A condition monitoring method and system
By setting up a signal transmitting device that only transmits radio signals on the monitoring body, using signal strength, phase angle and coordinate changes for state monitoring, the problems of high power consumption and high cost in the prior art are solved, and low cost and low power are achieved Status monitoring and management of consumption.
Patent Information
- Application Number
- CN202310543431.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-12
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-05-12
AI Technical Summary
The existing state monitoring methods have high power consumption and high cost problems, which limit their management and promotion.
A signal transmitting device that only transmits radio signals is provided on the monitoring body. The state monitoring is realized through the signal intensity changes, phase angle changes and coordinate position changes of the radio signals transmitted by the signal transmitting device to the base station, reducing the hardware complexity and power consumption and cost.
It realizes low-cost and low-power state monitoring, simplifies hardware complexity, and improves the convenience of monitoring and management.
Smart Images

Figure CN116763298B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of wireless communication technology, and in particular to a state monitoring method and system. Background Art
[0002] Condition monitoring technology is widely used in equipment operation status monitoring, biological living state judgment, biological exercise statistics, biological physiological and psychological behavior analysis, etc.; currently, sensor technology is usually used to directly monitor the status of the monitored object, which will bring about high power consumption and high cost, which is not conducive to the management and promotion of condition monitoring.
[0003] It can be seen that the state monitoring method in the prior art has the problems of high power consumption and high cost. Summary of the invention
[0004] The present application provides a condition monitoring method and system, which solves the problems of high power consumption and high cost in the condition monitoring methods in the prior art. Condition monitoring can be achieved by setting a signal transmitting device that only transmits radio signals on the monitoring body, which greatly reduces the hardware complexity, power consumption and cost of condition monitoring, and brings convenience to the management and promotion of condition monitoring.
[0005] In a first aspect, the present invention provides a state monitoring method, which is applied to a state monitoring system, wherein the state monitoring system includes a base station and a signal transmitting device arranged on a monitored object, and the monitoring method includes: obtaining original characteristic parameters based on a radio signal transmitted by the signal transmitting device and received by the base station, wherein the original characteristic parameters include one or any combination of signal strength, positioning coordinates or phase angle; and obtaining the state characteristics of each monitored object based on the original characteristic parameters of each monitored object.
[0006] Optionally, based on the original characteristic parameters of each monitoring body, the state characteristics of each monitoring body are obtained, including: performing data segmentation on all the original characteristic parameters of each monitoring body within a preset time period to obtain the statistical probability of each data segment; performing statistical analysis on the statistical probabilities of all the data segments of each monitoring body to obtain the statistical characteristic parameters of each monitoring body; and obtaining the state characteristics of each monitoring body based on the statistical characteristic parameters of each monitoring body.
[0007] Optionally, when the original characteristic parameter is signal strength, data segmentation is performed on all original characteristic parameters of each monitoring object within a preset time period to obtain the statistical probability of each data segment, including: segmenting the signal strength value according to preset intervals to obtain multiple segmentation intervals; and according to the segmentation interval to which each original characteristic parameter of each monitoring object within the preset time period belongs, calculating the statistical probability of each segmentation interval.
[0008] Optionally, when the original characteristic parameter is a positioning coordinate, data segmentation is performed on all the original characteristic parameters of each monitored object within a preset time period to obtain the statistical probability of each data segment, including: establishing a first coordinate system with the base station as the origin; dividing the first coordinate system into regions according to a grid method to obtain multiple regional intervals; and calculating the statistical probability of each regional interval according to the regional interval to which each original characteristic parameter of each monitored object within the preset time period belongs.
[0009] Optionally, when the original characteristic parameter is a combination of signal strength and phase angle, data segmentation is performed on all original characteristic parameters of each monitored object within a preset time period to obtain the statistical probability of each data segment, including: establishing a second coordinate system with the base station as the origin, signal strength as the horizontal coordinate, and phase angle as the vertical coordinate; dividing the second coordinate system into regions according to a grid method to obtain multiple regional intervals; and calculating the statistical probability of each regional interval according to the regional interval to which each original characteristic parameter of each monitored object within the preset time period belongs.
[0010] Optionally, statistical analysis is performed on the statistical probabilities of all data segments of each monitoring object to obtain statistical characteristic parameters of each monitoring object, including: calculating the information entropy of each monitoring object based on the statistical probabilities of all data segments of each monitoring object; wherein the statistical characteristic parameters of each monitoring object include the information entropy of each monitoring object.
