Multi-source redundancy falling active protection method and system for CT examination bed

Abstract

The application discloses a kind of multi-source redundancy falling active protection method and system of CT examination bed, it is related to artificial intelligence technical field, the method includes: the position signal of potentiometer is collected;The position change slope of the position signal is calculated by linear regression algorithm;According to the preset slope threshold range, the position change slope is classified, and the classification result is obtained;According to the classification result, corresponding preset action is executed, to realize the multi-source redundancy falling active protection of CT examination bed, it is helpful to solve the problem that prior art cannot realize the early prediction and multi-source redundancy active protection of falling risk in the process of CT examination bed lifting.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a multi-source redundant fall protection method and system for a CT examination bed. Background Technology

[0002] The CT examination bed lifting system is a core safety component of CT equipment, and its operational stability directly affects patient safety and the smoothness of the examination process. Currently, CT examination bed lifting position monitoring largely relies on single-point potentiometer (POT) sensors. This solution is simple in structure, low in cost, and widely used in various CT devices. However, in practical applications, POT sensors are susceptible to link failures, loose wiring, and electromagnetic interference from the equipment, resulting in pulsed and distorted signal abnormalities.

[0003] This single-source detection mechanism cannot effectively distinguish between the actual physical fall of the bed and sensor malfunctions, which can easily lead to system misjudgments or missed judgments, resulting in delayed or false triggering of protective actions. At the same time, blindly adopting multi-source data acquisition and continuous high-frequency polling will significantly increase the communication load of the motion control system, affecting the overall operating efficiency of the equipment. Existing technologies cannot balance the reliability of safety protection with the stability of system operation.

[0004] Therefore, there is an urgent need for a multi-source redundant fall protection method for CT examination beds. Summary of the Invention

[0005] In view of this, the present invention proposes a multi-source redundant active protection method and system for CT examination beds, which can realize the early prediction of fall risk and multi-source redundant active protection during the lifting and lowering of CT examination beds.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A multi-source redundant fall protection method for a CT examination table includes: Acquire the position signal of the potentiometer; The slope of the position change of the position signal is calculated using a linear regression algorithm; The position change slope is classified according to a preset slope threshold range to obtain the classification result; Based on the classification results, corresponding preset actions are executed to achieve active protection against multi-source redundant falls of the CT examination bed.

[0007] Based on the above technical solution, the present invention can be further improved as follows: Optionally, the position signal of the acquisition potentiometer includes: The position signal of the CT examination bed is acquired at high frequency by a pull-wire potentiometer, and the drive-side position signal fed back by the servo driver is acquired synchronously. The CT examination bed position signal and the drive side position signal are converted into digital signals; The digital signals are pushed into the sliding window buffer queue according to the acquisition time sequence.

[0008] Optionally, calculating the slope of the position change of the position signal using a linear regression algorithm includes: Obtain valid sampling points from the sliding window cache queue; The slope of the position change is calculated using formula (1); Formula (1); In the formula, The slope of the position change. The number of valid sampling points within the sliding window. For the index or timestamp of the sampling point, This represents the POT sensor readings at each sampling time.

[0009] Optionally, after the step of calculating the slope of the position change of the position signal using a linear regression algorithm, the method includes: When a suspected downward trend is detected and the signal-to-noise ratio is low, the window doubling logic is automatically triggered to expand the sampling window to increase the feature point sampling density and time integration span, thereby improving the R-Square coefficient of determination in regression analysis. This ensures the confidence of trend determination in extremely low-speed descent scenarios and avoids missing the risk of low-kinetic-energy falls.

[0010] Optionally, the classification results include rapid decline, slow decline, sudden change, abnormality, and stationary state.

[0011] Optionally, performing a corresponding preset action based on the classification result includes: When the classification result is rapid descent, the fall is confirmed, and the electromagnetic lock is released for emergency braking; When the classification result is slow descent, sudden change, or abnormal, a driver query is initiated to obtain the dual-source displacement increment and perform a displacement increment consistency check. If the dual-source displacement is consistent, it is confirmed that a fall has occurred and the electromagnetic lock is released for emergency braking. If the dual-source displacement is inconsistent, it is determined that the potentiometer is faulty and the fault isolation mode is entered. When the classification result is stable, the positional changes of the CT examination bed are continuously monitored.

[0012] Optionally, the step of obtaining the dual-source displacement increment and performing displacement increment consistency verification includes: The displacement increment of the two sources is calculated using formula (2); Formula (6); In the formula, For dual-source displacement increment, This is the initial reference position value of the potentiometer. This is the current position value of the potentiometer. This is the initial reference position value for the driver encoder. This represents the current position value of the driver encoder. When Δdiff is less than the preset value, it is determined that the displacements of the two sources are consistent, confirming it as a real fall; when Δdiff is greater than or equal to the preset value, it is determined to be a POT sensor link failure.

