Temperature control method of endoscope camera

Abstract

The invention discloses a temperature control method for an endoscope camera, and the endoscope camera comprises a housing, an image sensor disposed in the housing, an image preprocessing chip disposed in the housing, a CPU chip disposed in the housing, three thermocouple temperature sensors, and a thermistor temperature sensor disposed on the housing. The three thermocouple temperature sensors are arranged in the shell and are respectively arranged near the image sensor, the image preprocessing chip and the CPU chip. The temperature control method of the endoscope camera comprises the following steps: acquiring temperature data detected by the three thermocouple temperature sensors and the thermistor temperature sensor; taking the temperature data as input, and utilizing a Kalman filtering algorithm to output fused temperature after fusion; the monitoring frame rate and the image resolution of the endoscope camera and the working voltage and the working current of the image sensor are obtained in real time, and the total heat production power in the endoscope camera and the corresponding heat production power change rate are calculated.

Description

Technical Field

[0001] The present invention relates to the technical field of endoscopes, and in particular to a temperature control method for an endoscope camera head. Background Art

[0002] Currently, heat dissipation in endoscope cameras relies primarily on hardware thermal components, which is passive heat dissipation. This approach has significant drawbacks. Hardware heat dissipation is limited by physical structure and material properties. For example, the heat dissipation efficiency of a heat sink depends on its surface area and heat dissipation coefficient. However, in the compact internal space of a camera, the size of the heat sink cannot be increased indefinitely, resulting in insufficient heat dissipation area. Furthermore, the thermal conductivity of traditional thermally conductive materials such as metals has limited room for improvement, making it difficult to cope with the large amount of heat generated by image sensors and circuit boards under high load.

[0003] Furthermore, the hardware's heat dissipation lacks dynamic adjustment capabilities. When the camera's operating state changes, such as increasing the frame rate from 30fps to 60fps or the image resolution from 720p to 4K, the heat generated increases significantly, but the hardware's heat dissipation system cannot automatically adapt to this change. Under prolonged, high-load operating conditions, the limitations of hardware heat dissipation become increasingly apparent, leading to heat accumulation within the camera housing. This not only affects the doctor's grip comfort but, in severe cases, can cause circuit board short circuits and damage, or even fires due to high temperatures, endangering patient safety.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a temperature control method for an endoscopic camera, aiming to solve the above-mentioned technical problems in the prior art.

[0006] To achieve the above objectives, the present invention provides a temperature control method for an endoscopic camera head. The endoscopic camera head includes a housing, an image sensor located within the housing, an image preprocessing chip located within the housing, a CPU chip located within the housing, three thermocouple temperature sensors, and a thermistor temperature sensor provided on the housing. The three thermocouple temperature sensors are provided within the housing and are respectively provided near the image sensor, the image preprocessing chip, and the CPU chip. The temperature control method for the endoscopic camera head includes:

[0007] Obtain temperature data detected by three thermocouple temperature sensors and thermistor temperature sensor;

[0008] Based on the temperature data as input, a Kalman filter algorithm is used to output a fused temperature;

[0009] Acquire the monitoring frame rate, image resolution, and operating voltage and current of the image sensor of the endoscope camera in real time, and calculate the total heat generation power and the corresponding heat generation power change rate in the endoscope camera;

[0010] The heat generation power change rate and the fusion temperature are respectively used as inputs of a fuzzy controller, and a frame rate adjustment coefficient and a resolution adjustment ratio are output;

[0011] The operating parameters of the endoscope camera are adjusted according to the frame rate adjustment coefficient and the resolution adjustment ratio.

[0012] Preferably, in the temperature control method of the endoscopic camera, the step of using the temperature data as input and utilizing a Kalman filter algorithm to output a fused temperature includes:

[0013] The temperature data detected by the three thermocouple temperature sensors and the thermistor temperature sensor at time k are defined as observation variables, and the actual temperature of the endoscope camera at time k is defined as a state variable;

[0014] Establish state equations and observation equations according to the defined state variables and observation variables;

[0015] For each moment k, the state estimation value at the current moment is predicted based on the state equation, and the covariance at the current moment is predicted based on the system noise covariance;

[0016] The Kalman gain is calculated based on the predicted covariance at the current moment and the observation noise covariance matrix. The state estimate at the current moment and the estimated covariance at the current moment are updated using the Kalman gain, the observed variables, and the predicted state estimate. The updated state estimate is the fusion temperature at the current moment.

[0017] Preferably, in the temperature control method of the endoscopic camera, the step of establishing the state equation and the observation equation according to the defined state variables and observation variables respectively includes:

[0018] The state equation is expressed as: k|k-1 =X k-1 +ω k ;

[0019] Among them, X k|k-1 is the predicted value of the state at the kth moment using the state at the k-1th moment; X k-1 is the state variable at the kth moment; ω k is the system noise, which obeys a Gaussian distribution with a mean of 0 and a covariance of Q. The covariance Q represents the system noise ω k The degree of impact on state estimation needs to be determined based on actual conditions.