[0011] Optionally, the information entropy formula of each monitoring object is expressed as:
[0012]
[0013] in, represents information entropy, represents the statistical probability of each data segment, .
[0014] Optionally, obtaining the state characteristics of each monitoring body according to the statistical characteristic parameters of each monitoring body also includes: comparing the statistical characteristic parameters of each monitoring body with a threshold interval, when the statistical characteristic parameters are within the threshold interval, the state characteristics of the monitoring body are normal; when the statistical characteristic parameters are outside the threshold interval, the state characteristics of the monitoring body are abnormal.
[0015] Optionally, the method also includes: obtaining a first information entropy based on the signal strength and phase angle of each monitored object; obtaining a second information entropy based on the positioning coordinates of each monitored object; and performing a joint threshold judgment on the first information entropy and the second information entropy to obtain the state characteristics of each monitored object.
[0016] Optionally, obtaining the state characteristics of each monitored object based on the original characteristic parameters of each monitored object also includes: taking the base station as the origin, the signal strength in the original characteristic parameters as the radius, and the phase angle in the original characteristic parameters as the polar angle, and generating a motion trajectory diagram with the original characteristic parameters within a preset time period; performing image recognition on the motion trajectory diagram to obtain the state characteristics of each monitored object.
[0017] Optionally, the state characteristics of each monitoring body are obtained based on the original characteristic parameters of each monitoring body, including: calculating the distance between the monitoring body and the base station based on the signal strength or positioning coordinates in the original characteristic parameters; obtaining the activity amount of each monitoring body within the preset time period based on the change in the distance between each monitoring body and the base station within the preset time period; and obtaining the state characteristics of each monitoring body based on the activity amount of each monitoring body.
[0018] Optionally, the distance between the monitored object and the base station is calculated based on the signal strength or positioning coordinates in the original characteristic parameters, including: according to the sliding time window, the original characteristic parameters are corrected and denoised, and then the distance between the monitored object and the base station is calculated based on the signal strength or positioning coordinates in the original characteristic parameters.
[0019] In a second aspect, the present invention provides a status monitoring system, which includes: a signal transmitting device, which is arranged on a monitored object and is used to transmit a radio signal; a base station, which is used to obtain original characteristic parameters based on the radio signal transmitted by the signal transmitting device received by the base station, wherein the original characteristic parameters include one or any combination of signal strength, positioning coordinates or phase angle; and is also used to obtain the status characteristics of each monitored object based on the original characteristic parameters of each monitored object.
[0020] Optionally, the signal transmitting device includes: a wireless module for transmitting radio signals; and a power module connected to the wireless model for providing power to the wireless module.
[0021] Compared with the prior art, the present invention has the following beneficial effects:
[0022] The present invention realizes the state monitoring of the monitored object by arranging a signal transmitting device which only transmits radio signals on the monitored object, and based on the signal strength change, phase angle change and coordinate position change of the radio signal transmitted by the signal transmitting device reaching the base station, thereby greatly reducing the hardware complexity of the state monitoring, and further reducing the power consumption and cost, bringing convenience to the management and promotion of the state monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 The figure is a flow chart of a state monitoring method provided in an embodiment of the present application;
[0024] Figure 2 Shown is a structural schematic diagram of a state monitoring system provided in an embodiment of the present application;
[0025] Figure 3 The embodiment of the present application is shown in Figure 1 A first specific flow chart of step S102;
[0026] Figure 4 The figure shows a data segmentation schematic diagram based on a segmentation method provided in an embodiment of the present application;
[0027] Figure 5 The figure shows a first data segmentation schematic diagram based on the grid method provided in an embodiment of the present application;
[0028] Figure 6 The figure shows a second data segmentation schematic diagram based on the grid method provided in an embodiment of the present application;
[0029] Figure 7 The embodiment of the present application is shown in Figure 1 A second specific flow chart of step S102;
[0030] Figure 8 Shown is a schematic diagram of a motion trajectory diagram provided in an embodiment of the present application;
[0031] Fig. 9 The embodiment of the present application is shown in Figure 1 A third specific flow chart of step S102;
[0032] Fig.10 Shown is another schematic diagram of a motion trajectory diagram provided in an embodiment of the present application;
[0033] Fig.11 Shown is a training schematic diagram of a deep learning model provided in an embodiment of the present application;
[0034] Fig.12 Shown is a recognition schematic diagram of a deep learning model provided in an embodiment of the present application;
[0035] Fig.13 The figure shows a schematic diagram of the difference distribution of ΔRSSI values of ear tags of cattle in normal activities provided by an embodiment of the present application;
[0036] Fig.14 The figure shows a schematic diagram of the distribution of ΔRSSI differences when the cattle are marked off or have no vital signs, provided in an embodiment of the present application;
[0037] Fig.15 The figure shows a schematic diagram of an application scenario based on human behavior characteristics provided by an embodiment of the present application;
[0038] Fig.16 The figure shows a schematic diagram of a change in normal patrol signal strength provided by an embodiment of the present application;
[0039] Fig.17 The figure shows a schematic diagram of a change in the strength of an irregular patrol signal provided by an embodiment of the present application;
[0040] Fig.18 The figure shows a comparison diagram of a patrol trajectory and corresponding state characteristics provided by an embodiment of the present application;
[0041] Fig.19 The figure shows a schematic diagram of product tracking of a production line provided by an embodiment of the present application;
[0042] Fig. 20 Shown is a schematic diagram of wheel axle rotation tracking provided in an embodiment of the present application. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0044] In a first aspect, the present invention provides a state monitoring method, which specifically includes the following embodiments:
[0045] Embodiment 1
[0046] Figure 1 FIG. 1 is a flow chart of a state monitoring method provided in an embodiment of the present application, such as Figure 1 As shown, the monitoring method comprises:
[0047] Step S101: Acquire original characteristic parameters according to the radio signal transmitted by the signal transmitting device and received by the base station.