[0013] A multi-source redundant fall protection system for a CT examination table includes: The signal acquisition module is used to acquire the position signal of the potentiometer; The slope calculation module is used to calculate the slope of the position change of the position signal using a linear regression algorithm. The classification module is used to classify the position change slope according to a preset slope threshold range and obtain the classification result; The protection execution module is used to execute corresponding preset actions based on the classification results, so as to realize active protection against multi-source redundant falls of the CT examination table.

[0014] An electronic device includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the method described herein.

[0015] A non-transitory computer-readable storage medium having a computer program stored thereon, the computer program implementing the steps of the method when executed by a processor.

[0016] The present invention has the following advantages: The multi-source redundant fall protection method for CT examination tables in this invention constructs a redundant detection mechanism through multi-source potentiometer signal acquisition, avoiding the risk of false alarms and missed detections caused by single-source sensor failures and interference, thus improving protection reliability. By using a linear regression algorithm to calculate the slope of position change, the fall trend can be predicted in advance, achieving active protection. Actions are executed based on slope threshold classification, accurately matching risk levels, avoiding protection delays and eliminating the need for high-frequency polling, thus balancing protection safety and system operating efficiency. Attached Figure Description

[0017] For illustrative and not limiting purposes, the present invention will now be described in conjunction with embodiments and accompanying drawings, wherein: Figure 1 This is a schematic diagram of the first process of the multi-source redundant fall protection method for a CT examination bed in an embodiment of the present invention. Figure 2 This is a schematic diagram of the second process of the multi-source redundant fall protection method for a CT examination bed in an embodiment of the present invention. Figure 3This is a first schematic diagram of the main components of the multi-source redundant fall protection system for a CT examination bed in an embodiment of the present invention. Figure 4 This is a second schematic diagram showing the main components of the multi-source redundant fall protection system for the CT examination bed in an embodiment of the present invention. Figure 5 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be noted that, where there is no conflict, the embodiments and features of the present invention can be combined with each other. The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0021] Figure 1 This is a schematic diagram of the first process of the multi-source redundant fall protection method for a CT examination bed in an embodiment of the present invention, as shown below. Figure 1 As shown, the multi-source redundant fall protection method for CT examination bed provided in this embodiment of the invention includes the following steps S101 to S104.

[0022] S101, acquires the position signal of the potentiometer.

[0023] The position signal of the CT examination bed is acquired at high frequency by a pull-wire potentiometer, and the drive-side position signal fed back by the servo driver is acquired synchronously. The CT examination bed position signal and the drive side position signal are converted into digital signals; The digital signals are pushed into the sliding window buffer queue according to the acquisition time sequence.

[0024] S102 calculates the slope of the position change of the position signal using a linear regression algorithm.

[0025] Obtain valid sampling points from the sliding window cache queue; The slope of the position change is calculated using formula (1); Formula (1); In the formula, The slope of the position change. The number of valid sampling points within the sliding window. For the index or timestamp of the sampling point, This represents the POT sensor readings at each sampling time.

[0026] When a suspected downward trend is detected and the signal-to-noise ratio is low, the window doubling logic is automatically triggered to expand the sampling window to increase the feature point sampling density and time integration span, thereby improving the R-Square coefficient of determination in regression analysis. This ensures the confidence of trend determination in extremely low-speed descent scenarios and avoids missing the risk of low-kinetic-energy falls.

[0027] This invention no longer relies on single-point position determination, but instead employs a multi-sample sliding window technique combined with least squares linear regression analysis to calculate the slope of position signal changes in real time. This algorithm effectively filters out instantaneous random noise caused by potentiometer wear or electromagnetic interference, and extracts the physically continuous downward trend through statistical methods, achieving accurate modeling of mechanical motion characteristics.

[0028] S103, classify the position change slope according to the preset slope threshold range, and obtain the classification result.

[0029] The classification results include rapid decline, slow decline, sudden change, abnormality, and steady state.

[0030] S104 executes the corresponding preset action based on the classification result to achieve active protection against multi-source redundant fall of the CT examination table.

