Multi-airbag pillow self-adaptive adjusting method and multi-airbag self-adaptive pillow

Abstract

The invention discloses a multi-air-bag pillow self-adaptive adjusting method and a multi-air-bag self-adaptive pillow. The multi-air-bag pillow self-adaptive adjusting method comprises the steps that S1, when the multi-air-bag pillow is in a no-load state, each air bag is S2, calibrating the initial air pressure of each air bag, recording the current air pressure, the last air pressure and the difference between the last air pressure and the initial air pressure of the air bag, calculating the output power PWM of the corresponding air pump according to the three indexes, and adjusting the air bags; s3, multi-airbag pillow loading is carried out, the difference value between two times of air pressure of each airbag is obtained, the difference value detected by a single airbag for multiple times is larger than a set value for three times continuously, and the pressure Pi of the current airbag i is recorded; s4, continuously recording the pressure Pi of the current air bag for ten times, solving a mean value PTi, and summarizing to form a judgment matrix X0; s5, outputting a target pressure matrix X1 through X0 operation; and S6, comparing the X1 with the air pressure of the corresponding air bag, recording the current air pressure, the last air pressure and the difference value between the last air pressure and the target pressure, calculating the PWM of the corresponding air pump according to the three indexes, and adjusting the air bag. The problem that an existing air bag pillow is provided with few air bags and cannot be fully attached to the head and the neck for supporting is solved.

Description

Technical Field

[0001] The invention relates to the technical field of airbag pillows, and in particular to a multi-airbag pillow adaptive adjustment method and a multi-airbag adaptive pillow. Background Art

[0002] As people's living standards improve and their health awareness increases, more and more people are beginning to pay attention to sleep quality and its impact on physical health. Studies have shown that sleep quality directly affects a person's physical health, mental state, and overall quality of life. As an important part of the sleep system, the comfort and performance of the pillow largely determine the quality of sleep.

[0003] The support provided by a pillow to the head and neck is the result of a complex biomechanical interaction. It not only needs to effectively relieve the pressure on the neck and shoulders, but also needs to ensure the natural curvature of the cervical spine and the healthy compression of the intervertebral discs. In addition, the design of the pillow also needs to take into account the degree of relaxation of the neck muscles and the smooth blood supply from the carotid artery and vertebral artery to the brain. In summary, choosing the right pillow is of great significance to improving sleep quality and maintaining health.

[0004] In recent years, some smart pillow products have been launched on the market, mainly airbag pillows. However, these airbag pillows generally have a small number of airbags (1-2), which makes them unable to provide sufficient and fitting support during the adjustment process. During long sleep, unconscious movements of the human body often cause the head to shift, which in turn causes unnatural bending of the neck and increases the risk of neck diseases.

[0005] Based on the above problems, the present invention proposes a multi-airbag pillow adaptive adjustment method and a multi-airbag adaptive pillow. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a multi-airbag pillow adaptive adjustment method and a multi-airbag adaptive pillow which can fully fit and support the head and neck.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solution: a method for adaptively adjusting a multi-airbag pillow, comprising the following steps:

[0008] S1. The multi-airbag pillow is empty, and each airbag inside is inflated to an overfilled state through a separate air pump;

[0009] S2. Calibrate the initial air pressure of each airbag, continuously detect the internal air pressure of each airbag and calculate the difference between it and the initial air pressure, and record the difference between the current air pressure and the initial air pressure, the difference between the previous air pressure and the initial air pressure, and the difference between the previous air pressure and the initial air pressure. According to these three indicators, calculate the output power PWM of the corresponding air pump and adjust the airbag;

[0010] S3. Load the multi-airbag pillow, detect the pressure change process of each airbag, obtain the difference between the pressures of each airbag twice, and record the pressure Pi of the current airbag i when the difference between multiple detections of a single airbag is greater than the set value for three consecutive times;

[0011] S4. Record the pressure Pi of the current airbag ten times continuously. After recording, remove the maximum and minimum values ​​to obtain the average value to obtain the judgment pressure PTi, and summarize the judgment pressure of each airbag into a judgment matrix X0;

[0012] S5. Calculate the judgment matrix X0 and output the corresponding target pressure matrix X1;

[0013] S6. Compare the target pressure matrix X1 with the corresponding airbags, calculate the difference between each airbag and the target pressure, and record the difference between the current air pressure and the target pressure, the difference between the previous air pressure and the target pressure, and the difference between the previous air pressure and the target pressure. Based on these three indicators, calculate the output power PWM of the corresponding air pump and adjust the airbag.