[0048] In this embodiment, the status monitoring method is applied to a status monitoring system, which includes a base station and a signal transmitting device arranged on a monitoring object, wherein the signal transmitting device arranged on the monitoring object is not a part of the system. This monitoring system only includes a base station and a signal transmitting device, and the signal transmitting device includes but is not limited to a beacon device.
[0049] like Figure 2In the status monitoring system shown, the base station is used to receive the radio signal of the beacon, and calculate the signal strength and phase angle of the signal arriving at the base station location based on the received radio signal, and can also calculate the positioning coordinates of the beacon based on the received radio signal; therefore, the original characteristic parameters may include one or any combination of signal strength, positioning coordinates or phase angle.
[0050] Step S102: Obtain the state characteristics of each monitored object according to the original characteristic parameters of each monitored object.
[0051] In this embodiment, if Figure 3 As shown, according to the original characteristic parameters of each monitored object, obtaining the state characteristics of each monitored object specifically includes the following steps:
[0052] Step S201: perform data segmentation on all original characteristic parameters of each monitored object within a preset time period to obtain the statistical probability of each data segment.
[0053] In the first implementation of this embodiment, when the original characteristic parameter is signal strength, data segmentation is performed on all original characteristic parameters of each monitoring object within a preset time period to obtain the statistical probability of each data segment, including: segmenting the signal strength value according to a preset interval to obtain multiple segment intervals; and calculating the statistical probability of each segment interval according to the segment interval to which each original characteristic parameter of each monitoring object within the preset time period belongs. Figure 4 As shown, this implementation method performs data segmentation according to the segmentation method; the RSSI is segmented according to the preset interval, each segment interval represents a state, and the statistical probability of all original characteristic parameters (of each monitoring body) falling into the corresponding segment interval is counted to obtain the statistical probability of each segment interval; wherein, the length of each segment interval can be the same or different; the preset interval, preset time period and segment interval can be adjusted according to different monitoring bodies and monitoring scenarios in actual needs.
[0054] In a second implementation method of this embodiment, when the original characteristic parameter is a positioning coordinate, data segmentation is performed on all the original characteristic parameters of each monitored object within a preset time period to obtain the statistical probability of each data segment, including: establishing a first coordinate system with the base station as the origin; performing regional blocking on the first coordinate system according to a grid method to obtain multiple regional intervals; and calculating the statistical probability of each regional interval according to the regional interval to which each original characteristic parameter of each monitored object within the preset time period belongs.
[0055] like Figure 5As shown, this implementation method performs data segmentation according to the grid method; the spatial position in the first coordinate system is divided into regions according to the grid method, and the statistical probability that the positioning coordinates in the original feature parameters fall in different regions is counted respectively, so as to obtain the statistical probability of each regional interval.
[0056] In a third implementation of the present embodiment, when the original characteristic parameter is a combination of signal strength and phase angle, data segmentation is performed on all original characteristic parameters of each monitored object within a preset time period to obtain a statistical probability of each data segment, including: establishing a second coordinate system with the base station as the origin, signal strength as the horizontal coordinate, and phase angle as the vertical coordinate; performing regional blocking on the second coordinate system according to a grid method to obtain a plurality of regional intervals; and calculating the statistical probability of each regional interval according to the regional interval to which each original characteristic parameter of each monitored object within the preset time period belongs.
