Evaluation system for processing technology of tagatose milk tea

Abstract

The invention relates to the field of food processing, in particular to a tagatose milk tea processing technology evaluation system. In the background technology, tagatose as a low-calorie sweetening agent has a wide application prospect, but the tagatose faces challenges on solubility, flavor matching and process stability in milk tea processing, and the prior art lacks targeted intelligent evaluation means, resulting in fluctuation of product quality and low production efficiency. In order to solve the problem, the invention provides a system which comprises a multi-parameter sensor module, a data processing and analysis module, a process optimization and feedback control module and a user interaction module. The system adopts a formula S and an anomaly detection formula D to realize real-time monitoring and dynamic optimization. According to the embodiment verification, the product quality consistency is improved by 20%, the production efficiency is improved by 30%, the method is suitable for various formulas, the problems of tagatose crystallization and other abnormalities are solved, the requirements of low-sugar healthy drinks are met, and the method has remarkable innovativeness and practicability.

Description

Technical Field

[0001] The invention relates to the technical field of food processing, in particular to a tagatose milk tea processing technology evaluation system. Background Art

[0002] As modern consumers' demand for healthy diets continues to increase, low-calorie, low-sugar food and beverages have gradually become a hot spot in the market. Tagatose, as a natural low-calorie sweetener, has a sweet taste similar to sucrose (sweetness is about 70%-80%) and only 1 / 3 of the calories of sucrose (about 1.5 kcal / g). It does not significantly increase blood sugar levels (low glycemic index GI), so it has received widespread attention in the field of healthy foods. In recent years, tagatose has been successfully used in a variety of foods, such as low-sugar biscuits, candies and beverages, showing good market prospects.

[0003] As a popular drink, traditional formulas of milk tea usually rely on high-sugar ingredients (such as sucrose or fructose syrup) to enhance sweetness and flavor, which is high in calories and difficult to meet the needs of healthy eating trends. Introducing tagatose into milk tea processing has become an innovative attempt. Its unique physical and chemical properties (such as good solubility, thermal stability and compatibility with tea polyphenols) make it possible to develop low-sugar healthy milk tea. However, the application of tagatose in milk tea faces several technical challenges:

[0004] Solubility and stability issues: Tagatose has good solubility at higher temperatures (such as 60℃-80℃), but when mixed with milk fat, tea polyphenols and other ingredients in milk tea, it may cause crystallization or stratification due to improper temperature, pH value or stirring conditions, affecting the taste and stability of the product.

[0005] Matching flavor and taste: Although the sweetness of tagatose is close to that of sucrose, its aftertaste is slightly refreshing, which may be inconsistent with the rich flavor of traditional milk tea, so the formula and process parameters need to be precisely adjusted.

[0006] Complexity of processing technology: Existing milk tea production mostly relies on manual experience to adjust the stirring rate, heating temperature and cooling rate, and lacks systematic real-time monitoring and optimization methods, resulting in large fluctuations in product quality and low production efficiency.

[0007] Technological gap: Most of the milk tea processing equipment or systems on the market are designed for traditional sugars. The intelligent evaluation and control technology for tagatose characteristics is not yet mature, and there is a lack of dynamic quality assessment models and anomaly detection mechanisms for tagatose milk tea.

[0008] In the existing technology, although some food processing systems have introduced sensors and data analysis technologies (such as temperature sensors and viscometers), these technologies are mainly used for conventional foods (such as juice and dairy products) and are not optimized for the unique physical and chemical properties of tagatose milk tea.

[0009] Therefore, the existing technology has the following deficiencies: (1) There is a lack of intelligent processing technology evaluation system for tagatose milk tea; (2) It is impossible to achieve real-time monitoring and dynamic optimization of multiple parameters, making it difficult to ensure the stability and consistency of product quality; (3) There is insufficient analysis of the characteristics of the interaction between tagatose and milk tea ingredients, resulting in low production efficiency and difficulty in abnormal handling. These problems limit the widespread application of tagatose in the field of milk tea, and an innovative solution is urgently needed to solve the above technical bottlenecks.