[0020] The observation equation is expressed as: k =HX k +ν k ;

[0021] Among them, Z k is the observed variable at the kth moment; H is the observation matrix, H = [1, 1, 1, 1] T , indicating that the measurement value of each of the three thermocouple temperature sensors and the thermistor temperature sensor is linearly related to the true temperature; ν k is the observation noise vector, which obeys a Gaussian distribution with mean 0 and covariance R. The covariance R is a 4×4 diagonal matrix, and the elements on the diagonal represent the measurement noise variances of the three thermocouple temperature sensors and the thermistor temperature sensor.

[0022] Preferably, in the temperature control method of the endoscopic camera head, the method further comprises:

[0023] Provide sample data, including the predicted fusion temperature, the corresponding actual temperature, and the covariance Q and covariance R corresponding to the calculated fusion temperature;

[0024] The sample data are divided into multiple groups with the same covariance Q and covariance R. The mean square error between the predicted fusion temperature and the corresponding true temperature is calculated respectively. The group with the smallest mean square error is taken as the optimal parameter. The calculation formula is as follows:

[0025]

[0026] Where X is the mean square error;

[0027] n is the number of groups in the grouped data;

[0028] T ct is the fusion temperature of the tth data;

[0029] T zt is the actual temperature corresponding to the t-th data;

[0030] The process noise and measurement noise are set to a range of 0 to 1 with a step size of 0.01, and the covariance Q and covariance R among the selected optimal parameters are applied to the Kalman filter model to determine whether the noise and fluctuation are removed;

[0031] When the noise and fluctuation are removed, the optimal parameters screened out are used as the target covariance Q and covariance R; otherwise, the screening is repeated.

[0032] Preferably, in the temperature control method of the endoscopic camera, before the step of using the heat generation power change rate and the fusion temperature as inputs of the fuzzy controller and outputting the frame rate adjustment coefficient and the resolution adjustment ratio, the method further includes:

[0033] The heat generation power change rate, the difference between the fusion temperature and the preset safety temperature threshold, the frame rate adjustment coefficient, and the resolution adjustment ratio in the training sample data are converted into pre-partitioned fuzzy sets respectively;

[0034] Using the transformed training sample data, the fuzzy rule base in the fuzzy controller is determined;

[0035] A reward function is defined to optimize the fuzzy rule base. When the fusion temperature is within the preset safe temperature range and the monitoring frame rate and image resolution do not affect the imaging quality, a positive reward is given; when the fusion temperature is not within the preset safe temperature range and the monitoring frame rate and image resolution affect the imaging quality, a negative reward is given.

[0036] Preferably, the temperature control method of the endoscopic camera head further includes:

[0037] In response to the fusion temperature exceeding a preset safety temperature range, the operating voltages of the image sensor, the image preprocessing chip, and the CPU chip are adjusted according to a relationship between the operating voltages of the image sensor, the image preprocessing chip, and the CPU chip and their corresponding total power consumption to reduce the total power consumption, thereby adjusting the total heat generation power and the fusion temperature.

[0038] Preferably, in the temperature control method of the endoscopic camera, in the step of acquiring the monitoring frame rate, image resolution, and operating voltage and operating current of the image sensor of the endoscopic camera in real time, and calculating the total heat generation power and the corresponding heat generation power change rate in the endoscopic camera, the calculation formula of the total heat generation power is:

[0039] P=P s +P b ;

[0040] P s =VI;

[0041] P b =k1f+k2Re+k3;

[0042] Wherein, P is the total heat generation power;

[0043] P s is the heat generation power of the image sensor;

[0044] V is the operating voltage of the image sensor;

[0045] I is the operating current of the image sensor;

[0046] P b is the heat generation power of other components in the endoscope camera except the image sensor;

[0047] f is the monitoring frame rate;

[0048] Re is the image resolution;

[0049] k1, k2, and k3 are coefficients.

[0050] Preferably, in the temperature control method of the endoscopic camera, a liquid circulation heat dissipation device is installed at the endoscopic camera, and the liquid circulation heat dissipation device includes a liquid pump, a pipe, and a coolant contained in the pipe. The liquid pump is provided outside the endoscopic camera, one end of the pipe is connected to the liquid pump, and the other end extends into the housing of the endoscopic camera and is closely attached to the surfaces of the image sensor, the image pre-processing chip, and the CPU chip.

[0051] Accordingly, after the step of adjusting the working parameters of the endoscope camera according to the frame rate adjustment coefficient and the resolution adjustment ratio, the method further includes:

[0052] Get the current fusion temperature;

[0053] In response to the current fusion temperature exceeding a preset safety temperature range, the cooling pump is controlled to start working, and the power of the cooling pump is dynamically adjusted according to the difference between the safety temperature range and the current fusion temperature.