[0057] like Figure 6 As shown, on a two-dimensional plane, a second coordinate system is established with the base station as the origin, the signal strength as the horizontal coordinate, and the phase angle as the vertical coordinate. Divide the grid and calculate the statistical probability of falling into each grid.
[0058] Step S202: Statistical analysis is performed on the statistical probabilities of all data segments of each monitored object to obtain statistical characteristic parameters of each monitored object.
[0059] In this embodiment, a statistical analysis is performed on the statistical probabilities of all data segments of each monitoring body to obtain statistical characteristic parameters of each monitoring body, including: calculating the information entropy of each monitoring body based on the statistical probabilities of all data segments of each monitoring body; wherein the statistical characteristic parameters of each monitoring body include the information entropy of each monitoring body.
[0060] It should be noted that in statistical physics, entropy is used as a statistical characteristic quantity to judge whether things move in an orderly or disordered manner. The more states a system presents, the greater the entropy value of the system; on the contrary, if the system is more stable and presents a state with limited rules (such as periodic reciprocating motion, stillness, etc.), the smaller the entropy value of the system. The thermodynamic entropy of the system can be obtained by the Boltzmann formula, as shown in formula (1):
[0061] (1)
[0062] In the formula, S represents the entropy of the system, W is the number of microscopic states observed in the system, and k is the Boltzmann constant.
[0063] Thermodynamic entropy defined by Boltzmann usually requires a relatively large number of microscopic states W for statistical analysis. The present invention mainly performs statistical analysis based on information entropy. If something has n independent possible results or states X1, X2, ..., Xn (Such as the segmentation state mentioned in the previous data segmentation), and the probability of each result occurring is p1, p2, ..., p n , , then the information entropy H of things can be expressed as formula (2):
[0064] (2)
[0065] Information entropy reflects the uncertainty of things. The greater the uncertainty, the greater the entropy, and the smaller the uncertainty, the smaller the entropy. The relationship between information entropy and thermodynamic entropy can be expressed as formula (3):
[0066] (3)
[0067] Therefore, it can be seen from formulas (1) to (3) that in this embodiment, whether the state of the monitored object is normal can be determined based on the information entropy of the monitored object, that is, the information entropy of the monitored object is used as a statistical characteristic parameter.
[0068] Step S203: Obtaining the state characteristics of each monitored object according to the statistical characteristic parameters of each monitored object.
[0069] In this embodiment, the statistical characteristic parameters of each monitored object are compared with the threshold interval. When the statistical characteristic parameters are within the threshold interval, the state characteristics of the monitored object are normal; when the statistical characteristic parameters are outside the threshold interval, the state characteristics of the monitored object are abnormal.
[0070] In this embodiment, the threshold interval includes a first threshold and a second threshold; wherein, the first threshold can be 0. When the information entropy approaches 0, it means that the object is close to being quiet and motionless, and the state characteristic is stillness; when the information entropy is larger and greater than the second threshold, it means that the state of the object is more complex and irregular movement is present. For animals, if the RSSI statistics in a day calculate the information entropy, the information entropy approaches 0, which means that the animal is completely motionless, and the possibility of an unhealthy state is greater, that is, it is an abnormal state and a prompt needs to be made; the information entropy is too large, and the animal may be in a state of restless and disordered movement for a day, and the possibility of an unhealthy state is greater, and a prompt needs to be made; the information entropy is fixed within the range of the threshold interval, and the animal conducts regular activities and is in a normal state. In addition, the change in the health state of the animal during its life cycle can be judged by comparing the changes in information entropy at different times of the day. Among them, for different monitoring objects, the second threshold is also different. For example, in Example 1, the RSSI entropy value of the cow can be set to 2.0 to distinguish between normal cows and cows that have dropped the label or have no vital signs.
[0071] Embodiment 2
[0072] Figure 7The embodiment of the present application is shown in Figure 1 A second specific flow chart of step S102 in FIG. Figure 7 As shown, the state characteristics of each monitored object are obtained according to the original characteristic parameters of each monitored object, and the following specific steps are also included:
[0073] Step S301, taking the base station as the origin, the signal strength in the original characteristic parameters as the radius, and the phase angle in the original characteristic parameters as the polar angle, the original characteristic parameters in a preset time period are used to generate a motion trajectory diagram.