[0010] Based on the above background, the present invention proposes a tagatose milk tea processing technology evaluation system, which realizes online monitoring, quality prediction and process optimization by integrating multi-parameter sensors, machine learning algorithms and closed-loop feedback control, filling the gap in the existing technology and improving product quality and production efficiency.

[0011] Therefore, we urgently need to design a tagatose milk tea processing technology evaluation system to solve the above problems. Summary of the invention

[0012] The purpose of the present invention is to provide a tagatose milk tea processing technology evaluation system to address the deficiencies of the prior art and to solve the problems raised in the background technology.

[0013] To achieve the above object, the present invention provides the following technical solution: a tagatose milk tea processing technology evaluation system, comprising a multi-parameter sensor module, a data processing and analysis module, and a process optimization and feedback control module, wherein: the multi-parameter sensor module is used to collect the temperature of the tagatose milk tea processing process in real time. , pH value , Viscosity and tagatose concentration ;

[0014] The data processing and analysis module calculates the quality score based on the collected data using the quality assessment model and predict abnormal processing status through anomaly detection algorithms;

[0015] The process optimization and feedback control module adjusts the stirring rate according to the quality score S , Heating temperature and cooling rate , to optimize the flavor and stability of tagatose milk tea.

[0016] As a preferred technical solution of the present invention, the multi-parameter sensor module includes: a temperature sensor for measuring the temperature during the processing , range is 20℃ to 80℃, accuracy is ±0.1℃; pH sensor, used to measure the pH value of the mixed solution , range is 4.0 to 7.0, accuracy ±0.05; viscosity sensor, used to measure the viscosity of the mixed liquid , range 10mPa·s to 100mPa·s, accuracy ±1mPa·s; spectral sensor for analyzing tagatose concentration by near infrared spectroscopy , range is 1% to 10%, accuracy ± .

[0017] As a preferred technical solution of the present invention, the data processing and analysis module uses a quality assessment model to calculate the quality score S, and the model formula is:

[0018]

[0019] in:

[0020] are the standard reference values ​​for temperature, pH value, viscosity, and tagatose concentration, respectively;

[0021] are the maximum values ​​allowed for each parameter respectively;

[0022] is the weight coefficient, and , the initial value is 0.25.

[0023] As a preferred technical solution of the present invention, the data processing and analysis module identifies abnormal processing status through an abnormality detection algorithm, and the algorithm formula is:

[0024]

[0025] in: is the abnormal deviation value, when When it is judged as abnormal state, is the preset threshold;

[0026] is the abnormal sensitivity coefficient, with initial values ​​of 0.2, 0.2, 0.4, and 0.2, respectively, and is the parameter value collected in real time, It is the standard reference value.

[0027] As a preferred technical solution of the present invention, the process optimization and feedback control module is based on the quality score Adjust the stirring rate R, the adjustment formula is:

[0028]

[0029] in: is the initial stirring rate, ranging from 100rpm to 300rpm; is the target quality score, ranging from 80 to 100; is the adjustment coefficient, and its value range is 50 to 100 rpm / unit score; The adjustment range is limited to 100rpm to 300rpm.

[0030] As a preferred technical solution of the present invention, the process optimization and feedback control module is based on the quality score Adjust heating temperature , the adjustment formula is:

[0031]

[0032] in: is the initial heating temperature, ranging from 50°C to 70°C; is the adjustment factor, with a value range of 5°C to 10°C / unit score; Target quality score; The adjustment range is limited to 50℃ to 70℃.

[0033] As a preferred technical solution of the present invention, the process optimization and feedback control module is based on the quality score Adjusting the cooling rate , the adjustment formula is:

[0034]

[0035] in: is the initial cooling rate, ranging from 2°C / min to 8°C / min; is the adjustment coefficient, with a value range of 1°C / min to 3°C / min / unit score; Target quality score; The adjustment range is limited to 2°C / min to 8°C / min.

[0036] As a preferred technical solution of the present invention, the weight coefficient Dynamic adjustment is made through adaptive learning algorithm, and the adjustment formula is:

[0037]

[0038] in: For the The weight coefficient of the iteration, ;

[0039] is the learning rate, ranging from 0.01 to 0.1; is the partial derivative of the quality score S with respect to the weight coefficient, for example The constraints are and 1.

