Food processing detection equipment and detection method thereof

Abstract

A food processing detection apparatus and a detection method thereof, the detection apparatus comprising: a detection device (1) for transmitting a sound wave signal to a food to be detected, and receiving energy information corresponding to at least one reflected sound wave signal after the sound wave signal penetrates the food to be detected; the operation processing module (2) is in signal connection with the detection device (1) and is used for operating the energy information and generating a detection result; and the conduction structure (3) is arranged on the surface of one side of the food to be detected, and the conduction structure (3) is arranged between the food to be detected and the detection device (1) and is used for transmitting the sound wave signal and at least one reflection sound wave signal. According to the detection method, the actual ripening situation of the to-be-detected food is obtained, and the stability of the ripening quality is improved.

Description

Food processing testing equipment and testing methods Technical Field

[0001] The present invention belongs to the field of detection, and in particular relates to food processing detection equipment and a detection method thereof. Background Art

[0002] Food aging is a food processing process, mostly used for meat or dairy products. Its aging methods can be roughly divided into dry aging, wet aging and lactic acid fermentation. Among them, dry aging is a aging method for meat, especially beef. Its production method is usually to place the meat in a low temperature and set humidity environment (60-80 degrees, or slightly changed in different process processes) for several weeks to several months, using the enzymes of the meat itself to mature (some processes claim to be related to microorganisms, but there are also contrary arguments). During this process, the surface of the meat will The physical mechanical force generated by the formation of a hard cortex will release other beef enzymes, making it easier to decompose the internal tissue protein. After the enzyme hydrolysis, the meat protein is degraded into peptides and amino acids, causing the perimysium to be damaged. It will not shrink due to heating, making the meat more tender and smooth during cooking, and its flavor will be more intense due to the increase in amino acids. Wet aging is another method of meat aging. The meat pieces are packaged in vacuum-sealed bags and usually stored at low temperatures for several days to weeks. The natural enzymes of the meat pieces themselves are used for aging to achieve a tender and juicy effect.

[0003] The difference between dry-aging and wet-aging is that the fat on the outer layer and skin of dry-aged beef will dry out due to water evaporation, which helps to lock in the internal moisture and maintain the texture of fresh meat. The fat will be relatively more concentrated, making it more delicious. However, due to the high loss rate of dry-aged meat, after dry-aging, the surface of the meat becomes hard due to drying and cannot be eaten. The hardened surface part needs to be removed, so the culinary part is often less than 70% of the original. In addition, the process relies heavily on the subjective experience and judgment of professionals, and its production cost is also considerable.

[0004] In the past, during the dry-aging process, the thickness and quality of each piece of meat varied, and therefore the aging time would also vary. Determining whether dry-aging had reached the ideal state required individual assessment by professionals, using factors such as appearance, texture, and smell. Traditional sampling methods involved professionals inserting bamboo sticks into the sampling location and then assessing the meat based on its color, smell, and texture. This assessment required a high level of experience from the professionals, and because the assessment was subjective, different professionals might have different opinions on the quality of aging, making it impossible to effectively control the quality of the resulting meat. Furthermore, traditional sampling methods could also result in a certain degree of meat loss, and could even lead to aging failure. These factors indirectly resulted in high investment costs.

[0005] To this end, the present invention provides a food processing detection device and a detection method thereof, which can quantify the degree of maturity specifically, understand the degree of maturity and status more objectively, and more accurately control the maturity quality, greatly reduce the loss level, and save production costs.

[0006] Summary of the Invention

[0007] The main purpose of the present invention is to provide a food processing detection device, which uses a detection device to obtain the internal structure of the food to be tested, and further obtains the actual ripening detection results based on the calculation processing module, so that the ripening quality can be effectively controlled.

[0008] Another object of the present invention is to provide a food processing detection method that uses acoustic signals to penetrate the food to be detected and calculates the detection results based on the energy distribution of the reflected acoustic signals to improve detection accuracy and effectively enhance the success rate of cooking and its quality.

[0009] To achieve the aforementioned objectives, one embodiment of the present invention discloses a food processing inspection device, characterized by comprising: a detection device for emitting an acoustic wave signal to a food to be inspected, and receiving energy information corresponding to at least one reflected acoustic wave signal after the acoustic wave signal penetrates the food to be inspected; a processing module signal-connected to the detection device for calculating the energy information and generating a detection result; and a conductive structure disposed on a side surface of the food to be inspected, wherein the conductive structure is disposed between the food to be inspected and the detection device for transmitting the acoustic wave signal and the at least one reflected acoustic wave signal.