[0031] When the classification result is rapid descent, the fall is confirmed, and the electromagnetic lock is released for emergency braking; When the classification result is slow descent, sudden change, or abnormal, a driver query is initiated to obtain the dual-source displacement increment and perform a displacement increment consistency check. If the dual-source displacement is consistent, it is confirmed that a fall has occurred and the electromagnetic lock is released for emergency braking. If the dual-source displacement is inconsistent, it is determined that the potentiometer is faulty and the fault isolation mode is entered. The displacement increment of the two sources is calculated using formula (2); Formula (6); In the formula, For dual-source displacement increment, This is the initial reference position value of the potentiometer. This is the current position value of the potentiometer. This is the initial reference position value for the driver encoder. This represents the current position value of the driver encoder. When Δdiff is less than the preset value, it is determined that the displacements of the two sources are consistent, confirming it as a real fall; when Δdiff is greater than or equal to the preset value, it is determined to be a POT sensor link failure.

[0032] To address the challenges of varying encoder ranges, resolutions, and zero-positions between the POT and driver encoders, a dynamic displacement increment verification model was designed. This algorithm calculates the displacement vector deviation between the two sources within the same time window. This transforms incomparable absolute coordinates into comparable motion displacements, thereby enabling precise decoupling and determination of actual physical falls and sensor link failures (such as voltage drift and loose wiring).

[0033] To address the most challenging aspect of detection—slow falling—a dynamic sampling window expansion mechanism is introduced. When the system detects a suspected downward trend but with a low signal-to-noise ratio, the algorithm automatically triggers window doubling logic. By increasing the feature point sampling density and the time integration span, the R-squared (coefficient of determination) of the regression analysis is improved, ensuring extremely high confidence in the decision even in extremely low-speed scenarios.

[0034] When the classification result is stable, the positional changes of the CT examination bed are continuously monitored.

[0035] Figure 2 This is a schematic diagram of the second process of the multi-source redundant fall protection method for a CT examination bed in an embodiment of the present invention, as shown below. Figure 2 As shown, S1-Pot high-frequency data acquisition: Real-time position signals of the CT examination table are acquired at high frequency through a pull-wire potentiometer (Pot) to ensure that subtle position changes are captured.

[0036] S2: Push into sliding window buffer queue: Store the collected location data into a sliding time window buffer queue to provide continuous sample data for subsequent trend calculation.

[0037] M1: Linear regression trend molecular model (calculating slope): Perform linear regression fitting on continuous position data within the sliding window to calculate the slope of position change, thereby reflecting the lifting speed and acceleration trend of the bed.

[0038] M2: Feature Extraction and Classification: Based on the preset slope threshold range, the calculated slope is classified to determine whether the current bed is in a "stable / noise", "rapid descent" or "slow descent / abnormal" state.

[0039] Path B: Stable / Noise → Determined to be in normal condition, directly return to S1 to continue monitoring, without triggering any protection actions.

[0040] Path A: Rapid descent characteristics → Determined to be a high-risk fall trend, immediately execute Action 1: Immediately trigger the safety brake (Lock), lock the bed through the electromagnetic lock device to prevent a fall.

[0041] Path C: Slowing down / abnormal → Determined as a suspected abnormality, proceeding to the next step of the dual-source verification process.

[0042] When a suspected anomaly is detected, the system will perform cross-verification using a second signal to distinguish between a genuine fault and a sensor false alarm. S3: Trigger Driver Query: The core controller sends a command to the servo driver to query the signals of the drive encoder.

[0043] S4: Synchronously acquire Pot and Driver displacement: Simultaneously acquire the actual displacement of the pull wire potentiometer and the indirect displacement of the drive encoder.

[0044] M3: Displacement Increment Consistency Verification Model (Calculate Diff): Compare the consistency of the two displacement increments and calculate the deviation value (Diff).

[0045] Final anomaly cause: Yes: Consistent physical movement → Deviation value within the threshold range indicates that the two signals match, and the anomaly is a genuine bed movement anomaly. Immediately execute Action 1: Immediately trigger the safety brake (Lock). No: Sensor malfunction → Deviation value exceeds the threshold, indicating that the signal anomaly is caused by a fault in the pull-wire potentiometer itself. Execute Action 2: Enter sensor fault isolation mode (PotFault), the system switches to a degraded operation mode that relies solely on the drive encoder, and simultaneously issues a fault alarm.

[0046] This invention aims to improve the accuracy and reliability of fall detection in CT examination table lifting systems. By introducing multi-source data cross-validation and sliding window trend analysis, it effectively solves the problem of misjudgment of faults that easily arises from relying solely on potentiometer (POT) single-source detection, achieving accurate differentiation between actual fall processes and sensor link failures. Simultaneously, through an on-demand triggering verification mechanism, it minimizes the query burden on the motion control system while ensuring no fall risks are missed, thereby comprehensively improving the system's safety and operational efficiency.