[0054] Preferably, in the temperature control method of the endoscopic camera, dynamically adjusting the power of the cooling pump according to the difference between the safe temperature range and the current fusion temperature includes:

[0055] When the difference between the safe temperature range and the current fusion temperature is greater than a first preset value, increasing the power of the cooling pump;

[0056] When the difference between the safe temperature range and the current fusion temperature is less than a second preset value, the power of the cooling pump is reduced.

[0057] Preferably, in the temperature control method of the endoscopic camera, adjusting the operating parameters of the endoscopic camera according to the frame rate adjustment coefficient and the resolution adjustment ratio includes:

[0058] The adjusted monitoring frame rate f1 = α*f0, and the adjusted image resolution Re1 = (1-β)*Re0;

[0059] Among them, f1 is the adjusted monitoring frame rate;

[0060] f0 is the monitoring frame rate before adjustment;

[0061] α is the frame rate adjustment coefficient;

[0062] Re1 is the adjusted image resolution;

[0063] Re0 is the image resolution before adjustment;

[0064] β is the resolution adjustment ratio.

[0065] The present invention has at least the following beneficial effects:

[0066] The temperature control method for an endoscopic camera provided by the present invention obtains temperature data detected by three thermocouple temperature sensors and a thermistor temperature sensor; uses the temperature data as input and utilizes a Kalman filter algorithm to output a fused fusion temperature; obtains the monitoring frame rate, image resolution, and operating voltage and current of the endoscopic camera in real time, and calculates the total heat generation power and the corresponding heat generation power change rate within the endoscopic camera; uses the heat generation power change rate and fusion temperature as inputs of a fuzzy controller, outputting a frame rate adjustment coefficient and a resolution adjustment ratio; and adjusts the operating parameters of the endoscopic camera based on the frame rate adjustment coefficient and the resolution adjustment ratio. This allows for more accurate perception of temperature changes within the camera and for timely and accurate adjustments to be made. Compared to traditional methods, the temperature control accuracy can be improved to within ±1°C, effectively preventing the impact of temperature fluctuations on device performance and safety.

[0067] Furthermore, regardless of sudden changes in the camera's operating state or prolonged high-load operation, this solution maintains effective temperature control through adaptive learning and dynamic adjustment strategies. Even in extreme situations such as the frame rate increasing from 30fps to 60fps or the resolution switching from 720p to 4K, the solution can quickly stabilize the temperature within a safe range.

[0068] Furthermore, this invention significantly improves safety and reliability, greatly reducing the risk of equipment failure due to overheating, reducing the probability of circuit board damage by over 80%, and effectively avoiding fire hazards. It also extends the lifespan of the equipment, reduces equipment maintenance and replacement costs, and provides more reliable protection for medical work.

[0069] Furthermore, this invention optimizes the user experience, minimizing temperature interference with the doctor's operation while ensuring image quality. By intelligently adjusting operating parameters and heat dissipation strategies, the camera is always kept at a comfortable grip temperature, improving the smoothness and accuracy of the doctor's surgical or examination operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A schematic diagram of a first embodiment of the temperature control method for an endoscopic camera head provided by the present invention;

[0071] Figure 2 A schematic diagram of a second embodiment of the temperature control method for an endoscopic camera head provided by the present invention;

[0072] Figure 3 A schematic diagram of a third embodiment of the temperature control method for an endoscopic camera head provided by the present invention;

[0073] Figure 4 A schematic diagram of an endoscope according to an embodiment of the present invention.

[0074] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0075] The technical solutions of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments. It should be noted that the embodiments of the present invention and the features therein may be combined with each other unless there is a conflict.

[0076] In embodiments of the present invention, the term "and / or" describes the association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0077] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0078] In the embodiments of the present invention, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0079] In the present invention, unless otherwise specified, the directional words used, such as "up, down, top, bottom", usually refer to the directions shown in the drawings, or to the components themselves in the vertical, perpendicular or gravity direction; similarly, for ease of understanding and description, "inside and outside" refer to the inside and outside relative to the outline of each component itself, but the above directional words are not used to limit the present invention.

[0080] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in the embodiments of the present invention, many technical details are provided to enable the reader to better understand the present invention. However, even without these technical details and the various changes and modifications based on the following embodiments, the technical solutions claimed in the present invention can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with each other and referenced to each other under the premise that there is no contradiction.

[0081] The present invention provides a temperature control method for an endoscopic camera. The endoscopic camera includes a shell, an image sensor located in the shell, an image preprocessing chip located in the shell, a CPU chip located in the shell, three thermocouple temperature sensors, and a thermistor temperature sensor arranged on the shell. The three thermocouple temperature sensors are arranged in the shell and are respectively arranged near the image sensor, the image preprocessing chip, and the CPU chip. Figure 1 and Figure 2 The figure shows a flow chart of the temperature control method of the endoscope camera provided by the present invention.