[0014] Furthermore, in S2 and S6, the difference between the current airbag pressure and the initial air pressure / target air pressure is continuously calculated and adjusted by the following formula until the error is zero:

[0015] u(k)=u(k-1)+Δu(k)

[0016] Δu(k)=K_P·[e(k)-e(k-1)]+K_I·e(k)+K_D·[e(k)-2e(k-1)+e(k-2)]

[0017] Among them, u(k) is the airbag pressure value in the current state, u(k-1) is the airbag pressure value adjusted last time, Δu(k) is the increase in this adjustment, K_P is the proportional coefficient, K_I is the integral coefficient, K_D is the differential coefficient, e(k) is the error between the current airbag pressure and the initial air pressure / target air pressure, e(k-1) is the error between the last airbag pressure and the initial air pressure / target air pressure, and e(k-2) is the error between the previous airbag pressure and the initial air pressure / target air pressure.

[0018] Furthermore, in S2 and S6, the output power of the air pump is calculated using the following formula:

[0019] PWM=Last_PWM+K_P·[Bias-Last_bias]+K_I·Bias+K_D·[Bias-2

[0020] *Last_bias+Last2_bias]

[0021] Among them, PWM is the output power of the air pump in the current state, Last_PWM is the output power of the air pump adjusted last time, Bias is the difference between the current air pressure and the initial air pressure / target air pressure, Last_bias is the previous air pressure and the initial air pressure / target air pressure, and Last2_bias is the difference between the previous air pressure and the initial air pressure / target air pressure.

[0022] Furthermore, the specific adjustment of the airbag according to the calculated output power PWM of the air pump is as follows:

[0023] When the calculated output power PWM of the air pump is greater than 1000, PWM is set equal to 1000, the output power of the air pump is limited, and the air pump is in the output state to inflate the airbag;

[0024] When PWM is less than -1000, set PWM equal to -1000, limit the output power of the air pump, and the air pump is in the off state;

[0025] And according to the data of the target pressure matrix X1, the airbags are adjusted one by one in order from large to small, and the process is repeated three times.

[0026] Furthermore, in S5, the process of obtaining the target pressure matrix X1 through X0 operation is as follows:

[0027] S5.1. For the data sequence represented by the input judgment matrix X0, extract the data units corresponding to one time step each time in sequence and input them into the RNN model;

[0028] S5.2. At each time step, the data of the N parameters corresponding to the input judgment matrix X0 will be combined with the current hidden layer state;

[0029] S5.3. According to the RNN's own operation logic, the corresponding transformation is performed through the pre-set weight matrix to form an X1 matrix containing N parameters.

[0030] Furthermore, in S1, the multi-airbag pillow being unloaded includes an automatic inflation stage of the multi-airbag pillow and a recovery stage when the human head and neck leave the pillow.

[0031] A multi-airbag adaptive pillow comprises a pillow cover, a surface comfort layer and a sponge filling frame arranged in the pillow cover from top to bottom, a supporting airbag array embedded in the sponge filling frame, a control box and a host computer for controlling the inflation and deflation of the supporting airbag array, wherein the control box and the host computer cooperate to adopt the multi-airbag pillow adaptive adjustment method to realize the inflation and deflation of the supporting airbag array.

[0032] Furthermore, the surface comfort layer includes a three-dimensional wave pressure-relieving sponge layer, a carbon fiber grid moisture and heat dissipation layer, and a cotton fiber rod sound insulation layer, which are arranged in sequence from top to bottom.