[0040] As a preferred technical solution of the present invention, the threshold value in the anomaly detection algorithm is Dynamically update through historical data, the update formula is:

[0041]

[0042] in: is the mean of the historical abnormal deviation values; is the standard deviation of historical abnormal deviation values; is the adjustment factor, and its value range is 1.5 to 2.5.

[0043] As a preferred technical solution of the present invention, it also includes a user interaction and visualization module, which displays real-time parameters through a touch screen. , quality score S and abnormal deviation value , and supports remote monitoring through cloud data transmission.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention realizes dynamic optimization of tagatose milk tea processing by real-time monitoring of temperature, pH value, viscosity and tagatose concentration through a multi-parameter sensor module, and calculating the quality score S in combination with a quality assessment model. Four examples show that the system improves the quality score to above 90, improves the product flavor consistency by 20%, and has a delicate and stable taste without stratification or precipitation, fully meeting the market demand for low-sugar healthy drinks.

[0046] The data processing and analysis module uses machine learning algorithms and adaptive weight adjustment, with anomaly detection response time of less than 1 second and process optimization time of less than 5 seconds, significantly improving production efficiency by 30%. The process optimization and feedback control module adjusts the stirring rate, heating temperature and cooling rate through a closed loop to ensure accurate parameter matching, reduce manual intervention by 50%, and reduce production costs.

[0047] This system supports a variety of recipes (such as black tea, oolong tea, green tea) and milk sources (such as whole milk, plant milk, low-fat milk), has strong adaptability, and fills the gap in intelligent evaluation and control technology for tagatose milk tea. Innovatively introduces anomaly detection algorithms and dynamic threshold updates (

[0048] ), effectively solve abnormal problems such as tagatose crystallization, and significantly improve the reliability and market competitiveness of the processing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a system block diagram of a tagatose milk tea processing technology evaluation system proposed by the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0051] The following is combined with Figure 1 With reference to the accompanying drawings and a number of embodiments, specific embodiments of the present invention are described in detail.

[0052] Composition and technical principle of a tagatose milk tea processing technology evaluation system:

[0053] 1. Multi-parameter sensor module:

[0054] Function: Real-time collection of temperature T, pH value P, viscosity V and tagatose concentration C during tagatose milk tea processing.

[0055] Hardware specifications and installation:

[0056] Temperature sensor: Thermistor type, measuring range 20℃-80℃, accuracy ±0.1℃, installed on the upper inner wall of the processing container (5cm from the liquid surface), directly contacting the liquid through the thermal conduction sensor.

[0057] pH sensor: glass electrode type, measuring range 4.0-7.0, accuracy ±0.05, placed in the center of the mixed liquid, equipped with automatic cleaning function to avoid residual influence.

[0058] Viscosity sensor: Rotary viscometer, measuring range 10-100mPa·s, accuracy ±1mPa·s, probe depth 10cm in the liquid, equipped with anti-clogging design.

[0059] Spectral sensor: Near-infrared spectrometer, wavelength range 800-2500nm, measures tagatose concentration C (range 1% to 10%), accuracy ±0.1%, installed in a transparent pipe, equipped with real-time calibration function.

[0060] Data collection and transmission: Data is collected once per second and transmitted to the data processing module via the RS485 interface with a delay of 10ms to ensure data real-time and synchronization.

[0061] 2. Data processing and analysis module:

[0062] Hardware: Embedded microprocessor (such as ARMCortex-M4, frequency 120MHz, memory 256KB), running real-time operating system FreeRTOS, supporting multi-task parallel processing.

[0063] Quality assessment model: Calculate the quality score S. The model formula is:

[0064]

[0065] Parameter settings:

[0066] Standard reference value: =60℃, =5.5, =50mPa·s, =5%;

[0067] Maximum value: =80℃, =7, =100mPa·s, =10%;

[0068] Initial weights: , the initial value is 0.25.

[0069] Data processing flow: First, apply a 5-second sliding window average (window size 50 samples) to the sensor data, use the simple moving average method to filter out noise, and then substitute the real-time data into the formula for calculation , the results are normalized to the range of 0-100, and the calculation time is less than 10ms.