[0082] At step S100, the temperature data detected by the three thermocouple temperature sensors and the thermistor temperature sensor are obtained. It should be noted that multiple thermistor temperature sensors can be provided, and thermistor temperature sensors can be provided at different positions of the housing. In some embodiments, the number of thermocouple temperature sensors can be more than three. In addition to providing thermocouple temperature sensors on electronic components other than the image sensor, image preprocessing chip, and CPU chip, thermocouple temperature sensors can also be provided on other electronic components. Assume that the temperature collected by the thermocouple sensor is T th1 、T th2 、T th3 、T th4 , ..., the temperature collected by the thermistor sensor is T tr .

[0083] Thermocouple sensors have a fast response speed and can accurately capture the instantaneous temperature changes of major heating components, while thermistor sensors have a wide coverage range and can monitor the overall temperature distribution inside the shell.

[0084] In step S200, the temperature data is used as input and the Kalman filter algorithm is used to output the fused temperature. The Kalman filter algorithm is used to fuse these temperature data of different types and positions to obtain a more accurate integrated temperature inside the camera, that is, the fused temperature T c .

[0085] Wherein, step S200 includes step S210, step S220, step S230, step S240, and step S250.

[0086] In step S210 , the temperature data detected by the three thermocouple temperature sensors and the thermistor temperature sensor at time k are defined as observation variables, and the actual temperature of the endoscope camera at time k is defined as a state variable.

[0087] Specifically, the state variable X k is the actual temperature of the endoscope camera at time k. The temperature data detected by the three thermocouple temperature sensors at time k are recorded as T th1,k 、T th2,k 、T th3,k The temperature data detected by the thermistor temperature sensor at time k is recorded as T tr,k The observation vector is [T th1,k , T th2,k , T th3,k , T tr,k ] T .

[0088] At step S220, the state equation and observation equation are established according to the defined state variables and observation variables. The state equation can be expressed as: k|k-1 =X k-1 +ω k ;

[0089] Among them, X k|k-1 The predicted value of the state at the kth moment is obtained by using the state at the k-1 moment;

[0090] X k-1 is the state variable at the kth moment;

[0091] ω k is the system noise, which obeys a Gaussian distribution with a mean of 0 and a covariance of Q, where the covariance Q represents the system noise ω k The degree of impact on state estimation needs to be determined based on actual conditions.

[0092] The observation equation is used to describe the relationship between the state variable and the observation variable. Since the observation variable is the measurement of the real temperature, assuming that there is noise in the measurement process, the observation equation can be expressed as: Z k =HX k +ν k ;

[0093] Among them, Z k is the observed variable at the kth moment;

[0094] H is the measurement matrix. In this embodiment, H = [1, 1, 1, 1] T, indicating that the measurement value of each of the three thermocouple temperature sensors and the thermistor temperature sensor is linearly related to the true temperature;

[0095] ν k is the observation noise vector, which obeys a Gaussian distribution with mean 0 and covariance R. The covariance R is a 4×4 diagonal matrix. The elements on the diagonal represent the measurement noise variances of the three thermocouple temperature sensors and the thermistor temperature sensor, respectively, which are determined according to the accuracy and characteristics of the sensors.

[0096] At step S230, for each moment k, the state estimation value at the current moment is predicted based on the state equation, and the covariance at the current moment is predicted based on the system noise covariance. It should be noted that the initial state estimation value and initial estimated covariance are also included before step S230.

[0097] Specifically, the initial state estimate

[0098] is the estimated value of the initial state;

[0099] T th1,0 , T th2,0 , T th3,0 , T tr,0 These are the temperature data detected by three thermocouple temperature sensors and the thermistor temperature sensor at time 0.

[0100] The initial estimate covariance represents the uncertainty of the initial state estimate. An appropriate value can be set based on experience or prior knowledge, such as a large positive number indicating a large uncertainty in the initial estimate.

[0101] The prediction step involves predicting the state estimate and predicting the covariance.

[0102] Among them, the predicted state estimate is the state estimate value at the current moment predicted by the state equation

[0103] The predicted covariance is the covariance P predicted at the current moment based on the system noise covariance Q k|k-1 =P k-1|k-1 +Q.

[0104] In step S240, the Kalman gain is calculated based on the predicted covariance at the current moment and the observation noise covariance matrix; the state estimate at the current moment and the estimated covariance at the current moment are updated using the Kalman gain, the observed variables and the predicted state estimate, where the updated state estimate is the fusion temperature at the current moment.

[0105] The updating step includes calculating the Kalman gain, updating the state estimate, and updating the estimated covariance.

[0106] The Kalman gain is calculated based on the prediction covariance P k|k-1 and the observation noise covariance matrix R to calculate the Kalman gain K k , the formula is: K k =(P k|k-1 H T (HP k|k-1 H T )+R) -1 .

[0107] Update the state estimate using the Kalman gain K k , observed variable Z k And the predicted state estimate Update the current state estimate The updated state estimate is the fusion temperature T at the current moment. c,k .

[0108] in,

[0109] Update the estimated covariance to update the estimated covariance P at the current moment k|k =(IK k H)P k|k-1 .