[0033] Furthermore, the control box at least includes a control circuit board, an airway control valve, multiple pressure monitoring modules and multiple air pumps. The airway control valve connects the support airbag array with the multiple pressure monitoring modules and the multiple air pumps one-to-one through an airway diverter and a hose. The control circuit board connects the airway control valve and the air pump through a signal control line to realize the inflation and deflation functions of the airbag. The control circuit board is connected to the pressure monitoring module through a signal control line to realize continuous data exchange and real-time detection of the pressure status of each airbag.

[0034] Furthermore, the control circuit board includes at least a main control module for collecting and analyzing the pressure data obtained by the sensor in real time, and a communication module for communicating with the host computer. The host computer includes at least a receiving module for connecting the pressure data of the communication module and returning the target control instructions, and a processing module for processing the pressure data.

[0035] The beneficial effects of the present invention are embodied in:

[0036] 1. Automatically adjust the inflation volume of the airbag according to the user's posture changes during sleep to achieve the best fit and support for the head; by changing the gas volume of multiple airbags, the height of different parts of the human head can be adjusted separately during sleep, so that the pillow can be adjusted to different heights according to different sleeping positions of the human body, avoiding problems such as cervical deformation caused by long-term stress on the neck during sleep, reducing the tension and fatigue of the neck muscles, and reducing the risk of cervical diseases;

[0037] 2. The multi-airbag structure that supports the airbag array can better detect the real-time pressure of the head. According to the pressure of each user's head and neck on the airbag, it automatically adapts the most comfortable and healthy head support height, which can help the human cervical spine maintain a natural curvature during sleep, and is conducive to the relaxation and recovery of the cervical spine during sleep, reducing the risk of cervical spine diseases;

[0038] 3. The use of a supporting airbag array and a sponge-filled frame avoids head deviation during sleep due to insufficient support caused by traditional airbag pillows due to too few airbags. It can provide stable and effective support to avoid slippage during sleep. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the steps of the adaptive adjustment method of the multi-airbag pillow of the present invention;

[0040] Figure 2 Schematic diagram of the structure of the multi-airbag adaptive pillow of the present invention;

[0041] Figure 3 This is an exploded view of the structure of the multi-airbag adaptive pillow of the present invention;

[0042] Figure 4 This is an exploded view of the surface comfort layer structure of the present invention;

[0043] Figure 5 It is a schematic diagram of a control box of the present invention.

[0044] The components in the accompanying drawings are marked as follows: 1. Pillow cover; 2. Surface comfort layer; 21. Three-dimensional wave pressure-relieving sponge layer; 22. Carbon fiber grid moisture dissipation and heat dissipation layer; 23. Cotton fiber rod sound insulation layer; 3. Sponge filling skeleton; 4. Support airbag array; 5. Control box; 51. Control circuit board; 511. Main control module; 512. Communication module; 52. Airway control valve; 53. Pressure monitoring module; 54. Air pump; 6. Host computer. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0046] See also Figure 1 .

[0047] The multi-airbag pillow adaptive adjustment method of the present invention comprises the following steps:

[0048] S1. The multi-airbag pillow is empty, and each airbag inside is inflated to an overfilled state through a separate air pump;

[0049] In this step, the airbag is inflated to above 1Kpa. When the pressure monitoring module detects that the airbag pressure reaches 1Kpa, the air pump continues to work for 500ms to ensure that each airbag is in a slightly overcharged state.

[0050] S2. Calibrate the initial air pressure of each airbag, continuously detect the internal air pressure of each airbag and calculate the difference between it and the initial air pressure, and record the difference between the current air pressure and the initial air pressure, the difference between the previous air pressure and the initial air pressure, and the difference between the previous air pressure and the initial air pressure. According to these three indicators, calculate the output power PWM of the corresponding air pump and adjust the airbag;

[0051] S3. Load the multi-airbag pillow, detect the pressure change process of each airbag, obtain the difference between the pressures of each airbag twice, and record the pressure Pi of the current airbag i when the difference between multiple detections of a single airbag is greater than the set value for three consecutive times;

[0052] In this step, the difference between the two air pressures of each airbag Error_i (the difference of the i-th airbag) is continuously detected. When the sum of the differences detected multiple times for a single airbag is greater than 3.0Kpa for three consecutive times, the current pressure Pi (representing the i-th airbag) is recorded;

[0053] S4. Record the pressure Pi of the current airbag ten times continuously. After recording, remove the maximum and minimum values ​​to obtain the average value to obtain the judgment pressure PTi, and summarize the judgment pressure of each airbag into a judgment matrix X0;

[0054] In this step, ten consecutive records are recorded as Pi_n (representing the nth air pressure recorded by the i-th airbag).