[0010] Preferably, the detection device is selected from an ultrasonic imager.

[0011] Preferably, the conductive structure includes an insulating layer and a gel layer, the insulating layer is made of a material selected from polyethylene (PE), polyvinyl chloride (PVC), polyvinylidene chloride (PCDC), polymethylpentene (PMP) or a combination thereof, and the gel layer is made of a material selected from water, glycerin, gelatin or a combination thereof.

[0012] Preferably, the conductive structure comprises a liquid layer, the liquid layer is disposed between the insulating layer and the gel layer, and the liquid layer is selected from water.

[0013] Preferably, it includes an adjustment device, which is arranged on the other side surface of the food to be tested, for adjusting the energy information of the at least one reflected sound wave signal, and the adjustment device is selected from a curved metal part or a material that can reflect sound waves, a convex lens, a concave lens, a biconcave lens, a biconvex lens, an array lens, a spherical lens, a Fresnel lens or a combination of the above.

[0014] Preferably, the food to be tested is selected from cooked meat, seafood, cheese or a combination thereof.

[0015] To achieve the aforementioned other objective, one embodiment of the present invention discloses a food processing detection method, characterized in that the steps include: transmitting an acoustic wave signal to a food to be detected using a detection device; after the acoustic wave signal penetrates the food to be detected, reflecting energy information of at least one reflected acoustic wave signal by the internal tissue of the food to be detected; and calculating the energy information distribution to generate a detection result.

[0016] Preferably, in the step of calculating the energy information distribution to generate a detection result, the energy information is converted into a grayscale image, and calculation is performed based on a plurality of grayscale values ​​of the grayscale image to generate the detection result, wherein the detection result includes a degree of maturity.

[0017] Preferably, in the step of calculating the energy information distribution to generate a detection result, an artificial intelligence is used to process the energy information, the detection result and information of the food to be detected to generate predicted maturity information.

[0018] Preferably, the predicted ripening information includes a ripening temperature value, a humidity value, a ripening time, an air flow rate, or a combination thereof.

[0019] The beneficial effect of the present invention is that it can quickly and accurately detect the actual ripening situation. Furthermore, artificial intelligence can be used to collect the above data to better predict the optimal ripening environment and time, greatly improving the stability of ripening quality and reducing production costs and losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1A is a schematic diagram of an apparatus according to an embodiment of the present invention;

[0021] FIG1B is a schematic diagram of a conductive structure according to an embodiment of the present invention;

[0022] FIG2A is a schematic diagram of an apparatus implementation according to an embodiment of the present invention;

[0023] FIG2B shows the detection image results of different adjustment device types according to an embodiment of the present invention;

[0024] FIG3 is a flow chart of a method according to an embodiment of the present invention;

[0025] FIG4A is an example image of a calculation according to an embodiment of the present invention;

[0026] FIG4B is an example image of a calculation according to an embodiment of the present invention;

[0027] FIG5A is an image of shell and flesh according to an embodiment of the present invention;

[0028] FIG5B is a blurred image of muscle tissue according to an embodiment of the present invention;

[0029] FIG6A is an example image of a detection according to an embodiment of the present invention;

[0030] FIG6B is an example image of a detection according to an embodiment of the present invention;

[0031] FIG6C is an example image of a detection according to an embodiment of the present invention;

[0032] FIG7A is an actual detection image according to an embodiment of the present invention;

[0033] FIG7B is an actual detection image according to an embodiment of the present invention;

[0034] FIG7C is an actual detection image of an embodiment of the present invention;

[0035] FIG7D is an actual detection image of an embodiment of the present invention; and

[0036] FIG8 is a diagram of analysis data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] To make the above and / or other purposes, effects, and features of the present invention more clearly understood, preferred embodiments are described in detail below:

[0038] Please refer to Figures 1A, 1B, and 2A, which illustrate the equipment, conductive structure, and implementation diagrams of one embodiment of the present invention. As shown, food processing detection equipment E according to one embodiment of the present invention comprises: a detection device 1, a processing module 2, a conductive structure 3, and a regulating device 4. The detection device 1 is signal-connected to the processing module 2, and its operation is described in detail as follows:

[0039] The detection device 1 is used to transmit an acoustic wave signal to the food to be detected F. After the acoustic wave signal penetrates the food to be detected F, when it contacts the tissue interface of different densities inside the food to be detected F, part of the acoustic wave signal will be reflected back. In this way, the detection device 1 will receive energy information of at least one reflected acoustic wave signal. In one embodiment, the detection device is selected from an ultrasonic imager, and the acoustic wave signal can be an ultra-high frequency sound wave, whose frequency is mostly between 1 MHz and 15 MHz, but not limited thereto.