[0110] For each time instant k (k=1, 2, 3, ...), the prediction step and the update step are repeated.

[0111] At each time point k, the state estimate obtained after the above Kalman filter iteration process is the fused temperature. Through continuous iteration, the fused temperature estimate becomes increasingly accurate over time. It can comprehensively consider data from multiple sensors, reduce the impact of measurement noise, and obtain a more reliable estimate of the internal temperature of the endoscope camera.

[0112] In other embodiments, the system noise covariance Q and the observation noise covariance matrix R may need to be adjusted and optimized based on specific circumstances. The most appropriate parameter values ​​are further determined to improve the performance of the Kalman filter algorithm and the accuracy of the fusion temperature. For example, offline training can be performed using historical data, and the parameters can be adjusted to minimize the error between the fusion temperature and the true temperature. To optimize the covariance Q and covariance R, the method further includes steps S251 to S254.

[0113] At step S251 , sample data is provided, including the predicted fusion temperature, the corresponding actual temperature, and the covariance Q and covariance R corresponding to the calculated fusion temperature;

[0114] In step S252, the sample data are divided into multiple groups according to the data with the same covariance Q and covariance R. The mean square error between the predicted fusion temperature and the corresponding true temperature is calculated respectively, and the group with the smallest mean square error is taken as the optimal parameter. The calculation formula is as follows:

[0115]

[0116] Where X is the mean square error;

[0117] n is the number of groups in the grouped data;

[0118] T ct is the fusion temperature of the tth data;

[0119] T zt is the actual temperature corresponding to the t-th data;

[0120] In step S253, the process noise and measurement noise are set to a range of 0 to 1 with a step size of 0.01, and the covariance Q and covariance R in the selected optimal parameters are applied to the Kalman filter model to determine whether the noise and fluctuation are removed;

[0121] At step S254, if the noise and fluctuation are removed, the selected optimal parameters are used as the target covariance Q and covariance R; otherwise, the selection is repeated. If the selected optimal parameters do not meet the expectations, steps S251 to S254 can be repeated; or, the set with the second smallest mean square error (i.e., the second smallest from the last) calculated in step S252 is used as the optimal parameters, and steps S253 and S254 are continued.

[0122] In step S300, the monitoring frame rate, image resolution, and operating voltage and current of the endoscope camera are acquired in real time, and the total heat generation power and the corresponding heat generation power change rate within the endoscope camera are calculated. The operating voltage and heat generation of the image sensor are closely related in different operating modes.

[0123] Image sensor heat generation power P s It is the product of the operating voltage and the operating current.

[0124] Heat generation power P of other electronic components except image sensor b .

[0125] P=P s +P b ;

[0126] P s =VI;

[0127] P b =k1f+k2Re+k3;

[0128] Wherein, P is the total heat generation power;

[0129] P s is the heat generation power of the image sensor;

[0130] V is the operating voltage of the image sensor;

[0131] I is the operating current of the image sensor;

[0132] P b is the heat generation power of other components in the endoscope camera except the image sensor;

[0133] f is the monitoring frame rate;

[0134] Re is the image resolution;

[0135] k1, k2, and k3 are coefficients.

[0136] At step S400, the heat generation power change rate and the fusion temperature are respectively used as inputs of the fuzzy controller, which outputs a frame rate adjustment coefficient and a resolution adjustment ratio. Prior to step S400, the fuzzy controller further includes determining a fuzzy rule base, specifically including steps S410, S420, and S430.

[0137] In step S410, the heat generation power change rate, the difference between the fusion temperature and the preset safety temperature threshold, the frame rate adjustment coefficient, and the resolution adjustment ratio in the training sample data are converted into pre-divided fuzzy sets. c and the preset safety temperature threshold T max The difference ΔT=T c -T max .

[0138] In some embodiments, the difference between the fusion temperature and the preset safety temperature threshold is divided into seven fuzzy sets, such as NB (negative large), NM (negative medium), NS (negative small), Z (zero), PS (positive small), PM (positive medium), and PB (positive large).

[0139] In some embodiments, the heat generation power change rate is divided into seven fuzzy sets, such as NB (negative large), NM (negative medium), NS (negative small), Z (zero), PS (positive small), PM (positive medium), and PB (positive large).

[0140] In some embodiments, the frame rate adjustment coefficient is divided into 7 fuzzy sets, such as NB (decrease by 50%), NM (decrease by 30%), NS (decrease by 10%), Z (unchanged), PS (increase by 10%), PM (increase by 30%), and PB (increase by 50%).

[0141] In some embodiments, the resolution adjustment ratio is divided into five fuzzy sets, such as NB (50% reduction), NM (30% reduction), NS (10% reduction), Z (unchanged), and PS (fine-tuning only at low temperatures).

[0142] In step S420, the converted training sample data is used to determine the fuzzy rule base in the fuzzy controller. The fuzzy rule base is, for example:

[0143] when Δ When T is positive (PB) and the heat generation power change rate is positive (PB), the frame rate adjustment coefficient is small (S) and the resolution adjustment ratio is large (L), which means that the frame rate and resolution are greatly reduced.