[0055]

[0056] (Total 15 airbags);

[0057] S5. Calculate the judgment matrix X0 and output the corresponding target pressure matrix X1;

[0058] S6. Compare the target pressure matrix X1 with the corresponding airbags, calculate the difference between each airbag and the target pressure, and record the difference between the current air pressure and the target pressure, the difference between the previous air pressure and the target pressure, and the difference between the previous air pressure and the target pressure. Calculate the output power PWM of the corresponding air pump based on these three indicators and adjust the airbag;

[0059] This design automatically adjusts the inflation volume of the airbag according to the changes in the user's posture during sleep, thereby achieving the best fit and support for the head; by changing the amount of gas in multiple airbags, the height of different parts of the human head can be adjusted separately during sleep, so that the pillow can be adjusted to different heights according to different sleeping positions, avoiding long-term stress on the neck during sleep and causing cervical deformation and other problems, reducing tension and fatigue of the neck muscles, and reducing the risk of cervical diseases.

[0060] In one embodiment, in S2 and S6, the difference between the current airbag pressure and the initial air pressure / target air pressure is continuously calculated and adjusted by the following formula until the error is zero:

[0061] u(k)=u(k-1)+Δu(k)

[0062] Δu(k)=K_P·[e(k)-e(k-1)]+K_I·e(k)+K_D·[e(k)-2e(k-1)+e(k-2)]

[0063] Among them, u(k) is the airbag pressure value in the current state, u(k-1) is the airbag pressure value adjusted last time, Δu(k) is the increase in this adjustment, K_P is the proportional coefficient, K_I is the integral coefficient, K_D is the differential coefficient, e(k) is the error between the current airbag pressure and the initial air pressure / target air pressure, e(k-1) is the error between the last airbag pressure and the initial air pressure / target air pressure, and e(k-2) is the error between the previous airbag pressure and the initial air pressure / target air pressure.

[0064] In one embodiment, in S2 and S6, the output power of the air pump is calculated using the following formula:

[0065] PWM=Last_PWM+K_P·[Bias-Last_bias]+K_I·Bias+K_D·[Bias-2

[0066] *Last_bias+Last2_bias]

[0067] Among them, PWM is the output power of the air pump in the current state, Last_PWM is the output power of the air pump adjusted last time, Bias is the difference between the current air pressure and the initial air pressure / target air pressure, Last_bias is the previous air pressure and the initial air pressure / target air pressure, and Last2_bias is the difference between the previous air pressure and the initial air pressure / target air pressure.

[0068] In one embodiment, the specific adjustment of the airbag according to the calculated output power PWM of the air pump is as follows:

[0069] When the calculated output power PWM of the air pump is greater than 1000, PWM is set equal to 1000, the output power of the air pump is limited, and the air pump is in the output state to inflate the airbag;

[0070] When PWM is less than -1000, set PWM equal to -1000, limit the output power of the air pump, and the air pump is in the off state;

[0071] And according to the data of the target pressure matrix X1, the airbags are adjusted one by one in order from large to small, and the process is repeated three times. It should be noted that the airbag is connected to the airway control valve. When PWM is greater than 1000, the airway control valve is closed, and the air pump is connected to the airbag to achieve inflation. When PWM is less than -1000, the airway control valve is open, and the airbag is connected to the outside world to achieve deflation.