[0070] Dynamic weight adjustment: Optimizing weights through adaptive learning , the formula is:

[0071]

[0072] (learning rate), (target quality score);

[0073] Partial derivative example: ;

[0074] constraint: .

[0075] Adjustment frequency: Iterate once per minute, calculate the gradient based on the data of the previous 5 minutes, and fix the weight after convergence (usually 3-5 iterations).

[0076] Anomaly Detection: Calculate anomaly deviation values , the formula is:

[0077]

[0078] Initial sensitivity coefficient: .

[0079] Threshold dynamic update: ,initial .

[0080] Update process: After each batch of production is completed, update based on the latest 100 sets of data and , the calculation takes less than 1 second.

[0081] like , trigger an abnormal alarm (sound and light prompt + log record) and record the abnormal type (such as abnormal viscosity).

[0082] 3. Process optimization and feedback control module:

[0083] Hardware: PLC controller (model: Siemens S7-1200, supporting PID adjustment), connected to the stirring motor, heater and cooling system via MODBUS protocol.

[0084] Adjustment formula: stirring rate

[0085] rpm, rpm / unit score, range 100-300rpm.

[0086] Heating temperature

[0087] Unit score, range 50-70 .

[0088] Cooling rate

[0089] C / min C / min / unit score, range 2-8 / min.

[0090] Execution steps:

[0091] Calculated every 2 seconds and Deviation;

[0092] Calculate the adjustment value according to the formula. If it exceeds the range (e.g. R>300 rpm), take the boundary value (e.g. R=300);

[0093] The stirring motor (frequency 50 Hz, duty cycle 0-100%), heater (power 2 kW) and cooling system (compressor power 1.5 kW) are controlled by PWM signals with an adjustment time interval of 2 seconds to ensure a smooth transition.

[0094] For example, when adjusting R, the motor acceleration or deceleration time is controlled within 0.5 seconds to avoid liquid splashing.

[0095] 4. User interaction and visualization module:

[0096] Hardware: 7-inch industrial-grade touch screen (resolution 1024×600), integrated Wi-Fi module (2.4GHz, transmission rate 54Mbps).

[0097] Function: Real-time display of parameters: T, P, V, C, S, D, refresh rate 1Hz, data presented in graphical curves (5-minute window).

[0098] Abnormal alarm: When The screen flashes red and a buzzer sounds (frequency 2kHz, lasting 2 seconds).

[0099] Remote monitoring: Upload data through the cloud server (based on MQTT protocol), support mobile phone APP viewing (updated every 10 seconds), and provide parameter history records and optimization suggestions.

[0100] The following is a specific description with reference to several embodiments:

[0101] Example 1: Processing of black tea full-fat tagatose milk tea: Target production of 500mL black tea-based tagatose milk tea, quality score .

[0102] process:

[0103] 1. Raw material preparation: 350 mL of black tea extract (concentration 2g / L, pH about 5.5), 150 mL of whole milk (30%), and 25 g of tagatose (5%).

[0104] 2. Initial processing: Add tagatose to black tea extract, place in a processing container, and set the heating temperature , stirring rate rpm, and the stirring motor runs for 5 minutes.

[0105] 3. Data collection: Sensor measurement: text mPa s o

[0106] 4. Quality assessment: Calculate the quality score S:

[0107]

[0108]

[0109]

[0110] (Note: The basic score of 85 is the calibration value for the full-fat black tea recipe, reflecting the initial flavor stability).

[0111] .

[0112] 5. Process optimization:

[0113] Calculate the adjustment parameters:

[0114] Stirring rate: rpm (limited to 300rpm).

[0115] Heating temperature: C (limited to 70°C).

[0116] Cooling rate: C / min (limited to 8°C / min).

[0117] Perform adjustments: Increase stirring rate to 300 rpm, heat to 70°C for 2 minutes and then cool to 25°C (cooling rate .

[0118] 6. Verification: Remeasure mPa·s Calculate new .

[0119] The finished product has a delicate taste, moderate sweetness, and no stratification or precipitation.

