An intelligent control system for preventing bedsores to implement the method as described in claim 1, characterized in that, include: The sensing module includes a pressure sensor array, a temperature sensor array, and a humidity sensor array, used to collect pressure, temperature, and humidity data; A data processing and control module is used to receive data from the sensing module, execute the method described in any one of claims 1-9, and generate control commands; The execution module includes a ventilation device and a heating device with at least two wind speeds, used to perform graded response operations in response to the control command; The power supply module is used to supply power to each module.

Images