[0072] In one embodiment, in S5, the process of obtaining the target pressure matrix X1 through X0 operation is as follows:

[0073] S5.1. For the data sequence represented by the input judgment matrix X0, extract the data units corresponding to one time step each time in sequence and input them into the RNN model;

[0074] In this step, the data unit is represented as Its dimensions correspond to 15 parameters (there are 15 airbags in total), namely

[0075] S5.2. At each time step, the data of the N parameters corresponding to the input judgment matrix X0 will be combined with the current hidden layer state;

[0076] In this step, the time step is t, the N parameters are 15, and the current hidden layer state is h t-1 , the initial hidden layer state h0 is usually initialized in a conventional way, such as an all-zero vector, and Here n is the number of neurons in the hidden layer;

[0077] S5.3. According to the RNN's own operation logic, the pre-set weight matrix is ​​used for corresponding transformation to form an X1 matrix containing N parameters;

[0078] In this step, "performing corresponding transformations through a preset weight matrix" is specifically:

[0079] Suppose the weight matrix input to the hidden layer is The weight matrix from hidden layer to hidden layer is The bias vector is Then the hidden layer state update calculation formula is as follows:

[0080] h t =tanh(W ih x t +W hh h t-1 +b h )

[0081]

[0082] The weight matrix from the hidden layer to the output layer is The corresponding bias vector is Using the updated hidden layer state h t Perform a linear transformation to generate the predicted output y t , and its calculation formula is:

[0083] y t =W ho h t +b o

[0084] Heret It is also a vector with dimensions corresponding to 15 parameters, that is As time steps progress, such prediction outputs are continuously generated, and finally converge to form an X1 matrix containing 15 parameters.

[0085] In one embodiment, in S1, the multi-airbag pillow when unloaded includes the multi-airbag pillow automatic inflation stage and the recovery stage when the human head and neck leave the pillow. It should be noted that when the human head and neck leave the pillow, the air pressure of the airbag inside the pillow drops suddenly. When the sudden drop in airbag pressure is detected (when the difference of a single airbag detection is greater than 1.5Kpa, and the sum of the differences of all airbags is greater than 4.5Kpa), the pillow starts the recovery stage and repeats S1-S2.

[0086] A multi-airbag adaptive pillow, see Figure 2-3 , comprising a pillow cover 1, a surface comfort layer 2 and a sponge filling frame 3 arranged in the pillow cover 1 from top to bottom, a support airbag array 4 embedded in the sponge filling frame 3, a control box 5 and a host computer 6 for controlling the inflation and deflation of the support airbag array 4, and the control box 5 and the host computer 6 cooperate to adopt the multi-airbag pillow adaptive adjustment method to realize the inflation and deflation of the support airbag array 4;

[0087] It should be noted that the sponge filling skeleton 3 is cut from a piece of D-shaped sponge, a 4-6CM circular through hole is opened in the center of the D-shaped sponge, and 3-5 rows and 3-7 columns of circular through hole skeletons symmetrical about the center of the D-shaped sponge are formed with a spacing of 1-2.5CM. An airbag of 4-6CM and 8-12CM in height is placed in the through hole of the D-shaped sponge. The size of the airbag is consistent with the through hole on the B-shaped sponge, and multiple airbags form a supporting airbag array 4;

[0088] Such a design, using a multi-airbag structure supporting the airbag array 4, can better detect the real-time pressure of the head, and automatically adapt the most comfortable and healthy head support height according to the pressure of the head and neck of each user on the airbag, which can help the human cervical spine to maintain a natural curvature during sleep, and is conducive to the relaxation and recovery of the cervical spine during sleep, reducing the risk of cervical spine diseases;

[0089] The use of the supporting airbag array 4 and the sponge-filled skeleton 3 avoids the head deviation caused by insufficient support during sleep due to too few airbags in traditional airbag pillows, and can provide stable and effective support to avoid slippage during sleep.

[0090] In one embodiment, see Figure 4The surface comfort layer 2 includes a three-dimensional wave pressure-relief sponge layer 21, a carbon fiber mesh moisture-dissipation and heat-dissipation layer 22, and a cotton fiber rod sound-insulating layer 23, which are arranged in sequence from top to bottom. This design effectively absorbs moisture and perspiration from the head during sleep, reduces the feeling of stuffiness, and provides a more comfortable sleeping experience.