[0144] when Δ When T is zero (Z) and the rate of change of heat generation power is negative small (NS), the frame rate adjustment coefficient is medium (M) and the resolution adjustment ratio is medium (M), that is, the frame rate and resolution are appropriately fine-tuned to maintain the image quality of the endoscope.

[0145] A reward function is defined at step S430. When the fusion temperature is within the preset safe temperature range and the monitoring frame rate and image resolution do not affect the imaging quality, a positive reward is given; when the fusion temperature is not within the preset safe temperature range and the monitoring frame rate and image resolution affect the imaging quality, a negative reward is given, thereby optimizing the fuzzy rule base. The fuzzy rule base is continuously optimized based on the real-time calculated fusion temperature and working state changes of the endoscope camera. When the fusion temperature remains within the safe temperature range and the frame rate and resolution loss is small, a positive reward is given; when the fusion temperature is too high or too low, or when the frame rate and resolution are excessively adjusted and affect the imaging quality, a negative reward is given, thereby improving the accuracy and stability of temperature control.

[0146] In step S500, the operating parameters of the endoscope camera are adjusted according to the frame rate adjustment coefficient and the resolution adjustment ratio. In some embodiments, the adjusted monitoring frame rate f1 = α * f0, and the adjusted image resolution Re1 = (1-β) * Re0.

[0147] Among them, f1 is the adjusted monitoring frame rate;

[0148] f0 is the monitoring frame rate before adjustment;

[0149] α is the frame rate adjustment coefficient;

[0150] Re1 is the adjusted image resolution;

[0151] Re0 is the image resolution before adjustment;

[0152] β is the resolution adjustment ratio.

[0153] The temperature control method for an endoscopic camera provided by the present invention obtains temperature data detected by three thermocouple temperature sensors and a thermistor temperature sensor; uses the temperature data as input and utilizes a Kalman filter algorithm to output a fused fusion temperature; obtains the monitoring frame rate, image resolution, and operating voltage and current of the endoscopic camera in real time, and calculates the total heat generation power and the corresponding heat generation power change rate within the endoscopic camera; uses the heat generation power change rate and fusion temperature as inputs of a fuzzy controller, outputting a frame rate adjustment coefficient and a resolution adjustment ratio; and adjusts the operating parameters of the endoscopic camera based on the frame rate adjustment coefficient and the resolution adjustment ratio. This allows for more accurate perception of temperature changes within the camera and for timely and accurate adjustments to be made. Compared to traditional methods, the temperature control accuracy can be improved to within ±1°C, effectively preventing the impact of temperature fluctuations on device performance and safety.

[0154] In step S600, in response to the fusion temperature exceeding the preset safety temperature range, the operating voltages of the image sensor, the image preprocessing chip, and the CPU chip are adjusted according to the relationship between the operating voltages of the image sensor, the image preprocessing chip, and the CPU chip and their corresponding total power consumption to reduce the total power consumption, thereby adjusting the total heat generation power and the fusion temperature.

[0155] In some other embodiments, a liquid circulation heat dissipation device can also be provided to adjust the fusion temperature through the liquid circulation heat dissipation device, especially when adjusting the working parameters still cannot effectively reduce the fusion temperature, the liquid circulation heat dissipation device can be used for adjustment. Specifically, a liquid circulation heat dissipation device is installed at the endoscope camera, and the liquid circulation heat dissipation device includes a liquid pump, a pipe, and a coolant contained in the pipe. The liquid pump is provided on the outside of the endoscope camera, one end of the pipe is connected to the liquid pump, and the other end extends to the housing of the endoscope camera and is closely attached to the surface of the image sensor, the image preprocessing chip, and the CPU chip. In some embodiments, the coolant is a liquid with a low boiling point, a high specific heat capacity and stable chemical properties, such as a specially formulated water-ethylene glycol mixture.

[0156] Accordingly, if Figure 3 As shown, after step S500, step S710 and step S720 are also included.

[0157] In step S710 , the current fusion temperature is obtained.

[0158] In step S720 , in response to the current fusion temperature exceeding the preset safety temperature range, the cooling pump is controlled to start working, and the power of the cooling pump is dynamically adjusted according to the difference between the safety temperature range and the current fusion temperature.

[0159] P p =k4(T c -T set )+k5P+k6;

[0160] Among them, P p is the power of the liquid pump;

[0161] P is the total heat production power;

[0162] K4, k5, and k6 are coefficients;

[0163] T set The temperature threshold for setting the cooling of the startup cycle.

[0164] In specific implementation, when the difference between the safety temperature range and the current fusion temperature is greater than a first preset value, the power of the cooling pump is increased; when the difference between the safety temperature range and the current fusion temperature is less than a second preset value, the power of the cooling pump is reduced.