[0047] Figure 3This is a first schematic diagram showing the main components of the multi-source redundant fall protection system for a CT examination bed in an embodiment of the present invention. Figure 3 As shown, the multi-source redundant fall protection system 1 for a CT examination bed provided in this embodiment of the invention includes a signal acquisition module 10, a slope calculation module 20, a classification module 30, and a protection execution module 40.

[0048] Signal acquisition module 10 is used to acquire the position signal of the potentiometer; The slope calculation module 20 is used to calculate the slope of the position change of the position signal using a linear regression algorithm; The classification module 30 is used to classify the position change slope according to a preset slope threshold range to obtain a classification result; The protection execution module 40 is used to execute corresponding preset actions according to the classification results, so as to realize active protection against multi-source redundant fall of the CT examination table.

[0049] The multi-source redundant fall protection system for a CT examination bed provided in this embodiment of the invention consists of a CT examination bed, a POT sensor (directly measuring height), a driver encoder (providing feedback on the driving side position), an electromagnetic lock braking device, and a controller.

[0050] System monitoring is implemented through a polymorphic state machine, with the main states including: Idle: High-frequency sampling POT to establish a location baseline.

[0051] WaitingDriverQuery: Upon detecting a POT exception, initiates a Driver query and waits for the result.

[0052] Lock: Confirming the fall, release the electromagnetic lock for emergency braking.

[0053] PotFault: Determined as a sensor malfunction, protective isolation is implemented but the lifting and lowering movement of the examination bed is not locked.

[0054] Core decision-making logic Preliminary judgment logic (based on POT) Rapid Descent Detection: If the POT continues to descend at a speed exceeding the high-speed descent speed threshold, it is determined to be a high-speed descent. Action: Immediately enter Lock state, without waiting for Driver verification.

[0055] Gradual descent assessment: POT shows a linear decreasing trend, but the speed is low. Action: Initiate Driver verification.

[0056] Sudden Change / Anomaly Detection: POT readings exhibit non-linear jumps, fluctuations, or increases. Action: Initiate Driver verification.

[0057] Verification and decision logic (based on Driver) Scenario A (Careful Descent Verification): If the Driver descends synchronously and the displacement is consistent, it is confirmed as a real descent (Lock); if the Driver is stable, it is determined to be a POT fault (PotFault).

[0058] Scenario B (Mutation Verification): If the Driver is stable, it is confirmed as a PotFault; if both sources are abnormal, it is conservatively judged as a real abnormality based on the principle of safety first and the lock is released.

[0059] Figure 4 This is a second schematic diagram showing the main components of the multi-source redundant fall protection system for a CT examination bed in an embodiment of the present invention. Figure 4 As shown, the CT examination bed lifting system includes: CT examination bed: the core component that carries the patient, which is lifted by a drive motor.

[0060] Drive motor: The power source for lifting and lowering movements, coupled to the CT examination table through a mechanical structure to output power.

[0061] Electromagnetic lock device: The actuator of the safety brake. When it receives a safety brake signal, it applies a physical lock to the inspection bed to prevent it from falling.

[0062] The pull-wire potentiometer (Pot) is physically connected to the CT examination bed, acquiring the bed's real-time position signal (analog / digital signal) and sending it to the core controller as the most direct position feedback.

[0063] The drive encoder is internally coupled to the drive motor, collecting the motor's rotation angle and speed signals, indirectly reflecting the lifting status of the inspection bed, and sending it as a second feedback signal to the servo driver, which then synchronizes it to the core controller.

[0064] The core controller (running the algorithm model) receives two position feedback signals and calculates the slope of position change through built-in algorithms such as linear regression to determine whether the rising or falling state is abnormal.

[0065] Normal state: Sends motion commands to the servo driver to control the drive motor.

[0066] Abnormal state: Immediately send a safety braking signal to the electromagnetic lock device to trigger physical locking.

[0067] The servo driver receives instructions from the core controller to precisely control the speed and torque of the drive motor; at the same time, it feeds back the signal from the drive encoder to the core controller, forming a closed-loop control.

[0068] The system achieves active protection through a three-layer mechanism of "dual-source signal cross-checking + slope prediction + physical braking": Redundancy check: The core controller compares the actual position of the pull-wire potentiometer with the indirect position of the drive encoder to determine whether there is a sensor malfunction or actual drop.

[0069] Trend prediction: By calculating the slope of position change through linear regression, abnormally accelerated downward trends can be identified in advance.

[0070] Active braking: Once a risk is detected, the electromagnetic lock device is immediately triggered to lock the bed and prevent an accident from occurring.