[0091] In one embodiment, see Figure 5 The control box 5 at least includes a control circuit board 51, an airway control valve 52, a plurality of pressure monitoring modules 53 and a plurality of air pumps 54. The airway control valve 52 connects the support airbag array 4 with the plurality of pressure monitoring modules 53 and the plurality of air pumps 54 in a one-to-one correspondence through an airway diverter and a hose. The control circuit board 51 connects the airway control valve 52 and the air pump 54 through a signal control line to realize the inflation and deflation function of the airbag. The control circuit board 51 connects the pressure monitoring module 53 through a signal control line to realize continuous data exchange and real-time detection of the pressure status of each airbag.

[0092] It should be noted that each airbag supporting the airbag array 4 corresponds to an air pump 54 and a pressure monitoring module 53 .

[0093] In one embodiment, see Figure 5 The control circuit board 51 at least includes a main control module 511 for real-time collection and analysis of pressure data acquired by the sensor, and a communication module 512 for communicating with the host computer 6. The host computer 6 at least includes a receiving module for connecting to the pressure data of the communication module 512 and returning the target control instruction, and a processing module for processing the pressure data;

[0094] It should be noted that the communication module includes a Bluetooth module, which is used for communication between various devices;

[0095] The Bluetooth module is used for short-range communication to transmit data at the measurement site, using short baud high frequency (UHF) radio waves to communicate via the ISM frequency band of 2.4 to 2.85 GHz;

[0096] The main control module 511 includes a data processing module capable of collecting and analyzing pressure data acquired by the sensor in real time;

[0097] The data processing module is used to receive the output signal of the pressure sensor and convert it into a digital signal, so as to calculate the airbag pressure value;

[0098] The status display indicator light displays the connection status of the device and is used to check the power status of the device;

[0099] The power supply is also provided with a control switch;

[0100] The pressure monitoring module 53 is a highly sensitive air pressure sensor with a sensitivity of up to 0.5%, which can accurately sense and respond to tiny pressure changes;

[0101] The receiving module is a Bluetooth receiving terminal, which is used to connect to the Bluetooth module on the communication module 512 of the control box, receive the pressure data of the adaptive pillow in real time and return the target control instruction;

[0102] The target control command, after the computer collects the adaptive control data, it analyzes and processes it and returns the head pressure data suitable for the current user;

[0103] After receiving the target control instruction, the control box 5 adjusts each corresponding small airbag to the target air pressure through the adjustment algorithm;

[0104] The host computer 6 also includes a display part, which includes a computer and real-time detection system software. The software can process data from the receiving module and convert the pressure value into a matrix or pressure image display;

[0105] The pressure image visualizes and outputs the monitored real-time pressure signal of the subject's head in the form of a 3D topographic map, uses different colors to represent different pressure states, and provides an intuitive user interface and data interaction;

[0106] The real-time detection system software has the functions of displaying pressure data of all positions of the head, starting and stopping acquisition, storing the head pressure signal of the subject and presenting the thermal map of the human head.

[0107] It should also be noted that the present application also conducts a human head pressure distribution test on a multi-airbag adaptive pillow made in the above embodiment, and uses a body pressure distribution measurement system (BPMS) provided by Tekscan of the United States to test the pressure distribution data between the person and the pillow, including a CONFOR body pressure sensing pad (1 piece) and a handle (1 piece). In this experiment, four pressure threshold values ​​of 5 mmHg (0.67 kPa), 10 mmHg (1.33 kPa), 20 mmHg (2.67 kPa), and 30 mmHg (4.00 kPa) were used, and five contact surface indexes were used to reflect the contact area between the person and the pillow, namely: "≤0.67 kPa contact area" (contact area within the low pressure threshold), "0.67-1.33 kPa contact area" (contact area within the medium-low pressure threshold), "1.33-2.67 kPa contact area" (contact area within the medium pressure threshold), "2.67-4.00 kPa contact area" (contact area within the medium-high pressure threshold), and "≥4.00 kPa contact area" (contact area within the high pressure threshold). The contact area data of the head and shoulders are shown in Table 1, and the press pressure index data of the head and shoulders are shown in Table 2.