[0120] Example 2: Oolong tea plant milk tagatose milk tea processing: Target production 400mL oolong tea base tagatose milk tea, quality score .

[0121] Process: 1. Raw material preparation: 300mL of oolong tea extract (concentration 1.5g / L, pH about 5.4), 100mL of coconut milk (2596), and 28g of tagatose (7%).

[0122] 2. Initial processing: heating to C, stirring rate rpm, run for 3 minutes.

[0123] 3. Data collection: C mPa·s o

[0124] 4. Quality assessment calculation:

[0125]

[0126]

[0127]

[0128] (Note: The basic score of 70 is the calibration value for the Oolong tea plant milk formula).

[0129] .

[0130] Process optimization: small deviation, no need for adjustment, maintain rpm C °C / min;

[0131] 6. Verification: After cooling to 25°C, , refreshing flavor, stable taste, and no stratification.

[0132] Example 3: Abnormal treatment (tagatose crystallization);

[0133] Objective To deal with abnormal tagatose crystallization in the processing of 500mL black tea and milk tea.

[0134] Process: 1. Initial processing. 350mL black tea extract, 150mL whole milk, 25g tagatose, rpm.

[0135] 2. Data Collection mPa·s .

[0136] 3. Anomaly detection calculation:

[0137]

[0138] .

[0139] 4. Analysis and optimization: , triggering an alarm (the red light on the screen flashes and the buzzer sounds for 2 seconds), prompting "abnormal viscosity (tagatose crystallization)".

[0140] Calculating Quality Score (Detailed calculation omitted).

[0141] Adjustment parameters: C (limited to 70°C).

[0142] rpm (limited to 300rpm).

[0143] Execution: Heat to 70°C, increase stirring rate to 300 rpm, hold for 3 minutes, and observe viscosity changes.

[0144] 5. Verification:

[0145] Remeasure: mPa·s

[0146] calculate:

[0147] , , the anomaly is eliminated.

[0148] new At this time, the finished product is stable and tastes normal.

[0149] Example 4: Processing of green tea low-fat tagatose milk tea;

[0150] The goal is to produce 600mL of green tea-based tagatose milk tea with a quality score of .process:

[0151] 1. Raw material preparation: 450 mL of green tea extract (concentration 1.8 g / L, pH about 5.3), 150 mL of low-fat milk (25%), and 36 g of tagatose (6%).

[0152] 2. Initial processing: heating to C, stirring rate rpm, run for 4 minutes.

[0153] 3. Data collection: C mPa·s .

[0154] 4. Quality Assessment:

[0155] calculate:

[0156]

[0157]

[0158]

[0159] (Note: The basic score of 90 is the calibration value for the green tea low-fat formula).

[0160] .

[0161] 5. Process optimization: Adjustment:

[0162] rpm (limited to 300rpm).

[0163] C (limited to 70°C).

[0164] C / min (limited to 8°C / min).

[0165] Execution: Stirring rate adjusted to 300 rpm, heating to 70°C for 2 min, cooling to 25°C (rate 8°C / min).

[0166] 6. Verify the new data: mPa·s ;

[0167] (Calculation omitted), the finished product has a fresh fragrance, stable taste and no stratification.

[0168] In summary:

[0169] Four examples demonstrate the excellent performance of the tagatose milk tea processing technology evaluation system: the quality score of black tea full-fat milk tea increased from 87 to 92 by optimizing the stirring rate to 300rpm, heating to 70℃ and cooling rate to 8℃ / min, and the taste was delicate; oolong tea plant milk tea maintained 150rpm and 65℃ without adjustment, and the score was stable at 90, with a refreshing flavor; abnormal processing successfully eliminated tagatose crystallization, and the viscosity dropped from 75mPa·s to 55mPa·s, with a quality score of 91; the score of green tea low-fat milk tea increased from 82 to 91 after optimization, and the finished product was fragrant and stable. The system achieved a 20% improvement in quality consistency and a 30% increase in production efficiency, adapted to a variety of recipes, met low-sugar health needs, and the abnormal response time was less than 1 second.