[0165] The calculated power drives the liquid pump, circulating the coolant through the pipes. The coolant absorbs heat from the heating element and circulates it away from the camera, dissipating it into the external environment. Simultaneously, based on real-time fusion temperature feedback, the liquid pump power is dynamically adjusted to achieve precise temperature control. For example, as the temperature gradually decreases and approaches a safe threshold, the liquid pump power is reduced to reduce energy consumption. When the temperature rises again, the liquid pump power is promptly increased to enhance heat dissipation.

[0166] In order to achieve the above object, the present invention also provides an endoscope, such as Figure 4 As shown, the endoscope includes at least one processor 801; and a memory 802 communicatively connected to the at least one processor 801; wherein the memory 802 stores instructions that can be executed by the at least one processor 801, and the instructions are executed by the at least one processor 801 to enable the at least one processor 801 to execute the above-mentioned temperature control method of the endoscope camera.

[0167] The memory 802 and processor 801 are connected using a bus. The bus may include any number of interconnected buses and bridges, connecting various circuits of one or more processors 801 and memory 802. The bus may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. These are all well known in the art and are therefore not described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver may be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor 801 is transmitted over a wireless medium via an antenna. Furthermore, the antenna receives data and transmits it to the processor 801.

[0168] The processor 801 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. The memory 802 can be used to store data used by the processor 801 when performing operations.

[0169] In order to achieve the above-mentioned object, the present invention provides a computer-readable storage medium storing a computer program, which implements the above-mentioned temperature control method for an endoscopic camera when executed by the processor 801.

[0170] That is, those skilled in the art will understand that all or part of the steps in the above-described embodiments can be implemented by instructing the relevant hardware through a program. The program is stored in a storage medium and includes a number of instructions for causing a device (which may be a single-chip microcomputer, chip, etc.) or processor 8014 (processor) to execute all or part of the steps in the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0171] Obviously, the embodiments described above are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, those skilled in the art may make other different forms of changes or modifications without making any creative work, and all of these should fall within the scope of protection of the present invention.

Claims

1. A method for controlling the temperature of an endoscopic camera head, the endoscopic camera head comprising a housing, an image sensor located within the housing, an image pre-processing chip located within the housing, a CPU chip located within the housing, three thermocouple temperature sensors, and a thermistor temperature sensor disposed on the housing, wherein the three thermocouple temperature sensors are disposed within the housing and are respectively disposed near the image sensor, the image pre-processing chip, and the CPU chip, wherein: include: Obtain temperature data detected by three thermocouple temperature sensors and thermistor temperature sensor; Based on the temperature data as input, a Kalman filter algorithm is used to output a fused temperature; Acquire the monitoring frame rate, image resolution, and operating voltage and current of the image sensor of the endoscope camera in real time, and calculate the total heat generation power and the corresponding heat generation power change rate in the endoscope camera; The heat generation power change rate and the fusion temperature are respectively used as inputs of a fuzzy controller, and a frame rate adjustment coefficient and a resolution adjustment ratio are output; The operating parameters of the endoscope camera are adjusted according to the frame rate adjustment coefficient and the resolution adjustment ratio.

2. The temperature control method of an endoscopic camera head according to claim 1, wherein: The method of outputting a fused temperature by using a Kalman filter algorithm based on the temperature data as input includes: The temperature data detected by the three thermocouple temperature sensors and the thermistor temperature sensor at time k are defined as observation variables, and the actual temperature of the endoscope camera at time k is defined as a state variable; Establish state equations and observation equations according to the defined state variables and observation variables; For each moment k, the state estimation value at the current moment is predicted based on the state equation, and the covariance at the current moment is predicted based on the system noise covariance; The Kalman gain is calculated based on the predicted covariance at the current moment and the observation noise covariance matrix. The state estimate at the current moment and the estimated covariance at the current moment are updated using the Kalman gain, the observed variables, and the predicted state estimate. The updated state estimate is the fusion temperature at the current moment.

3. The temperature control method of an endoscopic camera head according to claim 2, wherein: The steps of establishing the state equation and the observation equation respectively according to the defined state variables and observation variables include: The state equation is expressed as: k|k-1 =X k-1 +ω k ; Among them, X k|k-1 is the predicted value of the state at the kth moment using the state at the k-1th moment; X k-1 is the state variable at the kth moment; ω k is the system noise, which obeys a Gaussian distribution with a mean of 0 and a covariance of Q. The covariance Q represents the system noise ω k The degree of impact on state estimation needs to be determined based on actual conditions. The observation equation is expressed as: k =HX k +ν k ; Among them, Z k is the observed variable at the kth moment; H is the observation matrix, H = [1, 1, 1, 1] T , indicating that the measurement value of each of the three thermocouple temperature sensors and the thermistor temperature sensor is linearly related to the true temperature; ν k is the observation noise vector, which obeys a Gaussian distribution with mean 0 and covariance R. The covariance R is a 4×4 diagonal matrix, and the elements on the diagonal represent the measurement noise variances of the three thermocouple temperature sensors and the thermistor temperature sensor.