[0108] Table 1 Human-pillow interface contact area

[0109]

[0110] As can be seen from Table 1, the contact area of ​​the multi-airbag adaptive pillow within the medium-high pressure and high pressure threshold range is small, both before and after adjustment, and most of them are less than 10%. At the same time, the contact area within the low pressure and medium-low pressure threshold range of each part accounts for more than 75% of the total contact area; after adjustment, the contact area within the medium pressure threshold and the medium-low pressure contact area of ​​the multi-airbag adaptive pillow increase, and the contact area within the medium-high pressure threshold and the contact area within the high pressure threshold significantly decrease. This shows that the multi-airbag adaptive pillow can increase the medium-low pressure contact area during use, and reduce the high pressure contact area, which can relieve pressure on the head and neck of the human body and improve sleep comfort.

[0111] Table 2 Pressure distribution and pressure index

[0112]

[0113] As can be seen from Table 2, the multi-airbag adaptive pillow has lower pressure and pressure index than the control pillow before and after adjustment. The maximum pressure and average pressure of the multi-airbag adaptive pillow are reduced after adjustment, which shows that the airbag pillow has the effect of regulating and relieving pressure. When in use, the pressure of any part of the human head is below 2.02Kpa, which is much lower than the pressure of the arteriolar blood vessels (3.3-4.6kPa), which can ensure the normal blood circulation of the human head and neck, effectively relieve the pressure on the human-pillow interface, and improve sleep comfort.

[0114] It should be understood that the examples and implementation modes described herein are for illustrative purposes only and are not intended to limit the present invention. Those skilled in the art may make various modifications or changes based on the examples and implementation modes. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0115] It should be noted that if the embodiments of the present invention involve directional indications such as up, down, left, right, front, back, etc., then the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture as shown in the accompanying drawings. If the specific posture changes, the directional indication will also change accordingly.

[0116] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or schemes that A and B meet at the same time. In addition, "multiple" refers to more than two. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

Claims

1. A method for adaptively adjusting a multi-airbag pillow, characterized in that: The following steps are involved: S1. The multi-airbag pillow is empty, and each airbag inside is inflated to an overfilled state through a separate air pump; S2. Calibrate the initial air pressure of each airbag, continuously detect the internal air pressure of each airbag and calculate the difference between it and the initial air pressure, and record the difference between the current air pressure and the initial air pressure, the difference between the previous air pressure and the initial air pressure, and the difference between the previous air pressure and the initial air pressure. According to these three indicators, calculate the output power PWM of the corresponding air pump and adjust the airbag; S3. Load the multi-airbag pillow, detect the pressure change process of each airbag, obtain the difference between the pressures of each airbag twice, and record the pressure Pi of the current airbag i when the difference between multiple detections of a single airbag is greater than the set value for three consecutive times; S4. Record the pressure Pi of the current airbag ten times continuously. After recording, remove the maximum and minimum values ​​to obtain the average value to obtain the judgment pressure PTi, and summarize the judgment pressure of each airbag into a judgment matrix X0; S5. Calculate the judgment matrix X0 and output the corresponding target pressure matrix X1; S6. Compare the target pressure matrix X1 with the corresponding airbags, calculate the difference between each airbag and the target pressure, and record the difference between the current air pressure and the target pressure, the difference between the previous air pressure and the target pressure, and the difference between the previous air pressure and the target pressure. Based on these three indicators, calculate the output power PWM of the corresponding air pump and adjust the airbag.

2. The method for adaptively adjusting a multi-airbag pillow according to claim 1, characterized in that: In S2 and S6, the difference between the current airbag pressure and the initial air pressure / target air pressure is continuously calculated and adjusted using the following formula until the error is zero: u(k)=u(k-1)+Δu(k) Δu(k)=K_P·[e(k)-e(k-1)]+K_I·e(k)+K_D·[e(k)-2e(k-1)+e(k-2)] Among them, u(k) is the airbag pressure value in the current state, u(k-1) is the airbag pressure value adjusted last time, Δu(k) is the increase in this adjustment, K_P is the proportional coefficient, K_I is the integral coefficient, K_D is the differential coefficient, e(k) is the error between the current airbag pressure and the initial air pressure / target air pressure, e(k-1) is the error between the last airbag pressure and the initial air pressure / target air pressure, and e(k-2) is the error between the previous airbag pressure and the initial air pressure / target air pressure.