[0170] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A tagatose milk tea processing technology evaluation system, characterized in that: It includes a multi-parameter sensor module, a data processing and analysis module, and a process optimization and feedback control module, wherein: the multi-parameter sensor module is used to collect the temperature in real time during the tagatose milk tea processing process , pH value , Viscosity and tagatose concentration ; The data processing and analysis module calculates the quality score based on the collected data using the quality assessment model and predict abnormal processing status through anomaly detection algorithms; The process optimization and feedback control module adjusts the stirring rate according to the quality score S , Heating temperature and cooling rate , to optimize the flavor and stability of tagatose milk tea.

2. A tagatose milk tea processing technology evaluation system according to claim 1, characterized in that: The multi-parameter sensor module includes: a temperature sensor for measuring the temperature during the processing , range is 20℃ to 80℃, accuracy is ±0.1℃; pH sensor, used to measure the pH value of the mixed solution , range is 4.0 to 7.0, accuracy ±0.05; viscosity sensor, used to measure the viscosity of the mixed liquid , range 10mPa·s to 100mPa·s, accuracy ±1mPa·s; spectral sensor for analyzing tagatose concentration by near infrared spectroscopy , range is 1% to 10%, accuracy ± .

3. A tagatose milk tea processing technology evaluation system according to claim 1, characterized in that: The data processing and analysis module uses a quality assessment model to calculate the quality score S, and the model formula is: ， in: are the standard reference values ​​for temperature, pH value, viscosity, and tagatose concentration, respectively; are the maximum values ​​allowed for each parameter respectively; is the weight coefficient, and , the initial value is 0.

25.

4. A tagatose milk tea processing technology evaluation system according to claim 1, characterized in that: The data processing and analysis module identifies abnormal processing status through an abnormality detection algorithm, and the algorithm formula is: ， in: is the abnormal deviation value, when When it is judged as abnormal state, is the preset threshold; is the abnormal sensitivity coefficient, with initial values ​​of 0.2, 0.2, 0.4, and 0.2, respectively, and is the parameter value collected in real time, It is the standard reference value.

5. A tagatose milk tea processing technology evaluation system according to claim 1, characterized in that: The process optimization and feedback control module is based on the quality score Adjust the stirring rate R, the adjustment formula is: ， in: is the initial stirring rate, ranging from 100rpm to 300rpm; is the target quality score, ranging from 80 to 100; is the adjustment coefficient, and its value range is 50 to 100 rpm / unit score; The adjustment range is limited to 100rpm to 300rpm.

6. A tagatose milk tea processing technology evaluation system according to claim 1, characterized in that: The process optimization and feedback control module is based on the quality score Adjust heating temperature , the adjustment formula is: ， in: is the initial heating temperature, ranging from 50°C to 70°C; is the adjustment factor, with a value range of 5°C to 10°C / unit score; Target quality score; The adjustment range is limited to 50℃ to 70℃.

7. The tagatose milk tea processing technology evaluation system according to claim 1, characterized in that: The process optimization and feedback control module is based on the quality score Adjusting the cooling rate , the adjustment formula is: ， in: is the initial cooling rate, ranging from 2°C / min to 8°C / min; is the adjustment coefficient, with a value range of 1°C / min to 3°C / min / unit score; Target quality score; The adjustment range is limited to 2°C / min to 8°C / min.

8. The tagatose milk tea processing technology evaluation system according to claim 3, characterized in that: The weight coefficient Dynamic adjustment is made through adaptive learning algorithm, and the adjustment formula is: ， in: For the The weight coefficient of the iteration, ; is the learning rate, ranging from 0.01 to 0.1; is the partial derivative of the quality score S with respect to the weight coefficient, for example The constraints are and 1.

9. A tagatose milk tea processing technology evaluation system according to claim 4, characterized in that: Thresholds in the anomaly detection algorithm Dynamically update through historical data, the update formula is: ， in: is the mean of the historical abnormal deviation values; is the standard deviation of historical abnormal deviation values; is the adjustment factor, and its value range is 1.5 to 2.

5.

10. The tagatose milk tea processing technology evaluation system according to claim 1, characterized in that: It also includes a user interaction and visualization module, which displays real-time parameters through a touch screen. , quality score S and abnormal deviation value , and supports remote monitoring through cloud data transmission.

Images