4. The temperature control method of an endoscopic camera head according to claim 3, wherein: The method further comprises: Provide sample data, including the predicted fusion temperature, the corresponding actual temperature, and the covariance Q and covariance R corresponding to the calculated fusion temperature; The sample data are divided into multiple groups with the same covariance Q and covariance R. The mean square error between the predicted fusion temperature and the corresponding true temperature is calculated respectively. The group with the smallest mean square error is taken as the optimal parameter. The calculation formula is as follows: Where X is the mean square error; n is the number of groups in the grouped data; T ct is the fusion temperature of the tth data; T zt is the actual temperature corresponding to the t-th data; The process noise and measurement noise are set to a range of 0 to 1 with a step size of 0.01, and the covariance Q and covariance R among the selected optimal parameters are applied to the Kalman filter model to determine whether the noise and fluctuation are removed; When the noise and fluctuation are removed, the optimal parameters screened out are used as the target covariance Q and covariance R; otherwise, the screening is repeated.

5. The temperature control method of an endoscopic camera head according to claim 1, wherein: Before the step of using the heat generation power change rate and the fusion temperature as inputs of the fuzzy controller and outputting the frame rate adjustment coefficient and the resolution adjustment ratio, the method further includes: The heat generation power change rate, the difference between the fusion temperature and the preset safety temperature threshold, the frame rate adjustment coefficient, and the resolution adjustment ratio in the training sample data are converted into pre-partitioned fuzzy sets respectively; Using the transformed training sample data, the fuzzy rule base in the fuzzy controller is determined; A reward function is defined to optimize the fuzzy rule base. When the fusion temperature is within the preset safe temperature range and the monitoring frame rate and image resolution do not affect the imaging quality, a positive reward is given; when the fusion temperature is not within the preset safe temperature range and the monitoring frame rate and image resolution affect the imaging quality, a negative reward is given.

6. The temperature control method of an endoscopic camera head according to claim 1, wherein: Also includes: In response to the fusion temperature exceeding a preset safety temperature range, the operating voltages of the image sensor, the image preprocessing chip, and the CPU chip are adjusted according to a relationship between the operating voltages of the image sensor, the image preprocessing chip, and the CPU chip and their corresponding total power consumption to reduce the total power consumption, thereby adjusting the total heat generation power and the fusion temperature.

7. The temperature control method of an endoscopic camera head according to claim 1, wherein: In the step of obtaining the monitoring frame rate, image resolution, and operating voltage and current of the image sensor of the endoscope camera in real time, and calculating the total heat generation power and the corresponding heat generation power change rate in the endoscope camera, the calculation formula of the total heat generation power is: P=P s +P b ; P s =VI; P b =k1f+k2Re+k3; Wherein, P is the total heat generation power; P s is the heat generation power of the image sensor; V is the operating voltage of the image sensor; I is the operating current of the image sensor; P b is the heat generation power of other components in the endoscope camera except the image sensor; f is the monitoring frame rate; Re is the image resolution; k1, k2, and k3 are coefficients.

8. The temperature control method of an endoscopic camera head according to claim 1, wherein: A liquid circulation heat dissipation device is installed at the endoscope camera head, and the liquid circulation heat dissipation device includes a liquid pump, a pipe, and a coolant contained in the pipe. The liquid pump is arranged outside the endoscope camera head, one end of the pipe is connected to the liquid pump, and the other end extends into the housing of the endoscope camera head and is closely attached to the surface of the image sensor, image pre-processing chip, and CPU chip; Accordingly, after the step of adjusting the working parameters of the endoscope camera according to the frame rate adjustment coefficient and the resolution adjustment ratio, the method further includes: Get the current fusion temperature; In response to the current fusion temperature exceeding a preset safety temperature range, the cooling pump is controlled to start working, and the power of the cooling pump is dynamically adjusted according to the difference between the safety temperature range and the current fusion temperature.

9. The temperature control method of an endoscopic camera head according to claim 8, wherein: The dynamically adjusting the power of the cooling pump according to the difference between the safe temperature range and the current fusion temperature includes: When the difference between the safe temperature range and the current fusion temperature is greater than a first preset value, increasing the power of the cooling pump; When the difference between the safety temperature range and the current fusion temperature is less than a second preset value, the power of the cooling pump is reduced.

10. The temperature control method of an endoscopic camera head according to claim 1, wherein: The adjusting the operating parameters of the endoscope camera according to the frame rate adjustment coefficient and the resolution adjustment ratio includes: The adjusted monitoring frame rate f1 = α*f0, and the adjusted image resolution Re1 = (1-β)*Re0; Among them, f1 is the adjusted monitoring frame rate; f0 is the monitoring frame rate before adjustment; α is the frame rate adjustment coefficient; Re1 is the adjusted image resolution; Re0 is the image resolution before adjustment; β is the resolution adjustment ratio.

Images