[0074] It should be noted that, in this embodiment, the base station is taken as the origin, the RSSI value is taken as the radius, and the phase angle is taken as the The signal strength and phase angle in the preset time period are converted into two-dimensional coordinates according to formula (4), and then the following is generated based on the two-dimensional coordinates: Figure 8 The motion trajectory diagram shown in FIG. 4 is as follows:
[0075] (4)
[0076] Wherein, P represents the RSSI value.
[0077] Step S302: Perform image recognition on the motion trajectory diagram to obtain state characteristics of each monitored object.
[0078] It should be noted that the motion trajectory graph is analyzed and processed based on image processing technology to obtain the corresponding state characteristics. Specifically, in the training stage, each image is labeled in the form of (image, state), and the state value can be one or more of quiet, motionless, and different levels of motion. In the actual application stage, (RSSI, ) is converted into coordinates according to formula (4) to generate Figure 8 The trajectory diagram shown in the figure is then substituted into an image classification model, such as a deep model, to obtain the corresponding state features.
[0079] Embodiment 3
[0080] Fig. 9 The embodiment of the present application is shown in Figure 1 A third specific flow chart of step S102 in FIG. Fig. 9 As shown, the state characteristics of each monitored object are obtained according to the original characteristic parameters of each monitored object, and the following specific steps are also included:
[0081] Step S401: Calculate the distance between the monitored object and the base station according to the signal strength or positioning coordinates in the original characteristic parameters.
[0082] Step S402: Obtain the activity amount of each monitored object in the preset time period according to the change amount of the distance between each monitored object and the base station in the preset time period.
[0083] Step S403: Obtain the state characteristics of each monitored body according to the activity amount of each monitored body.
[0084] In the first implementation of this embodiment, the activity of the monitored body is calculated based on the signal strength in the original characteristic parameters; this embodiment reflects the basic vital signs of the monitored body, such as activity status, amount of exercise, etc., through the relationship between the amount of exercise and the signal strength RSSI. It can be known from wireless communication theory that the relationship between RSSI and communication distance satisfies formula (5):
[0085] (5)
[0086] Where P represents the RSSI value; A is a fixed constant related to the transmit power of the beacon; k is a constant; and r represents the distance between the beacon and the base station.
[0087] From formula (5), we can deduce the relationship between distance and RSSI value as formula (6):
[0088] (6)
[0089] Therefore, for scenarios where the accuracy of activity statistics is not high, the activity can be estimated based on the relationship between distance and RSSI according to the change in distance, as shown in formula (7):
[0090] (7)
[0091] in, represents the distance between the monitoring object and the base station at the tth moment, Represents the distance between the monitoring object and the base station at the t+1th time.
[0092] In the second implementation of this embodiment, the activity of the monitored object is calculated based on the positioning coordinates in the original characteristic parameters; typically, when the receiving base station is an array antenna or there are multiple base stations monitoring the beacon device at the same time, the coordinate position of the beacon device can be obtained through the arrival angle positioning technology (AOA), triangulation positioning technology, and departure angle positioning technology (AOD). After obtaining the coordinate position of the beacon device, it can be based on Figure 5 The described grid method is used to divide the area, count the probability of falling into different areas, calculate the information entropy, and make state judgments. Since the specific coordinate position of the beacon device is obtained, the state judgment can be made directly based on the activity trajectory.
[0093] Specifically, the activity amount can be calculated directly based on the accumulated activity mileage. As shown in formula (8), the length of the straight-line movement distance of the beacon device over a period of time is calculated to represent the accumulated activity amount.
[0094] (8)
[0095] In the formula, ( , ) represents the coordinate position of the beacon at time t.
[0096] In this embodiment, the distance between the monitored object and the base station is calculated based on the signal strength or positioning coordinates in the original characteristic parameters, including: according to the sliding time window, the original characteristic parameters are corrected and denoised, and then the distance between the monitored object and the base station is calculated based on the signal strength or positioning coordinates in the original characteristic parameters.
[0097] It should be noted that the original coordinate data is affected by the positioning accuracy, and the positioning trajectory may be inaccurate. In order to ensure the accuracy of monitoring, the processing process of this embodiment is as follows: (1) Signal pickup: The radio signal data of the beacon device is picked up by the array antenna of the base station; (2) Coordinate calculation: The coordinate position of the beacon device is calculated according to the positioning algorithm (departure angle positioning algorithm, arrival angle positioning algorithm, triangulation positioning algorithm); (3) Noise reduction processing: According to a certain window, the activity trajectory is denoised, artifacts are removed, and error correction is performed, such as median filtering, Kalman filtering, etc. for noise reduction processing. At the same time, error correction and joint noise reduction can be performed in combination with the actual speed range of the beacon device; (4) Model calculation: The amount of motion is extracted and calculated from the filtered trajectory information. Typically, the activity amount can be calculated or behavior analysis can be performed according to formula (8); (5) State output: The result of the model calculation is output.