[0040] In one embodiment, the food F to be tested may be aged meat, seafood, cheese, or a combination thereof. Preferably, it may be dry-aged beef, overnight dried meat, cheese, ham, etc., but is not limited thereto.

[0041] The processing module 2 is used to calculate the energy information obtained by the detection device 1 to generate a detection result. This detection result can be the degree of cookedness at different locations on the food F to be detected. In other words, the detection result can present the cookedness distribution of each part of the food F to be detected.

[0042] The conductive structure 3 is disposed on a side surface of the food to be tested and is located between the food to be tested F and the detection device 1. The conductive structure 3 is used to transmit and reflect acoustic wave signals. In one embodiment, as shown in FIG. 1B, the conductive structure 3 includes an insulating layer 31 and a gel layer 32. The insulating layer 31 is made of a material selected from polyethylene (PE), polyvinyl chloride (PVC), polyvinylidene chloride (PCDC), polymethylpentene (PMP), or a combination thereof. The gel layer 32 is made of a material selected from water, glycerin, gelatin, or a combination thereof. The number of gel layers 32 is not limited.

[0043] Preferably, in one embodiment, the conductive structure 3 may further include a liquid layer 33 . The liquid layer 33 is disposed between the insulating layer 31 and the gel layer 32 . The liquid layer 33 is selected from water, but is not limited thereto.

[0044] In one embodiment, to avoid loss or noise interference during the transmission of the acoustic wave signal, the present invention further provides an adjustment device 4, which is provided on the other side surface of the food F to be tested. Specifically, the position of the food F to be tested is located between the adjustment device 4 and the conductive structure 3. It is used to adjust the energy information of the reflected acoustic wave signal. The energy information includes the intensity of the energy and the depth of its reflection position, which is determined by the energy size and reflection time of the reflected acoustic wave signal. The transmission conditions for tissues of different densities will also be different. According to needs, the adjustment device 4 can be used to further adjust the energy information to reflect a reflected acoustic wave signal with higher energy or reduce the energy of the reflected acoustic wave signal to calculate a more accurate detection result.

[0045] In one embodiment, the adjustment device 4 can be selected from a curved metal part or a material that can reflect sound waves, a convex lens, a concave lens, a biconcave lens, a biconvex lens, an array lens, a spherical lens, a Fresnel lens, or a combination thereof, wherein the material of the metal part can be iron, copper, titanium, stainless steel, aluminum alloy, or a combination thereof, as long as it can be used to adjust the energy of the sound waves.

[0046] Please refer to Figure 2B, which shows the image results of different adjustment device types tested according to an embodiment of the present invention. As shown in the figure, the adjustment device materials (from left to right) are iron, paper, and foam, respectively. The acoustic signal frequency used was 7.1 MHz, the scanning depth was 7.1 cm, and the contrast enhancement was 60. The measured data is shown in the following table:

[0047] Table 1 Test data of different types of regulating devices

[0048] It can be clearly seen from the aforementioned Table 1 and Figure 2B that different materials of the adjustment device 4 present different acoustic wave energies. The metal material performs better than other materials. Therefore, the appropriate adjustment device 4 can be selected according to the calculation requirements to effectively increase the detection accuracy.

[0049] Please refer to the third figure, which is a flow chart of a method according to an embodiment of the present invention. As shown in the figure, the food processing detection method according to an embodiment of the present invention comprises the following steps:

[0050] Step S1: Using a detection device to transmit an acoustic wave signal to a food to be detected;

[0051] Step S2: After the acoustic wave signal penetrates the food to be tested, energy information of at least one reflected acoustic wave signal is reflected by the internal tissue of the food to be tested; and

[0052] Step S3: Calculate the energy information distribution to generate a detection result.

[0053] As shown in step S1, the detection device 1 transmits an acoustic wave signal to one side surface of the food F to be detected, wherein the food F to be detected is cooked meat, seafood, cheese or a combination thereof, and the frequency of the acoustic wave signal is mostly between 1MHz and 15MHz.

[0054] As shown in step S2, after the acoustic signal penetrates the food F to be tested, the energy information of at least one reflected acoustic signal is reflected according to the different densities of the internal tissue of the food F to be tested. This energy information can be presented as an image with a gray-white contrasting tone, wherein the intensity of the gray-white image is determined by the energy of the reflected acoustic signal. The greater the reflected energy, the brighter the image point on the image. Conversely, the smaller the reflected energy, the darker the image point on the image. The depth of the image point on the image is determined by the time it takes for the acoustic signal to be emitted and reflected. For example, tissue with a higher water content has a higher conductivity for ultrasound, and the reflected acoustic signal is less, resulting in a black anechoic image on the image. Conversely, tissue with a lower water content reflects more acoustic signals, and will appear as a grayish low-echo or equal-echo image on the image.