3. The method for adaptively adjusting a multi-airbag pillow according to claim 2, characterized in that: In S2 and S6, the output power of the air pump is calculated using the following formula: PWM=Last_PWM+K_P·[Bias-Last_bias]+K_I·Bias+K_D·[Bias-2 *Last_bias+Last2_bias] Among them, PWM is the output power of the air pump in the current state, Last_PWM is the output power of the air pump adjusted last time, Bias is the difference between the current air pressure and the initial air pressure / target air pressure, Last_bias is the previous air pressure and the initial air pressure / target air pressure, and Last2_bias is the difference between the previous air pressure and the initial air pressure / target air pressure.

4. The method for adaptively adjusting a multi-airbag pillow according to claim 3, characterized in that: The specific adjustment of the airbag according to the calculated output power PWM of the air pump is as follows: When the calculated output power PWM of the air pump is greater than 1000, PWM is set equal to 1000, the output power of the air pump is limited, and the air pump is in the output state to inflate the airbag; When PWM is less than -1000, set PWM equal to -1000, limit the output power of the air pump, and the air pump is in the off state; And according to the data of the target pressure matrix X1, the airbags are adjusted one by one in order from large to small, and the process is repeated three times.

5. The method for adaptively adjusting a multi-airbag pillow according to claim 1, characterized in that: In S5, the process of obtaining the target pressure matrix X1 through X0 operation is as follows: S5.

1. For the data sequence represented by the input judgment matrix X0, extract the data units corresponding to one time step each time in sequence and input them into the RNN model; S5.

2. At each time step, the data of the N parameters corresponding to the input judgment matrix X0 will be combined with the current hidden layer state; S5.

3. According to the RNN's own operation logic, the corresponding transformation is performed through the pre-set weight matrix to form an X1 matrix containing N parameters.

6. The method for adaptively adjusting a multi-airbag pillow according to claim 1, characterized in that: In S1, the multi-airbag pillow is unloaded, including the automatic inflation stage of the multi-airbag pillow and the recovery stage when the human head and neck leave the pillow.

7. A multi-airbag adaptive pillow, characterized in that: The invention comprises a pillow cover (1), a surface comfort layer (2) and a sponge filling frame (3) arranged in the pillow cover (1) from top to bottom, a support airbag array (4) embedded in the sponge filling frame (3), a control box (5) and a host computer (6) for controlling the inflation and deflation of the support airbag array (4), wherein the control box (5) and the host computer (6) cooperate to adopt the multi-airbag pillow adaptive adjustment method as described in any one of claims 1 to 6 to realize the inflation and deflation of the support airbag array (4).

8. The multi-airbag adaptive pillow according to claim 7, characterized in that: The surface comfort layer (2) comprises a three-dimensional wave pressure-reducing sponge layer (21), a carbon fiber grid moisture and heat dissipation layer (22), and a cotton fiber rod sound insulation layer (23) which are arranged in sequence from top to bottom.

9. The multi-airbag adaptive pillow according to claim 7, characterized in that: The control box (5) at least comprises a control circuit board (51), an airway control valve (52), a plurality of pressure monitoring modules (53) and a plurality of air pumps (54); the airway control valve (52) connects the support airbag array (4) with the plurality of pressure monitoring modules (53) and the plurality of air pumps (54) in a one-to-one correspondence via an airway diverter and a hose connection; the control circuit board (51) connects the airway control valve (52) and the air pump (54) via a signal control line to realize the inflation and deflation functions of the airbags; the control circuit board (51) connects the pressure monitoring modules (53) via a signal control line to realize continuous data exchange and real-time detection of the pressure status of each airbag.

10. The multi-airbag adaptive pillow according to claim 9, characterized in that: The control circuit board (51) comprises at least a main control module (511) for real-time collection and analysis of pressure data acquired by the sensor, and a communication module (512) for communicating with the host computer (6); the host computer (6) comprises at least a receiving module for connecting to the pressure data of the communication module (512) and returning target control instructions, and a processing module for processing the pressure data.

Images