[0098] Furthermore, data processing can also be performed based on image processing methods. Fig.10 As shown in the figure, the activity trajectory forms a standard rectangle. In actual implementation, the activity trajectory within the specified time can be drawn into an image, and the state corresponding to the image can be given. The model can be trained using deep learning tools. In actual application, it is only necessary to obtain the image according to the same window and substitute it into the model for calculation to obtain the state result.
[0099] Embodiment 4
[0100] like Figure 2As shown, the base station side can extract signal features including signal strength (RSSI), phase angle, location coordinates and other signals. In this embodiment, in addition to performing state analysis separately, it is also possible to perform fusion analysis to improve the accuracy of system analysis, that is, the first information entropy can be obtained based on the signal strength and phase angle of each monitored object; the second information entropy can be obtained based on the positioning coordinates of each monitored object; the first information entropy and the second information entropy are combined with a threshold judgment to obtain the state characteristics of each monitored object.
[0101] In this embodiment, by calculating (RSSI, ) and (x, y), and make a joint threshold judgment based on the two entropies. Represents the entropy calculated by the grid method. H1L, H1H, H2L, and H2H are all set thresholds.
[0102] Table 1 Comparison table of information entropy and state
[0103]
[0104] More generally, signals such as signal strength (RSSI), phase angle, and position coordinates can be converted into feature matrices. The eigenvalues of the feature matrix can be regarded as pixels on an image and calculated based on the deep learning model. Fig.11 As shown in the figure, N represents the size of the window, that is, the number of time points of data taken as the calculation window. In the training phase, the feature matrix is labeled. After collecting enough data, a deep learning model is constructed for training, and finally a deep learning model is obtained. In the actual work process, Fig.12 As shown, the feature matrix is collected according to the same window and substituted into the deep learning model for calculation to obtain the final state value and motion amount.
[0105] Compared with the prior art, this embodiment has the following beneficial effects:
[0106] The present invention realizes the state monitoring of the monitored object by arranging a signal transmitting device which only transmits radio signals on the monitored object, and based on the signal strength change, phase angle change and coordinate position change of the radio signal transmitted by the signal transmitting device reaching the base station, thereby greatly reducing the hardware complexity of the state monitoring, and further reducing the power consumption and cost, bringing convenience to the management and promotion of the state monitoring.
[0107] In a second aspect, the present invention provides a state monitoring system, the monitoring system comprising:
[0108] A signal transmitting device for transmitting radio signals;
[0109] The base station is used to obtain original characteristic parameters based on the radio signal transmitted by the signal transmitting device, wherein the original characteristic parameters include one or any combination of signal strength, positioning coordinates or phase angle; and is also used to obtain the state characteristics of each monitored object based on the original characteristic parameters of each monitored object.
[0110] In this embodiment, the signal transmitting device includes: a wireless module, which is used to transmit radio signals; and a power module, which is connected to the wireless module and is used to provide power to the wireless module.
[0111] It should be noted that the signal transmitting device in this embodiment includes a beacon, and the basic components of the beacon include two parts: a wireless module and a power module: (1) Wireless module: responsible for transmitting radio signals, which can be ordinary radio broadcast data (not modulated and loaded with specific parameters) or a radio signal modulated and loaded with specific characteristic data; (2) Power module: a module for storing energy. When a passive design is adopted, the power module can be simplified to a capacitor, which only stores and stabilizes wireless energy; when an active sampling design is adopted, the power module can be a battery.
[0112] It should be noted that the monitoring method of the status monitoring system provided in this embodiment is the same as any of the above embodiments 1 to 4, and will not be repeated here.
[0113] In this embodiment, the application scenarios of the status monitoring system are as follows:
[0114] Application scenario 1
[0115] In the breeding field, live pledge has become a new direction in the financial field. The premise of live pledge is that the status of live assets can be effectively supervised. This embodiment proposes a status monitoring system based on a low-cost, low-power ear tag. The ear tag serves as a signal transmitting device that transmits radio signals. Only a wireless module and a power module need to be integrated inside the ear tag to achieve the management of the animal asset status. There is no need to integrate any other sensors inside the ear tag, and feature collection is completely based on radio signals. On the one hand, the system is simple, and only needs to drive the wireless module to work, and the power consumption can be controlled to an extremely low level. On the other hand, it will also bring extremely low cost, extremely small size, and extremely light weight smart ear tags to ensure feasibility.