[0071] Figure 5 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 5 As shown, the electronic device 50 includes: a processor 501, a memory 502, and a bus 503; The processor 501 and the memory 502 communicate with each other via the bus 503. The processor 501 is used to call program instructions in the memory 502 to execute the methods provided in the above-described method embodiments, and to execute the methods provided in the embodiments of the present invention.

[0072] This embodiment provides a non-transitory computer-readable storage medium that stores computer instructions, which cause a computer to execute the method provided in this embodiment of the invention.

[0073] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various storage media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.

[0074] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A multi-source redundant fall protection method for a CT examination table, characterized in that, include: Acquire the position signal of the potentiometer; The slope of the position change of the position signal is calculated using a linear regression algorithm; After the step of calculating the slope of the position change of the position signal using a linear regression algorithm, the following steps are included: When a suspected downward trend is detected and the signal-to-noise ratio is low, the window doubling logic is automatically triggered to expand the sampling window to increase the feature point sampling density and time integration span, thereby improving the R-Square coefficient of determination in regression analysis. This ensures the confidence of trend determination in extremely low-speed descent scenarios and avoids missing the risk of low-kinetic-energy falls. The position change slope is classified according to a preset slope threshold range to obtain the classification result; Based on the classification results, corresponding preset actions are executed to achieve active protection against multi-source redundant falls of the CT examination bed.

2. The multi-source redundant fall protection method for a CT examination bed according to claim 1, characterized in that, The position signal of the acquisition potentiometer includes: The position signal of the CT examination bed is acquired at high frequency by a pull-wire potentiometer, and the drive-side position signal fed back by the servo driver is acquired synchronously. The CT examination bed position signal and the drive side position signal are converted into digital signals; The digital signals are pushed into the sliding window buffer queue according to the acquisition time sequence.

3. The multi-source redundant fall protection method for a CT examination bed according to claim 2, characterized in that, The calculation of the slope of the position change of the position signal using a linear regression algorithm includes: Obtain valid sampling points from the sliding window cache queue; The slope of the position change is calculated using formula (1); Official (1); In the formula, The slope of the position change. The number of valid sampling points within the sliding window. For the index or timestamp of the sampling point, This represents the POT sensor readings at each sampling time.

4. The multi-source redundant fall protection method for a CT examination bed according to claim 1, characterized in that, The classification results include rapid decline, slow decline, sudden change, abnormality, and steady state.

5. The multi-source redundant fall protection method for a CT examination table according to claim 4, characterized in that, The step of performing a corresponding preset action based on the classification result includes: When the classification result is rapid descent, the fall is confirmed, and the electromagnetic lock is released for emergency braking; When the classification result is slow descent, sudden change, or abnormal, a driver query is initiated to obtain the dual-source displacement increment and perform a displacement increment consistency check. If the dual-source displacement is consistent, it is confirmed that a fall has occurred and the electromagnetic lock is released for emergency braking. If the dual-source displacement is inconsistent, it is determined that the potentiometer is faulty and the fault isolation mode is entered. When the classification result is stable, the positional changes of the CT examination bed are continuously monitored.

6. The multi-source redundant fall protection method for a CT examination table according to claim 5, characterized in that, The process of obtaining the dual-source displacement increment and performing displacement increment consistency verification includes: The displacement increment of the two sources is calculated using formula (2); Official (2); In the formula, For dual-source displacement increment, This is the initial reference position value of the potentiometer. This is the current position value of the potentiometer. This is the initial reference position value for the driver encoder. This represents the current position value of the driver encoder. When Δdiff is less than the preset value, it is determined that the displacements of the two sources are consistent, confirming it as a real fall; when Δdiff is greater than or equal to the preset value, it is determined to be a POT sensor link failure.

7. A multi-source redundant fall protection system for a CT examination table, characterized in that, include: The signal acquisition module is used to acquire the position signal of the potentiometer; The slope calculation module is used to calculate the slope of the position change of the position signal using a linear regression algorithm. When a suspected downward trend is detected and the signal-to-noise ratio is low, the window doubling logic is automatically triggered to expand the sampling window to increase the feature point sampling density and time integration span, thereby improving the R-Square coefficient of determination in regression analysis. This ensures the confidence of trend determination in extremely low-speed descent scenarios and avoids missing the risk of low-kinetic-energy falls. The classification module is used to classify the position change slope according to a preset slope threshold range and obtain the classification result; The protection execution module is used to execute corresponding preset actions based on the classification results, so as to realize active protection against multi-source redundant falls of the CT examination table.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images