[0055] As shown in step S3, calculation is performed based on the energy information obtained in the previous step to generate a detection result. This detection result can be a classification based on the degree of maturity, but is not limited to this.

[0056] In one embodiment, the calculation method can be to convert the energy information into a grayscale image and perform calculations based on multiple grayscale values ​​of the grayscale image. Preferably, the calculation can be performed based on the average value of the grayscale values ​​of the specific selected area to generate the final detection result.

[0057] Please refer to Figures 4A-4B, which illustrate example computational images according to an embodiment of the present invention. As shown, computation can be performed initially on the circled area in the upper left corner to determine whether the device is properly contacting the food being tested. Once correct contact is confirmed, computation and identification can then be performed on the circled area in the lower right corner. For example, the grayscale image has a value range of 0-255, and the average grayscale value of the circled area is calculated. Alternatively, the grayscale values ​​of multiple areas can be averaged, and different default grayscale values ​​can be compared based on the properties of the food being tested to determine the degree of doneness.

[0058] In one embodiment, taking the test results of aged beef as an example, as shown in Figure 4B, the beef was tested each week during the aging process, for a total of four tests. The upper box represents the circled area after correct contact was determined, and the average grayscale value of the area was calculated. The calculated data is shown in the following table:

[0059] Table 2 Calculation data of the circled area

[0060] As shown in Table 2, it can be clearly seen that the average grayscale values ​​of the circled areas are significantly different at different ripening stages, which can be used as a method for judging the degree of ripening, but is not limited thereto.

[0061] In one embodiment, artificial intelligence can be used to process energy information, test results, and information about the food to be tested to generate predicted ripening information. Since the quality of each food F to be tested is different, the ripening temperature, humidity, ripening time, and air flow rate will be adjusted according to the different food F to be tested. Therefore, artificial intelligence can be used to further find the optimal ripening information for each food F to be tested. Preferably, the information about the food to be tested can be related information such as meat part, fat content level, and the aging room or aging bag used. Classification training is performed using the above information to obtain a more accurate judgment model.

[0062] To more clearly illustrate the embodiments of the present invention, examples are given below:

[0063] Taking the dry-aged beef process as an example, since cells are degraded into amino acids during the aging process, the food processing detection equipment of the present invention can be used to detect the aging status of each stage. Based on the aging status, the most appropriate aging temperature, humidity, time, and air flow rate can be estimated to accurately control the aging quality.

[0064] Taking US Choice tenderloin as an example, the weight is 3,050g and the aging time is 47 days. The weight is measured every week during the dry-aging process. The weight data from week 1 to week 8 are shown in Table 3.

[0065] Table 3 Weight data of US Choice grade tenderloin

[0066] Please refer to Figures 5A to 5B, which are images of shell meat and blurred images of muscle tissue according to an embodiment of the present invention. This embodiment uses an ultrasonic imager as a detection device. During the dry-aging process, the outermost layer will gradually dry out to produce shell meat (as shown in the box in the figure). The shell meat will reduce the microbial contamination of the internal beef and prevent the internal drying and dehydration to maintain a certain humidity for enzyme hydrolysis reaction and aging. When the internal enzymes continue to hydrolyze the muscle tissue, the disintegrated muscle bundles, sarcolemma and proteins continue to degrade into amino acids and peptides to produce a rich aroma, and the process of these reactions will cause the muscle tissue image to continue to blur (as shown in the box in the figure). In this way, the stage of aging can be estimated through the results detected at different times.

[0067] Each inspection captures an image of the energy distribution and performs computational processing in two stages. The first stage identifies the degree of blur in the energy distribution image. See Figures 6A through 6C for example inspection images according to one embodiment of the present invention. As shown, the boxed area in Figure 6A indicates where the device improperly contacts the beef, the boxed area in Figure 6B indicates where the device partially improperly contacts the beef, and Figure 6C indicates where the device completely and correctly contacts the beef. After removing the images of the images identified in Figures 6A and / or 6B, the second stage of AI recognition is performed, which estimates the degree of doneness based on shell thickness and underlying tissue type.