[0116] Specifically, based on the above technical solution, it is possible to determine whether an animal is alive or how much it exercises, etc. ΔRSSI is defined as the difference between the strengths of two consecutive ear tag signals received, as shown in formula (10).
[0117] ΔRSSI(t) = RSSI(t) – RSSI(t-1)(9)
[0118] Take the actual data of smart cattle ear tags in the farm for analysis, such as Fig.13 As shown, a scatter plot of normal activity cattle with time as the horizontal axis and ΔRSSI as the vertical axis, Fig.14 is the ΔRSSI distribution of the ear tag that has fallen off. It is obvious that Fig.13 The dispersion is better than Fig.14 The reason is that the cattle ear tags are worn on cattle, and the cattle's activities (including walking, turning, etc.) will cause the equivalent wireless transmission distance between the cattle and the receiving base station to change.
[0119] The actual data of smart cattle ear tags in the farm are further analyzed. The ΔRSSI is divided into (-∞,-30), [-30,-25), [-25,-20), [-20,-15), [-15,-10), [-10,-5), [-5,-0), [0,5), [5,10), [10,15), [15,20), [20,25), [25,30), [30,+∞). The entropy is calculated according to the above formula (2) as shown in Table 2. It can be seen that the mean RSSI entropy of cattle with lost tags or no vital signs is about 1.09; the RSSI entropy of cattle with normal activities is shown in Table 3, and the mean RSSI entropy is about 2.92. The RSSI entropy values are quite different. For this farm, the threshold can be set to 2 to distinguish whether the current cattle are in normal supervision status.
[0120] Table 2 Entropy values of cattle with missing labels or no vital signs
[0121]
[0122] Table 3 Entropy values of normal cattle activities
[0123]
[0124] Application scenario 2
[0125] The state monitoring system provided in this embodiment is applied to the characteristic analysis scenario of personnel behavior, and actual data collection is performed based on smart clothing tags, such as Fig.15 As shown in the figure, a signal receiving device with a smart clothing tag is installed on the computer, and the computer is placed in the middle of the corridor. People wearing smart clothing with tags walk back and forth along the corridor, and the following is obtained: Fig.16 The signal strength change diagram shown in the figure shows that the points represent the RSSI values captured in real time, and the line represents the RSSI curve after mean smoothing. It can be seen that the smoothed curve shows obvious periodic changes, which can be used to determine the activity trajectory of people wearing smart clothing; if they do not reach the end point or do not walk according to the established trajectory, then Fig.17As shown in FIG. 1 , the signal value changes in an irregular state. In addition, the trajectory of the aforementioned personnel can also be obtained through wireless positioning technology to obtain the actual trajectory map of the personnel. Fig.18 As shown in the figure, it is a typical picture of patrol officers. The trajectory can be converted into a picture, and image recognition can be used to easily determine whether the patrol officers are performing patrol tasks according to the prescribed trajectory.
[0126] Application scenario three
[0127] The state monitoring system provided in this embodiment can be applied in the field of monitoring the operation of equipment, such as Fig.19 and Fig. 20 As shown, the beacon is placed in the device to be monitored, and the monitoring device is monitored to see whether it is in normal operation according to the change in the signal strength value received by the base station.
[0128] Therefore, the status monitoring system provided by the present invention only needs the signal transmitting device to send wireless signals to realize the status monitoring of the monitored object, which greatly reduces the complexity of the signal transmitting device and thus can realize low-cost and low-power status monitoring.
[0129] Finally, it should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0130] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.
Claims
1. A condition monitoring method, characterized in that: Applied to a state monitoring system, the state monitoring system includes a base station and a signal transmitting device arranged on a monitoring object, and the monitoring method includes: Acquire original characteristic parameters according to the radio signal transmitted by the signal transmitting device received by the base station, wherein the original characteristic parameters include one or any combination of signal strength, positioning coordinates or phase angle; According to the original characteristic parameters of each monitoring object, the state characteristics of each monitoring object are obtained, including: Perform data segmentation on all original characteristic parameters of each monitoring object within a preset time period to obtain the statistical probability of each data segment; Perform statistical analysis on the statistical probabilities of all data segments of each monitoring object to obtain statistical characteristic parameters of each monitoring object; According to the statistical characteristic parameters of each monitoring object, the state characteristics of each monitoring object are obtained, Wherein, when the original characteristic parameter is a combination of signal strength and phase angle, data segmentation is performed on all original characteristic parameters of each monitored object within a preset time period to obtain the statistical probability of each data segment, including: Establishing a second coordinate system with the base station as the origin, the signal strength as the abscissa, and the phase angle as the ordinate; Divide the second coordinate system into regions according to a grid method to obtain a plurality of region intervals; According to the regional interval to which each original characteristic parameter of each monitoring object belongs within a preset time period, the statistical probability of each regional interval is calculated.
2. The condition monitoring method according to any one of claim 1, characterized in that: Perform statistical analysis on the statistical probabilities of all data segments of each monitoring object to obtain the statistical characteristic parameters of each monitoring object, including: According to the statistical probability of all data segments of each monitoring object, the information entropy of each monitoring object is calculated; The statistical characteristic parameters of each monitored object include the information entropy of each monitored object.
3. The condition monitoring method according to claim 2, characterized in that: The information entropy formula of each monitoring object is expressed as: in, represents information entropy, represents the statistical probability of each data segment, .
4. The condition monitoring method according to claim 2, characterized in that: According to the statistical characteristic parameters of each monitored object, the state characteristics of each monitored object are obtained, and the following steps are further included: Comparing the statistical characteristic parameters of each monitored object with a threshold interval, if the statistical characteristic parameters are within the threshold interval, the state characteristic of the monitored object is a normal state; The statistical characteristic parameter is outside the threshold range, and the state characteristic of the monitored object is an abnormal state.
5. The condition monitoring method according to claim 4, characterized in that: The method further comprises: Obtaining a first information entropy according to the signal strength and phase angle of each monitored object; Obtaining the second information entropy according to the positioning coordinates of each monitored object; The first information entropy and the second information entropy are jointly thresholded to obtain the state characteristics of each monitored object.
6. The condition monitoring method according to claim 1, characterized in that: The step of obtaining the state characteristics of each monitored object according to the original characteristic parameters of each monitored object further includes: Taking the base station as the origin, the signal strength in the original characteristic parameter as the radius, and the phase angle in the original characteristic parameter as the polar angle, the original characteristic parameter within a preset time period is used to generate a motion trajectory diagram; Image recognition is performed on the motion trajectory diagram to obtain the state characteristics of each monitored object.
7. The condition monitoring method according to claim 1, characterized in that: The state characteristics of each monitored object are obtained according to the original characteristic parameters of each monitored object, including: Calculating the distance between the monitored object and the base station according to the signal strength or positioning coordinates in the original characteristic parameters; Obtaining the activity amount of each monitored object in the preset time period according to the change in the distance between each monitored object and the base station in the preset time period; According to the activity amount of each monitored body, the state characteristics of each monitored body are obtained.
8. The state monitoring method according to claim 7, characterized in that: Calculating the distance between the monitored object and the base station according to the signal strength or positioning coordinates in the original characteristic parameters includes: After error correction and noise reduction processing are performed on the original characteristic parameters according to the sliding time window, the distance between the monitored object and the base station is calculated according to the signal strength or positioning coordinates in the original characteristic parameters.
9. A condition monitoring system, characterized in that: The monitoring system comprises: A signal transmitting device for transmitting radio signals; The base station is used to obtain original characteristic parameters according to the received radio signal transmitted by the signal transmitting device, wherein the original characteristic parameters include one or any combination of signal strength, positioning coordinates or phase angle; and is also used to obtain the state characteristics of each monitored object according to the original characteristic parameters of each monitored object, including: Perform data segmentation on all original characteristic parameters of each monitoring object within a preset time period to obtain the statistical probability of each data segment; Perform statistical analysis on the statistical probabilities of all data segments of each monitoring object to obtain statistical characteristic parameters of each monitoring object; According to the statistical characteristic parameters of each monitoring object, the state characteristics of each monitoring object are obtained, Wherein, when the original characteristic parameter is a combination of signal strength and phase angle, data segmentation is performed on all original characteristic parameters of each monitored object within a preset time period to obtain the statistical probability of each data segment, including: Establishing a second coordinate system with the base station as the origin, the signal strength as the abscissa, and the phase angle as the ordinate; Divide the second coordinate system into regions according to a grid method to obtain a plurality of region intervals; According to the regional interval to which each original characteristic parameter of each monitoring object belongs within a preset time period, the statistical probability of each regional interval is calculated.
10. The condition monitoring system according to claim 9, characterized in that: The signal transmitting device comprises: A wireless module for transmitting radio signals; The power module is connected to the wireless module and is used to provide power to the wireless module.