[0068] Implementation process: First, the cleaned beef is wiped dry and placed in an aging bag, sealed with a sealed clamp, and tested three times a week. In this embodiment, the degree of maturity is divided into four levels: Level 1: less than 30%; Level 2: greater than 30% and less than 60%; Level 3: greater than 60% and less than 90%; and Level 4: greater than 90%. The degree of maturity can be set according to needs and is not limited to this.

[0069] Please refer to Figures 7A to 7D, which are actual inspection images of an embodiment of the present invention. As shown, Figure 7A represents the first level of maturity; Figure 7B represents the second level of maturity; Figure 7C represents the third level of maturity; and Figure 7D represents the fourth level of maturity. Furthermore, the results of artificial intelligence classification and recognition training are shown in Tables 4-1, 4-2, and 4-3:

[0070] Table 4-1 Training results with two groups as classification and recognition targets

[0071] Table 4-2 Training results with three groups as classification and recognition targets

[0072] Table 4-3 Training results with five groups as classification and identification targets

[0073] Please also refer to Figure 8, which illustrates the analysis data from one embodiment of the present invention. As shown, the confusion matrix analysis data for this embodiment's artificial intelligence model serves as a classification performance evaluation indicator, with G1 representing the first-level classification; G2 representing the second-level classification; G3 representing the third-level classification; G4 representing the fourth-level classification; and G5 representing the classification of improperly contacted devices. The data in the chart clearly demonstrates that the classification and recognition results of this embodiment perform well, achieving the objectives of the present invention.

[0074] In summary, the present invention provides a food processing inspection device and a method thereof, wherein a detection device further obtains the internal structure of the food to be inspected through the transmission of acoustic signals, and calculates the energy information to obtain the actual ripening detection result, so that the ripening quality can be effectively controlled, thereby achieving the purpose of the present invention.

[0075] The above is only a preferred embodiment of the present invention. It should be pointed out that ordinary technicians in this technical field can make several improvements and modifications without departing from the concept of the present invention. These improvements and modifications should also be considered within the scope of the present invention.

Claims

1. A food processing detection device, characterized in that: Include: A detection device transmits a sound wave signal to a food to be detected, and receives energy information of at least one corresponding reflected sound wave signal after the sound wave signal penetrates the food to be detected; a calculation processing module, connected to the detection device signal, for calculating the energy information and generating a detection result; and A conductive structure is disposed on a side surface of the food to be detected, and the conductive structure is disposed between the food to be detected and the detection device to transmit the sound wave signal and the at least one reflected sound wave signal.

2. The food processing detection equipment according to claim 1, characterized in that: The detection device is selected from an ultrasonic imager.

3. The food processing detection equipment according to claim 1, characterized in that: The conductive structure includes an insulating layer and a gel layer, the insulating layer is made of a material selected from polyethylene (PE), polyvinyl chloride (PVC), polyvinylidene chloride (PCDC), polymethylpentene (PMP) or a combination thereof, and the gel layer is made of a material selected from water, glycerin, gelatin or a combination thereof.

4. The food processing detection equipment according to claim 3, characterized in that: The conductive structure includes a liquid layer, the liquid layer is disposed between the insulating layer and the gel layer, and the liquid layer is selected from water.

5. The food processing detection equipment according to claim 1 comprises an adjustment device, which is arranged on the other side surface of the food to be detected, for adjusting the energy information of the at least one reflected sound wave signal, and the adjustment device is selected from a curved metal part or a material that can reflect sound waves, a convex lens, a concave lens, a biconcave lens, a biconvex lens, an array lens, a spherical lens, a Fresnel lens or a combination of the above.

6. The food processing detection equipment according to claim 1, characterized in that: The food to be tested is selected from cooked meat, seafood, cheese or a combination thereof.

7. A food processing detection method, comprising the steps of: A detection device transmits an acoustic wave signal to a food to be detected; When the sound wave signal penetrates the food to be tested, at least one energy information of the reflected sound wave signal is reflected by the internal tissue of the food to be tested; and The energy information distribution is calculated to generate a detection result.

8. The food processing detection method according to claim 7, characterized in that: In the step of calculating the energy information distribution to generate a detection result, the energy information is converted into a grayscale image, and calculation is performed according to a plurality of grayscale values ​​of the grayscale image to generate the detection result, wherein the detection result includes a maturity level.

9. The food processing detection method according to claim 7, characterized in that: In the step of calculating the energy information distribution to generate a detection result, an artificial intelligence is used to process the energy information, the detection result and information of the food to be detected to generate predicted maturity information.

10. The food processing detection method according to claim 7, characterized in that: The predicted ripening information includes a temperature value, a humidity value, a ripening time, an air flow rate, or a combination thereof.

Images